diff options
Diffstat (limited to 'wqflask')
43 files changed, 1393 insertions, 958 deletions
diff --git a/wqflask/base/data_set.py b/wqflask/base/data_set.py index e37a838f..053b45fc 100755..100644 --- a/wqflask/base/data_set.py +++ b/wqflask/base/data_set.py @@ -44,6 +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_ignore_error from maintenance import get_group_samplelists @@ -57,40 +58,26 @@ 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): 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" @@ -99,32 +86,28 @@ 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(): @@ -133,10 +116,10 @@ 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 @@ -157,30 +140,30 @@ 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 @@ -213,18 +196,11 @@ 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: - # #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 = []): - 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() @@ -243,39 +219,21 @@ class HumanMarkers(Markers): marker['name'] = splat[1] marker['Mb'] = float(splat[3]) / 1000000 self.markers.append(marker) - + #print("markers is: ", pf(self.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): """ 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""" @@ -283,14 +241,14 @@ 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 @@ -301,7 +259,7 @@ 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 @@ -310,12 +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)) @@ -355,7 +307,7 @@ 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): @@ -383,7 +335,7 @@ 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: @@ -402,21 +354,17 @@ class DatasetGroup(object): #print(" type: ", type(self.samplelist)) #print(" self.samplelist: ", self.samplelist) else: - #print("Cache not hit") - - from utility.tools import plink_command - PLINK_PATH,PLINK_COMMAND = plink_command() - - geno_file_path = webqtlConfig.GENODIR+self.name+".geno" - plink_file_path = PLINK_PATH+"/"+self.name+".fam" - - if os.path.isfile(plink_file_path): - self.samplelist = get_group_samplelists.get_samplelist("plink", plink_file_path) - elif os.path.isfile(geno_file_path): - self.samplelist = get_group_samplelists.get_samplelist("geno", geno_file_path) + print("Cache not hit") + + 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: + 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) @@ -428,30 +376,14 @@ 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) 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 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!") + full_filename = str(locate(self.name+'.geno','genotype')) + 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) @@ -460,39 +392,15 @@ 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) + return genotype -#ds = DataSets() -#print("[orange] ds:", ds.datasets) class DataSet(object): """ @@ -509,13 +417,14 @@ class DataSet(object): self.shortname = None self.fullname = None self.type = None + self.data_scale = None #ZS: For example log2 self.setup() 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() @@ -525,32 +434,11 @@ 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 - # - # """) - # - # 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): """ @@ -560,7 +448,7 @@ 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 ( @@ -569,8 +457,8 @@ class DataSet(object): self.name, self.name)) - self.id, self.name, self.fullname, self.shortname, self.tissue = g.db.execute(""" - SELECT ProbeSetFreeze.Id, ProbeSetFreeze.Name, ProbeSetFreeze.FullName, ProbeSetFreeze.ShortName, Tissue.Name + self.id, self.name, self.fullname, self.shortname, self.data_scale, self.tissue = g.db.execute(""" + SELECT ProbeSetFreeze.Id, ProbeSetFreeze.Name, ProbeSetFreeze.FullName, ProbeSetFreeze.ShortName, ProbeSetFreeze.DataScale, Tissue.Name FROM ProbeSetFreeze, ProbeFreeze, Tissue WHERE ProbeSetFreeze.public > %s AND ProbeSetFreeze.ProbeFreezeId = ProbeFreeze.Id AND @@ -596,17 +484,17 @@ 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 {} @@ -623,21 +511,6 @@ 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: @@ -658,7 +531,7 @@ 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 @@ -675,16 +548,16 @@ 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): @@ -697,9 +570,9 @@ 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', @@ -770,26 +643,26 @@ 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: @@ -834,7 +707,7 @@ 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 @@ -892,7 +765,7 @@ class GenotypeDataSet(DataSet): def check_confidentiality(self): return geno_mrna_confidentiality(self) - + def get_trait_list(self): query = """ select Geno.Name @@ -926,7 +799,7 @@ 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 @@ -1018,7 +891,7 @@ class MrnaAssayDataSet(DataSet): def check_confidentiality(self): return geno_mrna_confidentiality(self) - + def get_trait_list_1(self): query = """ select ProbeSet.Name @@ -1027,86 +900,14 @@ 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. + # Note: setting trait_list to [] is probably not a great idea. if not trait_list: trait_list = [] @@ -1169,7 +970,7 @@ class MrnaAssayDataSet(DataSet): #print("query is:", pf(query)) result = g.db.execute(query).fetchone() - + mean = result[0] if result else 0 if mean: @@ -1190,28 +991,15 @@ 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] - # 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)) - + def convert_location_to_value(self, chromosome, mb): try: @@ -1222,7 +1010,7 @@ class MrnaAssayDataSet(DataSet): else: location_value = (ord(str(chromosome).upper()[0])*1000 + float(mb)) - + return location_value def get_sequence(self): @@ -1239,7 +1027,7 @@ 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 @@ -1260,8 +1048,8 @@ 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 @@ -1270,37 +1058,8 @@ 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): - # 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 - - + return dict(results) class TempDataSet(DataSet): @@ -1322,8 +1081,8 @@ class TempDataSet(DataSet): self.id = 1 self.fullname = 'Temporary Storage' self.shortname = 'Temp' - - + + @staticmethod def handle_pca(desc): if 'PCA' in desc: @@ -1332,13 +1091,13 @@ 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 @@ -1351,7 +1110,7 @@ class TempDataSet(DataSet): """, self.name) self.group, self.group_id = self.cursor.fetchone() #return self.group - + def retrieve_sample_data(self, trait): query = """ SELECT @@ -1365,7 +1124,7 @@ class TempDataSet(DataSet): Order BY Strain.Name """ % escape(trait.name) - + results = g.db.execute(query).fetchall() diff --git a/wqflask/base/webqtlConfig.py b/wqflask/base/webqtlConfig.py new file mode 100755 index 00000000..0358bcbf --- /dev/null +++ b/wqflask/base/webqtlConfig.py @@ -0,0 +1,79 @@ +#########################################' +# Environment Variables - public +# +# Note: much of this needs to handled by the settings/environment +# scripts. But rather than migrating everything in one go, we'll +# take it a step at a time. First the hard coded paths get replaced +# with those in utility/tools.py +# +######################################### + +from utility.tools import mk_dir, assert_dir, flat_files, TEMPDIR + +#Debug Level +#1 for debug, mod python will reload import each time +DEBUG = 1 + +#USER privilege +USERDICT = {'guest':1,'user':2, 'admin':3, 'root':4} + +#minimum number of informative strains +KMININFORMATIVE = 5 + +#maximum number of traits for interval mapping +MULTIPLEMAPPINGLIMIT = 11 + +#maximum number of traits for correlation +MAXCORR = 100 + +#Daily download limit from one IP +DAILYMAXIMUM = 1000 + +#maximum LRS value +MAXLRS = 460.0 + +#temporary data life span +MAXLIFE = 86400 + +#MINIMUM Database public value +PUBLICTHRESH = 0 + +#NBCI address +NCBI_LOCUSID = "http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=gene&cmd=Retrieve&dopt=Graphics&list_uids=%s" +UCSC_REFSEQ = "http://genome.cse.ucsc.edu/cgi-bin/hgGene?db=%s&hgg_gene=%s&hgg_chrom=chr%s&hgg_start=%s&hgg_end=%s" +GENBANK_ID = "http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=Nucleotide&cmd=search&doptcmdl=DocSum&term=%s" +OMIM_ID = "http://www.ncbi.nlm.nih.gov/omim/%s" +UNIGEN_ID = "http://www.ncbi.nlm.nih.gov/UniGene/clust.cgi?ORG=%s&CID=%s"; +HOMOLOGENE_ID = "http://www.ncbi.nlm.nih.gov/sites/entrez?Db=homologene&Cmd=DetailsSearch&Term=%s" +PUBMEDLINK_URL = "http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=PubMed&list_uids=%s&dopt=Abstract" +UCSC_POS = "http://genome.ucsc.edu/cgi-bin/hgTracks?clade=mammal&org=%s&db=%s&position=chr%s:%s-%s&pix=800&Submit=submit" +UCSC_BLAT = 'http://genome.ucsc.edu/cgi-bin/hgBlat?org=%s&db=%s&type=0&sort=0&output=0&userSeq=%s' +UTHSC_BLAT = 'http://ucscbrowser.genenetwork.org/cgi-bin/hgBlat?org=%s&db=%s&type=0&sort=0&output=0&userSeq=%s' +UCSC_GENOME = "http://genome.ucsc.edu/cgi-bin/hgTracks?db=%s&position=chr%s:%d-%d&hgt.customText=http://web2qtl.utmem.edu:88/snp/chr%s" +ENSEMBLE_BLAT = 'http://www.ensembl.org/Mus_musculus/featureview?type=AffyProbe&id=%s' +DBSNP = 'http://www.ncbi.nlm.nih.gov/SNP/snp_ref.cgi?type=rs&rs=%s' +UCSC_RUDI_TRACK_URL = " http://genome.cse.ucsc.edu/cgi-bin/hgTracks?org=%s&db=%s&hgt.customText=http://gbic.biol.rug.nl/~ralberts/tracks/%s/%s" +GENOMEBROWSER_URL="http://ucscbrowser.genenetwork.org/cgi-bin/hgTracks?clade=mammal&org=Mouse&db=mm9&position=%s&hgt.suggest=&pix=800&Submit=submit" +ENSEMBLETRANSCRIPT_URL="http://useast.ensembl.org/Mus_musculus/Lucene/Details?species=Mus_musculus;idx=Transcript;end=1;q=%s" + +# The following paths are no longer in use! +# HTMLPATH is replaced by GENODIR +# IMGDIR is replaced by GENERATED_IMAGE_DIR + +# Temporary storage: +TMPDIR = mk_dir(TEMPDIR+'/gn2/') +CACHEDIR = mk_dir(TEMPDIR+'/cache/') +# We can no longer write into the git tree: +GENERATED_IMAGE_DIR = mk_dir(TMPDIR+'/generated/') +GENERATED_TEXT_DIR = mk_dir(TMPDIR+'/generated_text/') + +# Flat file directories +GENODIR = flat_files('genotype')+'/' +JSON_GENODIR = assert_dir(GENODIR+'json/') + +PORTADDR = "http://50.16.251.170" + +INFOPAGEHREF = '/dbdoc/%s.html' +CGIDIR = '/webqtl/' #XZ: The variable name 'CGIDIR' should be changed to 'PYTHONDIR' +SCRIPTFILE = 'main.py' + 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/gen_select_dataset.py b/wqflask/maintenance/gen_select_dataset.py index e080050e..489d291f 100755 --- a/wqflask/maintenance/gen_select_dataset.py +++ b/wqflask/maintenance/gen_select_dataset.py @@ -36,8 +36,7 @@ from __future__ import print_function, division #print("cdict is:", cdict) import sys -sys.path.append("/home/zas1024/") -import zach_settings +import zach_settings # no hard code paths! import MySQLdb 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/runserver.py b/wqflask/runserver.py index 59ebf0d4..e4392b3f 100755 --- a/wqflask/runserver.py +++ b/wqflask/runserver.py @@ -25,8 +25,8 @@ file_handler = logging.FileHandler(app.config['LOGFILE']) file_handler.setLevel(logging.DEBUG) app.logger.addHandler(file_handler) -import logging_tree -logging_tree.printout() +# import logging_tree +# logging_tree.printout() app.run(host='0.0.0.0', port=app.config['SERVER_PORT'], diff --git a/wqflask/utility/external.py b/wqflask/utility/external.py new file mode 100644 index 00000000..50afea08 --- /dev/null +++ b/wqflask/utility/external.py @@ -0,0 +1,9 @@ +# Call external program + +import os +import sys +import subprocess + +def shell(command): + if subprocess.call(command, shell=True) != 0: + raise Exception("ERROR: failed on "+command) diff --git a/wqflask/utility/genofile_parser.py b/wqflask/utility/genofile_parser.py new file mode 100644 index 00000000..67b84dc9 --- /dev/null +++ b/wqflask/utility/genofile_parser.py @@ -0,0 +1,100 @@ +# CTL analysis for GN2 +# Author / Maintainer: Danny Arends <Danny.Arends@gmail.com> + +from __future__ import print_function, division, absolute_import +import sys +import os +import glob +import traceback +import gzip + + +import simplejson as json + +from pprint import pformat as pf + +class Marker(object): + def __init__(self): + self.name = None + self.chr = None + self.cM = None + self.Mb = None + self.genotypes = [] + + +class ConvertGenoFile(object): + + def __init__(self, input_file): + self.mb_exists = False + self.cm_exists = False + self.markers = [] + + self.latest_row_pos = None + self.latest_col_pos = None + + self.latest_row_value = None + self.latest_col_value = None + self.input_fh = open(input_file) + print("!!!!!!!!!!!!!!!!PARSER!!!!!!!!!!!!!!!!!!") + self.haplotype_notation = { + '@mat': "1", + '@pat': "2", + '@het': "-999", + '@unk': "-999" + } + self.configurations = {} + + def process_rows(self): + for self.latest_row_pos, row in enumerate(self.input_fh): + self.latest_row_value = row + # Take care of headers + if not row.strip(): + continue + if row.startswith('#'): + continue + if row.startswith('Chr'): + if 'Mb' in row.split(): + self.mb_exists = True + if 'cM' in row.split(): + self.cm_exists = True + skip = 2 + self.cm_exists + self.mb_exists + self.individuals = row.split()[skip:] + continue + if row.startswith('@'): + key, _separater, value = row.partition(':') + key = key.strip() + value = value.strip() + if key in self.haplotype_notation: + self.configurations[value] = self.haplotype_notation[key] + continue + if not len(self.configurations): + raise EmptyConfigurations + yield row + + def process_csv(self): + for row_count, row in enumerate(self.process_rows()): + row_items = row.split("\t") + + this_marker = Marker() + this_marker.name = row_items[1] + this_marker.chr = row_items[0] + if self.cm_exists and self.mb_exists: + this_marker.cM = row_items[2] + this_marker.Mb = row_items[3] + genotypes = row_items[4:] + elif self.cm_exists: + this_marker.cM = row_items[2] + genotypes = row_items[3:] + elif self.mb_exists: + this_marker.Mb = row_items[2] + genotypes = row_items[3:] + else: + genotypes = row_items[2:] + for item_count, genotype in enumerate(genotypes): + if genotype.upper().strip() in self.configurations: + this_marker.genotypes.append(self.configurations[genotype.upper().strip()]) + else: + print("WARNING:", genotype.upper()) + this_marker.genotypes.append("NA") + self.markers.append(this_marker.