diff options
151 files changed, 7897 insertions, 2153 deletions
diff --git a/docs/dev/background_jobs.md b/docs/dev/background_jobs.md new file mode 100644 index 0000000..1a41636 --- /dev/null +++ b/docs/dev/background_jobs.md @@ -0,0 +1,62 @@ +# Background Jobs + +We run background jobs for long-running processes, e.g. quality-assurance checks +across multiple huge files, inserting huge data to databases, etc. The system +needs to keep track of the progress of these jobs and communicate the state to +the user whenever the user requests. + +This details some thoughts on how to handle these jobs, especially in failure +conditions. + +We currently use Redis[^redis] to keep track of the state of the background +processes. + +Every background job started will have a Redis[^redis] key with the prefix `gn-uploader:jobs` + +## Users + +Currently (2024-10-23T13:29UTC-05:00), we do not track the user that started the job. Moving forward, we will track this information. + +We could have the keys be something like, `gn-uploader:jobs:<user-id>:<job-id>`. + +Another option is track any particular users jobs with a key of the form +`gn-uploader:users:<user-id>:jobs` and in that case, have the job keys take the +form `gn-uploader:jobs:<job-id>`. I (@fredmanglis) favour this option over +having the user's ID in the jobs keys directly, since it provides a way to +interact with **ALL** the jobs without indirecting through each specific user. +This is a useful ability to have, especially for system administrative tasks. + +## Multiprocessing Within Jobs + +Some jobs, e.g. quality-assurance jobs, can run multiple threads/processes +themselves. This brings up a problem because Redis[^redis] does not allow +parallel access to a key, especially for writing. + +We also do not want to create bottlenecks by writing to the same key from +multiple threads/processes. + +The design I have currently come up with, that might work is as follows: + +- At any point just before where multiple threads/processes are started, a list + of new keys, each of which will collect the output from a single thread, will + be built. +- These keys are recorded in the parent's redis key data +- The threads/processes are started and do whatever they need, pushing their + outputs to the appropriate keys within redis. + +The new keys for the children threads/processe could build on the theme + + +## Fetching Jobs Status + +Different jobs could have different ways of requirements for handling/processing +their outputs, and those of any children they might spawn. The system will need +to provide a way to pass in the correct function/code to process the outputs at +the point where the job status is requested. + +This implies that we need to track the type of job in order to be able to select +the correct code for processing such output. + +## Links + +- [^redis]: https://redis.io/ diff --git a/docs/dev/quality_assurance_on_csv_files.md b/docs/dev/quality_assurance_on_csv_files.md new file mode 100644 index 0000000..02d63c9 --- /dev/null +++ b/docs/dev/quality_assurance_on_csv_files.md @@ -0,0 +1,52 @@ +# Quality Assurance/Control on CSV Files + +## Abbreviations + +- CSV files: Character-separated-values files — these are data files structured in a table-like format, with a specific character chosen as the column/field separator. The comma (,) is the most common field separator used by most csv files. It is, however, possible to encounter files with other characters separating the values. + +## General Pattern + +A general pattern has emerged when performing quality assurance on the data in +CSV files — the pseudocode below shows the general pattern: + +```python +def qc_function(filepath, …): + open(filepath, …) + + headers = read_first_line(…) + perform_qc_on_headings(headers, …) + + for each subsequent line in file: + perform_qc_on_first_column(line, …) + + for each subsequent field in line: + perform_qc_on_field(field, …) +``` + +We want to list the errors found in each file, so it makes sense for the `perform_qc_on*` functions in the pseudocode above to return the list of errors found for each file. + +The actual quality assurance done on the headers, first column of data rows, and the fields can differ from one type of file to the next, but the structure remains relatively unchanged. + +This implies we could make use of a higher-order function that contains the general structure with the actual qc steps passed in as functions that are called in the higher-order structuring function. This gives something like: + +```python +def qc_function(filepath, headers_qc, first_column_qc, data_qc, …): + for line in file: + if line is a comment line: + skip line and continue iteration + if line is first non-comment line: + line is the header line + call headers_qc on fields in this line + if line is not first non-comment line: + line is data line + call first_column_qc on first field of line + call data_qc on each of the subsequent fields of the line + + collect and return errors +``` + +## Improvements + +- Read the file in a separate generator function +- Parallelize QC if many files are present +- Add logging/output for user update (how do we do this correctly?) diff --git a/r_qtl/r_qtl2.py b/r_qtl/r_qtl2.py index 9da4081..c6307f5 100644 --- a/r_qtl/r_qtl2.py +++ b/r_qtl/r_qtl2.py @@ -18,6 +18,10 @@ FILE_TYPES = ( "geno", "founder_geno", "pheno", "covar", "phenocovar", "gmap", "pmap", "phenose") +__CONTROL_FILE_ERROR_MESSAGE__ = ( + "The zipped bundle that was provided does not contain a valid control file " + "in either JSON or YAML format.") + def __special_file__(filename): """ @@ -72,6 +76,8 @@ def transpose_csv( def __read_by_line__(_path): with open(_path, "r", encoding="utf8") as infile: for line in infile: + if line.startswith("#"): + continue yield line transposed_data= (f"{linejoinerfn(items)}\n" for items in zip(*( @@ -112,7 +118,7 @@ def __control_data_from_zipfile__(zfile: ZipFile) -> dict: or filename.endswith(".json")))) num_files = len(files) if num_files == 0: - raise InvalidFormat("Expected a json or yaml control file.") + raise InvalidFormat(__CONTROL_FILE_ERROR_MESSAGE__) if num_files > 1: raise InvalidFormat("Found more than one possible control file.") @@ -129,7 +135,6 @@ def __control_data_from_zipfile__(zfile: ZipFile) -> dict: else yaml.safe_load(zfile.read(files[0]))) } - def __control_data_from_dirpath__(dirpath: Path): """Load control data from a given directory path.""" files = tuple(path for path in dirpath.iterdir() @@ -137,7 +142,7 @@ def __control_data_from_dirpath__(dirpath: Path): and (path.suffix in (".yaml", ".json")))) num_files = len(files) if num_files == 0: - raise InvalidFormat("Expected a json or yaml control file.") + raise InvalidFormat(__CONTROL_FILE_ERROR_MESSAGE__) if num_files > 1: raise InvalidFormat("Found more than one possible control file.") @@ -200,8 +205,8 @@ def control_data(control_src: Union[Path, ZipFile]) -> dict: if control_src.is_dir(): return __cleanup__(__control_data_from_dirpath__(control_src)) raise InvalidFormat( - "Expects either a zipfile.ZipFile object or a pathlib.Path object " - "pointing to a directory containing the R/qtl2 bundle.") + "Expects either a zipped bundle of files or a path-like object " + "pointing to the zipped R/qtl2 bundle.") def replace_na_strings(cdata, val): @@ -549,3 +554,21 @@ def load_samples(zipfilepath: Union[str, Path], pass return tuple(samples) + + + +def read_text_file(filepath: Union[str, Path]) -> Iterator[str]: + """Read the raw text from a text file.""" + with open(filepath, "r", encoding="utf8") as _file: + for line in _file: + yield line + + +def read_csv_file(filepath: Union[str, Path], + separator: str = ",", + comment_char: str = "#") -> Iterator[tuple[str, ...]]: + """Read a file as a csv file.""" + for line in read_text_file(filepath): + if line.startswith(comment_char): + continue + yield tuple(field.strip() for field in line.split(separator)) diff --git a/r_qtl/r_qtl2_qc.py b/r_qtl/r_qtl2_qc.py index 6f7b374..2d9e9a8 100644 --- a/r_qtl/r_qtl2_qc.py +++ b/r_qtl/r_qtl2_qc.py @@ -8,6 +8,7 @@ from r_qtl import r_qtl2 as rqtl2 from r_qtl import exceptions as rqe from r_qtl.r_qtl2 import FILE_TYPES from r_qtl.fileerrors import MissingFile +from r_qtl.exceptions import InvalidFormat from quality_control.errors import InvalidValue from quality_control.checks import decimal_points_error @@ -86,7 +87,7 @@ def missing_files(bundlesrc: Union[Path, ZipFile]) -> tuple[tuple[str, str], ... return __missing_from_zipfile__(bundlesrc, cdata) if isinstance(bundlesrc, Path): if is_zipfile(bundlesrc): - return __missing_from_zipfile__(ZipFile(bundlesrc, cdata)) + return __missing_from_zipfile__(ZipFile(bundlesrc), cdata) if bundlesrc.is_dir(): return __missing_from_dirpath__(bundlesrc, cdata) raise InvalidFormat( @@ -94,7 +95,7 @@ def missing_files(bundlesrc: Union[Path, ZipFile]) -> tuple[tuple[str, str], ... "pointing to a directory containing the R/qtl2 bundle.") -def validate_bundle(zfile: ZipFile): +def validate_bundle(zfile: Union[Path, ZipFile]): """Ensure the R/qtl2 bundle is valid.""" missing = missing_files(zfile) if len(missing) > 0: diff --git a/scripts/cli_parser.py b/scripts/cli_parser.py index 308ee4b..d42ae66 100644 --- a/scripts/cli_parser.py +++ b/scripts/cli_parser.py @@ -19,6 +19,12 @@ def init_cli_parser(program: str, description: Optional[str] = None) -> Argument type=int, default=86400, help="How long to keep any redis keys around.") + parser.add_argument( + "--loglevel", + type=str, + default="INFO", + choices=["DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL"], + help="The severity of events to track with the logger.") return parser def add_global_data_arguments(parser: ArgumentParser) -> ArgumentParser: diff --git a/scripts/insert_samples.py b/scripts/insert_samples.py index 87f29dc..e3577b6 100644 --- a/scripts/insert_samples.py +++ b/scripts/insert_samples.py @@ -9,8 +9,9 @@ from redis import Redis from uploader.db_utils import database_connection from uploader.check_connections import check_db, check_redis -from uploader.db import species_by_id, population_by_id -from uploader.samples import ( +from uploader.species.models import species_by_id +from uploader.population.models import population_by_id +from uploader.samples.models import ( save_samples_data, read_samples_file, cross_reference_samples) diff --git a/scripts/process_rqtl2_bundle.py b/scripts/process_rqtl2_bundle.py index 20cfd3b..ade9862 100644 --- a/scripts/process_rqtl2_bundle.py +++ b/scripts/process_rqtl2_bundle.py @@ -2,6 +2,7 @@ import sys import uuid import json +import argparse import traceback from typing import Any from pathlib import Path @@ -94,10 +95,11 @@ def process_bundle(dbconn: mdb.Connection, logger.info("Processing geno files.") genoexit = install_genotypes( dbconn, - meta["speciesid"], - meta["populationid"], - meta["geno-dataset-id"], - Path(meta["rqtl2-bundle-file"]), + argparse.Namespace( + speciesid=meta["speciesid"], + populationid=meta["populationid"], + datasetid=meta["geno-dataset-id"], + rqtl2bundle=Path(meta["rqtl2-bundle-file"])), logger) if genoexit != 0: raise Exception("Processing 'geno' file failed.") @@ -109,10 +111,11 @@ def process_bundle(dbconn: mdb.Connection, if has_pheno_file(thejob): phenoexit = install_pheno_files( dbconn, - meta["speciesid"], - meta["platformid"], - meta["probe-dataset-id"], - Path(meta["rqtl2-bundle-file"]), + argparse.Namespace( + speciesid=meta["speciesid"], + platformid=meta["platformid"], + dataset_id=meta["probe-dataset-id"], + rqtl2bundle=Path(meta["rqtl2-bundle-file"])), logger) if phenoexit != 0: raise Exception("Processing 'pheno' file failed.") diff --git a/scripts/qc_on_rqtl2_bundle2.py b/scripts/qc_on_rqtl2_bundle2.py new file mode 100644 index 0000000..7e5d253 --- /dev/null +++ b/scripts/qc_on_rqtl2_bundle2.py @@ -0,0 +1,346 @@ +"""Run Quality Control checks on R/qtl2 bundle.""" +import os +import sys +import json +from time import sleep +from pathlib import Path +from zipfile import ZipFile +from argparse import Namespace +from datetime import timedelta +import multiprocessing as mproc +from functools import reduce, partial +from logging import Logger, getLogger, StreamHandler +from typing import Union, Sequence, Callable, Iterator + +import MySQLdb as mdb +from redis import Redis + +from quality_control.errors import InvalidValue +from quality_control.checks import decimal_points_error + +from uploader import jobs +from uploader.db_utils import database_connection +from uploader.check_connections import check_db, check_redis + +from r_qtl import r_qtl2 as rqtl2 +from r_qtl import r_qtl2_qc as rqc +from r_qtl import exceptions as rqe +from r_qtl import fileerrors as rqfe + +from scripts.process_rqtl2_bundle import parse_job +from scripts.redis_logger import setup_redis_logger +from scripts.cli_parser import init_cli_parser, add_global_data_arguments +from scripts.rqtl2.bundleutils import build_line_joiner, build_line_splitter + + +def check_for_missing_files( + rconn: Redis, fqjobid: str, extractpath: Path, logger: Logger) -> bool: + """Check that all files listed in the control file do actually exist.""" + logger.info("Checking for missing files.") + missing = rqc.missing_files(extractpath) + # add_to_errors(rconn, fqjobid, "errors-generic", tuple( + # rqfe.MissingFile( + # mfile[0], mfile[1], ( + # f"File '{mfile[1]}' is listed in the control file under " + # f"the '{mfile[0]}' key, but it does not actually exist in " + # "the bundle.")) + # for mfile in missing)) + if len(missing) > 0: + logger.error(f"Missing files in the bundle!") + return True + return False + + +def open_file(file_: Path) -> Iterator: + """Open file and return one line at a time.""" + with open(file_, "r", encoding="utf8") as infile: + for line in infile: + yield line + + +def check_markers( + filename: str, + row: tuple[str, ...], + save_error: lambda val: val +) -> tuple[rqfe.InvalidValue]: + """Check that the markers are okay""" + errors = tuple() + counts = {} + for marker in row: + counts = {**counts, marker: counts.get(marker, 0) + 1} + if marker is None or marker == "": + errors = errors + (save_error(rqfe.InvalidValue( + filename, + "markers" + "-", + marker, + "A marker MUST be a valid value.")),) + + return errors + tuple( + save_error(rqfe.InvalidValue( + filename, + "markers", + key, + f"Marker '{key}' was repeated {value} times")) + for key,value in counts.items() if value > 1) + + +def check_geno_line( + filename: str, + headers: tuple[str, ...], + row: tuple[Union[str, None]], + cdata: dict, + save_error: lambda val: val +) -> tuple[rqfe.InvalidValue]: + """Check that the geno line is correct.""" + errors = tuple() + # Verify that line has same number of columns as headers + if len(headers) != len(row): + errors = errors + (save_error(rqfe.InvalidValue( + filename, + headers[0], + row[0], + row[0], + "Every line MUST have the same number of columns.")),) + + # First column is the individuals/cases/samples + if not bool(row[0]): + errors = errors + (save_error(rqfe.InvalidValue( + filename, + headers[0], + row[0], + row[0], + "The sample/case MUST be a valid value.")),) + + def __process_value__(val): + if val in cdata["na.strings"]: + return None + if val in cdata["alleles"]: + return cdata["genotypes"][val] + + genocode = cdata.get("genotypes", {}) + for coltitle, cellvalue in zip(headers[1:],row[1:]): + if ( + bool(genocode) and + cellvalue is not None and + cellvalue not in genocode.keys() + ): + errors = errors + (save_error(rqfe.InvalidValue( + filename, row[0], coltitle, cellvalue, + f"Value '{cellvalue}' is invalid. Expected one of " + f"'{', '.join(genocode.keys())}'.")),) + + return errors + + +def push_file_error_to_redis(rconn: Redis, key: str, error: InvalidValue) -> InvalidValue: + """Push the file error to redis a json string + + Parameters + ---------- + rconn: Connection to redis + key: The name of the list where we push the errors + error: The file error to save + + Returns + ------- + Returns the file error it saved + """ + if bool(error): + rconn.rpush(key, json.dumps(error._asdict())) + return error + + +def file_errors_and_details( + redisargs: dict[str, str], + file_: Path, + filetype: str, + cdata: dict, + linesplitterfn: Callable, + linejoinerfn: Callable, + headercheckers: tuple[Callable, ...], + bodycheckers: tuple[Callable, ...] +) -> dict: + """Compute errors, and other file metadata.""" + errors = tuple() + if cdata[f"{filetype}_transposed"]: + rqtl2.transpose_csv_with_rename(file_, linesplitterfn, linejoinerfn) + + with Redis.from_url(redisargs["redisuri"], decode_responses=True) as rconn: + save_error_fn = partial(push_file_error_to_redis, + rconn, + error_list_name(filetype, file_.name)) + for lineno, line in enumerate(open_file(file_), start=1): + row = linesplitterfn(line) + if lineno == 1: + headers = tuple(row) + errors = errors + reduce( + lambda errs, fnct: errs + fnct( + file_.name, row[1:], save_error_fn), + headercheckers, + tuple()) + continue + + errors = errors + reduce( + lambda errs, fnct: errs + fnct( + file_.name, headers, row, cdata, save_error_fn), + bodycheckers, + tuple()) + + filedetails = { + "filename": file_.name, + "filesize": os.stat(file_).st_size, + "linecount": lineno + } + rconn.hset(redisargs["fqjobid"], + f"file-details:{filetype}:{file_.name}", + json.dumps(filedetails)) + return {**filedetails, "errors": errors} + + +def error_list_name(filetype: str, filename: str): + """Compute the name of the list where the errors will be pushed. + + Parameters + ---------- + filetype: The type of file. One of `r_qtl.r_qtl2.FILE_TYPES` + filename: The name of the file. + """ + return f"errors:{filetype}:{filename}" + + +def check_for_geno_errors( + redisargs: dict[str, str], + extractdir: Path, + cdata: dict, + linesplitterfn: Callable[[str], tuple[Union[str, None]]], + linejoinerfn: Callable[[tuple[Union[str, None], ...]], str], + logger: Logger +) -> bool: + """Check for errors in genotype files.""" + if "geno" in cdata or "founder_geno" in cdata: + genofiles = tuple( + extractdir.joinpath(fname) for fname in cdata.get("geno", [])) + fgenofiles = tuple( + extractdir.joinpath(fname) for fname in cdata.get("founder_geno", [])) + allgenofiles = genofiles + fgenofiles + with Redis.from_url(redisargs["redisuri"], decode_responses=True) as rconn: + error_list_names = [ + error_list_name("geno", file_.name) for file_ in allgenofiles] + for list_name in error_list_names: + rconn.delete(list_name) + rconn.hset( + redisargs["fqjobid"], + "geno-errors-lists", + json.dumps(error_list_names)) + processes = [ + mproc.Process(target=file_errors_and_details, + args=( + redisargs, + file_, + ftype, + cdata, + linesplitterfn, + linejoinerfn, + (check_markers,), + (check_geno_line,)) + ) + for ftype, file_ in ( + tuple(("geno", file_) for file_ in genofiles) + + tuple(("founder_geno", file_) for file_ in fgenofiles)) + ] + for process in processes: + process.start() + # Set expiry for any created error lists + for key in error_list_names: + rconn.expire(name=key, + time=timedelta(seconds=redisargs["redisexpiry"])) + + # TOD0: Add the errors to redis + if any(rconn.llen(errlst) > 0 for errlst in error_list_names): + logger.error("At least one of the 'geno' files has (an) error(s).") + return True + logger.info("No error(s) found in any of the 'geno' files.") + + else: + logger.info("No 'geno' files to check.") + + return False + + +# def check_for_pheno_errors(...): +# """Check for errors in phenotype files.""" +# pass + + +# def check_for_phenose_errors(...): +# """Check for errors in phenotype, standard-error files.""" +# pass + + +# def check_for_phenocovar_errors(...): +# """Check for errors in phenotype-covariates files.""" +# pass + + +def run_qc(rconn: Redis, args: Namespace, fqjobid: str, logger: Logger) -> int: + """Run quality control checks on R/qtl2 bundles.""" + thejob = parse_job(rconn, args.redisprefix, args.jobid) + print(f"THE JOB =================> {thejob}") + jobmeta = thejob["job-metadata"] + inpath = Path(jobmeta["rqtl2-bundle-file"]) + extractdir = inpath.parent.joinpath(f"{inpath.name}__extraction_dir") + with ZipFile(inpath, "r") as zfile: + rqtl2.extract(zfile, extractdir) + + ### BEGIN: The quality control checks ### + cdata = rqtl2.control_data(extractdir) + splitter = build_line_splitter(cdata) + joiner = build_line_joiner(cdata) + + redisargs = { + "fqjobid": fqjobid, + "redisuri": args.redisuri, + "redisexpiry": args.redisexpiry + } + check_for_missing_files(rconn, fqjobid, extractdir, logger) + # check_for_pheno_errors(...) + check_for_geno_errors(redisargs, extractdir, cdata, splitter, joiner, logger) + # check_for_phenose_errors(...) + # check_for_phenocovar_errors(...) + ### END: The quality control checks ### + + def __fetch_errors__(rkey: str) -> tuple: + return tuple(json.loads(rconn.hget(fqjobid, rkey) or "[]")) + + return (1 if any(( + bool(__fetch_errors__(key)) + for key in + ("errors-geno", "errors-pheno", "errors-phenos", "errors-phenocovar"))) + else 0) + + +if __name__ == "__main__": + def main(): + """Enter R/qtl2 bundle QC runner.""" + args = add_global_data_arguments(init_cli_parser( + "qc-on-rqtl2-bundle", "Run QC on R/qtl2 bundle.")).parse_args() + check_redis(args.redisuri) + check_db(args.databaseuri) + + logger = getLogger("qc-on-rqtl2-bundle") + logger.addHandler(StreamHandler(stream=sys.stderr)) + logger.setLevel("DEBUG") + + fqjobid = jobs.job_key(args.redisprefix, args.jobid) + with Redis.from_url(args.redisuri, decode_responses=True) as rconn: + logger.addHandler(setup_redis_logger( + rconn, fqjobid, f"{fqjobid}:log-messages", + args.redisexpiry)) + + exitcode = run_qc(rconn, args, fqjobid, logger) + rconn.hset( + jobs.job_key(args.redisprefix, args.jobid), "exitcode", exitcode) + return exitcode + + sys.exit(main()) diff --git a/scripts/redis_logger.py b/scripts/redis_logger.py index 2ae682b..d3fde5f 100644 --- a/scripts/redis_logger.py +++ b/scripts/redis_logger.py @@ -1,5 +1,6 @@ """Utilities to log to redis for our worker scripts.""" import logging +from typing import Optional from redis import Redis @@ -26,6 +27,26 @@ class RedisLogger(logging.Handler): self.redisconnection.rpush(self.messageslistname, self.format(record)) self.redisconnection.expire(self.messageslistname, self.expiry) +class RedisMessageListHandler(logging.Handler): + """Send messages to specified redis list.""" + def __init__(self, + rconn: Redis, + fullyqualifiedkey: str, + loglevel: int = logging.NOTSET, + expiry: Optional[int] = 86400): + super().__init__(loglevel) + self.redisconnection = rconn + self.fullyqualifiedkey = fullyqualifiedkey + self.expiry = expiry + + def emit(self, record): + """Log out to specified `fullyqualifiedkey`.""" + self.redisconnection.rpush(self.fullyqualifiedkey, self.format(record)) + if bool(self.expiry): + self.redisconnection.expire(self.fullyqualifiedkey, self.expiry) + else: + self.redisconnection.persist(self.fullyqualifiedkey) + def setup_redis_logger(rconn: Redis, fullyqualifiedjobid: str, job_messagelist: str, diff --git a/scripts/rqtl2/bundleutils.py b/scripts/rqtl2/bundleutils.py new file mode 100644 index 0000000..17faa7c --- /dev/null +++ b/scripts/rqtl2/bundleutils.py @@ -0,0 +1,44 @@ +"""Common utilities to operate in R/qtl2 bundles.""" +from typing import Union, Callable + +def build_line_splitter(cdata: dict) -> Callable[[str], tuple[Union[str, None], ...]]: + """Build and return a function to use to split data in the files. + + Parameters + ---------- + cdata: A dict holding the control information included with the R/qtl2 + bundle. + + Returns + ------- + A function that takes a string and return a tuple of strings. + """ + separator = cdata["sep"] + na_strings = cdata["na.strings"] + def __splitter__(line: str) -> tuple[Union[str, None], ...]: + return tuple( + item if item not in na_strings else None + for item in + (field.strip() for field in line.strip().split(separator))) + return __splitter__ + + +def build_line_joiner(cdata: dict) -> Callable[[tuple[Union[str, None], ...]], str]: + """Build and return a function to use to split data in the files. + + Parameters + ---------- + cdata: A dict holding the control information included with the R/qtl2 + bundle. + + Returns + ------- + A function that takes a string and return a tuple of strings. + """ + separator = cdata["sep"] + na_strings = cdata["na.strings"] + def __joiner__(row: tuple[Union[str, None], ...]) -> str: + return separator.join( + (na_strings[0] if item is None else item) + for item in row) + return __joiner__ diff --git a/scripts/rqtl2/cli_parser.py b/scripts/rqtl2/cli_parser.py index bcc7a4f..9bb60a3 100644 --- a/scripts/rqtl2/cli_parser.py +++ b/scripts/rqtl2/cli_parser.py @@ -2,12 +2,22 @@ from pathlib import Path from argparse import ArgumentParser -def add_common_arguments(parser: ArgumentParser) -> ArgumentParser: - """Add common arguments to the CLI parser.""" - parser.add_argument("datasetid", - type=int, - help="The dataset to which the data belongs.") +def add_bundle_argument(parser: ArgumentParser) -> ArgumentParser: + """Add the `rqtl2bundle` argument.""" parser.add_argument("rqtl2bundle", type=Path, help="Path to R/qtl2 bundle zip file.") return parser + + +def add_datasetid_argument(parser: ArgumentParser) -> ArgumentParser: + """Add the `datasetid` argument.""" + parser.add_argument("datasetid", + type=int, + help="The dataset to which the data belongs.") + return parser + + +def add_common_arguments(parser: ArgumentParser) -> ArgumentParser: + """Add common arguments to the CLI parser.""" + return add_bundle_argument(add_datasetid_argument(parser)) diff --git a/scripts/rqtl2/entry.py b/scripts/rqtl2/entry.py index b7fb68e..bc4cd9f 100644 --- a/scripts/rqtl2/entry.py +++ b/scripts/rqtl2/entry.py @@ -1,5 +1,5 @@ """Build common script-entry structure.""" -from logging import Logger +import logging from typing import Callable from argparse import Namespace @@ -12,12 +12,19 @@ from uploader.check_connections import check_db, check_redis from scripts.redis_logger import setup_redis_logger -def build_main(args: Namespace, - run_fn: Callable[[Connection, Namespace], int], - logger: Logger, - loglevel: str = "INFO") -> Callable[[],int]: +def build_main( + args: Namespace, + run_fn: Callable[[Connection, Namespace, logging.Logger], int], + loggername: str +) -> Callable[[],int]: """Build a function to be used as an entry-point for scripts.""" def main(): + logging.basicConfig( + format=( + "%(asctime)s - %(levelname)s %(name)s: " + "(%(pathname)s: %(lineno)d) %(message)s"), + level=args.loglevel) + logger = logging.getLogger(loggername) check_db(args.databaseuri) check_redis(args.redisuri) if not args.rqtl2bundle.exists(): @@ -26,13 +33,12 @@ def build_main(args: Namespace, with (Redis.from_url(args.redisuri, decode_responses=True) as rconn, database_connection(args.databaseuri) as dbconn): - fqjobid = jobs.job_key(jobs.jobsnamespace(), args.jobid) + fqjobid = jobs.job_key(args.redisprefix, args.jobid) logger.addHandler(setup_redis_logger( rconn, fqjobid, f"{fqjobid}:log-messages", args.redisexpiry)) - logger.setLevel(loglevel) - return run_fn(dbconn, args) + return run_fn(dbconn, args, logger) return main diff --git a/scripts/rqtl2/install_genotypes.py b/scripts/rqtl2/install_genotypes.py index 08fc0ba..20a19da 100644 --- a/scripts/rqtl2/install_genotypes.py +++ b/scripts/rqtl2/install_genotypes.py @@ -1,11 +1,11 @@ """Load genotypes from R/qtl2 bundle into the database.""" import sys +import argparse import traceback -from pathlib import Path from zipfile import ZipFile from functools import reduce from typing import Iterator, Optional -from logging import Logger, getLogger, StreamHandler +from logging import Logger, getLogger import MySQLdb as mdb from MySQLdb.cursors import DictCursor @@ -19,6 +19,8 @@ from scripts.rqtl2.entry import build_main from scripts.rqtl2.cli_parser import add_common_arguments from scripts.cli_parser import init_cli_parser, add_global_data_arguments +__MODULE__ = "scripts.rqtl2.install_genotypes" + def insert_markers( dbconn: mdb.Connection, speciesid: int, @@ -179,20 +181,18 @@ def cross_reference_genotypes( } for row in dataids) _logger.debug( "The insert query was\n\t%s\n\nwith the parameters\n\t%s", - insertquery, - (speciesid,) + markers) + insertquery, insertparams) cursor.executemany(insertquery, insertparams) return cursor.rowcount def install_genotypes(#pylint: disable=[too-many-arguments, too-many-locals] dbconn: mdb.Connection, - speciesid: int, - populationid: int, - datasetid: int, - rqtl2bundle: Path, + args: argparse.Namespace, logger: Logger = getLogger(__name__) ) -> int: """Load any existing genotypes into the database.""" + (speciesid, populationid, datasetid, rqtl2bundle) = ( + args.speciesid, args.populationid, args.datasetid, args.rqtl2bundle) count = 0 with ZipFile(str(rqtl2bundle.absolute()), "r") as zfile: try: @@ -254,15 +254,5 @@ if __name__ == "__main__": return parser.parse_args() - thelogger = getLogger("install_genotypes") - thelogger.addHandler(StreamHandler(stream=sys.stderr)) - main = build_main( - cli_args(), - lambda dbconn, args: install_genotypes(dbconn, - args.speciesid, - args.populationid, - args.datasetid, - args.rqtl2bundle), - thelogger, - "INFO") + main = build_main(cli_args(), install_genotypes, __MODULE__) sys.exit(main()) diff --git a/scripts/rqtl2/install_phenos.py b/scripts/rqtl2/install_phenos.py index b5cab8e..a6e9fb2 100644 --- a/scripts/rqtl2/install_phenos.py +++ b/scripts/rqtl2/install_phenos.py @@ -1,10 +1,10 @@ """Load pheno from R/qtl2 bundle into the database.""" import sys +import argparse import traceback -from pathlib import Path from zipfile import ZipFile from functools import reduce -from logging import Logger, getLogger, StreamHandler +from logging import Logger, getLogger import MySQLdb as mdb from MySQLdb.cursors import DictCursor @@ -18,6 +18,8 @@ from r_qtl import r_qtl2_qc as rqc from functional_tools import take +__MODULE__ = "scripts.rqtl2.install_phenos" + def insert_probesets(dbconn: mdb.Connection, platformid: int, phenos: tuple[str, ...]) -> int: @@ -95,12 +97,11 @@ def cross_reference_probeset_data(dbconn: mdb.Connection, def install_pheno_files(#pylint: disable=[too-many-arguments, too-many-locals] dbconn: mdb.Connection, - speciesid: int, - platformid: int, - datasetid: int, - rqtl2bundle: Path, + args: argparse.Namespace, logger: Logger = getLogger()) -> int: """Load data in `pheno` files and other related files into the database.""" + (speciesid, platformid, datasetid, rqtl2bundle) = ( + args.speciesid, args.platformid, args.datasetid, args.rqtl2bundle) with ZipFile(str(rqtl2bundle), "r") as zfile: try: rqc.validate_bundle(zfile) @@ -155,16 +156,5 @@ if __name__ == "__main__": return parser.parse_args() - thelogger = getLogger("install_phenos") - thelogger.addHandler(StreamHandler(stream=sys.stderr)) - main = build_main( - cli_args(), - lambda dbconn, args: install_pheno_files(dbconn, - args.speciesid, - args.platformid, - args.datasetid, - args.rqtl2bundle, - thelogger), - thelogger, - "DEBUG") + main = build_main(cli_args(), install_pheno_files, __MODULE__) sys.exit(main()) diff --git a/scripts/rqtl2/phenotypes_qc.py b/scripts/rqtl2/phenotypes_qc.py new file mode 100644 index 0000000..83828e4 --- /dev/null +++ b/scripts/rqtl2/phenotypes_qc.py @@ -0,0 +1,468 @@ +"""Run quality control on phenotypes-specific files in the bundle.""" +import sys +import uuid +import shutil +import logging +import tempfile +import contextlib +from pathlib import Path +from logging import Logger +from zipfile import ZipFile +from argparse import Namespace +import multiprocessing as mproc +from functools import reduce, partial +from typing import Union, Iterator, Callable, Optional, Sequence + +import MySQLdb as mdb +from redis import Redis + +from r_qtl import r_qtl2 as rqtl2 +from r_qtl import r_qtl2_qc as rqc +from r_qtl import exceptions as rqe +from r_qtl.fileerrors import InvalidValue + +from functional_tools import chain + +from quality_control.checks import decimal_places_pattern + +from uploader.files import sha256_digest_over_file +from uploader.samples.models import samples_by_species_and_population + +from scripts.rqtl2.entry import build_main +from scripts.redis_logger import RedisMessageListHandler +from scripts.rqtl2.cli_parser import add_bundle_argument +from scripts.cli_parser import init_cli_parser, add_global_data_arguments +from scripts.rqtl2.bundleutils import build_line_joiner, build_line_splitter + +__MODULE__ = "scripts.rqtl2.phenotypes_qc" + +def validate(phenobundle: Path, logger: Logger) -> dict: + """Check that the bundle is generally valid""" + try: + rqc.validate_bundle(phenobundle) + except rqe.RQTLError as rqtlerr: + # logger.error("Bundle file validation failed!", exc_info=True) + return { + "skip": True, + "logger": logger, + "phenobundle": phenobundle, + "errors": (" ".join(rqtlerr.args),) + } + return { + "errors": tuple(), + "skip": False, + "phenobundle": phenobundle, + "logger": logger + } + + +def check_for_mandatory_pheno_keys( + phenobundle: Path, + logger: Logger, + **kwargs +) -> dict: + """Check that the mandatory keys exist for phenotypes.""" + if kwargs.get("skip", False): + return { + **kwargs, + "logger": logger, + "phenobundle": phenobundle + } + + _mandatory_keys = ("pheno", "phenocovar") + _cdata = rqtl2.read_control_file(phenobundle) + _errors = kwargs.get("errors", tuple()) + tuple( + f"Expected '{key}' file(s) are not declared in the bundle." + for key in _mandatory_keys if key not in _cdata.keys()) + return { + **kwargs, + "logger": logger, + "phenobundle": phenobundle, + "errors": _errors, + "skip": len(_errors) > 0 + } + + +def check_for_averages_files( + phenobundle: Path, + logger: Logger, + **kwargs +) -> dict: + """Check that averages files appear together""" + if kwargs.get("skip", False): + return { + **kwargs, + "logger": logger, + "phenobundle": phenobundle + } + + _together = (("phenose", "phenonum"), ("phenonum", "phenose")) + _cdata = rqtl2.read_control_file(phenobundle) + _errors = kwargs.get("errors", tuple()) + tuple( + f"'{first}' is defined in the control file but there is no " + f"corresponding '{second}'" + for first, second in _together + if ((first in _cdata.keys()) and (second not in _cdata.keys()))) + return { + **kwargs, + "logger": logger, + "phenobundle": phenobundle, + "errors": _errors, + "skip": len(_errors) > 0 + } + + +def extract_bundle( + bundle: Path, workdir: Path, jobid: uuid.UUID +) -> tuple[Path, tuple[Path, ...]]: + """Extract the bundle.""" + with ZipFile(bundle) as zfile: + extractiondir = workdir.joinpath( + f"{str(jobid)}-{sha256_digest_over_file(bundle)}-{bundle.name}") + return extractiondir, rqtl2.extract(zfile, extractiondir) + + +def undo_transpose(filetype: str, cdata: dict, extractiondir): + """Undo transposition of all files of type `filetype` in thebundle.""" + if len(cdata.get(filetype, [])) > 0 and cdata.get(f"{filetype}_transposed", False): + files = (extractiondir.joinpath(_file) for _file in cdata[filetype]) + for _file in files: + rqtl2.transpose_csv_with_rename( + _file, + build_line_splitter(cdata), + build_line_joiner(cdata)) + + +@contextlib.contextmanager +def redis_logger( + redisuri: str, loggername: str, filename: str, fqkey: str +) -> Iterator[logging.Logger]: + """Build a Redis message-list logger.""" + rconn = Redis.from_url(redisuri, decode_responses=True) + logger = logging.getLogger(loggername) + logger.propagate = False + handler = RedisMessageListHandler( + rconn, + fullyqualifiedkey(fqkey, filename))#type: ignore[arg-type] + handler.setFormatter(logging.getLogger().handlers[0].formatter) + logger.addHandler(handler) + try: + yield logger + finally: + rconn.close() + + +def qc_phenocovar_file( + filepath: Path, + redisuri, + fqkey: str, + separator: str, + comment_char: str): + """Check that `phenocovar` files are structured correctly.""" + with redis_logger( + redisuri, + f"{__MODULE__}.qc_phenocovar_file", + filepath.name, + fqkey) as logger: + logger.info("Running QC on file: %s", filepath.name) + _csvfile = rqtl2.read_csv_file(filepath, separator, comment_char) + _headings = tuple(heading.lower() for heading in next(_csvfile)) + _errors: tuple[InvalidValue, ...] = tuple() + for heading in ("description", "units"): + if heading not in _headings: + _errors = (InvalidValue( + filepath.name, + "header row", + "-", + "-", + (f"File {filepath.name} is missing the {heading} heading " + "in the header line.")),) + + def collect_errors(errors_and_linecount, line): + _errs, _lc = errors_and_linecount + logger.info("Testing record '%s'", line[0]) + if len(line) != len(_headings): + _errs = _errs + (InvalidValue( + filepath.name, + line[0], + "-", + "-", + (f"Record {_lc} in file {filepath.name} has a different " + "number of columns than the number of headings")),) + _line = dict(zip(_headings, line)) + if not bool(_line["description"]): + _errs = _errs + ( + InvalidValue(filepath.name, + _line[_headings[0]], + "description", + _line["description"], + "The description is not provided!"),) + + return _errs, _lc+1 + + return { + filepath.name: dict(zip( + ("errors", "linecount"), + reduce(collect_errors, _csvfile, (_errors, 1)))) + } + + +def merge_dicts(*dicts): + """Merge multiple dicts into a single one.""" + return reduce(lambda merged, dct: {**merged, **dct}, dicts, {}) + + +def decimal_points_error(# pylint: disable=[too-many-arguments] + filename: str, + rowtitle: str, + coltitle: str, + cellvalue: str, + message: str, + decimal_places: int = 1 +) -> Optional[InvalidValue]: + """Returns an error if the value does not meet the checks.""" + if not bool(decimal_places_pattern(decimal_places).match(cellvalue)): + return InvalidValue(filename, rowtitle, coltitle, cellvalue, message) + return None + + +def integer_error( + filename: str, + rowtitle: str, + coltitle: str, + cellvalue: str, + message: str +) -> Optional[InvalidValue]: + """Returns an error if the value does not meet the checks.""" + try: + value = int(cellvalue) + if value <= 0: + raise ValueError("Must be a non-zero, positive number.") + return None + except ValueError as _verr: + return InvalidValue(filename, rowtitle, coltitle, cellvalue, message) + + +def qc_pheno_file(# pylint: disable=[too-many-arguments] + filepath: Path, + redisuri: str, + fqkey: str, + samples: tuple[str, ...], + phenonames: tuple[str, ...], + separator: str, + comment_char: str, + na_strings: Sequence[str], + error_fn: Callable = decimal_points_error +): + """Run QC/QA on a `pheno` file.""" + with redis_logger( + redisuri, + f"{__MODULE__}.qc_pheno_file", + filepath.name, + fqkey) as logger: + logger.info("Running QC on file: %s", filepath.name) + _csvfile = rqtl2.read_csv_file(filepath, separator, comment_char) + _headings: tuple[str, ...] = tuple( + heading.lower() for heading in next(_csvfile)) + _errors: tuple[InvalidValue, ...] = tuple() + + _absent = tuple(pheno for pheno in _headings[1:] if pheno not in phenonames) + if len(_absent) > 0: + _errors = _errors + (InvalidValue( + filepath.name, + "header row", + "-", + ", ".join(_absent), + (f"The phenotype names ({', '.join(samples)}) do not exist in any " + "of the provided phenocovar files.")),) + + def collect_errors(errors_and_linecount, line): + _errs, _lc = errors_and_linecount + if line[0] not in samples: + _errs = _errs + (InvalidValue( + filepath.name, + line[0], + _headings[0], + line[0], + (f"The sample named '{line[0]}' does not exist in the database. " + "You will need to upload that first.")),) + + for field, value in zip(_headings[1:], line[1:]): + if value in na_strings: + continue + _err = error_fn( + filepath.name, + line[0], + field, + value) + _errs = _errs + ((_err,) if bool(_err) else tuple()) + + return _errs, _lc+1 + + return { + filepath.name: dict(zip( + ("errors", "linecount"), + reduce(collect_errors, _csvfile, (_errors, 1)))) + } + + +def phenotype_names(filepath: Path, + separator: str, + comment_char: str) -> tuple[str, ...]: + """Read phenotype names from `phenocovar` file.""" + return reduce(lambda tpl, line: tpl + (line[0],),#type: ignore[arg-type, return-value] + rqtl2.read_csv_file(filepath, separator, comment_char), + tuple())[1:] + +def fullyqualifiedkey( + prefix: str, + rest: Optional[str] = None +) -> Union[Callable[[str], str], str]: + """Compute fully qualified Redis key.""" + if not bool(rest): + return lambda _rest: f"{prefix}:{_rest}" + return f"{prefix}:{rest}" + +def run_qc(# pylint: disable=[too-many-locals] + dbconn: mdb.Connection, + args: Namespace, + logger: Logger +) -> int: + """Run quality control checks on the bundle.""" + logger.debug("Beginning the quality assuarance checks.") + results = check_for_averages_files( + **check_for_mandatory_pheno_keys( + **validate(args.rqtl2bundle, logger))) + errors = results.get("errors", tuple()) + if len(errors) > 0: + logger.error("We found the following errors:\n%s", + "\n".join(f" - {error}" for error in errors)) + return 1 + # Run QC on actual values + # Steps: + # - Extract file to specific directory + extractiondir, *_bundlefiles = extract_bundle( + args.rqtl2bundle, args.workingdir, args.jobid) + + # - For every pheno, phenocovar, phenose, phenonum file, undo + # transposition where relevant + cdata = rqtl2.control_data(extractiondir) + with mproc.Pool(mproc.cpu_count() - 1) as pool: + pool.starmap( + undo_transpose, + ((ftype, cdata, extractiondir) + for ftype in ("pheno", "phenocovar", "phenose", "phenonum"))) + + # - Fetch samples/individuals from database. + logger.debug("Fetching samples/individuals from the database.") + samples = tuple(#type: ignore[var-annotated] + item for item in set(reduce( + lambda acc, item: acc + ( + item["Name"], item["Name2"], item["Symbol"], item["Alias"]), + samples_by_species_and_population( + dbconn, args.speciesid, args.populationid), + tuple())) + if bool(item)) + + # - Check that `description` and `units` is present in phenocovar for + # all phenotypes + with mproc.Pool(mproc.cpu_count() - 1) as pool: + logger.debug("Check for errors in 'phenocovar' file(s).") + _phenocovar_qc_res = merge_dicts(*pool.starmap(qc_phenocovar_file, tuple( + (extractiondir.joinpath(_file), + args.redisuri, + chain( + "phenocovar", + fullyqualifiedkey(args.jobid), + fullyqualifiedkey(args.redisprefix)), + cdata["sep"], + cdata["comment.char"]) + for _file in cdata.get("phenocovar", [])))) + + # - Check all samples in pheno files exist in database + # - Check all phenotypes in pheno files exist in phenocovar files + # - Check all numeric values in pheno files + phenonames = tuple(set( + name for names in pool.starmap(phenotype_names, tuple( + (extractiondir.joinpath(_file), cdata["sep"], cdata["comment.char"]) + for _file in cdata.get("phenocovar", []))) + for name in names)) + + dec_err_fn = partial(decimal_points_error, message=( + "Expected a non-negative number with at least one decimal " + "place.")) + + logger.debug("Check for errors in 'pheno' file(s).") + _pheno_qc_res = merge_dicts(*pool.starmap(qc_pheno_file, tuple(( + extractiondir.joinpath(_file), + args.redisuri, + chain( + "pheno", + fullyqualifiedkey(args.jobid), + fullyqualifiedkey(args.redisprefix)), + samples, + phenonames, + cdata["sep"], + cdata["comment.char"], + cdata["na.strings"], + dec_err_fn + ) for _file in cdata.get("pheno", [])))) + + # - Check the 3 checks above for phenose and phenonum values too + # qc_phenose_files(…) + # qc_phenonum_files(…) + logger.debug("Check for errors in 'phenose' file(s).") + _phenose_qc_res = merge_dicts(*pool.starmap(qc_pheno_file, tuple(( + extractiondir.joinpath(_file), + args.redisuri, + chain( + "phenose", + fullyqualifiedkey(args.jobid), + fullyqualifiedkey(args.redisprefix)), + samples, + phenonames, + cdata["sep"], + cdata["comment.char"], + cdata["na.strings"], + dec_err_fn + ) for _file in cdata.get("phenose", [])))) + + logger.debug("Check for errors in 'phenonum' file(s).") + _phenonum_qc_res = merge_dicts(*pool.starmap(qc_pheno_file, tuple(( + extractiondir.joinpath(_file), + args.redisuri, + chain( + "phenonum", + fullyqualifiedkey(args.jobid), + fullyqualifiedkey(args.redisprefix)), + samples, + phenonames, + cdata["sep"], + cdata["comment.char"], + cdata["na.strings"], + partial(integer_error, message=( + "Expected a non-negative, non-zero integer value.")) + ) for _file in cdata.get("phenonum", [])))) + + # - Delete all extracted files + shutil.rmtree(extractiondir) + raise NotImplementedError("WIP!") + + +if __name__ == "__main__": + def cli_args(): + """Process command-line arguments for `install_phenos`""" + parser = add_bundle_argument(add_global_data_arguments(init_cli_parser( + program="PhenotypesQC", + description=( + "Perform Quality Control checks on a phenotypes bundle file")))) + parser.add_argument( + "--workingdir", + default=f"{tempfile.gettempdir()}/phenotypes_qc", + help=("The directory where this script will put its intermediate " + "files."), + type=Path) + return parser.parse_args() + + main = build_main(cli_args(), run_qc, __MODULE__) + sys.exit(main()) diff --git a/tests/qc_app/__init__.py b/tests/uploader/__init__.py index e69de29..e69de29 100644 --- a/tests/qc_app/__init__.py +++ b/tests/uploader/__init__.py diff --git a/tests/qc_app/test_entry.py b/tests/uploader/test_entry.py index 0c614a5..0c614a5 100644 --- a/tests/qc_app/test_entry.py +++ b/tests/uploader/test_entry.py diff --git a/tests/qc_app/test_expression_data_pages.py b/tests/uploader/test_expression_data_pages.py index c2f7de1..c2f7de1 100644 --- a/tests/qc_app/test_expression_data_pages.py +++ b/tests/uploader/test_expression_data_pages.py diff --git a/tests/uploader/test_files.py b/tests/uploader/test_files.py new file mode 100644 index 0000000..cb22fff --- /dev/null +++ b/tests/uploader/test_files.py @@ -0,0 +1,17 @@ +"""Tests functions in the `uploader.files` module.""" +from pathlib import Path + +import pytest + +from uploader.files import sha256_digest_over_file + +@pytest.mark.unit_test +@pytest.mark.parametrize( + "filepath,expectedhash", + ((Path("tests/test_data/average.tsv.zip"), + "a371c654c095c030edad468e1c3d6b176ea8adfbcd91a322afd37779044478d9"), + (Path("tests/test_data/standarderror.tsv"), + "a08332e0b06391d50eecb722f69d85fbdf374a2d77713ee879d3fd6c60419d55"))) +def test_sha256_digest_over_file(filepath: Path, expectedhash: str): + """Test the `sha256_digest_over_file` function.""" + assert sha256_digest_over_file(filepath) == expectedhash diff --git a/tests/qc_app/test_parse.py b/tests/uploader/test_parse.py index 076c47c..076c47c 100644 --- a/tests/qc_app/test_parse.py +++ b/tests/uploader/test_parse.py diff --git a/tests/qc_app/test_progress_indication.py b/tests/uploader/test_progress_indication.py index 14a1050..14a1050 100644 --- a/tests/qc_app/test_progress_indication.py +++ b/tests/uploader/test_progress_indication.py diff --git a/tests/qc_app/test_results_page.py b/tests/uploader/test_results_page.py index 8c8379f..8c8379f 100644 --- a/tests/qc_app/test_results_page.py +++ b/tests/uploader/test_results_page.py diff --git a/tests/qc_app/test_uploads_with_zip_files.py b/tests/uploader/test_uploads_with_zip_files.py index 1506cfa..1506cfa 100644 --- a/tests/qc_app/test_uploads_with_zip_files.py +++ b/tests/uploader/test_uploads_with_zip_files.py diff --git a/uploader/__init__.py b/uploader/__init__.py index 2d731af..9fdb383 100644 --- a/uploader/__init__.py +++ b/uploader/__init__.py @@ -9,13 +9,11 @@ from flask_session import Session from uploader.oauth2.client import user_logged_in, authserver_authorise_uri -from .entry import entrybp -from .upload import upload -from .parse import parsebp -from .samples import samples +from . import session from .base_routes import base -from .dbinsert import dbinsertbp +from .species import speciesbp from .oauth2.views import oauth2 +from .expression_data import exprdatabp from .errors import register_error_handlers def override_settings_with_envvars( @@ -78,17 +76,14 @@ def create_app(): app.add_template_global(lambda: app.config["GN2_SERVER_URL"], name="gn2server_uri") app.add_template_global(user_logged_in) + app.add_template_global(lambda : session.user_details()["email"], name="user_email") Session(app) # setup blueprints app.register_blueprint(base, url_prefix="/") - app.register_blueprint(entrybp, url_prefix="/") - app.register_blueprint(parsebp, url_prefix="/parse") app.register_blueprint(oauth2, url_prefix="/oauth2") - app.register_blueprint(upload, url_prefix="/upload") - app.register_blueprint(dbinsertbp, url_prefix="/dbinsert") - app.register_blueprint(samples, url_prefix="/samples") + app.register_blueprint(speciesbp, url_prefix="/species") register_error_handlers(app) return app diff --git a/uploader/authorisation.py b/uploader/authorisation.py index 8ab83f8..ee8fe97 100644 --- a/uploader/authorisation.py +++ b/uploader/authorisation.py @@ -1,9 +1,15 @@ """Authorisation utilities.""" +import logging from functools import wraps +from typing import Callable from flask import flash, redirect +from pymonad.either import Left, Right, Either +from authlib.jose import KeySet, JsonWebToken +from authlib.jose.errors import BadSignatureError from uploader import session +from uploader.oauth2.client import auth_server_jwks def require_login(function): """Check that the user is logged in before executing `func`.""" @@ -19,3 +25,43 @@ def require_login(function): __clear_session__, lambda token: function(*args, **kwargs)) return __is_session_valid__ + + +def __validate_token__(jwks: KeySet, token: dict) -> Either: + """Check that a token is signed by a key from the authorisation server.""" + for key in jwks.keys: + try: + # Fixes CVE-2016-10555. See + # https://docs.authlib.org/en/latest/jose/jwt.html + jwt = JsonWebToken(["RS256"]) + jwt.decode(token["access_token"], key) + return Right(token) + except BadSignatureError: + pass + + return Left({"token": token}) + + +def require_token(func: Callable) -> Callable: + """ + Wrap functions that require the user be authorised to perform the operations + that the functions in question provide. + """ + def __invalid_token__(_whatever): + logging.debug("==========> Failure log: %s", _whatever) + raise Exception( + "You attempted to access a feature of the system that requires " + "authorisation. Unfortunately, we could not verify you have the " + "appropriate authorisation to perform the action you requested. " + "You might need to log in, or if you already are logged in, you " + "need to log out, then log back in to get a newer token/session.") + @wraps(func) + def __wrapper__(*args, **kwargs): + return session.user_token().then(lambda tok: { + "jwks": auth_server_jwks(), + "token": tok + }).then(lambda vals: __validate_token__(**vals)).either( + __invalid_token__, + lambda tok: func(*args, **{**kwargs, "token": tok})) + + return __wrapper__ diff --git a/uploader/base_routes.py b/uploader/base_routes.py index 9daf439..742a254 100644 --- a/uploader/base_routes.py +++ b/uploader/base_routes.py @@ -1,8 +1,32 @@ """Basic routes required for all pages""" import os -from flask import Blueprint, send_from_directory +from urllib.parse import urljoin + +from flask import (Blueprint, + current_app as app, + send_from_directory) + +from uploader.ui import make_template_renderer +from uploader.oauth2.client import user_logged_in base = Blueprint("base", __name__) +render_template = make_template_renderer("home") + + +@base.route("/favicon.ico", methods=["GET"]) +def favicon(): + """Return the favicon.""" + return send_from_directory(os.path.join(app.root_path, "static"), + "images/CITGLogo.png", + mimetype="image/png") + + +@base.route("/", methods=["GET"]) +def index(): + """Load the landing page""" + return render_template("index.html" if user_logged_in() else "login.html", + gn2server_intro=urljoin(app.config["GN2_SERVER_URL"], + "/intro")) def appenv(): """Get app's guix environment path.""" diff --git a/uploader/datautils.py b/uploader/datautils.py new file mode 100644 index 0000000..46a55c4 --- /dev/null +++ b/uploader/datautils.py @@ -0,0 +1,38 @@ +"""Generic data utilities: Rename module.""" +import math +from functools import reduce +from typing import Union, Sequence + +def enumerate_sequence(seq: Sequence[dict], start:int = 1) -> Sequence[dict]: + """Enumerate sequence beginning at 1""" + return tuple({**item, "sequence_number": seqno} + for seqno, item in enumerate(seq, start=start)) + + +def order_by_family(items: tuple[dict, ...], + family_key: str = "Family", + order_key: str = "FamilyOrderId") -> list: + """Order the populations by their families.""" + def __family_order__(item): + orderval = item[order_key] + return math.inf if orderval is None else orderval + + def __order__(ordered, current): + _key = (__family_order__(current), current[family_key]) + return { + **ordered, + _key: ordered.get(_key, tuple()) + (current,) + } + + return sorted(tuple(reduce(__order__, items, {}).items()), + key=lambda item: item[0][0]) + + +def safe_int(val: Union[str, int, float]) -> int: + """ + Convert val into an integer: if val cannot be converted, return a zero. + """ + try: + return int(val) + except ValueError: + return 0 diff --git a/uploader/db/__init__.py b/uploader/db/__init__.py index 36e93e8..d2b1d9d 100644 --- a/uploader/db/__init__.py +++ b/uploader/db/__init__.py @@ -1,8 +1,2 @@ """Database functions""" -from .species import species, species_by_id -from .populations import ( - save_population, - population_by_id, - populations_by_species, - population_by_species_and_id) from .datasets import geno_datasets_by_species_and_population diff --git a/uploader/db/platforms.py b/uploader/db/platforms.py deleted file mode 100644 index cb527a7..0000000 --- a/uploader/db/platforms.py +++ /dev/null @@ -1,25 +0,0 @@ -"""Handle db interactions for platforms.""" -from typing import Optional - -import MySQLdb as mdb -from MySQLdb.cursors import DictCursor - -def platforms_by_species( - conn: mdb.Connection, speciesid: int) -> tuple[dict, ...]: - """Retrieve platforms by the species""" - with conn.cursor(cursorclass=DictCursor) as cursor: - cursor.execute("SELECT * FROM GeneChip WHERE SpeciesId=%s " - "ORDER BY GeneChipName ASC", - (speciesid,)) - return tuple(dict(row) for row in cursor.fetchall()) - -def platform_by_id(conn: mdb.Connection, platformid: int) -> Optional[dict]: - """Retrieve a platform by its ID""" - with conn.cursor(cursorclass=DictCursor) as cursor: - cursor.execute("SELECT * FROM GeneChip WHERE Id=%s", - (platformid,)) - result = cursor.fetchone() - if bool(result): - return dict(result) - - return None diff --git a/uploader/db/populations.py b/uploader/db/populations.py deleted file mode 100644 index 4485e52..0000000 --- a/uploader/db/populations.py +++ /dev/null @@ -1,54 +0,0 @@ -"""Functions for accessing the database relating to species populations.""" -import MySQLdb as mdb -from MySQLdb.cursors import DictCursor - -def population_by_id(conn: mdb.Connection, population_id) -> dict: - """Get the grouping/population by id.""" - with conn.cursor(cursorclass=DictCursor) as cursor: - cursor.execute("SELECT * FROM InbredSet WHERE InbredSetId=%s", - (population_id,)) - return cursor.fetchone() - -def population_by_species_and_id( - conn: mdb.Connection, species_id, population_id) -> dict: - """Retrieve a population by its identifier and species.""" - with conn.cursor(cursorclass=DictCursor) as cursor: - cursor.execute("SELECT * FROM InbredSet WHERE SpeciesId=%s AND Id=%s", - (species_id, population_id)) - return cursor.fetchone() - -def populations_by_species(conn: mdb.Connection, speciesid) -> tuple: - "Retrieve group (InbredSet) information from the database." - with conn.cursor(cursorclass=DictCursor) as cursor: - query = "SELECT * FROM InbredSet WHERE SpeciesId=%s" - cursor.execute(query, (speciesid,)) - return tuple(cursor.fetchall()) - - return tuple() - -def save_population(conn: mdb.Connection, population_details: dict) -> dict: - """Save the population details to the db.""" - with conn.cursor(cursorclass=DictCursor) as cursor: - cursor.execute( - "INSERT INTO InbredSet(" - "InbredSetId, InbredSetName, Name, SpeciesId, FullName, " - "MenuOrderId, Description" - ") " - "VALUES (" - "%(InbredSetId)s, %(InbredSetName)s, %(Name)s, %(SpeciesId)s, " - "%(FullName)s, %(MenuOrderId)s, %(Description)s" - ")", - { - "MenuOrderId": 0, - "InbredSetId": 0, - **population_details - }) - new_id = cursor.lastrowid - cursor.execute("UPDATE InbredSet SET InbredSetId=%s WHERE Id=%s", - (new_id, new_id)) - return { - **population_details, - "Id": new_id, - "InbredSetId": new_id, - "population_id": new_id - } diff --git a/uploader/db/species.py b/uploader/db/species.py deleted file mode 100644 index 653e59b..0000000 --- a/uploader/db/species.py +++ /dev/null @@ -1,22 +0,0 @@ -"""Database functions for species.""" -import MySQLdb as mdb -from MySQLdb.cursors import DictCursor - -def species(conn: mdb.Connection) -> tuple: - "Retrieve the species from the database." - with conn.cursor(cursorclass=DictCursor) as cursor: - cursor.execute( - "SELECT SpeciesId, SpeciesName, LOWER(Name) AS Name, MenuName, " - "FullName FROM Species") - return tuple(cursor.fetchall()) - - return tuple() - -def species_by_id(conn: mdb.Connection, speciesid) -> dict: - "Retrieve the species from the database by id." - with conn.cursor(cursorclass=DictCursor) as cursor: - cursor.execute( - "SELECT SpeciesId, SpeciesName, LOWER(Name) AS Name, MenuName, " - "FullName FROM Species WHERE SpeciesId=%s", - (speciesid,)) - return cursor.fetchone() diff --git a/uploader/db_utils.py b/uploader/db_utils.py index 5b79762..d31e2c2 100644 --- a/uploader/db_utils.py +++ b/uploader/db_utils.py @@ -7,6 +7,7 @@ from typing import Any, Tuple, Iterator, Callable import MySQLdb as mdb from redis import Redis +from MySQLdb.cursors import Cursor from flask import current_app as app def parse_db_url(db_url) -> Tuple: @@ -43,3 +44,11 @@ def with_redis_connection(func: Callable[[Redis], Any]) -> Any: redisuri = app.config["REDIS_URL"] with Redis.from_url(redisuri, decode_responses=True) as rconn: return func(rconn) + + +def debug_query(cursor: Cursor): + """Debug the actual query run with MySQLdb""" + for attr in ("_executed", "statement", "_last_executed"): + if hasattr(cursor, attr): + logging.debug("MySQLdb QUERY: %s", getattr(cursor, attr)) + break diff --git a/uploader/default_settings.py b/uploader/default_settings.py index 26fe665..1acb247 100644 --- a/uploader/default_settings.py +++ b/uploader/default_settings.py @@ -2,15 +2,12 @@ The default configuration file. The values here should be overridden in the actual configuration file used for the production and staging systems. """ - -import os - -LOG_LEVEL = os.getenv("LOG_LEVEL", "WARNING") +LOG_LEVEL = "WARNING" SECRET_KEY = b"<Please! Please! Please! Change This!>" UPLOAD_FOLDER = "/tmp/qc_app_files" REDIS_URL = "redis://" JOBS_TTL_SECONDS = 1209600 # 14 days -GNQC_REDIS_PREFIX="GNQC" +GNQC_REDIS_PREFIX="gn-uploader" SQL_URI = "" GN2_SERVER_URL = "https://genenetwork.org/" diff --git a/uploader/entry.py b/uploader/entry.py deleted file mode 100644 index 82034ed..0000000 --- a/uploader/entry.py +++ /dev/null @@ -1,131 +0,0 @@ -"""Entry-point module""" -import os -import mimetypes -from typing import Tuple -from zipfile import ZipFile, is_zipfile - -from werkzeug.utils import secure_filename -from flask import ( - flash, - request, - url_for, - redirect, - Blueprint, - render_template, - current_app as app, - send_from_directory) - -from uploader.db import species -from uploader.authorisation import require_login -from uploader.db_utils import with_db_connection -from uploader.oauth2.client import user_logged_in - -entrybp = Blueprint("entry", __name__) - -@entrybp.route("/favicon.ico", methods=["GET"]) -def favicon(): - """Return the favicon.""" - return send_from_directory(os.path.join(app.root_path, "static"), - "images/CITGLogo.png", - mimetype="image/png") - - -def errors(rqst) -> Tuple[str, ...]: - """Return a tuple of the errors found in the request `rqst`. If no error is - found, then an empty tuple is returned.""" - def __filetype_error__(): - return ( - ("Invalid file type provided.",) - if rqst.form.get("filetype") not in ("average", "standard-error") - else tuple()) - - def __file_missing_error__(): - return ( - ("No file was uploaded.",) - if ("qc_text_file" not in rqst.files or - rqst.files["qc_text_file"].filename == "") - else tuple()) - - def __file_mimetype_error__(): - text_file = rqst.files["qc_text_file"] - return ( - ( - ("Invalid file! Expected a tab-separated-values file, or a zip " - "file of the a tab-separated-values file."),) - if text_file.mimetype not in ( - "text/plain", "text/tab-separated-values", - "application/zip") - else tuple()) - - return ( - __filetype_error__() + - (__file_missing_error__() or __file_mimetype_error__())) - -def zip_file_errors(filepath, upload_dir) -> Tuple[str, ...]: - """Check the uploaded zip file for errors.""" - zfile_errors: Tuple[str, ...] = tuple() - if is_zipfile(filepath): - with ZipFile(filepath, "r") as zfile: - infolist = zfile.infolist() - if len(infolist) != 1: - zfile_errors = zfile_errors + ( - ("Expected exactly one (1) member file within the uploaded zip " - f"file. Got {len(infolist)} member files."),) - if len(infolist) == 1 and infolist[0].is_dir(): - zfile_errors = zfile_errors + ( - ("Expected a member text file in the uploaded zip file. Got a " - "directory/folder."),) - - if len(infolist) == 1 and not infolist[0].is_dir(): - zfile.extract(infolist[0], path=upload_dir) - mime = mimetypes.guess_type(f"{upload_dir}/{infolist[0].filename}") - if mime[0] != "text/tab-separated-values": - zfile_errors = zfile_errors + ( - ("Expected the member text file in the uploaded zip file to" - " be a tab-separated file."),) - - return zfile_errors - -@entrybp.route("/", methods=["GET"]) -def index(): - """Load the landing page""" - return render_template("index.html" if user_logged_in() else "login.html") - -@entrybp.route("/upload", methods=["GET", "POST"]) -@require_login -def upload_file(): - """Enables uploading the files""" - if request.method == "GET": - return render_template( - "select_species.html", species=with_db_connection(species)) - - upload_dir = app.config["UPLOAD_FOLDER"] - request_errors = errors(request) - if request_errors: - for error in request_errors: - flash(error, "alert-danger error-expr-data") - return redirect(url_for("entry.upload_file")) - - filename = secure_filename(request.files["qc_text_file"].filename) - if not os.path.exists(upload_dir): - os.mkdir(upload_dir) - - filepath = os.path.join(upload_dir, filename) - request.files["qc_text_file"].save(os.path.join(upload_dir, filename)) - - zip_errors = zip_file_errors(filepath, upload_dir) - if zip_errors: - for error in zip_errors: - flash(error, "alert-danger error-expr-data") - return redirect(url_for("entry.upload_file")) - - return redirect(url_for("parse.parse", - speciesid=request.form["speciesid"], - filename=filename, - filetype=request.form["filetype"])) - -@entrybp.route("/data-review", methods=["GET"]) -@require_login -def data_review(): - """Provide some help on data expectations to the user.""" - return render_template("data_review.html") diff --git a/uploader/expression_data/__init__.py b/uploader/expression_data/__init__.py new file mode 100644 index 0000000..fc8bd41 --- /dev/null +++ b/uploader/expression_data/__init__.py @@ -0,0 +1,2 @@ +"""Package handling upload of files.""" +from .views import exprdatabp diff --git a/uploader/dbinsert.py b/uploader/expression_data/dbinsert.py index 559dc5e..32ca359 100644 --- a/uploader/dbinsert.py +++ b/uploader/expression_data/dbinsert.py @@ -11,11 +11,12 @@ from flask import ( flash, request, url_for, Blueprint, redirect, render_template, current_app as app) +from uploader import jobs from uploader.authorisation import require_login +from uploader.population.models import populations_by_species +from uploader.species.models import all_species, species_by_id +from uploader.platforms.models import platform_by_species_and_id from uploader.db_utils import with_db_connection, database_connection -from uploader.db import species, species_by_id, populations_by_species - -from . import jobs dbinsertbp = Blueprint("dbinsert", __name__) @@ -48,14 +49,6 @@ def genechips(): return {} -def platform_by_id(genechipid:int) -> Union[dict, None]: - "Retrieve the gene platform by id" - with database_connection(app.config["SQL_URI"]) as conn: - with conn.cursor(cursorclass=DictCursor) as cursor: - cursor.execute( - "SELECT * FROM GeneChip WHERE GeneChipId=%s", - (genechipid,)) - return cursor.fetchone() def studies_by_species_and_platform(speciesid:int, genechipid:int) -> tuple: "Retrieve the studies by the related species and gene platform" @@ -107,7 +100,7 @@ def select_platform(): return render_template( "select_platform.html", filename=filename, filetype=job["filetype"], totallines=int(job["currentline"]), - default_species=default_species, species=species(conn), + default_species=default_species, species=all_species(conn), genechips=gchips[default_species], genechips_data=json.dumps(gchips)) return render_error(f"File '{filename}' no longer exists.") @@ -326,37 +319,38 @@ def selected_keys(original: dict, keys: tuple) -> dict: @require_login def final_confirmation(): "Preview the data before triggering entry into the database" - form = request.form - try: - assert form.get("filename"), "filename" - assert form.get("filetype"), "filetype" - assert form.get("species"), "species" - assert form.get("genechipid"), "platform" - assert form.get("studyid"), "study" - assert form.get("datasetid"), "dataset" - - speciesid = form["species"] - genechipid = form["genechipid"] - studyid = form["studyid"] - datasetid=form["datasetid"] - return render_template( - "final_confirmation.html", filename=form["filename"], - filetype=form["filetype"], totallines=form["totallines"], - species=speciesid, genechipid=genechipid, studyid=studyid, - datasetid=datasetid, the_species=selected_keys( - with_db_connection(lambda conn: species_by_id(conn, speciesid)), - ("SpeciesName", "Name", "MenuName")), - platform=selected_keys( - platform_by_id(genechipid), - ("GeneChipName", "Name", "GeoPlatform", "Title", "GO_tree_value")), - study=selected_keys( - study_by_id(studyid), ("Name", "FullName", "ShortName")), - dataset=selected_keys( - dataset_by_id(datasetid), - ("AvgMethodName", "Name", "Name2", "FullName", "ShortName", - "DataScale"))) - except AssertionError as aserr: - return render_error(f"Missing data: {aserr.args[0]}") + with database_connection(app.config["SQL_URI"]) as conn: + form = request.form + try: + assert form.get("filename"), "filename" + assert form.get("filetype"), "filetype" + assert form.get("species"), "species" + assert form.get("genechipid"), "platform" + assert form.get("studyid"), "study" + assert form.get("datasetid"), "dataset" + + speciesid = form["species"] + genechipid = form["genechipid"] + studyid = form["studyid"] + datasetid=form["datasetid"] + return render_template( + "final_confirmation.html", filename=form["filename"], + filetype=form["filetype"], totallines=form["totallines"], + species=speciesid, genechipid=genechipid, studyid=studyid, + datasetid=datasetid, the_species=selected_keys( + with_db_connection(lambda conn: species_by_id(conn, speciesid)), + ("SpeciesName", "Name", "MenuName")), + platform=selected_keys( + platform_by_species_and_id(conn, speciesid, genechipid), + ("GeneChipName", "Name", "GeoPlatform", "Title", "GO_tree_value")), + study=selected_keys( + study_by_id(studyid), ("Name", "FullName", "ShortName")), + dataset=selected_keys( + dataset_by_id(datasetid), + ("AvgMethodName", "Name", "Name2", "FullName", "ShortName", + "DataScale"))) + except AssertionError as aserr: + return render_error(f"Missing data: {aserr.args[0]}") @dbinsertbp.route("/insert-data", methods=["POST"]) @require_login diff --git a/uploader/expression_data/views.py b/uploader/expression_data/views.py new file mode 100644 index 0000000..bbe6538 --- /dev/null +++ b/uploader/expression_data/views.py @@ -0,0 +1,384 @@ +"""Views for expression data""" +import os +import uuid +import mimetypes +from typing import Tuple +from zipfile import ZipFile, is_zipfile + +import jsonpickle +from redis import Redis +from werkzeug.utils import secure_filename +from flask import (flash, + request, + url_for, + redirect, + Blueprint, + current_app as app) + +from quality_control.errors import InvalidValue, DuplicateHeading + +from uploader import jobs +from uploader.datautils import order_by_family +from uploader.ui import make_template_renderer +from uploader.authorisation import require_login +from uploader.species.models import all_species, species_by_id +from uploader.db_utils import with_db_connection, database_connection +from uploader.population.models import (populations_by_species, + population_by_species_and_id) + +exprdatabp = Blueprint("expression-data", __name__) +render_template = make_template_renderer("expression-data") + +def isinvalidvalue(item): + """Check whether item is of type InvalidValue""" + return isinstance(item, InvalidValue) + + +def isduplicateheading(item): + """Check whether item is of type DuplicateHeading""" + return isinstance(item, DuplicateHeading) + + +def errors(rqst) -> Tuple[str, ...]: + """Return a tuple of the errors found in the request `rqst`. If no error is + found, then an empty tuple is returned.""" + def __filetype_error__(): + return ( + ("Invalid file type provided.",) + if rqst.form.get("filetype") not in ("average", "standard-error") + else tuple()) + + def __file_missing_error__(): + return ( + ("No file was uploaded.",) + if ("qc_text_file" not in rqst.files or + rqst.files["qc_text_file"].filename == "") + else tuple()) + + def __file_mimetype_error__(): + text_file = rqst.files["qc_text_file"] + return ( + ( + ("Invalid file! Expected a tab-separated-values file, or a zip " + "file of the a tab-separated-values file."),) + if text_file.mimetype not in ( + "text/plain", "text/tab-separated-values", + "application/zip") + else tuple()) + + return ( + __filetype_error__() + + (__file_missing_error__() or __file_mimetype_error__())) + + +def zip_file_errors(filepath, upload_dir) -> Tuple[str, ...]: + """Check the uploaded zip file for errors.""" + zfile_errors: Tuple[str, ...] = tuple() + if is_zipfile(filepath): + with ZipFile(filepath, "r") as zfile: + infolist = zfile.infolist() + if len(infolist) != 1: + zfile_errors = zfile_errors + ( + ("Expected exactly one (1) member file within the uploaded zip " + f"file. Got {len(infolist)} member files."),) + if len(infolist) == 1 and infolist[0].is_dir(): + zfile_errors = zfile_errors + ( + ("Expected a member text file in the uploaded zip file. Got a " + "directory/folder."),) + + if len(infolist) == 1 and not infolist[0].is_dir(): + zfile.extract(infolist[0], path=upload_dir) + mime = mimetypes.guess_type(f"{upload_dir}/{infolist[0].filename}") + if mime[0] != "text/tab-separated-values": + zfile_errors = zfile_errors + ( + ("Expected the member text file in the uploaded zip file to" + " be a tab-separated file."),) + + return zfile_errors + + +@exprdatabp.route("populations/expression-data", methods=["GET"]) +@require_login +def index(): + """Display the expression data index page.""" + with database_connection(app.config["SQL_URI"]) as conn: + if not bool(request.args.get("species_id")): + return render_template("expression-data/index.html", + species=order_by_family(all_species(conn)), + activelink="expression-data") + species = species_by_id(conn, request.args.get("species_id")) + if not bool(species): + flash("Could not find species selected!", "alert-danger") + return redirect(url_for("species.populations.expression-data.index")) + return redirect(url_for( + "species.populations.expression-data.select_population", + species_id=species["SpeciesId"])) + + +@exprdatabp.route("<int:species_id>/populations/expression-data/select-population", + methods=["GET"]) +@require_login +def select_population(species_id: int): + """Select the expression data's population.""" + with database_connection(app.config["SQL_URI"]) as conn: + species = species_by_id(conn, species_id) + if not bool(species): + flash("No such species!", "alert-danger") + return redirect(url_for("species.populations.expression-data.index")) + + if not bool(request.args.get("population_id")): + return render_template("expression-data/select-population.html", + species=species, + populations=order_by_family( + populations_by_species(conn, species_id), + order_key="FamilyOrder"), + activelink="expression-data") + + population = population_by_species_and_id( + conn, species_id, request.args.get("population_id")) + if not bool(population): + flash("No such population!", "alert-danger") + return redirect(url_for( + "species.populations.expression-data.select_population", + species_id=species_id)) + + return redirect(url_for("species.populations.expression-data.upload_file", + species_id=species_id, + population_id=population["Id"])) + + +@exprdatabp.route("<int:species_id>/populations/<int:population_id>/" + "expression-data/upload", + methods=["GET", "POST"]) +@require_login +def upload_file(species_id: int, population_id: int): + """Enables uploading the files""" + with database_connection(app.config["SQL_URI"]) as conn: + species = species_by_id(conn, species_id) + population = population_by_species_and_id(conn, species_id, population_id) + if request.method == "GET": + return render_template("expression-data/select-file.html", + species=species, + population=population) + + upload_dir = app.config["UPLOAD_FOLDER"] + request_errors = errors(request) + if request_errors: + for error in request_errors: + flash(error, "alert-danger error-expr-data") + return redirect(url_for("species.populations.expression-data.upload_file")) + + filename = secure_filename( + request.files["qc_text_file"].filename)# type: ignore[arg-type] + if not os.path.exists(upload_dir): + os.mkdir(upload_dir) + + filepath = os.path.join(upload_dir, filename) + request.files["qc_text_file"].save(os.path.join(upload_dir, filename)) + + zip_errors = zip_file_errors(filepath, upload_dir) + if zip_errors: + for error in zip_errors: + flash(error, "alert-danger error-expr-data") + return redirect(url_for("species.populations.expression-data.index.upload_file")) + + return redirect(url_for("species.populations.expression-data.parse_file", + species_id=species_id, + population_id=population_id, + filename=filename, + filetype=request.form["filetype"])) + + +@exprdatabp.route("/data-review", methods=["GET"]) +@require_login +def data_review(): + """Provide some help on data expectations to the user.""" + return render_template("expression-data/data-review.html") + + +@exprdatabp.route( + "<int:species_id>/populations/<int:population_id>/expression-data/parse", + methods=["GET"]) +@require_login +def parse_file(species_id: int, population_id: int): + """Trigger file parsing""" + _errors = False + filename = request.args.get("filename") + filetype = request.args.get("filetype") + + species = with_db_connection(lambda con: species_by_id(con, species_id)) + if not bool(species): + flash("No such species.", "alert-danger") + _errors = True + + if filename is None: + flash("No file provided", "alert-danger") + _errors = True + + if filetype is None: + flash("No filetype provided", "alert-danger") + _errors = True + + if filetype not in ("average", "standard-error"): + flash("Invalid filetype provided", "alert-danger") + _errors = True + + if filename: + filepath = os.path.join(app.config["UPLOAD_FOLDER"], filename) + if not os.path.exists(filepath): + flash("Selected file does not exist (any longer)", "alert-danger") + _errors = True + + if _errors: + return redirect(url_for("species.populations.expression-data.upload_file")) + + redisurl = app.config["REDIS_URL"] + with Redis.from_url(redisurl, decode_responses=True) as rconn: + job = jobs.launch_job( + jobs.build_file_verification_job( + rconn, app.config["SQL_URI"], redisurl, + species_id, filepath, filetype,# type: ignore[arg-type] + app.config["JOBS_TTL_SECONDS"]), + redisurl, + f"{app.config['UPLOAD_FOLDER']}/job_errors") + + return redirect(url_for("species.populations.expression-data.parse_status", + species_id=species_id, + population_id=population_id, + job_id=job["jobid"])) + + +@exprdatabp.route( + "<int:species_id>/populations/<int:population_id>/expression-data/parse/" + "status/<uuid:job_id>", + methods=["GET"]) +@require_login +def parse_status(species_id: int, population_id: int, job_id: str): + "Retrieve the status of the job" + with Redis.from_url(app.config["REDIS_URL"], decode_responses=True) as rconn: + try: + job = jobs.job(rconn, jobs.jobsnamespace(), job_id) + except jobs.JobNotFound as _exc: + return render_template("no_such_job.html", job_id=job_id), 400 + + error_filename = jobs.error_filename( + job_id, f"{app.config['UPLOAD_FOLDER']}/job_errors") + if os.path.exists(error_filename): + stat = os.stat(error_filename) + if stat.st_size > 0: + return redirect(url_for("parse.fail", job_id=job_id)) + + job_id = job["jobid"] + progress = float(job["percent"]) + status = job["status"] + filename = job.get("filename", "uploaded file") + _errors = jsonpickle.decode( + job.get("errors", jsonpickle.encode(tuple()))) + if status in ("success", "aborted"): + return redirect(url_for("species.populations.expression-data.results", + species_id=species_id, + population_id=population_id, + job_id=job_id)) + + if status == "parse-error": + return redirect(url_for("species.populations.expression-data.fail", job_id=job_id)) + + app.jinja_env.globals.update( + isinvalidvalue=isinvalidvalue, + isduplicateheading=isduplicateheading) + return render_template( + "expression-data/job-progress.html", + job_id = job_id, + job_status = status, + progress = progress, + message = job.get("message", ""), + job_name = f"Parsing '{filename}'", + errors=_errors, + species=with_db_connection( + lambda conn: species_by_id(conn, species_id)), + population=with_db_connection( + lambda conn: population_by_species_and_id( + conn, species_id, population_id))) + + +@exprdatabp.route( + "<int:species_id>/populations/<int:population_id>/expression-data/parse/" + "<uuid:job_id>/results", + methods=["GET"]) +@require_login +def results(species_id: int, population_id: int, job_id: uuid.UUID): + """Show results of parsing...""" + with Redis.from_url(app.config["REDIS_URL"], decode_responses=True) as rconn: + job = jobs.job(rconn, jobs.jobsnamespace(), job_id) + + if job: + filename = job["filename"] + _errors = jsonpickle.decode(job.get("errors", jsonpickle.encode(tuple()))) + app.jinja_env.globals.update( + isinvalidvalue=isinvalidvalue, + isduplicateheading=isduplicateheading) + return render_template( + "expression-data/parse-results.html", + errors=_errors, + job_name = f"Parsing '{filename}'", + user_aborted = job.get("user_aborted"), + job_id=job["jobid"], + species=with_db_connection( + lambda conn: species_by_id(conn, species_id)), + population=with_db_connection( + lambda conn: population_by_species_and_id( + conn, species_id, population_id))) + + return render_template("expression-data/no-such-job.html", job_id=job_id) + + +@exprdatabp.route( + "<int:species_id>/populations/<int:population_id>/expression-data/parse/" + "<uuid:job_id>/fail", + methods=["GET"]) +@require_login +def fail(species_id: int, population_id: int, job_id: str): + """Handle parsing failure""" + with Redis.from_url(app.config["REDIS_URL"], decode_responses=True) as rconn: + job = jobs.job(rconn, jobs.jobsnamespace(), job_id) + + if job: + error_filename = jobs.error_filename( + job_id, f"{app.config['UPLOAD_FOLDER']}/job_errors") + if os.path.exists(error_filename): + stat = os.stat(error_filename) + if stat.st_size > 0: + return render_template( + "worker_failure.html", job_id=job_id) + + return render_template("parse_failure.html", job=job) + + return render_template("expression-data/no-such-job.html", + **with_db_connection(lambda conn: { + "species_id": species_by_id(conn, species_id), + "population_id": population_by_species_and_id( + conn, species_id, population_id)}), + job_id=job_id) + + +@exprdatabp.route( + "<int:species_id>/populations/<int:population_id>/expression-data/parse/" + "abort", + methods=["POST"]) +@require_login +def abort(species_id: int, population_id: int): + """Handle user request to abort file processing""" + job_id = request.form["job_id"] + + with Redis.from_url(app.config["REDIS_URL"], decode_responses=True) as rconn: + job = jobs.job(rconn, jobs.jobsnamespace(), job_id) + + if job: + rconn.hset(name=jobs.job_key(jobs.jobsnamespace(), job_id), + key="user_aborted", + value=int(True)) + + return redirect(url_for("species.populations.expression-data.parse_status", + species_id=species_id, + population_id=population_id, + job_id=job_id)) diff --git a/uploader/files.py b/uploader/files.py index b163612..d37a53e 100644 --- a/uploader/files.py +++ b/uploader/files.py @@ -1,7 +1,9 @@ """Utilities to deal with uploaded files.""" import hashlib from pathlib import Path +from typing import Iterator from datetime import datetime + from flask import current_app from werkzeug.utils import secure_filename @@ -21,6 +23,27 @@ def save_file(fileobj: FileStorage, upload_dir: Path) -> Path: fileobj.save(filepath) return filepath + def fullpath(filename: str): """Get a file's full path. This makes use of `flask.current_app`.""" return Path(current_app.config["UPLOAD_FOLDER"], filename).absolute() + + +def chunked_binary_read(filepath: Path, chunksize: int = 2048) -> Iterator: + """Read a file in binary mode in chunks.""" + with open(filepath, "rb") as inputfile: + while True: + data = inputfile.read(chunksize) + if data != b"": + yield data + continue + break + + +def sha256_digest_over_file(filepath: Path) -> str: + """Compute the sha256 digest over a file's contents.""" + filehash = hashlib.sha256() + for chunk in chunked_binary_read(filepath): + filehash.update(chunk) + + return filehash.hexdigest() diff --git a/uploader/genotypes/__init__.py b/uploader/genotypes/__init__.py new file mode 100644 index 0000000..d0025d6 --- /dev/null +++ b/uploader/genotypes/__init__.py @@ -0,0 +1 @@ +"""The Genotypes module.""" diff --git a/uploader/genotypes/models.py b/uploader/genotypes/models.py new file mode 100644 index 0000000..44c98b1 --- /dev/null +++ b/uploader/genotypes/models.py @@ -0,0 +1,101 @@ +"""Functions for handling genotypes.""" +from typing import Optional +from datetime import datetime + +import MySQLdb as mdb +from MySQLdb.cursors import Cursor, DictCursor + +from uploader.db_utils import debug_query + +def genocode_by_population( + conn: mdb.Connection, population_id: int) -> tuple[dict, ...]: + """Get the allele/genotype codes.""" + with conn.cursor(cursorclass=DictCursor) as cursor: + cursor.execute("SELECT * FROM GenoCode WHERE InbredSetId=%s", + (population_id,)) + return tuple(dict(item) for item in cursor.fetchall()) + + +def genotype_markers_count(conn: mdb.Connection, species_id: int) -> int: + """Find the total count of the genotype markers for a species.""" + with conn.cursor(cursorclass=DictCursor) as cursor: + cursor.execute( + "SELECT COUNT(Name) AS markers_count FROM Geno WHERE SpeciesId=%s", + (species_id,)) + return int(cursor.fetchone()["markers_count"]) + + +def genotype_markers( + conn: mdb.Connection, + species_id: int, + offset: int = 0, + limit: Optional[int] = None +) -> tuple[dict, ...]: + """Retrieve markers from the database.""" + _query = "SELECT * FROM Geno WHERE SpeciesId=%s" + if bool(limit) and limit > 0:# type: ignore[operator] + _query = _query + f" LIMIT {limit} OFFSET {offset}" + + with conn.cursor(cursorclass=DictCursor) as cursor: + cursor.execute(_query, (species_id,)) + debug_query(cursor) + return tuple(dict(row) for row in cursor.fetchall()) + + +def genotype_dataset( + conn: mdb.Connection, + species_id: int, + population_id: int, + dataset_id: Optional[int] = None +) -> Optional[dict]: + """Retrieve genotype datasets from the database. + + Apparently, you should only ever have one genotype dataset for a population. + """ + _query = ( + "SELECT gf.* FROM Species AS s INNER JOIN InbredSet AS iset " + "ON s.Id=iset.SpeciesId INNER JOIN GenoFreeze AS gf " + "ON iset.Id=gf.InbredSetId " + "WHERE s.Id=%s AND iset.Id=%s") + _params = (species_id, population_id) + if bool(dataset_id): + _query = _query + " AND gf.Id=%s" + _params = _params + (dataset_id,)# type: ignore[assignment] + + with conn.cursor(cursorclass=DictCursor) as cursor: + cursor.execute(_query, _params) + debug_query(cursor) + result = cursor.fetchone() + if bool(result): + return dict(result) + return None + + +def save_new_dataset( + cursor: Cursor, + population_id: int, + name: str, + fullname: str, + shortname: str +) -> dict: + """Save a new genotype dataset into the database.""" + params = { + "InbredSetId": population_id, + "Name": name, + "FullName": fullname, + "ShortName": shortname, + "CreateTime": datetime.now().date().isoformat(), + "public": 2, + "confidentiality": 0, + "AuthorisedUsers": None + } + cursor.execute( + "INSERT INTO GenoFreeze(" + "Name, FullName, ShortName, CreateTime, public, InbredSetId, " + "confidentiality, AuthorisedUsers" + ") VALUES (" + "%(Name)s, %(FullName)s, %(ShortName)s, %(CreateTime)s, %(public)s, " + "%(InbredSetId)s, %(confidentiality)s, %(AuthorisedUsers)s" + ")", + params) + return {**params, "Id": cursor.lastrowid} diff --git a/uploader/genotypes/views.py b/uploader/genotypes/views.py new file mode 100644 index 0000000..0821eca --- /dev/null +++ b/uploader/genotypes/views.py @@ -0,0 +1,204 @@ +"""Views for the genotypes.""" +from MySQLdb.cursors import DictCursor +from flask import (flash, + request, + url_for, + redirect, + Blueprint, + render_template, + current_app as app) + +from uploader.ui import make_template_renderer +from uploader.oauth2.client import oauth2_post +from uploader.authorisation import require_login +from uploader.db_utils import database_connection +from uploader.species.models import all_species, species_by_id +from uploader.monadic_requests import make_either_error_handler +from uploader.request_checks import with_species, with_population +from uploader.datautils import safe_int, order_by_family, enumerate_sequence +from uploader.population.models import (populations_by_species, + population_by_species_and_id) + +from .models import (genotype_markers, + genotype_dataset, + save_new_dataset, + genotype_markers_count, + genocode_by_population) + +genotypesbp = Blueprint("genotypes", __name__) +render_template = make_template_renderer("genotypes") + +@genotypesbp.route("populations/genotypes", methods=["GET"]) +@require_login +def index(): + """Direct entry-point for genotypes.""" + with database_connection(app.config["SQL_URI"]) as conn: + if not bool(request.args.get("species_id")): + return render_template("genotypes/index.html", + species=order_by_family(all_species(conn)), + activelink="genotypes") + species = species_by_id(conn, request.args.get("species_id")) + if not bool(species): + flash(f"Could not find species with ID '{request.args.get('species_id')}'!", + "alert-danger") + return redirect(url_for("species.populations.genotypes.index")) + return redirect(url_for("species.populations.genotypes.select_population", + species_id=species["SpeciesId"])) + + +@genotypesbp.route("/<int:species_id>/populations/genotypes/select-population", + methods=["GET"]) +@require_login +@with_species(redirect_uri="species.populations.genotypes.index") +def select_population(species: dict, species_id: int): + """Select the population under which the genotypes go.""" + with database_connection(app.config["SQL_URI"]) as conn: + if not bool(request.args.get("population_id")): + return render_template("genotypes/select-population.html", + species=species, + populations=order_by_family( + populations_by_species(conn, species_id), + order_key="FamilyOrder"), + activelink="genotypes") + + population = population_by_species_and_id( + conn, species_id, request.args.get("population_id")) + if not bool(population): + flash("Invalid population selected!", "alert-danger") + return redirect(url_for( + "species.populations.genotypes.select_population", + species_id=species_id)) + + return redirect(url_for("species.populations.genotypes.list_genotypes", + species_id=species_id, + population_id=population["Id"])) + + +@genotypesbp.route( + "/<int:species_id>/populations/<int:population_id>/genotypes", + methods=["GET"]) +@require_login +@with_population(species_redirect_uri="species.populations.genotypes.index", + redirect_uri="species.populations.genotypes.select_population") +def list_genotypes(species: dict, population: dict, **kwargs):# pylint: disable=[unused-argument] + """List genotype details for species and population.""" + with database_connection(app.config["SQL_URI"]) as conn: + return render_template("genotypes/list-genotypes.html", + species=species, + population=population, + genocode=genocode_by_population( + conn, population["Id"]), + total_markers=genotype_markers_count( + conn, species["SpeciesId"]), + dataset=genotype_dataset(conn, + species["SpeciesId"], + population["Id"]), + activelink="list-genotypes") + + +@genotypesbp.route("/<int:species_id>/genotypes/list-markers", methods=["GET"]) +@require_login +@with_species(redirect_uri="species.populations.genotypes.index") +def list_markers(species: dict, **kwargs):# pylint: disable=[unused-argument] + """List a species' genetic markers.""" + with database_connection(app.config["SQL_URI"]) as conn: + start_from = max(safe_int(request.args.get("start_from") or 0), 0) + count = safe_int(request.args.get("count") or 20) + return render_template("genotypes/list-markers.html", + species=species, + total_markers=genotype_markers_count( + conn, species["SpeciesId"]), + start_from=start_from, + count=count, + markers=enumerate_sequence( + genotype_markers(conn, + species["SpeciesId"], + offset=start_from, + limit=count), + start=start_from+1), + activelink="list-markers") + +@genotypesbp.route( + "/<int:species_id>/populations/<int:population_id>/genotypes/datasets/" + "<int:dataset_id>/view", + methods=["GET"]) +@require_login +def view_dataset(species_id: int, population_id: int, dataset_id: int): + """View details regarding a specific dataset.""" + with database_connection(app.config["SQL_URI"]) as conn: + species = species_by_id(conn, species_id) + if not bool(species): + flash("Invalid species provided!", "alert-danger") + return redirect(url_for("species.populations.genotypes.index")) + + population = population_by_species_and_id( + conn, species_id, population_id) + if not bool(population): + flash("Invalid population selected!", "alert-danger") + return redirect(url_for( + "species.populations.genotypes.select_population", + species_id=species_id)) + + dataset = genotype_dataset(conn, species_id, population_id, dataset_id) + if not bool(dataset): + flash("Could not find such a dataset!", "alert-danger") + return redirect(url_for( + "species.populations.genotypes.list_genotypes", + species_id=species_id, + population_id=population_id)) + + return render_template("genotypes/view-dataset.html", + species=species, + population=population, + dataset=dataset, + activelink="view-dataset") + + +@genotypesbp.route( + "/<int:species_id>/populations/<int:population_id>/genotypes/datasets/" + "create", + methods=["GET", "POST"]) +@require_login +@with_population(species_redirect_uri="species.populations.genotypes.index", + redirect_uri="species.populations.genotypes.select_population") +def create_dataset(species: dict, population: dict, **kwargs):# pylint: disable=[unused-argument] + """Create a genotype dataset.""" + with (database_connection(app.config["SQL_URI"]) as conn, + conn.cursor(cursorclass=DictCursor) as cursor): + if request.method == "GET": + return render_template("genotypes/create-dataset.html", + species=species, + population=population, + activelink="create-dataset") + + form = request.form + new_dataset = save_new_dataset( + cursor, + population["Id"], + form["geno-dataset-name"], + form["geno-dataset-fullname"], + form["geno-dataset-shortname"]) + + def __success__(_success): + flash("Successfully created genotype dataset.", "alert-success") + return redirect(url_for( + "species.populations.genotypes.list_genotypes", + species_id=species["SpeciesId"], + population_id=population["Id"])) + + return oauth2_post( + "auth/resource/genotypes/create", + json={ + **dict(request.form), + "species_id": species["SpeciesId"], + "population_id": population["Id"], + "dataset_id": new_dataset["Id"], + "dataset_name": form["geno-dataset-name"], + "dataset_fullname": form["geno-dataset-fullname"], + "dataset_shortname": form["geno-dataset-shortname"], + "public": "on" + } + ).either( + make_either_error_handler( + "There was an error creating the genotype dataset."), + __success__) diff --git a/uploader/input_validation.py b/uploader/input_validation.py index 9abe742..627c69e 100644 --- a/uploader/input_validation.py +++ b/uploader/input_validation.py @@ -1,14 +1,19 @@ """Input validation utilities""" +import re +import json +import base64 from typing import Any def is_empty_string(value: str) -> bool: """Check whether as string is empty""" return (isinstance(value, str) and value.strip() == "") + def is_empty_input(value: Any) -> bool: """Check whether user provided an empty value.""" return (value is None or is_empty_string(value)) + def is_integer_input(value: Any) -> bool: """ Check whether user provided a value that can be parsed into an integer. @@ -25,3 +30,42 @@ def is_integer_input(value: Any) -> bool: __is_int__(value, 10) or __is_int__(value, 8) or __is_int__(value, 16)))) + + +def is_valid_representative_name(repr_name: str) -> bool: + """ + Check whether the given representative name is a valid according to our rules. + + Parameters + ---------- + repr_name: a string of characters. + + Checks For + ---------- + * The name MUST start with an alphabet [a-zA-Z] + * The name MUST end with an alphabet [a-zA-Z] or number [0-9] + * The name MUST be composed of alphabets [a-zA-Z], numbers [0-9], + underscores (_) and/or hyphens (-). + + Returns + ------- + Boolean indicating whether or not the name is valid. + """ + pattern = re.compile(r"^[a-zA-Z]+[a-zA-Z0-9_-]*[a-zA-Z0-9]$") + return bool(pattern.match(repr_name)) + + +def encode_errors(errors: tuple[tuple[str, str], ...], form) -> bytes: + """Encode form errors into base64 string.""" + return base64.b64encode( + json.dumps({ + "errors": dict(errors), + "original_formdata": dict(form) + }).encode("utf8")) + + +def decode_errors(errorstr) -> dict[str, dict]: + """Decode errors from base64 string""" + if not bool(errorstr): + return {"errors": {}, "original_formdata": {}} + return json.loads(base64.b64decode(errorstr.encode("utf8")).decode("utf8")) diff --git a/uploader/jobs.py b/uploader/jobs.py index 21889da..4a3fc80 100644 --- a/uploader/jobs.py +++ b/uploader/jobs.py @@ -10,7 +10,7 @@ from typing import Union, Optional from redis import Redis from flask import current_app as app -JOBS_PREFIX = "JOBS" +JOBS_PREFIX = "jobs" class JobNotFound(Exception): """Raised if we try to retrieve a non-existent job.""" diff --git a/uploader/monadic_requests.py b/uploader/monadic_requests.py index aa34951..c492df5 100644 --- a/uploader/monadic_requests.py +++ b/uploader/monadic_requests.py @@ -5,13 +5,12 @@ from typing import Union, Optional, Callable import requests from requests.models import Response from pymonad.either import Left, Right, Either -from flask import ( - flash, - request, - redirect, - render_template, - current_app as app, - escape as flask_escape) +from flask import (flash, + request, + redirect, + render_template, + current_app as app, + escape as flask_escape) # HTML Status codes indicating a successful request. SUCCESS_CODES = (200, 201, 202, 203, 204, 205, 206, 207, 208, 226) @@ -84,3 +83,22 @@ def post(url, data=None, json=None, **kwargs) -> Either: return Left(resp) except requests.exceptions.RequestException as exc: return Left(exc) + + +def make_either_error_handler(msg): + """Make generic error handler for pymonads Either objects.""" + def __fail__(error): + if issubclass(type(error), Exception): + app.logger.debug("\n\n%s (Exception)\n\n", msg, exc_info=True) + raise error + if issubclass(type(error), Response): + try: + _data = error.json() + except Exception as _exc: + raise Exception(error.content) from _exc + raise Exception(_data) + + app.logger.debug("\n\n%s\n\n", msg) + raise Exception(error) + + return __fail__ diff --git a/uploader/oauth2/client.py b/uploader/oauth2/client.py index a3e4ba3..e7128de 100644 --- a/uploader/oauth2/client.py +++ b/uploader/oauth2/client.py @@ -1,5 +1,7 @@ """OAuth2 client utilities.""" import json +import time +import random from datetime import datetime, timedelta from urllib.parse import urljoin, urlparse @@ -8,10 +10,9 @@ from flask import request, current_app as app from pymonad.either import Left, Right, Either -from authlib.jose import jwt from authlib.common.urls import url_decode -from authlib.jose import KeySet, JsonWebKey from authlib.jose.errors import BadSignatureError +from authlib.jose import KeySet, JsonWebKey, JsonWebToken from authlib.integrations.requests_client import OAuth2Session from uploader import session @@ -36,49 +37,41 @@ def oauth2_clientsecret(): return app.config["OAUTH2_CLIENT_SECRET"] -def __make_token_validator__(keys: KeySet): - """Make a token validator function.""" - def __validator__(token: dict): - for key in keys.keys: - try: - jwt.decode(token["access_token"], key) - return Right(token) - except BadSignatureError: - pass - - return Left("INVALID-TOKEN") - - return __validator__ - - -def __validate_token__(sess_info): - """Validate that the token is really from the auth server.""" - info = sess_info - info["user"]["token"] = info["user"]["token"].then(__make_token_validator__( - KeySet([JsonWebKey.import_key(key) for key in info.get( - "auth_server_jwks", {}).get( - "jwks", {"keys": []})["keys"]]))) - return session.save_session_info(info) - - -def __update_auth_server_jwks__(sess_info): - """Updates the JWKs every 2 hours or so.""" - jwks = sess_info.get("auth_server_jwks") - if bool(jwks): - last_updated = jwks.get("last-updated") - now = datetime.now().timestamp() - if bool(last_updated) and (now - last_updated) < timedelta(hours=2).seconds: - return __validate_token__({**sess_info, "auth_server_jwks": jwks}) - - jwksuri = urljoin(authserver_uri(), "auth/public-jwks") - return __validate_token__({ - **sess_info, - "auth_server_jwks": { +def __fetch_auth_server_jwks__() -> KeySet: + """Fetch the JWKs from the auth server.""" + return KeySet([ + JsonWebKey.import_key(key) + for key in requests.get( + urljoin(authserver_uri(), "auth/public-jwks") + ).json()["jwks"]]) + + +def __update_auth_server_jwks__(jwks) -> KeySet: + """Update the JWKs from the servers if necessary.""" + last_updated = jwks["last-updated"] + now = datetime.now().timestamp() + # Maybe the `two_hours` variable below can be made into a configuration + # variable and passed in to this function + two_hours = timedelta(hours=2).seconds + if bool(last_updated) and (now - last_updated) < two_hours: + return jwks["jwks"] + + return session.set_auth_server_jwks(__fetch_auth_server_jwks__()) + + +def auth_server_jwks() -> KeySet: + """Fetch the auth-server JSON Web Keys information.""" + _jwks = session.session_info().get("auth_server_jwks") or {} + if bool(_jwks): + return __update_auth_server_jwks__({ + "last-updated": _jwks["last-updated"], "jwks": KeySet([ - JsonWebKey.import_key(key) - for key in requests.get(jwksuri).json()["jwks"]]).as_dict(), - "last-updated": datetime.now().timestamp() - } + JsonWebKey.import_key(key) for key in _jwks.get( + "jwks", {"keys": []})["keys"]]) + }) + + return __update_auth_server_jwks__({ + "last-updated": (datetime.now() - timedelta(hours=3)).timestamp() }) @@ -111,8 +104,43 @@ def oauth2_client(): ("client_secret_post", __json_auth__)) return client - __update_auth_server_jwks__(session.session_info()) - return session.user_token().either( + def __token_expired__(token): + """Check whether the token has expired.""" + jwks = auth_server_jwks() + if bool(jwks): + for jwk in jwks.keys: + try: + jwt = JsonWebToken(["RS256"]).decode( + token["access_token"], key=jwk) + return datetime.now().timestamp() > jwt["exp"] + except BadSignatureError as _bse: + pass + + return False + + def __delay__(): + """Do a tiny delay.""" + time.sleep(random.choice(tuple(i/1000.0 for i in range(0,100)))) + + def __refresh_token__(token): + """Refresh the token if necessary — synchronise amongst threads.""" + if __token_expired__(token): + __delay__() + if session.is_token_refreshing(): + while session.is_token_refreshing(): + __delay__() + + return session.user_token().either(None, lambda _tok: _tok) + + session.toggle_token_refreshing() + _client = __client__(token) + _client.get(urljoin(authserver_uri(), "auth/user/")) + session.toggle_token_refreshing() + return _client.token + + return token + + return session.user_token().then(__refresh_token__).either( lambda _notok: __client__(None), __client__) @@ -163,7 +191,7 @@ def oauth2_get(url, **kwargs) -> Either: return Right(resp.json()) return Left(resp) except Exception as exc:#pylint: disable=[broad-except] - app.logger.error("Error retriving data from auth server: (GET %s)", + app.logger.error("Error retrieving data from auth server: (GET %s)", _uri, exc_info=True) return Left(exc) @@ -195,7 +223,7 @@ def oauth2_post(url, data=None, json=None, **kwargs):#pylint: disable=[redefined return Right(resp.json()) return Left(resp) except Exception as exc:#pylint: disable=[broad-except] - app.logger.error("Error retriving data from auth server: (POST %s)", + app.logger.error("Error retrieving data from auth server: (POST %s)", _uri, exc_info=True) return Left(exc) diff --git a/uploader/parse.py b/uploader/parse.py deleted file mode 100644 index dea4f95..0000000 --- a/uploader/parse.py +++ /dev/null @@ -1,178 +0,0 @@ -"""File parsing module""" -import os - -import jsonpickle -from redis import Redis -from flask import flash, request, url_for, redirect, Blueprint, render_template -from flask import current_app as app - -from quality_control.errors import InvalidValue, DuplicateHeading - -from uploader import jobs -from uploader.dbinsert import species_by_id -from uploader.db_utils import with_db_connection -from uploader.authorisation import require_login - -parsebp = Blueprint("parse", __name__) - -def isinvalidvalue(item): - """Check whether item is of type InvalidValue""" - return isinstance(item, InvalidValue) - -def isduplicateheading(item): - """Check whether item is of type DuplicateHeading""" - return isinstance(item, DuplicateHeading) - -@parsebp.route("/parse", methods=["GET"]) -@require_login -def parse(): - """Trigger file parsing""" - errors = False - speciesid = request.args.get("speciesid") - filename = request.args.get("filename") - filetype = request.args.get("filetype") - if speciesid is None: - flash("No species selected", "alert-error error-expr-data") - errors = True - else: - try: - speciesid = int(speciesid) - species = with_db_connection( - lambda con: species_by_id(con, speciesid)) - if not bool(species): - flash("No such species.", "alert-error error-expr-data") - errors = True - except ValueError: - flash("Invalid speciesid provided. Expected an integer.", - "alert-error error-expr-data") - errors = True - - if filename is None: - flash("No file provided", "alert-error error-expr-data") - errors = True - - if filetype is None: - flash("No filetype provided", "alert-error error-expr-data") - errors = True - - if filetype not in ("average", "standard-error"): - flash("Invalid filetype provided", "alert-error error-expr-data") - errors = True - - if filename: - filepath = os.path.join(app.config["UPLOAD_FOLDER"], filename) - if not os.path.exists(filepath): - flash("Selected file does not exist (any longer)", - "alert-error error-expr-data") - errors = True - - if errors: - return redirect(url_for("entry.upload_file")) - - redisurl = app.config["REDIS_URL"] - with Redis.from_url(redisurl, decode_responses=True) as rconn: - job = jobs.launch_job( - jobs.build_file_verification_job( - rconn, app.config["SQL_URI"], redisurl, - speciesid, filepath, filetype, - app.config["JOBS_TTL_SECONDS"]), - redisurl, - f"{app.config['UPLOAD_FOLDER']}/job_errors") - - return redirect(url_for("parse.parse_status", job_id=job["jobid"])) - -@parsebp.route("/status/<job_id>", methods=["GET"]) -def parse_status(job_id: str): - "Retrieve the status of the job" - with Redis.from_url(app.config["REDIS_URL"], decode_responses=True) as rconn: - try: - job = jobs.job(rconn, jobs.jobsnamespace(), job_id) - except jobs.JobNotFound as _exc: - return render_template("no_such_job.html", job_id=job_id), 400 - - error_filename = jobs.error_filename( - job_id, f"{app.config['UPLOAD_FOLDER']}/job_errors") - if os.path.exists(error_filename): - stat = os.stat(error_filename) - if stat.st_size > 0: - return redirect(url_for("parse.fail", job_id=job_id)) - - job_id = job["jobid"] - progress = float(job["percent"]) - status = job["status"] - filename = job.get("filename", "uploaded file") - errors = jsonpickle.decode( - job.get("errors", jsonpickle.encode(tuple()))) - if status in ("success", "aborted"): - return redirect(url_for("parse.results", job_id=job_id)) - - if status == "parse-error": - return redirect(url_for("parse.fail", job_id=job_id)) - - app.jinja_env.globals.update( - isinvalidvalue=isinvalidvalue, - isduplicateheading=isduplicateheading) - return render_template( - "job_progress.html", - job_id = job_id, - job_status = status, - progress = progress, - message = job.get("message", ""), - job_name = f"Parsing '{filename}'", - errors=errors) - -@parsebp.route("/results/<job_id>", methods=["GET"]) -def results(job_id: str): - """Show results of parsing...""" - with Redis.from_url(app.config["REDIS_URL"], decode_responses=True) as rconn: - job = jobs.job(rconn, jobs.jobsnamespace(), job_id) - - if job: - filename = job["filename"] - errors = jsonpickle.decode(job.get("errors", jsonpickle.encode(tuple()))) - app.jinja_env.globals.update( - isinvalidvalue=isinvalidvalue, - isduplicateheading=isduplicateheading) - return render_template( - "parse_results.html", - errors=errors, - job_name = f"Parsing '{filename}'", - user_aborted = job.get("user_aborted"), - job_id=job["jobid"]) - - return render_template("no_such_job.html", job_id=job_id) - -@parsebp.route("/fail/<job_id>", methods=["GET"]) -def fail(job_id: str): - """Handle parsing failure""" - with Redis.from_url(app.config["REDIS_URL"], decode_responses=True) as rconn: - job = jobs.job(rconn, jobs.jobsnamespace(), job_id) - - if job: - error_filename = jobs.error_filename( - job_id, f"{app.config['UPLOAD_FOLDER']}/job_errors") - if os.path.exists(error_filename): - stat = os.stat(error_filename) - if stat.st_size > 0: - return render_template( - "worker_failure.html", job_id=job_id) - - return render_template("parse_failure.html", job=job) - - return render_template("no_such_job.html", job_id=job_id) - -@parsebp.route("/abort", methods=["POST"]) -@require_login -def abort(): - """Handle user request to abort file processing""" - job_id = request.form["job_id"] - - with Redis.from_url(app.config["REDIS_URL"], decode_responses=True) as rconn: - job = jobs.job(rconn, jobs.jobsnamespace(), job_id) - - if job: - rconn.hset(name=jobs.job_key(jobs.jobsnamespace(), job_id), - key="user_aborted", - value=int(True)) - - return redirect(url_for("parse.parse_status", job_id=job_id)) diff --git a/uploader/phenotypes/__init__.py b/uploader/phenotypes/__init__.py new file mode 100644 index 0000000..c17d32c --- /dev/null +++ b/uploader/phenotypes/__init__.py @@ -0,0 +1,2 @@ +"""Package for handling ('classical') phenotype data""" +from .views import phenotypesbp diff --git a/uploader/phenotypes/models.py b/uploader/phenotypes/models.py new file mode 100644 index 0000000..9324601 --- /dev/null +++ b/uploader/phenotypes/models.py @@ -0,0 +1,232 @@ +"""Database and utility functions for phenotypes.""" +from typing import Optional +from functools import reduce +from datetime import datetime + +import MySQLdb as mdb +from MySQLdb.cursors import Cursor, DictCursor + +from uploader.db_utils import debug_query + +def datasets_by_population( + conn: mdb.Connection, + species_id: int, + population_id: int +) -> tuple[dict, ...]: + """Retrieve all of a population's phenotype studies.""" + with conn.cursor(cursorclass=DictCursor) as cursor: + cursor.execute( + "SELECT s.SpeciesId, pf.* FROM Species AS s " + "INNER JOIN InbredSet AS iset ON s.Id=iset.SpeciesId " + "INNER JOIN PublishFreeze AS pf ON iset.Id=pf.InbredSetId " + "WHERE s.Id=%s AND iset.Id=%s;", + (species_id, population_id)) + return tuple(dict(row) for row in cursor.fetchall()) + + +def dataset_by_id(conn: mdb.Connection, + species_id: int, + population_id: int, + dataset_id: int) -> dict: + """Fetch dataset details by identifier""" + with conn.cursor(cursorclass=DictCursor) as cursor: + cursor.execute( + "SELECT s.SpeciesId, pf.* FROM Species AS s " + "INNER JOIN InbredSet AS iset ON s.Id=iset.SpeciesId " + "INNER JOIN PublishFreeze AS pf ON iset.Id=pf.InbredSetId " + "WHERE s.Id=%s AND iset.Id=%s AND pf.Id=%s", + (species_id, population_id, dataset_id)) + return dict(cursor.fetchone()) + + +def phenotypes_count(conn: mdb.Connection, + population_id: int, + dataset_id: int) -> int: + """Count the number of phenotypes in the dataset.""" + with conn.cursor(cursorclass=DictCursor) as cursor: + cursor.execute( + "SELECT COUNT(*) AS total_phenos FROM Phenotype AS pheno " + "INNER JOIN PublishXRef AS pxr ON pheno.Id=pxr.PhenotypeId " + "INNER JOIN PublishFreeze AS pf ON pxr.InbredSetId=pf.InbredSetId " + "WHERE pxr.InbredSetId=%s AND pf.Id=%s", + (population_id, dataset_id)) + return int(cursor.fetchone()["total_phenos"]) + + +def dataset_phenotypes(conn: mdb.Connection, + population_id: int, + dataset_id: int, + offset: int = 0, + limit: Optional[int] = None) -> tuple[dict, ...]: + """Fetch the actual phenotypes.""" + _query = ( + "SELECT pheno.*, pxr.Id, ist.InbredSetCode FROM Phenotype AS pheno " + "INNER JOIN PublishXRef AS pxr ON pheno.Id=pxr.PhenotypeId " + "INNER JOIN PublishFreeze AS pf ON pxr.InbredSetId=pf.InbredSetId " + "INNER JOIN InbredSet AS ist ON pf.InbredSetId=ist.Id " + "WHERE pxr.InbredSetId=%s AND pf.Id=%s") + ( + f" LIMIT {limit} OFFSET {offset}" if bool(limit) else "") + with conn.cursor(cursorclass=DictCursor) as cursor: + cursor.execute(_query, (population_id, dataset_id)) + debug_query(cursor) + return tuple(dict(row) for row in cursor.fetchall()) + + +def __phenotype_se__(cursor: Cursor, + species_id: int, + population_id: int, + dataset_id: int, + xref_id: str) -> dict: + """Fetch standard-error values (if they exist) for a phenotype.""" + _sequery = ( + "SELECT pxr.Id AS xref_id, pxr.DataId, str.Id AS StrainId, pse.error, nst.count " + "FROM Phenotype AS pheno " + "INNER JOIN PublishXRef AS pxr ON pheno.Id=pxr.PhenotypeId " + "INNER JOIN PublishSE AS pse ON pxr.DataId=pse.DataId " + "INNER JOIN NStrain AS nst ON pse.DataId=nst.DataId " + "INNER JOIN Strain AS str ON nst.StrainId=str.Id " + "INNER JOIN StrainXRef AS sxr ON str.Id=sxr.StrainId " + "INNER JOIN PublishFreeze AS pf ON sxr.InbredSetId=pf.InbredSetId " + "INNER JOIN InbredSet AS iset ON pf.InbredSetId=iset.InbredSetId " + "WHERE (str.SpeciesId, pxr.InbredSetId, pf.Id, pxr.Id)=(%s, %s, %s, %s)") + cursor.execute(_sequery, + (species_id, population_id, dataset_id, xref_id)) + return {(row["DataId"], row["StrainId"]): { + "xref_id": row["xref_id"], + "DataId": row["DataId"], + "error": row["error"], + "count": row["count"] + } for row in cursor.fetchall()} + +def __organise_by_phenotype__(pheno, row): + """Organise disparate data rows into phenotype 'objects'.""" + _pheno = pheno.get(row["Id"]) + return { + **pheno, + row["Id"]: { + "Id": row["Id"], + "Pre_publication_description": row["Pre_publication_description"], + "Post_publication_description": row["Post_publication_description"], + "Original_description": row["Original_description"], + "Units": row["Units"], + "Pre_publication_abbreviation": row["Pre_publication_abbreviation"], + "Post_publication_abbreviation": row["Post_publication_abbreviation"], + "xref_id": row["pxr.Id"], + "data": { + **(_pheno["data"] if bool(_pheno) else {}), + (row["DataId"], row["StrainId"]): { + "DataId": row["DataId"], + "mean": row["mean"], + "Locus": row["Locus"], + "LRS": row["LRS"], + "additive": row["additive"], + "Sequence": row["Sequence"], + "comments": row["comments"], + "value": row["value"], + "StrainName": row["Name"], + "StrainName2": row["Name2"], + "StrainSymbol": row["Symbol"], + "StrainAlias": row["Alias"] + } + } + } + } + + +def __merge_pheno_data_and_se__(data, sedata) -> dict: + """Merge phenotype data with the standard errors.""" + return { + key: {**value, **sedata.get(key, {})} + for key, value in data.items() + } + + +def phenotype_by_id( + conn: mdb.Connection, + species_id: int, + population_id: int, + dataset_id: int, + xref_id +) -> Optional[dict]: + """Fetch a specific phenotype.""" + _dataquery = ("SELECT pheno.*, pxr.*, pd.*, str.*, iset.InbredSetCode " + "FROM Phenotype AS pheno " + "INNER JOIN PublishXRef AS pxr ON pheno.Id=pxr.PhenotypeId " + "INNER JOIN PublishData AS pd ON pxr.DataId=pd.Id " + "INNER JOIN Strain AS str ON pd.StrainId=str.Id " + "INNER JOIN StrainXRef AS sxr ON str.Id=sxr.StrainId " + "INNER JOIN PublishFreeze AS pf ON sxr.InbredSetId=pf.InbredSetId " + "INNER JOIN InbredSet AS iset ON pf.InbredSetId=iset.InbredSetId " + "WHERE " + "(str.SpeciesId, pxr.InbredSetId, pf.Id, pxr.Id)=(%s, %s, %s, %s)") + with conn.cursor(cursorclass=DictCursor) as cursor: + cursor.execute(_dataquery, + (species_id, population_id, dataset_id, xref_id)) + _pheno: dict = reduce(__organise_by_phenotype__, cursor.fetchall(), {}) + if bool(_pheno) and len(_pheno.keys()) == 1: + _pheno = tuple(_pheno.values())[0] + return { + **_pheno, + "data": tuple(__merge_pheno_data_and_se__( + _pheno["data"], + __phenotype_se__(cursor, + species_id, + population_id, + dataset_id, + xref_id)).values()) + } + if bool(_pheno) and len(_pheno.keys()) > 1: + raise Exception( + "We found more than one phenotype with the same identifier!") + + return None + + +def phenotypes_data(conn: mdb.Connection, + population_id: int, + dataset_id: int, + offset: int = 0, + limit: Optional[int] = None) -> tuple[dict, ...]: + """Fetch the data for the phenotypes.""" + # — Phenotype -> PublishXRef -> PublishData -> Strain -> StrainXRef -> PublishFreeze + _query = ("SELECT pheno.*, pxr.*, pd.*, str.*, iset.InbredSetCode " + "FROM Phenotype AS pheno " + "INNER JOIN PublishXRef AS pxr ON pheno.Id=pxr.PhenotypeId " + "INNER JOIN PublishData AS pd ON pxr.DataId=pd.Id " + "INNER JOIN Strain AS str ON pd.StrainId=str.Id " + "INNER JOIN StrainXRef AS sxr ON str.Id=sxr.StrainId " + "INNER JOIN PublishFreeze AS pf ON sxr.InbredSetId=pf.InbredSetId " + "INNER JOIN InbredSet AS iset ON pf.InbredSetId=iset.InbredSetId " + "WHERE pxr.InbredSetId=%s AND pf.Id=%s") + ( + f" LIMIT {limit} OFFSET {offset}" if bool(limit) else "") + with conn.cursor(cursorclass=DictCursor) as cursor: + cursor.execute(_query, (population_id, dataset_id)) + debug_query(cursor) + return tuple(dict(row) for row in cursor.fetchall()) + + +def save_new_dataset(cursor: Cursor, + population_id: int, + dataset_name: str, + dataset_fullname: str, + dataset_shortname: str) -> dict: + """Create a new phenotype dataset.""" + params = { + "population_id": population_id, + "dataset_name": dataset_name, + "dataset_fullname": dataset_fullname, + "dataset_shortname": dataset_shortname, + "created": datetime.now().date().isoformat(), + "public": 2, + "confidentiality": 0, + "users": None + } + cursor.execute( + "INSERT INTO PublishFreeze(Name, FullName, ShortName, CreateTime, " + "public, InbredSetId, confidentiality, AuthorisedUsers) " + "VALUES(%(dataset_name)s, %(dataset_fullname)s, %(dataset_shortname)s, " + "%(created)s, %(public)s, %(population_id)s, %(confidentiality)s, " + "%(users)s)", + params) + debug_query(cursor) + return {**params, "Id": cursor.lastrowid} diff --git a/uploader/phenotypes/views.py b/uploader/phenotypes/views.py new file mode 100644 index 0000000..02e8078 --- /dev/null +++ b/uploader/phenotypes/views.py @@ -0,0 +1,368 @@ +"""Views handling ('classical') phenotypes.""" +import sys +import uuid +import json +from pathlib import Path +from functools import wraps + +from redis import Redis +from requests.models import Response +from MySQLdb.cursors import DictCursor +from flask import (flash, + request, + url_for, + redirect, + Blueprint, + render_template, + current_app as app) + +# from r_qtl import r_qtl2 as rqtl2 +from r_qtl import r_qtl2_qc as rqc +from r_qtl import exceptions as rqe + +from uploader import jobs +from uploader.files import save_file#, fullpath +from uploader.oauth2.client import oauth2_post +from uploader.authorisation import require_login +from uploader.db_utils import database_connection +from uploader.species.models import all_species, species_by_id +from uploader.monadic_requests import make_either_error_handler +from uploader.request_checks import with_species, with_population +from uploader.datautils import safe_int, order_by_family, enumerate_sequence +from uploader.population.models import (populations_by_species, + population_by_species_and_id) +from uploader.input_validation import (encode_errors, + decode_errors, + is_valid_representative_name) + +from .models import (dataset_by_id, + phenotype_by_id, + phenotypes_count, + save_new_dataset, + dataset_phenotypes, + datasets_by_population) + +phenotypesbp = Blueprint("phenotypes", __name__) + +@phenotypesbp.route("/phenotypes", methods=["GET"]) +@require_login +def index(): + """Direct entry-point for phenotypes data handling.""" + with database_connection(app.config["SQL_URI"]) as conn: + if not bool(request.args.get("species_id")): + return render_template("phenotypes/index.html", + species=order_by_family(all_species(conn)), + activelink="phenotypes") + + species = species_by_id(conn, request.args.get("species_id")) + if not bool(species): + flash("No such species!", "alert-danger") + return redirect(url_for("species.populations.phenotypes.index")) + return redirect(url_for("species.populations.phenotypes.select_population", + species_id=species["SpeciesId"])) + + +@phenotypesbp.route("<int:species_id>/phenotypes/select-population", + methods=["GET"]) +@require_login +@with_species(redirect_uri="species.populations.phenotypes.index") +def select_population(species: dict, **kwargs):# pylint: disable=[unused-argument] + """Select the population for your phenotypes.""" + with database_connection(app.config["SQL_URI"]) as conn: + if not bool(request.args.get("population_id")): + return render_template("phenotypes/select-population.html", + species=species, + populations=order_by_family( + populations_by_species( + conn, species["SpeciesId"]), + order_key="FamilyOrder"), + activelink="phenotypes") + + population = population_by_species_and_id( + conn, species["SpeciesId"], int(request.args["population_id"])) + if not bool(population): + flash("No such population found!", "alert-danger") + return redirect(url_for( + "species.populations.phenotypes.select_population", + species_id=species["SpeciesId"])) + + return redirect(url_for("species.populations.phenotypes.list_datasets", + species_id=species["SpeciesId"], + population_id=population["Id"])) + + + +@phenotypesbp.route( + "<int:species_id>/populations/<int:population_id>/phenotypes/datasets", + methods=["GET"]) +@require_login +@with_population(species_redirect_uri="species.populations.phenotypes.index", + redirect_uri="species.populations.phenotypes.select_population") +def list_datasets(species: dict, population: dict, **kwargs):# pylint: disable=[unused-argument] + """List available phenotype datasets.""" + with database_connection(app.config["SQL_URI"]) as conn: + return render_template("phenotypes/list-datasets.html", + species=species, + population=population, + datasets=datasets_by_population( + conn, + species["SpeciesId"], + population["Id"]), + activelink="list-datasets") + + +def with_dataset( + species_redirect_uri: str, + population_redirect_uri: str, + redirect_uri: str +): + """Ensure the dataset actually exists.""" + def __decorator__(func): + @wraps(func) + @with_population(species_redirect_uri, population_redirect_uri) + def __with_dataset__(**kwargs): + try: + _spcid = int(kwargs["species_id"]) + _popid = int(kwargs["population_id"]) + _dsetid = int(kwargs.get("dataset_id")) + select_dataset_uri = redirect(url_for( + redirect_uri, species_id=_spcid, population_id=_popid)) + if not bool(_dsetid): + flash("You need to select a valid 'dataset_id' value.", + "alert-danger") + return select_dataset_uri + with database_connection(app.config["SQL_URI"]) as conn: + dataset = dataset_by_id(conn, _spcid, _popid, _dsetid) + if not bool(dataset): + flash("You must select a valid dataset.", + "alert-danger") + return select_dataset_uri + except ValueError as _verr: + app.logger.debug( + "Exception converting 'dataset_id' to integer: %s", + kwargs.get("dataset_id"), + exc_info=True) + flash("Expected 'dataset_id' value to be an integer." + "alert-danger") + return select_dataset_uri + return func(dataset=dataset, **kwargs) + return __with_dataset__ + return __decorator__ + + +@phenotypesbp.route( + "<int:species_id>/populations/<int:population_id>/phenotypes/datasets" + "/<int:dataset_id>/view", + methods=["GET"]) +@require_login +@with_dataset( + species_redirect_uri="species.populations.phenotypes.index", + population_redirect_uri="species.populations.phenotypes.select_population", + redirect_uri="species.populations.phenotypes.list_datasets") +def view_dataset(# pylint: disable=[unused-argument] + species: dict, population: dict, dataset: dict, **kwargs): + """View a specific dataset""" + with database_connection(app.config["SQL_URI"]) as conn: + dataset = dataset_by_id( + conn, species["SpeciesId"], population["Id"], dataset["Id"]) + if not bool(dataset): + flash("Could not find such a phenotype dataset!", "alert-danger") + return redirect(url_for( + "species.populations.phenotypes.list_datasets", + species_id=species["SpeciesId"], + population_id=population["Id"])) + + start_at = max(safe_int(request.args.get("start_at") or 0), 0) + count = int(request.args.get("count") or 20) + return render_template("phenotypes/view-dataset.html", + species=species, + population=population, + dataset=dataset, + phenotype_count=phenotypes_count( + conn, population["Id"], dataset["Id"]), + phenotypes=enumerate_sequence( + dataset_phenotypes(conn, + population["Id"], + dataset["Id"], + offset=start_at, + limit=count), + start=start_at+1), + start_from=start_at, + count=count, + activelink="view-dataset") + + +@phenotypesbp.route( + "<int:species_id>/populations/<int:population_id>/phenotypes/datasets" + "/<int:dataset_id>/phenotype/<xref_id>", + methods=["GET"]) +@require_login +@with_dataset( + species_redirect_uri="species.populations.phenotypes.index", + population_redirect_uri="species.populations.phenotypes.select_population", + redirect_uri="species.populations.phenotypes.list_datasets") +def view_phenotype(# pylint: disable=[unused-argument] + species: dict, + population: dict, + dataset: dict, + xref_id: int, + **kwargs +): + """View an individual phenotype from the dataset.""" + def __render__(privileges): + return render_template( + "phenotypes/view-phenotype.html", + species=species, + population=population, + dataset=dataset, + phenotype=phenotype_by_id(conn, + species["SpeciesId"], + population["Id"], + dataset["Id"], + xref_id), + privileges=(privileges + ### For demo! Do not commit this part + + ("group:resource:edit-resource", + "group:resource:delete-resource",) + ### END: For demo! Do not commit this part + ), + activelink="view-phenotype") + + def __fail__(error): + if isinstance(error, Response) and error.json() == "No linked resource!": + return __render__(tuple()) + return make_either_error_handler( + "There was an error fetching the roles and privileges.")(error) + + with database_connection(app.config["SQL_URI"]) as conn: + return oauth2_post( + "/auth/resource/phenotypes/individual/linked-resource", + json={ + "species_id": species["SpeciesId"], + "population_id": population["Id"], + "dataset_id": dataset["Id"], + "xref_id": xref_id + } + ).then( + lambda resource: tuple( + privilege["privilege_id"] for role in resource["roles"] + for privilege in role["privileges"]) + ).then(__render__).either(__fail__, lambda resp: resp) + + +@phenotypesbp.route( + "<int:species_id>/populations/<int:population_id>/phenotypes/datasets/create", + methods=["GET", "POST"]) +@require_login +@with_population( + species_redirect_uri="species.populations.phenotypes.index", + redirect_uri="species.populations.phenotypes.select_population") +def create_dataset(species: dict, population: dict, **kwargs):# pylint: disable=[unused-argument] + """Create a new phenotype dataset.""" + with (database_connection(app.config["SQL_URI"]) as conn, + conn.cursor(cursorclass=DictCursor) as cursor): + if request.method == "GET": + return render_template("phenotypes/create-dataset.html", + activelink="create-dataset", + species=species, + population=population, + **decode_errors( + request.args.get("error_values", ""))) + + form = request.form + _errors: tuple[tuple[str, str], ...] = tuple() + if not is_valid_representative_name( + (form.get("dataset-name") or "").strip()): + _errors = _errors + (("dataset-name", "Invalid dataset name."),) + + if not bool((form.get("dataset-fullname") or "").strip()): + _errors = _errors + (("dataset-fullname", + "You must provide a value for 'Full Name'."),) + + if bool(_errors) > 0: + return redirect(url_for( + "species.populations.phenotypes.create_dataset", + species_id=species["SpeciesId"], + population_id=population["Id"], + error_values=encode_errors(_errors, form))) + + dataset_shortname = ( + form["dataset-shortname"] or form["dataset-name"]).strip() + _pheno_dataset = save_new_dataset( + cursor, + population["Id"], + form["dataset-name"].strip(), + form["dataset-fullname"].strip(), + dataset_shortname) + return redirect(url_for("species.populations.phenotypes.list_datasets", + species_id=species["SpeciesId"], + population_id=population["Id"])) + + +@phenotypesbp.route( + "<int:species_id>/populations/<int:population_id>/phenotypes/datasets" + "/<int:dataset_id>/add-phenotypes", + methods=["GET", "POST"]) +@require_login +@with_dataset( + species_redirect_uri="species.populations.phenotypes.index", + population_redirect_uri="species.populations.phenotypes.select_population", + redirect_uri="species.populations.phenotypes.list_datasets") +def add_phenotypes(species: dict, population: dict, dataset: dict, **kwargs):# pylint: disable=[unused-argument, too-many-locals] + """Add one or more phenotypes to the dataset.""" + add_phenos_uri = redirect(url_for( + "species.populations.phenotypes.add_phenotypes", + species_id=species["SpeciesId"], + population_id=population["Id"], + dataset_id=dataset["Id"])) + _redisuri = app.config["REDIS_URL"] + _sqluri = app.config["SQL_URI"] + with (Redis.from_url(_redisuri, decode_responses=True) as rconn, + # database_connection(_sqluri) as conn, + # conn.cursor(cursorclass=DictCursor) as cursor + ): + if request.method == "GET": + return render_template("phenotypes/add-phenotypes.html", + species=species, + population=population, + dataset=dataset, + activelink="add-phenotypes") + + try: + ## Handle huge files here... + phenobundle = save_file(request.files["phenotypes-bundle"], + Path(app.config["UPLOAD_FOLDER"])) + rqc.validate_bundle(phenobundle) + except AssertionError as _aerr: + app.logger.debug("File upload error!", exc_info=True) + flash("Expected a zipped bundle of files with phenotypes' " + "information.", + "alert-danger") + return add_phenos_uri + except rqe.RQTLError as rqtlerr: + app.logger.debug("Bundle validation error!", exc_info=True) + flash("R/qtl2 Error: " + " ".join(rqtlerr.args), "alert-danger") + return add_phenos_uri + + _jobid = uuid.uuid4() + _namespace = jobs.jobsnamespace() + _ttl_seconds = app.config["JOBS_TTL_SECONDS"] + _job = jobs.initialise_job( + rconn, + _namespace, + str(_jobid), + [sys.executable, "-m", "scripts.rqtl2.phenotypes_qc", _sqluri, + _redisuri, _namespace, str(_jobid), str(species["SpeciesId"]), + str(population["Id"]), str(dataset["Id"]), "--redisexpiry", + str(_ttl_seconds)], "phenotype_qc", _ttl_seconds, + {"job-metadata": json.dumps({ + "speciesid": species["SpeciesId"], + "populationid": population["Id"], + "datasetid": dataset["Id"], + "bundle": str(phenobundle.absolute())})}) + # jobs.launch_job( + # _job, + # redisuri, + # f"{app.config['UPLOAD_FOLDER']}/job_errors") + + raise NotImplementedError("Please implement this...") diff --git a/uploader/platforms/__init__.py b/uploader/platforms/__init__.py new file mode 100644 index 0000000..8cb89c9 --- /dev/null +++ b/uploader/platforms/__init__.py @@ -0,0 +1,2 @@ +"""Module to handle management of genetic platforms.""" +from .views import platformsbp diff --git a/uploader/platforms/models.py b/uploader/platforms/models.py new file mode 100644 index 0000000..a859371 --- /dev/null +++ b/uploader/platforms/models.py @@ -0,0 +1,95 @@ +"""Handle db interactions for platforms.""" +from typing import Optional + +import MySQLdb as mdb +from MySQLdb.cursors import Cursor, DictCursor + +def platforms_by_species( + conn: mdb.Connection, + speciesid: int, + offset: int = 0, + limit: Optional[int] = None +) -> tuple[dict, ...]: + """Retrieve platforms by the species""" + _query = ("SELECT * FROM GeneChip WHERE SpeciesId=%s " + "ORDER BY GeneChipName ASC") + if bool(limit) and limit > 0:# type: ignore[operator] + _query = f"{_query} LIMIT {limit} OFFSET {offset}" + with conn.cursor(cursorclass=DictCursor) as cursor: + cursor.execute(_query, (speciesid,)) + return tuple(dict(row) for row in cursor.fetchall()) + + +def species_platforms_count(conn: mdb.Connection, species_id: int) -> int: + """Get the number of platforms in the database for a particular species.""" + with conn.cursor(cursorclass=DictCursor) as cursor: + cursor.execute( + "SELECT COUNT(GeneChipName) AS count FROM GeneChip " + "WHERE SpeciesId=%s", + (species_id,)) + return int(cursor.fetchone()["count"]) + + +def platform_by_id(conn: mdb.Connection, platformid: int) -> Optional[dict]: + """Retrieve a platform by its ID""" + with conn.cursor(cursorclass=DictCursor) as cursor: + cursor.execute("SELECT * FROM GeneChip WHERE Id=%s", + (platformid,)) + result = cursor.fetchone() + if bool(result): + return dict(result) + + return None + + +def platform_by_species_and_id( + conn: mdb.Connection, species_id: int, platformid: int +) -> Optional[dict]: + """Retrieve a platform by its species and ID""" + with conn.cursor(cursorclass=DictCursor) as cursor: + cursor.execute("SELECT * FROM GeneChip WHERE SpeciesId=%s AND Id=%s", + (species_id, platformid)) + result = cursor.fetchone()#pylint: disable=[duplicate-code] + if bool(result): + return dict(result) + + return None + + +def save_new_platform(# pylint: disable=[too-many-arguments] + cursor: Cursor, + species_id: int, + geo_platform: str, + platform_name: str, + platform_shortname: str, + platform_title: str, + go_tree_value: Optional[str] +) -> dict: + """Save a new platform to the database.""" + params = { + "species_id": species_id, + "GeoPlatform": geo_platform, + "GeneChipName": platform_name, + "Name": platform_shortname, + "Title": platform_title, + "GO_tree_value": go_tree_value + } + cursor.execute("SELECT SpeciesId, GeoPlatform FROM GeneChip") + assert (species_id, geo_platform) not in ( + (row["SpeciesId"], row["GeoPlatform"]) for row in cursor.fetchall()) + cursor.execute( + "INSERT INTO " + "GeneChip(SpeciesId, GeneChipName, Name, GeoPlatform, Title, GO_tree_value) " + "VALUES(" + "%(species_id)s, %(GeneChipName)s, %(Name)s, %(GeoPlatform)s, " + "%(Title)s, %(GO_tree_value)s" + ")", + params) + new_id = cursor.lastrowid + cursor.execute("UPDATE GeneChip SET GeneChipId=%s WHERE Id=%s", + (new_id, new_id)) + return { + **params, + "Id": new_id, + "GeneChipId": new_id + } diff --git a/uploader/platforms/views.py b/uploader/platforms/views.py new file mode 100644 index 0000000..2d61b6a --- /dev/null +++ b/uploader/platforms/views.py @@ -0,0 +1,112 @@ +"""The endpoints for the platforms""" +from MySQLdb.cursors import DictCursor +from flask import ( + flash, + request, + url_for, + redirect, + Blueprint, + current_app as app) + +from uploader.ui import make_template_renderer +from uploader.authorisation import require_login +from uploader.db_utils import database_connection +from uploader.species.models import all_species, species_by_id +from uploader.datautils import safe_int, order_by_family, enumerate_sequence + +from .models import (save_new_platform, + platforms_by_species, + species_platforms_count) + +platformsbp = Blueprint("platforms", __name__) +render_template = make_template_renderer("platforms") + +@platformsbp.route("platforms", methods=["GET"]) +@require_login +def index(): + """Entry-point to the platforms feature.""" + with database_connection(app.config["SQL_URI"]) as conn: + if not bool(request.args.get("species_id")): + return render_template( + "platforms/index.html", + species=order_by_family(all_species(conn)), + activelink="platforms") + + species = species_by_id(conn, request.args["species_id"]) + if not bool(species): + flash("No species selected.", "alert-danger") + return redirect(url_for("species.platforms.index")) + + return redirect(url_for("species.platforms.list_platforms", + species_id=species["SpeciesId"])) + + +@platformsbp.route("<int:species_id>/platforms", methods=["GET"]) +@require_login +def list_platforms(species_id: int): + """List all the available genetic sequencing platforms.""" + with database_connection(app.config["SQL_URI"]) as conn: + species = species_by_id(conn, species_id) + if not bool(species): + flash("No species provided.", "alert-danger") + return redirect(url_for("species.platforms.index")) + + start_from = max(safe_int(request.args.get("start_from") or 0), 0) + count = safe_int(request.args.get("count") or 20) + return render_template( + "platforms/list-platforms.html", + species=species, + platforms=enumerate_sequence( + platforms_by_species(conn, + species_id, + offset=start_from, + limit=count), + start=start_from+1), + start_from=start_from, + count=count, + total_platforms=species_platforms_count(conn, species_id), + activelink="list-platforms") + + +@platformsbp.route("<int:species_id>/platforms/create", methods=["GET", "POST"]) +@require_login +def create_platform(species_id: int): + """Create a new genetic sequencing platform.""" + with (database_connection(app.config["SQL_URI"]) as conn, + conn.cursor(cursorclass=DictCursor) as cursor): + species = species_by_id(conn, species_id) + if not bool(species): + flash("No species provided.", "alert-danger") + return redirect(url_for("species.platforms.index")) + + if request.method == "GET": + return render_template( + "platforms/create-platform.html", + species=species, + activelink="create-platform") + + try: + form = request.form + _new_platform = save_new_platform( + cursor, + species_id, + form["geo-platform"], + form["platform-name"], + form["platform-shortname"], + form["platform-title"], + form.get("go-tree-value") or None) + except KeyError as _kerr: + flash(f"Required value for field {_kerr.args[0]} was not provided.", + "alert-danger") + return redirect(url_for("species.platforms.create_platform", + species_id=species_id)) + except AssertionError as _aerr: + flash(f"Platform with GeoPlatform value of '{form['geo-platform']}'" + f" already exists for species '{species['FullName']}'.", + "alert-danger") + return redirect(url_for("species.platforms.create_platform", + species_id=species_id)) + + flash("Platform created successfully", "alert-success") + return redirect(url_for("species.platforms.list_platforms", + species_id=species_id)) diff --git a/uploader/population/__init__.py b/uploader/population/__init__.py new file mode 100644 index 0000000..bf6bf3c --- /dev/null +++ b/uploader/population/__init__.py @@ -0,0 +1,3 @@ +"""Package to handle creation and management of Populations/InbredSets""" + +from .views import popbp diff --git a/uploader/population/models.py b/uploader/population/models.py new file mode 100644 index 0000000..6dcd85e --- /dev/null +++ b/uploader/population/models.py @@ -0,0 +1,87 @@ +"""Functions for accessing the database relating to species populations.""" +import MySQLdb as mdb +from MySQLdb.cursors import DictCursor + +def population_by_id(conn: mdb.Connection, population_id) -> dict: + """Get the grouping/population by id.""" + with conn.cursor(cursorclass=DictCursor) as cursor: + cursor.execute("SELECT * FROM InbredSet WHERE InbredSetId=%s", + (population_id,)) + return cursor.fetchone() + +def population_by_species_and_id( + conn: mdb.Connection, species_id, population_id) -> dict: + """Retrieve a population by its identifier and species.""" + with conn.cursor(cursorclass=DictCursor) as cursor: + cursor.execute("SELECT * FROM InbredSet WHERE SpeciesId=%s AND Id=%s", + (species_id, population_id)) + return cursor.fetchone() + +def populations_by_species(conn: mdb.Connection, speciesid) -> tuple: + "Retrieve group (InbredSet) information from the database." + with conn.cursor(cursorclass=DictCursor) as cursor: + query = "SELECT * FROM InbredSet WHERE SpeciesId=%s" + cursor.execute(query, (speciesid,)) + return tuple(cursor.fetchall()) + + return tuple() + + +def population_families(conn) -> tuple: + """Fetch the families under which populations are grouped.""" + with conn.cursor(cursorclass=DictCursor) as cursor: + cursor.execute( + "SELECT DISTINCT(Family) FROM InbredSet WHERE Family IS NOT NULL") + return tuple(row["Family"] for row in cursor.fetchall()) + + +def population_genetic_types(conn) -> tuple: + """Fetch the families under which populations are grouped.""" + with conn.cursor(cursorclass=DictCursor) as cursor: + cursor.execute( + "SELECT DISTINCT(GeneticType) FROM InbredSet WHERE GeneticType IS " + "NOT NULL") + return tuple(row["GeneticType"] for row in cursor.fetchall()) + + +def save_population(cursor: mdb.cursors.Cursor, population_details: dict) -> dict: + """Save the population details to the db.""" + cursor.execute("SELECT DISTINCT(Family), FamilyOrder FROM InbredSet " + "WHERE Family IS NOT NULL AND Family != '' " + "AND FamilyOrder IS NOT NULL " + "ORDER BY FamilyOrder ASC") + _families = { + row["Family"]: int(row["FamilyOrder"]) + for row in cursor.fetchall() + } + params = { + "MenuOrderId": 0, + "InbredSetId": 0, + "public": 2, + **population_details, + "FamilyOrder": _families.get( + population_details["Family"], + max(_families.values())+1) + } + cursor.execute( + "INSERT INTO InbredSet(" + "InbredSetId, InbredSetName, Name, SpeciesId, FullName, " + "public, MappingMethodId, GeneticType, Family, FamilyOrder," + " MenuOrderId, InbredSetCode, Description" + ") " + "VALUES (" + "%(InbredSetId)s, %(InbredSetName)s, %(Name)s, %(SpeciesId)s, " + "%(FullName)s, %(public)s, %(MappingMethodId)s, %(GeneticType)s, " + "%(Family)s, %(FamilyOrder)s, %(MenuOrderId)s, %(InbredSetCode)s, " + "%(Description)s" + ")", + params) + new_id = cursor.lastrowid + cursor.execute("UPDATE InbredSet SET InbredSetId=%s WHERE Id=%s", + (new_id, new_id)) + return { + **params, + "Id": new_id, + "InbredSetId": new_id, + "population_id": new_id + } diff --git a/uploader/upload/rqtl2.py b/uploader/population/rqtl2.py index ff7556d..9968bd6 100644 --- a/uploader/upload/rqtl2.py +++ b/uploader/population/rqtl2.py @@ -3,7 +3,6 @@ import sys import json import traceback from pathlib import Path -from datetime import date from uuid import UUID, uuid4 from functools import partial from zipfile import ZipFile, is_zipfile @@ -29,18 +28,16 @@ from r_qtl import r_qtl2 from uploader import jobs from uploader.files import save_file, fullpath -from uploader.dbinsert import species as all_species +from uploader.species.models import all_species from uploader.db_utils import with_db_connection, database_connection from uploader.authorisation import require_login -from uploader.db.platforms import platform_by_id, platforms_by_species +from uploader.platforms.models import platform_by_id, platforms_by_species from uploader.db.averaging import averaging_methods, averaging_method_by_id from uploader.db.tissues import all_tissues, tissue_by_id, create_new_tissue -from uploader.db import ( - species_by_id, - save_population, - populations_by_species, - population_by_species_and_id,) +from uploader.population.models import (populations_by_species, + population_by_species_and_id) +from uploader.species.models import species_by_id from uploader.db.datasets import ( geno_dataset_by_id, geno_datasets_by_species_and_population, @@ -61,19 +58,21 @@ rqtl2 = Blueprint("rqtl2", __name__) def select_species(): """Select the species.""" if request.method == "GET": - return render_template("rqtl2/index.html", species=with_db_connection(all_species)) + return render_template("expression-data/rqtl2/index.html", + species=with_db_connection(all_species)) species_id = request.form.get("species_id") species = with_db_connection( lambda conn: species_by_id(conn, species_id)) if bool(species): return redirect(url_for( - "upload.rqtl2.select_population", species_id=species_id)) + "species.populations.expression-data.rqtl2.select_population", + species_id=species_id)) flash("Invalid species or no species selected!", "alert-error error-rqtl2") - return redirect(url_for("upload.rqtl2.select_species")) + return redirect(url_for("expression-data.rqtl2.select_species")) -@rqtl2.route("/upload/species/<int:species_id>/select-population", +@rqtl2.route("<int:species_id>/expression-data/rqtl2/select-population", methods=["GET", "POST"]) @require_login