From 07c0daa04b2693f55dd69cae43c254ebb5c9a35b Mon Sep 17 00:00:00 2001 From: zsloan Date: Fri, 6 Apr 2018 15:50:29 +0000 Subject: Mapping figure output now gives more accurate information Committing partway through removing a bunch of unused code/files just in case something necessary gets removed --- wqflask/base/data_set.py | 147 +---------------------- wqflask/base/mrna_assay_tissue_data.py | 1 - wqflask/base/species.py | 80 +------------ wqflask/base/template.py | 123 -------------------- wqflask/base/trait.py | 206 --------------------------------- 5 files changed, 4 insertions(+), 553 deletions(-) delete mode 100644 wqflask/base/template.py (limited to 'wqflask/base') diff --git a/wqflask/base/data_set.py b/wqflask/base/data_set.py index a4eaaa2e..9ca880d0 100644 --- a/wqflask/base/data_set.py +++ b/wqflask/base/data_set.py @@ -29,7 +29,6 @@ import json import gzip import cPickle as pickle import itertools -from operator import itemgetter from redis import Redis Redis = Redis() @@ -316,9 +315,6 @@ class DatasetGroup(object): return mapping_id, mapping_names - def get_specified_markers(self, markers = []): - self.markers = HumanMarkers(self.name, markers) - def get_markers(self): logger.debug("self.species is:", self.species) @@ -449,7 +445,6 @@ def datasets(group_name, this_group = None): group_name, webqtlConfig.PUBLICTHRESH, "'" + group_name + "'", webqtlConfig.PUBLICTHRESH)) - #for tissue_name, dataset in itertools.groupby(the_results, itemgetter(0)): for dataset_item in the_results: tissue_name = dataset_item[0] dataset = dataset_item[1] @@ -457,14 +452,10 @@ def datasets(group_name, this_group = None): if tissue_name in ['#PublishFreeze', '#GenoFreeze']: dataset_menu.append(dict(tissue=None, datasets=[(dataset, dataset_short)])) else: - dataset_sub_menu = [item[1:] for item in dataset] - tissue_already_exists = False - tissue_position = None for i, tissue_dict in enumerate(dataset_menu): if tissue_dict['tissue'] == tissue_name: tissue_already_exists = True - tissue_position = i break if tissue_already_exists: @@ -719,20 +710,6 @@ class PhenotypeDataSet(DataSet): # (Urgently?) Need to write this pass - def get_trait_list(self): - query = """ - select PublishXRef.Id - from PublishXRef, PublishFreeze - where PublishFreeze.InbredSetId=PublishXRef.InbredSetId - and PublishFreeze.Id = {} - """.format(escape(str(self.id))) - logger.sql(query) - results = g.db.execute(query).fetchall() - trait_data = {} - for trait in results: - trait_data[trait[0]] = self.retrieve_sample_data(trait[0]) - return trait_data - def get_trait_info(self, trait_list, species = ''): for this_trait in trait_list: @@ -746,7 +723,7 @@ class PhenotypeDataSet(DataSet): #of the post-publication description if this_trait.confidential: this_trait.description_display = "" - continue # for now + continue # for now, because no authorization features if not webqtlUtil.hasAccessToConfidentialPhenotypeTrait( privilege=self.privilege, @@ -770,9 +747,7 @@ class PhenotypeDataSet(DataSet): #LRS and its location this_trait.LRS_score_repr = "N/A" - this_trait.LRS_score_value = 0 this_trait.LRS_location_repr = "N/A" - this_trait.LRS_location_value = 1000000 if this_trait.lrs: query = """ @@ -789,17 +764,7 @@ class PhenotypeDataSet(DataSet): LRS_Chr = result[0] LRS_Mb = result[1] - #XZ: LRS_location_value is used for sorting - try: - LRS_location_value = int(LRS_Chr)*1000 + float(LRS_Mb) - except: - if LRS_Chr.upper() == 'X': - LRS_location_value = 20*1000 + float(LRS_Mb) - else: - LRS_location_value = ord(str(LRS_chr).upper()[0])*1000 + float(LRS_Mb) - this_trait.LRS_score_repr = LRS_score_repr = '%3.1f' % this_trait.lrs - this_trait.LRS_score_value = LRS_score_value = this_trait.lrs this_trait.LRS_location_repr = LRS_location_repr = 'Chr%s: %.6f' % (LRS_Chr, float(LRS_Mb)) def