__dict__) + diff --git a/wqflask/utility/tools.py b/wqflask/utility/tools.py index b8a41f60..dd8c4a1e 100644 --- a/wqflask/utility/tools.py +++ b/wqflask/utility/tools.py @@ -1,84 +1,137 @@ # Tools/paths finder resolves external paths from settings and/or environment # variables -# -# Currently supported: -# -# PYLMM_PATH finds the root of the git repository of the pylmm_gn2 tool import os import sys from wqflask import app -def get_setting(id,default,guess,get_valid_path): - """ - Resolve a setting from the environment or the global settings in app.config +def get_setting(command_id,guess=None): + """Resolve a setting from the environment or the global settings in + app.config, with get_valid_path is a function checking whether the + path points to an expected directory and returns the full path to + the binary command + + guess = os.environ.get('HOME')+'/pylmm' + get_setting('PYLMM_PATH',guess) + + first tries the environment variable in +id+, next gets the Flask + app setting for the same +id+ and finally does an educated + +guess+. + + In all, the environment overrides the others, next is the flask + setting, then the guess. A valid path to the binary command is + returned. If none is resolved an exception is thrown. + + Note that we do not use the system path. This is on purpose + because it will mess up controlled (reproducible) deployment. The + proper way is to either use the GNU Guix defaults as listed in + etc/default_settings.py or override them yourself by creating a + different settings.py file (or setting the environment). + """ + def value(command): + if command: + sys.stderr.write("Found path "+command+"\n") + return command + else: + return None + # ---- Check whether environment exists - path = get_valid_path(os.environ.get(id)) - # ---- Check whether setting exists - setting = app.config.get(id) - if not path: - path = get_valid_path(setting) - # ---- Check whether default exists - if not path: - path = get_valid_path(default) - # ---- Guess directory - if not path: - if not setting: - setting = guess - path = get_valid_path(guess) - if not path: - raise Exception(id+' '+setting+' path unknown or faulty (update settings.py?). '+id+' should point to the root of the git repository') - - return path - -def pylmm_command(default=None): + sys.stderr.write("Looking for "+command_id+"\n") + command = value(os.environ.get(command_id)) + if not command: + # ---- Check whether setting exists in app + command = value(app.config.get(command_id)) + if not command: + command = value(guess) + if not command: + 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 valid_file(bin): + return bin + return None + +def valid_file(fn): + if os.path.isfile(fn): + return fn + return None + +def valid_path(dir): + if os.path.isdir(dir): + return dir + return None + +def pylmm_command(guess=None): + return valid_bin(get_setting("PYLMM_COMMAND",guess)) + +def gemma_command(guess=None): + return valid_bin(get_setting("GEMMA_COMMAND",guess)) + +def plink_command(guess=None): + return valid_bin(get_setting("PLINK_COMMAND",guess)) + +def flat_files(subdir=None): + base = get_setting("GENENETWORK_FILES") + if subdir: + return assert_dir(base+"/"+subdir) + return assert_dir(base) + +def assert_dir(dir): + if not valid_path(dir): + raise Exception("ERROR: can not find directory "+dir) + return dir + +def mk_dir(dir): + if not valid_path(dir): + os.makedirs(dir) + return assert_dir(dir) + +def locate(name, subdir=None): """ - Return the path to the repository and the python command to call + Locate a static flat file in the GENENETWORK_FILES environment. + + This function throws an error when the file is not found. """ - def get_valid_path(path): - """Test for a valid repository""" - if path: - sys.stderr.write("Trying PYLMM_PATH in "+path+"\n") - if path and os.path.isfile(path+'/pylmm_gn2/lmm.py'): - return path + base = get_setting("GENENETWORK_FILES") + if subdir: + base = base+"/"+subdir + if valid_path(base): + lookfor = base + "/" + name + if valid_file(lookfor): + print("Found: file "+lookfor+"\n") + return lookfor else: - None + raise Exception("Can not locate "+lookfor) + if subdir: sys.stderr.write(subdir) + raise Exception("Can not locate "+name+" in "+base) - guess = os.environ.get('HOME')+'/pylmm_gn2' - path = get_setting('PYLMM_PATH',default,guess,get_valid_path) - pylmm_command = 'python '+path+'/pylmm_gn2/lmm.py' - return path,pylmm_command - -def plink_command(default=None): +def locate_ignore_error(name, subdir=None): """ - Return the path to the repository and the python command to call + Locate a static flat file in the GENENETWORK_FILES environment. + + This function does not throw an error when the file is not found + but returns None. """ - def get_valid_path(path): - """Test for a valid repository""" - if path: - sys.stderr.write("Trying PLINK_PATH in "+path+"\n") - if path and os.path.isfile(path+'/plink'): - return path - else: - None - - guess = os.environ.get('HOME')+'/plink_gemma' - path = get_setting('PLINK_PATH',default,guess,get_valid_path) - plink_command = path+'/plink' - return path,plink_command - -def gemma_command(default=None): - def get_valid_path(path): - """Test for a valid repository""" - if path: - sys.stderr.write("Trying PLINK_PATH in "+path+"\n") - if path and os.path.isfile(path+'/plink'): - return path - else: - None + base = get_setting("GENENETWORK_FILES") + if subdir: + base = base+"/"+subdir + 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 + +def tempdir(): + return valid_path(get_setting("TEMPDIR","/tmp")) - guess = os.environ.get('HOME')+'/plink' - path = get_setting('PLINK_PATH',default,guess,get_valid_path) - gemma_command = path+'/gemma' - return path, gemma_command
\ No newline at end of file + +# Cached values +PYLMM_COMMAND = pylmm_command() +GEMMA_COMMAND = gemma_command() +PLINK_COMMAND = plink_command() +FLAT_FILES = flat_files() +TEMPDIR = tempdir() diff --git a/wqflask/wqflask/correlation/show_corr_results.py b/wqflask/wqflask/correlation/show_corr_results.py index 98596ca4..dd661092 100755 --- a/wqflask/wqflask/correlation/show_corr_results.py +++ b/wqflask/wqflask/correlation/show_corr_results.py @@ -708,13 +708,11 @@ class CorrelationResults(object): for sample in sample_names: if sample not in excluded_samples: - value = start_vars['value:' + sample] - if value.strip().lower() == 'x': - self.sample_data[str(sample)] = None - else: - self.sample_data[str(sample)] = float(value) - - + # print("Looking for",sample,"in",start_vars) + value = start_vars.get('value:' + sample) + if value: + if not value.strip().lower() == 'x': + self.sample_data[str(sample)] = float(value) ##XZ, 12/16/2008: the input geneid is of mouse type #def checkForLitInfo(self,geneId): @@ -942,7 +940,7 @@ 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/ctl/__init__.py b/wqflask/wqflask/ctl/__init__.py new file mode 100755 index 00000000..e69de29b --- /dev/null +++ b/wqflask/wqflask/ctl/__init__.py diff --git a/wqflask/wqflask/ctl/ctl_analysis.py b/wqflask/wqflask/ctl/ctl_analysis.py new file mode 100644 index 00000000..7a42b2f8 --- /dev/null +++ b/wqflask/wqflask/ctl/ctl_analysis.py @@ -0,0 +1,194 @@ +# CTL analysis for GN2 +# Author / Maintainer: Danny Arends <Danny.Arends@gmail.com> +import sys +from numpy import * +import scipy as sp # SciPy +import rpy2.robjects as ro # R Objects +import rpy2.rinterface as ri + +from base.webqtlConfig import GENERATED_IMAGE_DIR +from utility import webqtlUtil # Random number for the image +from utility import genofile_parser # genofile_parser + +import base64 +import array +import csv +import itertools + +from base import data_set +from base import trait as TRAIT + +from utility import helper_functions +from utility.tools import locate + +from rpy2.robjects.packages import importr +utils = importr("utils") + +## Get pointers to some common R functions +r_library = ro.r["library"] # Map the library function +r_options = ro.r["options"] # Map the options function +r_read_csv = ro.r["read.csv"] # Map the read.csv function +r_dim = ro.r["dim"] # Map the dim function +r_c = ro.r["c"] # Map the c function +r_t = ro.r["t"] # Map the t function +r_cat = ro.r["cat"] # Map the cat function +r_paste = ro.r["paste"] # Map the paste function +r_unlist = ro.r["unlist"] # Map the unlist function +r_head = ro.r["head"] # Map the unlist function +r_unique = ro.r["unique"] # Map the unique function +r_length = ro.r["length"] # Map the length function +r_unlist = ro.r["unlist"] # Map the unlist function +r_list = ro.r.list # Map the list function +r_matrix = ro.r.matrix # Map the matrix function +r_seq = ro.r["seq"] # Map the seq function +r_table = ro.r["table"] # Map the table function +r_names = ro.r["names"] # Map the names function +r_sink = ro.r["sink"] # Map the sink function +r_is_NA = ro.r["is.na"] # Map the is.na function +r_file = ro.r["file"] # Map the file function +r_png = ro.r["png"] # Map the png function for plotting +r_dev_off = ro.r["dev.off"] # Map the dev.off function +r_save_image = ro.r["save.image"] # Map the save.image function +r_class = ro.r["class"] # Map the class function +r_save = ro.r["save"] # Map the save function +r_write_table = ro.r["write.table"] # Map the write.table function +r_read_table = ro.r["read.table"] # Map the read.table function +r_as_data_frame = ro.r["as.data.frame"] # Map the write.table function +r_data_frame = ro.r["data.frame"] # Map the write.table function +r_as_numeric = ro.r["as.numeric"] # Map the write.table function + +class CTL(object): + def __init__(self): + print("Initialization of CTL") + #log = r_file("/tmp/genenetwork_ctl.log", open = "wt") + #r_sink(log) # Uncomment the r_sink() commands to log output from stdout/stderr to a file + #r_sink(log, type = "message") + r_library("ctl") # Load CTL - Should only be done once, since it is quite expensive + r_options(stringsAsFactors = False) + print("Initialization of CTL done, package loaded in R session") + self.r_CTLscan = ro.r["CTLscan"] # Map the CTLscan function + self.r_CTLsignificant = ro.r["CTLsignificant"] # Map the CTLsignificant function + self.r_lineplot = ro.r["ctl.lineplot"] # Map the ctl.lineplot function + self.r_CTLsignificant = ro.r["CTLsignificant"] # Map the CTLsignificant function + self.r_CTLnetwork = ro.r["CTLnetwork"] # Map the CTLnetwork function + self.r_CTLprofiles = ro.r["CTLprofiles"] # Map the CTLprofiles function + self.r_plotCTLobject = ro.r["plot.CTLobject"] # Map the CTLsignificant function + print("Obtained pointers to CTL functions") + + def run_analysis(self, requestform): + print("Starting CTL analysis on dataset") + self.trait_db_list = [trait.strip() for trait in requestform['trait_list'].split(',')] + self.trait_db_list = [x for x in self.trait_db_list if x] + + print("strategy:", requestform.get("strategy")) + strategy = requestform.get("strategy") + + print("nperm:", requestform.get("nperm")) + nperm = int(requestform.get("nperm")) + + print("parametric:", requestform.get("parametric")) + parametric = bool(requestform.get("parametric")) + + print("significance:", requestform.get("significance")) + significance = float(requestform.get("significance")) + + # Get the name of the .geno file belonging to the first phenotype + datasetname = self.trait_db_list[0].split(":")[1] + dataset = data_set.create_dataset(datasetname) + + genofilelocation = locate(dataset.group.name + ".geno", "genotype") + parser = genofile_parser.ConvertGenoFile(genofilelocation) + parser.process_csv() + + # Create a genotype matrix + individuals = parser.individuals + markers = [] + markernames = [] + for marker in parser.markers: + markernames.append(marker["name"]) + markers.append(marker["genotypes"]) + + genotypes = list(itertools.chain(*markers)) + print(len(genotypes) / len(individuals), "==", len(parser.markers)) + + rGeno = r_t(ro.r.matrix(r_unlist(genotypes), nrow=len(markernames), ncol=len(individuals), dimnames = r_list(markernames, individuals), byrow=True)) + + # Create a phenotype matrix + traits = [] + for trait in self.trait_db_list: + print("retrieving data for", trait) + if trait != "": + ts = trait.split(':') + gt = TRAIT.GeneralTrait(name = ts[0], dataset_name = ts[1]) + gt.retrieve_sample_data(individuals) + for ind in individuals: + if ind in gt.data.keys(): + traits.append(gt.data[ind].value) + else: + traits.append("-999") + + rPheno = r_t(ro.r.matrix(r_as_numeric(r_unlist(traits)), nrow=len(self.trait_db_list), ncol=len(individuals), dimnames = r_list(self.trait_db_list, individuals), byrow=True)) + + # Use a data frame to store the objects + rPheno = r_data_frame(rPheno) + rGeno = r_data_frame(rGeno) + + # Debug: Print the genotype and phenotype files to disk + #r_write_table(rGeno, "~/outputGN/geno.csv") + #r_write_table(rPheno, "~/outputGN/pheno.csv") + + # Perform the CTL scan + res = self.r_CTLscan(rGeno, rPheno, strategy = strategy, nperm = nperm, parametric = parametric, ncores = 6) + + # Get significant interactions + significant = self.r_CTLsignificant(res, significance = significance) + + # Create an image for output + self.results = {} + self.results['imgurl1'] = webqtlUtil.genRandStr("CTLline_") + ".png" + self.results['imgloc1'] = GENERATED_IMAGE_DIR + self.results['imgurl1'] + + self.results['ctlresult'] = significant + self.results['requestform'] = requestform # Store the user specified parameters for the output page + + # Create the lineplot + r_png(self.results['imgloc1'], width=1000, height=600, type='cairo-png') + self.r_lineplot(res, significance = significance) + r_dev_off() + + n = 2 + for trait in self.trait_db_list: + # Create the QTL like CTL plots + self.results['imgurl' + str(n)] = webqtlUtil.genRandStr("CTL_") + ".png" + self.results['imgloc' + str(n)] = GENERATED_IMAGE_DIR + self.results['imgurl' + str(n)] + r_png(self.results['imgloc' + str(n)], width=1000, height=600, type='cairo-png') + self.r_plotCTLobject(res, (n-1), significance = significance, main='Phenotype ' + trait) + r_dev_off() + n = n + 1 + + # Flush any output from R + sys.stdout.flush() + + def loadImage(self, path, name): + print("pre-loading imgage results:", self.results[path]) + imgfile = open(self.results[path], 'rb') + imgdata = imgfile.read() + imgB64 = imgdata.encode("base64") + bytesarray = array.array('B', imgB64) + self.results[name] = bytesarray + + def render_image(self, results): + self.loadImage("imgloc1", "imgdata1") + n = 2 + for trait in self.trait_db_list: + self.loadImage("imgloc" + str(n), "imgdata" + str(n)) + n = n + 1 + + def process_results(self, results): + print("Processing