def _process_phenotype_data(self, limit): """ NOTE: If a Strain carries more than one mutation, then each Mutation description, i.e., the set: ( Mutation Type - Chromosome - Gene Symbol - Gene Name - Allele Symbol - Allele Name) will require a separate line. Note that MMRRC curates phenotypes to alleles, even though they distribute only one file with the phenotypes appearing to be associated with a strain. So, here we process the allele-to-phenotype relationships separately from the strain-to-allele relationships. :param limit: :return: """ if self.testMode: g = self.testgraph else: g = self.graph line_counter = 0 gu = GraphUtils(curie_map.get()) fname = '/'.join((self.rawdir, self.files['catalog']['file'])) self.strain_hash = {} self.id_label_hash = {} genes_with_no_ids = set() stem_cell_class = 'CL:0000034' mouse_taxon = 'NCBITaxon:10090' geno = Genotype(g) with open(fname, 'r', encoding="utf8") as csvfile: filereader = csv.reader(csvfile, delimiter=',', quotechar='\"') for row in filereader: line_counter += 1 # skip the first 3 lines which are header, etc. if line_counter < 4: continue (strain_id, strain_label, strain_type_symbol, strain_state, mgi_allele_id, mgi_allele_symbol, mgi_allele_name, mutation_type, chrom, mgi_gene_id, mgi_gene_symbol, mgi_gene_name, sds_url, accepted_date, mp_ids, pubmed_nums, research_areas) = row if self.testMode and (strain_id not in self.test_ids): continue # strip off stuff after the dash - # is the holding center important? # MMRRC:00001-UNC --> MMRRC:00001 strain_id = re.sub(r'-\w+$', '', strain_id) self.id_label_hash[strain_id] = strain_label # get the variant or gene to save for later building of # the genotype if strain_id not in self.strain_hash: self.strain_hash[strain_id] = {'variants': set(), 'genes': set()} # clean up the bad one if mgi_allele_id == 'multiple mutation': logger.error("Erroneous gene id: %s", mgi_allele_id) mgi_allele_id = '' if mgi_allele_id != '': self.strain_hash[strain_id]['variants'].add(mgi_allele_id) self.id_label_hash[mgi_allele_id] = mgi_allele_symbol # use the following if needing to add the # sequence alteration types # var_type = # self._get_variant_type_from_abbrev(mutation_type) # make a sequence alteration for this variant locus, # and link the variation type to it # sa_id = '_'+re.sub(r':','',mgi_allele_id)+'SA' # if self.nobnodes: # sa_id = ':'+sa_id # gu.addIndividualToGraph(g, sa_id, None, var_type) # geno.addSequenceAlterationToVariantLocus(sa_id, # mgi_allele_id) # scrub out any spaces mgi_gene_id = re.sub(r'\s+', '', mgi_gene_id) if mgi_gene_id.strip() != '': if re.match(r'Gene\s*ID:', mgi_gene_id, re.I): mgi_gene_id = re.sub(r'Gene\s*ID:\s*', 'NCBIGene:', mgi_gene_id) elif not re.match(r'MGI', mgi_gene_id): logger.info("Gene id not recognized: %s", mgi_gene_id) if re.match(r'\d+$', mgi_gene_id): # assume that if it's all numbers, then it's MGI mgi_gene_id = 'MGI:'+str(mgi_gene_id) logger.info("Assuming numerics are MGI.") self.strain_hash[strain_id]['genes'].add(mgi_gene_id) self.id_label_hash[mgi_gene_id] = mgi_gene_symbol # catch some errors - # some things have gene labels, but no identifiers - report if mgi_gene_symbol.strip() != '' and mgi_gene_id == '': logger.error( "Gene label with no identifier for strain %s: %s", strain_id, mgi_gene_symbol) genes_with_no_ids.add(mgi_gene_symbol.strip()) # make a temp id for genes that aren't identified # tmp_gene_id = '_'+mgi_gene_symbol # self.id_label_hash[tmp_gene_id] = mgi_gene_symbol # self.strain_hash[strain_id]['genes'].add(tmp_gene_id) # split apart the mp ids # ataxia [MP:0001393] ,hypoactivity [MP:0001402] ... # mp_ids are now a comma delimited list # with MP terms in brackets phenotype_ids = [] if mp_ids != '': for i in re.split(r',', mp_ids): i = i.strip() mps = re.search(r'\[(.