def process_gaf(self, file, limit, id_map=None, eco_map=None): if self.test_mode: graph = self.testgraph else: graph = self.graph model = Model(graph) geno = Genotype(graph) LOG.info("Processing Gene Associations from %s", file) line_counter = 0 uniprot_hit = 0 uniprot_miss = 0 if '7955' in self.tax_ids: zfin = ZFIN(self.graph_type, self.are_bnodes_skized) if '6239' in self.tax_ids: wbase = WormBase(self.graph_type, self.are_bnodes_skized) with gzip.open(file, 'rb') as csvfile: filereader = csv.reader(io.TextIOWrapper(csvfile, newline=""), delimiter='\t', quotechar='\"') for row in filereader: line_counter += 1 # comments start with exclamation if re.match(r'!', ''.join(row)): continue if len(row) > 17 or len(row) < 15: LOG.warning( "Wrong number of columns %i, expected 15 or 17\n%s", len(row), row) continue if 17 > len(row) >= 15: row += [""] * (17 - len(row)) (dbase, gene_num, gene_symbol, qualifier, go_id, ref, eco_symbol, with_or_from, aspect, gene_name, gene_synonym, object_type, taxon, date, assigned_by, annotation_extension, gene_product_form_id) = row # test for required fields if (dbase == '' or gene_num == '' or gene_symbol == '' or go_id == '' or ref == '' or eco_symbol == '' or aspect == '' or object_type == '' or taxon == '' or date == '' or assigned_by == ''): LOG.error( "Missing required part of annotation on row %d:\n" + '\t'.join(row), line_counter) continue # deal with qualifier NOT, contributes_to, colocalizes_with if re.search(r'NOT', qualifier): continue if dbase in self.localtt: dbase = self.localtt[dbase] uniprotid = None gene_id = None if dbase == 'UniProtKB': if id_map is not None and gene_num in id_map: gene_id = id_map[gene_num] uniprotid = ':'.join((dbase, gene_num)) (dbase, gene_num) = gene_id.split(':') uniprot_hit += 1 else: # LOG.warning( # "UniProt id %s is without a 1:1 mapping to entrez/ensembl", # gene_num) uniprot_miss += 1 continue else: gene_num = gene_num.split(':')[-1] # last gene_id = ':'.join((dbase, gene_num)) if self.test_mode and not (re.match(r'NCBIGene', gene_id) and int(gene_num) in self.test_ids): continue model.addClassToGraph(gene_id, gene_symbol) if gene_name != '': model.addDescription(gene_id, gene_name) if gene_synonym != '': for syn in re.split(r'\|', gene_synonym): model.addSynonym(gene_id, syn.strip()) if re.search(r'\|', taxon): # TODO add annotations with >1 taxon LOG.info(">1 taxon (%s) on line %d. skipping", taxon, line_counter) else: tax_id = re.sub(r'taxon:', 'NCBITaxon:', taxon) geno.addTaxon(tax_id, gene_id) assoc = Assoc(graph, self.name) assoc.set_subject(gene_id) assoc.set_object(go_id) try: eco_id = eco_map[eco_symbol] assoc.add_evidence(eco_id) except KeyError: LOG.error("Evidence code (%s) not mapped", eco_symbol) refs = re.split(r'\|', ref) for ref in refs: ref = ref.strip() if ref != '': prefix = ref.split(':')[0] # sidestep 'MGI:MGI:' if prefix in self.localtt: prefix = self.localtt[prefix] ref = ':'.join((prefix, ref.split(':')[-1])) refg = Reference(graph, ref) if prefix == 'PMID': ref_type = self.globaltt['journal article'] refg.setType(ref_type) refg.addRefToGraph() assoc.add_source(ref) # TODO add the source of the annotations from assigned by? rel = self.resolve(aspect, mandatory=False) if rel is not None and aspect == rel: if aspect == 'F' and re.search(r'contributes_to', qualifier): assoc.set_relationship(self.globaltt['contributes to']) else: LOG.error( "Aspect: %s with qualifier: %s is not recognized", aspect, qualifier) elif rel is not None: assoc.set_relationship(rel) assoc.add_association_to_graph() else: LOG.warning("No predicate for association \n%s\n", str(assoc)) if uniprotid is not None: assoc.set_description('Mapped from ' + uniprotid) # object_type should be one of: # protein_complex; protein; transcript; ncRNA; rRNA; tRNA; # snRNA; snoRNA; any subtype of ncRNA in the Sequence Ontology. # If the precise product type is unknown, # gene_product should be used ####################################################################### # Derive G2P Associations from IMP annotations # in version 2.1 Pipe will indicate 'OR' # and Comma will indicate 'AND'. # in version 2.0, multiple values are separated by pipes # where the pipe has been used to mean 'AND' if eco_symbol == 'IMP' and with_or_from != '': withitems = re.split(r'\|', with_or_from) phenotypeid = go_id + 'PHENOTYPE' # create phenotype associations for i in withitems: if i == '' or re.match( r'(UniProtKB|WBPhenotype|InterPro|HGNC)', i): LOG.warning( "Don't know what having a uniprot id " + "in the 'with' column means of %s", uniprotid) continue i = re.sub(r'MGI\:MGI\:', 'MGI:', i) i = re.sub(r'WB:', 'WormBase:', i) # for worms and fish, they might give a RNAi or MORPH # in these cases make a reagent-targeted gene if re.search('MRPHLNO|CRISPR|TALEN', i): targeted_gene_id = zfin.make_targeted_gene_id( gene_id, i) geno.addReagentTargetedGene( i, gene_id, targeted_gene_id) # TODO PYLINT why is this needed? # Redefinition of assoc type from # dipper.models.assoc.Association.Assoc to # dipper.models.assoc.G2PAssoc.G2PAssoc assoc = G2PAssoc(graph, self.name, targeted_gene_id, phenotypeid) elif re.search(r'WBRNAi', i): targeted_gene_id = wbase.make_reagent_targeted_gene_id( gene_id, i) geno.addReagentTargetedGene( i, gene_id, targeted_gene_id) assoc = G2PAssoc(graph, self.name, targeted_gene_id, phenotypeid) else: assoc = G2PAssoc(graph, self.name, i, phenotypeid) for ref in refs: ref = ref.strip() if ref != '': prefix = ref.split(':')[0] if prefix in self.localtt: prefix = self.localtt[prefix] ref = ':'.join((prefix, ref.split(':')[-1])) assoc.add_source(ref) # experimental phenotypic evidence assoc.add_evidence(self.globaltt[ 'experimental phenotypic evidence']) assoc.add_association_to_graph() # TODO should the G2PAssoc be # the evidence for the GO assoc? if not self.test_mode and limit is not None and line_counter > limit: break uniprot_tot = (uniprot_hit + uniprot_miss) uniprot_per = 0.0 if uniprot_tot != 0: uniprot_per = 100.0 * uniprot_hit / uniprot_tot LOG.info( "Uniprot: %.2f%% of %i benefited from the 1/4 day id mapping download", uniprot_per, uniprot_tot) return
def process_allele_phenotype(self, limit=None): """ This file compactly lists variant to phenotype associations, such that in a single row, there may be >1 variant listed per phenotype and paper. This indicates that each variant is individually assocated with the given phenotype, as listed in 1+ papers. (Not that the combination of variants is producing the phenotype.) :param limit: :return: """ raw = '/'.join((self.rawdir, self.files['allele_pheno']['file'])) if self.testMode: g = self.testgraph else: g = self.graph logger.info("Processing Allele phenotype associations") line_counter = 0 geno = Genotype(g) with open(raw, 'r') as csvfile: filereader = csv.reader(csvfile, delimiter='\t', quotechar='\"') for row in filereader: if re.match(r'!', ''.join(row)): # header continue line_counter += 1 (db, gene_num, gene_symbol, is_not, phenotype_id, ref, eco_symbol, with_or_from, aspect, gene_name, gene_synonym, gene_class, taxon, date, assigned_by, blank, blank2) = row if self.testMode and gene_num not in self.test_ids['gene']: continue # TODO add NOT phenotypes if is_not == 'NOT': continue eco_id = None if eco_symbol == 'IMP': eco_id = 'ECO:0000015' elif eco_symbol.strip() != '': logger.warning("Encountered an ECO code we don't have: %s", eco_symbol) # according to the GOA spec, persons are not allowed to be # in the reference column, therefore they the variant and # persons are swapped between the reference and with column. # we unswitch them here. temp_var = temp_ref = None if re.search(r'WBVar|WBRNAi', ref): temp_var = ref # move the paper from the with column into the ref if re.search(r'WBPerson', with_or_from): temp_ref = with_or_from if temp_var is not None or temp_ref is not None: with_or_from = temp_var ref = temp_ref allele_list = re.split(r'\|', with_or_from) if len(allele_list) == 0: logger.error( "Missing alleles from phenotype assoc at line %d", line_counter) continue else: for a in allele_list: allele_num = re.sub(r'WB:', '', a.strip()) allele_id = 'WormBase:' + allele_num gene_id = 'WormBase:' + gene_num if re.search(r'WBRNAi', allele_id): # make the reagent-targeted gene, # & annotate that instead of the RNAi item directly rnai_num = re.sub(r'WormBase:', '', allele_id) rnai_id = allele_id rtg_id = self.make_reagent_targeted_gene_id( gene_num, rnai_num) geno.addReagentTargetedGene( rnai_id, 'WormBase:' + gene_num, rtg_id) geno.addGeneTargetingReagent( rnai_id, None, geno.genoparts['RNAi_reagent'], gene_id) allele_id = rtg_id elif re.search(r'WBVar', allele_id): # this may become deprecated by using wormmine # make the allele to gene relationship # the WBVars are really sequence alterations # the public name will come from elsewhere geno.addSequenceAlteration(allele_id, None) vl_id = '_:' + '-'.join((gene_num, allele_num)) geno.addSequenceAlterationToVariantLocus( allele_id, vl_id) geno.addAlleleOfGene(vl_id, gene_id) else: logger.warning( "Some kind of allele I don't recognize: %s", allele_num) continue assoc = G2PAssoc(g, self.name, allele_id, phenotype_id) if eco_id is not None: assoc.add_evidence(eco_id) if ref is not None and ref != '': ref = re.sub(r'(WB:|WB_REF:)', 'WormBase:', ref) reference = Reference(g, ref) if re.search(r'Person', ref): reference.setType( reference.ref_types['person']) # also add # inferred from background scientific knowledge assoc.add_evidence('ECO:0000001') reference.addRefToGraph() assoc.add_source(ref) assoc.add_association_to_graph() # finish looping through all alleles if not self.testMode \ and limit is not None and line_counter > limit: break return