CTL output") + template_vars = {} + template_vars["results"] = self.results + self.render_image(self.results) + sys.stdout.flush() + return(dict(template_vars)) + diff --git a/wqflask/wqflask/database.py b/wqflask/wqflask/database.py index 159c5d6c..2f544d44 100755 --- a/wqflask/wqflask/database.py +++ b/wqflask/wqflask/database.py @@ -24,8 +24,9 @@ def init_db(): # you will have to import them first before calling init_db() #import yourapplication.models import wqflask.model - print("Creating all..") + print("database.py: Creating all model metadata..") Base.metadata.create_all(bind=engine) - print("Done creating all...") + print("database.py: Done creating all model metadata...") + print("Point your browser at http://localhost:5003/") init_db() diff --git a/wqflask/wqflask/heatmap/heatmap.py b/wqflask/wqflask/heatmap/heatmap.py index 40f518f0..2445b37f 100644 --- a/wqflask/wqflask/heatmap/heatmap.py +++ b/wqflask/wqflask/heatmap/heatmap.py @@ -26,13 +26,12 @@ 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 from utility import Plot, Bunch from utility import temp_data +from utility.tools import PYLMM_COMMAND from MySQLdb import escape_string as escape @@ -214,7 +213,7 @@ class Heatmap(object): #Redis.expire(key, 60*60) #print("before printing command") # - #command = 'python /home/zas1024/gene/wqflask/wqflask/my_pylmm/pyLMM/lmm.py --key {} --species {}'.format(key, + #command = 'python lmm.py --key {} --species {}'.format(key, # "other") #print("command is:", command) #print("after printing command") @@ -273,7 +272,7 @@ class Heatmap(object): Redis.expire(key, 60*60) print("before printing command") - command = 'python /home/zas1024/gene/wqflask/wqflask/my_pylmm/pyLMM/lmm.py --key {} --species {}'.format(key, + command = PYLMM_COMMAND+' --key {} --species {}'.format(key, "other") print("command is:", command) print("after printing command") 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..4c3391e5 100755 --- a/wqflask/wqflask/marker_regression/MarkerRegressionPage.py +++ b/wqflask/wqflask/marker_regression/MarkerRegressionPage.py @@ -72,7 +72,7 @@ class MarkerRegressionPage(templatePage): #automatically generate pheno txt file for PLINK self.genPhenoTxtFileForPlink(phenoFileName=plinkOutputFileName,RISetName=fd.RISet,probesetName=probesetName, valueDict=allTraitValueDict) # os.system full path is required for input and output files; specify missing value is -9999 - plink_command = '%splink/plink --noweb --ped %splink/%s.ped --no-fid --no-parents --no-sex --no-pheno --map %splink/%s.map --pheno %s/%s.txt --pheno-name %s --missing-phenotype -9999 --out %s%s --assoc ' % (webqtlConfig.HTMLPATH, webqtlConfig.HTMLPATH, fd.RISet, webqtlConfig.HTMLPATH, fd.RISet, webqtlConfig.TMPDIR, plinkOutputFileName, probesetName, webqtlConfig.TMPDIR, plinkOutputFileName) + plink_command = '%splink/plink --noweb --ped %splink/%s.ped --no-fid --no-parents --no-sex --no-pheno --map %splink/%s.map --pheno %s/%s.txt --pheno-name %s --missing-phenotype -9999 --out %s%s --assoc ' % (webqtlConfig.GENODIR, webqtlConfig.GENODIR, fd.RISet, webqtlConfig.GENODIR, fd.RISet, webqtlConfig.TMPDIR, plinkOutputFileName, probesetName, webqtlConfig.TMPDIR, plinkOutputFileName) os.system(plink_command) @@ -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: @@ -1597,7 +1597,7 @@ class MarkerRegressionPage(templatePage): # get strain name from ped file in order def getStrainNameFromPedFile(self, RISetName=''): - pedFileopen= open("%splink/%s.ped"%(webqtlConfig.HTMLPATH, RISetName),"r") + pedFileopen= open("%splink/%s.ped"%(webqtlConfig.GENODIR, RISetName),"r") line =pedFileopen.readline() strainNameList=[] diff --git a/wqflask/wqflask/marker_regression/gemma_mapping.py b/wqflask/wqflask/marker_regression/gemma_mapping.py index cfcd4783..caea5802 100644 --- a/wqflask/wqflask/marker_regression/gemma_mapping.py +++ b/wqflask/wqflask/marker_regression/gemma_mapping.py @@ -1,9 +1,7 @@ import os from base import webqtlConfig -from utility.tools import gemma_command - -GEMMA_PATH,GEMMA_COMMAND = gemma_command() +from utility.tools import GEMMA_COMMAND def run_gemma(this_dataset, samples, vals): """Generates p-values for each marker using GEMMA""" @@ -12,8 +10,11 @@ def run_gemma(this_dataset, samples, vals): gen_pheno_txt_file(this_dataset, samples, vals) - os.chdir(GEMMA_PATH) + # Don't do this! + # os.chdir("{}gemma".format(webqtlConfig.GENODIR)) + # use GEMMA_RUN in the next one, create a unique temp file + gemma_command = GEMMA_COMMAND + ' -bfile %s/%s -k %s/output/%s.cXX.txt -lmm 1 -o %s_output' % (GEMMA_PATH, this_dataset.group.name, GEMMA_PATH, @@ -46,4 +47,4 @@ def parse_gemma_output(this_dataset): p_values.append(float(line.split("\t")[10])) #print("p_values: ", p_values) - return included_markers, p_values
\ No newline at end of file + return included_markers, p_values diff --git a/wqflask/wqflask/marker_regression/marker_regression.py b/wqflask/wqflask/marker_regression/marker_regression.py index af320f65..08f422f0 100644 --- a/wqflask/wqflask/marker_regression/marker_regression.py +++ b/wqflask/wqflask/marker_regression/marker_regression.py @@ -30,21 +30,16 @@ from flask import Flask, g from base.trait import GeneralTrait from base import data_set from base import species -from base import webqtlConfig from utility import webqtlUtil from utility import helper_functions from utility import Plot, Bunch from utility import temp_data from utility.benchmark import Bench -from utility.tools import pylmm_command, plink_command, gemma_command from wqflask.marker_regression import gemma_mapping -#from wqflask.marker_regression import qtl_reaper_mapping -#from wqflask.marker_regression import plink_mapping -#from wqflask.marker_regression import rqtl_mapping -PYLMM_PATH,PYLMM_COMMAND = pylmm_command() -PLINK_PATH,PLINK_COMMAND = plink_command() -GEMMA_PATH,GEMMA_COMMAND = gemma_command() +from utility.tools import locate, locate_ignore_error, PYLMM_COMMAND, GEMMA_COMMAND, PLINK_COMMAND +from utility.external import shell +from base.webqtlConfig import TMPDIR, GENERATED_TEXT_DIR class MarkerRegression(object): @@ -68,7 +63,7 @@ class MarkerRegression(object): self.vals.append(value) self.mapping_method = start_vars['method'] - if start_vars['manhattan_plot'] == "true": + if start_vars['manhattan_plot'] == "True": self.manhattan_plot = True else: self.manhattan_plot = False @@ -79,6 +74,8 @@ class MarkerRegression(object): self.pair_scan = False # Initializing this since it is checked in views to determine which template to use self.score_type = "LRS" #ZS: LRS or LOD self.mapping_scale = "physic" + self.num_perm = 0 + self.perm_output = [] self.bootstrap_results = [] #ZS: This is passed to GN1 code for single chr mapping @@ -125,13 +122,14 @@ class MarkerRegression(object): try: if int(start_vars['num_perm']) > 0: self.num_perm = int(start_vars['num_perm']) - else: - self.num_perm = 0 except: self.num_perm = 0 self.LRSCheck = self.score_type - self.permCheck = "ON" + if self.num_perm > 0: + self.permCheck = "ON" + else: + self.permCheck = False self.showSNP = "ON" self.showGenes = "ON" self.viewLegend = "ON" @@ -278,6 +276,8 @@ class MarkerRegression(object): mapping_scale = self.mapping_scale, chromosomes = chromosome_mb_lengths, qtl_results = self.qtl_results, + num_perm = self.num_perm, + perm_results = self.perm_output, ) @@ -299,22 +299,14 @@ class MarkerRegression(object): included_markers, p_values = self.parse_gemma_output() self.dataset.group.get_specified_markers(markers = included_markers) - - #for marker in self.dataset.group.markers.markers: - # if marker['name'] not in included_markers: - # print("marker:", marker) - # self.dataset.group.markers.markers.remove(marker) - # #del self.dataset.group.markers.markers[marker] - self.dataset.group.markers.add_pvalues(p_values) - return self.dataset.group.markers.markers - def parse_gemma_output(self): included_markers = [] p_values = [] - with open("/home/zas1024/gene/web/gemma/output/{}_output.assoc.txt".format(self.dataset.group.name)) as output_file: + # Use a temporary file name here! + with open(webqtlConfig.GENERATED_TEXT_DIR+"/{}_output.assoc.txt".format(self.dataset.group.name)) as output_file: for line in output_file: if line.startswith("chr"): continue @@ -327,37 +319,18 @@ class MarkerRegression(object): def gen_pheno_txt_file(self): """Generates phenotype file for GEMMA""" - - #with open("/home/zas1024/gene/web/gemma/tmp_pheno/{}.txt".format(filename), "w") as outfile: - # for sample, i in enumerate(self.samples): - # print("sample:" + str(i)) - # print("self.vals[i]:" + str(self.vals[sample])) - # outfile.write(str(i) + "\t" + str(self.vals[sample]) + "\n") - - with open("/home/zas1024/gene/web/gemma/{}.fam".format(self.dataset.group.name), "w") as outfile: + with open(webqtlConfig.GENERATED_TEXT_DIR+"{}.fam".format(self.dataset.group.name), "w") as outfile: for i, sample in enumerate(self.samples): outfile.write(str(sample) + " " + str(sample) + " 0 0 0 " + str(self.vals[i]) + "\n") - - #def gen_plink_for_gemma(self, filename): - # - # make_bed = "/home/zas1024/plink/plink --file /home/zas1024/plink/%s --noweb --no-fid --no-parents --no-sex --no-pheno --pheno %s%s.txt --out %s%s --make-bed" % (webqtlConfig.HTMLPATH, - # webqtlConfig.HTMLPATH, - # self.dataset.group.name, - # webqtlConfig.TMPDIR, - # filename, - # webqtlConfig.TMPDIR, - # filename) - # - # def run_rqtl_plink(self): - os.chdir("/home/zas1024/plink") + # os.chdir("") never do this inside a webserver!! output_filename = webqtlUtil.genRandStr("%s_%s_"%(self.dataset.group.name, self.this_trait.name)) self.gen_pheno_txt_file_plink(pheno_filename = output_filename) - rqtl_command = './plink --noweb --ped %s.ped --no-fid --no-parents --no-sex --no-pheno --map %s.map --pheno %s/%s.txt --pheno-name %s --maf %s --missing-phenotype -9999 --out %s%s --assoc ' % (self.dataset.group.name, self.dataset.group.name, webqtlConfig.TMPDIR, plink_output_filename, self.this_trait.name, self.maf, webqtlConfig.TMPDIR, plink_output_filename) + rqtl_command = './plink --noweb --ped %s.ped --no-fid --no-parents --no-sex --no-pheno --map %s.map --pheno %s/%s.txt --pheno-name %s --maf %s --missing-phenotype -9999 --out %s%s --assoc ' % (self.dataset.group.name, self.dataset.group.name, TMPDIR, plink_output_filename, self.this_trait.name, self.maf, TMPDIR, plink_output_filename) os.system(rqtl_command) @@ -414,10 +387,11 @@ class MarkerRegression(object): calc_genoprob = ro.r["calc.genoprob"] # Map the calc.genoprob function read_cross = ro.r["read.cross"] # Map the read.cross function write_cross = ro.r["write.cross"] # Map the write.cross function - GENOtoCSVR = ro.r["GENOtoCSVR"] # Map the GENOtoCSVR function + GENOtoCSVR = ro.r["GENOtoCSVR"] # Map the local GENOtoCSVR function - genofilelocation = webqtlConfig.HTMLPATH + "genotypes/" + self.dataset.group.name + ".geno" - crossfilelocation = webqtlConfig.HTMLPATH + "genotypes/" + self.dataset.group.name + ".cross" + crossname = self.dataset.group.name + genofilelocation = locate(crossname + ".geno", "genotype") + crossfilelocation = TMPDIR + crossname + ".cross" #print("Conversion of geno to cross at location:", genofilelocation, " to ", crossfilelocation) @@ -444,7 +418,7 @@ class MarkerRegression(object): #print("Pair scan results:", result_data_frame) self.pair_scan_filename = webqtlUtil.genRandStr("scantwo_") + ".png" - png(file=webqtlConfig.TMPDIR+self.pair_scan_filename) + png(file=TMPDIR+self.pair_scan_filename) plot(result_data_frame) dev_off() @@ -554,8 +528,8 @@ class MarkerRegression(object): self.gen_pheno_txt_file_plink(pheno_filename = plink_output_filename) - plink_command = PLINK_COMMAND + ' --noweb --bed %s/%s.bed --bim %s/%s.bim --fam %s/%s.fam --no-fid --no-parents --no-sex --no-pheno --pheno %s%s.txt --pheno-name %s --maf %s --missing-phenotype -9999 --out %s%s --assoc ' % (PLINK_PATH, self.dataset.group.name, PLINK_PATH, self.dataset.group.name, PLINK_PATH, self.dataset.group.name, webqtlConfig.TMPDIR, plink_output_filename, self.this_trait.name, self.maf, webqtlConfig.TMPDIR, plink_output_filename) - #print("plink_command:", plink_command) + plink_command = PLINK_COMMAND + ' --noweb --ped %s/%s.ped --no-fid --no-parents --no-sex --no-pheno --map %s/%s.map --pheno %s%s.txt --pheno-name %s --maf %s --missing-phenotype -9999 --out %s%s --assoc ' % (PLINK_PATH, self.dataset.group.name, PLINK_PATH, self.dataset.group.name, TMPDIR, plink_output_filename, self.this_trait.name, self.maf, TMPDIR, plink_output_filename) + print("plink_command:", plink_command) os.system(plink_command) @@ -576,7 +550,7 @@ class MarkerRegression(object): def gen_pheno_txt_file_plink(self, pheno_filename = ''): ped_sample_list = self.get_samples_from_ped_file() - output_file = open("%s%s.txt" % (webqtlConfig.TMPDIR, pheno_filename), "wb") + output_file = open("%s%s.txt" % (TMPDIR, pheno_filename), "wb") header = 'FID\tIID\t%s\n' % self.this_trait.name output_file.write(header) @@ -611,7 +585,7 @@ class MarkerRegression(object): def gen_pheno_txt_file_rqtl(self, pheno_filename = ''): ped_sample_list = self.get_samples_from_ped_file() - output_file = open("%s%s.txt" % (webqtlConfig.TMPDIR, pheno_filename), "wb") + output_file = open("%s%s.txt" % (TMPDIR, pheno_filename), "wb") header = 'FID\tIID\t%s\n' % self.this_trait.name output_file.write(header) @@ -664,6 +638,9 @@ class MarkerRegression(object): def gen_reaper_results(self): genotype = self.dataset.group.read_genotype_file() + if self.manhattan_plot != True: + genotype = genotype.addinterval() + samples, values, variances = self.this_trait.export_informative() trimmed_samples = [] @@ -680,6 +657,7 @@ class MarkerRegression(object): self.perm_output = genotype.permutation(strains = trimmed_samples, trait = trimmed_values, nperm=self.num_perm) self.suggestive = self.perm_output[int(self.num_perm*0.37-1)] self.significant = self.perm_output[int(self.num_perm*0.95-1)] + self.highly_significant = self.perm_output[int(self.num_perm*0.99-1)] self.json_data['suggestive'] = self.suggestive self.json_data['significant'] = self.significant @@ -753,7 +731,7 @@ class MarkerRegression(object): threshold_p_value = 0.01 - result_fp = open("%s%s.qassoc"% (webqtlConfig.TMPDIR, output_filename), "rb") + result_fp = open("%s%s.qassoc"% (TMPDIR, output_filename), "rb") header_line = result_fp.readline()# read header