*)\]', i) if mps is not None: mp_id = mps.group(1).strip() phenotype_ids.append(mp_id) # pubmed ids are space delimited pubmed_ids = [] if pubmed_nums.strip() != '': for i in re.split(r'\s+', pubmed_nums): pmid = 'PMID:'+i.strip() pubmed_ids.append(pmid) r = Reference(pmid, Reference.ref_types['journal_article']) r.addRefToGraph(g) # https://www.mmrrc.org/catalog/sds.php?mmrrc_id=00001 # is a good example of 4 genotype parts gu.addClassToGraph(g, mouse_taxon, None) if research_areas.strip() == '': research_areas = None else: research_areas = 'Research Areas: '+research_areas strain_type = mouse_taxon if strain_state == 'ES': strain_type = stem_cell_class gu.addIndividualToGraph( g, strain_id, strain_label, strain_type, research_areas) # an inst of mouse?? gu.makeLeader(g, strain_id) # phenotypes are associated with the alleles for pid in phenotype_ids: # assume the phenotype label is in the ontology gu.addClassToGraph(g, pid, None) if mgi_allele_id is not None and mgi_allele_id != '': assoc = G2PAssoc(self.name, mgi_allele_id, pid, gu.object_properties['has_phenotype']) for p in pubmed_ids: assoc.add_source(p) assoc.add_association_to_graph(g) else: logger.info("Phenotypes and no allele for %s", strain_id) if not self.testMode and ( limit is not None and line_counter > limit): break # now that we've collected all of the variant information, build it # we don't know their zygosities for s in self.strain_hash: h = self.strain_hash.get(s) variants = h['variants'] genes = h['genes'] vl_set = set() # make variant loci for each gene if len(variants) > 0: for v in variants: vl_id = v vl_symbol = self.id_label_hash[vl_id] geno.addAllele(vl_id, vl_symbol, geno.genoparts['variant_locus']) vl_set.add(vl_id) if len(variants) == 1 and len(genes) == 1: for gene in genes: geno.addAlleleOfGene(vl_id, gene) else: geno.addAllele(vl_id, vl_symbol) else: # len(vars) == 0 # it's just anonymous variants in some gene for gene in genes: vl_id = '_'+gene+'-VL' vl_id = re.sub(r':', '', vl_id) if self.nobnodes: vl_id = ':'+vl_id vl_symbol = self.id_label_hash[gene]+'<?>' self.id_label_hash[vl_id] = vl_symbol geno.addAllele(vl_id, vl_symbol, geno.genoparts['variant_locus']) geno.addGene(gene, self.id_label_hash[gene]) geno.addAlleleOfGene(vl_id, gene) vl_set.add(vl_id) # make the vslcs vl_list = sorted(vl_set) vslc_list = [] for vl in vl_list: # for unknown zygosity vslc_id = '_'+re.sub(r'^_', '', vl)+'U' vslc_id = re.sub(r':', '', vslc_id) if self.nobnodes: vslc_id = ':' + vslc_id vslc_label = self.id_label_hash[vl] + '/?' self.id_label_hash[vslc_id] = vslc_label vslc_list.append(vslc_id) geno.addPartsToVSLC( vslc_id, vl, None, geno.zygosity['indeterminate'], geno.object_properties['has_alternate_part'], None) gu.addIndividualToGraph( g, vslc_id, vslc_label, geno.genoparts['variant_single_locus_complement']) if len(vslc_list) > 0: if len(vslc_list) > 1: gvc_id = '-'.join(vslc_list) gvc_id = re.sub(r':', '', gvc_id) if self.nobnodes: gvc_id = ':'+gvc_id gvc_label = \ '; '.join(self.id_label_hash[v] for v in vslc_list) gu.addIndividualToGraph( g, gvc_id, gvc_label, geno.genoparts['genomic_variation_complement']) for vslc_id in vslc_list: geno.addVSLCtoParent(vslc_id, gvc_id) else: # the GVC == VSLC, so don't have to make an extra piece gvc_id = vslc_list.pop() gvc_label = self.id_label_hash[gvc_id] genotype_label = gvc_label + ' [n.s.]' bkgd_id = \ '_' + re.sub(r':', '', '-'.join( (geno.genoparts['unspecified_genomic_background'], s))) genotype_id = '-'.join((gvc_id, bkgd_id)) if self.nobnodes: bkgd_id = ':'+bkgd_id geno.addTaxon(mouse_taxon, bkgd_id) geno.addGenomicBackground( bkgd_id, 'unspecified ('+s+')', geno.genoparts['unspecified_genomic_background'], "A placeholder for the " + "unspecified genetic background for "+s) geno.addGenomicBackgroundToGenotype( bkgd_id, genotype_id, geno.genoparts['unspecified_genomic_background']) geno.addParts( gvc_id, genotype_id, geno.object_properties['has_alternate_part']) geno.addGenotype(genotype_id, genotype_label) gu.addTriple( g, s, geno.object_properties['has_genotype'], genotype_id) else: # logger.debug( # "Strain %s is not making a proper genotype.", s) pass gu.loadProperties( g, G2PAssoc.object_properties, G2PAssoc.OBJECTPROP) gu.loadProperties( g, G2PAssoc.datatype_properties, G2PAssoc.DATAPROP) gu.loadProperties( g, G2PAssoc.annotation_properties, G2PAssoc.ANNOTPROP) gu.loadAllProperties(g) logger.warning( "The following gene symbols did not list identifiers: %s", str(sorted(list(genes_with_no_ids)))) return