def select_population(species_id: int): @@ -82,11 +81,11 @@ def select_population(species_id: int): species = species_by_id(conn, species_id) if not bool(species): flash("Invalid species selected!", "alert-error error-rqtl2") - return redirect(url_for("upload.rqtl2.select_species")) + return redirect(url_for("expression-data.rqtl2.select_species")) if request.method == "GET": return render_template( - "rqtl2/select-population.html", + "expression-data/rqtl2/select-population.html", species=species, populations=populations_by_species(conn, species_id)) @@ -95,52 +94,14 @@ def select_population(species_id: int): if not bool(population): flash("Invalid Population!", "alert-error error-rqtl2") return redirect( - url_for("upload.rqtl2.select_population", pgsrc="error"), + url_for("expression-data.rqtl2.select_population", pgsrc="error"), code=307) - return redirect(url_for("upload.rqtl2.upload_rqtl2_bundle", + return redirect(url_for("expression-data.rqtl2.upload_rqtl2_bundle", species_id=species["SpeciesId"], population_id=population["InbredSetId"])) -@rqtl2.route("/upload/species/<int:species_id>/create-population", - methods=["POST"]) -@require_login -def create_population(species_id: int): - """Create a new population for the given species.""" - population_page = redirect(url_for("upload.rqtl2.select_population", - species_id=species_id)) - with database_connection(app.config["SQL_URI"]) as conn: - species = species_by_id(conn, species_id) - population_name = request.form.get("inbredset_name", "").strip() - population_fullname = request.form.get("inbredset_fullname", "").strip() - if not bool(species): - flash("Invalid species!", "alert-error error-rqtl2") - return redirect(url_for("upload.rqtl2.select_species")) - if not bool(population_name): - flash("Invalid Population Name!", "alert-error error-rqtl2") - return population_page - if not bool(population_fullname): - flash("Invalid Population Full Name!", "alert-error error-rqtl2") - return population_page - new_population = save_population(conn, { - "SpeciesId": species["SpeciesId"], - "Name": population_name, - "InbredSetName": population_fullname, - "FullName": population_fullname, - "Family": request.form.get("inbredset_family") or None, - "Description": request.form.get("description") or None - }) - - flash("Population created successfully.", "alert-success") - return redirect( - url_for("upload.rqtl2.upload_rqtl2_bundle", - species_id=species_id, - population_id=new_population["population_id"], - pgsrc="create-population"), - code=307) - - class __RequestError__(Exception): #pylint: disable=[invalid-name] """Internal class to avoid pylint's `too-many-return-statements` error.""" @@ -157,18 +118,19 @@ def upload_rqtl2_bundle(species_id: int, population_id: int): conn, species["SpeciesId"], population_id) if not bool(species): flash("Invalid species!", "alert-error error-rqtl2") - return redirect(url_for("upload.rqtl2.select_species")) + return redirect(url_for("expression-data.rqtl2.select_species")) if not bool(population): flash("Invalid Population!", "alert-error error-rqtl2") return redirect( - url_for("upload.rqtl2.select_population", pgsrc="error"), + url_for("expression-data.rqtl2.select_population", pgsrc="error"), code=307) if request.method == "GET" or ( request.method == "POST" and bool(request.args.get("pgsrc"))): - return render_template("rqtl2/upload-rqtl2-bundle-step-01.html", - species=species, - population=population) + return render_template( + "expression-data/rqtl2/upload-rqtl2-bundle-step-01.html", + species=species, + population=population) try: app.logger.debug("Files in the form: %s", request.files) @@ -178,7 +140,7 @@ def upload_rqtl2_bundle(species_id: int, population_id: int): app.logger.debug(traceback.format_exc()) flash("Please provide a valid R/qtl2 zip bundle.", "alert-error error-rqtl2") - return redirect(url_for("upload.rqtl2.upload_rqtl2_bundle", + return redirect(url_for("expression-data.rqtl2.upload_rqtl2_bundle", species_id=species_id, population_id=population_id)) @@ -192,7 +154,7 @@ def upload_rqtl2_bundle(species_id: int, population_id: int): the_file, request.files["rqtl2_bundle_file"].filename)#type: ignore[arg-type] return redirect(url_for( - "upload.rqtl2.rqtl2_bundle_qc_status", jobid=jobid)) + "expression-data.rqtl2.rqtl2_bundle_qc_status", jobid=jobid)) def trigger_rqtl2_bundle_qc( @@ -244,7 +206,7 @@ def chunks_directory(uniqueidentifier: str) -> Path: return Path(app.config["UPLOAD_FOLDER"], f"tempdir_{uniqueidentifier}") -@rqtl2.route(("/upload/species/<int:species_id>/population/<int:population_id>" +@rqtl2.route(("<int:species_id>/populations/<int:population_id>/rqtl2/" "/rqtl2-bundle-chunked"), methods=["GET"]) @require_login @@ -255,7 +217,7 @@ def upload_rqtl2_bundle_chunked_get(# pylint: disable=["unused-argument"] """ Extension to the `upload_rqtl2_bundle` endpoint above that provides a way for testing whether all the chunks have been uploaded and to assist with - resuming a failed upload. + resuming a failed expression-data. """ fileid = request.args.get("resumableIdentifier", type=str) or "" filename = request.args.get("resumableFilename", type=str) or "" @@ -289,7 +251,7 @@ def __merge_chunks__(targetfile: Path, chunkpaths: tuple[Path, ...]) -> Path: return targetfile -@rqtl2.route(("/upload/species/<int:species_id>/population/<int:population_id>" +@rqtl2.route(("<int:species_id>/population/<int:population_id>/rqtl2/upload/" "/rqtl2-bundle-chunked"), methods=["POST"]) @require_login @@ -335,7 +297,7 @@ def upload_rqtl2_bundle_chunked_post(species_id: int, population_id: int): jobid = trigger_rqtl2_bundle_qc( species_id, population_id, _targetfile, _uploadfilename) return url_for( - "upload.rqtl2.rqtl2_bundle_qc_status", jobid=jobid) + "expression-data.rqtl2.rqtl2_bundle_qc_status", jobid=jobid) except Exception as exc:# pylint: disable=[broad-except] msg = "Error processing uploaded file chunks." app.logger.error(msg, exc_info=True, stack_info=True) @@ -363,24 +325,25 @@ def rqtl2_bundle_qc_status(jobid: UUID): if bool(messagelistname) else []) jobstatus = thejob["status"] if jobstatus == "error": - return render_template("rqtl2/rqtl2-qc-job-error.html", - job=thejob, - errorsgeneric=json.loads( - thejob.get("errors-generic", "[]")), - errorsgeno=json.loads( - thejob.get("errors-geno", "[]")), - errorspheno=json.loads( - thejob.get("errors-pheno", "[]")), - errorsphenose=json.loads( - thejob.get("errors-phenose", "[]")), - errorsphenocovar=json.loads( - thejob.get("errors-phenocovar", "[]")), - messages=logmessages) + return render_template( + "expression-data/rqtl2/rqtl2-qc-job-error.html", + job=thejob, + errorsgeneric=json.loads( + thejob.get("errors-generic", "[]")), + errorsgeno=json.loads( + thejob.get("errors-geno", "[]")), + errorspheno=json.loads( + thejob.get("errors-pheno", "[]")), + errorsphenose=json.loads( + thejob.get("errors-phenose", "[]")), + errorsphenocovar=json.loads( + thejob.get("errors-phenocovar", "[]")), + messages=logmessages) if jobstatus == "success": jobmeta = json.loads(thejob["job-metadata"]) species = species_by_id(dbconn, jobmeta["speciesid"]) return render_template( - "rqtl2/rqtl2-qc-job-results.html", + "expression-data/rqtl2/rqtl2-qc-job-results.html", species=species, population=population_by_species_and_id( dbconn, species["SpeciesId"], jobmeta["populationid"]), @@ -399,14 +362,14 @@ def rqtl2_bundle_qc_status(jobid: UUID): return None return render_template( - "rqtl2/rqtl2-qc-job-status.html", + "expression-data/rqtl2/rqtl2-qc-job-status.html", job=thejob, geno_percent=compute_percentage(thejob, "geno"), pheno_percent=compute_percentage(thejob, "pheno"), phenose_percent=compute_percentage(thejob, "phenose"), messages=logmessages) except jobs.JobNotFound: - return render_template("rqtl2/no-such-job.html", jobid=jobid) + return render_template("expression-data/rqtl2/no-such-job.html", jobid=jobid) def redirect_on_error(flaskroute, **kwargs): @@ -422,7 +385,7 @@ def check_species(conn: mdb.Connection, formargs: dict) -> Optional[ corresponding species exists in the database. Maybe give the function a better name...""" - speciespage = redirect_on_error("upload.rqtl2.select_species") + speciespage = redirect_on_error("expression-data.rqtl2.select_species") if "species_id" not in formargs: return "You MUST provide the Species identifier.", speciespage @@ -441,7 +404,7 @@ def check_population(conn: mdb.Connection, Maybe give the function a better name...""" poppage = redirect_on_error( - "upload.rqtl2.select_species", species_id=species_id) + "expression-data.rqtl2.select_species", species_id=species_id) if "population_id" not in formargs: return "You MUST provide the Population identifier.", poppage @@ -456,12 +419,12 @@ def check_r_qtl2_bundle(formargs: dict, species_id, population_id) -> Optional[tuple[str, Response]]: """Check for the existence of the R/qtl2 bundle.""" - fileuploadpage = redirect_on_error("upload.rqtl2.upload_rqtl2_bundle", + fileuploadpage = redirect_on_error("expression-data.rqtl2.upload_rqtl2_bundle", species_id=species_id, population_id=population_id) if not "rqtl2_bundle_file" in formargs: return ( - "You MUST provide a R/qtl2 zip bundle for upload.", fileuploadpage) + "You MUST provide a R/qtl2 zip bundle for expression-data.", fileuploadpage) if not Path(fullpath(formargs["rqtl2_bundle_file"])).exists(): return "No R/qtl2 bundle with the given name exists.", fileuploadpage @@ -474,7 +437,7 @@ def check_geno_dataset(conn: mdb.Connection, species_id, population_id) -> Optional[tuple[str, Response]]: """Check for the Genotype dataset.""" - genodsetpg = redirect_on_error("upload.rqtl2.select_dataset_info", + genodsetpg = redirect_on_error("expression-data.rqtl2.select_dataset_info", species_id=species_id, population_id=population_id) if not bool(formargs.get("geno-dataset-id")): @@ -499,7 +462,7 @@ def check_geno_dataset(conn: mdb.Connection, def check_tissue( conn: mdb.Connection,formargs: dict) -> Optional[tuple[str, Response]]: """Check for tissue/organ/biological material.""" - selectdsetpg = redirect_on_error("upload.rqtl2.select_dataset_info", + selectdsetpg = redirect_on_error("expression-data.rqtl2.select_dataset_info", species_id=formargs["species_id"], population_id=formargs["population_id"]) if not bool(formargs.get("tissueid", "").strip()): @@ -527,7 +490,7 @@ def check_probe_study(conn: mdb.Connection, species_id, population_id) -> Optional[tuple[str, Response]]: """Check for the ProbeSet study.""" - dsetinfopg = redirect_on_error("upload.rqtl2.select_dataset_info", + dsetinfopg = redirect_on_error("expression-data.rqtl2.select_dataset_info", species_id=species_id, population_id=population_id) if not bool(formargs.get("probe-study-id")): @@ -545,7 +508,7 @@ def check_probe_dataset(conn: mdb.Connection, species_id, population_id) -> Optional[tuple[str, Response]]: """Check for the ProbeSet dataset.""" - dsetinfopg = redirect_on_error("upload.rqtl2.select_dataset_info", + dsetinfopg = redirect_on_error("expression-data.rqtl2.select_dataset_info", species_id=species_id, population_id=population_id) if not bool(formargs.get("probe-dataset-id")): @@ -583,17 +546,17 @@ def select_geno_dataset(species_id: int, population_id: int): if not bool(geno_dset): flash("No genotype dataset was provided!", "alert-error error-rqtl2") - return redirect(url_for("upload.rqtl2.select_geno_dataset", + return redirect(url_for("expression-data.rqtl2.select_geno_dataset", species_id=species_id, population_id=population_id, pgsrc="error"), code=307) flash("Genotype accepted", "alert-success error-rqtl2") - return redirect(url_for("upload.rqtl2.select_dataset_info", + return redirect(url_for("expression-data.rqtl2.select_dataset_info", species_id=species_id, population_id=population_id, - pgsrc="upload.rqtl2.select_geno_dataset"), + pgsrc="expression-data.rqtl2.select_geno_dataset"), code=307) return with_errors(__thunk__, @@ -610,76 +573,6 @@ def select_geno_dataset(species_id: int, population_id: int): @rqtl2.route(("/upload/species/<int:species_id>/population/<int:population_id>" - "/rqtl2-bundle/create-geno-dataset"), - methods=["POST"]) -@require_login -def create_geno_dataset(species_id: int, population_id: int): - """Create a new geno dataset.""" - with database_connection(app.config["SQL_URI"]) as conn: - def __thunk__(): - sgeno_page = redirect(url_for("upload.rqtl2.select_dataset_info", - species_id=species_id, - population_id=population_id, - pgsrc="error"), - code=307) - errorclasses = "alert-error error-rqtl2 error-rqtl2-create-geno-dataset" - if not bool(request.form.get("dataset-name")): - flash("You must provide the dataset name", errorclasses) - return sgeno_page - if not bool(request.form.get("dataset-fullname")): - flash("You must provide the dataset full name", errorclasses) - return sgeno_page - public = 2 if request.form.get("dataset-public") == "on" else 0 - - with conn.cursor(cursorclass=DictCursor) as cursor: - datasetname = request.form["dataset-name"] - new_dataset = { - "name": datasetname, - "fname": request.form.get("dataset-fullname"), - "sname": request.form.get("dataset-shortname") or datasetname, - "today": date.today().isoformat(), - "pub": public, - "isetid": population_id - } - cursor.execute("SELECT * FROM GenoFreeze WHERE Name=%s", - (datasetname,)) - results = cursor.fetchall() - if bool(results): - flash( - f"A genotype dataset with name '{escape(datasetname)}' " - "already exists.", - errorclasses) - return redirect(url_for("upload.rqtl2.select_dataset_info", - species_id=species_id, - population_id=population_id, - pgsrc="error"), - code=307) - cursor.execute( - "INSERT INTO GenoFreeze(" - "Name, FullName, ShortName, CreateTime, public, InbredSetId" - ") " - "VALUES(" - "%(name)s, %(fname)s, %(sname)s, %(today)s, %(pub)s, %(isetid)s" - ")", - new_dataset) - flash("Created dataset successfully.", "alert-success") - return render_template( - "rqtl2/create-geno-dataset-success.html", - species=species_by_id(conn, species_id), - population=population_by_species_and_id( - conn, species_id, population_id), - rqtl2_bundle_file=request.form["rqtl2_bundle_file"], - geno_dataset={**new_dataset, "id": cursor.lastrowid}) - - return with_errors(__thunk__, - partial(check_species, conn=conn), - partial(check_population, conn=conn, species_id=species_id), - partial(check_r_qtl2_bundle, - species_id=species_id, - population_id=population_id)) - - -@rqtl2.route(("/upload/species/<int:species_id>/population/<int:population_id>" "/rqtl2-bundle/select-tissue"), methods=["POST"]) @require_login @@ -691,10 +584,10 @@ def select_tissue(species_id: int, population_id: int): flash("Invalid tissue selection!", "alert-error error-select-tissue error-rqtl2") - return redirect(url_for("upload.rqtl2.select_dataset_info", + return redirect(url_for("expression-data.rqtl2.select_dataset_info", species_id=species_id, population_id=population_id, - pgsrc="upload.rqtl2.select_geno_dataset"), + pgsrc="expression-data.rqtl2.select_geno_dataset"), code=307) return with_errors(__thunk__, @@ -718,10 +611,10 @@ def create_tissue(species_id: int, population_id: int): """Add new tissue, organ or biological material to the system.""" form = request.form datasetinfopage = redirect( - url_for("upload.rqtl2.select_dataset_info", + url_for("expression-data.rqtl2.select_dataset_info", species_id=species_id, population_id=population_id, - pgsrc="upload.rqtl2.select_geno_dataset"), + pgsrc="expression-data.rqtl2.select_geno_dataset"), code=307) with database_connection(app.config["SQL_URI"]) as conn: tissuename = form.get("tissuename", "").strip() @@ -740,7 +633,7 @@ def create_tissue(species_id: int, population_id: int): tissue = create_new_tissue(conn, tissuename, tissueshortname) flash("Tissue created successfully!", "alert-success") return render_template( - "rqtl2/create-tissue-success.html", + "expression-data/rqtl2/create-tissue-success.html", species=species_by_id(conn, species_id), population=population_by_species_and_id( conn, species_id, population_id), @@ -763,7 +656,7 @@ def select_probeset_study(species_id: int, population_id: int): """Select or create a probeset study.""" with database_connection(app.config["SQL_URI"]) as conn: def __thunk__(): - summary_page = redirect(url_for("upload.rqtl2.select_dataset_info", + summary_page = redirect(url_for("expression-data.rqtl2.select_dataset_info", species_id=species_id, population_id=population_id), code=307) @@ -799,7 +692,7 @@ def select_probeset_dataset(species_id: int, population_id: int): """Select or create a probeset dataset.""" with database_connection(app.config["SQL_URI"]) as conn: def __thunk__(): - summary_page = redirect(url_for("upload.rqtl2.select_dataset_info", + summary_page = redirect(url_for("expression-data.rqtl2.select_dataset_info", species_id=species_id, population_id=population_id), code=307) @@ -843,7 +736,7 @@ def create_probeset_study(species_id: int, population_id: int): def __thunk__(): form = request.form dataset_info_page = redirect( - url_for("upload.rqtl2.select_dataset_info", + url_for("expression-data.rqtl2.select_dataset_info", species_id=species_id, population_id=population_id), code=307) @@ -870,7 +763,7 @@ def create_probeset_study(species_id: int, population_id: int): errorclasses) return dataset_info_page return render_template( - "rqtl2/create-probe-study-success.html", + "expression-data/rqtl2/create-probe-study-success.html", species=species_by_id(conn, species_id), population=population_by_species_and_id( conn, species_id, population_id), @@ -905,7 +798,7 @@ def create_probeset_dataset(species_id: int, population_id: int):#pylint: disabl with database_connection(app.config["SQL_URI"]) as conn: def __thunk__():#pylint: disable=[too-many-return-statements] form = request.form - summary_page = redirect(url_for("upload.rqtl2.select_dataset_info", + summary_page = redirect(url_for("expression-data.rqtl2.select_dataset_info", species_id=species_id, population_id=population_id), code=307) @@ -955,7 +848,7 @@ def create_probeset_dataset(species_id: int, population_id: int):#pylint: disabl errorclasses) return summary_page return render_template( - "rqtl2/create-probe-dataset-success.html", + "expression-data/rqtl2/create-probe-dataset-success.html", species=species_by_id(conn, species_id), population=population_by_species_and_id( conn, species_id, population_id), @@ -1010,7 +903,7 @@ def select_dataset_info(species_id: int, population_id: int): conn,form.get("geno-dataset-id", "").strip()) if "geno" in cdata and not bool(form.get("geno-dataset-id")): return render_template( - "rqtl2/select-geno-dataset.html", + "expression-data/rqtl2/select-geno-dataset.html", species=species, population=population, rqtl2_bundle_file=thefile.name, @@ -1020,7 +913,7 @@ def select_dataset_info(species_id: int, population_id: int): tissue = tissue_by_id(conn, form.get("tissueid", "").strip()) if "pheno" in cdata and not bool(tissue): return render_template( - "rqtl2/select-tissue.html", + "expression-data/rqtl2/select-tissue.html", species=species, population=population, rqtl2_bundle_file=thefile.name, @@ -1034,7 +927,7 @@ def select_dataset_info(species_id: int, population_id: int): conn, form.get("probe-study-id", "").strip()) if "pheno" in cdata and not bool(probeset_study): return render_template( - "rqtl2/select-probeset-study-id.html", + "expression-data/rqtl2/select-probeset-study-id.html", species=species, population=population, rqtl2_bundle_file=thefile.name, @@ -1050,7 +943,7 @@ def select_dataset_info(species_id: int, population_id: int): conn, form.get("probe-dataset-id", "").strip()) if "pheno" in cdata and not bool(probeset_dataset): return render_template( - "rqtl2/select-probeset-dataset.html", + "expression-data/rqtl2/select-probeset-dataset.html", species=species, population=population, rqtl2_bundle_file=thefile.name, @@ -1061,7 +954,7 @@ def select_dataset_info(species_id: int, population_id: int): conn, int(form["probe-study-id"])), avgmethods=averaging_methods(conn)) - return render_template("rqtl2/summary-info.html", + return render_template("expression-data/rqtl2/summary-info.html", species=species, population=population, rqtl2_bundle_file=thefile.name, @@ -1126,7 +1019,7 @@ def confirm_bundle_details(species_id: int, population_id: int): redisuri, f"{app.config['UPLOAD_FOLDER']}/job_errors") - return redirect(url_for("upload.rqtl2.rqtl2_processing_status", + return redirect(url_for("expression-data.rqtl2.rqtl2_processing_status", jobid=jobid)) return with_errors(__thunk__, @@ -1164,13 +1057,19 @@ def rqtl2_processing_status(jobid: UUID): if thejob["status"] == "error": return render_template( - "rqtl2/rqtl2-job-error.html", job=thejob, messages=logmessages) + "expression-data/rqtl2/rqtl2-job-error.html", + job=thejob, + messages=logmessages) if thejob["status"] == "success": - return render_template("rqtl2/rqtl2-job-results.html", - job=thejob, - messages=logmessages) + return render_template( + "expression-data/rqtl2/rqtl2-job-results.html", + job=thejob, + messages=logmessages) return render_template( - "rqtl2/rqtl2-job-status.html", job=thejob, messages=logmessages) + "expression-data/rqtl2/rqtl2-job-status.html", + job=thejob, + messages=logmessages) except jobs.JobNotFound as _exc: - return render_template("rqtl2/no-such-job.html", jobid=jobid) + return render_template("expression-data/rqtl2/no-such-job.html", + jobid=jobid) diff --git a/uploader/population/views.py b/uploader/population/views.py new file mode 100644 index 0000000..36201ba --- /dev/null +++ b/uploader/population/views.py @@ -0,0 +1,199 @@ +"""Views dealing with populations/inbredsets""" +import json +import base64 + +from MySQLdb.cursors import DictCursor +from flask import (flash, + request, + url_for, + redirect, + Blueprint, + current_app as app) + +from uploader.samples.views import samplesbp +from uploader.oauth2.client import oauth2_post +from uploader.ui import make_template_renderer +from uploader.authorisation import require_login +from uploader.genotypes.views import genotypesbp +from uploader.db_utils import database_connection +from uploader.datautils import enumerate_sequence +from uploader.phenotypes.views import phenotypesbp +from uploader.expression_data.views import exprdatabp +from uploader.monadic_requests import make_either_error_handler +from uploader.input_validation import is_valid_representative_name +from uploader.species.models import (all_species, + species_by_id, + order_species_by_family) + +from .models import (save_population, + population_families, + populations_by_species, + population_genetic_types, + population_by_species_and_id) + +__active_link__ = "populations" +popbp = Blueprint("populations", __name__) +popbp.register_blueprint(samplesbp, url_prefix="/") +popbp.register_blueprint(genotypesbp, url_prefix="/") +popbp.register_blueprint(phenotypesbp, url_prefix="/") +popbp.register_blueprint(exprdatabp, url_prefix="/") +render_template = make_template_renderer("populations") + + +@popbp.route("/populations", methods=["GET", "POST"]) +@require_login +def index(): + """Entry point for populations.""" + with database_connection(app.config["SQL_URI"]) as conn: + if not bool(request.args.get("species_id")): + return render_template( + "populations/index.html", + species=order_species_by_family(all_species(conn))) + species = species_by_id(conn, request.args.get("species_id")) + if not bool(species): + flash("Invalid species identifier provided!", "alert-danger") + return redirect(url_for("species.populations.index")) + return redirect(url_for("species.populations.list_species_populations", + species_id=species["SpeciesId"])) + +@popbp.route("/<int:species_id>/populations", methods=["GET"]) +@require_login +def list_species_populations(species_id: int): + """List a particular species' populations.""" + with database_connection(app.config["SQL_URI"]) as conn: + species = species_by_id(conn, species_id) + if not bool(species): + flash("No species was found for given ID.", "alert-danger") + return redirect(url_for("species.populations.index")) + return render_template( + "populations/list-populations.html", + species=species, + populations=enumerate_sequence(populations_by_species( + conn, species_id)), + activelink="list-populations") + + +@popbp.route("/<int:species_id>/populations/create", methods=["GET", "POST"]) +@require_login +def create_population(species_id: int): + """Create a new population.""" + with (database_connection(app.config["SQL_URI"]) as conn, + conn.cursor(cursorclass=DictCursor) as cursor): + species = species_by_id(conn, species_id) + + if request.method == "GET": + error_values = request.args.get("error_values") + if not bool(error_values): + error_values = base64.b64encode( + '{"errors":{}, "error_values": {}}'.encode("utf8") + ).decode("utf8") + + error_values = json.loads(base64.b64decode( + error_values.encode("utf8")).decode("utf8"))# type: ignore[union-attr] + return render_template( + "populations/create-population.html", + species=species, + families = population_families(conn), + genetic_types = population_genetic_types(conn), + mapping_methods=( + {"id": "0", "value": "No mapping support"}, + {"id": "1", "value": "GEMMA, QTLReaper, R/qtl"}, + {"id": "2", "value": "GEMMA"}, + {"id": "3", "value": "R/qtl"}, + {"id": "4", "value": "GEMMA, PLINK"}), + activelink="create-population", + **error_values) + + if not bool(species): + flash("You must select a species.", "alert-danger") + return redirect(url_for("species.populations.index")) + + errors: tuple[tuple[str, str], ...] = tuple() + + population_name = (request.form.get( + "population_name") or "").strip() + if not bool(population_name): + errors = errors + (("population_name", + "You must provide a name for the population!"),) + + if not is_valid_representative_name(population_name): + errors = errors + (( + "population_name", + "The population name can only contain letters, numbers, " + "hyphens and underscores."),) + + population_fullname = (request.form.get( + "population_fullname") or "").strip() + if not bool(population_fullname): + errors = errors + ( + ("population_fullname", "Full Name MUST be provided."),) + + if bool(errors): + values = base64.b64encode( + json.dumps({ + "errors": dict(errors), + "error_values": dict(request.form) + }).encode("utf8")) + return redirect(url_for("species.populations.create_population", + species_id=species["SpeciesId"], + error_values=values)) + + new_population = save_population(cursor, { + "SpeciesId": species["SpeciesId"], + "Name": population_name, + "InbredSetName": population_fullname, + "FullName": population_fullname, + "InbredSetCode": request.form.get("population_code") or None, + "Description": request.form.get("population_description") or None, + "Family": request.form.get("population_family") or None, + "MappingMethodId": request.form.get("population_mapping_method_id"), + "GeneticType": request.form.get("population_genetic_type") or None + }) + + def __flash_success__(_success): + flash("Successfully created resource.", "alert-success") + return redirect(url_for( + "species.populations.view_population", + species_id=species["SpeciesId"], + population_id=new_population["InbredSetId"])) + + app.logger.debug("We begin setting up the privileges here…") + return oauth2_post( + "auth/resource/populations/create", + json={ + **dict(request.form), + "species_id": species_id, + "population_id": new_population["Id"], + "public": "on" + } + ).either( + make_either_error_handler( + "There was an error creating the population"), + __flash_success__) + + +@popbp.route("/<int:species_id>/populations/<int:population_id>", + methods=["GET"]) +@require_login +def view_population(species_id: int, population_id: int): + """View the details of a population.""" + with database_connection(app.config["SQL_URI"]) as conn: + species = species_by_id(conn, species_id) + population = population_by_species_and_id(conn, species_id, population_id) + error = False + + if not bool(species): + flash("You must select a species.", "alert-danger") + error = True + + if not bool(population): + flash("You must select a population.", "alert-danger") + error = True + + if error: + return redirect(url_for("species.populations.index")) + + return render_template("populations/view-population.html", + species=species, + population=population, + activelink="view-population") diff --git a/uploader/request_checks.py b/uploader/request_checks.py new file mode 100644 index 0000000..a24b2f7 --- /dev/null +++ b/uploader/request_checks.py @@ -0,0 +1,75 @@ +"""Functions to perform common checks. + +These are useful for reusability, and hence maintainability of the code. +""" +from functools import wraps + +from flask import flash, url_for, redirect, current_app as app + +from uploader.species.models import species_by_id +from uploader.db_utils import database_connection +from uploader.population.models import population_by_species_and_id + +def with_species(redirect_uri: str): + """Ensure the species actually exists.""" + def __decorator__(function): + @wraps(function) + def __with_species__(**kwargs): + try: + species_id = int(kwargs.get("species_id")) + if not bool(species_id): + flash("Expected species_id value to be present!", + "alert-danger") + return redirect(url_for(redirect_uri)) + with database_connection(app.config["SQL_URI"]) as conn: + species = species_by_id(conn, species_id) + if not bool(species): + flash("Could not find species with that ID", + "alert-danger") + return redirect(url_for(redirect_uri)) + except ValueError as _verr: + app.logger.debug( + "Exception converting value to integer: %s", + kwargs.get("species_id"), + exc_info=True) + flash("Expected an integer for 'species_id' value.", + "alert-danger") + return redirect(url_for(redirect_uri)) + return function(**{**kwargs, "species": species}) + return __with_species__ + return __decorator__ + + +def with_population(species_redirect_uri: str, redirect_uri: str): + """Ensure the population actually exists.""" + def __decorator__(function): + @wraps(function) + @with_species(redirect_uri=species_redirect_uri) + def __with_population__(**kwargs): + try: + species_id = int(kwargs["species_id"]) + population_id = int(kwargs.get("population_id")) + select_population_uri = redirect(url_for( + redirect_uri, species_id=species_id)) + if not bool(population_id): + flash("Expected population_id value to be present!", + "alert-danger") + return select_population_uri + with database_connection(app.config["SQL_URI"]) as conn: + population = population_by_species_and_id( + conn, species_id, population_id) + if not bool(population): + flash("Could not find population with that ID", + "alert-danger") + return select_population_uri + except ValueError as _verr: + app.logger.debug( + "Exception converting value to integer: %s", + kwargs.get("population_id"), + exc_info=True) + flash("Expected an integer for 'population_id' value.", + "alert-danger") + return select_population_uri + return function(**{**kwargs, "population": population}) + return __with_population__ + return __decorator__ diff --git a/uploader/samples.py b/uploader/samples.py deleted file mode 100644 index 7a80336..0000000 --- a/uploader/samples.py +++ /dev/null @@ -1,359 +0,0 @@ -"""Code regarding samples""" -import os -import sys -import csv -import uuid -from pathlib import Path -from typing import Iterator - -import MySQLdb as mdb -from redis import Redis -from MySQLdb.cursors import DictCursor -from flask import ( - flash, - request, - url_for, - redirect, - Blueprint, - render_template, - current_app as app) - -from functional_tools import take - -from uploader import jobs -from uploader.files import save_file -from uploader.authorisation import require_login -from uploader.input_validation import is_integer_input -from uploader.db_utils import ( - with_db_connection, - database_connection, - with_redis_connection) -from uploader.db import ( - species_by_id, - save_population, - population_by_id, - populations_by_species, - species as fetch_species) - -samples = Blueprint("samples", __name__) - -@samples.route("/upload/species", methods=["GET", "POST"]) -@require_login -def select_species(): - """Select the species.""" - if request.method == "GET": - return render_template("samples/select-species.html", - species=with_db_connection(fetch_species)) - - index_page = redirect(url_for("entry.upload_file")) - species_id = request.form.get("species_id") - if bool(species_id): - species_id = int(species_id) - species = with_db_connection( - lambda conn: species_by_id(conn, species_id)) - if bool(species): - return redirect(url_for( - "samples.select_population", species_id=species_id)) - flash("Invalid species selected!", "alert-error") - flash("You need to select a species", "alert-error") - return index_page - -@samples.route("/upload/species/<int:species_id>/create-population", - methods=["POST"]) -@require_login -def create_population(species_id: int): - """Create new grouping/population.""" - if not is_integer_input(species_id): - flash("You did not provide a valid species. Please select one to " - "continue.", - "alert-danger") - return redirect(url_for("samples.select_species")) - species = with_db_connection(lambda conn: species_by_id(conn, species_id)) - if not bool(species): - flash("Species with given ID was not found.", "alert-danger") - return redirect(url_for("samples.select_species")) - - species_page = redirect(url_for("samples.select_species"), code=307) - with database_connection(app.config["SQL_URI"]) as conn: - species = species_by_id(conn, species_id) - pop_name = request.form.get("inbredset_name", "").strip() - pop_fullname = request.form.get("inbredset_fullname", "").strip() - - if not bool(species): - flash("Invalid species!", "alert-error error-create-population") - return species_page - if (not bool(pop_name)) or (not bool(pop_fullname)): - flash("You *MUST* provide a grouping/population name", - "alert-error error-create-population") - return species_page - - pop = save_population(conn, { - "SpeciesId": species["SpeciesId"], - "Name": pop_name, - "InbredSetName": pop_fullname, - "FullName": pop_fullname, - "Family": request.form.get("inbredset_family") or None, - "Description": request.form.get("description") or None - }) - - flash("Grouping/Population created successfully.", "alert-success") - return redirect(url_for("samples.upload_samples", - species_id=species_id, - population_id=pop["population_id"])) - -@samples.route("/upload/species/<int:species_id>/population", - methods=["GET", "POST"]) -@require_login -def select_population(species_id: int): - """Select from existing groupings/populations.""" - if not is_integer_input(species_id): - flash("You did not provide a valid species. Please select one to " - "continue.", - "alert-danger") - return redirect(url_for("samples.select_species")) - species = with_db_connection(lambda conn: species_by_id(conn, species_id)) - if not bool(species): - flash("Species with given ID was not found.", "alert-danger") - return redirect(url_for("samples.select_species")) - - if request.method == "GET": - return render_template( - "samples/select-population.html", - species=species, - populations=with_db_connection( - lambda conn: populations_by_species(conn, species_id))) - - population_page = redirect(url_for( - "samples.select_population", species_id=species_id), code=307) - _population_id = request.form.get("inbredset_id") - if not is_integer_input(_population_id): - flash("You did not provide a valid population. Please select one to " - "continue.", - "alert-danger") - return population_page - population = with_db_connection( - lambda conn: population_by_id(conn, _population_id)) - if not bool(population): - flash("Invalid grouping/population!", - "alert-error error-select-population") - return population_page - - return redirect(url_for("samples.upload_samples", - species_id=species_id, - population_id=_population_id), - code=307) - -def read_samples_file(filepath, separator: str, firstlineheading: bool, **kwargs) -> Iterator[dict]: - """Read the samples file.""" - with open(filepath, "r", encoding="utf-8") as inputfile: - reader = csv.DictReader( - inputfile, - fieldnames=( - None if firstlineheading - else ("Name", "Name2", "Symbol", "Alias")), - delimiter=separator, - quotechar=kwargs.get("quotechar", '"')) - for row in reader: - yield row - -def save_samples_data(conn: mdb.Connection, - speciesid: int, - file_data: Iterator[dict]): - """Save the samples to DB.""" - data = ({**row, "SpeciesId": speciesid} for row in file_data) - total = 0 - with conn.cursor() as cursor: - while True: - batch = take(data, 5000) - if len(batch) == 0: - break - cursor.executemany( - "INSERT INTO Strain(Name, Name2, SpeciesId, Symbol, Alias) " - "VALUES(" - " %(Name)s, %(Name2)s, %(SpeciesId)s, %(Symbol)s, %(Alias)s" - ") ON DUPLICATE KEY UPDATE Name=Name", - batch) - total += len(batch) - print(f"\tSaved {total} samples total so far.") - -def cross_reference_samples(conn: mdb.Connection, - species_id: int, - population_id: int, - strain_names: Iterator[str]): - """Link samples to their population.""" - with conn.cursor(cursorclass=DictCursor) as cursor: - cursor.execute( - "SELECT MAX(OrderId) AS loid FROM StrainXRef WHERE InbredSetId=%s", - (population_id,)) - last_order_id = (cursor.fetchone()["loid"] or 10) - total = 0 - while True: - batch = take(strain_names, 5000) - if len(batch) == 0: - break - params_str = ", ".join(["%s"] * len(batch)) - ## This query is slow -- investigate. - cursor.execute( - "SELECT s.Id FROM Strain AS s LEFT JOIN StrainXRef AS sx " - "ON s.Id = sx.StrainId WHERE s.SpeciesId=%s AND s.Name IN " - f"({params_str}) AND sx.StrainId IS NULL", - (species_id,) + tuple(batch)) - strain_ids = (sid["Id"] for sid in cursor.fetchall()) - params = tuple({ - "pop_id": population_id, - "strain_id": strain_id, - "order_id": last_order_id + (order_id * 10), - "mapping": "N", - "pedigree": None - } for order_id, strain_id in enumerate(strain_ids, start=1)) - cursor.executemany( - "INSERT INTO StrainXRef( " - " InbredSetId, StrainId, OrderId, Used_for_mapping, PedigreeStatus" - ")" - "VALUES (" - " %(pop_id)s, %(strain_id)s, %(order_id)s, %(mapping)s, " - " %(pedigree)s" - ")", - params) - last_order_id += (len(params) * 10) - total += len(batch) - print(f"\t{total} total samples cross-referenced to the population " - "so far.") - -def build_sample_upload_job(# pylint: disable=[too-many-arguments] - speciesid: int, - populationid: int, - samplesfile: Path, - separator: str, - firstlineheading: bool, - quotechar: str): - """Define the async command to run the actual samples data upload.""" - return [ - sys.executable, "-m", "scripts.insert_samples", app.config["SQL_URI"], - str(speciesid), str(populationid), str(samplesfile.absolute()), - separator, f"--redisuri={app.config['REDIS_URL']}", - f"--quotechar={quotechar}" - ] + (["--firstlineheading"] if firstlineheading else []) - -@samples.route("/upload/species/<int:species_id>/populations/<int:population_id>/samples", - methods=["GET", "POST"]) -@require_login -def upload_samples(species_id: int, population_id: int):#pylint: disable=[too-many-return-statements] - """Upload the samples.""" - samples_uploads_page = redirect(url_for("samples.upload_samples", - species_id=species_id, - population_id=population_id)) - if not is_integer_input(species_id): - flash("You did not provide a valid species. Please select one to " - "continue.", - "alert-danger") - return redirect(url_for("samples.select_species")) - species = with_db_connection(lambda conn: species_by_id(conn, species_id)) - if not bool(species): - flash("Species with given ID was not found.", "alert-danger") - return redirect(url_for("samples.select_species")) - - if not is_integer_input(population_id): - flash("You did not provide a valid population. Please select one " - "to continue.", - "alert-danger") - return redirect(url_for("samples.select_population", - species_id=species_id), - code=307) - population = with_db_connection( - lambda conn: population_by_id(conn, int(population_id))) - if not bool(population): - flash("Invalid grouping/population!", "alert-error") - return redirect(url_for("samples.select_population", - species_id=species_id), - code=307) - - if request.method == "GET" or request.files.get("samples_file") is None: - return render_template("samples/upload-samples.html", - species=species, - population=population) - - try: - samples_file = save_file(request.files["samples_file"], - Path(app.config["UPLOAD_FOLDER"])) - except AssertionError: - flash("You need to provide a file with the samples data.", - "alert-error") - return samples_uploads_page - - firstlineheading = (request.form.get("first_line_heading") == "on") - - separator = request.form.get("separator", ",") - if separator == "other": - separator = request.form.get("other_separator", ",") - if not bool(separator): - flash("You need to provide a separator character.", "alert-error") - return samples_uploads_page - - quotechar = (request.form.get("field_delimiter", '"') or '"') - - redisuri = app.config["REDIS_URL"] - with Redis.from_url(redisuri, decode_responses=True) as rconn: - the_job = jobs.launch_job( - jobs.initialise_job( - rconn, - jobs.jobsnamespace(), - str(uuid.uuid4()), - build_sample_upload_job( - species["SpeciesId"], - population["InbredSetId"], - samples_file, - separator, - firstlineheading, - quotechar), - "samples_upload", - app.config["JOBS_TTL_SECONDS"], - {"job_name": f"Samples Upload: {samples_file.name}"}), - redisuri, - f"{app.config['UPLOAD_FOLDER']}/job_errors") - return redirect(url_for( - "samples.upload_status", job_id=the_job["jobid"])) - -@samples.route("/upload/status/<uuid:job_id>", methods=["GET"]) -def upload_status(job_id: uuid.UUID): - """Check on the status of a samples upload job.""" - job = with_redis_connection(lambda rconn: jobs.job( - rconn, jobs.jobsnamespace(), job_id)) - if job: - status = job["status"] - if status == "success": - return render_template("samples/upload-success.html", job=job) - - if status == "error": - return redirect(url_for("samples.upload_failure", job_id=job_id)) - - error_filename = Path(jobs.error_filename( - job_id, f"{app.config['UPLOAD_FOLDER']}/job_errors")) - if error_filename.exists(): - stat = os.stat(error_filename) - if stat.st_size > 0: - return redirect(url_for( - "samples.upload_failure", job_id=job_id)) - - return render_template( - "samples/upload-progress.html", - job=job) # maybe also handle this? - - return render_template("no_such_job.html", job_id=job_id), 400 - -@samples.route("/upload/failure/<uuid:job_id>", methods=["GET"]) -def upload_failure(job_id: uuid.UUID): - """Display the errors of the samples upload failure.""" - job = with_redis_connection(lambda rconn: jobs.job( - rconn, jobs.jobsnamespace(), job_id)) - if not bool(job): - return render_template("no_such_job.html", job_id=job_id), 400 - - error_filename = Path(jobs.error_filename( - job_id, f"{app.config['UPLOAD_FOLDER']}/job_errors")) - if error_filename.exists(): - stat = os.stat(error_filename) - if stat.st_size > 0: - return render_template("worker_failure.html", job_id=job_id) - - return render_template("samples/upload-failure.html", job=job) diff --git a/uploader/samples/__init__.py b/uploader/samples/__init__.py new file mode 100644 index 0000000..1bd6d2d --- /dev/null +++ b/uploader/samples/__init__.py @@ -0,0 +1 @@ +"""Samples package. Handle samples uploads and editing.""" diff --git a/uploader/samples/models.py b/uploader/samples/models.py new file mode 100644 index 0000000..d7d5384 --- /dev/null +++ b/uploader/samples/models.py @@ -0,0 +1,104 @@ +"""Functions for handling samples.""" +import csv +from typing import Iterator + +import MySQLdb as mdb +from MySQLdb.cursors import DictCursor + +from functional_tools import take + +def samples_by_species_and_population( + conn: mdb.Connection, + species_id: int, + population_id: int +) -> tuple[dict, ...]: + """Fetch the samples by their species and population.""" + with conn.cursor(cursorclass=DictCursor) as cursor: + cursor.execute( + "SELECT iset.InbredSetId, s.