line line = result_fp.readline() @@ -863,9 +841,7 @@ class MarkerRegression(object): Redis.expire(key, 60*60) command = PYLMM_COMMAND+' --key {} --species {}'.format(key,"other") - - os.system(command) - + shell(command) json_results = Redis.blpop("pylmm:results:" + temp_uuid, 45*60) results = json.loads(json_results[1]) @@ -940,12 +916,11 @@ class MarkerRegression(object): Redis.expire(key, 60*60) print("before printing command") - command = PYLMM_COMMAND + ' --key {} --species {}'.format(key, - "other") + command = PYLMM_COMMAND + ' --key {} --species {}'.format(key, "other") print("command is:", command) print("after printing command") - os.system(command) + shell(command) #t_stats, p_values = lmm.run(key) #lmm.run(key) @@ -982,8 +957,7 @@ class MarkerRegression(object): #def gen_human_results(self, pheno_vector, tempdata): def gen_human_results(self, pheno_vector, key, temp_uuid): - file_base = os.path.join(webqtlConfig.PYLMM_PATH, self.dataset.group.name) - print("file_base:", file_base) + file_base = locate(self.dataset.group.name,"mapping") plink_input = input.plink(file_base, type='b') input_file_name = os.path.join(webqtlConfig.SNP_PATH, self.dataset.group.name + ".snps.gz") @@ -1075,7 +1049,11 @@ class MarkerRegression(object): return trimmed_genotype_data def create_snp_iterator_file(group): - plink_file_base = os.path.join(webqtlConfig.PYLMM_PATH, group) + """ + This function is only called by main below + """ + raise Exception("Paths are undefined here") + plink_file_base = os.path.join(TMPDIR, group) plink_input = input.plink(plink_file_base, type='b') data = dict(plink_input = list(plink_input), @@ -1136,5 +1114,3 @@ def get_markers_from_csv(included_markers, p_values, group_name): if __name__ == '__main__': import cPickle as pickle - import gzip - create_snp_iterator_file("HLC") diff --git a/wqflask/wqflask/marker_regression/marker_regression_gn1.py b/wqflask/wqflask/marker_regression/marker_regression_gn1.py index 01303b0f..4460c06d 100644 --- a/wqflask/wqflask/marker_regression/marker_regression_gn1.py +++ b/wqflask/wqflask/marker_regression/marker_regression_gn1.py @@ -38,20 +38,11 @@ from htmlgen import HTMLgen2 as HT from base import webqtlConfig from base.GeneralObject import GeneralObject -#from base.webqtlTrait import webqtlTrait -#from base.templatePage import templatePage from utility import webqtlUtil from utility import helper_functions from utility import Plot -#from utility.THCell import THCell -#from utility.TDCell import TDCell from wqflask.interval_analyst import GeneUtil - -#from dbFunction import webqtlDatabaseFunction - -#import logging -#logging.basicConfig(filename="/tmp/gn_leiyan.log", level=logging.INFO) -#_log = logging.getLogger("gn\web\webqtl\intervalMapping\IntervalMappingPage.py") +from base.webqtlConfig import TMPDIR, GENERATED_TEXT_DIR, GENERATED_IMAGE_DIR ######################################### # Inteval Mapping Plot Page @@ -178,8 +169,8 @@ 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'] @@ -203,9 +194,9 @@ class MarkerRegression(object): # #self.species = webqtlDatabaseFunction.retrieveSpecies(cursor=self.cursor, RISet=fd.RISet) - if self.dataset.species == "rat": + if self.dataset.group.species == "rat": self._ucscDb = "rn3" - elif self.dataset.species == "mouse": + elif self.dataset.group.species == "mouse": self._ucscDb = "mm9" else: self._ucscDb = "" @@ -232,7 +223,7 @@ class MarkerRegression(object): self.significant = start_vars['significant'] else: self.nperm = 0 - + if 'bootCheck' in start_vars.keys(): self.bootChecked = start_vars['bootCheck'] else: @@ -295,7 +286,7 @@ class MarkerRegression(object): self.dominanceChecked = False self.LRS_LOD = start_vars['LRSCheck'] self.cutoff = start_vars['cutoff'] - self.intervalAnalystChecked = False + self.intervalAnalystChecked = True self.draw2X = False if 'additiveCheck' in start_vars.keys(): self.additiveChecked = start_vars['additiveCheck'] @@ -308,7 +299,7 @@ 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 +312,7 @@ 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 +354,7 @@ class MarkerRegression(object): self.ChrList.append((indChr.name, i)) - + self.ChrLengthMbList = g.db.execute(""" Select Length from Chr_Length, InbredSet @@ -514,34 +505,34 @@ class MarkerRegression(object): self.geneCol = None if self.plotScale == 'physic' and self.selectedChr > -1 and (self.intervalAnalystChecked or self.geneChecked): - 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": + 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": self.geneCol = GeneUtil.loadGenes(chrName, self.diffCol, self.startMb, self.endMb, webqtldatabase, "rat") - # - # if self.geneCol and self.intervalAnalystChecked: - # ####################################################################### - # #Nick use GENEID as RefGene to get Literature Correlation Informations# - # #For Interval Mapping, Literature Correlation isn't useful, so skip it# - # #through set GENEID is None # - # ####################################################################### - # - # #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')) - # tableForm.append(geneTableContainer) + if self.geneCol and self.intervalAnalystChecked: + ####################################################################### + #Nick use GENEID as RefGene to get Literature Correlation Informations# + #For Interval Mapping, Literature Correlation isn't useful, so skip it# + #through set GENEID is None # + ####################################################################### + + #GENEID = fd.formdata.getvalue('GeneId') or None + GENEID = None + + geneTableContainer = HT.Div(Id="sortable") #Div to hold table + self.geneTable(self.geneCol, GENEID) + #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')) + #tableForm.append(geneTableContainer) ################################################################ @@ -552,22 +543,22 @@ 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 +588,7 @@ 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 +658,7 @@ class MarkerRegression(object): TD_LR.append(HT.Blockquote(tableForm)) self.body = TD_LR - + #self.dict['body'] = TD_LR #self.dict['title'] = "Mapping" @@ -683,7 +674,7 @@ class MarkerRegression(object): fpText.write("Source: WebQTL, The GeneNetwork (%s)\n" % webqtlConfig.PORTADDR) # - fpText.write("Site: %s\n" % webqtlConfig.SITENAME) + fpText.write("Site: GN\n") fpText.write("Page: Map Viewer\n") fpText.write(time.strftime("Date and Time (US Center): %b %d, %Y at %I.%M %p\n", time.localtime())) fpText.write("Trait ID: %s\n" % self.this_trait.name) @@ -858,7 +849,7 @@ 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 +872,8 @@ 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 +1402,7 @@ 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 +1557,14 @@ 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 @@ -1620,30 +1611,30 @@ 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": + if self.dataset.group.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) else: UCSC_HREF = "http://genome.ucsc.edu/cgi-bin/hgTracks?db=%s&position=chr%s:%d-%d" % (self._ucscDb, self.selectedChr, max(0, calBase-flankingWidthInBases), calBase+flankingWidthInBases) @@ -1651,9 +1642,9 @@ 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": + if self.dataset.group.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) else: ENSEMBL_HREF = "http://www.ensembl.org/Rattus_norvegicus/contigview?chr=%s&start=%d&end=%d" % (self.selectedChr, max(0, calBase-flankingWidthInBases), calBase+flankingWidthInBases) @@ -1766,7 +1757,7 @@ 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 +1800,7 @@ 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 +1868,7 @@ 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 +1881,7 @@ 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 +1894,10 @@ 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 +1914,7 @@ 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 +1944,7 @@ 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 +1967,13 @@ 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 +1988,7 @@ class MarkerRegression(object): #else: # dominanceMax = -1 lrsEdgeWidth = 2 - + if zoom == 2: lrsEdgeWidth = 2 * lrsEdgeWidth @@ -2018,7 +2009,7 @@ 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 +2039,7 @@ 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'] @@ -2061,72 +2052,71 @@ 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]) else: - this_chr = str(self.ChrList[self.selectedChr][1]+1) + this_chr = str(self.ChrList[self.selectedChr][1]+1) if self.selectedChr == -1 or str(qtlresult['chr']) == this_chr: #AdditiveCoordXY = [] #DominanceCoordXY = [] #for k, _locus in enumerate(_chr): - if 1 == 1: - Xc = startPosX + (qtlresult['Mb']-startMb)*plotXScale - #if self.plotScale == 'physic': - #Xc = startPosX + (_locus.Mb-startMb)*plotXScale - #Xc = startPosX + (qtlresult['Mb']-startMb)*plotXScale - #else: - #Xc = startPosX + (_locus.cM-_chr[0].cM)*plotXScale - #Xc = startPosX + (qtlresult['cM']-qtlresult[0]['cM'])*plotXScale - - # updated by NL 06-18-2011: - # fix the over limit LRS graph issue since genotype trait may give infinite LRS; - # for any lrs is over than 460(LRS max in this system), it will be reset to 460 - if 'lrs_value' in qtlresult: - if self.LRS_LOD == "LOD": - if qtlresult['lrs_value'] > 460 or qtlresult['lrs_value']=='inf': - Yc = yZero - webqtlConfig.MAXLRS*LRSHeightThresh/(LRS_LOD_Max*self.LODFACTOR) - else: - Yc = yZero - qtlresult['lrs_value']*LRSHeightThresh/(LRS_LOD_Max*self.LODFACTOR) + Xc = startPosX + (qtlresult['Mb']-startMb)*plotXScale + #if self.plotScale == 'physic': + #Xc = startPosX + (_locus.Mb-startMb)*plotXScale + #Xc = startPosX + (qtlresult['Mb']-startMb)*plotXScale + #else: + #Xc = startPosX + (_locus.cM-_chr[0].cM)*plotXScale + #Xc = startPosX + (qtlresult['cM']-qtlresult[0]['cM'])*plotXScale + + # updated by NL 06-18-2011: + # fix the over limit LRS graph issue since genotype trait may give infinite LRS; + # for any lrs is over than 460(LRS max in this system), it will be reset to 460 + if 'lrs_value' in qtlresult: + if self.LRS_LOD == "LOD": + if qtlresult['lrs_value'] > 460 or qtlresult['lrs_value']=='inf': + Yc = yZero - webqtlConfig.MAXLRS*LRSHeightThresh/(LRS_LOD_Max*self.LODFACTOR) else: - if qtlresult['lrs_value'] > 460 or qtlresult['lrs_value']=='inf': - Yc = yZero - webqtlConfig.MAXLRS*LRSHeightThresh/LRS_LOD_Max - else: - Yc = yZero - qtlresult['lrs_value']*LRSHeightThresh/LRS_LOD_Max + Yc = yZero - qtlresult['lrs_value']*LRSHeightThresh/(LRS_LOD_Max*self.LODFACTOR) else: - if qtlresult['lod_score'] > 100 or qtlresult['lod_score']=='inf': + if qtlresult['lrs_value'] > 460 or qtlresult['lrs_value']=='inf': Yc = yZero - webqtlConfig.MAXLRS*LRSHeightThresh/LRS_LOD_Max else: - if self.LRS_LOD == "LRS": - Yc = yZero - qtlresult['lod_score']*self.LODFACTOR*LRSHeightThresh/LRS_LOD_Max - else: - Yc = yZero - qtlresult['lod_score']*LRSHeightThresh/LRS_LOD_Max - #if qtlresult['lrs_value'] > 460 or qtlresult['lrs_value']=='inf': - #if self.qtlresults[j]['lrs_value'] > 460 or self.qtlresults[j]['lrs_value']=='inf': - # Yc = yZero - webqtlConfig.MAXLRS*LRSHeightThresh/LRS_LOD_Max - #else: - # Yc = yZero - qtlresult['lrs_value']*LRSHeightThresh/LRS_LOD_Max - - if self.manhattan_plot == True: - canvas.drawEllipse(Xc-1, Yc-1, Xc+1, Yc+1, fillColor=pid.black) + Yc = yZero - qtlresult['lrs_value']*LRSHeightThresh/LRS_LOD_Max + else: + if qtlresult['lod_score'] > 100 or qtlresult['lod_score']=='inf': + Yc = yZero - webqtlConfig.MAXLRS*LRSHeightThresh/LRS_LOD_Max else: - LRSCoordXY.append((Xc, Yc)) - - if not self.multipleInterval and self.additiveChecked: - if additiveMax == 0.0: - additiveMax = 0.000001 - Yc = yZero - qtlresult['additive']*AdditiveHeightThresh/additiveMax - AdditiveCoordXY.append((Xc, Yc)) - # if not self.multipleInterval and INTERCROSS and self.additiveChecked: - # Yc = yZero - qtlresult['dominance']*DominanceHeightThresh/dominanceMax - # DominanceCoordXY.append((Xc, Yc)) - m += 1 - #canvas.drawPolygon(LRSCoordXY,edgeColor=thisLRSColor,closed=0, edgeWidth=lrsEdgeWidth, clipX=(xLeftOffset, xLeftOffset + plotWidth)) + if self.LRS_LOD == "LRS": + Yc = yZero - qtlresult['lod_score']*self.LODFACTOR*LRSHeightThresh/LRS_LOD_Max + else: + Yc = yZero - qtlresult['lod_score']*LRSHeightThresh/LRS_LOD_Max + #if qtlresult['lrs_value'] > 460 or qtlresult['lrs_value']=='inf': + #if self.qtlresults[j]['lrs_value'] > 460 or self.qtlresults[j]['lrs_value']=='inf': + # Yc = yZero - webqtlConfig.MAXLRS*LRSHeightThresh/LRS_LOD_Max + #else: + # Yc = yZero - qtlresult['lrs_value']*LRSHeightThresh/LRS_LOD_Max + + if self.manhattan_plot == True: + canvas.drawEllipse(Xc-1, Yc-1, Xc+1, Yc+1, fillColor=pid.black) + else: + LRSCoordXY.append((Xc, Yc)) + + if not self.multipleInterval and self.additiveChecked: + if additiveMax == 0.0: + additiveMax = 0.000001 + Yc = yZero - qtlresult['additive']*AdditiveHeightThresh/additiveMax + AdditiveCoordXY.append((Xc, Yc)) + # if not self.multipleInterval and INTERCROSS and self.additiveChecked: + # Yc = yZero - qtlresult['dominance']*DominanceHeightThresh/dominanceMax + # DominanceCoordXY.append((Xc, Yc)) + m += 1 + #canvas.drawPolygon(LRSCoordXY,edgeColor=thisLRSColor,closed=0, edgeWidth=lrsEdgeWidth, clipX=(xLeftOffset, xLeftOffset + plotWidth)) 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 +2146,7 @@ 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 +2176,7 @@ 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 +2212,7 @@ class MarkerRegression(object): if zoom == 2: fontZoom = 1.5 yTopOffset += 30 - + #calculate plot scale if self.plotScale != 'physic': self.ChrLengthDistList = self.ChrLengthCMList @@ -2589,13 +2579,13 @@ 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') - + myCanvas.save(GENERATED_IMAGE_DIR+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 +2599,9 @@ 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') @@ -2624,124 +2614,152 @@ 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): #SNPLink = 0 #Not sure what this is used for - if self.species == 'mouse' or self.species == 'rat': - - gene_tblobj = {} - gene_tblobj["header"] = self.getGeneTableHeader(refGene=None) - gene_tblobj["body"] = self.getGeneTableBody(geneCol, refGene=None) - - sortby = self.getSortByValue() + if self.dataset.group.species == 'mouse' or self.dataset.group.species == 'rat': + #gene_tblobj = {} + self.gene_table_header = self.getGeneTableHeader(refGene=None) + self.gene_table_body = self.getGeneTableBody(geneCol, refGene=None) + #gene_tblobj["header"] = self.getGeneTableHeader(refGene=None) + #gene_tblobj["body"] = self.getGeneTableBody(geneCol, refGene=None) - filename= webqtlUtil.genRandStr("Mapping_") + #sortby = self.getSortByValue() - objfile = open('%s.obj' % (webqtlConfig.TMPDIR+filename), 'wb') - cPickle.dump(gene_tblobj, objfile) - objfile.close() + #filename= webqtlUtil.genRandStr("Mapping_") - gene_table = webqtlUtil.genTableObj(tblobj=gene_tblobj, file=filename, sortby=sortby, tableID="sortable", addIndex="0") + #objfile = open('%s.obj' % (webqtlConfig.TMPDIR+filename), 'wb') + #cPickle.dump(gene_tblobj, objfile) + #objfile.close() + #gene_table = webqtlUtil.genTableObj(tblobj=gene_tblobj, file=filename, sortby=sortby, tableID="sortable", addIndex="0") else: - gene_table = "" + self.gene_table_header = None + self.gene_table_body = None + #gene_table = "" - return gene_table - - def getLiteratureCorrelation(cursor,geneId1=None,geneId2=None): - if not geneId1 or not geneId2: - return None - if geneId1 == geneId2: - return 1.0 - geneId1 = str(geneId1) - geneId2 = str(geneId2) - lCorr = None - try: - query = 'SELECT Value FROM LCorrRamin3 WHERE GeneId1 = %s and GeneId2 = %s' - for x,y in [(geneId1,geneId2),(geneId2,geneId1)]: - cursor.execute(query,(x,y)) - lCorr = cursor.fetchone() - if lCorr: - lCorr = lCorr[0] - break - except: raise #lCorr = None - return lCorr + #return gene_table def getGeneTableHeader(self, refGene=None): gene_tblobj_header = [] + + gene_table_header_list = [] col_class = "fs14 fwb ffl b1 cw cbrb" - if self.species == "mouse": + if self.dataset.group.species == "mouse": if refGene: - gene_tblobj_header = [[THCell(HT.TD('Index', HT.BR(), HT.BR(), align='left', width=50, Class=col_class), text="index", idx=0), - THCell(HT.TD('Symbol', HT.BR(), HT.BR(), align='left', width=100, Class=col_class), text="symbol", idx=1), - THCell(HT.TD('Mb Start',HT.BR(),'(mm9)', align='left', width=100, Class=col_class), text="mb_start_mm9", idx=2), - THCell(HT.TD('Length (Kb)', HT.BR(), HT.BR(), align='left', width=100, Class=col_class), text="length", idx=3), - THCell(HT.TD('SNP',HT.BR(),'Count', align='left', width=47, Class=col_class), text="snp_count", idx=4), - THCell(HT.TD('SNP',HT.BR(),'Density', align='left', width=78, Class=col_class), text="snp_density", idx=5), - THCell(HT.TD('Avg',HT.BR(),'Expr', HT.BR(), HT.BR(), align='left', width=44, Class=col_class), sort=0, idx=6), - THCell(HT.TD('Human',HT.BR(),'Chr', align='left', width=60, Class=col_class), text="human_chr", idx=7), - THCell(HT.TD('Mb Start',HT.BR(),'(hg19)', align='left', width=100, Class=col_class), text="mb_start_hg19", idx=8), - THCell(HT.TD('Literature',HT.BR(),'Correlation', align='left', width=100, Class=col_class), text="lit_corr", idx=9), - THCell(HT.TD('Gene Description', HT.BR(), HT.BR(), align='left', width=290, Class=col_class), text="description", idx=10), - THCell(HT.TD('PolymiRTS',HT.BR(),'Database', HT.BR(), HT.Href(url='http://compbio.uthsc.edu/miRSNP/', text='>>', target="_blank", Class="normalsize"), - align='left', width=100, Class=col_class), sort=0, idx=11), - THCell(HT.TD('Gene Weaver', HT.BR(), 'Info Content', HT.BR(), HT.Href(url='http://geneweaver.org/', text='>>', target="_blank", Class="normalsize"), - align='left', width=110, Class=col_class), sort=0, idx=12), - ]] + gene_table_header_list = ["Index", + "Symbol", + "Mb Start", + "Length (Kb)", + "SNP Count", + "SNP Density", + "Avg Expr", + "Human Chr", + "Mb Start (hg19)", + "Literature Correlation", + "Gene Description", + "PolymiRTS Database" + HT.Href(url='http://compbio.uthsc.edu/miRSNP/', text='>>', target="_blank").__str__(), + "Gene Weaver Info Content" + HT.Href(url='http://geneweaver.org/', text='>>', target="_blank").__str__()] + + # gene_tblobj_header = [[THCell(HT.TD('Index', HT.BR(), HT.BR(), align='left', width=50, Class=col_class), text="index", idx=0), + # THCell(HT.TD('Symbol', HT.BR(), HT.BR(), align='left', width=100, Class=col_class), text="symbol", idx=1), + # THCell(HT.TD('Mb Start',HT.BR(),'(mm9)', align='left', width=100, Class=col_class), text="mb_start_mm9", idx=2), + # THCell(HT.TD('Length (Kb)', HT.BR(), HT.BR(), align='left', width=100, Class=col_class), text="length", idx=3), + # THCell(HT.TD('SNP',HT.BR(),'Count', align='left', width=47, Class=col_class), text="snp_count", idx=4), + # THCell(HT.TD('SNP',HT.BR(),'Density', align='left', width=78, Class=col_class), text="snp_density", idx=5), + # THCell(HT.TD('Avg',HT.BR(),'Expr', HT.BR(), HT.BR(), align='left', width=44, Class=col_class), sort=0, idx=6), + # THCell(HT.TD('Human',HT.BR(),'Chr', align='left', width=60, Class=col_class), text="human_chr", idx=7), + # THCell(HT.TD('Mb Start',HT.BR(),'(hg19)', align='left', width=100, Class=col_class), text="mb_start_hg19", idx=8), + # THCell(HT.TD('Literature',HT.BR(),'Correlation', align='left', width=100, Class=col_class), text="lit_corr", idx=9), + # THCell(HT.TD('Gene Description', HT.BR(), HT.BR(), align='left', width=290, Class=col_class), text="description", idx=10), + # THCell(HT.TD('PolymiRTS',HT.BR(),'Database', HT.BR(), HT.Href(url='http://compbio.uthsc.edu/miRSNP/', text='>>', target="_blank", Class="normalsize"), + # align='left', width=100, Class=col_class), sort=0, idx=11), + # THCell(HT.TD('Gene Weaver', HT.BR(), 'Info Content', HT.BR(), HT.Href(url='http://geneweaver.org/', text='>>', target="_blank", Class="normalsize"), + # align='left', width=110, Class=col_class), sort=0, idx=12), + # ]] else: - gene_tblobj_header = [[THCell(HT.TD('Index', HT.BR(), HT.BR(), align='left', width=50, Class=col_class), text="index", idx=0), - THCell(HT.TD('Symbol', HT.BR(), HT.BR(), align='left', width=100, Class=col_class), text="symbol", idx=1), - THCell(HT.TD('Mb Start',HT.BR(),'(mm9)', align='left', width=100, Class=col_class), text="mb_start_mm9", idx=2), - THCell(HT.TD('Length (Kb)', HT.BR(), HT.BR(), align='left', width=100, Class=col_class), text="length", idx=3), - THCell(HT.TD('SNP',HT.BR(),'Count', align='left', width=47, Class=col_class), text="snp_count", idx=4), - THCell(HT.TD('SNP',HT.BR(),'Density', align='left', width=78, Class=col_class), text="snp_density", idx=5), - THCell(HT.TD('Avg',HT.BR(),'Expr', HT.BR(), HT.BR(), align='left', width=44, Class=col_class), sort=0, idx=6), - THCell(HT.TD('Human',HT.BR(),'Chr', align='left', width=60, Class=col_class), text="human_chr", idx=7), - THCell(HT.TD('Mb Start',HT.BR(),'(hg19)', align='left', width=100, Class=col_class), text="mb_start_hg19", idx=8), - THCell(HT.TD('Gene Description', HT.BR(), HT.BR(), align='left', width=290, Class=col_class), text="description", idx=9), - THCell(HT.TD('PolymiRTS',HT.BR(),'Database', HT.BR(), HT.Href(url='http://compbio.uthsc.edu/miRSNP/', text='>>', target="_blank", Class="normalsize"), - align='left', width=100, Class=col_class), sort=0, idx=10), - THCell(HT.TD('Gene Weaver', HT.BR(), 'Info Content', HT.BR(), HT.Href(url='http://geneweaver.org/', text='>>', target="_blank", Class="normalsize"), - align='left', width=110, Class=col_class), sort=0, idx=11), - ]] - - elif self.species == "rat": - - gene_tblobj_header = [[THCell(HT.TD('Index', HT.BR(), HT.BR(), align='left', width=50, Class=col_class), text="index", idx=0), - THCell(HT.TD('Symbol', HT.BR(), HT.BR(), align='left', width=100, Class=col_class), text="symbol", idx=1), - THCell(HT.TD('Mb Start',HT.BR(),'(rn3)', align='left', width=100, Class=col_class), text="mb_start_rn3", idx=2), - THCell(HT.TD('Length (Kb)', HT.BR(), HT.BR(), align='left', width=100, Class=col_class), text="length", idx=3), - THCell(HT.TD('Avg',HT.BR(),'Expr', HT.BR(), HT.BR(), align='left', width=44, Class=col_class), sort=0, idx=4), - THCell(HT.TD('Mouse',HT.BR(),'Chr', align='left', width=60, Class=col_class), text="mouse_chr", idx=5), - THCell(HT.TD('Mb Start',HT.BR(),'(mm9)', align='left', width=100, Class=col_class), text="mb_start_mm9", idx=6), - THCell(HT.TD('Human',HT.BR(),'Chr', align='left', width=60, Class=col_class), text="human_chr", idx=7), - THCell(HT.TD('Mb Start',HT.BR(),'(hg19)', align='left', width=100, Class=col_class), text="mb_start_hg19", idx=8), - THCell(HT.TD('Gene Description', HT.BR(), HT.BR(), align='left', Class=col_class), text="description", idx=9)]] + gene_table_header_list = ["", + "Index", + "Symbol", + "Mb Start", + "Length (Kb)", + "SNP Count", + "SNP Density", + "Avg Expr", + "Human Chr", + "Mb Start (hg19)", + "Gene Description", + "PolymiRTS Database" + HT.Href(url='http://compbio.uthsc.edu/miRSNP/', text='>>', target="_blank").__str__(), + "Gene Weaver Info Content" + HT.Href(url='http://geneweaver.org/', text='>>', target="_blank").__str__()] + + # gene_tblobj_header = [[THCell(HT.TD('Index', HT.BR(), HT.BR(), align='left', width=50, Class=col_class), text="index", idx=0), + # THCell(HT.TD('Symbol', HT.BR(), HT.BR(), align='left', width=100, Class=col_class), text="symbol", idx=1), + # THCell(HT.TD('Mb Start',HT.BR(),'(mm9)', align='left', width=100, Class=col_class), text="mb_start_mm9", idx=2), + # THCell(HT.TD('Length (Kb)', HT.BR(), HT.BR(), align='left', width=100, Class=col_class), text="length", idx=3), + # THCell(HT.TD('SNP',HT.BR(),'Count', align='left', width=47, Class=col_class), text="snp_count", idx=4), + # THCell(HT.TD('SNP',HT.BR(),'Density', align='left', width=78, Class=col_class), text="snp_density", idx=5), + # THCell(HT.TD('Avg',HT.BR(),'Expr', HT.BR(), HT.BR(), align='left', width=44, Class=col_class), sort=0, idx=6), + # THCell(HT.TD('Human',HT.BR(),'Chr', align='left', width=60, Class=col_class), text="human_chr", idx=7), + # THCell(HT.TD('Mb Start',HT.BR(),'(hg19)', align='left', width=100, Class=col_class), text="mb_start_hg19", idx=8), + # THCell(HT.TD('Gene Description', HT.BR(), HT.BR(), align='left', width=290, Class=col_class), text="description", idx=9), + # THCell(HT.TD('PolymiRTS',HT.BR(),'Database', HT.BR(), HT.Href(url='http://compbio.uthsc.edu/miRSNP/', text='>>', target="_blank", Class="normalsize"), + # align='left', width=100, Class=col_class), sort=0, idx=10), + # THCell(HT.TD('Gene Weaver', HT.BR(), 'Info Content', HT.BR(), HT.Href(url='http://geneweaver.org/', text='>>', target="_blank", Class="normalsize"), + # align='left', width=110, Class=col_class), sort=0, idx=11), + # ]] + + elif self.dataset.group.species == "rat": + + gene_table_header_list = ["", + "Index", + "Symbol", + "Mb Start", + "Length (Kb)", + "Avg Expr", + "Mouse Chr", + "Mb Start (mm9)", + "Human Chr", + "Mb Start (hg19)", + "Gene Description"] + + # gene_tblobj_header = [[THCell(HT.TD('Index', HT.BR(), HT.BR(), align='left', width=50, Class=col_class), text="index", idx=0), + # THCell(HT.TD('Symbol', HT.BR(), HT.BR(), align='left', width=100, Class=col_class), text="symbol", idx=1), + # THCell(HT.TD('Mb Start',HT.BR(),'(rn3)', align='left', width=100, Class=col_class), text="mb_start_rn3", idx=2), + # THCell(HT.TD('Length (Kb)', HT.BR(), HT.BR(), align='left', width=100, Class=col_class), text="length", idx=3), + # THCell(HT.TD('Avg',HT.BR(),'Expr', HT.BR(), HT.BR(), align='left', width=44, Class=col_class), sort=0, idx=4), + # THCell(HT.TD('Mouse',HT.BR(),'Chr', align='left', width=60, Class=col_class), text="mouse_chr", idx=5), + # THCell(HT.TD('Mb Start',HT.BR(),'(mm9)', align='left', width=100, Class=col_class), text="mb_start_mm9", idx=6), + # THCell(HT.TD('Human',HT.BR(),'Chr', align='left', width=60, Class=col_class), text="human_chr", idx=7), + # THCell(HT.TD('Mb Start',HT.BR(),'(hg19)', align='left', width=100, Class=col_class), text="mb_start_hg19", idx=8), + # THCell(HT.TD('Gene Description', HT.BR(), HT.BR(), align='left', Class=col_class), text="description", idx=9)]] else: pass - return gene_tblobj_header + return gene_table_header_list + #return gene_tblobj_header def getGeneTableBody(self, geneCol, refGene=None): tblobj_body = [] #contains table rows className = "fs13 b1 c222" + + gene_table_body = [] tableIterationsCnt = 0 - if self.species == "mouse": + if self.dataset.group.species == "mouse": # polymiRTS # http://lily.uthsc.edu:8080/20090422_UTHSC_cuiyan/PolymiRTS_CLS?chrom=2&chrom_from=115&chrom_to=125 @@ -2780,8 +2798,8 @@ class MarkerRegression(object): allProbeString = '%s?cmd=sch&gene=%s&alias=1' % (os.path.join(webqtlConfig.CGIDIR, webqtlConfig.SCRIPTFILE), theGO["GeneSymbol"]) if theGO["snpCount"]: - 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.diffCol[0], self.diffCol[1]), + snpString = HT.Href(url="http://genenetwork.org/webqtl/main.py?FormID=snpBrowser&chr=%s&start=%s&end=%s&geneName=%s&s1=%d&s2=%d" % (theGO["Chromosome"], + theGO["TxStart"], theGO["TxEnd"], theGO["GeneSymbol"], self.diffCol[0], self.diffCol[1]), text=theGO["snpCount"], target="_blank", Class="normalsize") else: snpString = 0 @@ -2818,7 +2836,7 @@ class MarkerRegression(object): geneDescription = theGO["GeneDescription"] if len(geneDescription) > 26: geneDescription = geneDescription[:26]+"..." - probeSetSearch = HT.Href(allProbeString, HT.Image("/images/webqtl_search.gif", border=0), target="_blank") + probeSetSearch = HT.Href(allProbeString, ">>", target="_blank") if theGO["snpDensity"] < 0.000001: snpDensityStr = "0" @@ -2845,37 +2863,69 @@ class MarkerRegression(object): literatureCorrelationString = str(self.getLiteratureCorrelation(self.cursor,refGene,theGO['GeneID']) or "N/A") - this_row.append(TDCell(HT.TD(tableIterationsCnt, selectCheck, width=30, align='right', Class=className), tableIterationsCnt, tableIterationsCnt)) - this_row.append(TDCell(HT.TD(HT.Href(geneIdString, theGO["GeneSymbol"], target="_blank"), " ", probeSetSearch, align='right', Class=className), theGO["GeneSymbol"], theGO["GeneSymbol"])) - this_row.append(TDCell(HT.TD(HT.Href(mouseStartString, "%0.6f" % txStart, target="_blank"), align='right', Class=className), str(mouseStartValue), mouseStartValue)) - this_row.append(TDCell(HT.TD(HT.Href("javascript:centerIntervalMapOnRange2('%s', " % theGO["Chromosome"]+str(txStart-tenPercentLength) + ", " + str(txEnd+tenPercentLength) + ", document.changeViewForm)", "%0.3f" % geneLength), align='right', Class=className), "%0.3f" % geneLength, geneLength)) - this_row.append(TDCell(HT.TD(snpString, align='right', Class=className), str(theGO["snpCount"]), theGO["snpCount"])) - this_row.append(TDCell(HT.TD(snpDensityStr, align='right', Class=className), snpDensityStr, theGO["snpDensity"])) - this_row.append(TDCell(HT.TD(avgExpr, align='right', Class=className), "--", "--")) - this_row.append(TDCell(HT.TD(humanChr, align='right', Class=className), humanChr, humanChrSort)) - this_row.append(TDCell(HT.TD(HT.Href(humanStartString, humanStartDisplay, target="_blank"), align='right', Class=className), humanStartDisplay, humanStartValue)) - this_row.append(TDCell(HT.TD(literatureCorrelationString, align='right', Class=className), literatureCorrelationString, literatureCorrelation)) - this_row.append(TDCell(HT.TD(geneDescription, align='right', Class=className), geneDescription, geneDescription)) - this_row.append(TDCell(HT.TD(polymiRTS, align='right', Class=className), "", "")) - this_row.append(TDCell(HT.TD("", align='right', Class=className), "", "")) + this_row = [selectCheck.