def _process_phenotype_data(self, limit): """ NOTE: If a Strain carries more than one mutation, then each Mutation description, i.e., the set: ( Mutation Type - Chromosome - Gene Symbol - Gene Name - Allele Symbol - Allele Name) will require a separate line. Note that MMRRC curates phenotypes to alleles, even though they distribute only one file with the phenotypes appearing to be associated with a strain. So, here we process the allele-to-phenotype relationships separately from the strain-to-allele relationships. :param limit: :return: """ if self.testMode: g = self.testgraph else: g = self.graph model = Model(g) line_counter = 0 fname = '/'.join((self.rawdir, self.files['catalog']['file'])) self.strain_hash = {} self.id_label_hash = {} genes_with_no_ids = set() stem_cell_class = 'CL:0000034' mouse_taxon = 'NCBITaxon:10090' geno = Genotype(g) with open(fname, 'r', encoding="utf8") as csvfile: filereader = csv.reader(csvfile, delimiter=',', quotechar='\"') for row in filereader: line_counter += 1 # skip the first 3 lines which are header, etc. if line_counter < 4: continue (strain_id, strain_label, strain_type_symbol, strain_state, mgi_allele_id, mgi_allele_symbol, mgi_allele_name, mutation_type, chrom, mgi_gene_id, mgi_gene_symbol, mgi_gene_name, sds_url, accepted_date, mp_ids, pubmed_nums, research_areas) = row if self.testMode and (strain_id not in self.test_ids) \ or mgi_gene_name == 'withdrawn': continue # strip off stuff after the dash - # is the holding center important? # MMRRC:00001-UNC --> MMRRC:00001 strain_id = re.sub(r'-\w+$', '', strain_id) self.id_label_hash[strain_id] = strain_label # get the variant or gene to save for later building of # the genotype if strain_id not in self.strain_hash: self.strain_hash[strain_id] = { 'variants': set(), 'genes': set() } # clean up the bad one if mgi_allele_id == 'multiple mutation': logger.error("Erroneous gene id: %s", mgi_allele_id) mgi_allele_id = '' if mgi_allele_id != '': self.strain_hash[strain_id]['variants'].add(mgi_allele_id) self.id_label_hash[mgi_allele_id] = mgi_allele_symbol # use the following if needing to add the # sequence alteration types # var_type = # self._get_variant_type_from_abbrev(mutation_type) # make a sequence alteration for this variant locus, # and link the variation type to it # sa_id = '_'+re.sub(r':','',mgi_allele_id)+'SA' # if self.nobnodes: # sa_id = ':'+sa_id # gu.addIndividualToGraph(g, sa_id, None, var_type) # geno.addSequenceAlterationToVariantLocus(sa_id, # mgi_allele_id) # scrub out any spaces mgi_gene_id = re.sub(r'\s+', '', mgi_gene_id) if mgi_gene_id.strip() != '': if re.match(r'Gene\s*ID:', mgi_gene_id, re.I): mgi_gene_id = re.sub(r'Gene\s*ID:\s*', 'NCBIGene:', mgi_gene_id) elif not re.match(r'MGI', mgi_gene_id): logger.info("Gene id not recognized: %s", mgi_gene_id) if re.match(r'\d+$', mgi_gene_id): # assume that if it's all numbers, then it's MGI mgi_gene_id = 'MGI:' + str(mgi_gene_id) logger.info("Assuming numerics are MGI.") self.strain_hash[strain_id]['genes'].add(mgi_gene_id) self.id_label_hash[mgi_gene_id] = mgi_gene_symbol # catch some errors - # some things have gene labels, but no identifiers - report if mgi_gene_symbol.strip() != '' and mgi_gene_id == '': logger.error( "Gene label with no identifier for strain %s: %s", strain_id, mgi_gene_symbol) genes_with_no_ids.add(mgi_gene_symbol.strip()) # make a temp id for genes that aren't identified # tmp_gene_id = '_'+mgi_gene_symbol # self.id_label_hash[tmp_gene_id] = mgi_gene_symbol # self.strain_hash[strain_id]['genes'].add(tmp_gene_id) # split apart the mp ids # ataxia [MP:0001393] ,hypoactivity [MP:0001402] ... # mp_ids are now a comma delimited list # with MP terms in brackets phenotype_ids = [] if mp_ids != '': for i in re.split(r',', mp_ids): i = i.strip() mps = re.search(r'\[(.*)\]', i) if mps is not None: mp_id = mps.group(1).strip() phenotype_ids.append(mp_id) # pubmed ids are space delimited pubmed_ids = [] if pubmed_nums.strip() != '': for i in re.split(r'\s+', pubmed_nums): pmid = 'PMID:' + i.strip() pubmed_ids.append(pmid) r = Reference(g, pmid, Reference.ref_types['journal_article']) r.addRefToGraph() # https://www.mmrrc.org/catalog/sds.php?mmrrc_id=00001 # is a good example of 4 genotype parts model.addClassToGraph(mouse_taxon, None) if research_areas.strip() == '': research_areas = None else: research_areas = 'Research Areas: ' + research_areas strain_type = mouse_taxon if strain_state == 'ES': strain_type = stem_cell_class model.addIndividualToGraph( strain_id, strain_label, strain_type, research_areas) # an inst of mouse?? model.makeLeader(strain_id) # phenotypes are associated with the alleles for pid in phenotype_ids: # assume the phenotype label is in the ontology model.addClassToGraph(pid, None) if mgi_allele_id is not None and mgi_allele_id != '': assoc = G2PAssoc( g, self.name, mgi_allele_id, pid, model.object_properties['has_phenotype']) for p in pubmed_ids: assoc.add_source(p) assoc.add_association_to_graph() else: logger.info("Phenotypes and no allele for %s", strain_id) if not self.testMode and (limit is not None and line_counter > limit): break # now that we've collected all of the variant information, build it # we don't know their zygosities for s in self.strain_hash: h = self.strain_hash.get(s) variants = h['variants'] genes = h['genes'] vl_set = set() # make variant loci for each gene if len(variants) > 0: for v in variants: vl_id = v vl_symbol = self.id_label_hash[vl_id] geno.addAllele(vl_id, vl_symbol, geno.genoparts['variant_locus']) vl_set.add(vl_id) if len(variants) == 1 and len(genes) == 1: for gene in genes: geno.addAlleleOfGene(vl_id, gene) else: geno.addAllele(vl_id, vl_symbol) else: # len(vars) == 0 # it's just anonymous variants in some gene for gene in genes: vl_id = '_:' + re.sub(r':', '', gene) + '-VL' vl_symbol = self.id_label_hash[gene] + '<?>' self.id_label_hash[vl_id] = vl_symbol geno.addAllele(vl_id, vl_symbol, geno.genoparts['variant_locus']) geno.addGene(gene, self.id_label_hash[gene]) geno.addAlleleOfGene(vl_id, gene) vl_set.add(vl_id) # make the vslcs vl_list = sorted(vl_set) vslc_list = [] for vl in vl_list: # for unknown zygosity vslc_id = re.sub(r'^_', '', vl) + 'U' vslc_id = re.sub(r':', '', vslc_id) vslc_id = '_:' + vslc_id vslc_label = self.id_label_hash[vl] + '/?' self.id_label_hash[vslc_id] = vslc_label vslc_list.append(vslc_id) geno.addPartsToVSLC( vslc_id, vl, None, geno.zygosity['indeterminate'], geno.object_properties['has_alternate_part'], None) model.addIndividualToGraph( vslc_id, vslc_label, geno.genoparts['variant_single_locus_complement']) if len(vslc_list) > 0: if len(vslc_list) > 1: gvc_id = '-'.join(vslc_list) gvc_id = re.sub(r'_|:', '', gvc_id) gvc_id = '_:' + gvc_id gvc_label = \ '; '.join(self.id_label_hash[v] for v in vslc_list) model.addIndividualToGraph( gvc_id, gvc_label, geno.genoparts['genomic_variation_complement']) for vslc_id in vslc_list: geno.addVSLCtoParent(vslc_id, gvc_id) else: # the GVC == VSLC, so don't have to make an extra piece gvc_id = vslc_list.pop() gvc_label = self.id_label_hash[gvc_id] genotype_label = gvc_label + ' [n.s.]' bkgd_id = \ re.sub(r':', '', '-'.join( (geno.genoparts['unspecified_genomic_background'], s))) genotype_id = '-'.join((gvc_id, bkgd_id)) bkgd_id = '_:' + bkgd_id geno.addTaxon(mouse_taxon, bkgd_id) geno.addGenomicBackground( bkgd_id, 'unspecified (' + s + ')', geno.genoparts['unspecified_genomic_background'], "A placeholder for the " + "unspecified genetic background for " + s) geno.addGenomicBackgroundToGenotype( bkgd_id, genotype_id, geno.genoparts['unspecified_genomic_background']) geno.addParts(gvc_id, genotype_id, geno.object_properties['has_alternate_part']) geno.addGenotype(genotype_id, genotype_label) g.addTriple(s, geno.object_properties['has_genotype'], genotype_id) else: # logger.debug( # "Strain %s is not making a proper genotype.", s) pass logger.warning( "The following gene symbols did not list identifiers: %s", str(sorted(list(genes_with_no_ids)))) return
def _process_phenotype_data(self, limit): """ NOTE: If a Strain carries more than one mutation, then each Mutation description, i.e., the set: ( Mutation Type - Chromosome - Gene Symbol - Gene Name - Allele Symbol - Allele Name) will require a separate line. Note that MMRRC curates phenotypes to alleles, even though they distribute only one file with the phenotypes appearing to be associated with a strain. So, here we process the allele-to-phenotype relationships separately from the strain-to-allele relationships. :param limit: :return: """ src_key = 'catalog' if self.test_mode: graph = self.testgraph else: graph = self.graph model = Model(graph) fname = '/'.join((self.rawdir, self.files[src_key]['file'])) self.strain_hash = {} self.id_label_hash = {} genes_with_no_ids = set() stem_cell_class = self.globaltt['stem cell'] mouse_taxon = self.globaltt['Mus musculus'] geno = Genotype(graph) with open(fname, 'r', encoding="utf8") as csvfile: reader = csv.reader(csvfile, delimiter=',', quotechar='\"') # First