def process_allele_phenotype(self, limit=None): """ This file compactly lists variant to phenotype associations, such that in a single row, there may be >1 variant listed per phenotype and paper. This indicates that each variant is individually assocated with the given phenotype, as listed in 1+ papers. (Not that the combination of variants is producing the phenotype.) :param limit: :return: """ raw = '/'.join((self.rawdir, self.files['allele_pheno']['file'])) if self.testMode: g = self.testgraph else: g = self.graph # gu = GraphUtils(curie_map.get()) # TODO unused logger.info("Processing Allele phenotype associations") line_counter = 0 geno = Genotype(g) with open(raw, 'r') as csvfile: filereader = csv.reader(csvfile, delimiter='\t', quotechar='\"') for row in filereader: if re.match(r'!', ''.join(row)): # header continue line_counter += 1 (db, gene_num, gene_symbol, is_not, phenotype_id, ref, eco_symbol, with_or_from, aspect, gene_name, gene_synonym, gene_class, taxon, date, assigned_by, blank, blank2) = row if self.testMode and gene_num not in self.test_ids['gene']: continue # TODO add NOT phenotypes if is_not == 'NOT': continue eco_id = None if eco_symbol == 'IMP': eco_id = 'ECO:0000015' elif eco_symbol.strip() != '': logger.warning( "Encountered an ECO code we don't have: %s", eco_symbol) # according to the GOA spec, persons are not allowed to be # in the reference column, therefore they the variant and # persons are swapped between the reference and with column. # we unswitch them here. temp_var = temp_ref = None if re.search(r'WBVar|WBRNAi', ref): temp_var = ref # move the paper from the with column into the ref if re.search(r'WBPerson', with_or_from): temp_ref = with_or_from if temp_var is not None or temp_ref is not None: with_or_from = temp_var ref = temp_ref allele_list = re.split(r'\|', with_or_from) if len(allele_list) == 0: logger.error( "Missing alleles from phenotype assoc at line %d", line_counter) continue else: for a in allele_list: allele_num = re.sub(r'WB:', '', a.strip()) allele_id = 'WormBase:'+allele_num gene_id = 'WormBase:'+gene_num if re.search(r'WBRNAi', allele_id): # make the reagent-targeted gene, # & annotate that instead of the RNAi item directly rnai_num = re.sub(r'WormBase:', '', allele_id) rnai_id = allele_id rtg_id = self.make_reagent_targeted_gene_id( gene_num, rnai_num, self.nobnodes) geno.addReagentTargetedGene( rnai_id, 'WormBase:'+gene_num, rtg_id) geno.addGeneTargetingReagent( rnai_id, None, geno.genoparts['RNAi_reagent'], gene_id) allele_id = rtg_id elif re.search(r'WBVar', allele_id): # this may become deprecated by using wormmine # make the allele to gene relationship # the WBVars are really sequence alterations # the public name will come from elsewhere geno.addSequenceAlteration(allele_id, None) vl_id = '_'+'-'.join((gene_num, allele_num)) if self.nobnodes: vl_id = ':'+vl_id geno.addSequenceAlterationToVariantLocus( allele_id, vl_id) geno.addAlleleOfGene(vl_id, gene_id) else: logger.warning( "Some kind of allele I don't recognize: %s", allele_num) continue assoc = G2PAssoc(self.name, allele_id, phenotype_id) if eco_id is not None: assoc.add_evidence(eco_id) if ref is not None and ref != '': ref = re.sub(r'(WB:|WB_REF:)', 'WormBase:', ref) r = Reference(ref) if re.search(r'Person', ref): r.setType(r.ref_types['person']) # also add # inferred from background scientific knowledge assoc.add_evidence('ECO:0000001') r.addRefToGraph(g) assoc.add_source(ref) assoc.add_association_to_graph(g) # finish looping through all alleles if not self.testMode \ and limit is not None and line_counter > limit: break return
def process_allele_phenotype(self, limit=None): """ This file compactly lists variant to phenotype associations, such that in a single row, there may be >1 variant listed per phenotype and paper. This indicates that each variant is individually assocated with the given phenotype, as listed in 1+ papers. (Not that the combination of variants is producing the phenotype.) :param limit: :return: """ src_key = 'allele_pheno' raw = '/'.join((self.rawdir, self.files[src_key]['file'])) col = self.files[src_key]['columns'] graph = self.graph model = Model(self.graph) LOG.info("Processing Allele phenotype associations") geno = Genotype(graph) with open(raw, 'r') as csvfile: reader = csv.reader(csvfile, delimiter='\t', quotechar='\"') row = next(reader) if row[0] != '!gaf-version: 2.0': LOG.error('Not a vlaid gaf v2.0 formatted file: %s', raw) # raise for row in reader: if row[0][0] == '!': continue # db = row[col.index('DB')] gene_num = row[col.index('DB Object ID')] # gene_symbol = row[col.index('DB Object Symbol')] is_not = row[col.index('Qualifier')] phenotype_id = row[col.index('GO ID')] ref = row[col.index('DB:Reference (|DB:Reference)')].strip() eco_symbol = row[col.index('Evidence Code')] with_or_from = row[col.index('With (or) From')] # aspect = row[col.index('Aspect')] # gene_name = row[col.index('DB Object Name')] # gene_synonym = row[col.index('DB Object Synonym (|Synonym)')] # gene_class = row[col.index('DB Object Type')] # taxon = row[col.index('Taxon(|taxon)')] # date = row[col.index('Date')] # assigned_by = row[col.index('Assigned By')] # blank = row[col.index('Annotation Extension')] # blank2 = row[col.index('Gene Product Form ID')] # TODO add NOT phenotypes if is_not == 'NOT': continue eco_symbol = eco_symbol.strip() eco_curie = None if eco_symbol.strip() != '' and eco_symbol in self.gaf_eco: eco_curie = self.gaf_eco[eco_symbol] else: LOG.warning( 'Evidence code %s is not found in the (gaf) gaf_eco', eco_symbol) # according to the GOA spec, persons are not allowed to be # in the reference column, therefore they the variant and # persons are swapped between the reference and with column. # we unswitch them here. temp_var = temp_ref = None if re.search(r'WBVar|WBRNAi', ref): temp_var = ref # move the paper from the with column into the ref if re.search(r'WBPerson', with_or_from): temp_ref = with_or_from if temp_var is not None or temp_ref is not None: with_or_from = temp_var ref = temp_ref allele_list = re.split(r'\|', with_or_from) if len(allele_list) == 0: LOG.error( "Missing alleles from phenotype assoc at line %d", reader.line_num) continue else: for allele in allele_list: allele_num = re.sub(r'WB:', '', allele.strip()) allele_id = 'WormBase:' + allele_num gene_id = 'WormBase:' + gene_num if re.search(r'WBRNAi', allele_id): # @kshefchek - removing this blank node # in favor of simpler modeling # make the WormBase:WBRNAi* id # a self.globaltt['reagent_targeted_gene'], and attach # phenotype to this ID # Previous model - make a bnode reagent-targeted gene, # & annotate that instead of the RNAi item directly # rnai_num = re.sub(r'WormBase:', '', allele_id) # rnai_id = allele_id # rtg_id = self.make_reagent_targeted_gene_id( # gene_num, rnai_num) # geno.addReagentTargetedGene( # rnai_id, 'WormBase:' + gene_num, rtg_id) # allele_id = rtg_id # Could type the IRI as both the reagant and reagant # targeted gene but not sure if this needed # geno.addGeneTargetingReagent( # allele_id, None, self.globaltt['RNAi_reagent'], gene_id) model.addIndividualToGraph( allele_id, None, self.globaltt['reagent_targeted_gene']) self.graph.addTriple( allele_id, self.globaltt['is_expression_variant_of'], gene_id) elif re.search(r'WBVar', allele_id): # this may become deprecated by using wormmine # make the allele to gene relationship # the WBVars are really sequence alterations # the public name will come from elsewhere # @kshefchek - removing this blank node # in favor of simpler modeling, treat variant # like an allele # vl_id = '_:'+'-'.join((gene_num, allele_num)) # geno.addSequenceAlterationToVariantLocus( # allele_id, vl_id) # geno.addAlleleOfGene(vl_id, gene_id) geno.addSequenceAlteration(allele_id, None) geno.addAlleleOfGene(allele_id, gene_id) else: LOG.warning( "Some kind of allele I don't recognize: %s", allele_num) continue assoc = G2PAssoc(graph, self.name, allele_id, phenotype_id) if eco_curie is not None: assoc.add_evidence(eco_curie) if ref is not None and ref != '': ref = re.sub(r'(WB:|WB_REF:)', 'WormBase:', ref) reference = Reference(graph, ref) if re.search(r'Person', ref): reference.setType(self.globaltt['person']) assoc.add_evidence(self.globaltt[ 'inference from background scientific knowledge'] ) reference.addRefToGraph() assoc.add_source(ref) assoc.add_association_to_graph() # finish looping through all alleles if limit is not None and reader.line_num > limit: break