* FROM InbredSet AS iset " + "INNER JOIN StrainXRef AS sxr ON iset.InbredSetId=sxr.InbredSetId " + "INNER JOIN Strain AS s ON sxr.StrainId=s.Id " + "WHERE s.SpeciesId=%(species_id)s " + "AND iset.InbredSetId=%(population_id)s", + {"species_id": species_id, "population_id": population_id}) + return tuple(cursor.fetchall()) + + +def read_samples_file(filepath, separator: str, firstlineheading: bool, **kwargs) -> Iterator[dict]: + """Read the samples file.""" + with open(filepath, "r", encoding="utf-8") as inputfile: + reader = csv.DictReader( + inputfile, + fieldnames=( + None if firstlineheading + else ("Name", "Name2", "Symbol", "Alias")), + delimiter=separator, + quotechar=kwargs.get("quotechar", '"')) + for row in reader: + yield row + + +def save_samples_data(conn: mdb.Connection, + speciesid: int, + file_data: Iterator[dict]): + """Save the samples to DB.""" + data = ({**row, "SpeciesId": speciesid} for row in file_data) + total = 0 + with conn.cursor() as cursor: + while True: + batch = take(data, 5000) + if len(batch) == 0: + break + cursor.executemany( + "INSERT INTO Strain(Name, Name2, SpeciesId, Symbol, Alias) " + "VALUES(" + " %(Name)s, %(Name2)s, %(SpeciesId)s, %(Symbol)s, %(Alias)s" + ") ON DUPLICATE KEY UPDATE Name=Name", + batch) + total += len(batch) + print(f"\tSaved {total} samples total so far.") + + +def cross_reference_samples(conn: mdb.Connection, + species_id: int, + population_id: int, + strain_names: Iterator[str]): + """Link samples to their population.""" + with conn.cursor(cursorclass=DictCursor) as cursor: + cursor.execute( + "SELECT MAX(OrderId) AS loid FROM StrainXRef WHERE InbredSetId=%s", + (population_id,)) + last_order_id = (cursor.fetchone()["loid"] or 10) + total = 0 + while True: + batch = take(strain_names, 5000) + if len(batch) == 0: + break + params_str = ", ".join(["%s"] * len(batch)) + ## This query is slow -- investigate. + cursor.execute( + "SELECT s.Id FROM Strain AS s LEFT JOIN StrainXRef AS sx " + "ON s.Id = sx.StrainId WHERE s.SpeciesId=%s AND s.Name IN " + f"({params_str}) AND sx.StrainId IS NULL", + (species_id,) + tuple(batch)) + strain_ids = (sid["Id"] for sid in cursor.fetchall()) + params = tuple({ + "pop_id": population_id, + "strain_id": strain_id, + "order_id": last_order_id + (order_id * 10), + "mapping": "N", + "pedigree": None + } for order_id, strain_id in enumerate(strain_ids, start=1)) + cursor.executemany( + "INSERT INTO StrainXRef( " + " InbredSetId, StrainId, OrderId, Used_for_mapping, PedigreeStatus" + ")" + "VALUES (" + " %(pop_id)s, %(strain_id)s, %(order_id)s, %(mapping)s, " + " %(pedigree)s" + ")", + params) + last_order_id += (len(params) * 10) + total += len(batch) + print(f"\t{total} total samples cross-referenced to the population " + "so far.") diff --git a/uploader/samples/views.py b/uploader/samples/views.py new file mode 100644 index 0000000..ed79101 --- /dev/null +++ b/uploader/samples/views.py @@ -0,0 +1,280 @@ +"""Code regarding samples""" +import os +import sys +import uuid +from pathlib import Path + +from redis import Redis +from flask import (flash, + request, + url_for, + redirect, + Blueprint, + current_app as app) + +from uploader import jobs +from uploader.files import save_file +from uploader.ui import make_template_renderer +from uploader.authorisation import require_login +from uploader.request_checks import with_population +from uploader.input_validation import is_integer_input +from uploader.datautils import safe_int, order_by_family, enumerate_sequence +from uploader.population.models import population_by_id, populations_by_species +from uploader.db_utils import (with_db_connection, + database_connection, + with_redis_connection) +from uploader.species.models import (all_species, + species_by_id, + order_species_by_family) + +from .models import samples_by_species_and_population + +samplesbp = Blueprint("samples", __name__) +render_template = make_template_renderer("samples") + +@samplesbp.route("/samples", methods=["GET"]) +@require_login +def index(): + """Direct entry-point for uploading/handling the samples.""" + with database_connection(app.config["SQL_URI"]) as conn: + if not bool(request.args.get("species_id")): + return render_template( + "samples/index.html", + species=order_species_by_family(all_species(conn)), + activelink="samples") + species = species_by_id(conn, request.args.get("species_id")) + if not bool(species): + flash("No such species!", "alert-danger") + return redirect(url_for("species.populations.samples.index")) + return redirect(url_for("species.populations.samples.select_population", + species_id=species["SpeciesId"])) + + +@samplesbp.route("<int:species_id>/samples/select-population", methods=["GET"]) +@require_login +def select_population(species_id: int): + """Select the population to use for the samples.""" + with database_connection(app.config["SQL_URI"]) as conn: + species = species_by_id(conn, species_id) + if not bool(species): + flash("Invalid species!", "alert-danger") + return redirect(url_for("species.populations.samples.index")) + + if not bool(request.args.get("population_id")): + return render_template("samples/select-population.html", + species=species, + populations=order_by_family( + populations_by_species( + conn, + species_id), + order_key="FamilyOrder"), + activelink="samples") + + population = population_by_id(conn, request.args.get("population_id")) + if not bool(population): + flash("Population not found!", "alert-danger") + return redirect(url_for( + "species.populations.samples.select_population", + species_id=species_id)) + + return redirect(url_for("species.populations.samples.list_samples", + species_id=species_id, + population_id=population["Id"])) + +@samplesbp.route("<int:species_id>/populations/<int:population_id>/samples") +@require_login +def list_samples(species_id: int, population_id: int): + """ + List the samples in a particular population and give the ability to upload + new ones. + """ + with database_connection(app.config["SQL_URI"]) as conn: + species = species_by_id(conn, species_id) + if not bool(species): + flash("Invalid species!", "alert-danger") + return redirect(url_for("species.populations.samples.index")) + + population = population_by_id(conn, population_id) + if not bool(population): + flash("Population not found!", "alert-danger") + return redirect(url_for( + "species.populations.samples.select_population", + species_id=species_id)) + + all_samples = enumerate_sequence(samples_by_species_and_population( + conn, species_id, population_id)) + total_samples = len(all_samples) + offset = max(safe_int(request.args.get("from") or 0), 0) + count = int(request.args.get("count") or 20) + return render_template("samples/list-samples.html", + species=species, + population=population, + samples=all_samples[offset:offset+count], + offset=offset, + count=count, + total_samples=total_samples, + activelink="list-samples") + + +def build_sample_upload_job(# pylint: disable=[too-many-arguments] + speciesid: int, + populationid: int, + samplesfile: Path, + separator: str, + firstlineheading: bool, + quotechar: str): + """Define the async command to run the actual samples data upload.""" + return [ + sys.executable, "-m", "scripts.insert_samples", app.config["SQL_URI"], + str(speciesid), str(populationid), str(samplesfile.absolute()), + separator, f"--redisuri={app.config['REDIS_URL']}", + f"--quotechar={quotechar}" + ] + (["--firstlineheading"] if firstlineheading else []) + + +@samplesbp.route("<int:species_id>/populations/<int:population_id>/upload-samples", + methods=["GET", "POST"]) +@require_login +def upload_samples(species_id: int, population_id: int):#pylint: disable=[too-many-return-statements] + """Upload the samples.""" + samples_uploads_page = redirect(url_for( + "species.populations.samples.upload_samples", + species_id=species_id, + population_id=population_id)) + if not is_integer_input(species_id): + flash("You did not provide a valid species. Please select one to " + "continue.", + "alert-danger") + return redirect(url_for("expression-data.samples.select_species")) + species = with_db_connection(lambda conn: species_by_id(conn, species_id)) + if not bool(species): + flash("Species with given ID was not found.", "alert-danger") + return redirect(url_for("expression-data.samples.select_species")) + + if not is_integer_input(population_id): + flash("You did not provide a valid population. Please select one " + "to continue.", + "alert-danger") + return redirect(url_for("species.populations.samples.select_population", + species_id=species_id), + code=307) + population = with_db_connection( + lambda conn: population_by_id(conn, int(population_id))) + if not bool(population): + flash("Invalid grouping/population!", "alert-error") + return redirect(url_for("species.populations.samples.select_population", + species_id=species_id), + code=307) + + if request.method == "GET" or request.files.get("samples_file") is None: + return render_template("samples/upload-samples.html", + species=species, + population=population) + + try: + samples_file = save_file(request.files["samples_file"], + Path(app.config["UPLOAD_FOLDER"])) + except AssertionError: + flash("You need to provide a file with the samples data.", + "alert-error") + return samples_uploads_page + + firstlineheading = (request.form.get("first_line_heading") == "on") + + separator = request.form.get("separator", ",") + if separator == "other": + separator = request.form.get("other_separator", ",") + if not bool(separator): + flash("You need to provide a separator character.", "alert-error") + return samples_uploads_page + + quotechar = (request.form.get("field_delimiter", '"') or '"') + + redisuri = app.config["REDIS_URL"] + with Redis.from_url(redisuri, decode_responses=True) as rconn: + #TODO: Add a QC step here — what do we check? + # 1. Does any sample in the uploaded file exist within the database? + # If yes, what is/are its/their species and population? + # 2. If yes 1. above, provide error with notes on which species and + # populations already own the samples. + the_job = jobs.launch_job( + jobs.initialise_job( + rconn, + jobs.jobsnamespace(), + str(uuid.uuid4()), + build_sample_upload_job( + species["SpeciesId"], + population["InbredSetId"], + samples_file, + separator, + firstlineheading, + quotechar), + "samples_upload", + app.config["JOBS_TTL_SECONDS"], + {"job_name": f"Samples Upload: {samples_file.name}"}), + redisuri, + f"{app.config['UPLOAD_FOLDER']}/job_errors") + return redirect(url_for( + "species.populations.samples.upload_status", + species_id=species_id, + population_id=population_id, + job_id=the_job["jobid"])) + + +@samplesbp.route("<int:species_id>/populations/<int:population_id>/" + "upload-samples/status/<uuid:job_id>", + methods=["GET"]) +@require_login +@with_population(species_redirect_uri="species.populations.samples.index", + redirect_uri="species.populations.samples.select_population") +def upload_status(species: dict, population: dict, job_id: uuid.UUID, **kwargs):# pylint: disable=[unused-argument] + """Check on the status of a samples upload job.""" + job = with_redis_connection(lambda rconn: jobs.job( + rconn, jobs.jobsnamespace(), job_id)) + if job: + status = job["status"] + if status == "success": + return render_template("samples/upload-success.html", + job=job, + species=species, + population=population,) + + if status == "error": + return redirect(url_for( + "species.populations.samples.upload_failure", job_id=job_id)) + + error_filename = Path(jobs.error_filename( + job_id, f"{app.config['UPLOAD_FOLDER']}/job_errors")) + if error_filename.exists(): + stat = os.stat(error_filename) + if stat.st_size > 0: + return redirect(url_for( + "samples.upload_failure", job_id=job_id)) + + return render_template("samples/upload-progress.html", + species=species, + population=population, + job=job) # maybe also handle this? + + return render_template("no_such_job.html", + job_id=job_id, + species=species, + population=population), 400 + +@samplesbp.route("/upload/failure/<uuid:job_id>", methods=["GET"]) +@require_login +def upload_failure(job_id: uuid.UUID): + """Display the errors of the samples upload failure.""" + job = with_redis_connection(lambda rconn: jobs.job( + rconn, jobs.jobsnamespace(), job_id)) + if not bool(job): + return render_template("no_such_job.html", job_id=job_id), 400 + + error_filename = Path(jobs.error_filename( + job_id, f"{app.config['UPLOAD_FOLDER']}/job_errors")) + if error_filename.exists(): + stat = os.stat(error_filename) + if stat.st_size > 0: + return render_template("worker_failure.html", job_id=job_id) + + return render_template("samples/upload-failure.html", job=job) diff --git a/uploader/session.py b/uploader/session.py index 8b72bce..b538187 100644 --- a/uploader/session.py +++ b/uploader/session.py @@ -1,7 +1,9 @@ """Deal with user sessions""" from uuid import UUID, uuid4 +from datetime import datetime from typing import Any, Optional, TypedDict +from authlib.jose import KeySet from flask import request, session from pymonad.either import Left, Right, Either @@ -89,3 +91,28 @@ def user_details() -> UserDetails: def user_token() -> Either: """Retrieve the user token.""" return session_info()["user"]["token"] + + +def set_auth_server_jwks(keyset: KeySet) -> KeySet: + """Update the JSON Web Keys in the session.""" + save_session_info({ + **session_info(),# type: ignore[misc] + "auth_server_jwks": { + "last-updated": datetime.now().timestamp(), + "jwks": keyset.as_dict() + } + }) + return keyset + + +def toggle_token_refreshing(): + """Toggle the state of the token_refreshing variable.""" + _session = session_info() + return save_session_info({ + **_session, + "token_refreshing": not _session.get("token_refreshing", False)}) + + +def is_token_refreshing(): + """Returns whether the token is being refreshed or not.""" + return session_info().get("token_refreshing", False) diff --git a/uploader/species/__init__.py b/uploader/species/__init__.py new file mode 100644 index 0000000..83f2165 --- /dev/null +++ b/uploader/species/__init__.py @@ -0,0 +1,2 @@ +"""Package to handle creation and management of species.""" +from .views import speciesbp diff --git a/uploader/species/models.py b/uploader/species/models.py new file mode 100644 index 0000000..51f941c --- /dev/null +++ b/uploader/species/models.py @@ -0,0 +1,152 @@ +"""Database functions for species.""" +import math +from typing import Optional +from functools import reduce + +import MySQLdb as mdb +from MySQLdb.cursors import DictCursor + +def all_species(conn: mdb.Connection) -> tuple: + "Retrieve the species from the database." + with conn.cursor(cursorclass=DictCursor) as cursor: + cursor.execute( + "SELECT Id AS SpeciesId, SpeciesName, LOWER(Name) AS Name, " + "MenuName, FullName, TaxonomyId, Family, FamilyOrderId, OrderId " + "FROM Species ORDER BY FamilyOrderId ASC, OrderID ASC") + return tuple(cursor.fetchall()) + + return tuple() + +def order_species_by_family(species: tuple[dict, ...]) -> list: + """Order the species by their family""" + def __family_order_id__(item): + orderid = item["FamilyOrderId"] + return math.inf if orderid is None else orderid + def __order__(ordered, current): + _key = (__family_order_id__(current), current["Family"]) + return { + **ordered, + _key: ordered.get(_key, tuple()) + (current,) + } + ordered = reduce(__order__, species, {})# type: ignore[var-annotated] + return sorted(tuple(ordered.items()), key=lambda item: item[0][0]) + + +def species_by_id(conn: mdb.Connection, speciesid) -> dict: + "Retrieve the species from the database by id." + with conn.cursor(cursorclass=DictCursor) as cursor: + cursor.execute( + "SELECT Id AS SpeciesId, SpeciesName, LOWER(Name) AS Name, " + "MenuName, FullName, TaxonomyId, Family, FamilyOrderId, OrderId " + "FROM Species WHERE SpeciesId=%s", + (speciesid,)) + return cursor.fetchone() + + +def save_species(conn: mdb.Connection, + common_name: str, + scientific_name: str, + family: str, + taxon_id: Optional[str] = None) -> dict: + """ + Save a new species to the database. + + Parameters + ---------- + conn: A connection to the MariaDB database. + taxon_id: The taxonomy identifier for the new species. + common_name: The species' common name. + scientific_name; The species' scientific name. + """ + genus, species_name = scientific_name.split(" ") + families = species_families(conn) + with conn.cursor() as cursor: + cursor.execute("SELECT MAX(OrderId) FROM Species") + species = { + "common_name": common_name, + "common_name_lower": common_name.lower(), + "menu_name": f"{common_name} ({genus[0]}. {species_name.lower()})", + "scientific_name": scientific_name, + "family": family, + "family_order": families[family], + "taxon_id": taxon_id, + "species_order": cursor.fetchone()[0] + 5 + } + cursor.execute( + "INSERT INTO Species(" + "SpeciesName, Name, MenuName, FullName, Family, FamilyOrderId, " + "TaxonomyId, OrderId" + ") VALUES (" + "%(common_name)s, %(common_name_lower)s, %(menu_name)s, " + "%(scientific_name)s, %(family)s, %(family_order)s, %(taxon_id)s, " + "%(species_order)s" + ")", + species) + species_id = cursor.lastrowid + cursor.execute("UPDATE Species SET SpeciesId=%s WHERE Id=%s", + (species_id, species_id)) + return { + **species, + "species_id": species_id + } + + +def update_species(# pylint: disable=[too-many-arguments] + conn: mdb.Connection, + species_id: int, + common_name: str, + scientific_name: str, + family: str, + family_order: int, + species_order: int +): + """Update a species' details. + + Parameters + ---------- + conn: A connection to the MariaDB database. + species_id: The species identifier + + Key-Word Arguments + ------------------ + common_name: A layman's name for the species + scientific_name: A binomial nomenclature name for the species + family: The grouping under which the species falls + family_order: The ordering for the "family" above + species_order: The ordering of this species in relation to others + """ + with conn.cursor(cursorclass=DictCursor) as cursor: + genus, species_name = scientific_name.split(" ") + species = { + "species_id": species_id, + "common_name": common_name, + "common_name_lower": common_name.lower(), + "menu_name": f"{common_name} ({genus[0]}. {species_name.lower()})", + "scientific_name": scientific_name, + "family": family, + "family_order": family_order, + "species_order": species_order + } + cursor.execute( + "UPDATE Species SET " + "SpeciesName=%(common_name)s, " + "Name=%(common_name_lower)s, " + "MenuName=%(menu_name)s, " + "FullName=%(scientific_name)s, " + "Family=%(family)s, " + "FamilyOrderId=%(family_order)s, " + "OrderId=%(species_order)s " + "WHERE Id=%(species_id)s", + species) + + +def species_families(conn: mdb.Connection) -> dict: + """Retrieve the families under which species are grouped.""" + with conn.cursor(cursorclass=DictCursor) as cursor: + cursor.execute( + "SELECT DISTINCT(Family), FamilyOrderId FROM Species " + "WHERE Family IS NOT NULL") + return { + fam["Family"]: fam["FamilyOrderId"] + for fam in cursor.fetchall() + } diff --git a/uploader/species/views.py b/uploader/species/views.py new file mode 100644 index 0000000..10715a5 --- /dev/null +++ b/uploader/species/views.py @@ -0,0 +1,200 @@ +"""Endpoints handling species.""" +from pymonad.either import Left, Right, Either +from flask import (flash, + request, + url_for, + redirect, + Blueprint, + current_app as app) + +from uploader.population import popbp +from uploader.platforms import platformsbp +from uploader.ui import make_template_renderer +from uploader.db_utils import database_connection +from uploader.oauth2.client import oauth2_get, oauth2_post +from uploader.authorisation import require_login, require_token +from uploader.datautils import order_by_family, enumerate_sequence + +from .models import (all_species, + save_species, + species_by_id, + update_species, + species_families) + + +speciesbp = Blueprint("species", __name__) +speciesbp.register_blueprint(popbp, url_prefix="/") +speciesbp.register_blueprint(platformsbp, url_prefix="/") +render_template = make_template_renderer("species") + + +@speciesbp.route("/", methods=["GET"]) +@require_login +def list_species(): + """List and display all the species in the database.""" + with database_connection(app.config["SQL_URI"]) as conn: + return render_template("species/list-species.html", + allspecies=enumerate_sequence(all_species(conn))) + +@speciesbp.route("/<int:species_id>", methods=["GET"]) +@require_login +def view_species(species_id: int): + """View details of a particular species and menus to act upon it.""" + with database_connection(app.config["SQL_URI"]) as conn: + species = species_by_id(conn, species_id) + if bool(species): + return render_template("species/view-species.html", + species=species, + activelink="view-species") + flash("Could not find a species with the given identifier.", + "alert-danger") + return redirect(url_for("species.view_species")) + +@speciesbp.route("/create", methods=["GET", "POST"]) +@require_login +def create_species(): + """Create a new species.""" + # We can use uniprot's API to fetch the details with something like + # https://rest.uniprot.org/taxonomy/<taxonID> e.g. + # https://rest.uniprot.org/taxonomy/6239 + with (database_connection(app.config["SQL_URI"]) as conn, + conn.cursor() as cursor): + if request.method == "GET": + return render_template("species/create-species.html", + families=species_families(conn), + activelink="create-species") + + error = False + taxon_id = request.form.get("species_taxonomy_id", "").strip() or None + + common_name = request.form.get("common_name", "").strip() + if not bool(common_name): + flash("The common species name MUST be provided.", "alert-danger") + error = True + + scientific_name = request.form.get("scientific_name", "").strip() + if not bool(scientific_name): + flash("The species' scientific name MUST be provided.", + "alert-danger") + error = True + + parts = tuple(name.strip() for name in scientific_name.split(" ")) + if len(parts) != 2 or not all(bool(name) for name in parts): + flash("The scientific name you provided is invalid.", "alert-danger") + error = True + + cursor.execute( + "SELECT * FROM Species WHERE FullName=%s", (scientific_name,)) + res = cursor.fetchone() + if bool(res): + flash("A species already exists with the provided scientific name.", + "alert-danger") + error = True + + family = request.form.get("species_family", "").strip() + if not bool(family): + flash("The species' family MUST be selected.", "alert-danger") + error = True + + if bool(taxon_id): + cursor.execute( + "SELECT * FROM Species WHERE TaxonomyId=%s", (taxon_id,)) + res = cursor.fetchone() + if bool(res): + flash("A species already exists with the provided scientific name.", + "alert-danger") + error = True + + if error: + return redirect(url_for("species.create_species", + common_name=common_name, + scientific_name=scientific_name, + taxon_id=taxon_id)) + + species = save_species( + conn, common_name, scientific_name, family, taxon_id) + flash("Species saved successfully!", "alert-success") + return redirect(url_for("species.view_species", species_id=species["species_id"])) + + +@speciesbp.route("/<int:species_id>/edit-extra", methods=["GET", "POST"]) +@require_login +@require_token +#def edit_species(species_id: int): +def edit_species_extra(token: dict, species_id: int):# pylint: disable=[unused-argument] + """Edit a species' details. + + Parameters + ---------- + token: A JWT token used for authorisation. + species_id: An identifier for the species being edited. + """ + def __failure__(res): + app.logger.debug( + "There was an error in the attempt to edit the species: %s", res) + flash(res, "alert-danger") + return redirect(url_for("species.view_species", species_id=species_id)) + + def __system_resource_uuid__(resources) -> Either: + sys_res = [ + resource for resource in resources + if resource["resource_category"]["resource_category_key"] == "system" + ] + if len(sys_res) != 1: + return Left("Could not find/identify a valid system resource.") + return Right(sys_res[0]["resource_id"]) + + def __check_privileges__(authorisations): + if len(authorisations.items()) != 1: + return Left("Got authorisations for more than a single resource!") + + auths = tuple(authorisations.items())[0][1] + authorised = "system:species:edit-extra-info" in tuple( + privilege["privilege_id"] + for role in auths["roles"] + for privilege in role["privileges"]) + if authorised: + return Right(authorised) + return Left("You are not authorised to edit species extra details.") + + with database_connection(app.config["SQL_URI"]) as conn: + species = species_by_id(conn, species_id) + all_the_species = all_species(conn) + families = species_families(conn) + family_order = tuple( + item[0] for item in order_by_family(all_the_species) + if item[0][1] is not None) + if bool(species) and request.method == "GET": + return oauth2_get("auth/user/resources").then( + __system_resource_uuid__ + ).then( + lambda resource_id: oauth2_post( + "auth/resource/authorisation", + json={"resource-ids": [resource_id]}) + ).then(__check_privileges__).then( + lambda authorisations: render_template( + "species/edit-species.html", + species=species, + families=families, + family_order=family_order, + max_order_id = max( + row["OrderId"] for row in all_the_species + if row["OrderId"] is not None), + activelink="edit-species") + ).either(__failure__, lambda res: res) + + if bool(species) and request.method == "POST": + update_species(conn, + species_id, + request.form["species_name"], + request.form["species_fullname"], + request.form["species_family"], + int(request.form["species_familyorderid"]), + int(request.form["species_orderid"])) + flash("Updated species successfully.", "alert-success") + return redirect(url_for("species.edit_species_extra", + species_id=species_id)) + + flash("Species with the given identifier was not found!", + "alert-danger") + return redirect(url_for("species.list_species")) diff --git a/uploader/static/css/styles.css b/uploader/static/css/styles.css index a88c229..f482c1b 100644 --- a/uploader/static/css/styles.css +++ b/uploader/static/css/styles.css @@ -1,7 +1,161 @@ -.heading { +body { + margin: 0.7em; + box-sizing: border-box; + display: grid; + grid-template-columns: 1fr 6fr; + grid-template-rows: 5em 100%; + grid-gap: 20px; + + font-family: Georgia, Garamond, serif; + font-style: normal; +} + +#header { + grid-column: 1/3; + width: 100%; + /* background: cyan; */ + padding-top: 0.5em; + border-radius: 0.5em; + + background-color: #336699; + border-color: #080808; + color: #FFFFFF; + background-image: none; +} + +#header .header { + font-size: 2em; + display: inline-block; + text-align: start; +} + +#header .header-nav { + display: inline-block; + color: #FFFFFF; +} + +#header .header-nav li { + border-width: 1px; + border-color: #FFFFFF; + vertical-align: middle; + margin: 0.2em; + border-style: solid; + border-width: 2px; + border-radius: 0.5em; + text-align: center; +} + +#header .header-nav a { + color: #FFFFFF; + text-decoration: none; +} + +#nav-sidebar { + grid-column: 1/2; + /* background: #e5e5ff; */ + padding-top: 0.5em; + border-radius: 0.5em; + font-size: 1.2em; +} + +#main { + grid-column: 2/3; + width: 100%; + /* background: gray; */ + border-radius: 0.5em; +} + +.pagetitle { + padding-top: 0.5em; + /* background: pink; */ + border-radius: 0.5em; + /* background-color: #6699CC; */ + /* background-color: #77AADD; */ + background-color: #88BBEE; +} + +.pagetitle h1 { + text-align: start; text-transform: capitalize; + padding-left: 0.25em; +} + +.pagetitle .breadcrumb { + background: none; +} + +.pagetitle .breadcrumb .active a { + color: #333333; +} + +.pagetitle .breadcrumb a { + color: #666666; } -label { +.main-content { + font-size: 1.275em; +} + +.breadcrumb { + text-transform: capitalize; +} + +dd { + margin-left: 3em; + font-size: 0.88em; + padding-bottom: 1em; +} + +input[type="submit"], .btn { text-transform: capitalize; } + +.card { + margin-top: 0.3em; + border-width: 1px; + border-style: solid; + border-radius: 0.3em; + border-color: #AAAAAA; + padding: 0.5em; +} + +.activemenu { + border-style: solid; + border-radius: 0.5em; + border-color: #AAAAAA; + background-color: #EFEFEF; +} + +.danger { + color: #A94442; + border-color: #DCA7A7; + background-color: #F2DEDE; +} + +.heading { + border-bottom: solid #EEBB88; +} + +.subheading { + padding: 1em 0 0.1em 0.5em; + border-bottom: solid #88BBEE; +} + +form { + margin-top: 0.3em; + background: #E5E5FF; + padding: 0.5em; + border-radius:0.5em; +} + +form .form-control { + background-color: #EAEAFF; +} + +.sidebar-content .card .card-title { + font-size: 1.5em; +} + +.sidebar-content .card-text table tbody td:nth-child(1) { + font-weight: bolder; +} diff --git a/uploader/static/js/misc.js b/uploader/static/js/misc.js new file mode 100644 index 0000000..cf7b39e --- /dev/null +++ b/uploader/static/js/misc.js @@ -0,0 +1,6 @@ +"Miscellaneous functions and event-handlers" + +$(".not-implemented").click((event) => { + event.preventDefault(); + alert("This feature is not implemented yet. Please bear with us."); +}); diff --git a/uploader/templates/base.html b/uploader/templates/base.html index ee60fea..019aa39 100644 --- a/uploader/templates/base.html +++ b/uploader/templates/base.html @@ -1,6 +1,8 @@ <!DOCTYPE html> <html lang="en"> + <head> + <meta charset="UTF-8" /> <meta application-name="GeneNetwork Quality-Control Application" /> <meta name="viewport" content="width=device-width, initial-scale=1.0" /> @@ -14,49 +16,117 @@ <link rel="stylesheet" type="text/css" href="{{url_for('base.bootstrap', filename='css/bootstrap-theme.min.css')}}" /> - - - <link rel="shortcut icon" type="image/png" sizes="64x64" - href="{{url_for('static', filename='images/CITGLogo.png')}}" /> - - <link rel="stylesheet" type="text/css" href="/static/css/custom-bootstrap.css" /> <link rel="stylesheet" type="text/css" href="/static/css/styles.css" /> {%block css%}{%endblock%} + </head> <body> - <div class="navbar navbar-inverse navbar-static-top pull-left" - role="navigation" - style="width: 100%;min-width: 850px;white-space: nowrap;"> - <div class="container-fluid" style="width: 100%"> - <ul class="nav navbar-nav"> - <li><a href="/" style="font-weight: bold">GN Uploader</a></li> - <li> - <a href="{{gn2server_uri()}}">GeneNetwork</a> - </li> - </ul> - <ul class="nav navbar-nav" style="margin-left: 2em;"> - <li> - {%if user_logged_in()%} - <a href="{{url_for('oauth2.logout')}}" - title="Log out of the system">Log Out</a> - {%else%} - <a href="{{authserver_authorise_uri()}}" - title="Log in to the system">Log In</a> - {%endif%} - </li> - </ul> + <header id="header" class="container-fluid"> + <div class="row"> + <span class="header col-lg-9">GeneNetwork Data Quality Control and Upload</span> + <nav class="header-nav col-lg-3"> + <ul class="nav justify-content-end"> + <li> + {%if user_logged_in()%} + <a href="{{url_for('oauth2.logout')}}" + title="Log out of the system">{{user_email()}} — Log Out</a> + {%else%} + <a href="{{authserver_authorise_uri()}}" + title="Log in to the system">Log In</a> + {%endif%} + </li> + </ul> + </nav> + </header> + + <aside id="nav-sidebar" class="container-fluid"> + <ul class="nav flex-column"> + <li {%if activemenu=="home"%}class="activemenu"{%endif%}> + <a href="/" >Home</a></li> + <li {%if activemenu=="species"%}class="activemenu"{%endif%}> + <a href="{{url_for('species.list_species')}}" + title="View and manage species information.">Species</a></li> + <li {%if activemenu=="platforms"%}class="activemenu"{%endif%}> + <a href="{{url_for('species.platforms.index')}}" + title="View and manage species platforms.">Sequencing Platforms</a></li> + <li {%if activemenu=="populations"%}class="activemenu"{%endif%}> + <a href="{{url_for('species.populations.index')}}" + title="View and manage species populations.">Populations</a></li> + <li {%if activemenu=="samples"%}class="activemenu"{%endif%}> + <a href="{{url_for('species.populations.samples.index')}}" + title="Upload population samples.">Samples</a></li> + <li {%if activemenu=="genotypes"%}class="activemenu"{%endif%}> + <a href="{{url_for('species.populations.genotypes.index')}}" + title="Upload Genotype data.">Genotype Data</a></li> + <!-- + TODO: Maybe include menus here for managing studies and dataset or + maybe have the studies/datasets managed under their respective + sections, e.g. "Publish*" studies/datasets under the "Phenotypes" + section, "ProbeSet*" studies/datasets under the "Expression Data" + sections, etc. + --> + <li {%if activemenu=="phenotypes"%}class="activemenu"{%endif%}> + <a href="{{url_for('species.populations.phenotypes.index')}}" + title="Upload phenotype data.">Phenotype Data</a></li> + <li {%if activemenu=="expression-data"%}class="activemenu"{%endif%}> + <a href="{{url_for('species.populations.expression-data.index')}}" + title="Upload expression data.">Expression Data</a></li> + <li {%if activemenu=="individuals"%}class="activemenu"{%endif%}> + <a href="#" + class="not-implemented" + title="Upload individual data.">Individual Data</a></li> + <li {%if activemenu=="rna-seq"%}class="activemenu"{%endif%}> + <a href="#" + class="not-implemented" + title="Upload RNA-Seq data.">RNA-Seq Data</a></li> + <li {%if activemenu=="async-jobs"%}class="activemenu"{%endif%}> + <a href="#" + class="not-implemented" + title="View and manage the backgroud jobs you have running"> + Background Jobs</a></li> + </ul> + </aside> + + <main id="main" class="main container-fluid"> + + <div class="pagetitle row"> + <h1>GN Uploader: {%block pagetitle%}{%endblock%}</h1> + <nav> + <ol class="breadcrumb"> + <li {%if activelink is not defined or activelink=="home"%} + class="breadcrumb-item active" + {%else%} + class="breadcrumb-item" + {%endif%}> + <a href="{{url_for('base.index')}}">Home</a> + </li> + {%block lvl1_breadcrumbs%}{%endblock%} + </ol> + </nav> + </div> + + <div class="row"> + <div class="container-fluid"> + <div class="col-md-8 main-content"> + {%block contents%}{%endblock%} + </div> + <div class="sidebar-content col-md-4"> + {%block sidebarcontents%}{%endblock%} + </div> + </div> </div> - </div> - <div class="container"> - {%block contents%}{%endblock%} - </div> + </main> + <script src="{{url_for('base.jquery', filename='jquery.min.js')}}"></script> <script src="{{url_for('base.bootstrap', filename='js/bootstrap.min.js')}}"></script> + <script type="text/javascript" src="/static/js/misc.js"></script> {%block javascript%}{%endblock%} + </body> + </html> diff --git a/uploader/templates/expression-data/base.html b/uploader/templates/expression-data/base.html new file mode 100644 index 0000000..d63fd7e --- /dev/null +++ b/uploader/templates/expression-data/base.html @@ -0,0 +1,13 @@ +{%extends "populations/base.html"%} + +{%block lvl3_breadcrumbs%} +<li {%if activelink=="expression-data"%} + class="breadcrumb-item active" + {%else%} + class="breadcrumb-item" + {%endif%}> + <a href="{{url_for('species.populations.expression-data.index')}}"> + Expression Data</a> +</li> +{%block lvl4_breadcrumbs%}{%endblock%} +{%endblock%} diff --git a/uploader/templates/data_review.html b/uploader/templates/expression-data/data-review.html index b7528fd..c985b03 100644 --- a/uploader/templates/data_review.html +++ b/uploader/templates/expression-data/data-review.html @@ -26,7 +26,7 @@ <small class="text-muted"> If you encounter an error saying your sample(s)/case(s) do not exist in the GeneNetwork database, then you will have to use the - <a href="{{url_for('samples.select_species')}}" + <a href="{{url_for('species.populations.samples.index')}}" title="Upload samples/cases feature">Upload Samples/Cases</a> option on this system to upload them. </small> @@ -70,8 +70,8 @@ column</li> <li>The values of each field <strong>ARE NOT</strong> quoted.</li> <li>Here is an - <a href="https://gitlab.com/fredmanglis/gnqc_py/-/blob/main/tests/test_data/no_data_errors.tsv"> - example file</a> with a single data row.</li> + <a href="https://gitlab.com/fredmanglis/gnqc_py/-/blob/main/tests/test_data/no_data_errors.tsv" + target="_blank">example file</a> with a single data row.</li> </ul> </li> <li>.txt files: Content has the same format as .tsv file above</li> diff --git a/uploader/templates/expression-data/index.html b/uploader/templates/expression-data/index.html new file mode 100644 index 0000000..9ba3582 --- /dev/null +++ b/uploader/templates/expression-data/index.html @@ -0,0 +1,33 @@ +{%extends "expression-data/base.html"%} +{%from "flash_messages.html" import flash_all_messages%} +{%from "species/macro-select-species.html" import select_species_form%} + +{%block title%}Expression Data{%endblock%} + +{%block pagetitle%}Expression Data{%endblock%} + +{%block breadcrumb%} +<li class="breadcrumb-item"> + <a href="{{url_for('base.index')}}">Home</a> +</li> +<li class="breadcrumb-item active"> + <a href="{{url_for('species.populations.expression-data.index')}}" + title="Upload expression data."> + Expression Data</a> +</li> +{%endblock%} + +{%block contents%} +<div class="row"> + <h2 class="heading">Expression Data</h2> + {{flash_all_messages()}} + + <p>This section allows you to enter the expression data for your experiment. + You will need to select the species that your data concerns below.</p> +</div> + +<div class="row"> + {{select_species_form(url_for("species.populations.expression-data.index"), + species)}} +</div> +{%endblock%} diff --git a/uploader/templates/job_progress.html b/uploader/templates/expression-data/job-progress.html index 1af0763..ef264e1 100644 --- a/uploader/templates/job_progress.html +++ b/uploader/templates/expression-data/job-progress.html @@ -1,5 +1,6 @@ {%extends "base.html"%} {%from "errors_display.html" import errors_display%} +{%from "populations/macro-display-population-card.html" import display_population_card%} {%block extrameta%} <meta http-equiv="refresh" content="5"> @@ -11,7 +12,9 @@ <h1 class="heading">{{job_name}}</h2> <div class="row"> - <form action="{{url_for('parse.abort')}}" method="POST"> + <form action="{{url_for('species.populations.expression-data.abort', + species_id=species.SpeciesId, + population_id=population.Id)}}" method="POST"> <legend class="heading">Status</legend> <div class="form-group"> <label for="job_status" class="form-label">status:</label> @@ -38,3 +41,7 @@ </div> {%endblock%} + +{%block sidebarcontents%} +{{display_population_card(species, population)}} +{%endblock%} diff --git a/uploader/templates/no_such_job.html b/uploader/templates/expression-data/no-such-job.html index 42a2d48..d22c429 100644 --- a/uploader/templates/no_such_job.html +++ b/uploader/templates/expression-data/no-such-job.html @@ -1,7 +1,8 @@ {%extends "base.html"%} {%block extrameta%} -<meta http-equiv="refresh" content="5;url={{url_for('entry.upload_file')}}"> +<meta http-equiv="refresh" + content="5;url={{url_for('species.populations.expression-data.index.upload_file')}}"> {%endblock%} {%block title%}No Such Job{%endblock%} diff --git a/uploader/templates/parse_failure.html b/uploader/templates/expression-data/parse-failure.html index 31f6be8..31f6be8 100644 --- a/uploader/templates/parse_failure.html +++ b/uploader/templates/expression-data/parse-failure.html diff --git a/uploader/templates/expression-data/parse-results.html b/uploader/templates/expression-data/parse-results.html new file mode 100644 index 0000000..03a23e2 --- /dev/null +++ b/uploader/templates/expression-data/parse-results.html @@ -0,0 +1,39 @@ +{%extends "base.html"%} +{%from "errors_display.html" import errors_display%} +{%from "populations/macro-display-population-card.html" import display_population_card%} + +{%block title%}Parse Results{%endblock%} + +{%block contents%} + +<div class="row"> + <h2 class="heading">{{job_name}}: parse results</h2> + + {%if user_aborted%} + <span class="alert-warning">Job aborted by the user</span> + {%endif%} + + {{errors_display(errors, "No errors found in the file", "We found the following errors", True)}} + + {%if errors | length == 0 and not user_aborted %} + <form method="post" action="{{url_for('dbinsert.select_platform')}}"> + <input type="hidden" name="job_id" value="{{job_id}}" /> + <input type="submit" value="update database" class="btn btn-primary" /> + </form> + {%endif%} + + {%if errors | length > 0 or user_aborted %} + <br /> + <a href="{{url_for('species.populations.expression-data.upload_file', + species_id=species.SpeciesId, + population_id=population.Id)}}" + title="Back to index page." + class="btn btn-primary">Go back</a> + + {%endif%} +</div> +{%endblock%} + +{%block sidebarcontents%} +{{display_population_card(species, population)}} +{%endblock%} diff --git a/uploader/templates/expression-data/select-file.html b/uploader/templates/expression-data/select-file.html new file mode 100644 index 0000000..4ca461e --- /dev/null +++ b/uploader/templates/expression-data/select-file.html @@ -0,0 +1,115 @@ +{%extends "expression-data/base.html"%} +{%from "flash_messages.html" import flash_messages%} +{%from "upload_progress_indicator.html" import upload_progress_indicator%} +{%from "populations/macro-display-population-card.html" import display_population_card%} + +{%block title%}Expression Data — Upload Data{%endblock%} + +{%block pagetitle%}Expression Data — Upload Data{%endblock%} + +{%block contents%} +{{upload_progress_indicator()}} + +<div class="row"> + <h2 class="heading">Upload Expression Data</h2> + + <p>This feature enables you to upload expression data. It expects the data to + be in <strong>tab-separated values (TSV)</strong> files. The data should be + a simple matrix of <em>phenotype × sample</em>, i.e. The first column is a + list of the <em>phenotypes</em> and the first row is a list of + <em>samples/cases</em>.</p> + + <p>If you haven't done so please go to this page to learn the requirements for + file formats and helpful suggestions to enter your data in a fast and easy + way.</p> + + <ol> + <li><strong>PLEASE REVIEW YOUR DATA.</strong>Make sure your data complies + with our system requirements. ( + <a href="{{url_for('species.populations.expression-data.data_review')}}#data-concerns" + title="Details for the data expectations.">Help</a> + )</li> + <li><strong>UPLOAD YOUR DATA FOR DATA VERIFICATION.</strong> We accept + <strong>.csv</strong>, <strong>.txt</strong> and <strong>.zip</strong> + files (<a href="{{url_for('species.populations.expression-data.data_review')}}#file-types" + title="Details for the data expectations.">Help</a>)</li> + </ol> +</div> + +<div class="row"> + <form action="{{url_for( + 'species.populations.expression-data.upload_file', + species_id=species.SpeciesId, + population_id=population.Id)}}" + method="POST" + enctype="multipart/form-data" + id="frm-upload-expression-data"> + {{flash_messages("error-expr-data")}} + + <div class="form-group"> + <legend class="heading">File Type</legend> + + <div class="radio"> + <label for="filetype_average" class="form-check-label"> + <input type="radio" name="filetype" value="average" id="filetype_average" + required="required" class="form-check-input" /> + Average</label> + <p class="form-text text-muted"> + <small>The averages data …</small></p> + </div> + + <div class="radio"> + <label for="filetype_standard_error" class="form-check-label"> + <input type="radio" name="filetype" value="standard-error" + id="filetype_standard_error" required="required" + class="form-check-input" /> + Standard Error + </label> + <p class="form-text text-muted"> + <small>The standard errors computed from the averages …</small></p> + </div> + </div> + + <div class="form-group"> + <span id="no-file-error" class="alert-danger" style="display: none;"> + No file selected + </span> + <label for="file_upload" class="form-label">Select File</label> + <input type="file" name="qc_text_file" id="file_upload" + accept="text/plain, text/tab-separated-values, application/zip" + class="form-control"/> + <p class="form-text text-muted"> + <small>Select the file to upload.</small></p> + </div> + + <button type="submit" + class="btn btn-primary" + data-toggle="modal" + data-target="#upload-progress-indicator">upload file</button> + </form> +</div> +{%endblock%} + +{%block sidebarcontents%} +{{display_population_card(species, population)}} +{%endblock%} + +{%block javascript%} +<script type="text/javascript" src="/static/js/upload_progress.js"></script> +<script type="text/javascript"> + function setup_formdata(form) { + var formdata = new FormData(); + formdata.append( + "qc_text_file", + form.querySelector("input[type='file']").files[0]); + formdata.append( + "filetype", + selected_filetype( + Array.from(form.querySelectorAll("input[type='radio']")))); + return formdata; + } + + setup_upload_handlers( + "frm-upload-expression-data", make_data_uploader(setup_formdata)); +</script> +{%endblock%} diff --git a/uploader/templates/expression-data/select-population.html b/uploader/templates/expression-data/select-population.html new file mode 100644 index 0000000..8555e27 --- /dev/null +++ b/uploader/templates/expression-data/select-population.html @@ -0,0 +1,29 @@ +{%extends "expression-data/base.html"%} +{%from "flash_messages.html" import flash_all_messages%} +{%from "species/macro-display-species-card.html" import display_species_card%} +{%from "populations/macro-select-population.html" import select_population_form%} + +{%block title%}Expression Data{%endblock%} + +{%block pagetitle%}Expression Data{%endblock%} + + +{%block contents%} +{{flash_all_messages()}} + +<div class="row"> + <p>You have selected the species. Now you need to select the population that + the expression data belongs to.</p> +</div> + +<div class="row"> + {{select_population_form(url_for( + "species.populations.expression-data.select_population", + species_id=species.SpeciesId), + populations)}} +</div> +{%endblock%} + +{%block sidebarcontents%} +{{display_species_card(species)}} +{%endblock%} diff --git a/uploader/templates/genotypes/base.html b/uploader/templates/genotypes/base.html new file mode 100644 index 0000000..1b274bf --- /dev/null +++ b/uploader/templates/genotypes/base.html @@ -0,0 +1,12 @@ +{%extends "populations/base.html"%} + +{%block lvl3_breadcrumbs%} +<li {%if activelink=="genotypes"%} + class="breadcrumb-item active" + {%else%} + class="breadcrumb-item" + {%endif%}> + <a href="{{url_for('species.populations.genotypes.index')}}">Genotypes</a> +</li> +{%block lvl4_breadcrumbs%}{%endblock%} +{%endblock%} diff --git a/uploader/templates/genotypes/create-dataset.html b/uploader/templates/genotypes/create-dataset.html new file mode 100644 index 0000000..10331c1 --- /dev/null +++ b/uploader/templates/genotypes/create-dataset.html @@ -0,0 +1,82 @@ +{%extends "genotypes/base.html"%} +{%from "flash_messages.html" import flash_all_messages%} +{%from "populations/macro-display-population-card.html" import display_population_card%} + +{%block title%}Genotypes — Create Dataset{%endblock%} + +{%block pagetitle%}Genotypes — Create Dataset{%endblock%} + +{%block lvl4_breadcrumbs%} +<li {%if activelink=="create-dataset"%} + class="breadcrumb-item active" + {%else%} + class="breadcrumb-item" + {%endif%}> + <a href="{{url_for('species.populations.genotypes.create_dataset', + species_id=species.SpeciesId, + population_id=population.Id)}}">Create Dataset</a> +</li> +{%endblock%} + +{%block contents%} +{{flash_all_messages()}} + +<div class="row"> + <form id="frm-geno-create-dataset" + method="POST" + action="{{url_for('species.populations.genotypes.create_dataset', + species_id=species.SpeciesId, + population_id=population.Id)}}"> + <legend>Create a new Genotype Dataset</legend> + + <div class="form-group"> + <label for="txt-geno-dataset-name" class="form-label">Name</label> + <input type="text" + id="txt-geno-dataset-name" + name="geno-dataset-name" + required="required" + class="form-control" /> + <small class="form-text text-muted"> + <p>This is a short representative, but constrained name for the genotype + dataset.<br /> + The field will only accept letters ('A-Za-z'), numbers (0-9), hyphens + and underscores. Any other character will cause the name to be + rejected.</p></small> + </div> + + <div class="form-group"> + <label for="txt-geno-dataset-fullname" class="form-label">Full Name</label> + <input type="text" + id="txt-geno-dataset-fullname" + name="geno-dataset-fullname" + required="required" + class="form-control" /> + <small class="form-text text-muted"> + <p>This is a longer, more descriptive name for your dataset.</p></small> + </div> + + <div class="form-group"> + <label for="txt-geno-dataset-shortname" + class="form-label">Short Name</label> + <input type="text" + id="txt-geno-dataset-shortname" + name="geno-dataset-shortname" + class="form-control" /> + <small class="form-text text-muted"> + <p>A short name for your dataset. If you leave this field blank, the + short name will be set to the same value as the + "<strong>Name</strong>" field above.