line is header not date/version info. This changed recently, # apparently as of Sep 2019. Also, 3rd line is no longer blank. row = [x.strip() for x in next(reader)] # messy messy col = self.files['catalog']['columns'] strain_missing_allele = [] # to count the ones w/insufficent info if not self.check_fileheader(col, row): pass for row in reader: strain_id = row[col.index('STRAIN/STOCK_ID')].strip() strain_label = row[col.index('STRAIN/STOCK_DESIGNATION')] # strain_type_symbol = row[col.index('STRAIN_TYPE')] strain_state = row[col.index('STATE')] mgi_allele_id = row[col.index( 'MGI_ALLELE_ACCESSION_ID')].strip() mgi_allele_symbol = row[col.index('ALLELE_SYMBOL')] # mgi_allele_name = row[col.index('ALLELE_NAME')] # mutation_type = row[col.index('MUTATION_TYPE')] # chrom = row[col.index('CHROMOSOME')] mgi_gene_id = row[col.index('MGI_GENE_ACCESSION_ID')].strip() mgi_gene_symbol = row[col.index('GENE_SYMBOL')].strip() mgi_gene_name = row[col.index('GENE_NAME')] # sds_url = row[col.index('SDS_URL')] # accepted_date = row[col.index('ACCEPTED_DATE')] mpt_ids = row[col.index('MPT_IDS')].strip() pubmed_nums = row[col.index('PUBMED_IDS')].strip() research_areas = row[col.index('RESEARCH_AREAS')].strip() if self.test_mode and (strain_id not in self.test_ids) \ or mgi_gene_name == 'withdrawn': continue # strip off stuff after the dash - # is the holding center important? # MMRRC:00001-UNC --> MMRRC:00001 strain_id = re.sub(r'-\w+$', '', strain_id) self.id_label_hash[strain_id] = strain_label # get the variant or gene to save for later building of # the genotype if strain_id not in self.strain_hash: self.strain_hash[strain_id] = { 'variants': set(), 'genes': set() } # flag bad ones if mgi_allele_id[:4] != 'MGI:' and mgi_allele_id != '': LOG.error("Erroneous MGI allele id: %s", mgi_allele_id) if mgi_allele_id[:3] == 'MG:': mgi_allele_id = 'MGI:' + mgi_allele_id[3:] else: mgi_allele_id = '' if mgi_allele_id != '': self.strain_hash[strain_id]['variants'].add(mgi_allele_id) self.id_label_hash[mgi_allele_id] = mgi_allele_symbol # use the following if needing to add the sequence alteration types # var_type = self.localtt[mutation_type] # make a sequence alteration for this variant locus, # and link the variation type to it # sa_id = '_'+re.sub(r':','',mgi_allele_id)+'SA' # if self.nobnodes: # sa_id = ':'+sa_id # gu.addIndividualToGraph(g, sa_id, None, var_type) # geno.addSequenceAlterationToVariantLocus(sa_id, mgi_allele_id) # scrub out any spaces, fix known issues mgi_gene_id = re.sub(r'\s+', '', mgi_gene_id) if mgi_gene_id == 'NULL': mgi_gene_id = '' elif mgi_gene_id[:7] == 'GeneID:': mgi_gene_id = 'NCBIGene:' + mgi_gene_id[7:] if mgi_gene_id != '': try: [curie, localid] = mgi_gene_id.split(':') except ValueError as verror: LOG.warning( "Problem parsing mgi_gene_id %s from file %s: %s", mgi_gene_id, fname, verror) if curie not in ['MGI', 'NCBIGene']: LOG.info("MGI Gene id not recognized: %s", mgi_gene_id) self.strain_hash[strain_id]['genes'].add(mgi_gene_id) self.id_label_hash[mgi_gene_id] = mgi_gene_symbol # catch some errors - too many. report summary at the end # some things have gene labels, but no identifiers - report if mgi_gene_symbol != '' and mgi_gene_id == '': # LOG.error( # "Gene label with no MGI identifier for strain %s: %s", # strain_id, mgi_gene_symbol) genes_with_no_ids.add(mgi_gene_symbol) # make a temp id for genes that aren't identified ... err wow. # tmp_gene_id = '_' + mgi_gene_symbol # self.id_label_hash[tmp_gene_id.strip()] = mgi_gene_symbol # self.strain_hash[strain_id]['genes'].add(tmp_gene_id) # split apart the mp ids # ataxia [MP:0001393] ,hypoactivity [MP:0001402] ... # mpt_ids are a comma delimited list # labels with MP terms following in brackets phenotype_ids = [] if mpt_ids != '': for lb_mp in mpt_ids.split(r','): lb_mp = lb_mp.strip() if lb_mp[-1:] == ']' and lb_mp[-12:-8] == '[MP:': phenotype_ids.append(lb_mp[-11:-2]) # pubmed ids are space delimited pubmed_ids = [] if pubmed_nums != '': for pm_num in re.split(r'\s+', pubmed_nums): pmid = 'PMID:' + pm_num.strip() pubmed_ids.append(pmid) ref = Reference(graph, pmid, self.globaltt['journal article']) ref.addRefToGraph() # https://www.mmrrc.org/catalog/sds.php?mmrrc_id=00001 # is a good example of 4 genotype parts model.addClassToGraph(mouse_taxon, None) if