From af7d0bca229f3ebaa80a16d1ce3a2bf1a8abd5df Mon Sep 17 00:00:00 2001 From: Pjotr Prins Date: Wed, 20 Apr 2016 08:37:55 +0000 Subject: [PATCH 023/100] WIP fixing all paths --- wqflask/base/data_set.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'wqflask/base/data_set.py') diff --git a/wqflask/base/data_set.py b/wqflask/base/data_set.py index e37a838f..0e5a3ac1 100755 --- a/wqflask/base/data_set.py +++ b/wqflask/base/data_set.py @@ -405,10 +405,11 @@ class DatasetGroup(object): #print("Cache not hit") from utility.tools import plink_command - PLINK_PATH,PLINK_COMMAND = plink_command() + PLINK_RUN = plink_command() geno_file_path = webqtlConfig.GENODIR+self.name+".geno" plink_file_path = PLINK_PATH+"/"+self.name+".fam" + # @FIXME PJOTR/ZACH: .fam files should go into FLATFILES if os.path.isfile(plink_file_path): self.samplelist = get_group_samplelists.get_samplelist("plink", plink_file_path) -- cgit v1.2.3 From 4b80bbfe261e8d0587a637b35416834e027f0999 Mon Sep 17 00:00:00 2001 From: Pjotr Prins Date: Wed, 20 Apr 2016 08:46:23 +0000 Subject: [PATCH 024/100] Sanitizing file handling --- wqflask/base/data_set.py | 29 ++++++++++------------------- wqflask/utility/tools.py | 20 +++++++++++++++----- wqflask/wqflask/show_trait/show_trait.py | 11 ++++------- 3 files changed, 29 insertions(+), 31 deletions(-) (limited to 'wqflask/base/data_set.py') diff --git a/wqflask/base/data_set.py b/wqflask/base/data_set.py index 0e5a3ac1..c6f34143 100755 --- a/wqflask/base/data_set.py +++ b/wqflask/base/data_set.py @@ -44,12 +44,15 @@ from dbFunction import webqtlDatabaseFunction from utility import webqtlUtil from utility.benchmark import Bench from utility import chunks +from utility.tools import flat_files from maintenance import get_group_samplelists from MySQLdb import escape_string as escape from pprint import pformat as pf +MAPPING_PATH = flat_files("mapping") + # Used by create_database to instantiate objects # Each subclass will add to this DS_NAME_MAP = {} @@ -404,15 +407,11 @@ class DatasetGroup(object): else: #print("Cache not hit") - from utility.tools import plink_command - PLINK_RUN = plink_command() - geno_file_path = webqtlConfig.GENODIR+self.name+".geno" - plink_file_path = PLINK_PATH+"/"+self.name+".fam" - # @FIXME PJOTR/ZACH: .fam files should go into FLATFILES - if os.path.isfile(plink_file_path): - self.samplelist = get_group_samplelists.get_samplelist("plink", plink_file_path) + mapping_file_path = MAPPING_PATH+"/"+self.name+".fam" + if os.path.isfile(mapping_file_path): + self.samplelist = get_group_samplelists.get_samplelist("plink", mapping_file_path) elif os.path.isfile(geno_file_path): self.samplelist = get_group_samplelists.get_samplelist("geno", geno_file_path) else: @@ -441,18 +440,10 @@ class DatasetGroup(object): # reaper barfs on unicode filenames, so here we ensure it's a string full_filename = str(os.path.join(webqtlConfig.GENODIR, self.name + '.geno')) - if os.path.isfile(full_filename): - #print("Reading file: ", full_filename) - genotype_1.read(full_filename) - #print("File read") - else: - try: - full_filename = str(os.path.join(webqtlConfig.TMPDIR, self.name + '.geno')) - #print("Reading file") - genotype_1.read(full_filename) - #print("File read") - except IOError: - print("File doesn't exist!") + if not os.path.isfile(full_filename): + raise SystemError("File "+full_filename+" does not exist") + print("Reading file: ", full_filename) + genotype_1.read(full_filename) if genotype_1.type == "group" and self.parlist: genotype_2 = genotype_1.add(Mat=self.parlist[0], Pat=self.parlist[1]) #, F1=_f1) diff --git a/wqflask/utility/tools.py b/wqflask/utility/tools.py index c3c9b292..44bbb1b0 100644 --- a/wqflask/utility/tools.py +++ b/wqflask/utility/tools.py @@ -52,17 +52,27 @@ def get_setting(command_id,guess=None): raise Exception(command_id+' path unknown or faulty (update settings.py?). '+command_id+' should point to the path') return command +def valid_bin(bin): + if os.path.islink(bin) or os.path.isfile(bin): + return bin + return None + +def valid_path(dir): + if os.path.isdir(dir): + return dir + return None + def pylmm_command(guess=None): - return get_setting("PYLMM_RUN",guess) + return valid_bin(get_setting("PYLMM_RUN",guess)) def gemma_command(guess=None): - return get_setting("GEMMA_RUN",guess) + return valid_bin(get_setting("GEMMA_RUN",guess)) def plink_command(guess=None): - return get_setting("PLINK_RUN",guess) + return valid_bin(get_setting("PLINK_RUN",guess)) def flat_files(subdir=None): base = get_setting("GENENETWORK_FILES") if subdir: - return base+"/"+subdir - return base + return valid_path(base+"/"+subdir) + return valid_path(base) diff --git a/wqflask/wqflask/show_trait/show_trait.py b/wqflask/wqflask/show_trait/show_trait.py index 458e48da..35f7fe5f 100755 --- a/wqflask/wqflask/show_trait/show_trait.py +++ b/wqflask/wqflask/show_trait/show_trait.py @@ -16,8 +16,6 @@ from base import webqtlConfig from base import webqtlCaseData from wqflask.show_trait.SampleList import SampleList from utility import webqtlUtil, Plot, Bunch, helper_functions -# from utility.tools import plink_command -from utility.tools import flat_files from base.trait import GeneralTrait from base import data_set from dbFunction import webqtlDatabaseFunction @@ -25,7 +23,8 @@ from basicStatistics import BasicStatisticsFunctions from pprint import pformat as pf -MAPPING_FILES = flat_files("mapping") +from utility.tools import flat_files +MAPPING_PATH = flat_files("mapping") ############################################### # @@ -34,8 +33,6 @@ MAPPING_FILES = flat_files("mapping") # ############################################## - - class ShowTrait(object): def __init__(self, kw): @@ -162,8 +159,8 @@ class ShowTrait(object): def get_mapping_methods(self): '''Only display mapping methods when the dataset group's genotype file exists''' def check_plink_gemma(): - if (os.path.isfile(MAPPYING_FILES+"/"+self.dataset.group.name+".bed") and - os.path.isfile(MAPPING_FILES+"/"+self.dataset.group.name+".map")): + if (os.path.isfile(MAPPYING_PATH+"/"+self.dataset.group.name+".bed") and + os.path.isfile(MAPPING_PATH+"/"+self.dataset.group.name+".map")): return True else: return False -- cgit v1.2.3 From a5ff6520ad29266e1647ce54ad6b2c0f200dfe9a Mon Sep 17 00:00:00 2001 From: Pjotr Prins Date: Wed, 20 Apr 2016 08:55:56 +0000 Subject: [PATCH 032/100] file locating: error checking is built-in --- wqflask/base/data_set.py | 16 +++++----------- 1 file changed, 5 insertions(+), 11 deletions(-) (limited to 'wqflask/base/data_set.py') diff --git a/wqflask/base/data_set.py b/wqflask/base/data_set.py index c6f34143..9ffc09ac 100755 --- a/wqflask/base/data_set.py +++ b/wqflask/base/data_set.py @@ -44,15 +44,13 @@ from dbFunction import webqtlDatabaseFunction from utility import webqtlUtil from utility.benchmark import Bench from utility import chunks -from utility.tools import flat_files +from utility.tools import locate from maintenance import get_group_samplelists from MySQLdb import escape_string as escape from pprint import pformat as pf -MAPPING_PATH = flat_files("mapping") - # Used by create_database to instantiate objects # Each subclass will add to this DS_NAME_MAP = {} @@ -405,11 +403,10 @@ class DatasetGroup(object): #print(" type: ", type(self.samplelist)) #print(" self.samplelist: ", self.samplelist) else: - #print("Cache not hit") - - geno_file_path = webqtlConfig.GENODIR+self.name+".geno" + print("Cache not hit") - mapping_file_path = MAPPING_PATH+"/"+self.name+".fam" + geno_file_path = locate(self.name+".geno",'genotype') + mapping_file_path = locate(self.name+".fam",'mapping') if os.path.isfile(mapping_file_path): self.samplelist = get_group_samplelists.get_samplelist("plink", mapping_file_path) elif os.path.isfile(geno_file_path): @@ -439,10 +436,7 @@ class DatasetGroup(object): genotype_1 = reaper.Dataset() # reaper barfs on unicode filenames, so here we ensure it's a string - full_filename = str(os.path.join(webqtlConfig.GENODIR, self.name + '.geno')) - if not os.path.isfile(full_filename): - raise SystemError("File "+full_filename+" does not exist") - print("Reading file: ", full_filename) + full_filename = str(locate(self.name+'.geno','genotype')) genotype_1.read(full_filename) if genotype_1.type == "group" and self.parlist: -- cgit v1.2.3 From 218fd0c7666583748098f0b7b4286b6d1cbf6838 Mon Sep 17 00:00:00 2001 From: Pjotr Prins Date: Tue, 23 Feb 2016 11:16:33 +0000 Subject: [PATCH 033/100] Refactored file searching --- wqflask/base/data_set.py | 16 ++++++++-------- wqflask/utility/tools.py | 4 +++- 2 files changed, 11 insertions(+), 9 deletions(-) (limited to 'wqflask/base/data_set.py') diff --git a/wqflask/base/data_set.py b/wqflask/base/data_set.py index 9ffc09ac..ce13dd77 100755 --- a/wqflask/base/data_set.py +++ b/wqflask/base/data_set.py @@ -44,7 +44,7 @@ from dbFunction import webqtlDatabaseFunction from utility import webqtlUtil from utility.benchmark import Bench from utility import chunks -from utility.tools import locate +from utility.tools import locate, locate_without_error from maintenance import get_group_samplelists @@ -405,15 +405,15 @@ class DatasetGroup(object): else: print("Cache not hit") - geno_file_path = locate(self.name+".geno",'genotype') - mapping_file_path = locate(self.name+".fam",'mapping') - if os.path.isfile(mapping_file_path): - self.samplelist = get_group_samplelists.get_samplelist("plink", mapping_file_path) - elif os.path.isfile(geno_file_path): - self.samplelist = get_group_samplelists.get_samplelist("geno", geno_file_path) + genotype_fn = locate_without_error(self.name+".geno",'genotype') + mapping_fn = locate_without_error(self.name+".fam",'mapping') + if mapping_fn: + self.samplelist = get_group_samplelists.get_samplelist("plink", mapping_fn) + elif genotype_fn: + self.samplelist = get_group_samplelists.get_samplelist("geno", genotype_fn) else: self.samplelist = None - #print("after get_samplelist") + print("Sample list: ",self.samplelist) Redis.set(key, json.dumps(self.samplelist)) Redis.expire(key, 60*5) diff --git a/wqflask/utility/tools.py b/wqflask/utility/tools.py index dd40be99..d4c10c68 100644 --- a/wqflask/utility/tools.py +++ b/wqflask/utility/tools.py @@ -36,7 +36,7 @@ def get_setting(command_id,guess=None): """ def value(command): if command: - sys.stderr.write("Found value "+command+"\n") + sys.stderr.write("Found path "+command+"\n") return command else: return None @@ -95,6 +95,7 @@ def locate(name, subdir=None): if valid_path(base): lookfor = base + "/" + name if valid_file(lookfor): + print("Found: file "+lookfor+"\n") return lookfor else: raise IOError("Can not locate "+lookfor) @@ -114,6 +115,7 @@ def locate_without_error(name, subdir=None): if valid_path(base): lookfor = base + "/" + name if valid_file(lookfor): + print("Found: file "+name+"\n") return lookfor sys.stderr.write("WARNING: file "+name+" not found\n") return None -- cgit v1.2.3 From 5fffa1aa4260af6663c1f9b4cf7494d3ebc6995d Mon Sep 17 00:00:00 2001 From: Pjotr Prins Date: Wed, 24 Feb 2016 11:01:29 +0000 Subject: [PATCH 037/100] WebQtlConfig: sanitizing naming and used vars --- bin/genenetwork2 | 2 +- wqflask/base/data_set.py | 194 ++++++++++----------- wqflask/base/webqtlFormData.py | 2 +- .../basicStatistics/BasicStatisticsFunctions.py | 6 +- wqflask/maintenance/get_group_samplelists.py | 3 +- wqflask/utility/tools.py | 11 +- wqflask/wqflask/correlation/show_corr_results.py | 2 +- .../wqflask/correlation_matrix/show_corr_matrix.py | 1 - wqflask/wqflask/heatmap/heatmap.py | 2 - .../interval_analyst/IntervalAnalystPage.py | 138 +++++++-------- .../marker_regression/MarkerRegressionPage.py | 6 +- .../wqflask/marker_regression/marker_regression.py | 2 +- .../marker_regression/marker_regression_gn1.py | 116 ++++++------ wqflask/wqflask/search_results.py | 1 - wqflask/wqflask/show_trait/show_trait.py | 2 +- 15 files changed, 246 insertions(+), 242 deletions(-) (limited to 'wqflask/base/data_set.py') diff --git a/bin/genenetwork2 b/bin/genenetwork2 index 54eee02e..00ee09bf 100755 --- a/bin/genenetwork2 +++ b/bin/genenetwork2 @@ -1,6 +1,6 @@ #! /bin/bash # -# This will run the server with default settings +# This will run the server with default settings. # Absolute path to this script, e.g. /home/user/bin/foo.sh SCRIPT=$(readlink -f "$0") diff --git a/wqflask/base/data_set.py b/wqflask/base/data_set.py index ce13dd77..6527657a 100755 --- a/wqflask/base/data_set.py +++ b/wqflask/base/data_set.py @@ -76,22 +76,22 @@ def create_dataset(dataset_name, dataset_type = None, get_samplelist = True): #def get_dataset_type_from_json(dataset_name): - + class Dataset_Types(object): - + def __init__(self): self.datasets = {} file_name = "wqflask/static/new/javascript/dataset_menu_structure.json" with open(file_name, 'r') as fh: data = json.load(fh) - + print("*" * 70) for species in data['datasets']: for group in data['datasets'][species]: for dataset_type in data['datasets'][species][group]: for dataset in data['datasets'][species][group][dataset_type]: #print("dataset is:", dataset) - + short_dataset_name = dataset[1] if dataset_type == "Phenotypes": new_type = "Publish" @@ -100,32 +100,32 @@ class Dataset_Types(object): else: new_type = "ProbeSet" self.datasets[short_dataset_name] = new_type - + def __call__(self, name): return self.datasets[name] - + # Do the intensive work at startup one time only Dataset_Getter = Dataset_Types() # #print("Running at startup:", get_dataset_type_from_json("HBTRC-MLPFC_0611")) - + def create_datasets_list(): key = "all_datasets" result = Redis.get(key) - + if result: print("Cache hit!!!") datasets = pickle.loads(result) - + else: datasets = list() with Bench("Creating DataSets object"): type_dict = {'Publish': 'PublishFreeze', 'ProbeSet': 'ProbeSetFreeze', 'Geno': 'GenoFreeze'} - + for dataset_type in type_dict: query = "SELECT Name FROM {}".format(type_dict[dataset_type]) for result in g.db.execute(query).fetchall(): @@ -134,10 +134,10 @@ def create_datasets_list(): #print("type: {}\tname: {}".format(dataset_type, result.Name)) dataset = create_dataset(result.Name, dataset_type) datasets.append(dataset) - + Redis.set(key, pickle.dumps(datasets, pickle.HIGHEST_PROTOCOL)) Redis.expire(key, 60*60) - + return datasets @@ -158,30 +158,30 @@ def mescape(*items): class Markers(object): """Todo: Build in cacheing so it saves us reading the same file more than once""" def __init__(self, name): - json_data_fh = open(os.path.join(webqtlConfig.NEWGENODIR + name + '.json')) + json_data_fh = open(locate(name + '.json','genotype/json')) try: markers = json.load(json_data_fh) except: markers = [] - + for marker in markers: if (marker['chr'] != "X") and (marker['chr'] != "Y"): marker['chr'] = int(marker['chr']) marker['Mb'] = float(marker['Mb']) - + self.markers = markers #print("self.markers:", self.markers) - - + + def add_pvalues(self, p_values): print("length of self.markers:", len(self.markers)) print("length of p_values:", len(p_values)) - + if type(p_values) is list: # THIS IS only needed for the case when we are limiting the number of p-values calculated #if len(self.markers) > len(p_values): # self.markers = self.markers[:len(p_values)] - + for marker, p_value in itertools.izip(self.markers, p_values): if not p_value: continue @@ -214,7 +214,7 @@ class Markers(object): #self.markers.remove(marker) #del self.markers[i] self.markers = filtered_markers - + #for i, marker in enumerate(self.markers): # if not 'p_value' in marker: @@ -223,9 +223,9 @@ class Markers(object): # #self.markers.remove(self.markers[i]) class HumanMarkers(Markers): - + def __init__(self, name, specified_markers = []): - marker_data_fh = open(os.path.join(webqtlConfig.PYLMM_PATH + name + '.bim')) + marker_data_fh = open(locate('genotype') + '/' + name + '.bim') self.markers = [] for line in marker_data_fh: splat = line.strip().split() @@ -244,7 +244,7 @@ class HumanMarkers(Markers): marker['name'] = splat[1] marker['Mb'] = float(splat[3]) / 1000000 self.markers.append(marker) - + #print("markers is: ", pf(self.markers)) @@ -257,26 +257,26 @@ class HumanMarkers(Markers): # marker['lod_score'] = -math.log10(marker['p_value']) # #Using -log(p) for the LRS; need to ask Rob how he wants to get LRS from p-values # marker['lrs_value'] = -math.log10(marker['p_value']) * 4.61 - + #print("p_values2:", pf(p_values)) super(HumanMarkers, self).add_pvalues(p_values) - + #with Bench("deleting markers"): # markers = [] # for marker in self.markers: # if not marker['Mb'] <= 0 and not marker['chr'] == 0: # markers.append(marker) # self.markers = markers - - + + class DatasetGroup(object): """ Each group has multiple datasets; each species has multiple groups. - + For example, Mouse has multiple groups (BXD, BXA, etc), and each group has multiple datasets associated with it. - + """ def __init__(self, dataset): """This sets self.group and self.group_id""" @@ -284,14 +284,14 @@ class DatasetGroup(object): self.name, self.id = g.db.execute(dataset.query_for_group).fetchone() if self.name == 'BXD300': self.name = "BXD" - + self.f1list = None self.parlist = None self.get_f1_parent_strains() #print("parents/f1s: {}:{}".format(self.parlist, self.f1list)) - + self.species = webqtlDatabaseFunction.retrieve_species(self.name) - + self.incparentsf1 = False self.allsamples = None self._datasets = None @@ -302,7 +302,7 @@ class DatasetGroup(object): def get_markers(self): #print("self.species is:", self.species) if self.species == "human": - marker_class = HumanMarkers + marker_class = HumanMarkers else: marker_class = Markers @@ -356,7 +356,7 @@ class DatasetGroup(object): 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): @@ -384,7 +384,7 @@ class DatasetGroup(object): f1, f12, maternal, paternal = webqtlUtil.ParInfo[self.name] except KeyError: f1 = f12 = maternal = paternal = None - + if f1 and f12: self.f1list = [f1, f12] if maternal and paternal: @@ -455,18 +455,18 @@ class DatasetGroup(object): #self.samplelist = list(self.genotype.prgy) self.samplelist = list(genotype.prgy) - + return genotype #class DataSets(object): # """Builds a list of DataSets""" -# +# # def __init__(self): # self.datasets = list() -# +# + - #query = """SELECT Name FROM ProbeSetFreeze # UNION # SELECT Name From PublishFreeze @@ -501,7 +501,7 @@ class DataSet(object): self.check_confidentiality() self.retrieve_other_names() - + self.group = DatasetGroup(self) # sets self.group and self.group_id and gets genotype if get_samplelist == True: self.group.get_samplelist() @@ -511,30 +511,30 @@ class DataSet(object): def get_desc(self): """Gets overridden later, at least for Temp...used by trait's get_given_name""" return None - + #@staticmethod #def get_by_trait_id(trait_id): # """Gets the dataset object given the trait id""" - # - # # - # name = g.db.execute(""" SELECT - # + # + # + # name = g.db.execute(""" SELECT + # # """) - # + # # return DataSet(name) # Delete this eventually @property def riset(): Weve_Renamed_This_As_Group - - + + #@property #def group(self): # if not self._group: # self.get_group() - # + # # return self._group @@ -546,7 +546,7 @@ class DataSet(object): This is not meant to retrieve the data set info if no name at all is passed. """ - + try: if self.type == "ProbeSet": query_args = tuple(escape(x) for x in ( @@ -582,17 +582,17 @@ class DataSet(object): except TypeError: print("Dataset {} is not yet available in GeneNetwork.".format(self.name)) pass - + def get_trait_data(self, sample_list=None): if sample_list: self.samplelist = sample_list else: self.samplelist = self.group.samplelist - + if self.group.parlist != None and self.group.f1list != None: if (self.group.parlist + self.group.f1list) in self.samplelist: self.samplelist += self.group.parlist + self.group.f1list - + query = """ SELECT Strain.Name, Strain.Id FROM Strain, Species WHERE Strain.Name IN {} @@ -610,9 +610,9 @@ class DataSet(object): trait_sample_data = [] for sample_ids_step in chunks.divide_into_chunks(sample_ids, number_chunks): - #XZ, 09/24/2008: build one temporary table that only contains the records associated with the input GeneId + #XZ, 09/24/2008: build one temporary table that only contains the records associated with the input GeneId #tempTable = None - #if GeneId and db.type == "ProbeSet": + #if GeneId and db.type == "ProbeSet": # if method == "3": # tempTable = self.getTempLiteratureTable(species=species, # input_species_geneid=GeneId, @@ -623,7 +623,7 @@ class DataSet(object): # TissueProbeSetFreezeId=tissueProbeSetFreezeId, # method=method, # returnNumber=returnNumber) - + if self.type == "Publish": dataset_type = "Phenotype" else: @@ -644,7 +644,7 @@ class DataSet(object): left join {}Data as T{} on T{}.Id = {}XRef.DataId and T{}.StrainId={}\n """.format(*mescape(self.type, item, item, self.type, item, item)) - + if self.type == "Publish": query += """ WHERE {}XRef.InbredSetId = {}Freeze.InbredSetId @@ -661,16 +661,16 @@ class DataSet(object): order by {}.Id """.format(*mescape(self.type, self.type, self.type, self.type, self.name, dataset_type, self.type, self.type, dataset_type)) - + #print("trait data query: ", query) - + results = g.db.execute(query).fetchall() #print("query results:", results) trait_sample_data.append(results) trait_count = len(trait_sample_data[0]) self.trait_data = collections.defaultdict(list) - + # put all of the separate data together into a dictionary where the keys are # trait names and values are lists of sample values for trait_counter in range(trait_count): @@ -683,9 +683,9 @@ class PhenotypeDataSet(DataSet): DS_NAME_MAP['Publish'] = 'PhenotypeDataSet' def setup(self): - + #print("IS A PHENOTYPEDATASET") - + # Fields in the database table self.search_fields = ['Phenotype.Post_publication_description', 'Phenotype.Pre_publication_description', @@ -756,26 +756,26 @@ class PhenotypeDataSet(DataSet): def get_trait_info(self, trait_list, species = ''): for this_trait in trait_list: - + if not this_trait.haveinfo: this_trait.retrieve_info(get_qtl_info=True) description = this_trait.post_publication_description - + #If the dataset is confidential and the user has access to confidential #phenotype traits, then display the pre-publication description instead #of the post-publication description if this_trait.confidential: this_trait.description_display = "" continue # for now - + if not webqtlUtil.hasAccessToConfidentialPhenotypeTrait( privilege=self.privilege, userName=self.userName, authorized_users=this_trait.authorized_users): - + description = this_trait.pre_publication_description - + if len(description) > 0: this_trait.description_display = description.strip() else: @@ -820,7 +820,7 @@ class PhenotypeDataSet(DataSet): 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): query = """ SELECT @@ -878,7 +878,7 @@ class GenotypeDataSet(DataSet): def check_confidentiality(self): return geno_mrna_confidentiality(self) - + def get_trait_list(self): query = """ select Geno.Name @@ -912,7 +912,7 @@ class GenotypeDataSet(DataSet): 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 = """ SELECT @@ -1004,7 +1004,7 @@ class MrnaAssayDataSet(DataSet): def check_confidentiality(self): return geno_mrna_confidentiality(self) - + def get_trait_list_1(self): query = """ select ProbeSet.Name @@ -1020,7 +1020,7 @@ class MrnaAssayDataSet(DataSet): trait_data[trait[0]] = self.retrieve_sample_data(trait[0]) #print("After retrieve_sample_data") return trait_data - + #def get_trait_data(self): # self.samplelist = self.group.samplelist + self.group.parlist + self.group.f1list # query = """ @@ -1040,9 +1040,9 @@ class MrnaAssayDataSet(DataSet): # trait_sample_data = [] # for sample_ids_step in chunks.divide_into_chunks(sample_ids, number_chunks): # - # #XZ, 09/24/2008: build one temporary table that only contains the records associated with the input GeneId + # #XZ, 09/24/2008: build one temporary table that only contains the records associated with the input GeneId # #tempTable = None - # #if GeneId and db.type == "ProbeSet": + # #if GeneId and db.type == "ProbeSet": # # if method == "3": # # tempTable = self.getTempLiteratureTable(species=species, # # input_species_geneid=GeneId, @@ -1053,7 +1053,7 @@ class MrnaAssayDataSet(DataSet): # # TissueProbeSetFreezeId=tissueProbeSetFreezeId, # # method=method, # # returnNumber=returnNumber) - # + # # temp = ['T%s.value' % item for item in sample_ids_step] # query = "SELECT {}.Name,".format(escape(self.type)) # data_start_pos = 1 @@ -1067,7 +1067,7 @@ class MrnaAssayDataSet(DataSet): # left join {}Data as T{} on T{}.Id = {}XRef.DataId # and T{}.StrainId={}\n # """.format(*mescape(self.type, item, item, self.type, item, item)) - # + # # query += """ # WHERE {}XRef.{}FreezeId = {}Freeze.Id # and {}Freeze.Name = '{}' @@ -1080,7 +1080,7 @@ class MrnaAssayDataSet(DataSet): # # trait_count = len(trait_sample_data[0]) # self.trait_data = collections.defaultdict(list) - # + # # # put all of the separate data together into a dictionary where the keys are # # trait names and values are lists of sample values # for trait_counter in range(trait_count): @@ -1088,11 +1088,11 @@ class MrnaAssayDataSet(DataSet): # for chunk_counter in range(int(number_chunks)): # self.trait_data[trait_name] += ( # trait_sample_data[chunk_counter][trait_counter][data_start_pos:]) - + def get_trait_info(self, trait_list=None, species=''): - # Note: setting trait_list to [] is probably not a great idea. + # Note: setting trait_list to [] is probably not a great idea. if not trait_list: trait_list = [] @@ -1155,7 +1155,7 @@ class MrnaAssayDataSet(DataSet): #print("query is:", pf(query)) result = g.db.execute(query).fetchone() - + mean = result[0] if result else 0 if mean: @@ -1176,7 +1176,7 @@ class MrnaAssayDataSet(DataSet): Geno.SpeciesId = Species.Id """.format(species, this_trait.locus) result = g.db.execute(query).fetchone() - + if result: #if result[0] and result[1]: # lrs_chr = result[0] @@ -1184,7 +1184,7 @@ class MrnaAssayDataSet(DataSet): 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) - + #try: # lrs_location_value = int(lrs_chr)*1000 + float(lrs_mb) #except: @@ -1197,7 +1197,7 @@ class MrnaAssayDataSet(DataSet): 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: @@ -1208,7 +1208,7 @@ class MrnaAssayDataSet(DataSet): else: location_value = (ord(str(chromosome).upper()[0])*1000 + float(mb)) - + return location_value def get_sequence(self): @@ -1225,7 +1225,7 @@ class MrnaAssayDataSet(DataSet): """ % (escape(self.name), escape(self.dataset.name)) results = g.db.execute(query).fetchone() return results[0] - + def retrieve_sample_data(self, trait): query = """ SELECT @@ -1246,8 +1246,8 @@ class MrnaAssayDataSet(DataSet): results = g.db.execute(query).fetchall() #print("RETRIEVED RESULTS HERE:", results) return results - - + + def retrieve_genes(self, column_name): query = """ select ProbeSet.Name, ProbeSet.%s @@ -1256,7 +1256,7 @@ class MrnaAssayDataSet(DataSet): ProbeSetXRef.ProbeSetId=ProbeSet.Id; """ % (column_name, escape(str(self.id))) results = g.db.execute(query).fetchall() - + return dict(results) #def retrieve_gene_symbols(self): @@ -1285,8 +1285,8 @@ class MrnaAssayDataSet(DataSet): # for item in results: # symbol_dict[item[0]] = item[1] # return symbol_dict - - + + class TempDataSet(DataSet): @@ -1308,8 +1308,8 @@ class TempDataSet(DataSet): self.id = 1 self.fullname = 'Temporary Storage' self.shortname = 'Temp' - - + + @staticmethod def handle_pca(desc): if 'PCA' in desc: @@ -1318,13 +1318,13 @@ class TempDataSet(DataSet): else: desc = desc[:desc.index('entered')].strip() return desc - + def get_desc(self): g.db.execute('SELECT description FROM Temp WHERE Name=%s', self.name) desc = g.db.fetchone()[0] desc = self.handle_pca(desc) - return desc - + return desc + def get_group(self): self.cursor.execute(""" SELECT @@ -1337,7 +1337,7 @@ class TempDataSet(DataSet): """, self.name) self.group, self.group_id = self.cursor.fetchone() #return self.group - + def retrieve_sample_data(self, trait): query = """ SELECT @@ -1351,7 +1351,7 @@ class TempDataSet(DataSet): Order BY Strain.Name """ % escape(trait.name) - + results = g.db.execute(query).fetchall() diff --git a/wqflask/base/webqtlFormData.py b/wqflask/base/webqtlFormData.py index 44fdcc3f..10251756 100755 --- a/wqflask/base/webqtlFormData.py +++ b/wqflask/base/webqtlFormData.py @@ -157,7 +157,7 @@ class webqtlFormData(object): self.genotype_1 = reaper.Dataset() - full_filename = os.path.join(webqtlConfig.GENODIR, self.group + '.geno') + full_filename = locate(self.group + '.geno','genotype') # reaper barfs on unicode filenames, so here we ensure it's a string full_filename = str(full_filename) diff --git a/wqflask/basicStatistics/BasicStatisticsFunctions.py b/wqflask/basicStatistics/BasicStatisticsFunctions.py index 74784853..e748a822 100755 --- a/wqflask/basicStatistics/BasicStatisticsFunctions.py +++ b/wqflask/basicStatistics/BasicStatisticsFunctions.py @@ -118,7 +118,7 @@ def plotNormalProbability(vals=None, RISet='', title=None, showstrains=0, specia Plot.plotXY(c, dataZ, dataX, dataLabel = dataLabel, XLabel='Expected Z score', connectdot=0, YLabel='Trait value', title=title, specialCases=specialStrains, showLabel = showLabel) filename= webqtlUtil.genRandStr("nP_") - c.save(webqtlConfig.IMGDIR+filename, format='gif') + c.save(webqtlConfig.GENERATED_IMAGE_DIR+filename, format='gif') img=HT.Image('/image/'+filename+'.gif',border=0) @@ -145,7 +145,7 @@ def plotBoxPlot(vals): Plot.plotBoxPlot(canvas, XXX, offset=(xLeftOffset, xRightOffset, yTopOffset, yBottomOffset), XLabel= "Trait") filename= webqtlUtil.genRandStr("Box_") - canvas.save(webqtlConfig.IMGDIR+filename, format='gif') + canvas.save(webqtlConfig.GENERATED_IMAGE_DIR+filename, format='gif') img=HT.Image('/image/'+filename+'.gif',border=0) plotLink = HT.Span("More about ", HT.Href(text="Box Plots", url="http://davidmlane.com/hyperstat/A37797.html", target="_blank", Class="fs13")) @@ -201,7 +201,7 @@ def plotBarGraph(identification='', RISet='', vals=None, type="name"): Plot.plotBarText(c, tvals, tnames, variance=tvars, YLabel='Value', title=title, sLabel = sLabel, barSpace = sw) filename= webqtlUtil.genRandStr("Bar_") - c.save(webqtlConfig.IMGDIR+filename, format='gif') + c.save(webqtlConfig.GENERATED_IMAGE_DIR+filename, format='gif') img=HT.Image('/image/'+filename+'.gif',border=0) return img diff --git a/wqflask/maintenance/get_group_samplelists.py b/wqflask/maintenance/get_group_samplelists.py index b8397b47..a9059fad 100755 --- a/wqflask/maintenance/get_group_samplelists.py +++ b/wqflask/maintenance/get_group_samplelists.py @@ -6,7 +6,6 @@ import gzip from