</p></small> + </div> + + <div class="form-group"> + <input type="submit" + class="btn btn-primary" + value="create dataset" /> + </div> + </form> +</div> +{%endblock%} + +{%block sidebarcontents%} +{{display_population_card(species, population)}} +{%endblock%} diff --git a/uploader/templates/genotypes/index.html b/uploader/templates/genotypes/index.html new file mode 100644 index 0000000..e749f5a --- /dev/null +++ b/uploader/templates/genotypes/index.html @@ -0,0 +1,28 @@ +{%extends "genotypes/base.html"%} +{%from "flash_messages.html" import flash_all_messages%} +{%from "species/macro-select-species.html" import select_species_form%} + +{%block title%}Genotypes{%endblock%} + +{%block pagetitle%}Genotypes{%endblock%} + + +{%block contents%} +{{flash_all_messages()}} + +<div class="row"> + <p> + This section allows you to upload genotype information for your experiments, + in the case that you have not previously done so. + </p> + <p> + We'll need to link the genotypes to the species and population, so do please + go ahead and select those in the next two steps. + </p> +</div> + +<div class="row"> + {{select_species_form(url_for("species.populations.genotypes.index"), + species)}} +</div> +{%endblock%} diff --git a/uploader/templates/genotypes/list-genotypes.html b/uploader/templates/genotypes/list-genotypes.html new file mode 100644 index 0000000..e4c39eb --- /dev/null +++ b/uploader/templates/genotypes/list-genotypes.html @@ -0,0 +1,148 @@ +{%extends "genotypes/base.html"%} +{%from "flash_messages.html" import flash_all_messages%} +{%from "populations/macro-display-population-card.html" import display_population_card%} + +{%block title%}Genotypes{%endblock%} + +{%block pagetitle%}Genotypes{%endblock%} + +{%block lvl4_breadcrumbs%} +<li {%if activelink=="list-genotypes"%} + class="breadcrumb-item active" + {%else%} + class="breadcrumb-item" + {%endif%}> + <a href="{{url_for('species.populations.genotypes.list_genotypes', + species_id=species.SpeciesId, + population_id=population.Id)}}">List genotypes</a> +</li> +{%endblock%} + +{%block contents%} +{{flash_all_messages()}} + +<div class="row"> + <h2>Genetic Markers</h2> + <p>There are a total of {{total_markers}} currently registered genetic markers + for the "{{species.FullName}}" species. You can click + <a href="{{url_for('species.populations.genotypes.list_markers', + species_id=species.SpeciesId)}}" + title="View genetic markers for species '{{species.FullName}}"> + this link to view the genetic markers + </a>. + </p> +</div> + +<div class="row"> + <h2>Genotype Encoding</h2> + <p> + The genotype encoding used for the "{{population.FullName}}" population from + the "{{species.FullName}}" species is as shown in the table below. + </p> + <table class="table"> + + <thead> + <tr> + <th>Allele Type</th> + <th>Allele Symbol</th> + <th>Allele Value</th> + </tr> + </thead> + + <tbody> + {%for row in genocode%} + <tr> + <td>{{row.AlleleType}}</td> + <td>{{row.AlleleSymbol}}</td> + <td>{{row.DatabaseValue if row.DatabaseValue is not none else "NULL"}}</td> + </tr> + {%else%} + <tr> + <td colspan="7" class="text-info"> + <span class="glyphicon glyphicon-exclamation-sign"></span> + There is no explicit genotype encoding defined for this population. + </td> + </tr> + {%endfor%} + </tbody> + </table> + + {%if genocode | length < 1%} + <a href="#add-genotype-encoding" + title="Add a genotype encoding system for this population" + class="btn btn-primary"> + add genotype encoding + </a> + {%endif%} +</div> + +<div class="row text-danger"> + <h3>Some Important Concepts to Consider/Remember</h3> + <ul> + <li>Reference vs. Non-reference alleles</li> + <li>In <em>GenoCode</em> table, items are ordered by <strong>InbredSet</strong></li> + </ul> + <h3>Possible references</h3> + <ul> + <li>https://mr-dictionary.mrcieu.ac.uk/term/genotype/</li> + <li>https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7363099/</li> + </ul> +</div> + +<div class="row"> + <h2>Genotype Datasets</h2> + + <p>The genotype data is organised under various genotype datasets. You can + click on the link for the relevant dataset to view a little more information + about it.</p> + + {%if dataset is not none%} + <table class="table"> + <thead> + <tr> + <th>Name</th> + <th>Full Name</th> + </tr> + </thead> + + <tbody> + <tr> + <td>{{dataset.Name}}</td> + <td><a href="{{url_for('species.populations.genotypes.view_dataset', + species_id=species.SpeciesId, + population_id=population.Id, + dataset_id=dataset.Id)}}" + title="View details regarding and manage dataset '{{dataset.FullName}}'"> + {{dataset.FullName}}</a></td> + </tr> + </tbody> + </table> + {%else%} + <p class="text-warning"> + <span class="glyphicon glyphicon-exclamation-sign"></span> + There is no genotype dataset defined for this population. + </p> + <p> + <a href="{{url_for('species.populations.genotypes.create_dataset', + species_id=species.SpeciesId, + population_id=population.Id)}}" + title="Create a new genotype dataset for the '{{population.FullName}}' population for the '{{species.FullName}}' species." + class="btn btn-primary"> + create new genotype dataset</a></p> + {%endif%} +</div> +<div class="row text-warning"> + <p> + <span class="glyphicon glyphicon-exclamation-sign"></span> + <strong>NOTE</strong>: Currently the GN2 (and related) system(s) expect a + single genotype dataset. If there is more than one, the system apparently + fails in unpredictable ways. + </p> + <p>Fix this to allow multiple datasets, each with a different assembly from + all the rest.</p> +</div> +{%endblock%} + +{%block sidebarcontents%} +{{display_population_card(species, population)}} +{%endblock%} diff --git a/uploader/templates/genotypes/list-markers.html b/uploader/templates/genotypes/list-markers.html new file mode 100644 index 0000000..9198b44 --- /dev/null +++ b/uploader/templates/genotypes/list-markers.html @@ -0,0 +1,102 @@ +{%extends "genotypes/base.html"%} +{%from "flash_messages.html" import flash_all_messages%} +{%from "species/macro-display-species-card.html" import display_species_card%} + +{%block title%}Genotypes: List Markers{%endblock%} + +{%block pagetitle%}Genotypes: List Markers{%endblock%} + +{%block lvl4_breadcrumbs%} +<li {%if activelink=="list-markers"%} + class="breadcrumb-item active" + {%else%} + class="breadcrumb-item" + {%endif%}> + <a href="{{url_for('species.populations.genotypes.list_markers', + species_id=species.SpeciesId)}}">List markers</a> +</li> +{%endblock%} + +{%block contents%} +{{flash_all_messages()}} + +{%if markers | length > 0%} +<div class="row"> + <p> + There are a total of {{total_markers}} genotype markers for this species. + </p> + <div class="row"> + <div class="col-md-2" style="text-align: start;"> + {%if start_from > 0%} + <a href="{{url_for('species.populations.genotypes.list_markers', + species_id=species.SpeciesId, + start_from=start_from-count, + count=count)}}"> + <span class="glyphicon glyphicon-backward"></span> + Previous + </a> + {%endif%} + </div> + <div class="col-md-8" style="text-align: center;"> + Displaying markers {{start_from+1}} to {{start_from+count if start_from+count < total_markers else total_markers}} of + {{total_markers}} + </div> + <div class="col-md-2" style="text-align: end;"> + {%if start_from + count < total_markers%} + <a href="{{url_for('species.populations.genotypes.list_markers', + species_id=species.SpeciesId, + start_from=start_from+count, + count=count)}}"> + Next + <span class="glyphicon glyphicon-forward"></span> + </a> + {%endif%} + </div> + </div> + <table class="table"> + <thead> + <tr> + <th title="">#</th> + <th title="">Marker Name</th> + <th title="Chromosome">Chr</th> + <th title="Physical location of the marker in megabasepairs"> + Location (Mb)</th> + <th title="">Source</th> + <th title="">Source2</th> + </thead> + + <tbody> + {%for marker in markers%} + <tr> + <td>{{marker.sequence_number}}</td> + <td>{{marker.Marker_Name}}</td> + <td>{{marker.Chr}}</td> + <td>{{marker.Mb}}</td> + <td>{{marker.Source}}</td> + <td>{{marker.Source2}}</td> + </tr> + {%endfor%} + </tbody> + </table> +</div> +{%else%} +<div class="row"> + <p class="text-warning"> + <span class="glyphicon glyphicon-exclamation-sign"></span> + This species does not currently have any genetic markers uploaded, therefore, + there is nothing to display here. + </p> + <p> + <a href="#add-genetic-markers-for-species-{{species.SpeciesId}}" + title="Add genetic markers for this species" + class="btn btn-primary"> + add genetic markers + </a> + </p> +</div> +{%endif%} +{%endblock%} + +{%block sidebarcontents%} +{{display_species_card(species)}} +{%endblock%} diff --git a/uploader/templates/genotypes/select-population.html b/uploader/templates/genotypes/select-population.html new file mode 100644 index 0000000..7c81943 --- /dev/null +++ b/uploader/templates/genotypes/select-population.html @@ -0,0 +1,31 @@ +{%extends "genotypes/base.html"%} +{%from "flash_messages.html" import flash_all_messages%} +{%from "species/macro-display-species-card.html" import display_species_card%} +{%from "populations/macro-select-population.html" import select_population_form%} + +{%block title%}Genotypes{%endblock%} + +{%block pagetitle%}Genotypes{%endblock%} + + +{%block contents%} +{{flash_all_messages()}} + +<div class="row"> + <p> + You have indicated that you intend to upload the genotypes for species + '{{species.FullName}}'. We now just require the population for your + experiment/study, and you should be good to go. + </p> +</div> + +<div class="row"> + {{select_population_form(url_for("species.populations.genotypes.select_population", + species_id=species.SpeciesId), + populations)}} +</div> +{%endblock%} + +{%block sidebarcontents%} +{{display_species_card(species)}} +{%endblock%} diff --git a/uploader/templates/genotypes/view-dataset.html b/uploader/templates/genotypes/view-dataset.html new file mode 100644 index 0000000..e7ceb36 --- /dev/null +++ b/uploader/templates/genotypes/view-dataset.html @@ -0,0 +1,61 @@ +{%extends "genotypes/base.html"%} +{%from "flash_messages.html" import flash_all_messages%} +{%from "populations/macro-display-population-card.html" import display_population_card%} + +{%block title%}Genotypes: View Dataset{%endblock%} + +{%block pagetitle%}Genotypes: View Dataset{%endblock%} + +{%block lvl4_breadcrumbs%} +<li {%if activelink=="view-dataset"%} + class="breadcrumb-item active" + {%else%} + class="breadcrumb-item" + {%endif%}> + <a href="{{url_for('species.populations.genotypes.view_dataset', + species_id=species.SpeciesId, + population_id=population.Id, + dataset_id=dataset.Id)}}">view dataset</a> +</li> +{%endblock%} + +{%block contents%} +{{flash_all_messages()}} + +<div class="row"> + <h2>Genotype Dataset Details</h2> + <table class="table"> + <thead> + <tr> + <th>Name</th> + <th>Full Name</th> + </tr> + </thead> + + <tbody> + <tr> + <td>{{dataset.Name}}</td> + <td>{{dataset.FullName}}</td> + </tr> + </tbody> + </table> +</div> + +<div class="row text-warning"> + <h2>Assembly Details</h2> + + <p>Maybe include the assembly details here if found to be necessary.</p> +</div> + +<div class="row"> + <h2>Genotype Data</h2> + + <p class="text-danger"> + Provide link to enable uploading of genotype data here.</p> +</div> + +{%endblock%} + +{%block sidebarcontents%} +{{display_population_card(species, population)}} +{%endblock%} diff --git a/uploader/templates/index.html b/uploader/templates/index.html index 94060b7..d6f57eb 100644 --- a/uploader/templates/index.html +++ b/uploader/templates/index.html @@ -1,84 +1,99 @@ {%extends "base.html"%} {%from "flash_messages.html" import flash_all_messages%} -{%block title%}Data Upload{%endblock%} +{%block title%}Home{%endblock%} + +{%block pagetitle%}Home{%endblock%} {%block contents%} + <div class="row"> {{flash_all_messages()}} + <div class="explainer"> + <p>Welcome to the <strong>GeneNetwork Data Quality Control and Upload System</strong>. This system is provided to help in uploading your data onto GeneNetwork where you can do analysis on it.</p> - <h1 class="heading">data upload</h1> + <p>The sections below provide an overview of what features the menu items on + the left provide to you. Please peruse the information to get a good + big-picture understanding of what the system provides you and how to get + the most out of it.</p> - <div class="explainer"> - <p>Each of the sections below gives you a different option for data upload. - Please read the documentation for each section carefully to understand what - each section is about.</p> - </div> -</div> + {%block extrapageinfo%}{%endblock%} -<div class="row"> - <h2 class="heading">R/qtl2 Bundles</h2> + <h2>Species</h2> - <div class="explainer"> - <p>This feature combines and extends the two upload methods below. Instead of - uploading one item at a time, the R/qtl2 bundle you upload can contain both - the genotypes data (samples/individuals/cases and their data) and the - expression data.</p> - <p>The R/qtl2 bundle, additionally, can contain extra metadata, that neither - of the methods below can handle.</p> - - <a href="{{url_for('upload.rqtl2.select_species')}}" - title="Upload a zip bundle of R/qtl2 files"> - <button class="btn btn-primary">upload R/qtl2 bundle</button></a> - </div> -</div> + <p>The GeneNetwork service provides datasets and tools for doing genetic + studies — from + <a href="{{gn2server_intro}}" + target="_blank" + title="GeneNetwork introduction — opens in a new tab."> + its introduction</a>: + <blockquote class="blockquote"> + <p>GeneNetwork is a group of linked data sets and tools used to study + complex networks of genes, molecules, and higher order gene function + and phenotypes. …</p> + </blockquote> + </p> -<div class="row"> - <h2 class="heading">Expression Data</h2> + <p>With this in mind, it follows that the data in the system is centered + aroud a variety of species. The <strong>species section</strong> will + list the currently available species in the system, and give you the + ability to add new ones, if the one you want to work on does not currently + exist on GeneNetwork</p> - <div class="explainer"> - <p>This feature enables you to upload expression data. It expects the data to - be in <strong>tab-separated values (TSV)</strong> files. The data should be - a simple matrix of <em>phenotype × sample</em>, i.e. The first column is a - list of the <em>phenotypes</em> and the first row is a list of - <em>samples/cases</em>.</p> - - <p>If you haven't done so please go to this page to learn the requirements for - file formats and helpful suggestions to enter your data in a fast and easy - way.</p> - - <ol> - <li><strong>PLEASE REVIEW YOUR DATA.</strong>Make sure your data complies - with our system requirements. ( - <a href="{{url_for('entry.data_review')}}#data-concerns" - title="Details for the data expectations.">Help</a> - )</li> - <li><strong>UPLOAD YOUR DATA FOR DATA VERIFICATION.</strong> We accept - <strong>.csv</strong>, <strong>.txt</strong> and <strong>.zip</strong> - files (<a href="{{url_for('entry.data_review')}}#file-types" - title="Details for the data expectations.">Help</a>)</li> - </ol> - </div> + <h2>Populations</h2> - <a href="{{url_for('entry.upload_file')}}" - title="Upload your expression data" - class="btn btn-primary">upload expression data</a> -</div> + <p>Your studies will probably focus on a particular subset of the entire + species you are interested in – your population.</p> + <p>Populations are a way to organise the species data so as to link data to + specific know populations for a particular species, e.g. The BXD + population of mice (Mus musculus)</p> + <p>In older GeneNetwork documentation, you might run into the term + <em>InbredSet</em>. Should you run into it, it is a term that we've + deprecated that essentially just means the population.</p> -<div class="row"> - <h2 class="heading">samples/cases</h2> + <h2>Samples</h2> - <div class="explainer"> - <p>For the expression data above, you need the samples/cases in your file to - already exist in the GeneNetwork database. If there are any samples that do - not already exist the upload of the expression data will fail.</p> - <p>This section gives you the opportunity to upload any missing samples</p> - </div> + <p>These are the samples or individuals (sometimes cases) that were involved + in the experiment, and from whom the data was derived.</p> + + <h2>Genotype Data</h2> + + <p>This section will allow you to view and upload the genetic markers for + your species, and the genotype encodings used for your particular + population.</p> + <p>While, technically, genetic markers relate to the species in general, and + not to a particular population, the data (allele information) itself + relates to the particular population it was generated from – + specifically, to the actual individuals used in the experiment.</p> + <p>This is the reason why the genotype data information comes under the + population, and will check for the prior existence of the related + samples/individuals before attempting an upload of your data.</p> + + <h2>Expression Data</h2> + + <p class="text-danger"> + <span class="glyphicon glyphicon-exclamation-sign"></span> + <strong>TODO</strong>: Document this …</p> - <a href="{{url_for('samples.select_species')}}" - title="Upload samples/cases/individuals for your data" - class="btn btn-primary">upload Samples/Cases</a> + <h2>Phenotype Data</h2> + + <p class="text-danger"> + <span class="glyphicon glyphicon-exclamation-sign"></span> + <strong>TODO</strong>: Document this …</p> + + <h2>Individual Data</h2> + + <p class="text-danger"> + <span class="glyphicon glyphicon-exclamation-sign"></span> + <strong>TODO</strong>: Document this …</p> + + <h2>RNA-Seq Data</h2> + + <p class="text-danger"> + <span class="glyphicon glyphicon-exclamation-sign"></span> + <strong>TODO</strong>: Document this …</p> + </div> </div> {%endblock%} diff --git a/uploader/templates/login.html b/uploader/templates/login.html index 6ebf72e..1f71416 100644 --- a/uploader/templates/login.html +++ b/uploader/templates/login.html @@ -1,32 +1,11 @@ -{%extends "base.html"%} -{%from "flash_messages.html" import flash_all_messages%} +{%extends "index.html"%} {%block title%}Data Upload{%endblock%} -{%block contents%} -<div class="row"> - {{flash_all_messages()}} - - <h1 class="heading">log in</h1> - - <div class="explainer"> - <p> - This system enables you to upload data onto GeneNetwork. In order to do - that correctly, we need to know who you are.</p> - <p> - If you already have an account with GeneNetwork, you can simply click the - login button below, after which you can upload your data.<br /> - </p> - <a href="{{authserver_authorise_uri()}}" class="btn btn-primary" - style="display:block;width:15em;align:center;margin:1em 3em;"> - log in</a> - <p> - If you do not have an account with GeneNetwork, go to - <a href="{{gn2server_uri()}}" - title="GeneNetwork Service." - target="_blank">GeneNetwork</a> - and register for an account, then come back here to login and upload.</a> - </div> -</div> +{%block pagetitle%}log in{%endblock%} +{%block extrapageinfo%} +<p class="text-dark text-primary"> + You <strong>do need to be logged in</strong> to upload data onto this system. + Please do that by clicking the "Log In" button at the top of the page.</p> {%endblock%} diff --git a/uploader/templates/macro-table-pagination.html b/uploader/templates/macro-table-pagination.html new file mode 100644 index 0000000..292c531 --- /dev/null +++ b/uploader/templates/macro-table-pagination.html @@ -0,0 +1,26 @@ +{%macro table_pagination(start_at, page_count, total_count, base_uri, name)%} +{%set ns = namespace(forward_uri=base_uri, back_uri=base_uri)%} +{%set ns.forward_uri="brr"%} + <div class="row"> + <div class="col-md-2" style="text-align: start;"> + {%if start_at > 0%} + <a href="{{base_uri + + '?start_at='+((start_at-page_count)|string) + + '&count='+(page_count|string)}}"> + <span class="glyphicon glyphicon-backward"></span> + Previous + </a> + {%endif%} + </div> + <div class="col-md-8" style="text-align: center;"> + Displaying {{name}} {{start_at+1}} to {{start_at+page_count if start_at+page_count < total_count else total_count}} of {{total_count}}</div> + <div class="col-md-2" style="text-align: end;"> + {%if start_at + page_count < total_count%} + <a href="{{base_uri + + '?start_at='+((start_at+page_count)|string) + + '&count='+(page_count|string)}}"> + Next<span class="glyphicon glyphicon-forward"></span></a> + {%endif%} + </div> + </div> +{%endmacro%} diff --git a/uploader/templates/parse_results.html b/uploader/templates/parse_results.html deleted file mode 100644 index e2bf7f0..0000000 --- a/uploader/templates/parse_results.html +++ /dev/null @@ -1,30 +0,0 @@ -{%extends "base.html"%} -{%from "errors_display.html" import errors_display%} - -{%block title%}Parse Results{%endblock%} - -{%block contents%} -<h1 class="heading">{{job_name}}: parse results</h2> - -{%if user_aborted%} -<span class="alert-warning">Job aborted by the user</span> -{%endif%} - -{{errors_display(errors, "No errors found in the file", "We found the following errors", True)}} - -{%if errors | length == 0 and not user_aborted %} -<form method="post" action="{{url_for('dbinsert.select_platform')}}"> - <input type="hidden" name="job_id" value="{{job_id}}" /> - <input type="submit" value="update database" class="btn btn-primary" /> -</form> -{%endif%} - -{%if errors | length > 0 or user_aborted %} -<br /> -<a href="{{url_for('entry.upload_file')}}" title="Back to index page." - class="btn btn-primary"> - Go back -</a> -{%endif%} - -{%endblock%} diff --git a/uploader/templates/phenotypes/add-phenotypes.html b/uploader/templates/phenotypes/add-phenotypes.html new file mode 100644 index 0000000..196bc69 --- /dev/null +++ b/uploader/templates/phenotypes/add-phenotypes.html @@ -0,0 +1,231 @@ +{%extends "phenotypes/base.html"%} +{%from "flash_messages.html" import flash_all_messages%} +{%from "macro-table-pagination.html" import table_pagination%} +{%from "phenotypes/macro-display-pheno-dataset-card.html" import display_pheno_dataset_card%} + +{%block title%}Phenotypes{%endblock%} + +{%block pagetitle%}Phenotypes{%endblock%} + +{%block lvl4_breadcrumbs%} +<li {%if activelink=="add-phenotypes"%} + class="breadcrumb-item active" + {%else%} + class="breadcrumb-item" + {%endif%}> + <a href="{{url_for('species.populations.phenotypes.add_phenotypes', + species_id=species.SpeciesId, + population_id=population.Id, + dataset_id=dataset.Id)}}">View Datasets</a> +</li> +{%endblock%} + +{%block contents%} +{{flash_all_messages()}} + +<div class="row"> + <form id="frm-add-phenotypes" + method="POST" + enctype="multipart/form-data" + action="{{url_for('species.populations.phenotypes.add_phenotypes', + species_id=species.SpeciesId, + population_id=population.Id, + dataset_id=dataset.Id)}}"> + <legend>Add New Phenotypes</legend> + + <div class="form-text help-block"> + <p>Select the zip file bundle containing information on the phenotypes you + wish to upload, then click the "Upload Phenotypes" button below to + upload the data.</p> + <p>See the <a href="#section-file-formats">File Formats</a> section below + to get an understanding of what is expected of the bundle files you + upload.</p> + <p><strong>This will not update any existing phenotypes!</strong></p> + </div> + + <div class="form-group"> + <label for="finput-phenotypes-bundle" class="form-label"> + Phenotypes Bundle</label> + <input type="file" + id="finput-phenotypes-bundle" + name="phenotypes-bundle" + accept="application/zip, .zip" + required="required" + class="form-control" /> + </div> + + <div class="form-group"> + <input type="submit" + value="upload phenotypes" + class="btn btn-primary" /> + </div> + </form> +</div> + +<div class="row"> + <h2 class="heading" id="section-file-formats">File Formats</h2> + <p>We accept an extended form of the + <a href="https://kbroman.org/qtl2/assets/vignettes/input_files.html#format-of-the-data-files" + title="R/qtl2 software input file format documentation"> + input files' format used with the R/qtl2 software</a> as a single ZIP + file</p> + <p>The files that are used for this feature are: + <ul> + <li>the <em>control</em> file</li> + <li><em>pheno</em> file(s)</li> + <li><em>phenocovar</em> file(s)</li> + <li><em>phenose</em> files(s)</li> + </ul> + </p> + <p>Other files within the bundle will be ignored, for this feature.</p> + <p>The following section will detail the expectations for each of the + different file types within the uploaded ZIP file bundle for phenotypes:</p> + + <h3 class="subheading">Control File</h3> + <p>There <strong>MUST be <em>one, and only one</em></strong> file that acts + as the control file. This file can be: + <ul> + <li>a <em>JSON</em> file, or</li> + <li>a <em>YAML</em> file.</li> + </ul> + </p> + + <p>The control file is useful for defining things about the bundle such as:</p> + <ul> + <li>The field separator value (default: <code>sep: ','</code>). There can + only ever be one field separator and it <strong>MUST</strong> be the same + one for <strong>ALL</strong> files in the bundle.</li> + <li>The comment character (default: <code>comment.char: '#'</code>). Any + line that starts with this character will be considered a comment line and + be ignored in its entirety.</li> + <li>Code for missing values (default: <code>na.strings: 'NA'</code>). You + can specify more than one code to indicate missing values, e.g. + <code>{…, "na.strings": ["NA", "N/A", "-"], …}</code></li> + </ul> + + <h3 class="subheading"><em>pheno</em> File(s)</h3> + <p>These files are the main data files. You must have at least one of these + files in your bundle for it to be valid for this step.</p> + <p>The data is a matrix of <em>individuals × phenotypes</em> by default, as + below:<br /> + <code> + id,10001,10002,10003,10004,…<br /> + BXD1,61.400002,54.099998,483,49.799999,…<br /> + BXD2,49,50.099998,403,45.5,…<br /> + BXD5,62.5,53.299999,501,62.900002,…<br /> + BXD6,53.099998,55.099998,403,NA,…<br /> + â‹®<br /></code> + </p> + <p>If the <code>pheno_transposed</code> value is set to <code>True</code>, + then the data will be a <em>phenotypes × individuals</em> matrix as in the + example below:<br /> + <code> + id,BXD1,BXD2,BXD5,BXD6,…<br /> + 10001,61.400002,49,62.5,53.099998,…<br /> + 10002,54.099998,50.099998,53.299999,55.099998,…<br /> + 10003,483,403,501,403,…<br /> + 10004,49.799999,45.5,62.900002,NA,…<br /> + â‹® + </code> + </p> + + + <h3 class="subheading"><em>phenocovar</em> File(s)</h3> + <p>At least one phenotypes metadata file with the metadata values such as + descriptions, PubMed Identifier, publication titles (if present), etc.</p> + <p>The data in this/these file(s) is a matrix of + <em>phenotypes × phenotypes-covariates</em>. The first column is always the + phenotype names/identifiers — same as in the R/qtl2 format.</p> + <p><em>phenocovar</em> files <strong>should never be transposed</strong>!</p> + <p>This file <strong>MUST</strong> be present in the bundle, and have data for + the bundle to be considered valid by our system for this step.<br /> + In addition to that, the following are the fields that <strong>must be + present</strong>, and + have values, in the file before the file is considered valid: + <ul> + <li><em>description</em>: A description for each phenotype. Useful + for users to know what the phenotype is about.</li> + <li><em>units</em>: The units of measurement for the phenotype, + e.g. milligrams for brain weight, centimetres/millimetres for + tail-length, etc.</li> + </ul></p> + + <p>The following <em>optional</em> fields can also be provided: + <ul> + <li><em>pubmedid</em>: A PubMed Identifier for the publication where + the phenotype is published. If this field is not provided, the system will + assume your phenotype is not published.</li> + </ul> + </p> + <p>These files will be marked up in the control file with the + <code>phenocovar</code> key, as in the examples below: + <ol> + <li>JSON: single file<br /> + <code>{<br /> + â‹®,<br /> + "phenocovar": "your_covariates_file.csv",<br /> + â‹®<br /> + } + </code> + </li> + <li>JSON: multiple files<br /> + <code>{<br /> + â‹®,<br /> + "phenocovar": [<br /> + "covariates_file_01.csv",<br /> + "covariates_file_01.csv",<br /> + â‹®<br /> + ],<br /> + â‹®<br /> + } + </code> + </li> + <li>YAML: single file or<br /> + <code> + â‹®<br /> + phenocovar: your_covariates_file.csv<br /> + â‹® + </code> + </li> + <li>YAML: multiple files<br /> + <code> + â‹®<br /> + phenocovar:<br /> + - covariates_file_01.csv<br /> + - covariates_file_02.csv<br /> + - covariates_file_03.csv<br /> + …<br /> + â‹® + </code> + </li> + </ol> + </p> + + <h3 class="subheading"><em>phenose</em> and <em>phenonum</em> File(s)</h3> + <p>These are extensions to the R/qtl2 standard, i.e. these types ofs file are + not supported by the original R/qtl2 file format</p> + <p>We use these files to upload the standard errors (<em>phenose</em>) when + the data file (<em>pheno</em>) is average data. In that case, the + <em>phenonum</em> file(s) contains the number of individuals that were + involved when computing the averages.</p> + <p>Both types of files are matrices of <em>individuals × phenotypes</em> by + default. Like the related <em>pheno</em> files, if + <code>pheno_transposed: True</code>, then the file will be a matrix of + <em>phenotypes × individuals</em>.</p> +</div> + +<div class="row text-warning"> + <h3 class="subheading">Notes for Devs (well… Fred, really.)</h3> + <p>Use the following resources for automated retrieval of certain data</p> + <ul> + <li><a href="https://www.ncbi.nlm.nih.gov/pmc/tools/developers/" + title="NCBI APIs: Retrieve articles' metadata etc."> + NCBI APIS</a></li> + </ul> +</div> + +{%endblock%} + +{%block sidebarcontents%} +{{display_pheno_dataset_card(species, population, dataset)}} +{%endblock%} diff --git a/uploader/templates/phenotypes/base.html b/uploader/templates/phenotypes/base.html new file mode 100644 index 0000000..3bc5dea --- /dev/null +++ b/uploader/templates/phenotypes/base.html @@ -0,0 +1,12 @@ +{%extends "populations/base.html"%} + +{%block lvl3_breadcrumbs%} +<li {%if activelink=="phenotypes"%} + class="breadcrumb-item active" + {%else%} + class="breadcrumb-item" + {%endif%}> + <a href="{{url_for('species.populations.phenotypes.index')}}">Phenotypes</a> +</li> +{%block lvl4_breadcrumbs%}{%endblock%} +{%endblock%} diff --git a/uploader/templates/phenotypes/create-dataset.html b/uploader/templates/phenotypes/create-dataset.html new file mode 100644 index 0000000..93de92f --- /dev/null +++ b/uploader/templates/phenotypes/create-dataset.html @@ -0,0 +1,106 @@ +{%extends "phenotypes/base.html"%} +{%from "flash_messages.html" import flash_all_messages%} +{%from "macro-table-pagination.html" import table_pagination%} +{%from "populations/macro-display-population-card.html" import display_population_card%} + +{%block title%}Phenotypes{%endblock%} + +{%block pagetitle%}Phenotypes{%endblock%} + +{%block lvl4_breadcrumbs%} +<li {%if activelink=="create-dataset"%} + class="breadcrumb-item active" + {%else%} + class="breadcrumb-item" + {%endif%}> + <a href="{{url_for('species.populations.phenotypes.create_dataset', + species_id=species.SpeciesId, + population_id=population.Id)}}">Create Datasets</a> +</li> +{%endblock%} + +{%block contents%} +{{flash_all_messages()}} + +<div class="row"> + <p>Create a new phenotype dataset.</p> +</div> + +<div class="row"> + <form id="frm-create-pheno-dataset" + action="{{url_for('species.populations.phenotypes.create_dataset', + species_id=species.SpeciesId, + population_id=population.Id)}}" + method="POST"> + + <div class="form-group"> + <label class="form-label" for="txt-dataset-name">Name</label> + {%if errors["dataset-name"] is defined%} + <small class="form-text text-muted danger"> + <p>{{errors["dataset-name"]}}</p></small> + {%endif%} + <input type="text" + name="dataset-name" + id="txt-dataset-name" + value="{{original_formdata.get('dataset-name') or (population.InbredSetCode + 'Publish')}}" + {%if errors["dataset-name"] is defined%} + class="form-control danger" + {%else%} + class="form-control" + {%endif%} + required="required" /> + <small class="form-text text-muted"> + <p>A short representative name for the dataset.</p> + <p>Recommended: Use the population code and append "Publish" at the end. + <br />This field will only accept names composed of + letters ('A-Za-z'), numbers (0-9), hyphens and underscores.</p> + </small> + </div> + + <div class="form-group"> + <label class="form-label" for="txt-dataset-fullname">Full Name</label> + {%if errors["dataset-fullname"] is defined%} + <small class="form-text text-muted danger"> + <p>{{errors["dataset-fullname"]}}</p></small> + {%endif%} + <input id="txt-dataset-fullname" + name="dataset-fullname" + type="text" + value="{{original_formdata.get('dataset-fullname', '')}}" + {%if errors["dataset-fullname"] is defined%} + class="form-control danger" + {%else%} + class="form-control" + {%endif%} + required="required" /> + <small class="form-text text-muted"> + <p>A longer, descriptive name for the dataset — useful for humans. + </p></small> + </div> + + <div class="form-group"> + <label class="form-label" for="txt-dataset-shortname">Short Name</label> + <input id="txt-dataset-shortname" + name="dataset-shortname" + type="text" + class="form-control" + value="{{original_formdata.get('dataset-shortname') or (population.InbredSetCode + ' Publish')}}" /> + <small class="form-text text-muted"> + <p>An optional, short name for the dataset. <br /> + If this is not provided, it will default to the value provided for the + <strong>Name</strong> field above.</p></small> + </div> + + <div class="form-group"> + <input type="submit" + class="btn btn-primary" + value="create phenotype dataset" /> + </div> + + </form> +</div> +{%endblock%} + +{%block sidebarcontents%} +{{display_population_card(species, population)}} +{%endblock%} diff --git a/uploader/templates/phenotypes/index.html b/uploader/templates/phenotypes/index.html new file mode 100644 index 0000000..0c691e6 --- /dev/null +++ b/uploader/templates/phenotypes/index.html @@ -0,0 +1,26 @@ +{%extends "phenotypes/base.html"%} +{%from "flash_messages.html" import flash_all_messages%} +{%from "species/macro-select-species.html" import select_species_form%} + +{%block title%}Phenotypes{%endblock%} + +{%block pagetitle%}Phenotypes{%endblock%} + + +{%block contents%} +{{flash_all_messages()}} + +<div class="row"> + <p>This section deals with phenotypes that + <span class="text-warning"> + <span class="glyphicon glyphicon-exclamation-sign"></span> + … what are the characteristics of these phenotypes? …</span></p> + <p>Select the species to begin the process of viewing/uploading data about + your phenotypes</p> +</div> + +<div class="row"> + {{select_species_form(url_for("species.populations.phenotypes.index"), + species)}} +</div> +{%endblock%} diff --git a/uploader/templates/phenotypes/list-datasets.html b/uploader/templates/phenotypes/list-datasets.html new file mode 100644 index 0000000..2eaf43a --- /dev/null +++ b/uploader/templates/phenotypes/list-datasets.html @@ -0,0 +1,65 @@ +{%extends "phenotypes/base.html"%} +{%from "flash_messages.html" import flash_all_messages%} +{%from "populations/macro-display-population-card.html" import display_population_card%} + +{%block title%}Phenotypes{%endblock%} + +{%block pagetitle%}Phenotypes{%endblock%} + +{%block lvl4_breadcrumbs%} +<li {%if activelink=="list-datasets"%} + class="breadcrumb-item active" + {%else%} + class="breadcrumb-item" + {%endif%}> + <a href="{{url_for('species.populations.phenotypes.list_datasets', + species_id=species.SpeciesId, + population_id=population.Id)}}">List Datasets</a> +</li> +{%endblock%} + +{%block contents%} +{{flash_all_messages()}} + +<div class="row"> + {%if datasets | length > 0%} + <p>The dataset(s) available for this population is/are:</p> + + <table class="table"> + <thead> + <tr> + <th>Name</th> + <th>Full Name</th> + <th>Short Name</th> + </tr> + </thead> + + <tbody> + {%for dataset in datasets%} + <tr> + <td><a href="{{url_for('species.populations.phenotypes.view_dataset', + species_id=species.SpeciesId, + population_id=population.Id, + dataset_id=dataset.Id)}}">{{dataset.Name}}</a></td> + <td>{{dataset.FullName}}</td> + <td>{{dataset.ShortName}}</td> + </tr> + {%endfor%} + </tbody> + </table> + {%else%} + <p class="text-warning"> + <span class="glyphicon glyphicon-exclamation-sign"></span> + There is no dataset for this population!</p> + <p><a href="{{url_for('species.populations.phenotypes.create_dataset', + species_id=species.SpeciesId, + population_id=population.Id)}}" + class="btn btn-primary" + title="Create a new phenotype dataset.">create dataset</a></p> + {%endif%} +</div> +{%endblock%} + +{%block sidebarcontents%} +{{display_population_card(species, population)}} +{%endblock%} diff --git a/uploader/templates/phenotypes/macro-display-pheno-dataset-card.html b/uploader/templates/phenotypes/macro-display-pheno-dataset-card.html new file mode 100644 index 0000000..11b108b --- /dev/null +++ b/uploader/templates/phenotypes/macro-display-pheno-dataset-card.html @@ -0,0 +1,31 @@ +{%from "populations/macro-display-population-card.html" import display_population_card%} + +{%macro display_pheno_dataset_card(species, population, dataset)%} +{{display_population_card(species, population)}} + +<div class="card"> + <div class="card-body"> + <h5 class="card-title">Phenotypes' Dataset</h5> + <div class="card-text"> + <table class="table"> + <tbody> + <tr> + <td>Name</td> + <td>{{dataset.Name}}</td> + </tr> + + <tr> + <td>Full Name</td> + <td>{{dataset.FullName}}</td> + </tr> + + <tr> + <td>Short Name</td> + <td>{{dataset.ShortName}}</td> + </tr> + </tbody> + </table> + </div> + </div> +</div> +{%endmacro%} diff --git a/uploader/templates/phenotypes/select-population.html b/uploader/templates/phenotypes/select-population.html new file mode 100644 index 0000000..eafd4a7 --- /dev/null +++ b/uploader/templates/phenotypes/select-population.html @@ -0,0 +1,28 @@ +{%extends "phenotypes/base.html"%} +{%from "flash_messages.html" import flash_all_messages%} +{%from "species/macro-display-species-card.html" import display_species_card%} +{%from "populations/macro-select-population.html" import select_population_form%} + +{%block title%}Phenotypes{%endblock%} + +{%block pagetitle%}Phenotypes{%endblock%} + + +{%block contents%} +{{flash_all_messages()}} + +<div class="row"> + <p>Select the population for your phenotypes to view and manage the phenotype + datasets that relate to it.</p> +</div> + +<div class="row"> + {{select_population_form(url_for("species.populations.phenotypes.select_population", + species_id=species.SpeciesId), + populations)}} +</div> +{%endblock%} + +{%block sidebarcontents%} +{{display_species_card(species)}} +{%endblock%} diff --git a/uploader/templates/phenotypes/view-dataset.html b/uploader/templates/phenotypes/view-dataset.html new file mode 100644 index 0000000..b136bb6 --- /dev/null +++ b/uploader/templates/phenotypes/view-dataset.html @@ -0,0 +1,96 @@ +{%extends "phenotypes/base.html"%} +{%from "flash_messages.html" import flash_all_messages%} +{%from "macro-table-pagination.html" import table_pagination%} +{%from "populations/macro-display-population-card.html" import display_population_card%} + +{%block title%}Phenotypes{%endblock%} + +{%block pagetitle%}Phenotypes{%endblock%} + +{%block lvl4_breadcrumbs%} +<li {%if activelink=="view-dataset"%} + class="breadcrumb-item active" + {%else%} + class="breadcrumb-item" + {%endif%}> + <a href="{{url_for('species.populations.phenotypes.view_dataset', + species_id=species.SpeciesId, + population_id=population.Id, + dataset_id=dataset.Id)}}">View Datasets</a> +</li> +{%endblock%} + +{%block contents%} +{{flash_all_messages()}} + +<div class="row"> + <p>The basic dataset details are:</p> + + <table class="table"> + <thead> + <tr> + <th>Name</th> + <th>Full Name</th> + <th>Short Name</th> + </tr> + </thead> + + <tbody> + <tr> + <td>{{dataset.Name}}</td> + <td>{{dataset.FullName}}</td> + <td>{{dataset.ShortName}}</td> + </tr> + </tbody> + </table> +</div> + +<div class="row"> + <p><a href="{{url_for('species.populations.phenotypes.add_phenotypes', + species_id=species.SpeciesId, + population_id=population.Id, + dataset_id=dataset.Id)}}" + title="Add a bunch of phenotypes" + class="btn btn-primary">Add phenotypes</a></p> +</div> + +<div class="row"> + <h2>Phenotype Data</h2> + + <p>This dataset has a total of {{phenotype_count}} phenotypes.</p> + + {{table_pagination(start_from, count, phenotype_count, url_for('species.populations.phenotypes.view_dataset', species_id=species.SpeciesId, population_id=population.Id, dataset_id=dataset.Id), "phenotypes")}} + + <table class="table"> + <thead> + <tr> + <th>#</th> + <th>Record</th> + <th>Description</th> + </tr> + </thead> + + <tbody> + {%for pheno in phenotypes%} + <tr> + <td>{{pheno.sequence_number}}</td> + <td><a href="{{url_for('species.populations.phenotypes.view_phenotype', + species_id=species.SpeciesId, + population_id=population.Id, + dataset_id=dataset.Id, + xref_id=pheno['pxr.Id'])}}" + title="View phenotype details"> + {{pheno.InbredSetCode}}_{{pheno["pxr.Id"]}}</a></td> + <td>{{pheno.Post_publication_description or pheno.Pre_publication_abbreviation or pheno.Original_description}}</td> + </tr> + {%else%} + <tr><td colspan="5"></td></tr> + {%endfor%} + </tbody> + </table> +</div> +{%endblock%} + +{%block sidebarcontents%} +{{display_population_card(species, population)}} +{%endblock%} diff --git a/uploader/templates/phenotypes/view-phenotype.html b/uploader/templates/phenotypes/view-phenotype.html new file mode 100644 index 0000000..99bb8e5 --- /dev/null +++ b/uploader/templates/phenotypes/view-phenotype.html @@ -0,0 +1,126 @@ +{%extends "phenotypes/base.html"%} +{%from "flash_messages.html" import flash_all_messages%} +{%from "populations/macro-display-population-card.html" import display_population_card%} + +{%block title%}Phenotypes{%endblock%} + +{%block pagetitle%}Phenotypes{%endblock%} + +{%block lvl4_breadcrumbs%} +<li {%if activelink=="view-phenotype"%} + class="breadcrumb-item active" + {%else%} + class="breadcrumb-item" + {%endif%}> + <a href="{{url_for('species.populations.phenotypes.view_phenotype', + species_id=species.SpeciesId, + population_id=population.Id, + dataset_id=dataset.Id, + xref_id=xref_id)}}">View Datasets</a> +</li> +{%endblock%} + +{%block contents%} +{{flash_all_messages()}} + +<div class="row"> + <div class="panel panel-default"> + <div class="panel-heading"><strong>Basic Phenotype Details</strong></div> + + <table class="table"> + <tbody> + <tr> + <td><strong>Phenotype</strong></td> + <td>{{phenotype.Post_publication_description or phenotype.Pre_publication_abbreviation or phenotype.Original_description}} + </tr> + <tr> + <td><strong>Cross-Reference ID</strong></td> + <td>{{phenotype.xref_id}}</td> + </tr> + <tr> + <td><strong>Collation</strong></td> + <td>{{dataset.FullName}}</td> + </tr> + <tr> + <td><strong>Units</strong></td> + <td>{{phenotype.Units}}</td> + </tr> + </tbody> + </table> + + <form action="#edit-delete-phenotype" + method="POST" + id="frm-delete-phenotype"> + + <input type="hidden" name="species_id" value="{{species.SpeciesId}}" /> + <input type="hidden" name="population_id" value="{{population.Id}}" /> + <input type="hidden" name="dataset_id" value="{{dataset.Id}}" /> + <input type="hidden" name="phenotype_id" value="{{phenotype.Id}}" /> + + <div class="btn-group btn-group-justified"> + <div class="btn-group"> + {%if "group:resource:edit-resource" in privileges%} + <input type="submit" + title="Edit the values for the phenotype. This is meant to be used when you need to update only a few values." + class="btn btn-primary not-implemented" + value="edit" /> + {%endif%} + </div> + <div class="btn-group"></div> + <div class="btn-group"> + {%if "group:resource:delete-resource" in privileges%} + <input type="submit" + title="Delete the entire phenotype. This is useful when you need to change data for most or all of the fields for this phenotype." + class="btn btn-danger not-implemented" + value="delete" /> + {%endif%} + </div> + </div> + </form> + </div> +</div> + +<div class="row"> + <div class="panel panel-default"> + <div class="panel-heading"><strong>Phenotype Data</strong></div> + {%if "group:resource:view-resource" in privileges%} + <table class="table"> + <thead> + <tr> + <th>#</th> + <th>Sample</th> + <th>Value</th> + <th>Symbol</th> + <th>SE</th> + <th>N</th> + </tr> + </thead> + + <tbody> + {%for item in phenotype.data%} + <tr> + <td>{{loop.index}}</td> + <td>{{item.StrainName}}</td> + <td>{{item.value}}</td> + <td>{{item.Symbol or "-"}}</td> + <td>{{item.error or "-"}}</td> + <td>{{item.count or "-"}}</td> + </tr> + {%endfor%} + </tbody> + </table> + {%else%} + <p class="text-danger"> + <span class="glyphicon glyphicon-exclamation-sign"></span> + You do not currently have privileges to view this phenotype in greater + detail. + </p> + {%endif%} + </div> +</div> + +{%endblock%} + +{%block sidebarcontents%} +{{display_population_card(species, population)}} +{%endblock%} diff --git a/uploader/templates/platforms/base.html b/uploader/templates/platforms/base.html new file mode 100644 index 0000000..dac965f --- /dev/null +++ b/uploader/templates/platforms/base.html @@ -0,0 +1,13 @@ +{%extends "species/base.html"%} + +{%block lvl3_breadcrumbs%} +<li {%if activelink=="platforms"%} + class="breadcrumb-item active" + {%else%} + class="breadcrumb-item" + {%endif%}> + <a href="{{url_for('species.populations.platforms.index')}}"> + Sequencing Platforms</a> +</li> +{%block lvl4_breadcrumbs%}{%endblock%} +{%endblock%} diff --git a/uploader/templates/platforms/create-platform.html b/uploader/templates/platforms/create-platform.html new file mode 100644 index 0000000..0866d5e --- /dev/null +++ b/uploader/templates/platforms/create-platform.html @@ -0,0 +1,124 @@ +{%extends "platforms/base.html"%} +{%from "flash_messages.html" import flash_all_messages%} +{%from "species/macro-display-species-card.html" import display_species_card%} + +{%block title%}Platforms — Create Platforms{%endblock%} + +{%block pagetitle%}Platforms — Create Platforms{%endblock%} + +{%block lvl3_breadcrumbs%} +<li {%if activelink=="create-platform"%} + class="breadcrumb-item active" + {%else%} + class="breadcrumb-item" + {%endif%}> + <a href="{{url_for('species.platforms.create_platform', + species_id=species.SpeciesId)}}">create platform</a> +</li> +{%endblock%} + +{%block contents%} +{{flash_all_messages()}} + +<div class="row"> + <h2>Create New Platform</h2> + + <p>You can create a new genetic sequencing platform below.</p> +</div> + +<div class="row"> + <form id="frm-create-platform" + method="POST" + action="{{url_for('species.platforms.create_platform', + species_id=species.SpeciesId)}}"> + + <div class="form-group"> + <label for="txt-geo-platform" class="form-label">GEO Platform</label> + <input type="text" + id="txt-geo-platform" + name="geo-platform" + required="required" + class="form-control" /> + <small class="form-text text-muted"> + <p>This is the platform's + <a href="https://www.ncbi.nlm.nih.gov/geo/browse/?view=platforms&tax={{species.TaxonomyId}}" + title="Platforms for '{{species.FullName}}' on NCBI"> + accession value on NCBI</a>. If you do not know the value, click the + link and search on NCBI for species '{{species.FullName}}'.</p></small> + </div> + + <div class="form-group"> + <label for="txt-platform-name" class="form-label">Platform Name</label> + <input type="text" + id="txt-platform-name" + name="platform-name" + required="required" + class="form-control" /> + <small class="form-text text-muted"> + <p>This is name of the genetic sequencing platform.</p></small> + </div> + + <div class="form-group"> + <label for="txt-platform-shortname" class="form-label"> + Platform Short Name</label> + <input type="text" + id="txt-platform-shortname" + name="platform-shortname" + required="required" + class="form-control" /> + <small class="form-text text-muted"> + <p>Use the following conventions for this field: + <ol> + <li>Start with a 4-letter vendor code, e.g. "Affy" for "Affymetrix", "Illu" for "Illumina", etc.</li> + <li>Append an underscore to the 4-letter vendor code</li> + <li>Use the name of the array given by the vendor, e.g. U74AV2, MOE430A, etc.</li> + </ol> + </p> + </small> + </div> + + <div class="form-group"> + <label for="txt-platform-title" class="form-label">Platform Title</label> + <input type="text" + id="txt-platform-title" + name="platform-title" + required="required" + class="form-control" /> + <small class="form-text text-muted"> + <p>The full platform title. Sometimes, this is the same as the Platform + Name above.