research_areas == '': research_areas = None else: research_areas = 'Research Areas: ' + research_areas strain_type = mouse_taxon if strain_state == 'ES': strain_type = stem_cell_class model.addIndividualToGraph( # an inst of mouse?? strain_id, strain_label, strain_type, research_areas) model.makeLeader(strain_id) # phenotypes are associated with the alleles for pid in phenotype_ids: # assume the phenotype label is in some ontology model.addClassToGraph(pid, None) if mgi_allele_id is not None and mgi_allele_id != '': assoc = G2PAssoc(graph, self.name, mgi_allele_id, pid, self.globaltt['has phenotype']) for p in pubmed_ids: assoc.add_source(p) assoc.add_association_to_graph() else: # too chatty here. report aggregate # LOG.info("Phenotypes and no allele for %s", strain_id) strain_missing_allele.append(strain_id) if not self.test_mode and (limit is not None and reader.line_num > limit): break # report misses if strain_missing_allele: LOG.info("Phenotypes and no allele for %i strains", len(strain_missing_allele)) # now that we've collected all of the variant information, build it # we don't know their zygosities for s in self.strain_hash: h = self.strain_hash.get(s) variants = h['variants'] genes = h['genes'] vl_set = set() # make variant loci for each gene if variants: for var in variants: vl_id = var.strip() vl_symbol = self.id_label_hash[vl_id] geno.addAllele(vl_id, vl_symbol, self.globaltt['variant_locus']) vl_set.add(vl_id) if len(variants) == 1 and len(genes) == 1: for gene in genes: geno.addAlleleOfGene(vl_id, gene) else: geno.addAllele(vl_id, vl_symbol) else: # len(vars) == 0 # it's just anonymous variants in some gene for gene in genes: vl_id = '_:' + re.sub(r':', '', gene) + '-VL' vl_symbol = self.id_label_hash[gene] + '<?>' self.id_label_hash[vl_id] = vl_symbol geno.addAllele(vl_id, vl_symbol, self.globaltt['variant_locus']) geno.addGene(gene, self.id_label_hash[gene]) geno.addAlleleOfGene(vl_id, gene) vl_set.add(vl_id) # make the vslcs vl_list = sorted(vl_set) vslc_list = [] for vl in vl_list: # for unknown zygosity vslc_id = re.sub(r'^_', '', vl) + 'U' vslc_id = re.sub(r':', '', vslc_id) vslc_id = '_:' + vslc_id vslc_label = self.id_label_hash[vl] + '/?' self.id_label_hash[vslc_id] = vslc_label vslc_list.append(vslc_id) geno.addPartsToVSLC(vslc_id, vl, None, self.globaltt['indeterminate'], self.globaltt['has_variant_part'], None) model.addIndividualToGraph( vslc_id, vslc_label, self.globaltt['variant single locus complement']) if vslc_list: if len(vslc_list) > 1: gvc_id = '-'.join(vslc_list) gvc_id = re.sub(r'_|:', '', gvc_id) gvc_id = '_:' + gvc_id gvc_label = '; '.join(self.id_label_hash[v] for v in vslc_list) model.addIndividualToGraph( gvc_id, gvc_label, self.globaltt['genomic_variation_complement']) for vslc_id in vslc_list: geno.addVSLCtoParent(vslc_id, gvc_id) else: # the GVC == VSLC, so don't have to make an extra piece gvc_id = vslc_list.pop() gvc_label = self.id_label_hash[gvc_id] genotype_label = gvc_label + ' [n.s.]' bkgd_id = re.sub( r':', '', '-'.join( (self.globaltt['unspecified_genomic_background'], s))) genotype_id = '-'.join((gvc_id, bkgd_id)) bkgd_id = '_:' + bkgd_id geno.addTaxon(mouse_taxon, bkgd_id) geno.addGenomicBackground( bkgd_id, 'unspecified (' + s + ')', self.globaltt['unspecified_genomic_background'], "A placeholder for the unspecified genetic background for " + s) geno.addGenomicBackgroundToGenotype( bkgd_id, genotype_id, self.globaltt['unspecified_genomic_background']) geno.addParts(gvc_id, genotype_id, self.globaltt['has_variant_part']) geno.addGenotype(genotype_id, genotype_label) graph.addTriple(s, self.globaltt['has_genotype'], genotype_id) else: # LOG.debug( # "Strain %s is not making a proper genotype.", s) pass LOG.warning( "The following gene symbols did not list identifiers: %s", str(sorted(list(genes_with_no_ids)))) LOG.error('%i symbols given are missing their gene identifiers', len(genes_with_no_ids)) return