def _process_data(self, source, limit=None): """ This function will process the data files from Coriell. We make the assumption that any alleles listed are variants (alternates to w.t.) Triples: (examples) :NIGMSrepository a CLO_0000008 #repository label : NIGMS Human Genetic Cell Repository foaf:page https://catalog.coriell.org/0/sections/collections/NIGMS/?SsId=8 line_id a CL_0000057, #fibroblast line derives_from patient_id part_of :NIGMSrepository RO:model_of OMIM:disease_id patient id a foaf:person, label: "fibroblast from patient 12345 with disease X" member_of family_id #what is the right thing here? SIO:race EFO:caucasian #subclass of EFO:0001799 in_taxon NCBITaxon:9606 dc:description Literal(remark) RO:has_phenotype OMIM:disease_id GENO:has_genotype genotype_id family_id a owl:NamedIndividual foaf:page "https://catalog.coriell.org/0/Sections/BrowseCatalog/FamilyTypeSubDetail.aspx?PgId=402&fam=2104&coll=GM" genotype_id a intrinsic_genotype GENO:has_alternate_part allelic_variant_id we don't necessarily know much about the genotype, other than the allelic variant. also there's the sex here pub_id mentions cell_line_id :param raw: :param limit: :return: """ raw = '/'.join((self.rawdir, self.files[source]['file'])) LOG.info("Processing Data from %s", raw) if self.testMode: # set the graph to build graph = self.testgraph else: graph = self.graph family = Family(graph) model = Model(graph) line_counter = 1 geno = Genotype(graph) diputil = DipperUtil() col = self.files[source]['columns'] # affords access with # x = row[col.index('x')].strip() with open(raw, 'r', encoding="iso-8859-1") as csvfile: filereader = csv.reader(csvfile, delimiter=',', quotechar=r'"') # we can keep a close watch on changing file formats fileheader = next(filereader, None) fileheader = [c.lower() for c in fileheader] if col != fileheader: # assert LOG.error('Expected %s to have columns: %s', raw, col) LOG.error('But Found %s to have columns: %s', raw, fileheader) raise AssertionError('Incomming data headers have changed.') for row in filereader: line_counter += 1 if len(row) != len(col): LOG.warning('Expected %i values but find %i in row %i', len(col), len(row), line_counter) continue # (catalog_id, description, omim_number, sample_type, # cell_line_available, dna_in_stock, dna_ref, gender, age, # race, ethnicity, affected, karyotype, relprob, mutation, # gene, family_id, collection, url, cat_remark, pubmed_ids, # family_member, variant_id, dbsnp_id, species) = row # example: # GM00003,HURLER SYNDROME,607014,Fibroblast,Yes,No, # ,Female,26 YR,Caucasian,,,, # parent,,,39,NIGMS Human Genetic Cell Repository, # http://ccr.coriell.org/Sections/Search/Sample_Detail.aspx?Ref=GM00003, # 46;XX; clinically normal mother of a child with Hurler syndrome; # proband not in Repository,, # 2,,18343,H**o sapiens catalog_id = row[col.index('catalog_id')].strip() if self.testMode and catalog_id not in self.test_lines: # skip rows not in our test lines, when in test mode continue # ########### BUILD REQUIRED VARIABLES ########### # Make the cell line ID cell_line_id = 'Coriell:' + catalog_id # Map the cell/sample type cell_type = self.resolve(row[col.index('sample_type')].strip()) # on fail cell_type = self.globaltt['cell'] ? # Make a cell line label collection = row[col.index('collection')].strip() line_label = collection.partition(' ')[0] + '-' + catalog_id # Map the repository/collection repository = self.localtt[collection] # patients are uniquely identified by one of: # dbsnp id (which is == an individual haplotype) # family id + family member (if present) OR # probands are usually family member zero # cell line id # since some patients have >1 cell line derived from them, # we must make sure that the genotype is attached to # the patient, and can be inferred to the cell line # examples of repeated patients are: # famid=1159, member=1; fam=152,member=1 # Make the patient ID # make an anonymous patient patient_id = '_:person' fam_id = row[col.index('fam')].strip() fammember = row[col.index('fammember')].strip() if fam_id != '': patient_id = '-'.join((patient_id, fam_id, fammember)) else: # make an anonymous patient patient_id = '-'.join((patient_id, catalog_id)) # properties of the individual patients: sex, family id, # member/relproband, description descriptions are # really long and ugly SCREAMING text, so need to clean up # the control cases are so odd with this labeling scheme; # but we'll deal with it as-is for now. description = row[col.index('description')].strip() short_desc = (description.split(';')[0]).capitalize() gender = row[col.index('gender')].strip().lower() affected = row[col.index('affected')].strip() relprob = row[col.index('relprob')].strip() if affected == '': affected = 'unspecified' elif affected in self.localtt: affected = self.localtt[affected] else: LOG.warning('Novel Affected status %s at row: %i of %s', affected, line_counter, raw) patient_label = ' '.join((affected, gender, relprob)) if relprob == 'proband': patient_label = ' '.join( (patient_label.strip(), 'with', short_desc)) else: patient_label = ' '.join( (patient_label.strip(), 'of proband with', short_desc)) # ############# BUILD THE CELL LINE ############# # Adding the cell line as a typed individual. cell_line_reagent_id = self.globaltt['cell line'] model.addIndividualToGraph(cell_line_id, line_label, cell_line_reagent_id) # add the equivalent id == dna_ref dna_ref = row[col.index('dna_ref')].strip() if dna_ref != '' and dna_ref != catalog_id: equiv_cell_line = 'Coriell:' + dna_ref # some of the equivalent ids are not defined # in the source data; so add them model.addIndividualToGraph(equiv_cell_line, None, cell_line_reagent_id) model.addSameIndividual(cell_line_id, equiv_cell_line) # Cell line derives from patient geno.addDerivesFrom(cell_line_id, patient_id) geno.addDerivesFrom(cell_line_id, cell_type) # Cell line a member of repository family.addMember(repository, cell_line_id) cat_remark = row[col.index('cat_remark')].strip() if cat_remark != '': model.addDescription(cell_line_id, cat_remark) # Cell age_at_sampling # TODO add the age nodes when modeled properly in #78 # if (age != ''): # this would give a BNode that is an instance of Age. # but i don't know how to connect # the age node to the cell line? we need to ask @mbrush # age_id = '_'+re.sub('\s+','_',age) # gu.addIndividualToGraph( # graph,age_id,age,self.globaltt['age']) # gu.addTriple( # graph,age_id,self.globaltt['has measurement value'],age, # True) # ############# BUILD THE PATIENT ############# # Add the patient ID as an individual. model.addPerson(patient_id, patient_label) # TODO map relationship to proband as a class # (what ontology?) # Add race of patient # FIXME: Adjust for subcategories based on ethnicity field # EDIT: There are 743 different entries for ethnicity... # Too many to map? # Add ethnicity as literal in addition to the mapped race? # Adjust the ethnicity txt (if using) # to initial capitalization to remove ALLCAPS # TODO race should go into the individual's background # and abstracted out to the Genotype class punting for now. # if race != '': # mapped_race = self.resolve(race) # if mapped_race is not None: # gu.addTriple( # g,patient_id,self.globaltt['race'], mapped_race) # model.addSubClass( # mapped_race,self.globaltt['ethnic_group']) # ############# BUILD THE FAMILY ############# # Add triples for family_id, if present. if fam_id != '': family_comp_id = 'CoriellFamily:' + fam_id family_label = ' '.join( ('Family of proband with', short_desc)) # Add the family ID as a named individual model.addIndividualToGraph(family_comp_id, family_label, self.globaltt['family']) # Add the patient as a member of the family family.addMemberOf(patient_id, family_comp_id) # ############# BUILD THE GENOTYPE ############# # the important things to pay attention to here are: # karyotype = chr rearrangements (somatic?) # mutation = protein-level mutation as a label, # often from omim # gene = gene symbol - TODO get id # variant_id = omim variant ids (; delimited) # dbsnp_id = snp individual ids = full genotype? # note GM00633 is a good example of chromosomal variation # - do we have enough to capture this? # GM00325 has both abnormal karyotype and variation # make an assumption that if the taxon is blank, # that it is human! species = row[col.index('species')].strip() if species is None or species == '': species = 'H**o sapiens' taxon = self.resolve(species) # if there's a dbSNP id, # this is actually the individual's genotype genotype_id = None genotype_label = None dbsnp_id = row[col.index('dbsnp_id')].strip() if dbsnp_id != '': genotype_id = 'dbSNPIndividual:' + dbsnp_id omim_map = {} gvc_id = None # some of the karyotypes are encoded # with terrible hidden codes. remove them here # i've seen a <98> character karyotype = row[col.index('karyotype')].strip() karyotype = diputil.remove_control_characters(karyotype) karyotype_id = None if karyotype.strip() != '': karyotype_id = '_:' + re.sub('MONARCH:', '', self.make_id(karyotype)) # add karyotype as karyotype_variation_complement model.addIndividualToGraph( karyotype_id, karyotype, self.globaltt['karyotype_variation_complement']) # TODO break down the karyotype into parts # and map into GENO. depends on #77 # place the karyotype in a location(s). karyo_chrs = self._get_affected_chromosomes_from_karyotype( karyotype) for chrom in karyo_chrs: chr_id = makeChromID(chrom, taxon, 'CHR') # add an anonymous sequence feature, # each located on chr karyotype_feature_id = '-'.join((karyotype_id, chrom)) karyotype_feature_label = \ 'some karyotype alteration on chr' + str(chrom) feat = Feature(graph, karyotype_feature_id, karyotype_feature_label, self.globaltt['sequence_alteration']) feat.addFeatureStartLocation(None, chr_id) feat.addFeatureToGraph() geno.addParts(karyotype_feature_id, karyotype_id, self.globaltt['has_variant_part']) gene = row[col.index('gene')].strip() mutation = row[col.index('mutation')].strip() if gene != '': vl = gene + '(' + mutation + ')' # fix the variant_id so it's always in the same order variant_id = row[col.index('variant_id')].strip() vids = variant_id.split(';') variant_id = ';'.join(sorted(list(set(vids)))) if karyotype.strip() != '' and not self._is_normal_karyotype( karyotype): gvc_id = karyotype_id if variant_id != '': gvc_id = '_:' + variant_id.replace(';', '-') + '-' \ + re.sub(r'\w*:', '', karyotype_id) if mutation.strip() != '': gvc_label = '; '.join((vl, karyotype)) else: gvc_label = karyotype elif variant_id.strip() != '': gvc_id = '_:' + variant_id.replace(';', '-') gvc_label = vl else: # wildtype? pass # add the karyotype to the gvc. # use reference if normal karyotype karyo_rel = self.globaltt['has_variant_part'] if self._is_normal_karyotype(karyotype): karyo_rel = self.globaltt['has_reference_part'] if karyotype_id is not None \ and not self._is_normal_karyotype(karyotype) \ and gvc_id is not None and karyotype_id != gvc_id: geno.addParts(karyotype_id, gvc_id, karyo_rel) if variant_id.strip() != '': # split the variants & add them as part of the genotype # we don't necessarily know their zygosity, # just that they are part of the genotype variant ids # are from OMIM, so prefix as such we assume that the # sequence alts will be defined in OMIM not here # TODO sort the variant_id list, if the omim prefix is # the same, then assume it's the locus make a hashmap # of the omim id to variant id list; # then build the genotype hashmap is also useful for # removing the "genes" from the list of "phenotypes" # will hold gene/locus id to variant list omim_map = {} locus_num = None for var in variant_id.split(';'): # handle omim-style and odd var ids # like 610661.p.R401X mch = re.match(r'(\d+)\.