</p></small> + </div> + + <div class="form-group"> + <label for="txt-go-tree-value" class="form-label">GO Tree Value</label> + <input type="text" + id="txt-go-tree-value" + name="go-tree-value" + class="form-control" /> + <small class="form-text text-muted"> + <p>This is a Chip identification value useful for analysis with the + <strong> + <a href="https://www.geneweaver.org/" + title="Go to the GeneWeaver site." + target="_blank">GeneWeaver</a></strong> + and + <strong> + <a href="https://www.webgestalt.org/" + title="Go to the WEB-based GEne SeT AnaLysis Toolkit site." + target="_blank">WebGestalt</a></strong> + tools.<br /> + This can be left blank for custom platforms.</p></small> + </div> + + <div class="form-group"> + <input type="submit" + value="create new platform" + class="btn btn-primary" /> + </div> + </form> +</div> +{%endblock%} + +{%block sidebarcontents%} +{{display_species_card(species)}} +{%endblock%} diff --git a/uploader/templates/platforms/index.html b/uploader/templates/platforms/index.html new file mode 100644 index 0000000..35b6464 --- /dev/null +++ b/uploader/templates/platforms/index.html @@ -0,0 +1,21 @@ +{%extends "platforms/base.html"%} +{%from "flash_messages.html" import flash_all_messages%} +{%from "species/macro-select-species.html" import select_species_form%} + +{%block title%}Platforms{%endblock%} + +{%block pagetitle%}Platforms{%endblock%} + + +{%block contents%} +{{flash_all_messages()}} + +<div class="row"> + <p>In this section, you will be able to view and manage the sequencing + platforms that are currently supported by GeneNetwork.</p> +</div> + +<div class="row"> + {{select_species_form(url_for("species.platforms.index"), species)}} +</div> +{%endblock%} diff --git a/uploader/templates/platforms/list-platforms.html b/uploader/templates/platforms/list-platforms.html new file mode 100644 index 0000000..718dd1d --- /dev/null +++ b/uploader/templates/platforms/list-platforms.html @@ -0,0 +1,93 @@ +{%extends "platforms/base.html"%} +{%from "flash_messages.html" import flash_all_messages%} +{%from "species/macro-display-species-card.html" import display_species_card%} + +{%block title%}Platforms — List Platforms{%endblock%} + +{%block pagetitle%}Platforms — List Platforms{%endblock%} + + +{%block contents%} +{{flash_all_messages()}} + +<div class="row"> + <p>View the list of the genetic sequencing platforms that are currently + supported by GeneNetwork.</p> + <p>If you cannot find the platform you wish to use, you can add it by clicking + the "New Platform" button below.</p> + <p><a href="{{url_for('species.platforms.create_platform', + species_id=species.SpeciesId)}}" + title="Create a new genetic sequencing platform for species {{species.FullName}}" + class="btn btn-primary">Create Platform</a></p> +</div> + +<div class="row"> + <h2>Supported Platforms</h2> + {%if platforms is defined and platforms | length > 0%} + <p>There are {{total_platforms}} platforms supported by GeneNetwork</p> + + <div class="row"> + <div class="col-md-2" style="text-align: start;"> + {%if start_from > 0%} + <a href="{{url_for('species.platforms.list_platforms', + species_id=species.SpeciesId, + start_from=start_from-count, + count=count)}}"> + <span class="glyphicon glyphicon-backward"></span> + Previous + </a> + {%endif%} + </div> + <div class="col-md-8" style="text-align: center;"> + Displaying platforms {{start_from+1}} to {{start_from+count if start_from+count < total_platforms else total_platforms}} of + {{total_platforms}} + </div> + <div class="col-md-2" style="text-align: end;"> + {%if start_from + count < total_platforms%} + <a href="{{url_for('species.platforms.list_platforms', + species_id=species.SpeciesId, + start_from=start_from+count, + count=count)}}"> + Next + <span class="glyphicon glyphicon-forward"></span> + </a> + {%endif%} + </div> + </div> + + <table class="table"> + <thead> + <tr> + <th>#</th> + <th>Platform Name</th> + <th><a href="https://www.ncbi.nlm.nih.gov/geo/browse/?view=platforms&tax={{species.TaxonomyId}}" + title="Gene Expression Omnibus: Platforms section" + target="_blank">GEO Platform</a></th> + <th>Title</th> + </tr> + </thead> + + <tbody> + {%for platform in platforms%} + <tr> + <td>{{platform.sequence_number}}</td> + <td>{{platform.GeneChipName}}</td> + <td><a href="https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc={{platform.GeoPlatform}}" + title="View platform on the Gene Expression Omnibus" + target="_blank">{{platform.GeoPlatform}}</a></td> + <td>{{platform.Title}}</td> + </tr> + {%endfor%} + </tbody> + </table> + {%else%} + <p class="text-warning"> + <span class="glyphicon glyphicon-exclamation-sign"></span> + There are no platforms supported at this time!</p> + {%endif%} +</div> +{%endblock%} + +{%block sidebarcontents%} +{{display_species_card(species)}} +{%endblock%} diff --git a/uploader/templates/populations/base.html b/uploader/templates/populations/base.html new file mode 100644 index 0000000..d763fc1 --- /dev/null +++ b/uploader/templates/populations/base.html @@ -0,0 +1,12 @@ +{%extends "species/base.html"%} + +{%block lvl2_breadcrumbs%} +<li {%if activelink=="populations"%} + class="breadcrumb-item active" + {%else%} + class="breadcrumb-item" + {%endif%}> + <a href="{{url_for('species.populations.index')}}">Populations</a> +</li> +{%block lvl3_breadcrumbs%}{%endblock%} +{%endblock%} diff --git a/uploader/templates/populations/create-population.html b/uploader/templates/populations/create-population.html new file mode 100644 index 0000000..b05ce37 --- /dev/null +++ b/uploader/templates/populations/create-population.html @@ -0,0 +1,252 @@ +{%extends "populations/base.html"%} +{%from "flash_messages.html" import flash_all_messages%} +{%from "species/macro-select-species.html" import select_species_form%} +{%from "species/macro-display-species-card.html" import display_species_card%} + +{%block title%}Create Population{%endblock%} + +{%block pagetitle%}Create Population{%endblock%} + +{%block lvl3_breadcrumbs%} +<li {%if activelink=="create-population"%} + class="breadcrumb-item active" + {%else%} + class="breadcrumb-item" + {%endif%}> + <a href="{{url_for('species.populations.create_population', + species_id=species.SpeciesId)}}">create population</a> +</li> +{%endblock%} + + +{%block contents%} +<div class="row"> + <p>The population is the next hierarchical node under Species. Data is grouped under a specific population, under a particular species.</p> + <p> + This page enables you to create a new population, in the case that you + cannot find the population you want in the + <a + href="{{url_for('species.populations.list_species_populations', + species_id=species.SpeciesId)}}" + title="Population for species '{{species.FullName}}'."> + list of species populations + </a> + </p> +</div> + +<div class="row"> + <form method="POST" + action="{{url_for('species.populations.create_population', + species_id=species.SpeciesId)}}"> + + <legend>Create Population</legend> + + {{flash_all_messages()}} + + <div {%if errors.population_fullname%} + class="form-group has-error" + {%else%} + class="form-group" + {%endif%}> + <label for="txt-population-fullname" class="form-label">Full Name</label> + {%if errors.population_fullname%} + <small class="form-text text-danger">{{errors.population_fullname}}</small> + {%endif%} + <input type="text" + id="txt-population-fullname" + name="population_fullname" + required="required" + minLength="3" + maxLength="100" + value="{{error_values.population_fullname or ''}}" + class="form-control" /> + <small class="form-text text-muted"> + <p> + This is a descriptive name for your population — useful for + humans. + </p> + </small> + </div> + + <div {%if errors.population_name%} + class="form-group has-error" + {%else%} + class="form-group" + {%endif%}> + <label for="txt-population-name" class="form-label">Name</label> + {%if errors.population_name%} + <small class="form-text text-danger">{{errors.population_name}}</small> + {%endif%} + <input type="text" + id="txt-population-name" + name="population_name" + required="required" + minLength="3" + maxLength="30" + value="{{error_values.population_name or ''}}" + class="form-control" /> + <small class="form-text text-muted"> + <p> + This is a short representative, but constrained name for your + population. + <br /> + The field will only accept letters ('A-Za-z'), numbers (0-9), hyphens + and underscores. Any other character will cause the name to be + rejected. + </p> + </small> + </div> + + <div class="form-group"> + <label for="txt-population-code" class="form-label">Population Code</label> + <input type="text" + id="txt-population-code" + name="population_code" + maxLength="5" + minLength="3" + value="{{error_values.population_code or ''}}" + class="form-control" /> + <small class="form-text text-muted"> + <p class="text-danger"> + <span class="glyphicon glyphicon-exclamation-sign"></span> + What is this field is for? Confirm with Arthur and the rest. + </p> + </small> + </div> + + <div {%if errors.population_description%} + class="form-group has-error" + {%else%} + class="form-group" + {%endif%}> + <label for="txt-population-description" class="form-label"> + Description + </label> + {%if errors.population_description%} + <small class="form-text text-danger">{{errors.population_description}}</small> + {%endif%} + <textarea + id="txt-population-description" + name="population_description" + required="required" + class="form-control" + rows="5">{{error_values.population_description or ''}}</textarea> + <small class="form-text text-muted"> + <p> + This is a more detailed description for your population. This is + useful to communicate with other researchers some details regarding + your population, and what its about. + <br /> + Put, here, anything that describes your population but does not go + cleanly under metadata. + </p> + </small> + </div> + + <div {%if errors.population_family%} + class="form-group has-error" + {%else%} + class="form-group" + {%endif%}> + <label for="select-population-family" class="form-label">Family</label> + <select id="select-population-family" + name="population_family" + class="form-control" + required="required"> + <option value="">Please select a family</option> + {%for family in families%} + <option value="{{family}}" + {%if error_values.population_family == family%} + selected="selected" + {%endif%}>{{family}}</option> + {%endfor%} + </select> + <small class="form-text text-muted"> + <p> + This is a rough grouping of the populations in GeneNetwork into lists + of common types of populations. + </p> + </small> + </div> + + <div {%if errors.population_mapping_method_id%} + class="form-group has-error" + {%else%} + class="form-group" + {%endif%}> + <label for="select-population-mapping-methods" + class="form-label">Mapping Methods</label> + + <select id="select-population-mapping-methods" + name="population_mapping_method_id" + class="form-control" + required="required"> + <option value="">Select appropriate mapping methods</option> + {%for mmethod in mapping_methods%} + <option value="{{mmethod.id}}" + {%if error_values.population_mapping_method_id == mmethod.id%} + selected="selected" + {%endif%}>{{mmethod.value}}</option> + {%endfor%} + </select> + + <small class="form-text text-muted"> + <p>Select the mapping methods that your population will support.</p> + </small> + </div> + + <div {%if errors.population_genetic_type%} + class="form-group has-error" + {%else%} + class="form-group" + {%endif%}> + <label for="select-population-genetic-type" + class="form-label">Genetic Type</label> + <select id="select-population-genetic-type" + name="population_genetic_type" + class="form-control"> + <option value="">Select proper genetic type</option> + {%for gtype in genetic_types%} + <option value="{{gtype}}" + {%if error_values.population_genetic_type == gtype%} + selected="selected" + {%endif%}>{{gtype}}</option> + {%endfor%} + </select> + <small class="form-text text-muted text-danger"> + <p> + <span class="glyphicon glyphicon-exclamation-sign"></span> + This might be a poorly named field. + </p> + <p> + It probably has more to do with the mating crosses/crossings used to + produce the individuals in the population. I am no biologist, however, + and I'm leaving this here to remind myself to confirm this. + </p> + <p> + I still don't know what riset is.<br /> + … probably something to do with Recombinant Inbred Strains + </p> + <p> + Possible resources for this: + <ul> + <li>https://www.informatics.jax.org/silver/chapters/3-2.shtml</li> + <li>https://www.informatics.jax.org/silver/chapters/9-2.shtml</li> + </ul> + </p> + </small> + </div> + + <div class="form-group"> + <input type="submit" + value="create population" + class="btn btn-primary" /> + </div> + + </form> +</div> +{%endblock%} + +{%block sidebarcontents%} +{{display_species_card(species)}} +{%endblock%} diff --git a/uploader/templates/populations/index.html b/uploader/templates/populations/index.html new file mode 100644 index 0000000..4354e02 --- /dev/null +++ b/uploader/templates/populations/index.html @@ -0,0 +1,24 @@ +{%extends "populations/base.html"%} +{%from "flash_messages.html" import flash_all_messages%} +{%from "species/macro-select-species.html" import select_species_form%} + +{%block title%}Populations{%endblock%} + +{%block pagetitle%}Populations{%endblock%} + + +{%block contents%} +{{flash_all_messages()}} + +<div class="row"> + <p> + Your experiment data will relate to a particular population from a + particular species. Let us know what species it is you want to work with + below. + </p> +</div> + +<div class="row"> + {{select_species_form(url_for("species.populations.index"), species)}} +</div> +{%endblock%} diff --git a/uploader/templates/populations/list-populations.html b/uploader/templates/populations/list-populations.html new file mode 100644 index 0000000..7c7145f --- /dev/null +++ b/uploader/templates/populations/list-populations.html @@ -0,0 +1,93 @@ +{%extends "populations/base.html"%} +{%from "flash_messages.html" import flash_all_messages%} +{%from "species/macro-select-species.html" import select_species_form%} +{%from "species/macro-display-species-card.html" import display_species_card%} + +{%block title%}Populations{%endblock%} + +{%block pagetitle%}Populations{%endblock%} + +{%block lvl3_breadcrumbs%} +<li {%if activelink=="list-populations"%} + class="breadcrumb-item active" + {%else%} + class="breadcrumb-item" + {%endif%}> + <a href="{{url_for('species.populations.list_species_populations', + species_id=species.SpeciesId)}}">List populations</a> +</li> +{%endblock%} + + +{%block contents%} +{{flash_all_messages()}} +<div class="row"> + <p> + The following populations/groups exist for the '{{species.FullName}}' + species. + </p> + <p> + Click on the population's name to select and continue using the population. + </p> +</div> + +<div class="row"> + <p> + If the population you need for the species '{{species.FullName}}' does not + exist, click on the "Create Population" button below to create a new one. + </p> + <p> + <a href="{{url_for('species.populations.create_population', + species_id=species.SpeciesId)}}" + title="Create a new population for species '{{species.FullName}}'." + class="btn btn-danger"> + Create Population + </a> + </p> +</div> + +<div class="row"> + <table class="table"> + <caption>Populations for {{species.FullName}}</caption> + <thead> + <tr> + <th>#</th> + <th>Name</th> + <th>Full Name</th> + <th>Description</th> + </tr> + </thead> + + <tbody> + {%for population in populations%} + <tr> + <td>{{population["sequence_number"]}}</td> + <td> + <a href="{{url_for('species.populations.view_population', + species_id=species.SpeciesId, + population_id=population.InbredSetId)}}" + title="Population '{{population.FullName}}' for species '{{species.FullName}}'."> + {{population.Name}} + </a> + </td> + <td>{{population.FullName}}</td> + <td>{{population.Description}}</td> + </tr> + {%else%} + <tr> + <td colspan="3"> + <p class="text-danger"> + <span class="glyphicon glyphicon-exclamation-mark"></span> + There were no populations found for {{species.FullName}}! + </p> + </td> + </tr> + {%endfor%} + </tbody> + </table> +</div> +{%endblock%} + +{%block sidebarcontents%} +{{display_species_card(species)}} +{%endblock%} diff --git a/uploader/templates/populations/macro-display-population-card.html b/uploader/templates/populations/macro-display-population-card.html new file mode 100644 index 0000000..79f7925 --- /dev/null +++ b/uploader/templates/populations/macro-display-population-card.html @@ -0,0 +1,46 @@ +{%from "species/macro-display-species-card.html" import display_species_card%} + +{%macro display_population_card(species, population)%} +{{display_species_card(species)}} + +<div class="card"> + <div class="card-body"> + <h5 class="card-title">Population</h5> + <div class="card-text"> + <table class="table"> + <tbody> + <tr> + <td>Name</td> + <td>{{population.Name}}</td> + </tr> + + <tr> + <td>Full Name</td> + <td>{{population.FullName}}</td> + </tr> + + <tr> + <td>Code</td> + <td>{{population.InbredSetCode}}</td> + </tr> + + <tr> + <td>Genetic Type</td> + <td>{{population.GeneticType}}</td> + </tr> + + <tr> + <td>Family</td> + <td>{{population.Family}}</td> + </tr> + + <tr> + <td>Description</td> + <td>{{(population.Description or "")[0:500]}}…</td> + </tr> + </tbody> + </table> + </div> + </div> +</div> +{%endmacro%} diff --git a/uploader/templates/populations/macro-select-population.html b/uploader/templates/populations/macro-select-population.html new file mode 100644 index 0000000..af4fd3a --- /dev/null +++ b/uploader/templates/populations/macro-select-population.html @@ -0,0 +1,30 @@ +{%macro select_population_form(form_action, populations)%} +<form method="GET" action="{{form_action}}"> + <legend>Select Population</legend> + + <div class="form-group"> + <label for="select-population" class="form-label">Select Population</label> + <select id="select-population" + name="population_id" + class="form-control" + required="required"> + <option value="">Select Population</option> + {%for family in populations%} + <optgroup {%if family[0][1] is not none%} + label="{{family[0][1]}}" + {%else%} + label="Undefined" + {%endif%}> + {%for population in family[1]%} + <option value="{{population.Id}}">{{population.FullName}}</option> + {%endfor%} + </optgroup> + {%endfor%} + </select> + </div> + + <div class="form-group"> + <input type="submit" value="Select" class="btn btn-primary" /> + </div> +</form> +{%endmacro%} diff --git a/uploader/templates/rqtl2/create-tissue-success.html b/uploader/templates/populations/rqtl2/create-tissue-success.html index 5f2c5a0..d6fe154 100644 --- a/uploader/templates/rqtl2/create-tissue-success.html +++ b/uploader/templates/populations/rqtl2/create-tissue-success.html @@ -56,7 +56,7 @@ <form id="frm-create-tissue-success-continue" method="POST" - action="{{url_for('upload.rqtl2.select_dataset_info', + action="{{url_for('expression-data.rqtl2.select_dataset_info', species_id=species.SpeciesId, population_id=population.InbredSetId)}}" style="display: inline; width: 100%; grid-column: 1 / 2; @@ -85,7 +85,7 @@ <div class="row"> <form id="frm-create-tissue-success-select-existing" method="POST" - action="{{url_for('upload.rqtl2.select_tissue', + action="{{url_for('expression-data.rqtl2.select_tissue', species_id=species.SpeciesId, population_id=population.InbredSetId)}}" style="display: inline; width: 100%; grid-column: 3 / 4; diff --git a/uploader/templates/populations/rqtl2/index.html b/uploader/templates/populations/rqtl2/index.html new file mode 100644 index 0000000..ec6ffb8 --- /dev/null +++ b/uploader/templates/populations/rqtl2/index.html @@ -0,0 +1,54 @@ +{%extends "base.html"%} +{%from "flash_messages.html" import flash_messages%} + +{%block title%}Data Upload{%endblock%} + +{%block contents%} +<h1 class="heading">R/qtl2 data upload</h1> + +<h2>R/qtl2 Upload</h2> + +<div class="row"> + <form method="POST" action="{{url_for('expression-data.rqtl2.select_species')}}" + id="frm-rqtl2-upload"> + <legend class="heading">upload R/qtl2 bundle</legend> + {{flash_messages("error-rqtl2")}} + + <div class="form-group"> + <label for="select:species" class="form-label">Species</label> + <select id="select:species" + name="species_id" + required="required" + class="form-control"> + <option value="">Select species</option> + {%for spec in species%} + <option value="{{spec.SpeciesId}}">{{spec.MenuName}}</option> + {%endfor%} + </select> + <small class="form-text text-muted"> + Data that you upload to the system should belong to a know species. + Here you can select the species that you wish to upload data for. + </small> + </div> + + <input type="submit" class="btn btn-primary" value="submit" /> + </form> +</div> + +<div class="row"> + <h2 class="heading">R/qtl2 Bundles</h2> + + <div class="explainer"> + <p>This feature combines and extends the two upload methods below. Instead of + uploading one item at a time, the R/qtl2 bundle you upload can contain both + the genotypes data (samples/individuals/cases and their data) and the + expression data.</p> + <p>The R/qtl2 bundle, additionally, can contain extra metadata, that neither + of the methods below can handle.</p> + + <a href="{{url_for('expression-data.rqtl2.select_species')}}" + title="Upload a zip bundle of R/qtl2 files"> + <button class="btn btn-primary">upload R/qtl2 bundle</button></a> + </div> +</div> +{%endblock%} diff --git a/uploader/templates/rqtl2/no-such-job.html b/uploader/templates/populations/rqtl2/no-such-job.html index b17004f..b17004f 100644 --- a/uploader/templates/rqtl2/no-such-job.html +++ b/uploader/templates/populations/rqtl2/no-such-job.html diff --git a/uploader/templates/rqtl2/rqtl2-job-error.html b/uploader/templates/populations/rqtl2/rqtl2-job-error.html index 9817518..9817518 100644 --- a/uploader/templates/rqtl2/rqtl2-job-error.html +++ b/uploader/templates/populations/rqtl2/rqtl2-job-error.html diff --git a/uploader/templates/rqtl2/rqtl2-job-results.html b/uploader/templates/populations/rqtl2/rqtl2-job-results.html index 4ecd415..4ecd415 100644 --- a/uploader/templates/rqtl2/rqtl2-job-results.html +++ b/uploader/templates/populations/rqtl2/rqtl2-job-results.html diff --git a/uploader/templates/rqtl2/rqtl2-job-status.html b/uploader/templates/populations/rqtl2/rqtl2-job-status.html index e896f88..e896f88 100644 --- a/uploader/templates/rqtl2/rqtl2-job-status.html +++ b/uploader/templates/populations/rqtl2/rqtl2-job-status.html diff --git a/uploader/templates/rqtl2/rqtl2-qc-job-error.html b/uploader/templates/populations/rqtl2/rqtl2-qc-job-error.html index 90e8887..90e8887 100644 --- a/uploader/templates/rqtl2/rqtl2-qc-job-error.html +++ b/uploader/templates/populations/rqtl2/rqtl2-qc-job-error.html diff --git a/uploader/templates/rqtl2/rqtl2-qc-job-results.html b/uploader/templates/populations/rqtl2/rqtl2-qc-job-results.html index 59bc8cd..b3c3a8f 100644 --- a/uploader/templates/rqtl2/rqtl2-qc-job-results.html +++ b/uploader/templates/populations/rqtl2/rqtl2-qc-job-results.html @@ -15,7 +15,7 @@ <div class="row"> <form id="form-qc-job-results" - action="{{url_for('upload.rqtl2.select_dataset_info', + action="{{url_for('expression-data.rqtl2.select_dataset_info', species_id=species.SpeciesId, population_id=population.Id)}}" method="POST"> diff --git a/uploader/templates/rqtl2/rqtl2-qc-job-status.html b/uploader/templates/populations/rqtl2/rqtl2-qc-job-status.html index f4a6266..f4a6266 100644 --- a/uploader/templates/rqtl2/rqtl2-qc-job-status.html +++ b/uploader/templates/populations/rqtl2/rqtl2-qc-job-status.html diff --git a/uploader/templates/rqtl2/rqtl2-qc-job-success.html b/uploader/templates/populations/rqtl2/rqtl2-qc-job-success.html index 2861a04..f126835 100644 --- a/uploader/templates/rqtl2/rqtl2-qc-job-success.html +++ b/uploader/templates/populations/rqtl2/rqtl2-qc-job-success.html @@ -18,7 +18,7 @@ --> <div class="row"> <form id="frm-upload-rqtl2-bundle" - action="{{url_for('upload.rqtl2.select_dataset_info', + action="{{url_for('expression-data.rqtl2.select_dataset_info', species_id=species.SpeciesId, population_id=population.InbredSetId)}}" method="POST" diff --git a/uploader/templates/populations/rqtl2/select-geno-dataset.html b/uploader/templates/populations/rqtl2/select-geno-dataset.html new file mode 100644 index 0000000..3233abc --- /dev/null +++ b/uploader/templates/populations/rqtl2/select-geno-dataset.html @@ -0,0 +1,69 @@ +{%extends "base.html"%} +{%from "flash_messages.html" import flash_messages%} + +{%block title%}Upload R/qtl2 Bundle{%endblock%} + +{%block contents%} +<h2 class="heading">Select Genotypes Dataset</h2> + +<div class="row"> + <p>Your R/qtl2 files bundle could contain a "geno" specification. You will + therefore need to select from one of the existing Genotype datasets or + create a new one.</p> + <p>This is the dataset where your data will be organised under.</p> +</div> + +<div class="row"> + <form id="frm-upload-rqtl2-bundle" + action="{{url_for('expression-data.rqtl2.select_geno_dataset', + species_id=species.SpeciesId, + population_id=population.InbredSetId)}}" + method="POST" + enctype="multipart/form-data"> + <legend class="heading">select from existing genotype datasets</legend> + + <input type="hidden" name="species_id" value="{{species.SpeciesId}}" /> + <input type="hidden" name="population_id" + value="{{population.InbredSetId}}" /> + <input type="hidden" name="rqtl2_bundle_file" + value="{{rqtl2_bundle_file}}" /> + + {{flash_messages("error-rqtl2-select-geno-dataset")}} + + <div class="form-group"> + <legend>Datasets</legend> + <label for="select:geno-datasets" class="form-label">Dataset</label> + <select id="select:geno-datasets" + name="geno-dataset-id" + required="required" + {%if datasets | length == 0%} + disabled="disabled" + {%endif%} + class="form-control" + aria-describedby="help-geno-dataset-select-dataset"> + <option value="">Select dataset</option> + {%for dset in datasets%} + <option value="{{dset['Id']}}">{{dset["Name"]}} ({{dset["FullName"]}})</option> + {%endfor%} + </select> + <span id="help-geno-dataset-select-dataset" class="form-text text-muted"> + Select from the existing genotype datasets for species + {{species.SpeciesName}} ({{species.FullName}}). + </span> + </div> + + <button type="submit" class="btn btn-primary">select dataset</button> + </form> +</div> + +<div class="row"> + <p>If the genotype dataset you need does not currently exist for your dataset, + go the <a href="{{url_for( + 'species.populations.genotypes.create_dataset', + species_id=species.SpeciesId, + population_id=population.Id)}}" + title="Create a new genotypes dataset for {{species.FullName}}"> + genotypes page to create the genotype dataset</a></p> +</div> + +{%endblock%} diff --git a/uploader/templates/populations/rqtl2/select-population.html b/uploader/templates/populations/rqtl2/select-population.html new file mode 100644 index 0000000..ded425f --- /dev/null +++ b/uploader/templates/populations/rqtl2/select-population.html @@ -0,0 +1,57 @@ +{%extends "expression-data/index.html"%} +{%from "flash_messages.html" import flash_messages%} +{%from "species/macro-display-species-card.html" import display_species_card%} + +{%block title%}Select Grouping/Population{%endblock%} + +{%block contents%} +<h1 class="heading">Select grouping/population</h1> + +<div class="row"> + <p>The data is organised in a hierarchical form, beginning with + <em>species</em> at the very top. Under <em>species</em> the data is + organised by <em>population</em>, sometimes referred to as <em>grouping</em>. + (In some really old documents/systems, you might see this referred to as + <em>InbredSet</em>.)</p> + <p>In this section, you get to define what population your data is to be + organised by.</p> +</div> + +<div class="row"> + <form method="POST" + action="{{url_for('expression-data.rqtl2.select_population', + species_id=species.SpeciesId)}}"> + <legend class="heading">select grouping/population</legend> + {{flash_messages("error-select-population")}} + + <input type="hidden" name="species_id" value="{{species.SpeciesId}}" /> + + <div class="form-group"> + <label for="select:inbredset" class="form-label">population</label> + <select id="select:inbredset" + name="inbredset_id" + required="required" + class="form-control"> + <option value="">Select a grouping/population</option> + {%for pop in populations%} + <option value="{{pop.InbredSetId}}"> + {{pop.InbredSetName}} ({{pop.FullName}})</option> + {%endfor%} + </select> + <span class="form-text text-muted">Select the population for your data from + the list below.</span> + </div> + + <button type="submit" class="btn btn-primary" />select population</button> +</form> +</div> + +{%endblock%} + +{%block sidebarcontents%} +{{display_species_card(species)}} +{%endblock%} + + +{%block javascript%} +{%endblock%} diff --git a/uploader/templates/rqtl2/select-probeset-dataset.html b/uploader/templates/populations/rqtl2/select-probeset-dataset.html index 26f52ed..74f8f69 100644 --- a/uploader/templates/rqtl2/select-probeset-dataset.html +++ b/uploader/templates/populations/rqtl2/select-probeset-dataset.html @@ -15,7 +15,7 @@ {%if datasets | length > 0%} <div class="row"> <form method="POST" - action="{{url_for('upload.rqtl2.select_probeset_dataset', + action="{{url_for('expression-data.rqtl2.select_probeset_dataset', species_id=species.SpeciesId, population_id=population.Id)}}" id="frm:select-probeset-dataset"> <legend class="heading">Select from existing ProbeSet datasets</legend> @@ -68,7 +68,7 @@ <div class="row"> <form method="POST" - action="{{url_for('upload.rqtl2.create_probeset_dataset', + action="{{url_for('expression-data.rqtl2.create_probeset_dataset', species_id=species.SpeciesId, population_id=population.Id)}}" id="frm:create-probeset-dataset"> <legend class="heading">Create a new ProbeSet dataset</legend> diff --git a/uploader/templates/rqtl2/select-probeset-study-id.html b/uploader/templates/populations/rqtl2/select-probeset-study-id.html index b9bf52e..e3fd9cc 100644 --- a/uploader/templates/rqtl2/select-probeset-study-id.html +++ b/uploader/templates/populations/rqtl2/select-probeset-study-id.html @@ -12,7 +12,7 @@ <p>In this page, you can either select from a existing dataset:</p> <form method="POST" - action="{{url_for('upload.rqtl2.select_probeset_study', + action="{{url_for('expression-data.rqtl2.select_probeset_study', species_id=species.SpeciesId, population_id=population.Id)}}" id="frm:select-probeset-study"> <legend class="heading">Select from existing ProbeSet studies</legend> @@ -62,7 +62,7 @@ <p>Create a new ProbeSet dataset below:</p> <form method="POST" - action="{{url_for('upload.rqtl2.create_probeset_study', + action="{{url_for('expression-data.rqtl2.create_probeset_study', species_id=species.SpeciesId, population_id=population.Id)}}" id="frm:create-probeset-study"> <legend class="heading">Create new ProbeSet study</legend> diff --git a/uploader/templates/rqtl2/select-tissue.html b/uploader/templates/populations/rqtl2/select-tissue.html index 34e1758..fe3080a 100644 --- a/uploader/templates/rqtl2/select-tissue.html +++ b/uploader/templates/populations/rqtl2/select-tissue.html @@ -15,7 +15,7 @@ {%if tissues | length > 0%} <div class="row"> <form method="POST" - action="{{url_for('upload.rqtl2.select_tissue', + action="{{url_for('expression-data.rqtl2.select_tissue', species_id=species.SpeciesId, population_id=population.Id)}}" id="frm:select-probeset-dataset"> <legend class="heading">Select from existing ProbeSet datasets</legend> @@ -65,7 +65,7 @@ to the system below.</p> <form method="POST" - action="{{url_for('upload.rqtl2.create_tissue', + action="{{url_for('expression-data.rqtl2.create_tissue', species_id=species.SpeciesId, population_id=population.Id)}}" id="frm:create-probeset-dataset"> <legend class="heading">Add new tissue, organ or biological material</legend> diff --git a/uploader/templates/rqtl2/summary-info.html b/uploader/templates/populations/rqtl2/summary-info.html index 1be87fa..0adba2e 100644 --- a/uploader/templates/rqtl2/summary-info.html +++ b/uploader/templates/populations/rqtl2/summary-info.html @@ -44,7 +44,7 @@ <div class="row"> <form id="frm:confirm-rqtl2bundle-details" - action="{{url_for('upload.rqtl2.confirm_bundle_details', + action="{{url_for('expression-data.rqtl2.confirm_bundle_details', species_id=species.SpeciesId, population_id=population.InbredSetId)}}" method="POST" diff --git a/uploader/templates/rqtl2/upload-rqtl2-bundle-step-01.html b/uploader/templates/populations/rqtl2/upload-rqtl2-bundle-step-01.html index 07c240f..9d45c5f 100644 --- a/uploader/templates/rqtl2/upload-rqtl2-bundle-step-01.html +++ b/uploader/templates/populations/rqtl2/upload-rqtl2-bundle-step-01.html @@ -71,13 +71,13 @@ </div> <form id="frm-upload-rqtl2-bundle" - action="{{url_for('upload.rqtl2.upload_rqtl2_bundle', + action="{{url_for('expression-data.rqtl2.upload_rqtl2_bundle', species_id=species.SpeciesId, population_id=population.InbredSetId)}}" method="POST" enctype="multipart/form-data" data-resumable-target="{{url_for( - 'upload.rqtl2.upload_rqtl2_bundle_chunked_post', + 'expression-data.rqtl2.upload_rqtl2_bundle_chunked_post', species_id=species.SpeciesId, population_id=population.InbredSetId)}}"> <input type="hidden" name="species_id" value="{{species.SpeciesId}}" /> diff --git a/uploader/templates/rqtl2/upload-rqtl2-bundle-step-02.html b/uploader/templates/populations/rqtl2/upload-rqtl2-bundle-step-02.html index 93b1dc9..8210ed0 100644 --- a/uploader/templates/rqtl2/upload-rqtl2-bundle-step-02.html +++ b/uploader/templates/populations/rqtl2/upload-rqtl2-bundle-step-02.html @@ -14,7 +14,7 @@ <p>Click "Continue" below to proceed.</p> <form id="frm-upload-rqtl2-bundle" - action="{{url_for('upload.rqtl2.select_dataset_info', + action="{{url_for('expression-data.rqtl2.select_dataset_info', species_id=species.SpeciesId, population_id=population.InbredSetId)}}" method="POST" diff --git a/uploader/templates/populations/view-population.html b/uploader/templates/populations/view-population.html new file mode 100644 index 0000000..1e2964e --- /dev/null +++ b/uploader/templates/populations/view-population.html @@ -0,0 +1,96 @@ +{%extends "populations/base.html"%} +{%from "flash_messages.html" import flash_all_messages%} +{%from "species/macro-select-species.html" import select_species_form%} +{%from "species/macro-display-species-card.html" import display_species_card%} + +{%block title%}Populations{%endblock%} + +{%block pagetitle%}Populations{%endblock%} + +{%block lvl3_breadcrumbs%} +<li {%if activelink=="view-population"%} + class="breadcrumb-item active" + {%else%} + class="breadcrumb-item" + {%endif%}> + <a href="{{url_for('species.populations.view_population', + species_id=species.SpeciesId, + population_id=population.InbredSetId)}}">view population</a> +</li> +{%endblock%} + + +{%block contents%} +<div class="row"> + <h2>Population Details</h2> + + {{flash_all_messages()}} + + <dl> + <dt>Name</dt> + <dd>{{population.Name}}</dd> + + <dt>FullName</dt> + <dd>{{population.FullName}}</dd> + + <dt>Code</dt> + <dd>{{population.InbredSetCode}}</dd> + + <dt>Genetic Type</dt> + <dd>{{population.GeneticType}}</dd> + + <dt>Family</dt> + <dd>{{population.Family}}</dd> + + <dt>Description</dt> + <dd><pre>{{population.Description or "-"}}</pre></dd> + </dl> +</div> + +<div class="row"> + … maybe provide a way to organise populations in the same family here … +</div> + +<div class="row"> + <h3>Actions</h3> + + <p> + Click any of the following links to use this population in performing the + subsequent operations. + </p> + + <nav class="nav"> + <ul> + <li> + <a href="{{url_for('species.populations.genotypes.list_genotypes', + species_id=species.SpeciesId, + population_id=population.Id)}}" + title="Upload genotypes for {{species.FullName}}">Upload Genotypes</a> + </li> + <li> + <a href="{{url_for('species.populations.samples.list_samples', + species_id=species.SpeciesId, + population_id=population.Id)}}" + title="Manage samples: Add new or delete existing."> + manage samples</a> + </li> + <li> + <a href="#" title="Upload expression data">upload expression data</a> + </li> + <li> + <a href="#" title="Upload phenotype data">upload phenotype data</a> + </li> + <li> + <a href="#" title="Upload individual data">upload individual data</a> + </li> + <li> + <a href="#" title="Upload RNA-Seq data">upload RNA-Seq data</a> + </li> + </ul> + </nav> +</div> +{%endblock%} + +{%block sidebarcontents%} +{{display_species_card(species)}} +{%endblock%} diff --git a/uploader/templates/rqtl2/create-geno-dataset-success.html b/uploader/templates/rqtl2/create-geno-dataset-success.html deleted file mode 100644 index 1b50221..0000000 --- a/uploader/templates/rqtl2/create-geno-dataset-success.html +++ /dev/null @@ -1,55 +0,0 @@ -{%extends "base.html"%} -{%from "flash_messages.html" import flash_messages%} - -{%block title%}Upload R/qtl2 Bundle{%endblock%} - -{%block contents%} -<h2 class="heading">Select Genotypes Dataset</h2> - -<div class="explainer"> - <p>You successfully created the genotype dataset with the following - information. - <dl> - <dt>ID</dt> - <dd>{{geno_dataset.id}}</dd> - - <dt>Name</dt> - <dd>{{geno_dataset.name}}</dd> - - <dt>Full Name</dt> - <dd>{{geno_dataset.fname}}</dd> - - <dt>Short Name</dt> - <dd>{{geno_dataset.sname}}</dd> - - <dt>Created On</dt> - <dd>{{geno_dataset.today}}</dd> - - <dt>Public?</dt> - <dd>{%if geno_dataset.public == 0%}No{%else%}Yes{%endif%}</dd> - </dl> - </p> -</div> - -<div class="row"> - <form id="frm-upload-rqtl2-bundle" - action="{{url_for('upload.rqtl2.select_dataset_info', - species_id=species.SpeciesId, - population_id=population.InbredSetId)}}" - method="POST" - enctype="multipart/form-data"> - <legend class="heading">select from existing genotype datasets</legend> - - <input type="hidden" name="species_id" value="{{species.SpeciesId}}" /> - <input type="hidden" name="population_id" - value="{{population.InbredSetId}}" /> - <input type="hidden" name="rqtl2_bundle_file" - value="{{rqtl2_bundle_file}}" /> - <input type="hidden" name="geno-dataset-id" - value="{{geno_dataset.id}}" /> - - <button type="submit" class="btn btn-primary">continue</button> - </form> -</div> - -{%endblock%} diff --git a/uploader/templates/rqtl2/create-probe-dataset-success.html b/uploader/templates/rqtl2/create-probe-dataset-success.html deleted file mode 100644 index 790d174..0000000 --- a/uploader/templates/rqtl2/create-probe-dataset-success.html +++ /dev/null @@ -1,59 +0,0 @@ -{%extends "base.html"%} -{%from "flash_messages.html" import flash_messages%} - -{%block title%}Upload R/qtl2 Bundle{%endblock%} - -{%block contents%} -<h2 class="heading">Create ProbeSet Dataset</h2> - -<div class="row"> - <p>You successfully created the ProbeSet dataset with the following - information. - <dl> - <dt>Averaging Method</dt> - <dd>{{avgmethod.Name}}</dd> - - <dt>ID</dt> - <dd>{{dataset.datasetid}}</dd> - - <dt>Name</dt> - <dd>{{dataset.name2}}</dd> - - <dt>Full Name</dt> - <dd>{{dataset.fname}}</dd> - - <dt>Short Name</dt> - <dd>{{dataset.sname}}</dd> - - <dt>Created On</dt> - <dd>{{dataset.today}}</dd> - - <dt>DataScale</dt> - <dd>{{dataset.datascale}}</dd> - </dl> - </p> -</div> - -<div class="row"> - <form id="frm-upload-rqtl2-bundle" - action="{{url_for('upload.rqtl2.select_dataset_info', - species_id=species.SpeciesId, - population_id=population.InbredSetId)}}" - method="POST" - enctype="multipart/form-data"> - <legend class="heading">Create ProbeSet dataset</legend> - - <input type="hidden" name="species_id" value="{{species.SpeciesId}}" /> - <input type="hidden" name="population_id" - value="{{population.InbredSetId}}" /> - <input type="hidden" name="rqtl2_bundle_file" value="{{rqtl2_bundle_file}}" /> - <input type="hidden" name="geno-dataset-id" value="{{geno_dataset.Id}}" /> - <input type="hidden" name="tissueid" value="{{tissue.Id}}" /> - <input type="hidden" name="probe-study-id" value="{{study.Id}}" /> - <input type="hidden" name="probe-dataset-id" value="{{dataset.datasetid}}" /> - - <button type="submit" class="btn btn-primary">continue</button> - </form> -</div> - -{%endblock%} diff --git a/uploader/templates/rqtl2/create-probe-study-success.html b/uploader/templates/rqtl2/create-probe-study-success.html deleted file mode 100644 index d0ee508..0000000 --- a/uploader/templates/rqtl2/create-probe-study-success.html +++ /dev/null @@ -1,49 +0,0 @@ -{%extends "base.html"%} -{%from "flash_messages.html" import flash_messages%} - -{%block title%}Upload R/qtl2 Bundle{%endblock%} - -{%block contents%} -<h2 class="heading">Create ProbeSet Study</h2> - -<div class="row"> - <p>You successfully created the ProbeSet study with the following - information. - <dl> - <dt>ID</dt> - <dd>{{study.id}}</dd> - - <dt>Name</dt> - <dd>{{study.name}}</dd> - - <dt>Full Name</dt> - <dd>{{study.fname}}</dd> - - <dt>Short Name</dt> - <dd>{{study.sname}}</dd> - - <dt>Created On</dt> - <dd>{{study.today}}</dd> - </dl> - </p> - - <form id="frm-upload-rqtl2-bundle" - action="{{url_for('upload.rqtl2.select_dataset_info', - species_id=species.SpeciesId, - population_id=population.InbredSetId)}}" - method="POST" - enctype="multipart/form-data"> - <legend class="heading">Create ProbeSet study</legend> - - <input type="hidden" name="species_id" value="{{species.SpeciesId}}" /> - <input type="hidden" name="population_id" - value="{{population.InbredSetId}}" /> - <input type="hidden" name="rqtl2_bundle_file" value="{{rqtl2_bundle_file}}" /> - <input type="hidden" name="geno-dataset-id" value="{{geno_dataset.Id}}" /> - <input type="hidden" name="probe-study-id" value="{{study.studyid}}" /> - - <button type="submit" class="btn btn-primary">continue</button> - </form> -</div> - -{%endblock%} diff --git a/uploader/templates/rqtl2/index.html b/uploader/templates/rqtl2/index.html deleted file mode 100644 index f3329c2..0000000 --- a/uploader/templates/rqtl2/index.html +++ /dev/null @@ -1,36 +0,0 @@ -{%extends "base.html"%} -{%from "flash_messages.html" import flash_messages%} - -{%block title%}Data Upload{%endblock%} - -{%block contents%} -<h1 class="heading">R/qtl2 data upload</h1> - -<h2>R/qtl2 Upload</h2> - -<form method="POST" action="{{url_for('upload.rqtl2.select_species')}}" - id="frm-rqtl2-upload"> - <legend class="heading">upload R/qtl2 bundle</legend> - {{flash_messages("error-rqtl2")}} - - <div class="form-group"> - <label for="select:species" class="form-label">Species</label> - <select id="select:species" - name="species_id" - required="required" - class="form-control"> - <option value="">Select species</option> - {%for spec in species%} - <option value="{{spec.SpeciesId}}">{{spec.MenuName}}</option> - {%endfor%} - </select> - <small class="form-text text-muted"> - Data that you upload to the system should belong to a know species. - Here you can select the species that you wish to upload data for. - </small> - </div> - - <button type="submit" class="btn btn-primary" />submit</button> -</form> - -{%endblock%} diff --git a/uploader/templates/rqtl2/select-geno-dataset.html b/uploader/templates/rqtl2/select-geno-dataset.html deleted file mode 100644 index 873f9c3..0000000 --- a/uploader/templates/rqtl2/select-geno-dataset.html +++ /dev/null @@ -1,144 +0,0 @@ -{%extends "base.html"%} -{%from "flash_messages.html" import flash_messages%} - -{%block title%}Upload R/qtl2 Bundle{%endblock%} - -{%block contents%} -<h2 class="heading">Select Genotypes Dataset</h2> - -<div class="row"> - <p>Your R/qtl2 files bundle contains a "geno" specification. You will - therefore need to select from one of the existing Genotype datasets or - create a new one.</p> - <p>This is the dataset where your data will be organised under.</p> -</div> - -<div class="row"> - <form id="frm-upload-rqtl2-bundle" - action="{{url_for('upload.rqtl2.select_geno_dataset', - species_id=species.SpeciesId, - population_id=population.InbredSetId)}}" - method="POST" - enctype="multipart/form-data"> - <legend class="heading">select from existing genotype datasets</legend> - - <input type="hidden" name="species_id" value="{{species.SpeciesId}}" /> - <input type="hidden" name="population_id" - value="{{population.InbredSetId}}" /> - <input type="hidden" name="rqtl2_bundle_file" - value="{{rqtl2_bundle_file}}" /> - - {{flash_messages("error-rqtl2-select-geno-dataset")}} - - <div class="form-group"> - <legend>Datasets</legend> - <label for="select:geno-datasets" class="form-label">Dataset</label> - <select id="select:geno-datasets" - name="geno-dataset-id" - required="required" - {%if datasets | length == 0%} - disabled="disabled" - {%endif%} - class="form-control" - aria-describedby="help-geno-dataset-select-dataset"> - <option value="">Select dataset</option> - {%for dset in datasets%} - <option value="{{dset['Id']}}">{{dset["Name"]}} ({{dset["FullName"]}})</option> - {%endfor%} - </select> - <span id="help-geno-dataset-select-dataset" class="form-text text-muted"> - Select from the existing genotype datasets for species - {{species.SpeciesName}} ({{species.FullName}}). - </span> - </div> - - <button type="submit" class="btn btn-primary">select dataset</button> - </form> -</div> - -<div class="row"> - <p style="color:#FE3535; padding-left:20em; font-weight:bolder;">OR</p> -</div> - -<div class="row"> - <form id="frm-upload-rqtl2-bundle" - action="{{url_for('upload.rqtl2.create_geno_dataset', - species_id=species.SpeciesId, - population_id=population.InbredSetId)}}" - method="POST" - enctype="multipart/form-data"> - <legend class="heading">create a new genotype dataset</legend> - - <input type="hidden" name="species_id" value="{{species.SpeciesId}}" /> - <input type="hidden" name="population_id" - value="{{population.InbredSetId}}" /> - <input type="hidden" name="rqtl2_bundle_file" - value="{{rqtl2_bundle_file}}" /> - - {{flash_messages("error-rqtl2-create-geno-dataset")}} - - <div class="form-group"> - <label for="txt:dataset-name" class="form-label">Name</label> - <input type="text" - id="txt:dataset-name" - name="dataset-name" - maxlength="100" - required="required" - class="form-control" - aria-describedby="help-geno-dataset-name" /> - <span id="help-geno-dataset-name" class="form-text text-muted"> - Provide the new name for the genotype dataset, e.g. "BXDGeno" - </span> - </div> - - <div class="form-group"> - <label for="txt:dataset-fullname" class="form-label">Full Name</label> - <input type="text" - id="txt:dataset-fullname" - name="dataset-fullname" - required="required" - maxlength="100" - class="form-control" - aria-describedby="help-geno-dataset-fullname" /> - - <span id="help-geno-dataset-fullname" class="form-text text-muted"> - Provide a longer name that better describes the genotype dataset, e.g. - "BXD Genotypes" - </span> - </div> - - <div class="form-group"> - <label for="txt:dataset-shortname" class="form-label">Short Name</label> - <input type="text" - id="txt:dataset-shortname" - name="dataset-shortname" - maxlength="100" - class="form-control" - aria-describedby="help-geno-dataset-shortname" /> - - <span id="help-geno-dataset-shortname" class="form-text text-muted"> - Provide a short name for the genotype dataset. This is optional. If not - provided, we'll default to the same value as the "Name" above. - </span> - </div> - - <div class="form-group"> - <input type="checkbox" - id="chk:dataset-public" - name="dataset-public" - checked="checked" - class="form-check" - aria-describedby="help-geno-datasent-public" /> - <label for="chk:dataset-public" class="form-check-label">Public?