def _process_phenotype_data(self, limit): """ NOTE: If a Strain carries more than one mutation, then each Mutation description, i.e., the set: ( Mutation Type - Chromosome - Gene Symbol - Gene Name - Allele Symbol - Allele Name) will require a separate line. Note that MMRRC curates phenotypes to alleles, even though they distribute only one file with the phenotypes appearing to be associated with a strain. So, here we process the allele-to-phenotype relationships separately from the strain-to-allele relationships. :param limit: :return: """ src_key = 'catalog' if self.test_mode: graph = self.testgraph else: graph = self.graph model = Model(graph) fname = '/'.join((self.rawdir, self.files[src_key]['file'])) self.strain_hash = {} self.id_label_hash = {} genes_with_no_ids = set() stem_cell_class = self.globaltt['stem cell'] mouse_taxon = self.globaltt['Mus musculus'] geno = Genotype(graph) with open(fname, 'r', encoding="utf8") as csvfile: reader = csv.reader(csvfile, delimiter=',', quotechar='\"') # This MMRRC catalog data file was generated on YYYY-MM-DD # insert or check date w/dataset line = next(reader) # gen_date = line[-10:] line = next(reader) col = self.files['catalog']['columns'] if col != line: LOG.error( '%s\nExpected Headers:\t%s\nRecived Headers:\t%s\n', src_key, col, line) LOG.info(set(col) - set(line)) line = next(reader) if line != []: LOG.warning('Expected third line to be blank. got "%s" instead', line) for row in reader: strain_id = row[col.index('STRAIN/STOCK_ID')].strip() strain_label = row[col.index('STRAIN/STOCK_DESIGNATION')] # strain_type_symbol = row[col.index('STRAIN_TYPE')] strain_state = row[col.index('STATE')] mgi_allele_id = row[col.index('MGI_ALLELE_ACCESSION_ID')].strip() mgi_allele_symbol = row[col.index('ALLELE_SYMBOL')] # mgi_allele_name = row[col.index('ALLELE_NAME')] # mutation_type = row[col.index('MUTATION_TYPE')] # chrom = row[col.index('CHROMOSOME')] mgi_gene_id = row[col.index('MGI_GENE_ACCESSION_ID')].strip() mgi_gene_symbol = row[col.index('GENE_SYMBOL')].strip() mgi_gene_name = row[col.index('GENE_NAME')] # sds_url = row[col.index('SDS_URL')] # accepted_date = row[col.index('ACCEPTED_DATE')] mpt_ids = row[col.index('MPT_IDS')].strip() pubmed_nums = row[col.index('PUBMED_IDS')].strip() research_areas = row[col.index('RESEARCH_AREAS')].strip() if self.test_mode and (strain_id not in self.test_ids) \ or mgi_gene_name == 'withdrawn': continue # strip off stuff after the dash - # is the holding center important? # MMRRC:00001-UNC --> MMRRC:00001 strain_id = re.sub(r'-\w+$', '', strain_id) self.id_label_hash[strain_id] = strain_label # get the variant or gene to save for later building of # the genotype if strain_id not in self.strain_hash: self.strain_hash[strain_id] = { 'variants': set(), 'genes': set()} # flag bad ones if mgi_allele_id[:4] != 'MGI:' and mgi_allele_id != '': LOG.error("Erroneous MGI allele id: %s", mgi_allele_id) if mgi_allele_id[:3] == 'MG:': mgi_allele_id = 'MGI:' + mgi_allele_id[3:] else: mgi_allele_id = '' if mgi_allele_id != '': self.strain_hash[strain_id]['variants'].add(mgi_allele_id) self.id_label_hash[mgi_allele_id] = mgi_allele_symbol # use the following if needing to add the sequence alteration types # var_type = self.localtt[mutation_type] # make a sequence alteration for this variant locus, # and link the variation type to it # sa_id = '_'+re.sub(r':','',mgi_allele_id)+'SA' # if self.nobnodes: # sa_id = ':'+sa_id # gu.addIndividualToGraph(g, sa_id, None, var_type) # geno.addSequenceAlterationToVariantLocus(sa_id, mgi_allele_id) # scrub out any spaces, fix known issues mgi_gene_id = re.sub(r'\s+', '', mgi_gene_id) if mgi_gene_id == 'NULL': mgi_gene_id = '' elif mgi_gene_id[:7] == 'GeneID:': mgi_gene_id = 'NCBIGene:' + mgi_gene_id[7:] if mgi_gene_id != '': [curie, localid] = mgi_gene_id.split(':') if curie not in ['MGI', 'NCBIGene']: LOG.info("MGI Gene id not recognized: %s", mgi_gene_id) self.strain_hash[strain_id]['genes'].add(mgi_gene_id) self.id_label_hash[mgi_gene_id] = mgi_gene_symbol # catch some errors - too many. report summary at the end # some things have gene labels, but no identifiers - report if mgi_gene_symbol != '' and mgi_gene_id == '': # LOG.error( # "Gene label with no MGI identifier for strain %s: %s", # strain_id, mgi_gene_symbol) genes_with_no_ids.add(mgi_gene_symbol) # make a temp id for genes that aren't identified ... err wow. # tmp_gene_id = '_' + mgi_gene_symbol # self.id_label_hash[tmp_gene_id.strip()] = mgi_gene_symbol # self.strain_hash[strain_id]['genes'].add(tmp_gene_id) # split apart the mp ids # ataxia [MP:0001393] ,hypoactivity [MP:0001402] ... # mpt_ids are a comma delimited list # labels with MP terms following in brackets