base import webqtlConfig - def process_genofiles(geno_dir=webqtlConfig.GENODIR): print("Yabba") #sys.exit("Dabba") @@ -54,4 +53,4 @@ def get_samplelist_from_plink(genofilename): line = line.split(" ") samplelist.append(line[0]) - return samplelist \ No newline at end of file + return samplelist diff --git a/wqflask/utility/tools.py b/wqflask/utility/tools.py index 0f2e4d88..c0f6a49a 100644 --- a/wqflask/utility/tools.py +++ b/wqflask/utility/tools.py @@ -79,6 +79,15 @@ def flat_files(subdir=None): return valid_path(base+"/"+subdir) return valid_path(base) +def assert_dir(dir): + if not valid_path(dir): + raise Exception("ERROR: can not find directory "+dir) + return dir + +def mk_dir(dir): + os.makedirs(dir) + return assert_dir(dir) + def locate(name, subdir=None): """ Locate a static flat file in the GENENETWORK_FILES environment. @@ -98,7 +107,7 @@ def locate(name, subdir=None): if subdir: sys.stderr.write(subdir) raise IOError("Can not locate "+name+" in "+base) -def locate_without_error(name, subdir=None): +def locate_ignore_error(name, subdir=None): """ Locate a static flat file in the GENENETWORK_FILES environment. diff --git a/wqflask/wqflask/correlation/show_corr_results.py b/wqflask/wqflask/correlation/show_corr_results.py index 21a2c26c..06b4860e 100755 --- a/wqflask/wqflask/correlation/show_corr_results.py +++ b/wqflask/wqflask/correlation/show_corr_results.py @@ -943,7 +943,7 @@ class CorrelationResults(object): use_tissue_corr = True DatabaseFileName = self.getFileName( target_db_name=self.target_db_name ) - datasetFile = open(webqtlConfig.TEXTDIR+DatabaseFileName,'r') + datasetFile = open(webqtlConfig.CACHEDIR+DatabaseFileName,'r') #XZ, 01/08/2009: read the first line line = datasetFile.readline() diff --git a/wqflask/wqflask/correlation_matrix/show_corr_matrix.py b/wqflask/wqflask/correlation_matrix/show_corr_matrix.py index 6bc0ef77..f74e655d 100755 --- a/wqflask/wqflask/correlation_matrix/show_corr_matrix.py +++ b/wqflask/wqflask/correlation_matrix/show_corr_matrix.py @@ -43,7 +43,6 @@ from pprint import pformat as pf from htmlgen import HTMLgen2 as HT import reaper -from base import webqtlConfig from utility.THCell import THCell from utility.TDCell import TDCell from base.trait import GeneralTrait diff --git a/wqflask/wqflask/heatmap/heatmap.py b/wqflask/wqflask/heatmap/heatmap.py index 40f518f0..61847bc3 100644 --- a/wqflask/wqflask/heatmap/heatmap.py +++ b/wqflask/wqflask/heatmap/heatmap.py @@ -26,8 +26,6 @@ import reaper from base.trait import GeneralTrait from base import data_set from base import species -from base import webqtlConfig -from utility import webqtlUtil # from wqflask.my_pylmm.pyLMM import lmm # from wqflask.my_pylmm.pyLMM import input from utility import helper_functions diff --git a/wqflask/wqflask/interval_analyst/IntervalAnalystPage.py b/wqflask/wqflask/interval_analyst/IntervalAnalystPage.py index ec9aa29c..f45ec0c4 100755 --- a/wqflask/wqflask/interval_analyst/IntervalAnalystPage.py +++ b/wqflask/wqflask/interval_analyst/IntervalAnalystPage.py @@ -45,40 +45,40 @@ class IntervalAnalystPage(templatePage): #A dictionary that lets us map the html form names "txStart_mm6" -> "Mb Start (mm8)" #the first item is the short name (column headers) and the second item is the long name (dropdown list) # [short name, long name, category] - columnNames = {"GeneSymbol" : ["Gene", "Gene Name", 'gene'], + columnNames = {"GeneSymbol" : ["Gene", "Gene Name", 'gene'], "GeneDescription" : ["Description", "Gene Description", 'species'], - 'GeneNeighborsCount' : ["Neighbors", "Gene Neighbors", 'gene'], - 'GeneNeighborsRange' : ["Neighborhood", "Gene Neighborhood (Mb)", 'gene'], - 'GeneNeighborsDensity' : ["Gene Density", "Gene Density (Neighbors/Mb)", 'gene'], + 'GeneNeighborsCount' : ["Neighbors", "Gene Neighbors", 'gene'], + 'GeneNeighborsRange' : ["Neighborhood", "Gene Neighborhood (Mb)", 'gene'], + 'GeneNeighborsDensity' : ["Gene Density", "Gene Density (Neighbors/Mb)", 'gene'], "ProteinID" : ["Prot ID", "Protein ID", 'protein'], - "Chromosome" : ["Chr", "Chromosome", 'species'], - "TxStart" : ["Start", "Mb Start", 'species'], - "TxEnd" : ["End", "Mb End", 'species'], - "GeneLength" : ["Length", "Kb Length", 'species'], - "cdsStart" : ["CDS Start", "Mb CDS Start", 'species'], + "Chromosome" : ["Chr", "Chromosome", 'species'], + "TxStart" : ["Start", "Mb Start", 'species'], + "TxEnd" : ["End", "Mb End", 'species'], + "GeneLength" : ["Length", "Kb Length", 'species'], + "cdsStart" : ["CDS Start", "Mb CDS Start", 'species'], "cdsEnd" : ["CDS End", "Mb CDS End", 'species'], - "exonCount" : ["Num Exons", "Exon Count", 'species'], - "exonStarts" : ["Exon Starts", "Exon Starts", 'species'], - "exonEnds" : ["Exon Ends", "Exon Ends", 'species'], - "Strand" : ["Strand", "Strand", 'species'], + "exonCount" : ["Num Exons", "Exon Count", 'species'], + "exonStarts" : ["Exon Starts", "Exon Starts", 'species'], + "exonEnds" : ["Exon Ends", "Exon Ends", 'species'], + "Strand" : ["Strand", "Strand", 'species'], "GeneID" : ["Gene ID", "Gene ID", 'species'], - "GenBankID" : ["GenBank", "GenBank ID", 'species'], + "GenBankID" : ["GenBank", "GenBank ID", 'species'], "UnigenID" : ["Unigen", "Unigen ID", 'species'], - "NM_ID" : ["NM ID", "NM ID", 'species'], + "NM_ID" : ["NM ID", "NM ID", 'species'], "kgID" : ["kg ID", "kg ID", 'species'], - "snpCount" : ["SNPs", "SNP Count", 'species'], - "snpDensity" : ["SNP Density", "SNP Density", 'species'], - "lrs" : ["LRS", "Likelihood Ratio Statistic", 'misc'], - "lod" : ["LOD", "Likelihood Odds Ratio", 'misc'], - "pearson" : ["Pearson", "Pearson Product Moment", 'misc'], - "literature" : ["Lit Corr", "Literature Correlation", 'misc'], + "snpCount" : ["SNPs", "SNP Count", 'species'], + "snpDensity" : ["SNP Density", "SNP Density", 'species'], + "lrs" : ["LRS", "Likelihood Ratio Statistic", 'misc'], + "lod" : ["LOD", "Likelihood Odds Ratio", 'misc'], + "pearson" : ["Pearson", "Pearson Product Moment", 'misc'], + "literature" : ["Lit Corr", "Literature Correlation", 'misc'], } ###Species Freeze speciesFreeze = {'mouse':'mm9', 'rat':'rn3', 'human':'hg19'} for key in speciesFreeze.keys(): speciesFreeze[speciesFreeze[key]] = key - + def __init__(self, fd): templatePage.__init__(self, fd) @@ -86,7 +86,7 @@ class IntervalAnalystPage(templatePage): fd.formdata['remote_ip'] = fd.remote_ip if not self.openMysql(): return - + self.species = fd.formdata.getvalue("species", "mouse") try: self.startMb = float(fd.formdata.getvalue("startMb")) @@ -96,7 +96,7 @@ class IntervalAnalystPage(templatePage): self.endMb = float(fd.formdata.getvalue("endMb")) except: self.endMb = self.startMb + 10 - + self.Chr = fd.formdata.getvalue("chromosome", "1") self.xls = fd.formdata.getvalue("xls", "1") try: @@ -107,38 +107,38 @@ class IntervalAnalystPage(templatePage): self.diffColDefault = self.diffCol = [] if self.species != 'mouse': self.diffColDefault = [2, 3]#default is B6 and D2 for other species - + controlFrm, dispFields = self.genControlForm(fd) geneTable, filename = self.genGeneTable(fd, dispFields) - + infoTD = HT.TD(width=400, valign= "top") - infoTD.append(HT.Paragraph("Interval Analyst : Chr %s" % self.Chr, Class="title"), - HT.Strong("Species : "), self.species.title(), HT.BR(), - HT.Strong("Database : "), "UCSC %s" % self.speciesFreeze[self.species], HT.BR(), - HT.Strong("Range : "), "%2.6f Mb - %2.6f Mb" % (self.startMb, self.endMb), HT.BR(), + infoTD.append(HT.Paragraph("Interval Analyst : Chr %s" % self.Chr, Class="title"), + HT.Strong("Species : "), self.species.title(), HT.BR(), + HT.Strong("Database : "), "UCSC %s" % self.speciesFreeze[self.species], HT.BR(), + HT.Strong("Range : "), "%2.6f Mb - %2.6f Mb" % (self.startMb, self.endMb), HT.BR(), ) if filename: infoTD.append(HT.BR(), HT.BR(), HT.Href(text="Download", url = "/tmp/" + filename, Class="normalsize") , " output in MS excel format.") - + mainTable = HT.TableLite(HT.TR(infoTD, HT.TD(controlFrm, Class="doubleBorder", width=400), HT.TD(" ", width="")), cellpadding=10) mainTable.append(HT.TR(HT.TD(geneTable, colspan=3))) self.dict['body'] = HT.TD(mainTable) self.dict['title'] = "Interval Analyst" - + def genGeneTable(self, fd, dispFields): filename = "" if self.xls: #import pyXLWriter as xl filename = "IntAn_Chr%s_%2.6f-%2.6f" % (self.Chr, self.startMb, self.endMb) filename += ".xls" - + # Create a new Excel workbook workbook = xl.Writer(os.path.join(webqtlConfig.TMPDIR, filename)) worksheet = workbook.add_worksheet() titleStyle = workbook.add_format(align = 'left', bold = 0, size=18, border = 1, border_color="gray") headingStyle = workbook.add_format(align = 'center', bold = 1, size=13, fg_color = 0x1E, color="white", border = 1, border_color="gray") - + ##Write title Info worksheet.write([0, 0], "GeneNetwork Interval Analyst Table", titleStyle) worksheet.write([1, 0], "%s%s" % (webqtlConfig.PORTADDR, os.path.join(webqtlConfig.CGIDIR, self._scriptfile))) @@ -148,12 +148,12 @@ class IntervalAnalystPage(templatePage): worksheet.write([4, 0], "Search by : %s" % fd.formdata['remote_ip']) worksheet.write([5, 0], "view region : Chr %s %2.6f - %2.6f Mb" % (self.Chr, self.startMb, self.endMb)) nTitleRow = 7 - + geneTable = HT.TableLite(Class="collap", cellpadding=5) headerRow = HT.TR(HT.TD(" ", Class="fs13 fwb ffl b1 cw cbrb", width="1")) if self.xls: worksheet.write([nTitleRow, 0], "Index", headingStyle) - + for ncol, column in enumerate(dispFields): if len(column) == 1: headerRow.append(HT.TD(self.columnNames[column[0]][0], Class="fs13 fwb ffl b1 cw cbrb", NOWRAP=1,align="Center")) @@ -162,24 +162,24 @@ class IntervalAnalystPage(templatePage): worksheet.write([nTitleRow, ncol+1], colTitle, headingStyle) worksheet.set_column([ncol+1, ncol+1], 2*len(colTitle)) else: - headerRow.append(HT.TD(self.columnNames[column[0]][0], HT.BR(), " (%s)" % self.speciesFreeze[column[1]], + headerRow.append(HT.TD(self.columnNames[column[0]][0], HT.BR(), " (%s)" % self.speciesFreeze[column[1]], Class="fs13 fwb ffl b1 cw cbrb", NOWRAP=1, align="Center")) if self.xls: colTitle = self.columnNames[column[0]][0] + " (%s)" % self.speciesFreeze[column[1]] worksheet.write([nTitleRow, ncol+1], colTitle, headingStyle) worksheet.set_column([ncol+1, ncol+1], 