+(.*)', var.strip()) if mch is not None and len(mch.groups()) == 2: (locus_num, var_num) = mch.groups() if locus_num is not None and locus_num not in omim_map: omim_map[locus_num] = [var_num] else: omim_map[locus_num] += [var_num] for omim in omim_map: # gene_id = 'OMIM:' + omim # TODO unused vslc_id = '_:' + '-'.join( [omim + '.' + a for a in omim_map.get(omim)]) vslc_label = vl # we don't really know the zygosity of # the alleles at all. # so the vslcs are just a pot of them model.addIndividualToGraph( vslc_id, vslc_label, self.globaltt['variant single locus complement']) for var in omim_map.get(omim): # this is actually a sequence alt allele1_id = 'OMIM:' + omim + '.' + var geno.addSequenceAlteration(allele1_id, None) # assume that the sa -> var_loc -> gene # is taken care of in OMIM geno.addPartsToVSLC( vslc_id, allele1_id, None, self.globaltt['indeterminate'], self.globaltt['has_variant_part']) if vslc_id != gvc_id: geno.addVSLCtoParent(vslc_id, gvc_id) if affected == 'unaffected': # let's just say that this person is wildtype model.addType(patient_id, self.globaltt['wildtype']) elif genotype_id is None: # make an anonymous genotype id (aka blank node) genotype_id = '_:geno' + catalog_id.strip() # add the gvc if gvc_id is not None: model.addIndividualToGraph( gvc_id, gvc_label, self.globaltt['genomic_variation_complement']) # add the gvc to the genotype if genotype_id is not None: if affected == 'unaffected': rel = self.globaltt['has_reference_part'] else: rel = self.globaltt['has_variant_part'] geno.addParts(gvc_id, genotype_id, rel) if karyotype_id is not None \ and self._is_normal_karyotype(karyotype): if gvc_label is not None and gvc_label != '': genotype_label = '; '.join((gvc_label, karyotype)) elif karyotype is not None: genotype_label = karyotype if genotype_id is None: genotype_id = karyotype_id else: geno.addParts(karyotype_id, genotype_id, self.globaltt['has_reference_part']) else: genotype_label = gvc_label # use the catalog id as the background genotype_label += ' [' + catalog_id.strip() + ']' if genotype_id is not None and gvc_id is not None: # only add the genotype if it has some parts geno.addGenotype(genotype_id, genotype_label, self.globaltt['intrinsic_genotype']) geno.addTaxon(taxon, genotype_id) # add that the patient has the genotype # TODO check if the genotype belongs to # the cell line or to the patient graph.addTriple(patient_id, self.globaltt['has_genotype'], genotype_id) else: geno.addTaxon(taxon, patient_id) # TODO: Add sex/gender (as part of the karyotype?) # = row[col.index('')].strip() # ############# DEAL WITH THE DISEASES ############# omim_num = row[col.index('omim_num')].strip() # we associate the disease to the patient if affected == 'affected' and omim_num != '': for d in omim_num.split(';'): if d is not None and d != '': # if the omim number is in omim_map, # then it is a gene not a pheno # TEC - another place to use the mimTitle omim # classifier omia & genereviews are using if d not in omim_map: disease_id = 'OMIM:' + d.strip() # assume the label is taken care of in OMIM model.addClassToGraph(disease_id, None) # add the association: # the patient has the disease assoc = G2PAssoc(graph, self.name, patient_id, disease_id) assoc.add_association_to_graph() # this line is a model of this disease # TODO abstract out model into # it's own association class? graph.addTriple(cell_line_id, self.globaltt['is model of'], disease_id) else: LOG.info('drop gene %s from disease list', d) # ############# ADD PUBLICATIONS ############# pubmed_ids = row[col.index('pubmed_ids')].strip() if pubmed_ids != '': for s in pubmed_ids.split(';'): pubmed_id = 'PMID:' + s.strip() ref = Reference(graph, pubmed_id) ref.setType(self.globaltt['journal article']) ref.addRefToGraph() graph.addTriple(pubmed_id, self.globaltt['mentions'], cell_line_id) if not self.testMode and (limit is not None and line_counter > limit): break return
def _process_data(self, raw, limit=None): """ This function will process the data files from Coriell. We make the assumption that any alleles listed are variants (alternates to w.t.) Triples: (examples) :NIGMSrepository a CLO_0000008 #repository label : NIGMS Human Genetic Cell Repository foaf:page https://catalog.coriell.org/0/sections/collections/NIGMS/?SsId=8 line_id a CL_0000057, #fibroblast line derives_from patient_id part_of :NIGMSrepository RO:model_of OMIM:disease_id patient id a foaf:person, label: "fibroblast from patient 12345 with disease X" member_of family_id #what is the right thing here? SIO:race EFO:caucasian #subclass of EFO:0001799 in_taxon NCBITaxon:9606 dc:description Literal(remark) RO:has_phenotype OMIM:disease_id GENO:has_genotype genotype_id family_id a owl:NamedIndividual foaf:page "https://catalog.coriell.org/0/Sections/BrowseCatalog/FamilyTypeSubDetail.aspx?PgId=402&fam=2104&coll=GM" genotype_id a intrinsic_genotype GENO:has_alternate_part allelic_variant_id we don't necessarily know much about the genotype, other than the allelic variant. also there's the sex here pub_id mentions cell_line_id :param raw: :param limit: :return: """ logger.info("Processing Data from %s", raw) gu = GraphUtils(curie_map.get()) if self.testMode: # set the graph to build g = self.testgraph else: g = self.graph line_counter = 0 geno = Genotype(g) du = DipperUtil() gu.loadProperties(g, geno.object_properties, gu.OBJPROP) gu.loadAllProperties(g) with open(raw, 'r', encoding="iso-8859-1") as csvfile: filereader = csv.reader(csvfile, delimiter=',', quotechar='\"') next(filereader, None) # skip the header row for row in filereader: if not row: pass else: line_counter += 1 (catalog_id, description, omim_number, sample_type, cell_line_available, dna_in_stock, dna_ref, gender, age, race, ethnicity, affected, karyotype, relprob, mutation, gene, family_id, collection, url, cat_remark, pubmed_ids, family_member, variant_id, dbsnp_id, species) = row # example: # GM00003,HURLER SYNDROME,607014,Fibroblast,Yes,No,,Female,26 YR,Caucasian,,,, # parent,,,39,NIGMS Human Genetic Cell Repository, # http://ccr.coriell.org/Sections/Search/Sample_Detail.aspx?Ref=GM00003, # 46;XX; clinically normal mother of a child with Hurler syndrome; proband not in Repository,, # 2,,18343,H**o sapiens if self.testMode and catalog_id not in self.test_lines: # skip rows not in our test lines, when in test mode continue # ########### BUILD REQUIRED VARIABLES ########### # Make the cell line ID cell_line_id = 'Coriell:'+catalog_id.strip() # Map the cell/sample type cell_type = self._map_cell_type(sample_type) # Make a cell line label line_label = \ collection.partition(' ')[0]+'-'+catalog_id.strip() # Map the repository/collection repository = self._map_collection(collection) # patients are uniquely identified by one of: # dbsnp id (which is == an individual haplotype) # family id + family member (if present) OR # probands are usually family member zero # cell line id # since some patients have >1 cell line derived from them, # we must make sure that the genotype is attached to # the patient, and can be inferred to the cell line # examples of repeated patients are: # famid=1159, member=1; fam=152,member=1 # Make the patient ID # make an anonymous patient patient_id = '_person' if self.nobnodes: patient_id = ':'+patient_id if family_id != '': patient_id = \ '-'.join((patient_id, family_id, family_member)) else: # make an anonymous patient patient_id = '-'.join((patient_id, catalog_id.strip())) # properties of the individual patients: sex, family id, # member/relproband, description descriptions are # really long and ugly SCREAMING text, so need to clean up # the control cases are so odd with this labeling scheme; # but we'll deal with it as-is for now. short_desc = (description.split(';')[0]).capitalize() if affected == 'Yes': affected = 'affected' elif affected == 'No': affected = 'unaffected' gender = gender.lower() patient_label = ' '.join((affected, gender, relprob)) if relprob == 'proband': patient_label = \ ' '.join( (patient_label.strip(), 'with', short_desc)) else: patient_label = \ ' '.join( (patient_label.strip(), 'of proband with', short_desc)) # ############# BUILD THE CELL LINE ############# # Adding the cell line as a typed individual. cell_line_reagent_id = 'CLO:0000031' gu.addIndividualToGraph( g, cell_line_id, line_label, cell_line_reagent_id) # add the equivalent id == dna_ref if dna_ref != '' and dna_ref != catalog_id: equiv_cell_line = 'Coriell:'+dna_ref # some of the equivalent ids are not defined # in the source data; so add them gu.addIndividualToGraph( g, equiv_cell_line, None, cell_line_reagent_id) gu.addSameIndividual(g, cell_line_id, equiv_cell_line) # Cell line derives from patient geno.addDerivesFrom(cell_line_id, patient_id) geno.addDerivesFrom(cell_line_id, cell_type) # Cell line a member of repository gu.addMember(g, repository, cell_line_id) if cat_remark != '': gu.addDescription(g, cell_line_id, cat_remark) # Cell age_at_sampling # TODO add the age nodes when modeled properly in #78 # if (age != ''): # this would give a BNode that is an instance of Age. # but i don't know how to connect # the age node to the cell line? we need to ask @mbrush # age_id = '_'+re.sub('\s+','_',age) # gu.addIndividualToGraph( # g,age_id,age,self.terms['age']) # gu.addTriple( # g,age_id,self.properties['has_measurement'],age, # True) # ############# BUILD THE PATIENT ############# # Add the patient ID as an individual. gu.addPerson(g, patient_id, patient_label) # TODO map relationship to proband as a class # (what ontology?) # Add race of patient # FIXME: Adjust for subcategories based on ethnicity field # EDIT: There are 743 different entries for ethnicity... # Too many to map? # Add ethnicity as literal in addition to the mapped race? # Adjust the ethnicity txt (if using) # to initial capitalization to remove ALLCAPS # TODO race should go into the individual's background # and abstracted out to the Genotype class punting for now. # if race != '': # mapped_race = self._map_race(race) # if mapped_race is not None: # gu.addTriple( # g,patient_id,self.terms['race'],mapped_race) # gu.addSubclass( # g,self.terms['ethnic_group'],mapped_race) # ############# BUILD THE FAMILY ############# # Add triples for family_id, if present. if family_id != '': family_comp_id = 'CoriellFamily:'+family_id family_label = \ ' '.join(('Family of proband with', short_desc)) # Add the family ID as a named individual gu.addIndividualToGraph( g, family_comp_id, family_label, geno.genoparts['family']) # Add the patient as a member of the family gu.addMemberOf(g, patient_id, family_comp_id) # ############# BUILD THE GENOTYPE ############# # the important things to pay attention to here are: # karyotype = chr rearrangements (somatic?) # mutation = protein-level mutation as a label, # often from omim # gene = gene symbol - TODO get id # variant_id = omim variant ids (; delimited) # dbsnp_id = snp individual ids = full genotype? # note GM00633 is a good example of chromosomal variation # - do we have enough to capture this? # GM00325 has both abnormal karyotype and variation # make an assumption that if the taxon is blank, # that it is human! if species is None or species == '': species = 'H**o sapiens' taxon = self._map_species(species) # if there's a dbSNP id, # this is actually the individual's genotype genotype_id = None genotype_label = None if dbsnp_id != '': genotype_id = 'dbSNPIndividual:'+dbsnp_id.strip() omim_map = {} gvc_id = None # some of the karyotypes are encoded # with terrible hidden codes. remove them here # i've seen a <98> character karyotype = du.remove_control_characters(karyotype) karyotype_id = None if karyotype.strip() != '': karyotype_id = \ '_'+re.sub('MONARCH:', '', self.make_id(karyotype)) if self.nobnodes: karyotype_id = ':'+karyotype_id # add karyotype as karyotype_variation_complement gu.addIndividualToGraph( g, karyotype_id, karyotype, geno.genoparts['karyotype_variation_complement']) # TODO break down the karyotype into parts # and map into GENO. depends on #77 # place the karyotype in a location(s). karyo_chrs = \ self._get_affected_chromosomes_from_karyotype( karyotype) for c in karyo_chrs: chr_id = makeChromID(c, taxon, 'CHR') # add an anonymous sequence feature, # each located on chr karyotype_feature_id = '-'.join((karyotype_id, c)) karyotype_feature_label = \ 'some karyotype alteration on chr'+str(c) f = Feature( karyotype_feature_id, karyotype_feature_label, geno.genoparts['sequence_alteration']) f.addFeatureStartLocation(None, chr_id) f.addFeatureToGraph(g) f.loadAllProperties(g) geno.addParts( karyotype_feature_id, karyotype_id, geno.object_properties['has_alternate_part']) if gene != '': vl = gene+'('+mutation+')' # fix the variant_id so it's always in the same order vids = variant_id.split(';') variant_id = ';'.join(sorted(list(set(vids)))) if karyotype.strip() != '' \ and not self._is_normal_karyotype(karyotype): mutation = mutation.strip() gvc_id = karyotype_id if variant_id != '': gvc_id = '_' + variant_id.replace(';', '-') + '-' \ + re.sub(r'\w*:', '', karyotype_id) if mutation.strip() != '': gvc_label = '; '.join((vl, karyotype)) else: gvc_label = karyotype elif variant_id.strip() != '': gvc_id = '_' + variant_id.replace(';', '-') gvc_label = vl else: # wildtype? pass if gvc_id is not None and gvc_id != karyotype_id \ and self.nobnodes: gvc_id = ':'+gvc_id # add the karyotype to the gvc. # use reference if normal karyotype karyo_rel = geno.object_properties['has_alternate_part'] if self._is_normal_karyotype(karyotype): karyo_rel = \ geno.object_properties['has_reference_part'] if karyotype_id is not None \ and not self._is_normal_karyotype(karyotype) \ and gvc_id is not None and karyotype_id != gvc_id: geno.addParts(karyotype_id, gvc_id, karyo_rel) if variant_id.strip() != '': # split the variants & add them as part of the genotype # we don't necessarily know their zygosity, # just that they are part of the genotype variant ids # are from OMIM, so prefix as such we assume that the # sequence alts will be defined in OMIM not here # TODO sort the variant_id list, if the omim prefix is # the same, then assume it's the locus make a hashmap # of the omim id to variant id list; # then build the genotype hashmap is also useful for # removing the "genes" from the list of "phenotypes" # will hold gene/locus id to variant list omim_map = {} locus_num = None for v in variant_id.split(';'): # handle omim-style and odd var ids # like 610661.p.R401X m = re.match(r'(\d+)\.+(.*)', v.strip()) if m is not None and len(m.groups()) == 2: (locus_num, var_num) = m.groups() if locus_num is not None \ and locus_num not in omim_map: omim_map[locus_num] = [var_num] else: omim_map[locus_num] += [var_num] for o in omim_map: # gene_id = 'OMIM:' + o # TODO unused vslc_id = \ '_' + '-'.join( [o + '.' + a for a in omim_map.get(o)]) if self.nobnodes: vslc_id = ':'+vslc_id vslc_label = vl # we don't really know the zygosity of # the alleles at all. # so the vslcs are just a pot of them gu.addIndividualToGraph( g, vslc_id, vslc_label, geno.genoparts[ 'variant_single_locus_complement']) for v in omim_map.get(o): # this is actually a sequence alt allele1_id = 'OMIM:'+o+'.'+v geno.addSequenceAlteration(allele1_id, None) # assume that the sa -> var_loc -> gene # is taken care of in OMIM geno.addPartsToVSLC( vslc_id, allele1_id, None, geno.zygosity['indeterminate'], geno.object_properties[ 'has_alternate_part']) if vslc_id != gvc_id: geno.addVSLCtoParent(vslc_id, gvc_id) if affected == 'unaffected': # let's just say that this person is wildtype gu.addType(g, patient_id, geno.genoparts['wildtype']) elif genotype_id is None: # make an anonymous genotype id genotype_id = '_geno'+catalog_id.strip() if self.nobnodes: genotype_id = ':'+genotype_id # add the gvc if gvc_id is not None: gu.addIndividualToGraph( g, gvc_id, gvc_label, geno.genoparts['genomic_variation_complement']) # add the gvc to the genotype if genotype_id is not None: if affected == 'unaffected': rel = \ geno.object_properties[ 'has_reference_part'] else: rel = \ geno.object_properties[ 'has_alternate_part'] geno.addParts(gvc_id, genotype_id, rel) if karyotype_id is not None \ and self._is_normal_karyotype(karyotype): if gvc_label is not None and gvc_label != '': genotype_label = \ '; '.join((gvc_label, karyotype)) else: genotype_label = karyotype if genotype_id is None: genotype_id = karyotype_id else: geno.addParts( karyotype_id, genotype_id, geno.object_properties[ 'has_reference_part']) else: genotype_label = gvc_label # use the catalog id as the background genotype_label += ' ['+catalog_id.strip()+']' if genotype_id is not None and gvc_id is not None: # only add the genotype if it has some parts geno.addGenotype( genotype_id, genotype_label, geno.genoparts['intrinsic_genotype']) geno.addTaxon(taxon, genotype_id) # add that the patient has the genotype # TODO check if the genotype belongs to # the cell line or to the patient gu.addTriple( g, patient_id, geno.properties['has_genotype'], genotype_id) else: geno.addTaxon(taxon, patient_id) # TODO: Add sex/gender (as part of the karyotype?) # ############# DEAL WITH THE DISEASES ############# # we associate the disease to the patient if affected == 'affected': if omim_number != '': for d in omim_number.split(';'): if d is not None and d != '': # if the omim number is in omim_map, # then it is a gene not a pheno if d not in omim_map: disease_id = 'OMIM:'+d.strip() # assume the label is taken care of gu.addClassToGraph(g, disease_id, None) # add the association: # the patient has the disease assoc = G2PAssoc( self.name, patient_id, disease_id) assoc.add_association_to_graph(g) # this line is a model of this disease # TODO abstract out model into # it's own association class? gu.addTriple( g, cell_line_id, gu.properties['model_of'], disease_id) else: logger.info( 'removing %s from disease list ' + 'since it is a gene', d) # ############# ADD PUBLICATIONS ############# if pubmed_ids != '': for s in pubmed_ids.split(';'): pubmed_id = 'PMID:'+s.strip() ref = Reference(pubmed_id) ref.setType(Reference.ref_types['journal_article']) ref.addRefToGraph(g) gu.addTriple( g, pubmed_id, gu.properties['mentions'], cell_line_id) if not self.testMode \ and (limit is not None and line_counter > limit): break Assoc(self.name).load_all_properties(g) return