phenotype_ids = [] if mpt_ids != '': for lb_mp in mpt_ids.split(r','): lb_mp = lb_mp.strip() if lb_mp[-1:] == ']' and lb_mp[-12:-8] == '[MP:': phenotype_ids.append(lb_mp[-11:-2]) # pubmed ids are space delimited pubmed_ids = [] if pubmed_nums != '': for pm_num in re.split(r'\s+', pubmed_nums): pmid = 'PMID:' + pm_num.strip() pubmed_ids.append(pmid) ref = Reference(graph, pmid, self.globaltt['journal article']) ref.addRefToGraph() # https://www.mmrrc.org/catalog/sds.php?mmrrc_id=00001 # is a good example of 4 genotype parts model.addClassToGraph(mouse_taxon, None) if research_areas == '': research_areas = None else: research_areas = 'Research Areas: ' + research_areas strain_type = mouse_taxon if strain_state == 'ES': strain_type = stem_cell_class model.addIndividualToGraph( # an inst of mouse?? strain_id, strain_label, strain_type, research_areas) model.makeLeader(strain_id) # phenotypes are associated with the alleles for pid in phenotype_ids: # assume the phenotype label is in some ontology model.addClassToGraph(pid, None) if mgi_allele_id is not None and mgi_allele_id != '': assoc = G2PAssoc( graph, self.name, mgi_allele_id, pid, self.globaltt['has phenotype']) for p in pubmed_ids: assoc.add_source(p) assoc.add_association_to_graph() else: LOG.info("Phenotypes and no allele for %s", strain_id) if not self.test_mode and ( limit is not None and reader.line_num > limit): break # now that we've collected all of the variant information, build it # we don't know their zygosities for s in self.strain_hash: h = self.strain_hash.get(s) variants = h['variants'] genes = h['genes'] vl_set = set() # make variant loci for each gene if len(variants) > 0: for var in variants: vl_id = var.strip() vl_symbol = self.id_label_hash[vl_id] geno.addAllele( vl_id, vl_symbol, self.globaltt['variant_locus']) vl_set.add(vl_id) if len(variants) == 1 and len(genes) == 1: for gene in genes: geno.addAlleleOfGene(vl_id, gene) else: geno.addAllele(vl_id, vl_symbol) else: # len(vars) == 0 # it's just anonymous variants in some gene for gene in genes: vl_id = '_:' + re.sub(r':', '', gene) + '-VL' vl_symbol = self.id_label_hash[gene]+'<?>' self.id_label_hash[vl_id] = vl_symbol geno.addAllele( vl_id, vl_symbol, self.globaltt['variant_locus']) geno.addGene(gene, self.id_label_hash[gene]) geno.addAlleleOfGene(vl_id, gene) vl_set.add(vl_id) # make the vslcs vl_list = sorted(vl_set) vslc_list = [] for vl in vl_list: # for unknown zygosity vslc_id = re.sub(r'^_', '', vl)+'U' vslc_id = re.sub(r':', '', vslc_id) vslc_id = '_:' + vslc_id vslc_label = self.id_label_hash[vl] + '/?' self.id_label_hash[vslc_id] = vslc_label vslc_list.append(vslc_id) geno.addPartsToVSLC( vslc_id, vl, None, self.globaltt['indeterminate'], self.globaltt['has_variant_part'], None) model.addIndividualToGraph( vslc_id, vslc_label, self.globaltt['variant single locus complement']) if len(vslc_list) > 0: if len(vslc_list) > 1: gvc_id = '-'.join(vslc_list) gvc_id = re.sub(r'_|:', '', gvc_id) gvc_id = '_:'+gvc_id gvc_label = '; '.join(self.id_label_hash[v] for v in vslc_list) model.addIndividualToGraph( gvc_id, gvc_label, self.globaltt['genomic_variation_complement']) for vslc_id in vslc_list: geno.addVSLCtoParent(vslc_id, gvc_id) else: # the GVC == VSLC, so don't have to make an extra piece gvc_id = vslc_list.pop() gvc_label = self.id_label_hash[gvc_id] genotype_label = gvc_label + ' [n.s.]' bkgd_id = re.sub( r':', '', '-'.join(( self.globaltt['unspecified_genomic_background'], s))) genotype_id = '-'.join((gvc_id, bkgd_id)) bkgd_id = '_:' + bkgd_id geno.addTaxon(mouse_taxon, bkgd_id) geno.addGenomicBackground( bkgd_id, 'unspecified (' + s + ')', self.globaltt['unspecified_genomic_background'], "A placeholder for the unspecified genetic background for " + s) geno.addGenomicBackgroundToGenotype( bkgd_id, genotype_id, self.globaltt['unspecified_genomic_background']) geno.addParts( gvc_id, genotype_id, self.globaltt['has_variant_part']) geno.addGenotype(genotype_id, genotype_label) graph.addTriple( s, self.globaltt['has_genotype'], genotype_id) else: # LOG.debug( # "Strain %s is not making a proper genotype.", s) pass LOG.warning( "The following gene symbols did not list identifiers: %s", str(sorted(list(genes_with_no_ids)))) LOG.error( '%i symbols given are missing their gene identifiers', len(genes_with_no_ids)) return