__str__(), + str(tableIterationsCnt), + HT.Href(geneIdString, theGO["GeneSymbol"], target="_blank").__str__() + " " + probeSetSearch.__str__(), + HT.Href(mouseStartString, "%0.6f" % txStart, target="_blank").__str__(), + HT.Href("javascript:rangeView('%s', %f, %f)" % (str(int(theGO["Chromosome"])-1), txStart-tenPercentLength, txEnd+tenPercentLength), "%0.3f" % geneLength).__str__(), + snpString, + snpDensityStr, + avgExpr, + humanChr, + HT.Href(humanStartString, humanStartDisplay, target="_blank").__str__(), + literatureCorrelationString, + geneDescription, + polymiRTS, + ""] + + # this_row.append(TDCell(HT.TD(tableIterationsCnt, selectCheck, width=30, align='right', Class=className), tableIterationsCnt, tableIterationsCnt)) + # this_row.append(TDCell(HT.TD(HT.Href(geneIdString, theGO["GeneSymbol"], target="_blank"), " ", probeSetSearch, align='right', Class=className), theGO["GeneSymbol"], theGO["GeneSymbol"])) + # this_row.append(TDCell(HT.TD(HT.Href(mouseStartString, "%0.6f" % txStart, target="_blank"), align='right', Class=className), str(mouseStartValue), mouseStartValue)) + # this_row.append(TDCell(HT.TD(HT.Href("javascript:centerIntervalMapOnRange2('%s', " % theGO["Chromosome"]+str(txStart-tenPercentLength) + ", " + str(txEnd+tenPercentLength) + ", document.changeViewForm)", "%0.3f" % geneLength), align='right', Class=className), "%0.3f" % geneLength, geneLength)) + # this_row.append(TDCell(HT.TD(snpString, align='right', Class=className), str(theGO["snpCount"]), theGO["snpCount"])) + # this_row.append(TDCell(HT.TD(snpDensityStr, align='right', Class=className), snpDensityStr, theGO["snpDensity"])) + # this_row.append(TDCell(HT.TD(avgExpr, align='right', Class=className), "--", "--")) + # this_row.append(TDCell(HT.TD(humanChr, align='right', Class=className), humanChr, humanChrSort)) + # this_row.append(TDCell(HT.TD(HT.Href(humanStartString, humanStartDisplay, target="_blank"), align='right', Class=className), humanStartDisplay, humanStartValue)) + # this_row.append(TDCell(HT.TD(literatureCorrelationString, align='right', Class=className), literatureCorrelationString, literatureCorrelation)) + # this_row.append(TDCell(HT.TD(geneDescription, align='right', Class=className), geneDescription, geneDescription)) + # this_row.append(TDCell(HT.TD(polymiRTS, align='right', Class=className), "", "")) + # this_row.append(TDCell(HT.TD("", align='right', Class=className), "", "")) else: - this_row.append(TDCell(HT.TD(tableIterationsCnt, selectCheck, width=30, align='right', Class=className), tableIterationsCnt, tableIterationsCnt)) - this_row.append(TDCell(HT.TD(HT.Href(geneIdString, theGO["GeneSymbol"], target="_blank"), " ", probeSetSearch, align='right', Class=className), theGO["GeneSymbol"], theGO["GeneSymbol"])) - this_row.append(TDCell(HT.TD(HT.Href(mouseStartString, "%0.6f" % txStart, target="_blank"), align='right', Class=className), str(mouseStartValue), mouseStartValue)) - this_row.append(TDCell(HT.TD(HT.Href("javascript:centerIntervalMapOnRange2('%s', " % theGO["Chromosome"]+str(txStart-tenPercentLength) + ", " + str(txEnd+tenPercentLength) + ", document.changeViewForm)", "%0.3f" % geneLength), align='right', Class=className), "%0.3f" % geneLength, geneLength)) - this_row.append(TDCell(HT.TD(snpString, align='right', Class=className), str(theGO["snpCount"]), theGO["snpCount"])) - this_row.append(TDCell(HT.TD(snpDensityStr, align='right', Class=className), snpDensityStr, theGO["snpDensity"])) - this_row.append(TDCell(HT.TD(avgExpr, align='right', Class=className), "--", "--")) - this_row.append(TDCell(HT.TD(humanChr, align='right', Class=className), humanChr, humanChrSort)) - this_row.append(TDCell(HT.TD(HT.Href(humanStartString, humanStartDisplay, target="_blank"), align='right', Class=className), humanStartDisplay, humanStartValue)) - this_row.append(TDCell(HT.TD(geneDescription, align='right', Class=className), geneDescription, geneDescription)) - this_row.append(TDCell(HT.TD(polymiRTS, align='right', Class=className), "", "")) - this_row.append(TDCell(HT.TD("", align='right', Class=className), "", "")) - - tblobj_body.append(this_row) - - elif self.species == 'rat': + + this_row = [selectCheck.__str__(), + str(tableIterationsCnt), + HT.Href(geneIdString, theGO["GeneSymbol"], target="_blank").__str__() + " " + probeSetSearch.__str__(), + HT.Href(mouseStartString, "%0.6f" % txStart, target="_blank").__str__(), + HT.Href("javascript:rangeView('%s', %f, %f)" % (str(int(theGO["Chromosome"])-1), txStart-tenPercentLength, txEnd+tenPercentLength), "%0.3f" % geneLength).__str__(), + snpString, + snpDensityStr, + avgExpr, + humanChr, + HT.Href(humanStartString, humanStartDisplay, target="_blank").__str__(), + geneDescription, + polymiRTS, + ""] + + + # this_row.append(TDCell(HT.TD(tableIterationsCnt, selectCheck, width=30, align='right', Class=className), tableIterationsCnt, tableIterationsCnt)) + # this_row.append(TDCell(HT.TD(HT.Href(geneIdString, theGO["GeneSymbol"], target="_blank"), " ", probeSetSearch, align='right', Class=className), theGO["GeneSymbol"], theGO["GeneSymbol"])) + # this_row.append(TDCell(HT.TD(HT.Href(mouseStartString, "%0.6f" % txStart, target="_blank"), align='right', Class=className), str(mouseStartValue), mouseStartValue)) + # this_row.append(TDCell(HT.TD(HT.Href("javascript:centerIntervalMapOnRange2('%s', " % theGO["Chromosome"]+str(txStart-tenPercentLength) + ", " + str(txEnd+tenPercentLength) + ", document.changeViewForm)", "%0.3f" % geneLength), align='right', Class=className), "%0.3f" % geneLength, geneLength)) + # this_row.append(TDCell(HT.TD(snpString, align='right', Class=className), str(theGO["snpCount"]), theGO["snpCount"])) + # this_row.append(TDCell(HT.TD(snpDensityStr, align='right', Class=className), snpDensityStr, theGO["snpDensity"])) + # this_row.append(TDCell(HT.TD(avgExpr, align='right', Class=className), "--", "--")) + # this_row.append(TDCell(HT.TD(humanChr, align='right', Class=className), humanChr, humanChrSort)) + # this_row.append(TDCell(HT.TD(HT.Href(humanStartString, humanStartDisplay, target="_blank"), align='right', Class=className), humanStartDisplay, humanStartValue)) + # this_row.append(TDCell(HT.TD(geneDescription, align='right', Class=className), geneDescription, geneDescription)) + # this_row.append(TDCell(HT.TD(polymiRTS, align='right', Class=className), "", "")) + # this_row.append(TDCell(HT.TD("", align='right', Class=className), "", "")) + + gene_table_body.append(this_row) + #tblobj_body.append(this_row) + + elif self.dataset.group.species == 'rat': for gIndex, theGO in enumerate(geneCol): @@ -2923,35 +2973,60 @@ class MarkerRegression(object): if geneDesc == "---": geneDesc = "" - """ - if len(geneDesc) > 40: - geneDesc = gene0So apparently Angola prison (which used to be a slave plantation) has a rodeo that they invite the general public to. -The prisoners are not trained before hand -But its cool because its completely voluntary. -And by voluntary, according to HFG when I talked to him, they have a choice between doing it or door number two and "door number 2 is... rather worse than volunteering"Desc[:37] + "..." - """ - - this_row.append(TDCell(HT.TD(gIndex + 1, selectCheck, align='left', Class=className), str(gIndex+1), gIndex+1)) - this_row.append(TDCell(HT.TD(webqtlSearch, geneSymbolNCBI, align='left', Class=className), theGO["GeneSymbol"], theGO["GeneSymbol"])) - this_row.append(TDCell(HT.TD(theGO["TxStart"], align='left', Class=className), theGO["TxStart"], theGO["TxStart"])) - this_row.append(TDCell(HT.TD(HT.Href(geneLengthURL, "%0.3f" % (geneLength*1000.0)), align='left', Class=className), "%0.3f" % (geneLength*1000.0), (geneLength*1000.0))) - this_row.append(TDCell(HT.TD(avgExprVal, align='left', Class=className), "", "")) - this_row.append(TDCell(HT.TD(mouseChr, align='left', Class=className), mouseChr, mouseChr)) - this_row.append(TDCell(HT.TD(mouseTxStart, align='left', Class=className), mouseTxStart, mouseTxStart)) - this_row.append(TDCell(HT.TD(humanChr, align='left', Class=className), humanChr, humanChrSort)) - this_row.append(TDCell(HT.TD(humanTxStart, align='left', Class=className), humanTxStart, humanTxStart)) - this_row.append(TDCell(HT.TD(geneDesc, align='left', Class=className), geneDesc, geneDesc)) - - tblobj_body.append(this_row) + this_row = [selectCheck.__str__(), + str(gIndex+1), + webqtlSearch.__str__() + geneSymbolNCBI, + theGO["TxStart"], + HT.Href(geneLengthURL, "%0.3f" % (geneLength*1000.0)).__str__(), + avgExprVal, + mouseChr, + mouseTxStart, + humanChr, + humanTxStart, + geneDesc] + + + #this_row.append(TDCell(HT.TD(gIndex + 1, selectCheck, align='left', Class=className), str(gIndex+1), gIndex+1)) + #this_row.append(TDCell(HT.TD(webqtlSearch, geneSymbolNCBI, align='left', Class=className), theGO["GeneSymbol"], theGO["GeneSymbol"])) + #this_row.append(TDCell(HT.TD(theGO["TxStart"], align='left', Class=className), theGO["TxStart"], theGO["TxStart"])) + #this_row.append(TDCell(HT.TD(HT.Href(geneLengthURL, "%0.3f" % (geneLength*1000.0)), align='left', Class=className), "%0.3f" % (geneLength*1000.0), (geneLength*1000.0))) + #this_row.append(TDCell(HT.TD(avgExprVal, align='left', Class=className), "", "")) + #this_row.append(TDCell(HT.TD(mouseChr, align='left', Class=className), mouseChr, mouseChr)) + #this_row.append(TDCell(HT.TD(mouseTxStart, align='left', Class=className), mouseTxStart, mouseTxStart)) + #this_row.append(TDCell(HT.TD(humanChr, align='left', Class=className), humanChr, humanChrSort)) + #this_row.append(TDCell(HT.TD(humanTxStart, align='left', Class=className), humanTxStart, humanTxStart)) + #this_row.append(TDCell(HT.TD(geneDesc, align='left', Class=className), geneDesc, geneDesc)) + + gene_table_body.append(this_row) + #tblobj_body.append(this_row) else: pass - return tblobj_body - + return gene_table_body + #return tblobj_body + + def getLiteratureCorrelation(cursor,geneId1=None,geneId2=None): + if not geneId1 or not geneId2: + return None + if geneId1 == geneId2: + return 1.0 + geneId1 = str(geneId1) + geneId2 = str(geneId2) + lCorr = None + try: + query = 'SELECT Value FROM LCorrRamin3 WHERE GeneId1 = %s and GeneId2 = %s' + for x,y in [(geneId1,geneId2),(geneId2,geneId1)]: + cursor.execute(query,(x,y)) + lCorr = cursor.fetchone() + if lCorr: + lCorr = lCorr[0] + break + except: raise #lCorr = None + return lCorr def getSortByValue(self): 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 a57bfffe..9941a4d3 100755 --- a/wqflask/wqflask/search_results.py +++ b/wqflask/wqflask/search_results.py @@ -24,9 +24,8 @@ from flask import Flask, g 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 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 2d4c952a..074c78bf 100755 --- a/wqflask/wqflask/show_trait/show_trait.py +++ b/wqflask/wqflask/show_trait/show_trait.py @@ -16,7 +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 pylmm_command, plink_command from base.trait import GeneralTrait from base import data_set from dbFunction import webqtlDatabaseFunction @@ -24,8 +23,8 @@ from basicStatistics import BasicStatisticsFunctions from pprint import pformat as pf -PYLMM_PATH,PYLMM_COMMAND = pylmm_command() -PLINK_PATH,PLINK_COMMAND = plink_command() +from utility.tools import flat_files +MAPPING_PATH = flat_files("mapping") ############################################### # @@ -34,8 +33,6 @@ PLINK_PATH,PLINK_COMMAND = plink_command() # ############################################## - - class ShowTrait(object): def __init__(self, kw): @@ -153,6 +150,7 @@ class ShowTrait(object): self.trait_table_width = get_trait_table_width(self.sample_groups) js_data = dict(dataset_type = self.dataset.type, + data_scale = self.dataset.data_scale, sample_group_types = self.sample_group_types, sample_lists = sample_lists, attribute_names = self.sample_groups[0].attributes, @@ -162,14 +160,14 @@ 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(PLINK_PATH+"/"+self.dataset.group.name+".bed") and - os.path.isfile(PLINK_PATH+"/"+self.dataset.group.name+".map")): + if (os.path.isfile(MAPPING_PATH+"/"+self.dataset.group.name+".bed") and + os.path.isfile(MAPPING_PATH+"/"+self.dataset.group.name+".map")): return True else: 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 diff --git a/wqflask/wqflask/static/css b/wqflask/wqflask/static/css deleted file mode 120000 index 9d8c2f68..00000000 --- a/wqflask/wqflask/static/css +++ /dev/null @@ -1 +0,0 @@ -../../../web/css
\ No newline at end of file diff --git a/wqflask/wqflask/static/dbdoc/TODO.md b/wqflask/wqflask/static/dbdoc/TODO.md deleted file mode 100644 index c0a8bab7..00000000 --- a/wqflask/wqflask/static/dbdoc/TODO.md +++ /dev/null @@ -1 +0,0 @@ -TODO: Add all database documentation into this folder diff --git a/wqflask/wqflask/static/images b/wqflask/wqflask/static/images deleted file mode 120000 index 12f0f8b5..00000000 --- a/wqflask/wqflask/static/images +++ /dev/null @@ -1 +0,0 @@ -../../../web/images
\ No newline at end of file diff --git a/wqflask/wqflask/static/javascript b/wqflask/wqflask/static/javascript deleted file mode 120000 index 5f58faf4..00000000 --- a/wqflask/wqflask/static/javascript +++ /dev/null @@ -1 +0,0 @@ -../../../web/javascript