</label> - - <span id="help-geno-dataset-public" class="form-text text-muted"> - Specify whether the dataset will be available publicly. Check to make the - dataset publicly available and uncheck to limit who can access the dataset. - </span> - </div> - - <button type="submit" class="btn btn-primary">create new dataset</button> - </form> -</div> - -{%endblock%} diff --git a/uploader/templates/rqtl2/select-population.html b/uploader/templates/rqtl2/select-population.html deleted file mode 100644 index 37731f0..0000000 --- a/uploader/templates/rqtl2/select-population.html +++ /dev/null @@ -1,136 +0,0 @@ -{%extends "base.html"%} -{%from "flash_messages.html" import flash_messages%} - -{%block title%}Select Grouping/Population{%endblock%} - -{%block contents%} -<h1 class="heading">Select grouping/population</h1> - -<div class="explainer"> - <p>The data is organised in a hierarchical form, beginning with - <em>species</em> at the very top. Under <em>species</em> the data is - organised by <em>population</em>, sometimes referred to as <em>grouping</em>. - (In some really old documents/systems, you might see this referred to as - <em>InbredSet</em>.)</p> - <p>In this section, you get to define what population your data is to be - organised by.</p> -</div> - -<form method="POST" - action="{{url_for('upload.rqtl2.select_population', species_id=species.SpeciesId)}}"> - <legend class="heading">select grouping/population</legend> - {{flash_messages("error-select-population")}} - - <input type="hidden" name="species_id" value="{{species.SpeciesId}}" /> - - <div class="form-group"> - <label for="select:inbredset" class="form-label">population</label> - <select id="select:inbredset" - name="inbredset_id" - required="required" - class="form-control"> - <option value="">Select a grouping/population</option> - {%for pop in populations%} - <option value="{{pop.InbredSetId}}"> - {{pop.InbredSetName}} ({{pop.FullName}})</option> - {%endfor%} - </select> - <span class="form-text text-muted">If you are adding data to an already existing - population, simply pick the population from this drop-down selector. If - you cannot find your population from this list, try the form below to - create a new one..</span> - </div> - - <button type="submit" class="btn btn-primary" />select population</button> -</form> - -<p style="color:#FE3535; padding-left:20em; font-weight:bolder;">OR</p> - -<form method="POST" - action="{{url_for('upload.rqtl2.create_population', species_id=species.SpeciesId)}}"> - <legend class="heading">create new grouping/population</legend> - {{flash_messages("error-create-population")}} - - <input type="hidden" name="species_id" value="{{species.SpeciesId}}" /> - - <div class="form-group"> - <legend class="heading">mandatory</legend> - - <div class="form-group"> - <label for="txt:inbredset-name" class="form-label">name</label> - <input id="txt:inbredset-name" - name="inbredset_name" - type="text" - required="required" - maxlength="30" - placeholder="Enter grouping/population name" - class="form-control" /> - <span class="form-text text-muted">This is a short name that identifies the - population. Useful for menus, and quick scanning.</span> - </div> - - <div class="form-group"> - <label for="txt:" class="form-label">full name</label> - <input id="txt:inbredset-fullname" - name="inbredset_fullname" - type="text" - required="required" - maxlength="100" - placeholder="Enter the grouping/population's full name" - class="form-control" /> - <span class="form-text text-muted">This can be the same as the name above, or can - be longer. Useful for documentation, and human communication.</span> - </div> - </div> - - <div class="form-group"> - <legend class="heading">optional</legend> - - <div class="form-group"> - <label for="num:public" class="form-label">public?</label> - <select id="num:public" - name="public" - class="form-control"> - <option value="0">0 - Only accessible to authorised users</option> - <option value="1">1 - Publicly accessible to all users</option> - <option value="2" selected> - 2 - Publicly accessible to all users</option> - </select> - <span class="form-text text-muted">This determines whether the - population/grouping will appear on the menus for users.</span> - </div> - - <div class="form-group"> - <label for="txt:inbredset-family" class="form-label">family</label> - <input id="txt:inbredset-family" - name="inbredset_family" - type="text" - placeholder="I am not sure what this is about." - class="form-control" /> - <span class="form-text text-muted">I do not currently know what this is about. - This is a failure on my part to figure out what this is and provide a - useful description. Please feel free to remind me.</span> - </div> - - <div class="form-group"> - <label for="txtarea:" class="form-label">Description</label> - <textarea id="txtarea:description" - name="description" - rows="5" - placeholder="Enter a description of this grouping/population" - class="form-control"></textarea> - <span class="form-text text-muted"> - A long-form description of what the population consists of. Useful for - humans.</span> - </div> - </div> - - <button type="submit" class="btn btn-primary" /> - create grouping/population</button> -</form> - -{%endblock%} - - -{%block javascript%} -{%endblock%} diff --git a/uploader/templates/samples/base.html b/uploader/templates/samples/base.html new file mode 100644 index 0000000..291782b --- /dev/null +++ b/uploader/templates/samples/base.html @@ -0,0 +1,12 @@ +{%extends "populations/base.html"%} + +{%block lvl3_breadcrumbs%} +<li {%if activelink=="samples"%} + class="breadcrumb-item active" + {%else%} + class="breadcrumb-item" + {%endif%}> + <a href="{{url_for('species.populations.samples.index')}}">Samples</a> +</li> +{%block lvl4_breadcrumbs%}{%endblock%} +{%endblock%} diff --git a/uploader/templates/samples/index.html b/uploader/templates/samples/index.html new file mode 100644 index 0000000..ee4a63e --- /dev/null +++ b/uploader/templates/samples/index.html @@ -0,0 +1,19 @@ +{%extends "samples/base.html"%} +{%from "flash_messages.html" import flash_all_messages%} +{%from "species/macro-select-species.html" import select_species_form%} + +{%block title%}Populations{%endblock%} + +{%block pagetitle%}Populations{%endblock%} + + +{%block contents%} +{{flash_all_messages()}} + +<div class="row"> + <p>GeneNetwork has a selection of different species of organisms to choose from. Within those species, there are the populations of interest for a variety of experiments, from which you, the researcher, picked your samples (or individuals or cases) from. Here you can provide some basic details about your samples.</p> + <p>To start off, we will need to know what species and population your samples belong to. Please provide that information in the next sections.</p> + + {{select_species_form(url_for("species.populations.samples.index"), species)}} +</div> +{%endblock%} diff --git a/uploader/templates/samples/list-samples.html b/uploader/templates/samples/list-samples.html new file mode 100644 index 0000000..13e5cec --- /dev/null +++ b/uploader/templates/samples/list-samples.html @@ -0,0 +1,132 @@ +{%extends "samples/base.html"%} +{%from "flash_messages.html" import flash_all_messages%} +{%from "populations/macro-select-population.html" import select_population_form%} +{%from "populations/macro-display-population-card.html" import display_population_card%} + +{%block title%}Samples — List Samples{%endblock%} + +{%block pagetitle%}Samples — List Samples{%endblock%} + +{%block lvl4_breadcrumbs%} +<li {%if activelink=="list-samples"%} + class="breadcrumb-item active" + {%else%} + class="breadcrumb-item" + {%endif%}> + <a href="{{url_for('species.populations.samples.list_samples', + species_id=species.SpeciesId, + population_id=population.Id)}}">List</a> +</li> +{%endblock%} + +{%block contents%} +{{flash_all_messages()}} + +<div class="row"> + <p> + You selected the population "{{population.FullName}}" from the + "{{species.FullName}}" species. + </p> +</div> + +{%if samples | length > 0%} +<div class="row"> + <p> + This population already has <strong>{{total_samples}}</strong> + samples/individuals entered. You can explore the list of samples in this + population in the table below. + </p> +</div> + +<div class="row"> + <div class="col-md-2"> + {%if offset > 0:%} + <a href="{{url_for('species.populations.samples.list_samples', + species_id=species.SpeciesId, + population_id=population.Id, + from=offset-count, + count=count)}}"> + <span class="glyphicon glyphicon-backward"></span> + Previous + </a> + {%endif%} + </div> + + <div class="col-md-8" style="text-align: center;"> + Samples {{offset}} — {{offset+(count if offset + count < total_samples else total_samples - offset)}} / {{total_samples}} + </div> + + <div class="col-md-2"> + {%if offset + count < total_samples:%} + <a href="{{url_for('species.populations.samples.list_samples', + species_id=species.SpeciesId, + population_id=population.Id, + from=offset+count, + count=count)}}"> + Next + <span class="glyphicon glyphicon-forward"></span> + </a> + {%endif%} + </div> +</div> +<div class="row"> + <table class="table"> + <thead> + <tr> + <th>#</th> + <th>Name</th> + <th>Auxilliary Name</th> + <th>Symbol</th> + <th>Alias</th> + </tr> + </thead> + + <tbody> + {%for sample in samples%} + <tr> + <td>{{sample.sequence_number}}</td> + <td>{{sample.Name}}</td> + <td>{{sample.Name2}}</td> + <td>{{sample.Symbol or "-"}}</td> + <td>{{sample.Alias or "-"}}</td> + </tr> + {%endfor%} + </tbody> + </table> + + <p> + <a href="#" + title="Add samples for population '{{population.FullName}}' from species + '{{species.FullName}}'." + class="btn btn-danger"> + delete all samples + </a> + </p> +</div> + +{%else%} + +<div class="row"> + <p> + There are no samples entered for this population. Do please go ahead and add + the samples for this population by clicking on the button below. + </p> + + <p> + <a href="{{url_for('species.populations.samples.upload_samples', + species_id=species.SpeciesId, + population_id=population.Id)}}" + title="Add samples for population '{{population.FullName}}' from species + '{{species.FullName}}'." + class="btn btn-primary"> + add samples + </a> + </p> +</div> +{%endif%} + +{%endblock%} + +{%block sidebarcontents%} +{{display_population_card(species, population)}} +{%endblock%} diff --git a/uploader/templates/samples/select-population.html b/uploader/templates/samples/select-population.html index da19ddc..f437780 100644 --- a/uploader/templates/samples/select-population.html +++ b/uploader/templates/samples/select-population.html @@ -1,99 +1,39 @@ -{%extends "base.html"%} -{%from "flash_messages.html" import flash_messages%} +{%extends "samples/base.html"%} +{%from "flash_messages.html" import flash_all_messages%} +{%from "populations/macro-select-population.html" import select_population_form%} +{%from "species/macro-display-species-card.html" import display_species_card%} -{%block title%}Select Grouping/Population{%endblock%} +{%block title%}Samples — Select Population{%endblock%} -{%block contents%} -<h1 class="heading">Select grouping/population</h1> - -<div> - <p>We organise the samples/cases/strains in a hierarchichal form, starting - with <strong>species</strong> at the very top. Under species, we have a - grouping in terms of the relevant population - (e.g. Inbred populations, cell tissue, etc.)</p> -</div> - -<form method="POST" action="{{url_for('samples.select_population', - species_id=species.SpeciesId)}}"> - <legend class="heading">select grouping/population</legend> - {{flash_messages("error-select-population")}} - - <input type="hidden" name="species_id" value="{{species.SpeciesId}}" /> - - <div class="form-group"> - <label for="select:inbredset" class="form-label">grouping/population</label> - <select id="select:inbredset" - name="inbredset_id" - required="required" - class="form-control"> - <option value="">Select a grouping/population</option> - {%for pop in populations%} - <option value="{{pop.InbredSetId}}"> - {{pop.InbredSetName}} ({{pop.FullName}})</option> - {%endfor%} - </select> - </div> - - <button type="submit" class="btn btn-primary">select population</button> -</form> - -<p style="color:#FE3535; padding-left:20em; font-weight:bolder;">OR</p> - -<form method="POST" action="{{url_for('samples.create_population', - species_id=species.SpeciesId)}}"> - <legend class="heading">create new grouping/population</legend> - {{flash_messages("error-create-population")}} +{%block pagetitle%}Samples — Select Population{%endblock%} - <input type="hidden" name="species_id" value="{{species.SpeciesId}}" /> - <div class="form-group"> - <legend>mandatory</legend> - <label for="txt:inbredset-name" class="form-label">name</label> - <input id="txt:inbredset-name" - name="inbredset_name" - type="text" - required="required" - placeholder="Enter grouping/population name" - class="form-control" /> - - <label for="txt:" class="form-label">full name</label> - <input id="txt:inbredset-fullname" - name="inbredset_fullname" - type="text" - required = "required" - placeholder="Enter the grouping/population's full name" - class="form-control" /> - </div> - <div class="form-group"> - <legend>Optional</legend> - - <label for="num:public" class="form-label">public?</label> - <input id="num:public" - name="public" - type="number" - min="0" max="2" value="2" - class="form-control" /> - - <label for="txt:inbredset-family" class="form-label">family</label> - <input id="txt:inbredset-family" - name="inbredset_family" - type="text" - placeholder="I am not sure what this is about." - class="form-control" /> +{%block contents%} +{{flash_all_messages()}} - <label for="txtarea:" class="form-label">Description</label> - <textarea id="txtarea:description" - name="description" - rows="5" - placeholder="Enter a description of this grouping/population" - class="form-control"></textarea> - </div> +<div class="row"> + <p>You have selected "{{species.FullName}}" as the species that your data relates to.</p> + <p>Next, we need information regarding the population your data relates to. Do please select the population from the existing ones below</p> +</div> - <button type="submit" class="btn btn-primary">create grouping/population</button> -</form> +<div class="row"> + {{select_population_form( + url_for("species.populations.samples.select_population", species_id=species.SpeciesId), + populations)}} +</div> +<div class="row"> + <p> + If you cannot find the population your data relates to in the drop-down + above, you might want to + <a href="{{url_for('species.populations.create_population', + species_id=species.SpeciesId)}}" + title="Create a new population for species '{{species.FullName}},"> + add a new population to GeneNetwork</a> + instead. +</div> {%endblock%} - -{%block javascript%} +{%block sidebarcontents%} +{{display_species_card(species)}} {%endblock%} diff --git a/uploader/templates/samples/select-species.html b/uploader/templates/samples/select-species.html deleted file mode 100644 index edadc61..0000000 --- a/uploader/templates/samples/select-species.html +++ /dev/null @@ -1,30 +0,0 @@ -{%extends "base.html"%} -{%from "flash_messages.html" import flash_all_messages%} - -{%block title%}Select Grouping/Population{%endblock%} - -{%block contents%} -<h2 class="heading">upload samples/cases</h2> - -<p>We need to know what species your data belongs to.</p> - -{{flash_all_messages()}} - -<form method="POST" action="{{url_for('samples.select_species')}}"> - <legend class="heading">upload samples</legend> - <div class="form-group"> - <label for="select_species02" class="form-label">Species</label> - <select id="select_species02" - name="species_id" - required="required" - class="form-control"> - <option value="">Select species</option> - {%for spec in species%} - <option value="{{spec.SpeciesId}}">{{spec.MenuName}}</option> - {%endfor%} - </select> - </div> - - <button type="submit" class="btn btn-primary">submit</button> -</form> -{%endblock%} diff --git a/uploader/templates/samples/upload-failure.html b/uploader/templates/samples/upload-failure.html index 09e2ecf..458ab55 100644 --- a/uploader/templates/samples/upload-failure.html +++ b/uploader/templates/samples/upload-failure.html @@ -1,10 +1,12 @@ {%extends "base.html"%} {%from "cli-output.html" import cli_output%} +{%from "populations/macro-display-population-card.html" import display_population_card%} {%block title%}Samples Upload Failure{%endblock%} {%block contents%} -<h1 class="heading">{{job.job_name}}</h2> +<div class="row"> +<h2 class="heading">{{job.job_name[0:50]}}…</h2> <p>There was a failure attempting to upload the samples.</p> @@ -17,11 +19,19 @@ <li><strong>status</strong>: {{job.status}}</li> <li><strong>job type</strong>: {{job["job-type"]}}</li> </ul> +</div> +<div class="row"> <h4>stdout</h4> {{cli_output(job, "stdout")}} +</div> +<div class="row"> <h4>stderr</h4> {{cli_output(job, "stderr")}} +</div> +{%endblock%} +{%block sidebarcontents%} +{{display_population_card(species, population)}} {%endblock%} diff --git a/uploader/templates/samples/upload-progress.html b/uploader/templates/samples/upload-progress.html index 7bb02be..677d457 100644 --- a/uploader/templates/samples/upload-progress.html +++ b/uploader/templates/samples/upload-progress.html @@ -1,5 +1,6 @@ -{%extends "base.html"%} +{%extends "samples/base.html"%} {%from "cli-output.html" import cli_output%} +{%from "populations/macro-display-population-card.html" import display_population_card%} {%block extrameta%} <meta http-equiv="refresh" content="5"> @@ -8,7 +9,8 @@ {%block title%}Job Status{%endblock%} {%block contents%} -<h1 class="heading">{{job.job_name}}</h2> +<div class="row" style="overflow-x: clip;"> +<h2 class="heading">{{job.job_name[0:50]}}…</h2> <p> <strong>status</strong>: @@ -16,7 +18,14 @@ </p> <p>saving to database...</p> +</div> -{{cli_output(job, "stdout")}} +<div class="row"> + {{cli_output(job, "stdout")}} +</div> {%endblock%} + +{%block sidebarcontents%} +{{display_population_card(species, population)}} +{%endblock%} diff --git a/uploader/templates/samples/upload-samples.html b/uploader/templates/samples/upload-samples.html index e62de57..25d3290 100644 --- a/uploader/templates/samples/upload-samples.html +++ b/uploader/templates/samples/upload-samples.html @@ -1,138 +1,159 @@ -{%extends "base.html"%} -{%from "flash_messages.html" import flash_messages%} - -{%block title%}Upload Samples{%endblock%} - -{%block css%}{%endblock%} +{%extends "samples/base.html"%} +{%from "flash_messages.html" import flash_all_messages%} +{%from "populations/macro-select-population.html" import select_population_form%} +{%from "populations/macro-display-population-card.html" import display_population_card%} + +{%block title%}Samples — Upload Samples{%endblock%} + +{%block pagetitle%}Samples — Upload Samples{%endblock%} + +{%block lvl4_breadcrumbs%} +<li {%if activelink=="uploade-samples"%} + class="breadcrumb-item active" + {%else%} + class="breadcrumb-item" + {%endif%}> + <a href="{{url_for('species.populations.samples.upload_samples', + species_id=species.SpeciesId, + population_id=population.Id)}}">List</a> +</li> +{%endblock%} {%block contents%} -<h1 class="heading">upload samples</h1> - -{{flash_messages("alert-success")}} - -<p>You can now upload a character-separated value (CSV) file that contains - details about your samples. The CSV file should have the following fields: - <dl> - <dt>Name</dt> - <dd>The primary name for the sample</dd> - - <dt>Name2</dt> - <dd>A secondary name for the sample. This can simply be the same as - <strong>Name</strong> above. This field <strong>MUST</strong> contain a - value.</dd> - - <dt>Symbol</dt> - <dd>A symbol for the sample. Can be an empty field.</dd> - - <dt>Alias</dt> - <dd>An alias for the sample. Can be an empty field.</dd> - </dl> -</p> - -<form id="form-samples" - method="POST" - action="{{url_for('samples.upload_samples', - species_id=species.SpeciesId, - population_id=population.InbredSetId)}}" - enctype="multipart/form-data"> - <legend class="heading">upload samples</legend> - - <div class="form-group"> - <input type="hidden" name="species_id" value="{{species.SpeciesId}}" /> - <label class="form-label">species:</label> - <span class="form-text">{{species.SpeciesName}} [{{species.MenuName}}]</span> - </div> - - <div class="form-group"> - <input type="hidden" name="inbredset_id" value="{{population.InbredSetId}}" /> - <label class="form-label">grouping/population:</label> - <span class="form-text">{{population.Name}} [{{population.FullName}}]</span> - </div> - - <div class="form-group"> - <label for="file-samples" class="form-label">select file</label> - <input type="file" name="samples_file" id="file:samples" - accept="text/csv, text/tab-separated-values" - class="form-control" /> - </div> - - <div class="form-group"> - <label for="select:separator" class="form-label">field separator</label> - <select id="select:separator" - name="separator" - required="required" - class="form-control"> - <option value="">Select separator for your file: (default is comma)</option> - <option value="	">TAB</option> - <option value=" ">Space</option> - <option value=",">Comma</option> - <option value=";">Semicolon</option> - <option value="other">Other</option> - </select> - <input id="txt:separator" - type="text" - name="other_separator" - class="form-control" /> - <small class="form-text text-muted"> - If you select '<strong>Other</strong>' for the field separator value, - enter the character that separates the fields in your CSV file in the form - field below. - </small> - </div> - - <div class="form-group form-check"> - <input id="chk:heading" - type="checkbox" - name="first_line_heading" - class="form-check-input" /> - <label for="chk:heading" class="form-check-label"> - first line is a heading?</label> - <small class="form-text text-muted"> - Select this if the first line in your file contains headings for the - columns. - </small> - </div> - - <div class="form-group"> - <label for="txt:delimiter" class="form-label">field delimiter</label> - <input id="txt:delimiter" - type="text" - name="field_delimiter" - maxlength="1" - class="form-control" /> - <small class="form-text text-muted"> - If there is a character delimiting the string texts within particular - fields in your CSV, provide the character here. This can be left blank if - no such delimiters exist in your file. - </small> - </div> - - <button type="submit" - class="btn btn-primary">upload samples file</button> -</form> - -<table id="tbl:samples-preview" class="table"> - <caption class="heading">preview content</caption> - - <thead> - <tr> - <th>Name</th> - <th>Name2</th> - <th>Symbol</th> - <th>Alias</th> - </tr> - </thead> - - <tbody> - <tr id="default-row"> - <td colspan="4"> - Please make some selections to preview the data.</td> - </tr> - </tbody> -</table> +{{flash_all_messages()}} + +<div class="row"> + <p> + You can now upload the samples for the "{{population.FullName}}" population + from the "{{species.FullName}}" species here. + </p> + <p> + Upload a <strong>character-separated value (CSV)</strong> file that contains + details about your samples. The CSV file should have the following fields: + <dl> + <dt>Name</dt> + <dd>The primary name/identifier for the sample/individual.</dd> + + <dt>Name2</dt> + <dd>A secondary name for the sample. This can simply be the same as + <strong>Name</strong> above. This field <strong>MUST</strong> contain a + value.</dd> + + <dt>Symbol</dt> + <dd>A symbol for the sample. This can be a strain name, e.g. 'BXD60' for + species that have strains. This field can be left empty for species like + Humans that do not have strains..</dd> + + <dt>Alias</dt> + <dd>An alias for the sample. Can be an empty field, or take on the same + value as that of the Symbol.</dd> + </dl> + </p> +</div> + +<div class="row"> + <form id="form-samples" + method="POST" + action="{{url_for('species.populations.samples.upload_samples', + species_id=species.SpeciesId, + population_id=population.InbredSetId)}}" + enctype="multipart/form-data"> + <legend class="heading">upload samples</legend> + <input type="hidden" name="species_id" value="{{species.SpeciesId}}" /> + <input type="hidden" name="population_id" value="{{population.Id}}" /> + + <div class="form-group"> + <label for="file-samples" class="form-label">select file</label> + <input type="file" name="samples_file" id="file:samples" + accept="text/csv, text/tab-separated-values" + class="form-control" /> + </div> + + <div class="form-group"> + <label for="select:separator" class="form-label">field separator</label> + <select id="select:separator" + name="separator" + required="required" + class="form-control"> + <option value="">Select separator for your file: (default is comma)</option> + <option value="	">TAB</option> + <option value=" ">Space</option> + <option value=",">Comma</option> + <option value=";">Semicolon</option> + <option value="other">Other</option> + </select> + <input id="txt:separator" + type="text" + name="other_separator" + class="form-control" /> + <small class="form-text text-muted"> + If you select '<strong>Other</strong>' for the field separator value, + enter the character that separates the fields in your CSV file in the form + field below. + </small> + </div> + + <div class="form-group form-check"> + <input id="chk:heading" + type="checkbox" + name="first_line_heading" + class="form-check-input" /> + <label for="chk:heading" class="form-check-label"> + first line is a heading?</label> + <small class="form-text text-muted"> + Select this if the first line in your file contains headings for the + columns. + </small> + </div> + + <div class="form-group"> + <label for="txt:delimiter" class="form-label">field delimiter</label> + <input id="txt:delimiter" + type="text" + name="field_delimiter" + maxlength="1" + class="form-control" /> + <small class="form-text text-muted"> + If there is a character delimiting the string texts within particular + fields in your CSV, provide the character here. This can be left blank if + no such delimiters exist in your file. + </small> + </div> + + <button type="submit" + class="btn btn-primary">upload samples file</button> + </form> +</div> + +<div class="row"> + <h3>Preview File Content</h3> + + <table id="tbl:samples-preview" class="table"> + <caption class="heading">preview content</caption> + + <thead> + <tr> + <th>Name</th> + <th>Name2</th> + <th>Symbol</th> + <th>Alias</th> + </tr> + </thead> + + <tbody> + <tr id="default-row"> + <td colspan="4"> + Please make some selections in the form above to preview the data.</td> + </tr> + </tbody> + </table> +</div> {%endblock%} +{%block sidebarcontents%} +{{display_population_card(species, population)}} +{%endblock%} {%block javascript%} <script src="/static/js/upload_samples.js" type="text/javascript"></script> diff --git a/uploader/templates/samples/upload-success.html b/uploader/templates/samples/upload-success.html index cb745c3..881d466 100644 --- a/uploader/templates/samples/upload-success.html +++ b/uploader/templates/samples/upload-success.html @@ -1,18 +1,36 @@ -{%extends "base.html"%} +{%extends "samples/base.html"%} {%from "cli-output.html" import cli_output%} +{%from "populations/macro-display-population-card.html" import display_population_card%} {%block title%}Job Status{%endblock%} {%block contents%} -<h1 class="heading">{{job.job_name}}</h2> -<p> -<strong>status</strong>: -<span>{{job["status"]}} ({{job.get("message", "-")}})</span><br /> -</p> +<div class="row" style="overflow-x: clip;"> + <h2 class="heading">{{job.job_name[0:50]}}…</h2> -<p>Successfully uploaded the samples.</p> + <p> + <strong>status</strong>: + <span>{{job["status"]}} ({{job.get("message", "-")}})</span><br /> + </p> -{{cli_output(job, "stdout")}} + <p>Successfully uploaded the samples.</p> + <p> + <a href="{{url_for('species.populations.samples.list_samples', + species_id=species.SpeciesId, + population_id=population.Id)}}" + title="View population samples"> + View samples + </a> + </p> +</div> +<div class="row"> + {{cli_output(job, "stdout")}} +</div> + +{%endblock%} + +{%block sidebarcontents%} +{{display_population_card(species, population)}} {%endblock%} diff --git a/uploader/templates/select_species.html b/uploader/templates/select_species.html deleted file mode 100644 index 3b1a8a9..0000000 --- a/uploader/templates/select_species.html +++ /dev/null @@ -1,92 +0,0 @@ -{%extends "base.html"%} -{%from "flash_messages.html" import flash_messages%} -{%from "upload_progress_indicator.html" import upload_progress_indicator%} - -{%block title%}expression data: select species{%endblock%} - -{%block contents%} -{{upload_progress_indicator()}} - -<h2 class="heading">expression data: select species</h2> - -<div class="row"> - <form action="{{url_for('entry.upload_file')}}" - method="POST" - enctype="multipart/form-data" - id="frm-upload-expression-data"> - <legend class="heading">upload expression data</legend> - {{flash_messages("error-expr-data")}} - - <div class="form-group"> - <label for="select_species01" class="form-label">Species</label> - <select id="select_species01" - name="speciesid" - required="required" - class="form-control"> - <option value="">Select species</option> - {%for aspecies in species%} - <option value="{{aspecies.SpeciesId}}">{{aspecies.MenuName}}</option> - {%endfor%} - </select> - </div> - - <div class="form-group"> - <legend class="heading">file type</legend> - - <div class="form-check"> - <input type="radio" name="filetype" value="average" id="filetype_average" - required="required" class="form-check-input" /> - <label for="filetype_average" class="form-check-label">average</label> - </div> - - <div class="form-check"> - <input type="radio" name="filetype" value="standard-error" - id="filetype_standard_error" required="required" - class="form-check-input" /> - <label for="filetype_standard_error" class="form-check-label"> - standard error - </label> - </div> - </div> - - <div class="form-group"> - <span id="no-file-error" class="alert-danger" style="display: none;"> - No file selected - </span> - <label for="file_upload" class="form-label">select file</label> - <input type="file" name="qc_text_file" id="file_upload" - accept="text/plain, text/tab-separated-values, application/zip" - class="form-control"/> - </div> - - <button type="submit" - class="btn btn-primary" - data-toggle="modal" - data-target="#upload-progress-indicator">upload file</button> - </form> -</div> -{%endblock%} - - -{%block javascript%} -<script type="text/javascript" src="static/js/upload_progress.js"></script> -<script type="text/javascript"> - function setup_formdata(form) { - var formdata = new FormData(); - formdata.append( - "speciesid", - form.querySelector("#select_species01").value) - formdata.append( - "qc_text_file", - form.querySelector("input[type='file']").files[0]); - formdata.append( - "filetype", - selected_filetype( - Array.from(form.querySelectorAll("input[type='radio']")))); - return formdata; - } - - setup_upload_handlers( - "frm-upload-expression-data", make_data_uploader(setup_formdata)); -</script> -{%endblock%} diff --git a/uploader/templates/species/base.html b/uploader/templates/species/base.html new file mode 100644 index 0000000..04391db --- /dev/null +++ b/uploader/templates/species/base.html @@ -0,0 +1,12 @@ +{%extends "base.html"%} + +{%block lvl1_breadcrumbs%} +<li {%if activelink=="species"%} + class="breadcrumb-item active" + {%else%} + class="breadcrumb-item" + {%endif%}> + <a href="{{url_for('species.list_species')}}">Species</a> +</li> +{%block lvl2_breadcrumbs%}{%endblock%} +{%endblock%} diff --git a/uploader/templates/species/create-species.html b/uploader/templates/species/create-species.html new file mode 100644 index 0000000..0d0bedf --- /dev/null +++ b/uploader/templates/species/create-species.html @@ -0,0 +1,132 @@ +{%extends "species/base.html"%} +{%from "flash_messages.html" import flash_all_messages%} + +{%block title%}Create Species{%endblock%} + +{%block pagetitle%}Create Species{%endblock%} + +{%block lvl2_breadcrumbs%} +<li {%if activelink=="create-species"%} + class="breadcrumb-item active" + {%else%} + class="breadcrumb-item" + {%endif%}> + <a href="{{url_for('species.create_species')}}">Create</a> +</li> +{%endblock%} + +{%block contents%} +<div class="row"> + <form id="frm-create-species" + method="POST" + action="{{url_for('species.create_species')}}"> + <legend>Create Species</legend> + + {{flash_all_messages()}} + + <div class="form-group"> + <label for="txt-taxonomy-id" class="form-label"> + Taxonomy ID</label> + <div class="input-group"> + <input id="txt-taxonomy-id" + name="species_taxonomy_id" + type="text" + class="form-control" /> + <span class="input-group-btn"> + <button id="btn-search-taxonid" class="btn btn-info">Search</button> + </span> + </div> + <small class="form-text text-small text-muted">Provide the taxonomy ID for + your species that can be used to link to external sites like NCBI. Enter + the taxonomy ID and click "Search" to auto-fill the form with data. + <br /> + While it is recommended to provide a value for this field, doing so is + optional. + </small> + </div> + + <div class="form-group"> + <label for="txt-species-name" class="form-label">Common Name</label> + <input id="txt-species-name" + name="common_name" + type="text" + class="form-control" + required="required" /> + <small class="form-text text-muted">Provide the common, possibly + non-scientific name for the species here, e.g. Human, Mouse, etc.</small> + </div> + + <div class="form-group"> + <label for="txt-species-scientific" class="form-label"> + Scientific Name</label> + <input id="txt-species-scientific" + name="scientific_name" + type="text" + class="form-control" + required="required" /> + <small class="form-text text-muted">Provide the scientific name for the + species you are creating, e.g. Homo sapiens, Mus musculus, etc.</small> + </div> + + <div class="form-group"> + <label for="select-species-family" class="form-label">Family</label> + <select id="select-species-family" + name="species_family" + required="required" + class="form-control"> + <option value="">Please select a grouping</option> + {%for family in families%} + <option value="{{family}}">{{family}}</option> + {%endfor%} + </select> + <small class="form-text text-muted"> + This is a generic grouping for the species that determines under which + grouping the species appears in the GeneNetwork menus</small> + </div> + + <div class="form-group"> + <input type="submit" + value="create new species" + class="btn btn-primary" /> + </div> + + </form> +</div> +{%endblock%} + +{%block javascript%} +<script> + var lastTaxonId = null; + + var fetch_taxonomy = (taxonId) => { + var uri = ( + "https://rest.uniprot.org/taxonomy/" + encodeURIComponent(taxonId)); + $.get( + uri, + {}, + (data, textStatus, jqXHR) => { + if(textStatus == "success") { + lastTaxonId = taxonId; + $("#txt-species-scientific").val(data.scientificName); + $("#txt-species-name").val(data.commonName); + return false; + } + msg = ( + "Request to '${uri}' failed with message '${textStatus}'. " + + "Please try again later, or fill the details manually."); + alert(msg); + console.error(msg, data, textStatus); + return false; + }, + "json"); + }; + + $("#btn-search-taxonid").on("click", (event) => { + event.preventDefault(); + taxonId = $("#txt-taxonomy-id").val(); + if((taxonId !== "") && (taxonId !== lastTaxonId)) { + fetch_taxonomy(taxonId); + } + }); +</script> +{%endblock%} diff --git a/uploader/templates/species/edit-species.html b/uploader/templates/species/edit-species.html new file mode 100644 index 0000000..5a26455 --- /dev/null +++ b/uploader/templates/species/edit-species.html @@ -0,0 +1,177 @@ +{%extends "species/base.html"%} +{%from "flash_messages.html" import flash_all_messages%} + +{%block title%}Edit Species{%endblock%} + +{%block pagetitle%}Edit Species{%endblock%} + +{%block css%} +<style type="text/css"> + .card { + margin-top: 0.3em; + border-width: 1px; + border-style: solid; + border-radius: 0.3em; + border-color: #AAAAAA; + padding: 0.5em; + } +</style> +{%endblock%} + +{%block lvl2_breadcrumbs%} +<li {%if activelink=="edit-species"%} + class="breadcrumb-item active" + {%else%} + class="breadcrumb-item" + {%endif%}> + <a href="{{url_for('species.edit_species_extra', + species_id=species.SpeciesId)}}">Edit</a> +</li> +{%endblock%} + +{%block contents%} +{{flash_all_messages()}} +<div class="row"> + <form id="frm-edit-species" + method="POST" + action="{{url_for('species.edit_species_extra', + species_id=species.SpeciesId)}}"> + + <legend>Edit Extra Detail for Species '{{species.FullName}}'</legend> + + <input type="hidden" name="species_id" value="{{species.SpeciesId}}" /> + + <div class="form-group"> + <label for="lbl-species-taxonid" class="form-label"> + Taxonomy Id + </label> + <label id="lbl-species-taxonid" + disabled="disabled" + class="form-control">{{species.TaxonomyId}}</label> + </div> + + <div class="form-group"> + <label for="txt-species-name" class="form-label"> + Common Name + </label> + <input type="text" + id="txt-species-name" + name="species_name" + required="required" + value="{{species.SpeciesName}}" + class="form-control" /> + <small class="form-text text-muted"> + This is the layman's name for the species, e.g. mouse</mall> + </div> + + <div class="form-group"> + <label for="txt-species-fullname" class="form-label"> + Scientific Name + </label> + <input type="text" + id="txt-species-fullname" + name="species_fullname" + required="required" + value="{{species.FullName}}" + class="form-control" /> + <small class="form-text text-muted"> + A scientific name for the species that mostly adheres to the biological + binomial nomenclature system.</small> + </div> + + <div class="form-group"> + <label for="select-species-family" class="form-label"> + Family + </label> + <select id="select-species-family" + name="species_family" + class="form-control"> + <option value="">Select the family</option> + {%for family in families%} + <option value="{{family}}" + {%if species.Family == family%} + selected="selected" + {%endif%}>{{family}}</option> + {%endfor%} + </select> + <small class="form-text text-muted"> + A general classification for the species. This is mostly for use in + GeneNetwork's menus.</small> + </div> + + <div class="form-group"> + <label for="txt-species-familyorderid" class="form-label"> + Family Order Id + </label> + <input type="number" + id="txt-species-familyorderid" + name="species_familyorderid" + value="{{species.FamilyOrderId}}" + required="required" + class="form-control" /> + <small class="form-text text-muted"> + This is a number that determines the order of the "Family" groupings + above in the GeneNetwork menus. This is an integer value that's manually + assigned.</small> + </div> + + <div class="form-group"> + <label for="txt-species-orderid" class="form-label"> + Order Id + </label> + <input type="number" + id="txt-species-orderid" + name="species_orderid" + value="{{species.OrderId or (max_order_id + 5)}}" + class="form-control" /> + <small class="form-text text-muted"> + This integer value determines the order of the species in relation to + each other, but also within the respective "Family" groups.</small> + </div> + + <div class="form-group"> + <input type="submit" value="Submit Changes" class="btn btn-primary" /> + </div> + + </form> +</div> +{%endblock%} + +{%block sidebarcontents%} + +<div class="card"> + <div class="card-body"> + <h5 class="card-title">Family Order</h5> + <div class="card-text"> + <p>The current family order is as follows</p> + <table class="table"> + <thead> + <tr> + <th>Family Order Id</th> + <th>Family</th> + </tr> + </thead> + <tbody> + {%for item in family_order%} + <tr> + <td>{{item[0]}}</td> + <td>{{item[1]}}</td> + </tr> + {%endfor%} + </tbody> + </table> + </div> + </div> +</div> + +<div class="card"> + <div class="card-body"> + <h5 class="card-title">Order ID</h5> + <div class="card-text"> + <p>The current largest OrderID is: {{max_order_id}}</p> + <p>We recommend giving a new species an order ID that is five more than + the current highest i.e. {{max_order_id + 5}}.</p> + </div> + </div> +</div> +{%endblock%} diff --git a/uploader/templates/species/list-species.html b/uploader/templates/species/list-species.html new file mode 100644 index 0000000..85c9d40 --- /dev/null +++ b/uploader/templates/species/list-species.html @@ -0,0 +1,75 @@ +{%extends "species/base.html"%} +{%from "flash_messages.html" import flash_all_messages%} + +{%block title%}List Species{%endblock%} + +{%block pagetitle%}List Species{%endblock%} + +{%block contents%} +{{flash_all_messages()}} +<div class="row"> + <p> + All data in GeneNetwork revolves around species. This is the core of the + system.</p> + <p>Here you can see a list of all the species available in GeneNetwork. + Click on the link besides each species to view greater detail on the species, + and access further operations that are possible for said species.</p> +</div> + +<div class="row"> + <p>If you cannot find the species you are looking for below, click the button + below to create it</p> + <p><a href="{{url_for('species.create_species')}}" + title="Add a new species to GeneNetwork" + class="btn btn-danger">Create Species</a></p> +</div> + +<div class="row"> + <table class="table"> + <caption>Available Species</caption> + <thead> + <tr> + <th>#</td> + <th title="A common, layman's name for the species.">Common Name</th> + <th title="The scientific name for the species">Organism Name</th> + <th title="An identifier for the species in the NCBI taxonomy database"> + Taxonomy ID + </th> + <th title="A generic grouping used internally by GeneNetwork for organising species."> + Family + </th> + </tr> + </thead> + <tbody> + {%for species in allspecies%} + <tr> + <td>{{species["sequence_number"]}}</td> + <td>{{species["SpeciesName"]}}</td> + <td> + <a href="{{url_for('species.view_species', + species_id=species['SpeciesId'])}}" + title="View details in GeneNetwork on {{species['FullName']}}"> + {{species["FullName"]}} + </a> + </td> + <td> + <a href="https://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?id={{species['TaxonomyId']}}" + title="View species details on NCBI" + target="_blank">{{species["TaxonomyId"]}}</a> + </td> + <td>{{species.Family}}</td> + </tr> + {%else%} + <tr> + <td colspan="3"> + <p class="text-danger"> + <span class="glyphicon glyphicon-exclamation-mark"></span> + There were no species found! + </p> + </td> + </tr> + {%endfor%} + </tbody> + </table> +</div> +{%endblock%} diff --git a/uploader/templates/species/macro-display-species-card.html b/uploader/templates/species/macro-display-species-card.html new file mode 100644 index 0000000..166c7b9 --- /dev/null +++ b/uploader/templates/species/macro-display-species-card.html @@ -0,0 +1,22 @@ +{%macro display_species_card(species)%} +<div class="card"> + <div class="card-body"> + <h5 class="card-title">Species</h5> + <div class="card-text"> + <table class="table"> + <tbody> + <tr> + <td>Common Name</td> + <td>{{species.SpeciesName}}</td> + </tr> + + <tr> + <td>Scientific Name</td> + <td>{{species.FullName}}</td> + </tr> + </tbody> + </table> + </div> + </div> +</div> +{%endmacro%} diff --git a/uploader/templates/species/macro-select-species.html b/uploader/templates/species/macro-select-species.html new file mode 100644 index 0000000..dd086c0 --- /dev/null +++ b/uploader/templates/species/macro-select-species.html @@ -0,0 +1,36 @@ +{%macro select_species_form(form_action, species)%} +{%if species | length > 0%} +<form method="GET" action="{{form_action}}"> + <div class="form-group"> + <label for="select-species" class="form-label">Species</label> + <select id="select-species" + name="species_id" + class="form-control" + required="required"> + <option value="">Select Species</option> + {%for group in species%} + {{group}} + <optgroup {%if group[0][1] is not none%} + label="{{group[0][1].capitalize()}}" + {%else%} + label="Undefined" + {%endif%}> + {%for aspecies in group[1]%} + <option value="{{aspecies.SpeciesId}}">{{aspecies.MenuName}}</option> + {%endfor%} + </optgroup> + {%endfor%} + </select> + </div> + + <div class="form-group"> + <input type="submit" value="Select" class="btn btn-primary" /> + </div> +</form> +{%else%} +<p class="text-danger"> + <span class="glyphicon glyphicon-exclamation-mark"></span> + We could not find species to select from! +</p> +{%endif%} +{%endmacro%} diff --git a/uploader/templates/species/view-species.html b/uploader/templates/species/view-species.html new file mode 100644 index 0000000..b01864d --- /dev/null +++ b/uploader/templates/species/view-species.html @@ -0,0 +1,84 @@ +{%extends "species/base.html"%} +{%from "flash_messages.html" import flash_all_messages%} + +{%block title%}View Species{%endblock%} + +{%block pagetitle%}View Species{%endblock%} + +{%block lvl2_breadcrumbs%} +<li {%if activelink=="view-species"%} + class="breadcrumb-item active" + {%else%} + class="breadcrumb-item" + {%endif%}> + <a href="{{url_for('species.view_species', species_id=species.SpeciesId)}}">View</a> +</li> +{%endblock%} + +{%block contents%} +{{flash_all_messages()}} +<div class="row"> + <h2>Details on species {{species.FullName}}</h2> + + <dl> + <dt>Common Name</dt> + <dd>{{species.SpeciesName}}</dd> + + <dt>Scientific Name</dt> + <dd>{{species.FullName}}</dd> + + <dt>Taxonomy ID</dt> + <dd>{{species.TaxonomyId}}</dd> + </dl> + + <h3>Actions</h3> + + <p> + You can proceed to perform any of the following actions for species + {{species.FullName}} + </p> + + <ol> + <li> + <a href="{{url_for('species.populations.list_species_populations', + species_id=species.SpeciesId)}}" + title="Create/Edit populations for {{species.FullName}}"> + Manage populations</a> + </li> + </ol> + + +</div> +{%endblock%} + +{%block sidebarcontents%} +<div class="card"> + <div class="card-body"> + <h5 class="card-title">Species Extras</h5> + <div class="card-text"> + <p>Some extra internal-use details (mostly for UI concerns on GeneNetwork)</p> + <p> + <small> + If you do not understand what the following are about, simply ignore them + — + They have no bearing whatsoever on your data, or its analysis. + </small> + </p> + <dl> + <dt>Family</dt> + <dd>{{species.Family}}</dd> + + <dt>FamilyOrderId</dt> + <dd>{{species.FamilyOrderId}}</dd> + + <dt>OrderId</dt> + <dd>{{species.OrderId}}</dd> + </dl> + </div> + <a href="{{url_for('species.edit_species_extra', + species_id=species.SpeciesId)}}" + class="card-link" + title="Edit the species' internal-use details.">Edit</a> + </div> +</div> +{%endblock%} diff --git a/uploader/ui.py b/uploader/ui.py new file mode 100644 index 0000000..1994056 --- /dev/null +++ b/uploader/ui.py @@ -0,0 +1,14 @@ +"""Utilities to handle the UI""" +from flask import render_template as flask_render_template + +def make_template_renderer(default): + """Render template for species.""" + def render_template(template, **kwargs): + return flask_render_template( + template, + **{ + **kwargs, + "activemenu": default, + "activelink": kwargs.get("activelink", default) + }) + return render_template diff --git a/uploader/upload/__init__.py b/uploader/upload/__init__.py deleted file mode 100644 index 5f120d4..0000000 --- a/uploader/upload/__init__.py +++ /dev/null @@ -1,7 +0,0 @@ -"""Package handling upload of files.""" -from flask import Blueprint - -from .rqtl2 import rqtl2 - -upload = Blueprint("upload", __name__) -upload.register_blueprint(rqtl2, url_prefix="/rqtl2") |