retrieve_sample_data(self, trait): @@ -861,40 +826,13 @@ class GenotypeDataSet(DataSet): def check_confidentiality(self): return geno_mrna_confidentiality(self) - def get_trait_list(self): - query = """ - select Geno.Name - from Geno, GenoXRef - where GenoXRef.GenoId = Geno.Id - and GenoFreezeId = {} - """.format(escape(str(self.id))) - logger.sql(query) - results = g.db.execute(query).fetchall() - trait_data = {} - for trait in results: - trait_data[trait[0]] = self.retrieve_sample_data(trait[0]) - return trait_data - def get_trait_info(self, trait_list, species=None): for this_trait in trait_list: if not this_trait.haveinfo: this_trait.retrieveInfo() - #XZ: trait_location_value is used for sorting - trait_location_repr = 'N/A' - trait_location_value = 1000000 - if this_trait.chr and this_trait.mb: - try: - trait_location_value = int(this_trait.chr)*1000 + this_trait.mb - except: - if this_trait.chr.upper() == 'X': - trait_location_value = 20*1000 + this_trait.mb - else: - trait_location_value = ord(str(this_trait.chr).upper()[0])*1000 + this_trait.mb - this_trait.location_repr = 'Chr%s: %.6f' % (this_trait.chr, float(this_trait.mb) ) - this_trait.location_value = trait_location_value def retrieve_sample_data(self, trait): query = """ @@ -989,20 +927,6 @@ class MrnaAssayDataSet(DataSet): def check_confidentiality(self): return geno_mrna_confidentiality(self) - def get_trait_list_1(self): - query = """ - select ProbeSet.Name - from ProbeSet, ProbeSetXRef - where ProbeSetXRef.ProbeSetId = ProbeSet.Id - and ProbeSetFreezeId = {} - """.format(escape(str(self.id))) - logger.sql(query) - results = g.db.execute(query).fetchall() - trait_data = {} - for trait in results: - trait_data[trait[0]] = self.retrieve_sample_data(trait[0]) - return trait_data - def get_trait_info(self, trait_list=None, species=''): # Note: setting trait_list to [] is probably not a great idea. @@ -1034,27 +958,8 @@ class MrnaAssayDataSet(DataSet): # Save it for the jinja2 template this_trait.description_display = description_display - #XZ: trait_location_value is used for sorting - trait_location_repr = 'N/A' - trait_location_value = 1000000 - if this_trait.chr and this_trait.mb: - #Checks if the chromosome number can be cast to an int (i.e. isn't "X" or "Y") - #This is so we can convert the location to a number used for sorting - trait_location_value = self.convert_location_to_value(this_trait.chr, this_trait.mb) - #try: - # trait_location_value = int(this_trait.chr)*1000 + this_trait.mb - #except ValueError: - # if this_trait.chr.upper() == 'X': - # trait_location_value = 20*1000 + this_trait.mb - # else: - # trait_location_value = (ord(str(this_trait.chr).upper()[0])*1000 + - # this_trait.mb) - - #ZS: Put this in function currently called "convert_location_to_value" - this_trait.location_repr = 'Chr%s: %.6f' % (this_trait.chr, - float(this_trait.mb)) - this_trait.location_value = trait_location_value + this_trait.location_repr = 'Chr%s: %.6f' % (this_trait.chr, float(this_trait.mb)) #Get mean expression value query = ( @@ -1076,9 +981,7 @@ class MrnaAssayDataSet(DataSet): #LRS and its location this_trait.LRS_score_repr = 'N/A' - this_trait.LRS_score_value = 0 this_trait.LRS_location_repr = 'N/A' - this_trait.LRS_location_value = 1000000 #Max LRS and its Locus location if this_trait.lrs and this_trait.locus: @@ -1093,40 +996,10 @@ class MrnaAssayDataSet(DataSet): if result: lrs_chr, lrs_mb = result - #XZ: LRS_location_value is used for sorting - lrs_location_value = self.convert_location_to_value(lrs_chr, lrs_mb) this_trait.LRS_score_repr = '%3.1f' % this_trait.lrs - this_trait.LRS_score_value = this_trait.lrs this_trait.LRS_location_repr = 'Chr%s: %.6f' % (lrs_chr, float(lrs_mb)) - - def convert_location_to_value(self, chromosome, mb): - try: - location_value = int(chromosome)*1000 + float(mb) - except ValueError: - if chromosome.upper() == 'X': - location_value = 20*1000 + float(mb) - else: - location_value = (ord(str(chromosome).upper()[0])*1000 + - float(mb)) - - return location_value - - def get_sequence(self): - query = """ - SELECT - ProbeSet.BlatSeq - FROM - ProbeSet, ProbeSetFreeze, ProbeSetXRef - WHERE - ProbeSet.Id=ProbeSetXRef.ProbeSetId and - ProbeSetFreeze.Id = ProbeSetXRef.ProbSetFreezeId and - ProbeSet.Name = %s - ProbeSetFreeze.Name = %s - """ % (escape(self.name), escape(self.dataset.name)) - logger.sql(query) - results = g.db.execute(query).fetchone() - return results[0] + return trait_list def retrieve_sample_data(self, trait): query = """ @@ -1150,7 +1023,6 @@ class MrnaAssayDataSet(DataSet): #logger.debug("RETRIEVED RESULTS HERE:", results) return results - def retrieve_genes(self, column_name): query = """ select ProbeSet.Name, ProbeSet.%s @@ -1204,19 +1076,6 @@ class TempDataSet(DataSet): desc = self.handle_pca(desc) return desc - def get_group(self): - query = """ - SELECT - InbredSet.Name, InbredSet.Id - FROM - InbredSet, Temp - WHERE - Temp.InbredSetId = InbredSet.Id AND - Temp.Name = "%s" - """ % self.name - logger.sql(query) - self.group, self.group_id = g.db.execute(query).fetchone() - def retrieve_sample_data(self, trait): query = """ SELECT diff --git a/wqflask/base/mrna_assay_tissue_data.py b/wqflask/base/mrna_assay_tissue_data.py index eb836e6c..53f7c16a 100644 --- a/wqflask/base/mrna_assay_tissue_data.py +++ b/wqflask/base/mrna_assay_tissue_data.py @@ -18,7 +18,6 @@ class MrnaAssayTissueData(object): def __init__(self, gene_symbols=None): self.gene_symbols = gene_symbols - self.have_data = False if self.gene_symbols == None: self.gene_symbols = [] diff --git a/wqflask/base/species.py b/wqflask/base/species.py index ce763fc3..4ac2213c 100644 --- a/wqflask/base/species.py +++ b/wqflask/base/species.py @@ -18,19 +18,6 @@ class TheSpecies(object): self.dataset = dataset #print("self.dataset is:", pf(self.dataset.__dict__)) self.chromosomes = Chromosomes(self.dataset) - self.genome_mb_length = self.chromosomes.get_genome_mb_length() - - #@property - #def chromosomes(self): - # chromosomes = [("All", -1)] - # - # for counter, genotype in enumerate(self.dataset.group.genotype): - # if len(genotype) > 1: - # chromosomes.append((genotype.name, counter)) - # - # print("chromosomes is: ", pf(chromosomes)) - # - # return chromosomes class IndChromosome(object): def __init__(self, name, length): @@ -42,16 +29,11 @@ class IndChromosome(object): """Chromosome length in megabases""" return self.length / 1000000 - def set_cm_length(self, genofile_chr): - self.cm_length = genofile_chr[-1].cM - genofile_chr[0].cM - - class Chromosomes(object): def __init__(self, dataset): self.dataset = dataset self.chromosomes = collections.OrderedDict() - query = """ Select Chr_Length.Name, Chr_Length.OrderId, Length from Chr_Length, InbredSet @@ -64,64 +46,4 @@ class Chromosomes(object): results = g.db.execute(query).fetchall() for item in results: - self.chromosomes[item.OrderId] = IndChromosome(item.Name, item.Length) - - self.set_mb_graph_interval() - #self.get_cm_length_list() - - - def set_mb_graph_interval(self): - """Empirical megabase interval""" - - if self.chromosomes: - self.mb_graph_interval = self.get_genome_mb_length()/(len(self.chromosomes)*12) - else: - self.mb_graph_interval = 1 - - #if self.chromosomes: - #assert self.chromosomes, "Have to add some code back in apparently to set it to 1" - #self.mb_graph_interval = self.get_genome_mb_length()/(len(self.chromosomes)*12) - #else: - #self.mb_graph_interval = 1 - - - def get_genome_mb_length(self): - """Gets the sum of each chromosome's length in megabases""" - - return sum([ind_chromosome.mb_length