def process_gaf(self, gaffile, limit, id_map=None, eco_map=None): if self.test_mode: graph = self.testgraph else: graph = self.graph model = Model(graph) geno = Genotype(graph) LOG.info("Processing Gene Associations from %s", gaffile) uniprot_hit = 0 uniprot_miss = 0 col = self.gaf_columns with gzip.open(gaffile, 'rb') as csvfile: reader = csv.reader( io.TextIOWrapper(csvfile, newline=""), delimiter='\t', quotechar='\"') for row in reader: # comments start with exclamation if row[0][0] == '!': continue if len(row) != len(col): LOG.error( "Wrong number of columns %i, expected ... got:\n\t%s", len(col), row) exit(1) dbase = row[col.index('DB')].strip() gene_num = row[col.index('DB_Object_ID')].strip() gene_symbol = row[col.index('DB_Object_Symbol')].strip() qualifier = row[col.index('Qualifier')] go_id = row[col.index('GO_ID')].strip() ref = row[col.index('DB:Reference')].strip() eco_symbol = row[col.index('Evidence Code')].strip() with_or_from = row[col.index('With (or) From')] aspect = row[col.index('Aspect')].strip() gene_name = row[col.index('DB_Object_Name')] gene_synonym = row[col.index('DB_Object_Synonym')] # object_type = row[col.index('DB_Object_Type')].strip() taxon = row[col.index('Taxon and Interacting taxon')].strip() # date = row[col.index('Date')].strip() # assigned_by = row[col.index('Assigned_By')].strip() # annotation_extension = row[col.index('Annotation_Extension')] # gene_product_form_id = row[col.index('Gene_Product_Form_ID')] # test for required fields if '' in [row[:10], row[12]]: LOG.error( "Missing required part of annotation on row %i:\n%s", reader.line_num, str(row[:-4])) continue # (Don't) deal with qualifier NOT, contributes_to, colocalizes_with if re.search(r'NOT', qualifier): continue if dbase in self.localtt: dbase = self.localtt[dbase] uniprotid = None gene_id = None if dbase == 'UniProtKB': if id_map is not None and gene_num in id_map: gene_id = id_map[gene_num] uniprotid = ':'.join((dbase, gene_num)) (dbase, gene_num) = gene_id.split(':') uniprot_hit += 1 else: # LOG.warning( # "UniProt id %s is without a 1:1 mapping to entrez/ensembl", # gene_num) uniprot_miss += 1 continue else: gene_num = gene_num.split(':')[-1] # last gene_id = ':'.join((dbase, gene_num)) if self.test_mode and gene_id[:9] != 'NCBIGene:' and\ gene_num not in self.test_ids: continue model.addClassToGraph(gene_id, gene_symbol) if gene_name != '': model.addDescription(gene_id, gene_name) if gene_synonym != '': for syn in re.split(r'\|', gene_synonym): syn = syn.strip() if syn[:10] == 'UniProtKB:': model.addTriple( gene_id, self.globaltt['has gene product'], syn) elif re.fullmatch(graph.curie_regexp, syn) is not None: LOG.warning( 'possible curie "%s" as a literal synomym for %s', syn, gene_id) model.addSynonym(gene_id, syn) else: model.addSynonym(gene_id, syn) for txid in taxon.split('|'): tax_curie = re.sub(r'taxon:', 'NCBITaxon:', txid) geno.addTaxon(tax_curie, gene_id) assoc = Assoc(graph, self.name) assoc.set_subject(gene_id) assoc.set_object(go_id) try: eco_id = eco_map[eco_symbol] assoc.add_evidence(eco_id) except KeyError: LOG.error("Evidence code (%s) not mapped", eco_symbol) refs = re.split(r'\|', ref) for ref in refs: ref = ref.strip() if ref != '': prefix = ref.split(':')[0] # sidestep 'MGI:MGI:' if prefix in self.localtt: prefix = self.localtt[prefix] ref = ':'.join((prefix, ref.split(':')[-1])) refg = Reference(graph, ref) if prefix == 'PMID': ref_type = self.globaltt['journal article'] refg.setType(ref_type) refg.addRefToGraph() assoc.add_source(ref) # TODO add the source of the annotations from assigned by? rel = self.resolve(aspect, mandatory=False) if rel is not None and aspect == rel: if aspect == 'F' and re.search(r'contributes_to', qualifier): assoc.set_relationship(self.globaltt['contributes to']) else: LOG.error( "Aspect: %s with qualifier: %s is not recognized", aspect, qualifier) elif rel is not None: assoc.set_relationship(rel) assoc.add_association_to_graph() else: LOG.warning("No predicate for association \n%s\n", str(assoc)) if uniprotid is not None: assoc.set_description('Mapped from ' + uniprotid) # object_type should be one of: # protein_complex; protein; transcript; ncRNA; rRNA; tRNA; # snRNA; snoRNA; any subtype of ncRNA in the Sequence Ontology. # If the precise product type is unknown, # gene_product should be used ######################################################################## # Derive G2P Associations from IMP annotations # in version 2.1 Pipe will indicate 'OR' # and Comma will indicate 'AND'. # in version 2.0, multiple values are separated by pipes # where the pipe has been used to mean 'AND' if eco_symbol == 'IMP' and with_or_from != '': withitems = with_or_from.split('|') phenotypeid = go_id + 'PHENOTYPE' # create phenotype associations for itm in withitems: if itm == '' or re.match( r'(UniProtKB|WBPhenotype|InterPro|HGNC)', itm): LOG.warning( "Skipping %s from or with %s", uniprotid, itm) continue itm = re.sub(r'MGI\:MGI\:', 'MGI:', itm) itm = re.sub(r'WB:', 'WormBase:', itm) # for worms and fish, they might give a RNAi or MORPH # in these cases make a reagent-targeted gene if re.search('MRPHLNO|CRISPR|TALEN', itm): targeted_gene_id = self.zfin.make_targeted_gene_id( gene_id, itm) geno.addReagentTargetedGene(itm, gene_id, targeted_gene_id) # TODO PYLINT why is this needed? # Redefinition of assoc type from # dipper.models.assoc.Association.Assoc to # dipper.models.assoc.G2PAssoc.G2PAssoc assoc = G2PAssoc( graph, self.name, targeted_gene_id, phenotypeid) elif re.search(r'WBRNAi', itm): targeted_gene_id = self.wbase.make_reagent_targeted_gene_id( gene_id, itm) geno.addReagentTargetedGene(itm, gene_id, targeted_gene_id) assoc = G2PAssoc( graph, self.name, targeted_gene_id, phenotypeid) else: assoc = G2PAssoc(graph, self.name, itm, phenotypeid) for ref in refs: ref = ref.strip() if ref != '': prefix = ref.split(':')[0] if prefix in self.localtt: prefix = self.localtt[prefix] ref = ':'.join((prefix, ref.split(':')[-1])) assoc.add_source(ref) # experimental phenotypic evidence assoc.add_evidence( self.globaltt['experimental phenotypic evidence']) assoc.add_association_to_graph() # TODO should the G2PAssoc be the evidence for the GO assoc? if not self.test_mode and limit is not None and \ reader.line_num > limit: break uniprot_tot = (uniprot_hit + uniprot_miss) uniprot_per = 0.0 if uniprot_tot != 0: uniprot_per = 100.0 * uniprot_hit / uniprot_tot LOG.info( "Uniprot: %.2f%% of %i benefited from the 1/4 day id mapping download", uniprot_per, uniprot_tot)
def process_allele_phenotype(self, limit=None): """ This file compactly lists variant to phenotype associations, such that in a single row, there may be >1 variant listed per phenotype and paper. This indicates that each variant is individually assocated with the given phenotype, as listed in 1+ papers. (Not that the combination of variants is producing the phenotype.) :param limit: :return: """ raw = '/'.join((self.rawdir, self.files['allele_pheno']['file'])) graph = self.graph model = Model(self.graph) LOG.info("Processing Allele phenotype associations") line_counter = 0 geno = Genotype(graph) with open(raw, 'r') as csvfile: filereader = csv.reader(csvfile, delimiter='\t', quotechar='\"') for row in filereader: if re.match(r'!', ''.join(row)): # header continue line_counter += 1 (db, gene_num, gene_symbol, is_not, phenotype_id, ref, eco_symbol, with_or_from, aspect, gene_name, gene_synonym, gene_class, taxon, date, assigned_by, blank, blank2) = row # TODO add NOT phenotypes if is_not == 'NOT': continue eco_symbol = eco_symbol.strip() eco_id = None if eco_symbol.strip() != '': eco_id = self.resolve(eco_symbol) # according to the GOA spec, persons are not allowed to be # in the reference column, therefore they the variant and # persons are swapped between the reference and with column. # we unswitch them here. temp_var = temp_ref = None if re.search(r'WBVar|WBRNAi', ref): temp_var = ref # move the paper from the with column into the ref if re.search(r'WBPerson', with_or_from): temp_ref = with_or_from if temp_var is not None or temp_ref is not None: with_or_from = temp_var ref = temp_ref allele_list = re.split(r'\|', with_or_from) if len(allele_list) == 0: LOG.error( "Missing alleles from phenotype assoc at line %d", line_counter) continue else: for allele in allele_list: allele_num = re.sub(r'WB:', '', allele.strip()) allele_id = 'WormBase:' + allele_num gene_id = 'WormBase:' + gene_num if re.search(r'WBRNAi', allele_id): # @kshefchek - removing this blank node # in favor of simpler modeling # make the WormBase:WBRNAi* id # a self.globaltt['reagent_targeted_gene'], and attach # phenotype to this ID # Previous model - make a bnode reagent-targeted gene, # & annotate that instead of the RNAi item directly #rnai_num = re.sub(r'WormBase:', '', allele_id) #rnai_id = allele_id #rtg_id = self.make_reagent_targeted_gene_id( # gene_num, rnai_num) #geno.addReagentTargetedGene( # rnai_id, 'WormBase:' + gene_num, rtg_id) # allele_id = rtg_id # Could type the IRI as both the reagant and reagant # targeted gene but not sure if this needed # geno.addGeneTargetingReagent( # allele_id, None, self.globaltt['RNAi_reagent'], gene_id) model.addIndividualToGraph( allele_id, None, self.globaltt['reagent_targeted_gene']) self.graph.addTriple( allele_id, self.globaltt['is_expression_variant_of'], gene_id) elif re.search(r'WBVar', allele_id): # this may become deprecated by using wormmine # make the allele to gene relationship # the WBVars are really sequence alterations # the public name will come from elsewhere # @kshefchek - removing this blank node # in favor of simpler modeling, treat variant # like an allele #vl_id = '_:'+'-'.join((gene_num, allele_num)) #geno.addSequenceAlterationToVariantLocus( # allele_id, vl_id) #geno.addAlleleOfGene(vl_id, gene_id) geno.addSequenceAlteration(allele_id, None) geno.addAlleleOfGene(allele_id, gene_id) else: LOG.warning( "Some kind of allele I don't recognize: %s", allele_num) continue assoc = G2PAssoc(graph, self.name, allele_id, phenotype_id) if eco_id is not None: assoc.add_evidence(eco_id) if ref is not None and ref != '': ref = re.sub(r'(WB:|WB_REF:)', 'WormBase:', ref) reference = Reference(graph, ref) if re.search(r'Person', ref): reference.setType(self.globaltt['person']) assoc.add_evidence( self.globaltt[ 'inference from background scientific knowledge' ]) reference.addRefToGraph() assoc.add_source(ref) assoc.add_association_to_graph() # finish looping through all alleles if limit is not None and line_counter > limit: break return