2*len(colTitle)) - #headerRow.append(HT.TD(self.columnNames[column[0]][0], HT.BR(), - # "(%s %s)" % (column[1].title(), self.speciesFreeze[column[1]]), + #headerRow.append(HT.TD(self.columnNames[column[0]][0], HT.BR(), + # "(%s %s)" % (column[1].title(), self.speciesFreeze[column[1]]), # Class="colorBlue", NOWRAP=1, align="Center")) geneTable.append(headerRow) - + geneCol = GeneUtil.loadGenes(self.cursor, self.Chr, self.diffColDefault, self.startMb, self.endMb, species=self.species) for gIndex, theGO in enumerate(geneCol): geneRow = HT.TR(HT.TD(gIndex+1, Class="fs12 fwn b1", align="right")) if self.xls: nTitleRow += 1 worksheet.write([nTitleRow, 0], gIndex + 1) - + for ncol, column in enumerate(dispFields): if len(column) == 1 or column[1]== self.species: keyValue = "" @@ -196,17 +196,17 @@ class IntervalAnalystPage(templatePage): curGO = theGO[subGO] if theGO[subGO].has_key(fieldName): keyValue = theGO[subGO][fieldName] - + if self.xls: worksheet.write([nTitleRow, ncol+1], keyValue) geneRow.append(self.formatTD(keyValue, fieldName, curSpecies, curGO)) - + geneTable.append(geneRow) - + if self.xls: workbook.close() return geneTable, filename - + def formatTD(self, keyValue, fieldName, Species, theGO): if keyValue is None: keyValue = "" @@ -219,7 +219,7 @@ class IntervalAnalystPage(templatePage): keyValue = "" return HT.TD(keyValue, Class="fs12 fwn b1", width=300) elif fieldName in ("GeneSymbol"): - webqtlLink = HT.Href("./%s?cmd=sch&gene=%s&alias=1&species=%s" % (webqtlConfig.SCRIPTFILE, keyValue, Species), + webqtlLink = HT.Href("./%s?cmd=sch&gene=%s&alias=1&species=%s" % (webqtlConfig.SCRIPTFILE, keyValue, Species), HT.Image("/images/webqtl_search.gif", border=0, valign="top"), target="_blank") if theGO['GeneID']: geneSymbolLink = HT.Href(webqtlConfig.NCBI_LOCUSID % theGO['GeneID'], keyValue, Class="normalsize", target="_blank") @@ -236,8 +236,8 @@ class IntervalAnalystPage(templatePage): return HT.TD(keyValue, Class="fs12 fwn b1",align="right") elif fieldName in ("snpCount"): if keyValue: - snpString = HT.Href(url="%s&chr=%s&start=%s&end=%s&geneName=%s&s1=%d&s2=%d" % (os.path.join(webqtlConfig.CGIDIR, 'main.py?FormID=snpBrowser'), - theGO["Chromosome"], theGO["TxStart"], theGO["TxEnd"], theGO["GeneSymbol"], self.diffColDefault[0], self.diffColDefault[1]), + snpString = HT.Href(url="%s&chr=%s&start=%s&end=%s&geneName=%s&s1=%d&s2=%d" % (os.path.join(webqtlConfig.CGIDIR, 'main.py?FormID=snpBrowser'), + theGO["Chromosome"], theGO["TxStart"], theGO["TxEnd"], theGO["GeneSymbol"], self.diffColDefault[0], self.diffColDefault[1]), text=theGO["snpCount"], target="_blank", Class="normalsize") else: snpString = keyValue @@ -252,13 +252,13 @@ class IntervalAnalystPage(templatePage): return HT.TD(keyValue, Class="fs12 fwn b1",NOWRAP=1) else: return HT.TD(keyValue, Class="fs12 fwn b1",NOWRAP=1,align="right") - + def genControlForm(self, fd): ##desc GeneList self.cursor.execute("Desc GeneList") GeneListFields = self.cursor.fetchall() GeneListFields = map(lambda X: X[0], GeneListFields) - + #group columns by category--used for creating the dropdown list of possible columns categories = {} for item in self.columnNames.keys(): @@ -267,7 +267,7 @@ class IntervalAnalystPage(templatePage): categories[category[-1]] = [item ] else: categories[category[-1]] = categories[category[-1]]+[item] - + ##List All Species in the Gene Table speciesDict = {} self.cursor.execute("select Species.Name, GeneList.SpeciesId from Species, GeneList where \ @@ -292,34 +292,34 @@ class IntervalAnalystPage(templatePage): pass AppliedField.append(item2) categories[specName] = AppliedField - + categoriesOrder += ['misc'] - + ############################################################ ## Create the list of possible columns for the dropdown list ############################################################ allColumnsList = HT.Select(name="allColumns", Class="snpBrowserDropBox") - + for category in categoriesOrder: allFields = categories[category] if allFields: geneOpt = HT.Optgroup(label=category.title()) for item in allFields: if category in self.speciesFreeze.keys(): - geneOpt.append(("%s (%s %s)" % (self.columnNames[item][1], category.title(), self.speciesFreeze[category]), + geneOpt.append(("%s (%s %s)" % (self.columnNames[item][1], category.title(), self.speciesFreeze[category]), "%s__%s" % (item, self.speciesFreeze[category]))) else: geneOpt.append((self.columnNames[item][1], item)) geneOpt.sort() allColumnsList.append(geneOpt) - + ###################################### ## Create the list of selected columns ###################################### - + #cols contains the value of all the selected columns submitCols = cols = fd.formdata.getvalue("columns", "default") - + if cols == "default": if self.species=="mouse": #these are the same columns that are shown on intervalPage.py cols = ['GeneSymbol', 'GeneDescription', 'Chromosome', 'TxStart', 'Strand', 'GeneLength', 'GeneID', 'NM_ID', 'snpCount', 'snpDensity'] @@ -331,12 +331,12 @@ class IntervalAnalystPage(templatePage): else: if type(cols)==type(""): cols = [cols] - + colsLst = [] dispFields = [] for column in cols: if submitCols == "default" and column not in ('GeneSymbol') and (column in GeneListFields or column in speciesField): - colsLst.append(("%s (%s %s)" % (self.columnNames[column][1], self.species.title(), self.speciesFreeze[self.species]), + colsLst.append(("%s (%s %s)" % (self.columnNames[column][1], self.species.title(), self.speciesFreeze[self.species]), "%s__%s" % (column, self.speciesFreeze[self.species]))) dispFields.append([column, self.species]) else: @@ -346,17 +346,17 @@ class IntervalAnalystPage(templatePage): dispFields.append([column]) else: thisSpecies = self.speciesFreeze[column2[1]] - colsLst.append(("%s (%s %s)" % (self.columnNames[column2[0]][1], thisSpecies.title(), column2[1]), + colsLst.append(("%s (%s %s)" % (self.columnNames[column2[0]][1], thisSpecies.title(), column2[1]), column)) dispFields.append((column2[0], thisSpecies)) selectedColumnsList = HT.Select(name="columns", Class="snpBrowserSelectBox", multiple="true", data=colsLst, size=6) - + ########################## ## Create the columns form - ########################## + ########################## columnsForm = HT.Form(name="columnsForm", submit=HT.Input(type='hidden'), cgi=os.path.join(webqtlConfig.CGIDIR, self._scriptfile), enctype="multipart/form-data") columnsForm.append(HT.Input(type="hidden", name="fromdatabase", value= fd.formdata.getvalue("fromdatabase", "unknown"))) - columnsForm.append(HT.Input(type="hidden", name="species", value=self.species)) + columnsForm.append(HT.Input(type="hidden", name="species", value=self.species)) if self.diffCol: columnsForm.append(HT.Input(type="hidden", name="s1", value=self.diffCol[0])) columnsForm.append(HT.Input(type="hidden", name="s2", value=self.diffCol[1])) @@ -366,8 +366,8 @@ class IntervalAnalystPage(templatePage): removeButton = HT.Input(type="button", name="remove", value="Remove", Class="button", onClick="removeFromList(this.form.columns.selectedIndex, this.form.columns)") upButton = HT.Input(type="button", name="up", value="Up", Class="button", onClick="swapOptions(this.form.columns.selectedIndex, this.form.columns.selectedIndex-1, this.form.columns)") downButton = HT.Input(type="button", name="down", value="Down", Class="button", onClick="swapOptions(this.form.columns.selectedIndex, this.form.columns.selectedIndex+1, this.form.columns)") - clearButton = HT.Input(type="button", name="clear", value="Clear", Class="button", onClick="deleteAllElements(this.form.columns)") - submitButton = HT.Input(type="submit", value="Refresh", Class="button", onClick="selectAllElements(this.form.columns)") + clearButton = HT.Input(type="button", name="clear", value="Clear", Class="button", onClick="deleteAllElements(this.form.columns)") + submitButton = HT.Input(type="submit", value="Refresh", Class="button", onClick="selectAllElements(this.form.columns)") selectChrBox = HT.Select(name="chromosome") self.cursor.execute(""" @@ -375,11 +375,11 @@ class IntervalAnalystPage(templatePage): Chr_Length.Name, Length from Chr_Length, Species where Chr_Length.SpeciesId = Species.Id AND - Species.Name = '%s' + Species.Name = '%s' Order by Chr_Length.OrderId """ % self.species) - + results = self.cursor.fetchall() for chrInfo in results: selectChrBox.append((chrInfo[0], chrInfo[0])) @@ -401,5 +401,5 @@ class IntervalAnalystPage(templatePage): #columnsForm.append(HT.Input(type="hidden", name="sort", value=diffCol), # HT.Input(type="hidden", name="identification", value=identification), # HT.Input(type="hidden", name="traitInfo", value=traitInfo)) - + return columnsForm, dispFields diff --git a/wqflask/wqflask/marker_regression/MarkerRegressionPage.py b/wqflask/wqflask/marker_regression/MarkerRegressionPage.py index d02d80b3..455fcf95 100755 --- a/wqflask/wqflask/marker_regression/MarkerRegressionPage.py +++ b/wqflask/wqflask/marker_regression/MarkerRegressionPage.py @@ -140,7 +140,7 @@ class MarkerRegressionPage(templatePage): intCanvas = pid.PILCanvas(size=(self.graphWidth,self.graphHeight)) gifmap = self.plotIntMappingForPLINK(fd, intCanvas, startMb = self.startMb, endMb = self.endMb, plinkResultDict=plinkResultDict) - intCanvas.save(os.path.join(webqtlConfig.IMGDIR, filename), format='png') + intCanvas.save(os.path.join(webqtlConfig.GENERATED_IMAGE_DIR, filename), format='png') intImg=HT.Image('/image/'+filename+'.png', border=0, usemap='#WebQTLImageMap') TD_LR = HT.TR(HT.TD(HT.Blockquote(gifmap,intImg, HT.P()), bgColor='#eeeeee', height = 200)) @@ -249,7 +249,7 @@ class MarkerRegressionPage(templatePage): intCanvas = pid.PILCanvas(size=(self.graphWidth,self.graphHeight)) gifmap = self.plotIntMapping(fd, intCanvas, startMb = self.startMb, endMb = self.endMb, showLocusForm= "") filename= webqtlUtil.genRandStr("Itvl_") - intCanvas.save(os.path.join(webqtlConfig.IMGDIR, filename), format='png') + intCanvas.save(os.path.join(webqtlConfig.GENERATED_IMAGE_DIR, filename), format='png') intImg=HT.Image('/image/'+filename+'.png', border=0, usemap='#WebQTLImageMap') ################################################################ @@ -458,7 +458,7 @@ class