for ind_chromosome in self.chromosomes.values()]) - - - def get_genome_cm_length(self): - """Gets the sum of each chromosome's length in centimorgans""" - - return sum([ind_chromosome.cm_length for ind_chromosome in self.chromosomes.values()]) - - def get_cm_length_list(self): - """Chromosome length in centimorgans - - Calculates the length in centimorgans by subtracting the centimorgan position - of the last marker in a chromosome by the position of the first marker - - """ - - self.dataset.group.read_genotype_file() - - self.cm_length_list = [] - - for chromosome in self.dataset.group.genotype: - self.cm_length_list.append(chromosome[-1].cM - chromosome[0].cM) - - print("self.cm_length_list:", pf(self.cm_length_list)) - - assert len(self.cm_length_list) == len(self.chromosomes), "Uh-oh lengths should be equal!" - for counter, chromosome in enumerate(self.chromosomes.values()): - chromosome.cm_length = self.cm_length_list[counter] - #self.chromosomes[counter].cm_length = item - - for key, value in self.chromosomes.items(): - print("bread - %s: %s" % (key, pf(vars(value)))) - - -# Testing -#if __name__ == '__main__': -# foo = dict(bar=dict(length)) + self.chromosomes[item.OrderId] = IndChromosome(item.Name, item.Length) \ No newline at end of file diff --git a/wqflask/base/template.py b/wqflask/base/template.py deleted file mode 100644 index aa8f90dc..00000000 --- a/wqflask/base/template.py +++ /dev/null @@ -1,123 +0,0 @@ -# Copyright (C) University of Tennessee Health Science Center, Memphis, TN. -# -# This program is free software: you can redistribute it and/or modify it -# under the terms of the GNU Affero General Public License -# as published by the Free Software Foundation, either version 3 of the -# License, or (at your option) any later version. -# -# This program is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. -# See the GNU Affero General Public License for more details. -# -# This program is available from Source Forge: at GeneNetwork Project -# (sourceforge.net/projects/genenetwork/). -# -# Contact Drs. Robert W. Williams and Xiaodong Zhou (2010) -# at rwilliams@uthsc.edu and xzhou15@uthsc.edu -# -# -# -# This module is used by GeneNetwork project (www.genenetwork.org) -# -# Created by GeneNetwork Core Team 2010/08/10 -# -# Last updated by GeneNetwork Core Team 2010/10/20 - -template = """ - - - - -%s - - - - - - - -%s - - - - - - - - - - - - - - -%s - - - - -%s - - - - - %s - - - - - - - - - - - - - - -
- - - %s - -
-
- %s
-
- - - - - - - - - - -""" diff --git a/wqflask/base/trait.py b/wqflask/base/trait.py index acc055d8..b71dacf6 100644 --- a/wqflask/base/trait.py +++ b/wqflask/base/trait.py @@ -25,10 +25,6 @@ logger = getLogger(__name__ ) from wqflask import user_manager -def print_mem(stage=""): - mem = resource.getrusage(resource.RUSAGE_SELF).ru_maxrss - print("{}: {}".format(stage, mem/1024)) - class GeneralTrait(object): """ Trait class defines a trait in webqtl, can be either Microarray, @@ -63,9 +59,7 @@ class GeneralTrait(object): self.symbol = None self.LRS_score_repr = "N/A" - self.LRS_score_value = 0 self.LRS_location_repr = "N/A" - self.LRS_location_value = 1000000 if kw.get('fullname'): name2 = value.split("::") @@ -82,90 +76,6 @@ class GeneralTrait(object): if get_sample_info != False: self = retrieve_sample_data(self, self.dataset) - - def get_name(self): - stringy = "" - if self.dataset and self.name: - stringy = "%s::%s" % (self.dataset, self.name) - if self.cellid: - stringy += "::" + self.cellid - else: - stringy = self.description - return stringy - - - def get_given_name(self): - """ - when user enter a trait or GN generate a trait, user want show the name - not the name that generated by GN randomly, the two follow function are - used to give the real name and the