def _process_phenotype_tab(self, raw, limit): if self.testMode: g = self.testgraph else: g = self.graph line_counter = 0 gu = GraphUtils(curie_map.get()) with open(raw, 'r', encoding="utf8") as csvfile: filereader = csv.reader(csvfile, delimiter='\t', quotechar='\"') for row in filereader: line_counter += 1 (db, num, name, qual, pheno_id, publist, eco, onset, freq, w, asp, syn, date, curator) = row disease_id = db + ":" + str(num) if self.testMode and disease_id.strip() not in config.get_config()['test_ids']['disease']: continue # logger.info('adding %s', disease_id) gu.addClassToGraph(g, disease_id, None) gu.addClassToGraph(g, pheno_id, None) eco_id = self._map_evidence_to_codes(eco) gu.addClassToGraph(g, eco_id, None) if onset is not None and onset.strip() != '': gu.addClassToGraph(g, onset, None) # we want to do things differently depending on the aspect of the annotation if asp == 'O' or asp == 'M': # organ abnormality or mortality assoc = D2PAssoc(self.name, disease_id, pheno_id, onset, freq) elif asp == 'I': # inheritance patterns for the whole disease assoc = DispositionAssoc(self.name, disease_id, pheno_id) elif asp == 'C': # clinical course / onset assoc = DispositionAssoc(self.name, disease_id, pheno_id) else: logger.error("I don't know what this aspect is:", asp) assoc.add_evidence(eco_id) publist = publist.split(';') # blow these apart if there is a list of pubs for pub in publist: pub = pub.strip() if pub != '': # if re.match('http://www.ncbi.nlm.nih.gov/bookshelf/br\.fcgi\?book=gene', pub): # #http://www.ncbi.nlm.nih.gov/bookshelf/br.fcgi?book=gene&part=ced # m = re.search('part\=(\w+)', pub) # pub_id = 'GeneReviews:'+m.group(1) # elif re.search('http://www.orpha.net/consor/cgi-bin/OC_Exp\.php\?lng\=en\&Expert\=', pub): # m = re.search('Expert=(\d+)', pub) # pub_id = 'Orphanet:'+m.group(1) if not re.match('http', pub): r = Reference(pub) if re.match('PMID', pub): r.setType(Reference.ref_types['journal_article']) r.addRefToGraph(g) # TODO add curator assoc.add_source(pub) assoc.add_association_to_graph(g) if not self.testMode and limit is not None and line_counter > limit: break Assoc(None).load_all_properties(g) return
def process_gaf(self, file, limit, id_map=None, eco_map=None): if self.test_mode: graph = self.testgraph else: graph = self.graph model = Model(graph) geno = Genotype(graph) LOG.info("Processing Gene Associations from %s", file) line_counter = 0 uniprot_hit = 0 uniprot_miss = 0 if 7955 in self.tax_ids: zfin = ZFIN(self.graph_type, self.are_bnodes_skized) if 6239 in self.tax_ids: wbase = WormBase(self.graph_type, self.are_bnodes_skized) with gzip.open(file, 'rb') as csvfile: filereader = csv.reader( io.TextIOWrapper(csvfile, newline=""), delimiter='\t', quotechar='\"') for row in filereader: line_counter += 1 # comments start with exclamation if re.match(r'!', ''.join(row)): continue if len(row) > 17 or len(row) < 15: LOG.warning( "Wrong number of columns %i, expected 15 or 17\n%s", len(row), row) continue if 17 > len(row) >= 15: row += [""] * (17 - len(row)) (dbase, gene_num, gene_symbol, qualifier, go_id, ref, eco_symbol, with_or_from, aspect, gene_name, gene_synonym, object_type, taxon, date, assigned_by, annotation_extension, gene_product_form_id) = row # test for required fields if (dbase == '' or gene_num == '' or gene_symbol == '' or go_id == '' or ref == '' or eco_symbol == '' or aspect == '' or object_type == '' or taxon == '' or date == '' or assigned_by == ''): LOG.error( "Missing required part of annotation on row %d:\n"+'\t' .join(row), line_counter) continue # deal with qualifier NOT, contributes_to, colocalizes_with if re.search(r'NOT', qualifier): continue if dbase in self.localtt: dbase = self.localtt[dbase] uniprotid = None gene_id = None if dbase == 'UniProtKB': if id_map is not None and gene_num in id_map: gene_id = id_map[gene_num] uniprotid = ':'.join((dbase, gene_num)) (dbase, gene_num) = gene_id.split(':') uniprot_hit += 1 else: # LOG.warning( # "UniProt id %s is without a 1:1 mapping to entrez/ensembl", # gene_num) uniprot_miss += 1 continue else: gene_num = gene_num.split(':')[-1] # last gene_id = ':'.join((dbase, gene_num)) if self.test_mode and not( re.match(r'NCBIGene', gene_id) and int(gene_num) in self.test_ids): continue model.addClassToGraph(gene_id, gene_symbol) if gene_name != '': model.addDescription(gene_id, gene_name) if gene_synonym != '': for syn in re.split(r'\|', gene_synonym): model.addSynonym(gene_id, syn.strip()) if re.search(r'\|', taxon): # TODO add annotations with >1 taxon LOG.info( ">1 taxon (%s) on line %d. skipping", taxon, line_counter) else: tax_id = re.sub(r'taxon:', 'NCBITaxon:', taxon) geno.addTaxon(tax_id, gene_id) assoc = Assoc(graph, self.name) assoc.set_subject(gene_id) assoc.set_object(go_id) try: eco_id = eco_map[eco_symbol] assoc.add_evidence(eco_id) except KeyError: LOG.error("Evidence code (%s) not mapped", eco_symbol) refs = re.split(r'\|', ref) for ref in refs: ref = ref.strip() if ref != '': prefix = ref.split(':')[0] # sidestep 'MGI:MGI:' if prefix in self.localtt: prefix = self.localtt[prefix] ref = ':'.join((prefix, ref.split(':')[-1])) refg = Reference(graph, ref) if prefix == 'PMID': ref_type = self.globaltt['journal article'] refg.setType(ref_type) refg.addRefToGraph() assoc.add_source(ref) # TODO add the source of the annotations from assigned by? rel = self.resolve(aspect, mandatory=False) if rel is not None and aspect == rel: if aspect == 'F' and re.search(r'contributes_to', qualifier): assoc.set_relationship(self.globaltt['contributes to']) else: LOG.error( "Aspect: %s with qualifier: %s is not recognized", aspect, qualifier) elif rel is not None: assoc.set_relationship(rel) assoc.add_association_to_graph() else: LOG.warning("No predicate for association \n%s\n", str(assoc)) if uniprotid is not None: assoc.set_description('Mapped from ' + uniprotid) # object_type should be one of: # protein_complex; protein; transcript; ncRNA; rRNA; tRNA; # snRNA; snoRNA; any subtype of ncRNA in the Sequence Ontology. # If the precise product type is unknown, # gene_product should be used ####################################################################### # Derive G2P Associations from IMP annotations # in version 2.1 Pipe will indicate 'OR' # and Comma will indicate 'AND'. # in version 2.0, multiple values are separated by pipes # where the pipe has been used to mean 'AND' if eco_symbol == 'IMP' and with_or_from != '': withitems = re.split(r'\|', with_or_from) phenotypeid = go_id+'PHENOTYPE' # create phenotype associations for i in withitems: if i == '' or re.match( r'(UniProtKB|WBPhenotype|InterPro|HGNC)', i): LOG.warning( "Don't know what having a uniprot id " + "in the 'with' column means of %s", uniprotid) continue i = re.sub(r'MGI\:MGI\:', 'MGI:', i) i = re.sub(r'WB:', 'WormBase:', i) # for worms and fish, they might give a RNAi or MORPH # in these cases make a reagent-targeted gene if re.search('MRPHLNO|CRISPR|TALEN', i): targeted_gene_id = zfin.make_targeted_gene_id(gene_id, i) geno.addReagentTargetedGene(i, gene_id, targeted_gene_id) # TODO PYLINT why is this needed? # Redefinition of assoc type from # dipper.models.assoc.Association.Assoc to # dipper.models.assoc.G2PAssoc.G2PAssoc assoc = G2PAssoc( graph, self.name, targeted_gene_id, phenotypeid) elif re.search(r'WBRNAi', i): targeted_gene_id = wbase.make_reagent_targeted_gene_id( gene_id, i) geno.addReagentTargetedGene(i, gene_id, targeted_gene_id) assoc = G2PAssoc( graph, self.name, targeted_gene_id, phenotypeid) else: assoc = G2PAssoc(graph, self.name, i, phenotypeid) for ref in refs: ref = ref.strip() if ref != '': prefix = ref.split(':')[0] if prefix in self.localtt: prefix = self.localtt[prefix] ref = ':'.join((prefix, ref.split(':')[-1])) assoc.add_source(ref) # experimental phenotypic evidence assoc.add_evidence( self.globaltt['experimental phenotypic evidence']) assoc.add_association_to_graph() # TODO should the G2PAssoc be # the evidence for the GO assoc? if not self.test_mode and limit is not None and line_counter > limit: break uniprot_tot = (uniprot_hit + uniprot_miss) uniprot_per = 0.0 if uniprot_tot != 0: uniprot_per = 100.0 * uniprot_hit / uniprot_tot LOG.info( "Uniprot: %f.2%% of %i benifited from the 1/4 day id mapping download", uniprot_per, uniprot_tot) return