MarkerRegressionPage(templatePage): #plotBar(myCanvas,10,10,390,290,LRSArray,XLabel='LRS',YLabel='Frequency',title=' Histogram of Permutation Test',identification=fd.identification) Plot.plotBar(myCanvas, LRSArray,XLabel='LRS',YLabel='Frequency',title=' Histogram of Permutation Test') filename= webqtlUtil.genRandStr("Reg_") - myCanvas.save(webqtlConfig.IMGDIR+filename, format='gif') + myCanvas.save(webqtlConfig.GENERATED_IMAGE_DIR+filename, format='gif') img=HT.Image('/image/'+filename+'.gif',border=0,alt='Histogram of Permutation Test') if fd.suggestive == None: diff --git a/wqflask/wqflask/marker_regression/marker_regression.py b/wqflask/wqflask/marker_regression/marker_regression.py index 36334317..265f9473 100644 --- a/wqflask/wqflask/marker_regression/marker_regression.py +++ b/wqflask/wqflask/marker_regression/marker_regression.py @@ -30,7 +30,7 @@ from flask import Flask, g from base.trait import GeneralTrait from base import data_set from base import species -from base import webqtlConfig +# from base import webqtlConfig from utility import webqtlUtil from utility import helper_functions from utility import Plot, Bunch diff --git a/wqflask/wqflask/marker_regression/marker_regression_gn1.py b/wqflask/wqflask/marker_regression/marker_regression_gn1.py index 01303b0f..decde579 100644 --- a/wqflask/wqflask/marker_regression/marker_regression_gn1.py +++ b/wqflask/wqflask/marker_regression/marker_regression_gn1.py @@ -178,8 +178,8 @@ class MarkerRegression(object): self.species = start_vars['species'] #Needing for form submission when doing single chr mapping or remapping after changing options - self.vals = start_vars['vals'] - self.mapping_method = start_vars['mapping_method'] + self.vals = start_vars['vals'] + self.mapping_method = start_vars['mapping_method'] if self.mapping_method == "rqtl_geno": self.mapmethod_rqtl_geno = start_vars['method'] self.mapmodel_rqtl_geno = start_vars['model'] @@ -232,7 +232,7 @@ class MarkerRegression(object): self.significant = start_vars['significant'] else: self.nperm = 0 - + if 'bootCheck' in start_vars.keys(): self.bootChecked = start_vars['bootCheck'] else: @@ -308,7 +308,7 @@ class MarkerRegression(object): if 'showSNP' in start_vars.keys(): self.SNPChecked = start_vars['showSNP'] else: - self.SNPChecked = False + self.SNPChecked = False if 'showGenes' in start_vars.keys(): self.geneChecked = start_vars['showGenes'] else: @@ -321,7 +321,7 @@ class MarkerRegression(object): self.endMb = float(start_vars['endMb']) except: self.endMb = -1 - try: + try: self.lrsMax = float(start_vars['lrsMax']) except: self.lrsMax = 0 @@ -363,7 +363,7 @@ class MarkerRegression(object): self.ChrList.append((indChr.name, i)) - + self.ChrLengthMbList = g.db.execute(""" Select Length from Chr_Length, InbredSet @@ -517,7 +517,7 @@ class MarkerRegression(object): chrName = self.selectedChr # Draw the genes for this chromosome / region of this chromosome webqtldatabase = self.dataset.name - + if self.dataset.group.species == "mouse": self.geneCol = GeneUtil.loadGenes(chrName, self.diffCol, self.startMb, self.endMb, webqtldatabase, "mouse") elif self.dataset.group.species == "rat": @@ -533,11 +533,11 @@ class MarkerRegression(object): # # #GENEID = fd.formdata.getvalue('GeneId') or None # GENEID = None - # + # # geneTableContainer = HT.Div(Id="sortable") #Div to hold table # geneTable = self.geneTable(self.geneCol,GENEID) # geneTableContainer.append(geneTable) - # + # # mainfmName = webqtlUtil.genRandStr("fm_") # tableForm = HT.Form(cgi=os.path.join(webqtlConfig.CGIDIR, webqtlConfig.SCRIPTFILE), enctype='multipart/form-data', name=mainfmName, submit=HT.Input(type='hidden')) # tableForm.append(HT.Input(name='FormID', value='', type='hidden')) @@ -552,22 +552,22 @@ class MarkerRegression(object): #else: showLocusForm = "" intCanvas = pid.PILCanvas(size=(self.graphWidth, self.graphHeight)) - gifmap = self.plotIntMapping(intCanvas, startMb = self.startMb, endMb = self.endMb, showLocusForm= showLocusForm) + gifmap = self.plotIntMapping(intCanvas, startMb = self.startMb, endMb = self.endMb, showLocusForm= showLocusForm) self.gifmap = gifmap.__str__() #print("GIFMAP:", gifmap.__str__()) self.filename= webqtlUtil.genRandStr("Itvl_") - intCanvas.save(os.path.join(webqtlConfig.IMGDIR, self.filename), format='jpeg') + intCanvas.save(os.path.join(webqtlConfig.GENERATED_IMAGE_DIR, self.filename), format='jpeg') intImg=HT.Image('/image/'+self.filename+'.png', border=0, usemap='#WebQTLImageMap') #Scales plot differently for high resolution if self.draw2X: intCanvasX2 = pid.PILCanvas(size=(self.graphWidth*2,self.graphHeight*2)) gifmapX2 = self.plotIntMapping(intCanvasX2, startMb = self.startMb, endMb = self.endMb, showLocusForm= showLocusForm, zoom=2) - intCanvasX2.save(os.path.join(webqtlConfig.IMGDIR, self.filename+"X2"), format='png') + intCanvasX2.save(os.path.join(webqtlConfig.GENERATED_IMAGE_DIR, self.filename+"X2"), format='png') #DLintImgX2=HT.Href(text='Download',url = '/image/'+self.filename+'X2.png', Class='smallsize', target='_blank') - + #textUrl = self.writeQTL2Text(fd, self.filename) ################################################################ @@ -597,7 +597,7 @@ class MarkerRegression(object): showLocusForm.append(intImg) else: showLocusForm = intImg - + if self.permChecked and self.nperm > 0 and not self.multipleInterval and 0 < self.nperm: self.perm_filename = self.drawPermutationHistogram() #perm_text_file = self.permutationTextFile() @@ -667,7 +667,7 @@ class MarkerRegression(object): TD_LR.append(HT.Blockquote(tableForm)) self.body = TD_LR - + #self.dict['body'] = TD_LR #self.dict['title'] = "Mapping" @@ -858,7 +858,7 @@ class MarkerRegression(object): BootCoord = [] i = 0 startX = xLeftOffset - + if self.selectedChr == -1: #ZS: If viewing full genome/all chromosomes for j, _chr in enumerate(self.genotype): BootCoord.append( []) @@ -881,8 +881,8 @@ class MarkerRegression(object): else: Xc = startX + (_locus.cM-_chr[0].cM)*plotXScale BootCoord[-1].append([Xc, self.bootResult[i]]) - i += 1 - + i += 1 + #reduce bootResult if self.selectedChr > -1: maxBootBar = 80.0 @@ -1411,7 +1411,7 @@ class MarkerRegression(object): if _strains[ii] in self.dataset.group.samplelist: temp = GeneralObject(name=_strains[ii], value=_val) smd.append(temp) - + smd.sort(lambda A, B: cmp(A.value, B.value)) smd.reverse() @@ -1566,14 +1566,14 @@ class MarkerRegression(object): firstGene = 0 else: lastGene = 0 - + for j, _geno in enumerate (self.genotype[0][1].genotype): plotbxd=0 for item in smd: if item.name == samplelist[j]: - plotbxd=1 - + plotbxd=1 + if (plotbxd == 1): ind = 0 @@ -1620,28 +1620,28 @@ class MarkerRegression(object): currentChromosome = self.genotype[0].name i = 0 - + paddingTop = yTopOffset ucscPaddingTop = paddingTop + self.WEBQTL_BAND_HEIGHT + self.BAND_SPACING ensemblPaddingTop = ucscPaddingTop + self.UCSC_BAND_HEIGHT + self.BAND_SPACING - + if zoom == 1: for pixel in range(xLeftOffset, xLeftOffset + plotWidth, pixelStep): - + calBase = self.kONE_MILLION*(startMb + (endMb-startMb)*(pixel-xLeftOffset-0.0)/plotWidth) - + xBrowse1 = pixel xBrowse2 = min(xLeftOffset + plotWidth, (pixel + pixelStep - 1)) - + WEBQTL_COORDS = "%d, %d, %d, %d" % (xBrowse1, paddingTop, xBrowse2, (paddingTop+self.WEBQTL_BAND_HEIGHT)) bandWidth = xBrowse2 - xBrowse1 WEBQTL_HREF = "javascript:rangeView('%s', %f, %f)" % (self.selectedChr - 1, max(0, (calBase-webqtlZoomWidth))/1000000.0, (calBase+webqtlZoomWidth)/1000000.0) - + WEBQTL_TITLE = "Click to view this section of the genome in WebQTL" gifmap.areas.append(HT.Area(shape='rect',coords=WEBQTL_COORDS,href=WEBQTL_HREF, title=WEBQTL_TITLE)) canvas.drawRect(xBrowse1, paddingTop, xBrowse2, (paddingTop + self.WEBQTL_BAND_HEIGHT), edgeColor=self.CLICKABLE_WEBQTL_REGION_COLOR, fillColor=self.CLICKABLE_WEBQTL_REGION_COLOR) canvas.drawLine(xBrowse1, paddingTop, xBrowse1, (paddingTop + self.WEBQTL_BAND_HEIGHT), color=self.CLICKABLE_WEBQTL_REGION_OUTLINE_COLOR) - + UCSC_COORDS = "%d, %d, %d, %d" %(xBrowse1, ucscPaddingTop, xBrowse2, (ucscPaddingTop+self.UCSC_BAND_HEIGHT)) if self.species == "mouse": UCSC_HREF = "http://genome.ucsc.edu/cgi-bin/hgTracks?db=%s&position=chr%s:%d-%d&hgt.customText=%s/snp/chr%s" % (self._ucscDb, self.selectedChr, max(0, calBase-flankingWidthInBases), calBase+flankingWidthInBases, webqtlConfig.PORTADDR, self.selectedChr) @@ -1651,7 +1651,7 @@ class MarkerRegression(object): gifmap.areas.append(HT.Area(shape='rect',coords=UCSC_COORDS,href=UCSC_HREF, title=UCSC_TITLE)) canvas.drawRect(xBrowse1, ucscPaddingTop, xBrowse2, (ucscPaddingTop+self.UCSC_BAND_HEIGHT), edgeColor=self.CLICKABLE_UCSC_REGION_COLOR, fillColor=self.CLICKABLE_UCSC_REGION_COLOR) canvas.drawLine(xBrowse1, ucscPaddingTop, xBrowse1, (ucscPaddingTop+self.UCSC_BAND_HEIGHT), color=self.CLICKABLE_UCSC_REGION_OUTLINE_COLOR) - + ENSEMBL_COORDS = "%d, %d, %d, %d" %(xBrowse1, ensemblPaddingTop, xBrowse2, (ensemblPaddingTop+self.ENSEMBL_BAND_HEIGHT)) if self.species == "mouse": ENSEMBL_HREF = "http://www.ensembl.org/Mus_musculus/contigview?highlight=&chr=%s&vc_start=%d&vc_end=%d&x=35&y=12" % (self.selectedChr, max(0, calBase-flankingWidthInBases), calBase+flankingWidthInBases) @@ -1766,7 +1766,7 @@ class MarkerRegression(object): ChrAInfo = [] preLpos = -1 distinctCount = 0.0 - + #if len(self.genotype) > 1: if self.selectedChr == -1: #ZS: If viewing full genome/all chromosomes for i, _chr in enumerate(self.genotype): @@ -1809,7 +1809,7 @@ class MarkerRegression(object): offsetA = -stepA lineColor = pid.lightblue startPosX = xLeftOffset - + for j, ChrInfo in enumerate(ChrAInfo): preLpos = -1 for i, item in enumerate(ChrInfo): @@ -1877,7 +1877,7 @@ class MarkerRegression(object): # lodm = self.LODFACTOR # else: # lodm = 1.0 - + #ZS: This is a mess, but I don't know a better way to account for different mapping methods returning results in different formats + the option to change between LRS and LOD if self.lrsMax <= 0: #sliding scale if "lrs_value" in self.qtlresults[0]: @@ -1890,7 +1890,7 @@ class MarkerRegression(object): else: if self.permChecked and self.nperm > 0 and not self.multipleInterval: self.significant = min(self.significant, webqtlConfig.MAXLRS) - self.suggestive = min(self.suggestive, webqtlConfig.MAXLRS) + self.suggestive = min(self.suggestive, webqtlConfig.MAXLRS) else: pass else: @@ -1903,10 +1903,10 @@ class MarkerRegression(object): else: if self.permChecked and self.nperm > 0 and not self.multipleInterval: self.significant = min(self.significant, webqtlConfig.MAXLRS) - self.suggestive = min(self.suggestive, webqtlConfig.MAXLRS) + self.suggestive = min(self.suggestive, webqtlConfig.MAXLRS) else: pass - + if self.permChecked and self.nperm > 0 and not self.multipleInterval: LRS_LOD_Max = max(self.significant, LRS_LOD_Max) @@ -1923,7 +1923,7 @@ class MarkerRegression(object): LRSScale = 2.5 else: LRSScale = 1.0 - + LRSAxisList = Plot.frange(LRSScale, LRS_LOD_Max, LRSScale) #make sure the user's value appears on the y-axis #update by NL 6-21-2011: round the LOD value to 100 when LRS_LOD_Max is equal to 460 @@ -1953,7 +1953,7 @@ class MarkerRegression(object): #"Significant" and "Suggestive" Drawing Routine # ======= Draw the thick lines for "Significant" and "Suggestive" ===== (crowell: I tried to make the SNPs draw over these lines, but piddle wouldn't have it...) - + #ZS: I don't know if what I did here with this inner function is clever or overly complicated, but it's the only way I could think of to avoid duplicating the code inside this function def add_suggestive_significant_lines_and_legend(start_pos_x, chr_length_dist): rightEdge = int(start_pos_x + chr_length_dist*plotXScale - self.SUGGESTIVE_WIDTH/1.5) @@ -1976,13 +1976,13 @@ class MarkerRegression(object): start_pos_x += (chr_length_dist+self.GraphInterval)*plotXScale return start_pos_x - + for i, _chr in enumerate(self.genotype): if self.selectedChr != -1: if _chr.name == self.ChrList[self.selectedChr][0]: startPosX = add_suggestive_significant_lines_and_legend(startPosX, self.ChrLengthDistList[0]) break - else: + else: continue else: startPosX = add_suggestive_significant_lines_and_legend(startPosX, self.ChrLengthDistList[i]) @@ -1997,7 +1997,7 @@ class MarkerRegression(object): #else: # dominanceMax = -1 lrsEdgeWidth = 2 - + if zoom == 2: lrsEdgeWidth = 2 * lrsEdgeWidth @@ -2018,7 +2018,7 @@ class MarkerRegression(object): if qtlresult['chr'] != previous_chr and self.selectedChr == -1: if self.manhattan_plot != True: canvas.drawPolygon(LRSCoordXY,edgeColor=thisLRSColor,closed=0, edgeWidth=lrsEdgeWidth, clipX=(xLeftOffset, xLeftOffset + plotWidth)) - + if not self.multipleInterval and self.additiveChecked: plusColor = self.ADDITIVE_COLOR_POSITIVE minusColor = self.ADDITIVE_COLOR_NEGATIVE @@ -2048,7 +2048,7 @@ class MarkerRegression(object): canvas.drawLine(Xc0, Yc0, Xc, Yc, color=plusColor, width=lineWidth, clipX=(xLeftOffset, xLeftOffset + plotWidth)) else: canvas.drawLine(Xc0, yZero - (Yc0-yZero), Xc, yZero - (Yc-yZero), color=minusColor, width=lineWidth, clipX=(xLeftOffset, xLeftOffset + plotWidth)) - + LRSCoordXY = [] AdditiveCoordXY = [] previous_chr = qtlresult['chr'] @@ -2061,7 +2061,7 @@ class MarkerRegression(object): #startPosX += (self.ChrLengthDistList[j]+self.GraphInterval)*plotXScale - #for j, _chr in enumerate(self.genotype): + #for j, _chr in enumerate(self.genotype): #ZS: This is beause the chromosome value stored in qtlresult['chr'] can be (for example) either X or 20 depending upon the mapping method/scale used if self.plotScale == "physic": this_chr = str(self.ChrList[self.selectedChr][0]) @@ -2126,7 +2126,7 @@ class MarkerRegression(object): if self.manhattan_plot != True: canvas.drawPolygon(LRSCoordXY,edgeColor=thisLRSColor,closed=0, edgeWidth=lrsEdgeWidth, clipX=(xLeftOffset, xLeftOffset + plotWidth)) - + if not self.multipleInterval and self.additiveChecked: plusColor = self.ADDITIVE_COLOR_POSITIVE minusColor = self.ADDITIVE_COLOR_NEGATIVE @@ -2156,7 +2156,7 @@ class MarkerRegression(object): canvas.drawLine(Xc0, Yc0, Xc, Yc, color=plusColor, width=lineWidth, clipX=(xLeftOffset, xLeftOffset + plotWidth)) else: canvas.drawLine(Xc0, yZero - (Yc0-yZero), Xc, yZero - (Yc-yZero), color=minusColor, width=lineWidth, clipX=(xLeftOffset, xLeftOffset + plotWidth)) - + if not self.multipleInterval and INTERCROSS and self.dominanceChecked: plusColor = self.DOMINANCE_COLOR_POSITIVE minusColor = self.DOMINANCE_COLOR_NEGATIVE @@ -2186,7 +2186,7 @@ class MarkerRegression(object): canvas.drawLine(Xc0, Yc0, Xc, Yc, color=plusColor, width=lineWidth, clipX=(xLeftOffset, xLeftOffset + plotWidth)) else: canvas.drawLine(Xc0, yZero - (Yc0-yZero), Xc, yZero - (Yc-yZero), color=minusColor, width=lineWidth, clipX=(xLeftOffset, xLeftOffset + plotWidth)) - + ###draw additive scale if not self.multipleInterval and self.additiveChecked: @@ -2222,7 +2222,7 @@ class MarkerRegression(object): if zoom == 2: fontZoom = 1.5 yTopOffset += 30 - + #calculate plot scale if self.plotScale != 'physic': self.ChrLengthDistList = self.ChrLengthCMList @@ -2589,13 +2589,13 @@ class MarkerRegression(object): perm_output = [value/4.16 for value in self.perm_output] else: perm_output = self.perm_output - + Plot.plotBar(myCanvas, perm_output, XLabel=self.LRS_LOD, YLabel='Frequency', title=' Histogram of Permutation Test') filename= webqtlUtil.genRandStr("Reg_") myCanvas.save(webqtlConfig.IMGDIR+filename, format='gif') - + return filename - + # img=HT.Image('/image/'+filename+'.gif',border=0,alt='Histogram of Permutation Test') # self.suggestive = self.perm_output[int(self.nperm*0.37-1)] @@ -2609,9 +2609,9 @@ class MarkerRegression(object): # permutation.append(HT.TR(HT.TD(img)), # HT.TR(HT.TD('')), # HT.TR(HT.TD('Total of %d permutations'%self.nperm))) - + # return permutation - + def permutationTextFile(self): filename= webqtlUtil.genRandStr("Reg_") fpText = open('%s.txt' % (webqtlConfig.TMPDIR+filename), 'wb') @@ -2624,12 +2624,12 @@ class MarkerRegression(object): '    Significant LRS =%3.2f\n'%self.significant, HT.BR(), '    Highly Significant LRS =%3.2f\n' % self.highlysignificant) - + for lrs_value in self.perm_output: fpText.write(str(lrs_value) + "\n") - + textUrl = HT.Href(text = 'Download Permutation Results', url= '/tmp/'+filename+'.txt', target = "_blank", Class='fs12 fwn') - + return textUrl def geneTable(self, geneCol, refGene=None): @@ -2654,7 +2654,7 @@ class MarkerRegression(object): else: gene_table = "" - return gene_table + return gene_table def getLiteratureCorrelation(cursor,geneId1=None,geneId2=None): if not geneId1 or not geneId2: @@ -2954,4 +2954,4 @@ And by voluntary, according to HFG when I talked to him, they have a choice betw sortby = ("", "") - return sortby \ No newline at end of file + return sortby diff --git a/wqflask/wqflask/search_results.py b/wqflask/wqflask/search_results.py index 52fe2e34..9941a4d3 100755 --- a/wqflask/wqflask/search_results.py +++ b/wqflask/wqflask/search_results.py @@ -26,7 +26,6 @@ from MySQLdb import escape_string as escape # Instead of importing HT we're going to build a class below until we can eliminate it # from htmlgen import HTMLgen2 as HT -from base import webqtlConfig from utility.benchmark import Bench from base.data_set import create_dataset from base.trait import GeneralTrait diff --git a/wqflask/wqflask/show_trait/show_trait.py b/wqflask/wqflask/show_trait/show_trait.py index 35f7fe5f..e80cf191 100755 --- a/wqflask/wqflask/show_trait/show_trait.py +++ b/wqflask/wqflask/show_trait/show_trait.py @@ -166,7 +166,7 @@ class ShowTrait(object): return False def check_pylmm_rqtl(): - if os.path.isfile(webqtlConfig.GENODIR+self.dataset.group.name+".geno") and (os.path.getsize(webqtlConfig.NEWGENODIR+self.dataset.group.name+".json") > 0): + if os.path.isfile(webqtlConfig.GENODIR+self.dataset.group.name+".geno") and (os.path.getsize(webqtlConfig.JSON_GENODIR+self.dataset.group.name+".json") > 0): return True else: return False -- cgit v1.2.3 From 31a1c126185adb747028d035717ad72728a52b0e Mon Sep 17 00:00:00 2001 From: Pjotr Prins Date: Wed, 24 Feb 2016 11:25:10 +0000 Subject: -a [PATCH 038/100] Fix compile errors --- wqflask/base/data_set.py | 6 +++--- wqflask/utility/tools.py | 6 ++++-- 2 files changed, 7 insertions(+), 5 deletions(-) (limited to 'wqflask/base/data_set.py') diff --git a/wqflask/base/data_set.py b/wqflask/base/data_set.py index 6527657a..8b2a9f01 100755 --- a/wqflask/base/data_set.py +++ b/wqflask/base/data_set.py @@ -44,7 +44,7 @@ from dbFunction import webqtlDatabaseFunction from utility import webqtlUtil from utility.benchmark import Bench from utility import chunks -from utility.tools import locate, locate_without_error +from utility.tools import locate, locate_ignore_error from maintenance import get_group_samplelists @@ -405,8 +405,8 @@ class DatasetGroup(object): else: print("Cache not hit") - genotype_fn = locate_without_error(self.name+".geno",'genotype') - mapping_fn = locate_without_error(self.name+".fam",'mapping') + genotype_fn = locate_ignore_error(self.name+".geno",'genotype') + mapping_fn = locate_ignore_error(self.name+".fam",'mapping') if mapping_fn: self.samplelist = get_group_samplelists.get_samplelist("plink", mapping_fn) elif genotype_fn: diff --git a/wqflask/utility/tools.py b/wqflask/utility/tools.py index c0f6a49a..67c5128a 100644 --- a/wqflask/utility/tools.py +++ b/wqflask/utility/tools.py @@ -1,3 +1,4 @@ + # Tools/paths finder resolves external paths from settings and/or environment # variables @@ -83,9 +84,10 @@ def assert_dir(dir): if not valid_path(dir): raise Exception("ERROR: can not find directory "+dir) return dir - + def mk_dir(dir): - os.makedirs(dir) + if not valid_path(dir): + os.makedirs(dir) return assert_dir(dir) def locate(name, subdir=None): -- cgit v1.2.3 From c5dbe982272ef95c6598c36172444b1e8263c01a Mon Sep 17 00:00:00 2001 From: Pjotr Prins Date: Wed, 24 Feb 2016 11:39:05 +0000 Subject: -a [PATCH 039/100] Removing commented code --- wqflask/base/data_set.py | 228 ----------------------------------------------- 1 file changed, 228 deletions(-) (limited to 'wqflask/base/data_set.py') diff --git a/wqflask/base/data_set.py b/wqflask/base/data_set.py index 8b2a9f01..52ac95f0 100755 --- a/wqflask/base/data_set.py +++ b/wqflask/base/data_set.py @@ -58,25 +58,13 @@ DS_NAME_MAP = {} def create_dataset(dataset_name, dataset_type = None, get_samplelist = True): if not dataset_type: dataset_type = Dataset_Getter(dataset_name) - #dataset_type = get_dataset_type_from_json(dataset_name) print("dataset_type is:", dataset_type) - #query = """ - # SELECT DBType.Name - # FROM DBList, DBType - # WHERE DBList.Name = '{}' and - # DBType.Id = DBList.DBTypeId - # """.format(escape(dataset_name)) - #dataset_type = g.db.execute(query).fetchone().Name - dataset_ob = DS_NAME_MAP[dataset_type] dataset_class = globals()[dataset_ob] return dataset_class(dataset_name, get_samplelist) - -#def get_dataset_type_from_json(dataset_name): - class Dataset_Types(object): def __init__(self): @@ -90,8 +78,6 @@ class Dataset_Types(object): for group in data['datasets'][species]: for dataset_type in data['datasets'][species][group]: for dataset in data['datasets'][species][group][dataset_type]: - #print("dataset is:", dataset) - short_dataset_name = dataset[1] if dataset_type == "Phenotypes": new_type = "Publish" @@ -107,10 +93,6 @@ class Dataset_Types(object): # Do the intensive work at startup one time only Dataset_Getter = Dataset_Types() -# -#print("Running at startup:", get_dataset_type_from_json("HBTRC-MLPFC_0611")) - - def create_datasets_list(): key = "all_datasets" result = Redis.get(key) @@ -215,13 +197,6 @@ class Markers(object): #del self.markers[i] self.markers = filtered_markers - - #for i, marker in enumerate(self.markers): - # if not 'p_value' in marker: - # #print("self.markers[i]", self.markers[i]) - # del self.markers[i] - # #self.markers.remove(self.markers[i]) - class HumanMarkers(Markers): def __init__(self, name, specified_markers = []): @@ -249,26 +224,8 @@ class HumanMarkers(Markers): def add_pvalues(self, p_values): - #for marker, p_value in itertools.izip(self.markers, p_values): - # if marker['Mb'] <= 0 and marker['chr'] == 0: - # continue - # marker['p_value'] = p_value - # print("p_value is:", marker['p_value']) - # marker['lod_score'] = -math.log10(marker['p_value']) - # #Using -log(p) for the LRS; need to ask Rob how he wants to get LRS from p-values - # marker['lrs_value'] = -math.log10(marker['p_value']) * 4.61 - - #print("p_values2:", pf(p_values)) super(HumanMarkers, self).add_pvalues(p_values) - #with Bench("deleting markers"): - # markers = [] - # for marker in self.markers: - # if not marker['Mb'] <= 0 and not marker['chr'] == 0: - # markers.append(marker) - # self.markers = markers - - class DatasetGroup(object): """ @@ -311,12 +268,6 @@ class DatasetGroup(object): def datasets(self): key = "group_dataset_menu:v2:" + self.name print("key is2:", key) - #with Bench("Loading cache"): - # result = Redis.get(key) - #if result: - # self._datasets = pickle.loads(result) - # return self._datasets - dataset_menu = [] print("[tape4] webqtlConfig.PUBLICTHRESH:", webqtlConfig.PUBLICTHRESH) print("[tape4] type webqtlConfig.PUBLICTHRESH:", type(webqtlConfig.PUBLICTHRESH)) @@ -425,11 +376,6 @@ class DatasetGroup(object): def read_genotype_file(self): '''Read genotype from .geno file instead of database''' - #if self.group == 'BXD300': - # self.group = 'BXD' - # - #assert self.group, "self.group needs to be set" - #genotype_1 is Dataset Object without parents and f1 #genotype_2 is Dataset Object with parents and f1 (not for intercross) @@ -446,40 +392,16 @@ class DatasetGroup(object): #determine default genotype object if self.incparentsf1 and genotype_1.type != "intercross": - #self.genotype = genotype_2 genotype = genotype_2 else: self.incparentsf1 = 0 - #self.genotype = genotype_1 genotype = genotype_1 - #self.samplelist = list(self.genotype.prgy) self.samplelist = list(genotype.prgy) return genotype -#class DataSets(object): -# """Builds a list of DataSets""" -# -# def __init__(self): -# self.datasets = list() -# - - - #query = """SELECT Name FROM ProbeSetFreeze - # UNION - # SELECT Name From PublishFreeze - # UNION - # SELECT Name From GenoFreeze""" - # - #for result in g.db.execute(query).fetchall(): - # dataset = DataSet(result.Name) - # self.datasets.append(dataset) - -#ds = DataSets() -#print("[orange] ds:", ds.datasets) - class DataSet(object): """ DataSet class defines a dataset in webqtl, can be either Microarray, @@ -512,32 +434,11 @@ class DataSet(object): """Gets overridden later, at least for Temp...used by trait's get_given_name""" return None - #@staticmethod - #def get_by_trait_id(trait_id): - # """Gets the dataset object given the trait id""" - # - # - # - # name = g.db.execute(""" SELECT - # - # """) - # - # return DataSet(name) - # Delete this eventually @property def riset(): Weve_Renamed_This_As_Group - - #@property - #def group(self): - # if not self._group: - # self.get_group() - # - # return self._group - - def retrieve_other_names(self): """ If the data set name parameter is not found in the 'Name' field of the data set table, @@ -609,21 +510,6 @@ class DataSet(object): number_chunks = int(math.ceil(len(sample_ids) / chunk_size)) trait_sample_data = [] for sample_ids_step in chunks.divide_into_chunks(sample_ids, number_chunks): - - #XZ, 09/24/2008: build one temporary table that only contains the records associated with the input GeneId - #tempTable = None - #if GeneId and db.type == "ProbeSet": - # if method == "3": - # tempTable = self.getTempLiteratureTable(species=species, - # input_species_geneid=GeneId, - # returnNumber=returnNumber) - # - # if method == "4" or method == "5": - # tempTable = self.getTempTissueCorrTable(primaryTraitSymbol=GeneSymbol, - # TissueProbeSetFreezeId=tissueProbeSetFreezeId, - # method=method, - # returnNumber=returnNumber) - if self.type == "Publish": dataset_type = "Phenotype" else: @@ -1013,83 +899,11 @@ class MrnaAssayDataSet(DataSet): and ProbeSetFreezeId = {} """.format(escape(str(self.id))) results = g.db.execute(query).fetchall() - #print("After get_trait_list query") trait_data = {} for trait in results: - #print("Retrieving sample_data for ", trait[0]) trait_data[trait[0]] = self.retrieve_sample_data(trait[0]) - #print("After retrieve_sample_data") return trait_data - #def get_trait_data(self): - # self.samplelist = self.group.samplelist + self.group.parlist + self.group.f1list - # query = """ - # SELECT Strain.Name, Strain.Id FROM Strain, Species - # WHERE Strain.Name IN {} - # and Strain.SpeciesId=Species.Id - # and Species.name = '{}' - # """.format(create_in_clause(self.samplelist), *mescape(self.group.species)) - # results = dict(g.db.execute(query).fetchall()) - # sample_ids = [results[item] for item in self.samplelist] - # - # # MySQL limits the number of tables that can be used in a join to 61, - # # so we break the sample ids into smaller chunks - # # Postgres doesn't have that limit, so we can get rid of this after we transition - # chunk_size = 50 - # number_chunks = int(math.ceil(len(sample_ids) / chunk_size)) - # trait_sample_data = [] - # for sample_ids_step in chunks.divide_into_chunks(sample_ids, number_chunks): - # - # #XZ, 09/24/2008: build one temporary table that only contains the records associated with the input GeneId - # #tempTable = None - # #if GeneId and db.type == "ProbeSet": - # # if method == "3": - # # tempTable = self.getTempLiteratureTable(species=species, - # # input_species_geneid=GeneId, - # # returnNumber=returnNumber) - # # - # # if method == "4" or method == "5": - # # tempTable = self.getTempTissueCorrTable(primaryTraitSymbol=GeneSymbol, - # # TissueProbeSetFreezeId=tissueProbeSetFreezeId, - # # method=method, - # # returnNumber=returnNumber) - # - # temp = ['T%s.value' % item for item in sample_ids_step] - # query = "SELECT {}.Name,".format(escape(self.type)) - # data_start_pos = 1 - # query += string.join(temp, ', ') - # query += ' FROM ({}, {}XRef, {}Freeze) '.format(*mescape(self.type, - # self.type, - # self.type)) - # - # for item in sample_ids_step: - # query += """ - # left join {}Data as T{} on T{}.Id = {}XRef.DataId - # and T{}.StrainId={}\n - # """.format(*mescape(self.type, item, item, self.type, item, item)) - # - # query += """ - # WHERE {}XRef.{}FreezeId = {}Freeze.Id - # and {}Freeze.Name = '{}' - # and {}.Id = {}XRef.{}Id - # order by {}.Id - # """.format(*mescape(self.type, self.type, self.type, self.type, - # self.name, self.type, self.type, self.type, self.type)) - # results = g.db.execute(query).fetchall() - # trait_sample_data.append(results) - # - # trait_count = len(trait_sample_data[0]) - # self.trait_data = collections.defaultdict(list) - # - # # put all of the separate data together into a dictionary where the keys are - # # trait names and values are lists of sample values - # for trait_counter in range(trait_count): - # trait_name = trait_sample_data[0][trait_counter][0] - # for chunk_counter in range(int(number_chunks)): - # self.trait_data[trait_name] += ( - # trait_sample_data[chunk_counter][trait_counter][data_start_pos:]) - - def get_trait_info(self, trait_list=None, species=''): # Note: setting trait_list to [] is probably not a great idea. @@ -1178,22 +992,9 @@ class MrnaAssayDataSet(DataSet): result = g.db.execute(query).fetchone() if result: - #if result[0] and result[1]: - # lrs_chr = result[0] - # lrs_mb = result[1] 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) - - #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 = '%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)) @@ -1259,35 +1060,6 @@ class MrnaAssayDataSet(DataSet): return dict(results) - #def retrieve_gene_symbols(self): - # query = """ - # select ProbeSet.Name, ProbeSet.Symbol, ProbeSet.GeneId - # from ProbeSet,ProbeSetXRef - # where ProbeSetXRef.ProbeSetFreezeId = %s and - # ProbeSetXRef.ProbeSetId=ProbeSet.Id; - # """ % (self.id) - # results = g.db.execute(query).fetchall() - # symbol_dict = {} - # for item in results: - # symbol_dict[item[0]] = item[1] - # return symbol_dict - # - #def retrieve_gene_ids(self): - # query = """ - # select ProbeSet.Name, ProbeSet.GeneId - # from ProbeSet,ProbeSetXRef - # where ProbeSetXRef.ProbeSetFreezeId = %s and - # ProbeSetXRef.ProbeSetId=ProbeSet.Id; - # """ % (self.id) - # return process_and_run_query(query) - # results = g.db.execute(query).fetchall() - # symbol_dict = {} - # for item in results: - # symbol_dict[item[0]] = item[1] - # return symbol_dict - - - class TempDataSet(DataSet): '''Temporary user-generated data set''' -- cgit v1.2.3