\ No newline at end of file diff --git a/wqflask/wqflask/static/new/css/corr_matrix.css b/wqflask/wqflask/static/new/css/corr_matrix.css index 495ca28c..cd2b0a80 100755 --- a/wqflask/wqflask/static/new/css/corr_matrix.css +++ b/wqflask/wqflask/static/new/css/corr_matrix.css @@ -3,7 +3,7 @@ -moz-transform: rotate(-90deg); -ms-transform: rotate(-90deg); -o-transform: rotate(-90deg); - trasnform: rotate(-90deg); + transform: rotate(-90deg); color: #000 font-size: 22px; height: 50px; diff --git a/wqflask/wqflask/static/new/javascript/show_trait.js b/wqflask/wqflask/static/new/javascript/show_trait.js index 9e249c28..2fa77ae0 100644 --- a/wqflask/wqflask/static/new/javascript/show_trait.js +++ b/wqflask/wqflask/static/new/javascript/show_trait.js @@ -296,18 +296,17 @@ }; on_corr_method_change = function() { var corr_method; - console.log("in beginning of on_corr_method_change"); - corr_method = $('select[name=corr_method]').val(); + corr_method = $('select[name=corr_type]').val(); console.log("corr_method is:", corr_method); $('.correlation_desc').hide(); $('#' + corr_method + "_r_desc").show().effect("highlight"); if (corr_method === "lit") { - return $("#corr_sample_method_options").hide(); + return $("#corr_sample_method").hide(); } else { - return $("#corr_sample_method_options").show(); + return $("#corr_sample_method").show(); } }; - $('select[name=corr_method]').change(on_corr_method_change); + $('select[name=corr_type]').change(on_corr_method_change); submit_special = function(url) { $("#trait_data_form").attr("action", url); diff --git a/wqflask/wqflask/templates/base.html b/wqflask/wqflask/templates/base.html index f25bf9f7..b4fdbd8e 100755 --- a/wqflask/wqflask/templates/base.html +++ b/wqflask/wqflask/templates/base.html @@ -151,7 +151,7 @@ <!--</p>--> <ul class="footer-links"> - <li><a href="http://atlas.uthsc.edu/mailman/listinfo/genenetwork" target="_blank">Join the mailing list</a></li> + <li><a href="http://listserv.uthsc.edu/mailman/listinfo/genenetwork-dev">Join the mailing list</a></li> <!--<li><a href="#">Friend us on facebook</a></li>--> <!--<li><a href="#">Follow us on twitter</a></li>--> </ul> diff --git a/wqflask/wqflask/templates/collections/view.html b/wqflask/wqflask/templates/collections/view.html index f92d9984..c1563b9c 100755 --- a/wqflask/wqflask/templates/collections/view.html +++ b/wqflask/wqflask/templates/collections/view.html @@ -55,6 +55,18 @@ <input type="submit" class="btn btn-primary" value="WGCNA Analysis" /> </div> </form> + <form action="/ctl_setup" method="post"> + {% if uc %} + <input type="hidden" name="uc_id" id="uc_id" value="{{ uc.id }}" /> + {% endif %} + <input type="hidden" name="trait_list" id="trait_list" value= " + {% for this_trait in trait_obs %} + {{ this_trait.name }}:{{ this_trait.dataset.name }}, + {% endfor %}" > + <div class="col-xs-2 controls"> + <input type="submit" class="btn btn-primary" value="CTL Analysis" /> + </div> + </form> <form action="/heatmap" method="post"> {% if uc %} <input type="hidden" name="uc_id" id="uc_id" value="{{ uc.id }}" /> diff --git a/wqflask/wqflask/templates/ctl_results.html b/wqflask/wqflask/templates/ctl_results.html new file mode 100644 index 00000000..a5cb1c08 --- /dev/null +++ b/wqflask/wqflask/templates/ctl_results.html @@ -0,0 +1,47 @@ +{% extends "base.html" %} +{% block title %}CTL results{% endblock %} + +{% block content %} <!-- Start of body --> +<div class="container"> + <h1>CTL Results</h1> + {{(request.form['trait_list'].split(',')|length -1)}} phenotypes as input<br> + <h3>Network Figure</h3> + <a href="/tmp/{{ results['imgurl1'] }}"> + <img alt="Embedded Image" src="data:image/png;base64, + {% for elem in results['imgdata1'] -%} + {% print("%c"|format(elem)) %} + {%- endfor %} + " /></a> + <h3>CTL/QTL Plots for individual traits</h3> + {% for r in range(2, (request.form['trait_list'].split(',')|length +1)) %} + <a href="/tmp/{{ results['imgurl' + r|string] }}"> + <img width=100 height=100 alt="Embedded Image" src="data:image/png;base64, + {% for elem in results['imgdata' + r|string] -%} + {% print("%c"|format(elem)) %} + {%- endfor %} + " /></a> + {% endfor %} + <h3>Tabular results</h3> + <table width="80%"> + <tr><th>trait</th><th>marker</th><th>trait</th><th>LOD</th><th>dCor</th></tr> + significant CTL:<br> + {% for r in range(results['ctlresult'][0]|length) %} + <tr> + {% for c in range(results['ctlresult']|length) %} + <td> + {% if c > 2 %} + {{results['ctlresult'][c][r]|float|round(2)}} + {% else %} + {{results['ctlresult'][c][r]}} + {% endif %} + </td> + {% endfor %} + </tr> + {% endfor %} + </table> + + + + +</div> +{% endblock %} diff --git a/wqflask/wqflask/templates/ctl_setup.html b/wqflask/wqflask/templates/ctl_setup.html new file mode 100644 index 00000000..9c0d7bea --- /dev/null +++ b/wqflask/wqflask/templates/ctl_setup.html @@ -0,0 +1,65 @@ +{% extends "base.html" %} +{% block title %}WCGNA analysis{% endblock %} + +{% block content %} <!-- Start of body --> +<div class="container"> + <h1>CTL analysis parameters</h1> + {{(request.form['trait_list'].split(',')|length -1)}} phenotypes as input + +<form action="/ctl_results" method="post" class="form-horizontal"> + <input type="hidden" name="trait_list" id="trait_list" value= "{{request.form['trait_list']}}"> + + <div class="dropdown"> + <label for="Strategy">Strategy</label> + <div class="col-sm-10"> + <select name="strategy" id="strategy"> + <option value="Exact">Exact</option> + <option value="Full">Full</option> + <option value="Pairwise">Pairwise</option> + </select> + </div> + </div> + + <div class="dropdown"> + <label for="Permutations">Number of permutation (Used when strategy is Full or Pairwise)</label> + <div class="col-sm-10"> + <select name="nperm" id="nperm"> + <option value="100">100</option> + <option value="1000" selected="selected">1000</option> + <option value="10000">10000</option> + </select> + </div> + </div> + + <div class="dropdown"> + <label for="Coefficient">Type of correlation coefficient</label> + <div class="col-sm-10"> + <select name="parametric" id="parametric"> + <option value="False">Spearman</option> + <option value="True">Pearson</option> + </select> + </div> + </div> + + + <div class="dropdown"> + <label for="Significance">Significance level</label> + <div class="col-sm-10"> + <select name="significance" id="significance"> + <option value="0.1">0.1</option> + <option value="0.05" selected="selected">0.05</option> + <option value="0.001">0.001</option> + </select> + </div> + </div> + <br> + <div class="form-group"> + <div class="col-sm-10"> + <input type="submit" class="btn btn-primary" value="Run CTL using these settings" /> + </div> + </div> + +</form> + +</div> +{% endblock %} diff --git a/wqflask/wqflask/templates/index_page.html b/wqflask/wqflask/templates/index_page.html index 5d658bc7..5cc15682 100755 --- a/wqflask/wqflask/templates/index_page.html +++ b/wqflask/wqflask/templates/index_page.html @@ -143,7 +143,7 @@ highly expressed genes (15 to 16 log2 units) AND with peak <a href="http://www.genenetwork.org/glossary.html#L" target="_blank">LRS</a> linkage between 23 and 46.</li> - <li><b>RIF=mitochondrial</b> searches RNA databases for <a href="http://www.ncbi.nlm.nih.gov/projects/GeneRIF/GeneRIFhelp.html" target="_blank"> + <li><b>RIF=mitochondrial</b> searches RNA databases for <a href="https://en.wikipedia.org/wiki/GeneRIF" target="_blank"> GeneRIF</a> links.</li> <li><b>WIKI=nicotine</b> searches <a href="http://www.genenetwork.org/webqtl/main.py?FormID=geneWiki" target="_blank"> diff --git a/wqflask/wqflask/templates/marker_regression_gn1.html b/wqflask/wqflask/templates/marker_regression_gn1.html index f3f33fad..978ea55f 100644 --- a/wqflask/wqflask/templates/marker_regression_gn1.html +++ b/wqflask/wqflask/templates/marker_regression_gn1.html @@ -20,8 +20,9 @@ {% endfor %} <input type="hidden" name="maf"> <input type="hidden" name="selected_chr" value="{{ selectedChr }}"> - <input type="hidden" name="manhattan_plot"> + <input type="hidden" name="manhattan_plot" value="{{ manhattan_plot }}"> <input type="hidden" name="num_perm" value="{{ nperm }}"> + <input type="hidden" name="perm_results" value=""> <input type="hidden" name="num_bootstrap" value="{{ nboot }}"> <input type="hidden" name="do_control" value="{{ doControl }}"> <input type="hidden" name="control_marker" value="{{ controlLocus }}"> @@ -117,10 +118,10 @@ <span style="color:red;">*</span> <br> <input type="checkbox" name="showGenes" class="checkbox" style="display: inline; margin-top: 0px;" {% if geneChecked|upper == "ON" %}value="ON" checked{% endif %}> <span style="font-size: 12px;">Gene Track </span> <span style="color:red;">*</span><br> - <input type="checkbox" name="viewLegend" class="checkbox" style="display: inline; margin-top: 0px;" {% if legendChecked|upper == "ON" %}value="ON" checked{% endif %}> <span style="font-size: 12px;">Legend </span><br> {% if plotScale != "morgan" %} - <input type="checkbox" name="haplotypeAnalystCheck" class="checkbox" style="display: inline; margin-top: 0px;" {% if haplotypeAnalystChecked|upper == "ON" %}value="ON" checked{% endif %}> <span style="font-size: 12px;">Haplotype Analyst </span> <span style="color:red;">*</span> + <input type="checkbox" name="haplotypeAnalystCheck" class="checkbox" style="display: inline; margin-top: 0px;" {% if haplotypeAnalystChecked|upper == "ON" %}value="ON" checked{% endif %}> <span style="font-size: 12px;">Haplotype Analyst </span> <span style="color:red;">*</span><br> {% endif %} + <input type="checkbox" name="viewLegend" class="checkbox" style="display: inline; margin-top: 0px;" {% if legendChecked|upper == "ON" %}value="ON" checked{% endif %}> <span style="font-size: 12px;">Legend </span> </div> <div class="col-xs-12" align="center" style="padding: 5px;"> <span style="color:red;">*</span> <span style="font-size: 12px;">only apply to single chromosome physical mapping</span> @@ -143,14 +144,17 @@ <div class="tab-pane active" id="gn1_map"> <div class="qtlcharts"> {{ gifmap|safe }} - <img src="/static/output/{{ filename }}.jpeg" usemap="#WebQTLImageMap"> + <img src="/generated/{{ filename }}.jpeg" usemap="#WebQTLImageMap"> {% if additiveChecked|upper == "ON" %} <br> <span style="white-space: nowrap;">A positive additive coefficient (green line) indicates that {{ dataset.group.parlist[1] }} alleles increase trait values. In contrast, a negative additive coefficient (orange line) indicates that {{ dataset.group.parlist[0] }} alleles increase trait values.</span> {% endif %} - {% if nperm > 0 %} + {% if nperm > 0 and permChecked == "ON" %} <br><br> - <img src="/static/output/{{ perm_filename }}.gif"> + <img src="/generated/{{ perm_filename }}.gif"> + <br><br> + Total of {{ nperm }} permutations <a href="javascript:export_perm_data();" target="_blank" >Download Permutation Results</a> + <br> {% endif %} </div> </div> @@ -165,65 +169,75 @@ </div> </form> - {% if selectedChr == -1 %} <div style="width:48%;"> - <h2> - Results - </h2> - <table id="qtl_results" class="table table-hover table-striped"> - <thead> - <tr> - <th></th> - <th>Index</th> - <th>{{ LRS_LOD }}</th> - <th>Chr</th> - {% if plotScale == "centimorgan" %} - <th>cM</th> - {% else %} - <th>Mb</th> - {% endif %} - <th>Locus</th> - </tr> - </thead> - <tbody> - {% for marker in trimmed_markers %} - <tr> - <td> - <input type="checkbox" name="selectCheck" - class="checkbox edit_sample_checkbox" - value="{{ marker.name }}" checked="checked"> - </td> - <td align="right">{{ loop.index }}</td> - {% if LRS_LOD == "LOD" %} - {% if 'lod_score' in marker %} - <td>{{ '%0.2f' | format(marker.lod_score|float) }}</td> - {% else %} - <td>{{ '%0.2f' | format(marker.lrs_value|float / 4.16) }}</td> - {% endif %} - {% else %} - {% if 'lod_score' in marker %} - <td>{{ '%0.2f' | format(marker.lod_score|float * 4.16) }}</td> - {% else %} - <td>{{ '%0.2f' | format(marker.lrs_value|float) }}</td> - {% endif %} - {% endif %} - <td>{{marker.chr}}</td> - <td>{{ '%0.6f' | format(marker.Mb|float) }}</td> - <td> - {{ marker.name }} - <!--<a href="{{ url_for('show_trait_page', - trait_id = marker.name, - dataset = dataset.name - )}}"> - {{ marker.name }} - </a>--> - </td> - </tr> - {% endfor %} - </tbody> - </table> + {% if selectedChr == -1 %} + <h2>Results</h2> + <table id="qtl_results" class="table table-hover table-striped"> + <thead> + <tr> + <th></th> + <th>Index</th> + <th>{{ LRS_LOD }}</th> + <th>Chr</th> + {% if plotScale == "centimorgan" %} + <th>cM</th> + {% else %} + <th>Mb</th> + {% endif %} + <th>Locus</th> + </tr> + </thead> + <tbody> + {% for marker in trimmed_markers %} + <tr> + <td> + <input type="checkbox" name="selectCheck" + class="checkbox edit_sample_checkbox" + value="{{ marker.name }}" checked="checked"> + </td> + <td align="right">{{ loop.index }}</td> + {% if LRS_LOD == "LOD" %} + {% if 'lod_score' in marker %} + <td>{{ '%0.2f' | format(marker.lod_score|float) }}</td> + {% else %} + <td>{{ '%0.2f' | format(marker.lrs_value|float / 4.16) }}</td> + {% endif %} + {% else %} + {% if 'lod_score' in marker %} + <td>{{ '%0.2f' | format(marker.lod_score|float * 4.16) }}</td> + {% else %} + <td>{{ '%0.2f' | format(marker.lrs_value|float) }}</td> + {% endif %} + {% endif %} + <td>{{marker.chr}}</td> + <td>{{ '%0.6f' | format(marker.Mb|float) }}</td> + <td>{{ marker.name }}</td> + </tr> + {% endfor %} + </tbody> + </table> + {% elif selectedChr > -1 %} + <h2>Interval Analyst</h2> + <table id="interval_analyst" class="table table-hover table-striped"> + <thead> + <tr> + {% for header in gene_table_header %} + <th>{{ header|safe }}</th> + {% endfor %} + </tr> + </thead> + <tbody> + {% for row in gene_table_body %} + <tr> + {% for n in range(row|length) %} + <td>{{ row[n]|safe }}</td> + {% endfor %} + </tr> + {% endfor %} + </tbody> + </table> + {% endif %} </div> - {% endif %} </div> <!