def process_gaf(self, file, limit, id_map=None): if self.testMode: g = self.testgraph else: g = self.graph model = Model(g) geno = Genotype(g) logger.info("Processing Gene Associations from %s", file) line_counter = 0 if 7955 in self.tax_ids: zfin = ZFIN(self.graph_type, self.are_bnodes_skized) elif 6239 in self.tax_ids: wbase = WormBase(self.graph_type, self.are_bnodes_skized) with gzip.open(file, 'rb') as csvfile: filereader = csv.reader(io.TextIOWrapper(csvfile, newline=""), delimiter='\t', quotechar='\"') for row in filereader: line_counter += 1 # comments start with exclamation if re.match(r'!', ''.join(row)): continue (db, gene_num, gene_symbol, qualifier, go_id, ref, eco_symbol, with_or_from, aspect, gene_name, gene_synonym, object_type, taxon, date, assigned_by, annotation_extension, gene_product_form_id) = row # test for required fields if (db == '' or gene_num == '' or gene_symbol == '' or go_id == '' or ref == '' or eco_symbol == '' or aspect == '' or object_type == '' or taxon == '' or date == '' or assigned_by == ''): logger.error( "Missing required part of annotation " + "on row %d:\n"+'\t'.join(row), line_counter) continue # deal with qualifier NOT, contributes_to, colocalizes_with if re.search(r'NOT', qualifier): continue db = self.clean_db_prefix(db) uniprotid = None gene_id = None if db == 'UniProtKB': mapped_ids = id_map.get(gene_num) if id_map is not None and mapped_ids is not None: if len(mapped_ids) == 1: gene_id = mapped_ids[0] uniprotid = ':'.join((db, gene_num)) gene_num = re.sub(r'\w+\:', '', gene_id) elif len(mapped_ids) > 1: # logger.warning( # "Skipping gene id mapped for >1 gene %s -> %s", # gene_num, str(mapped_ids)) continue else: continue elif db == 'MGI': gene_num = re.sub(r'MGI:', '', gene_num) gene_id = ':'.join((db, gene_num)) gene_id = re.sub(r'MGI\:MGI\:', 'MGI:', gene_id) else: gene_id = ':'.join((db, gene_num)) if self.testMode \ and not( re.match(r'NCBIGene', gene_id) and int(gene_num) in self.test_ids): continue model.addClassToGraph(gene_id, gene_symbol) if gene_name != '': model.addDescription(gene_id, gene_name) if gene_synonym != '': for s in re.split(r'\|', gene_synonym): model.addSynonym(gene_id, s.strip()) if re.search(r'\|', taxon): # TODO add annotations with >1 taxon logger.info(">1 taxon (%s) on line %d. skipping", taxon, line_counter) else: tax_id = re.sub(r'taxon:', 'NCBITaxon:', taxon) geno.addTaxon(tax_id, gene_id) assoc = Assoc(g, self.name) assoc.set_subject(gene_id) assoc.set_object(go_id) eco_id = self.map_go_evidence_code_to_eco(eco_symbol) if eco_id is not None: assoc.add_evidence(eco_id) refs = re.split(r'\|', ref) for r in refs: r = r.strip() if r != '': prefix = re.split(r':', r)[0] r = re.sub(prefix, self.clean_db_prefix(prefix), r) r = re.sub(r'MGI\:MGI\:', 'MGI:', r) ref = Reference(g, r) if re.match(r'PMID', r): ref_type = Reference.ref_types['journal_article'] ref.setType(ref_type) ref.addRefToGraph() assoc.add_source(r) # TODO add the source of the annotations from assigned by? aspect_rel_map = { 'P': model.object_properties['involved_in'], # involved in 'F': model.object_properties['enables'], # enables 'C': model.object_properties['part_of'] # part of } if aspect not in aspect_rel_map: logger.error("Aspect not recognized: %s", aspect) rel = aspect_rel_map.get(aspect) if aspect == 'F' and re.search(r'contributes_to', qualifier): rel = model.object_properties['contributes_to'] assoc.set_relationship(rel) if uniprotid is not None: assoc.set_description('Mapped from '+uniprotid) # object_type should be one of: # protein_complex; protein; transcript; ncRNA; rRNA; tRNA; # snRNA; snoRNA; any subtype of ncRNA in the Sequence Ontology. # If the precise product type is unknown, # gene_product should be used assoc.add_association_to_graph() # Derive G2P Associations from IMP annotations # in version 2.1 Pipe will indicate 'OR' # and Comma will indicate 'AND'. # in version 2.0, multiple values are separated by pipes # where the pipe has been used to mean 'AND' if eco_symbol == 'IMP' and with_or_from != '': withitems = re.split(r'\|', with_or_from) phenotypeid = go_id+'PHENOTYPE' # create phenotype associations for i in withitems: if i == '' or \ re.match( r'(UniProtKB|WBPhenotype|InterPro|HGNC)', i): logger.warning( "Don't know what having a uniprot id " + "in the 'with' column means of %s", uniprotid) continue i = re.sub(r'MGI\:MGI\:', 'MGI:', i) i = re.sub(r'WB:', 'WormBase:', i) # for worms and fish, they might give a RNAi or MORPH # in these cases make a reagent-targeted gene if re.search('MRPHLNO|CRISPR|TALEN', i): targeted_gene_id = zfin.make_targeted_gene_id( gene_id, i) geno.addReagentTargetedGene(i, gene_id, targeted_gene_id) # TODO PYLINT why is this: # Redefinition of assoc type from # dipper.models.assoc.Association.Assoc to # dipper.models.assoc.G2PAssoc.G2PAssoc assoc = G2PAssoc(g, self.name, targeted_gene_id, phenotypeid) elif re.search(r'WBRNAi', i): targeted_gene_id = \ wbase.make_reagent_targeted_gene_id( gene_id, i) geno.addReagentTargetedGene( i, gene_id, targeted_gene_id) assoc = G2PAssoc( g, self.name, targeted_gene_id, phenotypeid) else: assoc = G2PAssoc(g, self.name, i, phenotypeid) for r in refs: r = r.strip() if r != '': prefix = re.split(r':', r)[0] r = re.sub( prefix, self.clean_db_prefix(prefix), r) r = re.sub(r'MGI\:MGI\:', 'MGI:', r) assoc.add_source(r) # experimental phenotypic evidence assoc.add_evidence("ECO:0000059") assoc.add_association_to_graph() # TODO should the G2PAssoc be # the evidence for the GO assoc? if not self.testMode and \ limit is not None and line_counter > limit: break return
def process_gaf(self, file, limit, id_map=None): if self.testMode: g = self.testgraph else: g = self.graph model = Model(g) geno = Genotype(g) logger.info("Processing Gene Associations from %s", file) line_counter = 0 if 7955 in self.tax_ids: zfin = ZFIN(self.graph_type, self.are_bnodes_skized) elif 6239 in self.tax_ids: wbase = WormBase(self.graph_type, self.are_bnodes_skized) with gzip.open(file, 'rb') as csvfile: filereader = csv.reader(io.TextIOWrapper(csvfile, newline=""), delimiter='\t', quotechar='\"') for row in filereader: line_counter += 1 # comments start with exclamation if re.match(r'!', ''.join(row)): continue (db, gene_num, gene_symbol, qualifier, go_id, ref, eco_symbol, with_or_from, aspect, gene_name, gene_synonym, object_type, taxon, date, assigned_by, annotation_extension, gene_product_form_id) = row # test for required fields if (db == '' or gene_num == '' or gene_symbol == '' or go_id == '' or ref == '' or eco_symbol == '' or aspect == '' or object_type == '' or taxon == '' or date == '' or assigned_by == ''): logger.error( "Missing required part of annotation " + "on row %d:\n" + '\t'.join(row), line_counter) continue # deal with qualifier NOT, contributes_to, colocalizes_with if re.search(r'NOT', qualifier): continue db = self.clean_db_prefix(db) uniprotid = None gene_id = None if db == 'UniProtKB': mapped_ids = id_map.get(gene_num) if id_map is not None and mapped_ids is not None: if len(mapped_ids) == 1: gene_id = mapped_ids[0] uniprotid = ':'.join((db, gene_num)) gene_num = re.sub(r'\w+\:', '', gene_id) elif len(mapped_ids) > 1: # logger.warning( # "Skipping gene id mapped for >1 gene %s -> %s", # gene_num, str(mapped_ids)) continue else: continue elif db == 'MGI': gene_num = re.sub(r'MGI:', '', gene_num) gene_id = ':'.join((db, gene_num)) gene_id = re.sub(r'MGI\:MGI\:', 'MGI:', gene_id) else: gene_id = ':'.join((db, gene_num)) if self.testMode \ and not( re.match(r'NCBIGene', gene_id) and int(gene_num) in self.test_ids): continue model.addClassToGraph(gene_id, gene_symbol) if gene_name != '': model.addDescription(gene_id, gene_name) if gene_synonym != '': for s in re.split(r'\|', gene_synonym): model.addSynonym(gene_id, s.strip()) if re.search(r'\|', taxon): # TODO add annotations with >1 taxon logger.info(">1 taxon (%s) on line %d. skipping", taxon, line_counter) else: tax_id = re.sub(r'taxon:', 'NCBITaxon:', taxon) geno.addTaxon(tax_id, gene_id) assoc = Assoc(g, self.name) assoc.set_subject(gene_id) assoc.set_object(go_id) eco_id = self.map_go_evidence_code_to_eco(eco_symbol) if eco_id is not None: assoc.add_evidence(eco_id) refs = re.split(r'\|', ref) for r in refs: r = r.strip() if r != '': prefix = re.split(r':', r)[0] r = re.sub(prefix, self.clean_db_prefix(prefix), r) r = re.sub(r'MGI\:MGI\:', 'MGI:', r) ref = Reference(g, r) if re.match(r'PMID', r): ref_type = Reference.ref_types['journal_article'] ref.setType(ref_type) ref.addRefToGraph() assoc.add_source(r) # TODO add the source of the annotations from assigned by? aspect_rel_map = { 'P': model.object_properties['involved_in'], # involved in 'F': model.object_properties['enables'], # enables 'C': model.object_properties['part_of'] # part of } if aspect not in aspect_rel_map: logger.error("Aspect not recognized: %s", aspect) rel = aspect_rel_map.get(aspect) if aspect == 'F' and re.search(r'contributes_to', qualifier): rel = model.object_properties['contributes_to'] assoc.set_relationship(rel) if uniprotid is not None: assoc.set_description('Mapped from ' + uniprotid) # object_type should be one of: # protein_complex; protein; transcript; ncRNA; rRNA; tRNA; # snRNA; snoRNA; any subtype of ncRNA in the Sequence Ontology. # If the precise product type is unknown, # gene_product should be used assoc.add_association_to_graph() # Derive G2P Associations from IMP annotations # in version 2.1 Pipe will indicate 'OR' # and Comma will indicate 'AND'. # in version 2.0, multiple values are separated by pipes # where the pipe has been used to mean 'AND' if eco_symbol == 'IMP' and with_or_from != '': withitems = re.split(r'\|', with_or_from) phenotypeid = go_id + 'PHENOTYPE' # create phenotype associations for i in withitems: if i == '' or \ re.match( r'(UniProtKB|WBPhenotype|InterPro|HGNC)', i): logger.warning( "Don't know what having a uniprot id " + "in the 'with' column means of %s", uniprotid) continue i = re.sub(r'MGI\:MGI\:', 'MGI:', i) i = re.sub(r'WB:', 'WormBase:', i) # for worms and fish, they might give a RNAi or MORPH # in these cases make a reagent-targeted gene if re.search('MRPHLNO|CRISPR|TALEN', i): targeted_gene_id = zfin.make_targeted_gene_id( gene_id, i) geno.addReagentTargetedGene( i, gene_id, targeted_gene_id) # TODO PYLINT why is this: # Redefinition of assoc type from # dipper.models.assoc.Association.Assoc to # dipper.models.assoc.G2PAssoc.G2PAssoc assoc = G2PAssoc(g, self.name, targeted_gene_id, phenotypeid) elif re.search(r'WBRNAi', i): targeted_gene_id = \ wbase.make_reagent_targeted_gene_id( gene_id, i) geno.addReagentTargetedGene( i, gene_id, targeted_gene_id) assoc = G2PAssoc(g, self.name, targeted_gene_id, phenotypeid) else: assoc = G2PAssoc(g, self.name, i, phenotypeid) for r in refs: r = r.strip() if r != '': prefix = re.split(r':', r)[0] r = re.sub(prefix, self.clean_db_prefix(prefix), r) r = re.sub(r'MGI\:MGI\:', 'MGI:', r) assoc.add_source(r) # experimental phenotypic evidence assoc.add_evidence("ECO:0000059") assoc.add_association_to_graph() # TODO should the G2PAssoc be # the evidence for the GO assoc? if not self.testMode and \ limit is not None and line_counter > limit: break return