database. displayName() will show the - database also, getGivenName() just show the name. - For other trait, displayName() as same as getName(), getGivenName() as - same as self.name - - Hongqiang 11/29/07 - - """ - stringy = self.name - if self.dataset and self.name: - desc = self.dataset.get_desc() - if desc: - #desc = self.handle_pca(desc) - stringy = desc - return stringy - - - def display_name(self): - stringy = "" - if self.dataset and self.name: - desc = self.dataset.get_desc() - #desc = self.handle_pca(desc) - if desc: - #desc = self.handle_pca(desc) - #stringy = desc - #if desc.__contains__('PCA'): - # desc = desc[desc.rindex(':')+1:].strip() - #else: - # desc = desc[:desc.index('entered')].strip() - #desc = self.handle_pca(desc) - stringy = "%s::%s" % (self.dataset, desc) - else: - stringy = "%s::%s" % (self.dataset, self.name) - if self.cellid: - stringy += "::" + self.cellid - else: - stringy = self.description - - return stringy - - - #def __str__(self): - # #return "%s %s" % (self.getName(), self.group) - # return self.getName() - #__str__ = getName - #__repr__ = __str__ - - def export_data(self, samplelist, the_type="val"): - """ - export data according to samplelist - mostly used in calculating correlation - - """ - result = [] - for sample in samplelist: - if self.data.has_key(sample): - if the_type=='val': - result.append(self.data[sample].val) - elif the_type=='var': - result.append(self.data[sample].var) - elif the_type=='N': - result.append(self.data[sample].N) - else: - raise KeyError, `the_type`+' the_type is incorrect.' - else: - result.append(None) - return result - def export_informative(self, include_variance=0): """ export informative sample @@ -185,19 +95,6 @@ class GeneralTrait(object): sample_aliases.append(sample_data.name2) return samples, vals, the_vars, sample_aliases - - @property - def name_header_fmt(self): - '''Return a human-readable name for use in page header''' - if self.dataset.type == 'ProbeSet': - return self.symbol - elif self.dataset.type == 'Geno': - return self.name - elif self.dataset.type == 'Publish': - return self.post_publication_abbreviation - else: - return "unnamed" - @property def description_fmt(self): '''Return a text formated description''' @@ -252,29 +149,6 @@ class GeneralTrait(object): fmt += (' on the minus strand ') return fmt - -# In ProbeSet, there are maybe several annotations match one sequence -# so we need use sequence(BlatSeq) as the identification, when we update -# one annotation, we update the others who match the sequence also. -# -# Hongqiang Li, 3/3/2008 -def getSequence(trait, dataset_name): - dataset = create_dataset(dataset_name) - - if dataset.type == 'ProbeSet': - results = g.db.execute(''' - SELECT - ProbeSet.BlatSeq - FROM - ProbeSet, ProbeSetFreeze, ProbeSetXRef - WHERE - ProbeSet.Id=ProbeSetXRef.ProbeSetId and - ProbeSetFreeze.Id = ProbeSetXRef.ProbSetFreezeId and - ProbeSet.Name = %s - ProbeSetFreeze.Name = %s - ''', trait.name, dataset.name).fetchone() - - return results[0] def retrieve_sample_data(trait, dataset, samplelist=None): if samplelist == None: @@ -293,18 +167,6 @@ def retrieve_sample_data(trait, dataset, samplelist=None): if not samplelist or (samplelist and name in samplelist): trait.data[name] = webqtlCaseData(*item) #name, value, variance, num_cases) return trait - -def convert_location_to_value(chromosome, mb): - try: - location_value = int(chromosome)*1000 + float(mb) - except ValueError: - if chromosome.upper() == 'X': - location_value = 20*1000 + float(mb) - else: - location_value = (ord(str(chromosome).upper()[0])*1000 + - float(mb)) - - return location_value @app.route("/trait/get_sample_data") def get_sample_data(): @@ -542,38 +404,7 @@ def retrieve_trait_info(trait, dataset, get_qtl_info=False): if trait.pubmed_id: trait.pubmed_link = webqtlConfig.PUBMEDLINK_URL % trait.pubmed_id - - trait.homologeneid = None if dataset.type == 'ProbeSet' and dataset.group: - if trait.geneid: - #XZ, 05/26/2010: From time to time, this query get error message because some geneid values in database are not number. - #XZ: So I have to test if geneid is number before execute the query. - #XZ: The geneid values in database should be cleaned up. - #try: - # float(self.geneid) - # geneidIsNumber = True - #except ValueError: - # geneidIsNumber = False - #if geneidIsNumber: - query = """ - SELECT - HomologeneId - FROM - Homologene, Species, InbredSet - WHERE - Homologene.GeneId ='%s' AND - InbredSet.Name = '%s' AND - InbredSet.SpeciesId = Species.Id AND - Species.TaxonomyId = Homologene.TaxonomyId - """ % (escape(str(trait.geneid)), escape(dataset.group.name)) - logger.sql(query) - result = g.db.execute(query).fetchone() - #else: - # result = None - - if result: - trait.homologeneid = result[0] - description_string = unicode(str(trait.description).strip(codecs.BOM_UTF8), 'utf-8') target_string = unicode(str(trait.probe_target_description).strip(codecs.BOM_UTF8), 'utf-8') @@ -589,46 +420,19 @@ def retrieve_trait_info(trait, dataset, get_qtl_info=False): # Save it for the jinja2 template trait.description_display = description_display - #XZ: trait_location_value is used for sorting trait.location_repr = 'N/A' - trait.location_value = 1000000 - if trait.chr and trait.mb: - #Checks if the chromosome number can be cast to an int (i.e. isn't "X" or "Y") - #This is so we can convert the location to a number used for sorting - trait_location_value = convert_location_to_value(trait.chr, trait.mb) - #try: - # trait_location_value = int(self.chr)*1000 + self.mb - #except ValueError: - # if self.chr.upper() == 'X': - # trait_location_value = 20*1000 + self.mb - # else: - # trait_location_value = (ord(str(self.chr).upper()[0])*1000 + - # self.mb) - - #ZS: Put this in function currently called "convert_location_to_value" trait.location_repr = 'Chr%s: %.6f' % (trait.chr, float(trait.mb)) - trait.location_value = trait_location_value elif dataset.type == "Geno": trait.location_repr = 'N/A' - trait.location_value = 1000000 - if trait.chr and trait.mb: - #Checks if the chromosome number can be cast to an int (i.e. isn't "X" or "Y") - #This is so we can convert the location to a number used for sorting - trait_location_value = convert_location_to_value(trait.chr, trait.mb) - - #ZS: Put this in function currently called "convert_location_to_value" trait.location_repr = 'Chr%s: %.6f' % (trait.chr, float(trait.mb)) - trait.location_value = trait_location_value if get_qtl_info: #LRS and its location trait.LRS_score_repr = "N/A" - trait.LRS_score_value = 0 trait.LRS_location_repr = "N/A" - trait.LRS_location_value = 1000000 if dataset.type == 'ProbeSet' and not trait.cellid: query = """ SELECT @@ -699,19 +503,9 @@ def retrieve_trait_info(trait, dataset, get_qtl_info=False): trait.locus = trait.lrs = trait.additive = "" if (dataset.type == 'Publish' or dataset.type == "ProbeSet") and trait.locus_chr != "" and trait.locus_mb != "": - #XZ: LRS_location_value is used for sorting - try: - LRS_location_value = int(trait.locus_chr)*1000 + float(trait.locus_mb) - except: - if trait.locus_chr.upper() == 'X': - LRS_location_value = 20*1000 + float(trait.locus_mb) - else: - LRS_location_value = ord(str(trait.locus_chr).upper()[0])*1000 + float(trait.locus_mb) - trait.LRS_location_repr = LRS_location_repr = 'Chr%s: %.6f' % (trait.locus_chr, float(trait.locus_mb)) if trait.lrs != "": trait.LRS_score_repr = LRS_score_repr = '%3.1f' % trait.lrs - trait.LRS_score_value = LRS_score_value = trait.lrs else: raise KeyError, `trait.name`+' information is not found in the database.' -- cgit v1.2.3