-- End of body --> @@ -282,7 +296,20 @@ "scrollCollapse": true, "paging": false } ); - console.timeEnd("Creating table"); + + $('#interval_analyst').dataTable( { + "columnDefs": [ { + "targets": 0, + "sortable": false + }], + "order": [[3, "asc"]], + "sDom": "RZtir", + "iDisplayLength": -1, + "autoWidth": true, + "bDeferRender": true, + "bSortClasses": false, + "paging": false + } ); $('#vector_map_tab').click(function(){ $('div#gn1_map_options').hide(); @@ -315,6 +342,16 @@ return $('#marker_regression_form').submit(); }; + export_perm_data = function() { + var num_perm, perm_data; + num_perm = js_data.num_perm + perm_data = js_data.perm_results + json_perm_data = JSON.stringify(perm_data); + $('input[name=perm_results]').val(json_perm_data); + $('#marker_regression_form').attr('action', '/export_perm_data'); + return $('#marker_regression_form').submit(); + }; + </script> {% endblock %} diff --git a/wqflask/wqflask/templates/show_trait.html b/wqflask/wqflask/templates/show_trait.html index 7429cd5f..64638fc7 100755 --- a/wqflask/wqflask/templates/show_trait.html +++ b/wqflask/wqflask/templates/show_trait.html @@ -254,7 +254,6 @@ } ); {% endif %} - console.log("SAMPLE GROUP TYPES:", js_data.sample_group_types) if (Object.keys(js_data.sample_group_types).length > 1) { $('#stats_table').DataTable( { "columnDefs": [ diff --git a/wqflask/wqflask/templates/show_trait_calculate_correlations.html b/wqflask/wqflask/templates/show_trait_calculate_correlations.html index ed58b32c..80fafa5e 100755 --- a/wqflask/wqflask/templates/show_trait_calculate_correlations.html +++ b/wqflask/wqflask/templates/show_trait_calculate_correlations.html @@ -63,7 +63,7 @@ </div> </div> - <div class="form-group"> + <div id="corr_sample_method" class="form-group"> <label for="corr_sample_method" class="col-xs-1 control-label">Type</label> <div class="col-xs-2 controls"> <select name="corr_sample_method" class="form-control"> @@ -112,30 +112,30 @@ <label for="descriptions" class="col-xs-1 control-label"></label> <div class="col-xs-6 controls"> <span id="sample_r_desc" class="correlation_desc fs12"> - The <a href="/correlationAnnotation.html#sample_r" target="_blank">Sample Correlation</a> + The <a href="http://genenetwork.org/correlationAnnotation.html#genetic_r">Sample Correlation</a> is computed between trait data and any other traits in the sample database selected above. Use - <a href="/glossary.html#Correlations" target="_blank">Spearman + <a href="http://www.genenetwork.org/glossary.html#Correlations">Spearman Rank</a> when the sample size is small (<20) or when there are influential outliers. </span> <span id="lit_r_desc" style="display: none;" class="correlation_desc fs12"> - The <a href="/correlationAnnotation.html" target="_blank">Literature Correlation</a> + The <a href="http://genenetwork.org/correlationAnnotation.html#literatureCorr">Literature Correlation</a> (Lit r) between this gene and all other genes is computed<br> - using the <a href="https://grits.eecs.utk.edu/sgo/sgo.html" target="_blank"> + using the <a href="https://grits.eecs.utk.edu/sgo/sgo.html"> Semantic Gene Organizer</a> and human, rat, and mouse data from PubMed. Values are ranked by Lit r, but Sample r and Tissue r are also displayed.<br> - <a href="/glossary.html#Literature" target="_blank">More on using Lit r</a> + <a href="http://genenetwork.org/glossary.html#Literature">More on using Lit r</a> </span> <span id="tissue_r_desc" style="display: none;" class="correlation_desc fs12"> - The <a href="/webqtl/main.py?FormID=tissueCorrelation" target="_blank">Tissue Correlation</a> + The <a href="http://genenetwork.org/webqtl/main.py?FormID=tissueCorrelation">Tissue Correlation</a> (Tissue r) estimates the similarity of expression of two genes or transcripts across different cells, tissues, or organs - (<a href="/correlationAnnotation.html#tissue_r" target="_blank">glossary</a>). + (<a href="http://genenetwork.org/correlationAnnotation.html#tissueCorr">glossary</a>). Tissue correlations are generated by analyzing expression in multiple samples usually taken from single cases.<br> <strong>Pearson</strong> and <strong>Spearman Rank</strong> correlations have been diff --git a/wqflask/wqflask/templates/show_trait_details.html b/wqflask/wqflask/templates/show_trait_details.html index ccb3b51b..95a3b967 100755 --- a/wqflask/wqflask/templates/show_trait_details.html +++ b/wqflask/wqflask/templates/show_trait_details.html @@ -26,7 +26,7 @@ <tr> <td>Database</td> <td> - <a href="{{ url_for('static', filename='dbdoc/' + dataset.fullname + '.html') }}" target="_blank"> + <a href="http://genenetwork.org/dbdoc/{{ dataset.name }}.html"> {{ dataset.fullname }} </a> </td> diff --git a/wqflask/wqflask/templates/show_trait_mapping_tools.html b/wqflask/wqflask/templates/show_trait_mapping_tools.html index 620a4631..067dfc67 100755 --- a/wqflask/wqflask/templates/show_trait_mapping_tools.html +++ b/wqflask/wqflask/templates/show_trait_mapping_tools.html @@ -66,11 +66,11 @@ <label style="text-align:left;" class="col-xs-12 control-label">Manhattan Plot</label> <div class="col-xs-12 controls"> <label class="radio-inline"> - <input type="radio" name="manhattan_plot_pylmm" value="true"> + <input type="radio" name="manhattan_plot_pylmm" value="True"> Yes </label> <label class="radio-inline"> - <input type="radio" name="manhattan_plot_pylmm" value="false" checked=""> + <input type="radio" name="manhattan_plot_pylmm" value="False" checked=""> No </label> </div> @@ -160,11 +160,11 @@ <label style="text-align:left;" class="col-xs-12 control-label">Manhattan Plot</label> <div class="col-xs-12 controls"> <label class="radio-inline"> - <input type="radio" name="manhattan_plot_rqtl" value="true"> + <input type="radio" name="manhattan_plot_rqtl" value="True"> Yes </label> <label class="radio-inline"> - <input type="radio" name="manhattan_plot_rqtl" value="false" checked=""> + <input type="radio" name="manhattan_plot_rqtl" value="False" checked=""> No </label> </div> @@ -239,14 +239,14 @@ <div class="mapping_method_fields form-group"> - <label style="text-align:left;" class="col-xs-12 control-label">Manhattan Plot</label> + <label style="text-align:left;" class="col-xs-12 control-label">Marker Regr.</label> <div class="col-xs-12 controls"> <label class="radio-inline"> - <input type="radio" name="manhattan_plot_reaper" value="true"> + <input type="radio" name="manhattan_plot_reaper" value="True"> Yes </label> <label class="radio-inline"> - <input type="radio" name="manhattan_plot_reaper" value="false" checked=""> + <input type="radio" name="manhattan_plot_reaper" value="False" checked=""> No </label> </div> diff --git a/wqflask/wqflask/templates/show_trait_statistics.html b/wqflask/wqflask/templates/show_trait_statistics.html index 9c5c94b2..3ee8bdea 100755 --- a/wqflask/wqflask/templates/show_trait_statistics.html +++ b/wqflask/wqflask/templates/show_trait_statistics.html @@ -26,7 +26,7 @@ <div class="tab-content"> <div class="tab-pane active" id="stats_tab"> <div style="padding: 20px" class="form-horizontal"> - <table id="stats_table" style="width: 300px; float: left;" class="table table-hover table-striped"></table> + <table border="1" id="stats_table" style="width: 300px; float: left;" class="table table-hover table-striped cell-border"></table> </div> </div> <div class="tab-pane" id="histogram_tab"> @@ -108,8 +108,8 @@ </div> <div> - More about <a href="http://en.wikipedia.org/wiki/Normal_probability_plot" target="_blank">Normal Probability Plots</a> and more - about interpreting these plots from the <a href="/glossary.html#normal_probability" target="_blank">glossary</a> + More about <a href="http://en.wikipedia.org/wiki/Normal_probability_plot">Normal Probability Plots</a> and more + about interpreting these plots from the <a href="http://genenetwork.org/glossary.html#normal_probability">glossary</a> </div> </div> diff --git a/wqflask/wqflask/templates/wgcna_setup.html b/wqflask/wqflask/templates/wgcna_setup.html index 8ab8c4a0..b4a5730d 100644 --- a/wqflask/wqflask/templates/wgcna_setup.html +++ b/wqflask/wqflask/templates/wgcna_setup.html @@ -17,36 +17,36 @@ {% else %} <form action="/wgcna_results" method="post" class="form-horizontal"> <input type="hidden" name="trait_list" id="trait_list" value= "{{request.form['trait_list']}}"> - <div class="form-group"> + <div class="form-group"> <label for="SoftThresholds"> Soft threshold: </label> <div class="col-sm-10"> <input type="text" class="form-inline" name="SoftThresholds" id="SoftThresholds" value="1,2,3,4,5,6,7,8,9"> </div> </div> - <div class="form-group"> + <div class="form-group"> <label for="MinModuleSize"> Minimum module size: </label> <div class="col-sm-10"> <input type="text" class="form-inline" name="MinModuleSize" id="MinModuleSize" value="30"> </div> </div> - <div class="form-group"> + <div class="form-group"> <label for="TOMtype"> TOMtype: </label> <div class="col-sm-10"> <input type="text" class="form-inline" name="TOMtype" id="TOMtype" value="unsigned"> </div> - </div> - <div class="form-group"> + </div> + <div class="form-group"> <label for="mergeCutHeight"> mergeCutHeight: </label> <div class="col-sm-10"> <input type="text" class="form-inline" name="mergeCutHeight" id="mergeCutHeight" value="0.25"> </div> - </div> - <div class="form-group"> + </div> + <div class="form-group"> <div class="col-sm-10"> <input type="submit" class="btn btn-primary" value="Run WGCNA using these settings" /> </div> - </div> - </form> + </div> + </form> {% endif %} </div> {% endblock %} diff --git a/wqflask/wqflask/views.py b/wqflask/wqflask/views.py index 412491a1..7854b0df 100644 --- a/wqflask/wqflask/views.py +++ b/wqflask/wqflask/views.py @@ -30,7 +30,7 @@ import sqlalchemy from wqflask import app from flask import (render_template, request, make_response, Response, - Flask, g, config, jsonify, redirect, url_for) + Flask, g, config, jsonify, redirect, url_for, send_from_directory) from wqflask import search_results from wqflask import gsearch @@ -49,10 +49,13 @@ from wqflask.correlation_matrix import show_corr_matrix from wqflask.correlation import corr_scatter_plot from wqflask.wgcna import wgcna_analysis +from wqflask.ctl import ctl_analysis from utility import temp_data +from utility.tools import TEMPDIR from base import webqtlFormData +from base.webqtlConfig import GENERATED_IMAGE_DIR from utility.benchmark import Bench from pprint import pformat as pf @@ -97,7 +100,7 @@ def tmp_page(img_path): print("img_path:", img_path) initial_start_vars = request.form print("initial_start_vars:", initial_start_vars) - imgfile = open(webqtlConfig.TMPDIR + img_path, 'rb') + imgfile = open(GENERATED_IMAGE_DIR + img_path, 'rb') imgdata = imgfile.read() imgB64 = imgdata.encode("base64") bytesarray = array.array('B', imgB64) @@ -184,6 +187,10 @@ def docedit(): doc = docs.Docs(request.args['entry']) return render_template("docedit.html", **doc.__dict__) +@app.route('/generated/<filename>') +def generated_file(filename): + return send_from_directory(GENERATED_IMAGE_DIR,filename) + @app.route("/help") def help(): doc = docs.Docs("help") @@ -202,6 +209,18 @@ def wcgna_results(): result = wgcna.process_results(wgcnaA) # After the analysis is finished store the result return render_template("wgcna_results.html", **result) # Display them using the template +@app.route("/ctl_setup", methods=('POST',)) +def ctl_setup(): + print("In ctl, request.form is:", request.form) # We are going to get additional user input for the analysis + return render_template("ctl_setup.html", **request.form) # Display them using the template + +@app.route("/ctl_results", methods=('POST',)) +def ctl_results(): + print("In ctl, request.form is:", request.form) + ctl = ctl_analysis.CTL() # Start R, load the package and pointers and create the analysis + ctlA = ctl.run_analysis(request.form) # Start the analysis, a ctlA object should be a separate long running thread + result = ctl.process_results(ctlA) # After the analysis is finished store the result + return render_template("ctl_results.html", **result) # Display them using the template @app.route("/news") def news_route(): @@ -277,6 +296,29 @@ def export_trait_csv(): return Response(csv_data, mimetype='text/csv', headers={"Content-Disposition":"attachment;filename=sample_data.csv"}) + +@app.route('/export_perm_data', methods=('POST',)) +def export_perm_data(): + """CSV file consisting of the permutation data for the mapping results""" + num_perm = float(request.form['num_perm']) + perm_data = json.loads(request.form['perm_results']) + + buff = StringIO.StringIO() + writer = csv.writer(buff) + writer.writerow(["Suggestive LRS (p=0.63) = " + str(perm_data[int(num_perm*0.37-1)])]) + writer.writerow(["Significant LRS (p=0.05) = " + str(perm_data[int(num_perm*0.95-1)])]) + writer.writerow(["Highly Significant LRS (p=0.01) = " + str(perm_data[int(num_perm*0.99-1)])]) + writer.writerow("") + writer.writerow([str(num_perm) + " Permutations"]) + writer.writerow("") + for item in perm_data: + writer.writerow([item]) + csv_data = buff.getvalue() + buff.close() + + return Response(csv_data, + mimetype='text/csv', + headers={"Content-Disposition":"attachment;filename=perm_data.csv"}) @app.route("/show_trait") def show_trait_page(): @@ -435,7 +477,7 @@ def marker_regression_page(): print("img_path:", img_path) initial_start_vars = request.form print("initial_start_vars:", initial_start_vars) - imgfile = open('/home/zas1024/tmp/' + img_path, 'rb') + imgfile = open(TEMPDIR + '/' + img_path, 'rb') imgdata = imgfile.read() imgB64 = imgdata.encode("base64") bytesarray = array.array('B', imgB64) @@ -464,7 +506,7 @@ def export_pdf(): svg_xml = request.form.get("data", "Invalid data") print("svg_xml:", svg_xml) filename = request.form.get("filename", "interval_map_pdf") - filepath = "/home/zas1024/gene/wqflask/output/"+filename + filepath = GENERATED_IMAGE_DIR+filename pdf_file = cairosvg.svg2pdf(bytestring=svg_xml) response = Response(pdf_file, mimetype="application/pdf") response.headers["Content-Disposition"] = "attachment; filename=%s"%filename diff --git a/wqflask/wqflask/wgcna/wgcna_analysis.py b/wqflask/wqflask/wgcna/wgcna_analysis.py index 9e9f41bc..880a1cb2 100644 --- a/wqflask/wqflask/wgcna/wgcna_analysis.py +++ b/wqflask/wqflask/wgcna/wgcna_analysis.py @@ -6,7 +6,7 @@ import scipy as sp # SciPy import rpy2.robjects as ro # R Objects import rpy2.rinterface as ri -from base import webqtlConfig # For paths and stuff +from base.webqtlConfig import GENERATED_IMAGE_DIR from utility import webqtlUtil # Random number for the image import base64 @@ -127,8 +127,8 @@ class WGCNA(object): # The iconic WCGNA plot of the modules in the hanging tree self.results['imgurl'] = webqtlUtil.genRandStr("WGCNAoutput_") + ".png" - self.results['imgloc'] = webqtlConfig.TMPDIR + self.results['imgurl'] - r_png(self.results['imgloc'], width=1000, height=600) + self.results['imgloc'] = GENERATED_IMAGE_DIR + self.results['imgurl'] + r_png(self.results['imgloc'], width=1000, height=600, type='cairo-png') mergedColors = self.r_labels2colors(network[1]) self.r_plotDendroAndColors(network[5][0], mergedColors, "Module colors", dendroLabels = False, hang = 0.03, addGuide = True, guideHang = 0.05) r_dev_off() |