def _process_straininfo(self, limit): # line_counter = 0 # TODO unused if self.testMode: g = self.testgraph else: g = self.graph logger.info("Processing measurements ...") raw = '/'.join((self.rawdir, self.files['straininfo']['file'])) tax_id = 'NCBITaxon:10090' gu = GraphUtils(curie_map.get()) with open(raw, 'r') as f: reader = csv.reader(f, delimiter=',', quotechar='\"') f.readline() # read the header row; skip for row in reader: (strain_name, vendor, stocknum, panel, mpd_strainid, straintype, n_proj, n_snp_datasets, mpdshortname, url) = row # C57BL/6J,J,000664,,7,IN,225,17,,http://jaxmice.jax.org/strain/000664.html # create the strain as an instance of the taxon if self.testMode and \ 'MPD:'+str(mpd_strainid) not in self.test_ids: continue strain_id = 'MPD-strain:'+str(mpd_strainid) gu.addIndividualToGraph(g, strain_id, strain_name, tax_id) if mpdshortname.strip() != '': gu.addSynonym(g, strain_id, mpdshortname.strip()) self.idlabel_hash[strain_id] = strain_name # make it equivalent to the vendor+stock if stocknum != '': if vendor == 'J': jax_id = 'JAX:'+stocknum gu.addSameIndividual(g, strain_id, jax_id) elif vendor == 'Rbrc': # reiken reiken_id = 'RBRC:'+re.sub(r'RBRC', '', stocknum) gu.addSameIndividual(g, strain_id, reiken_id) else: if url != '': gu.addXref(g, strain_id, url, True) if vendor != '': gu.addXref( g, strain_id, ':'.join((vendor, stocknum)), True) # add the panel information if panel != '': desc = panel+' [panel]' gu.addDescription(g, strain_id, desc) # TODO make the panels as a resource collection return
def process_pub_xrefs(self, limit=None): raw = '/'.join((self.rawdir, self.files['pub_xrefs']['file'])) if self.testMode: g = self.testgraph else: g = self.graph gu = GraphUtils(curie_map.get()) logger.info("Processing publication xrefs") line_counter = 0 with open(raw, 'r') as csvfile: filereader = csv.reader(csvfile, delimiter='\t', quotechar='\"') for row in filereader: line_counter += 1 (wb_ref, xref) = row # WBPaper00000009 pmid8805<BR> # WBPaper00000011 doi10.1139/z78-244<BR> # WBPaper00000012 cgc12<BR> if self.testMode and wb_ref not in self.test_ids['pub']: continue ref_id = 'WormBase:'+wb_ref xref_id = r = None xref = re.sub(r'<BR>', '', xref) xref = xref.strip() if re.match(r'pmid', xref): xref_id = 'PMID:'+re.sub(r'pmid\s*', '', xref) r = Reference( xref_id, Reference.ref_types['journal_article']) elif re.search(r'[\(\)\<\>\[\]\s]', xref): continue elif re.match(r'doi', xref): xref_id = 'DOI:'+re.sub(r'doi', '', xref.strip()) r = Reference(xref_id) elif re.match(r'cgc', xref): # TODO not sure what to do here with cgc xrefs continue else: # logger.debug("Other xrefs like %s", xref) continue if xref_id is not None: r.addRefToGraph(g) gu.addSameIndividual(g, ref_id, xref_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 _add_variant_cdna_variant_assoc_to_graph(self, row): """ Generates relationships between variants and cDNA variants given a row of data :param iterable: row of data, see add_variant_info_to_graph() docstring for expected structure. Only applicable for structure 2. :return None """ gu = GraphUtils(curie_map.get()) geno = Genotype(self.graph) is_literal = True (variant_key, variant_label, amino_acid_variant, amino_acid_position, transcript_id, transcript_priority, protein_variant_type, functional_impact, stop_gain_loss, transcript_gene, protein_variant_source, variant_gene, bp_pos, variant_cdna, cosmic_id, db_snp_id, genome_pos_start, genome_pos_end, ref_base, variant_base, primary_transcript_exons, primary_transcript_variant_sub_types, variant_type, chromosome, genome_build, build_version, build_date) = row variant_id = self.make_cgd_id('variant{0}'.format(variant_key)) # Add gene self._add_variant_gene_relationship(variant_id, variant_gene) # Transcript reference for nucleotide position transcript_curie = self._make_transcript_curie(transcript_id) # Make region IDs cdna_region_id = ":_{0}Region".format(transcript_curie) chrom_region_id = ":_{0}{1}Region-{2}-{3}".format(genome_build, chromosome, genome_pos_start, genome_pos_end) # Add the genome build genome_label = "Human" build_id = "UCSC:{0}".format(genome_build) taxon_id = 'NCBITaxon:9606' geno.addGenome(taxon_id, genome_label) geno.addReferenceGenome(build_id, genome_build, taxon_id) # Add chromosome chrom_class_id = makeChromID(chromosome, '9606', 'CHR') # the chrom class (generic) id chrom_instance_id = makeChromID(chromosome, build_id, 'MONARCH') # first, add the chromosome class (in the taxon) geno.addChromosomeClass(chromosome, taxon_id, 'Human') # then, add the chromosome instance (from the given build) geno.addChromosomeInstance(chromosome, build_id, genome_build, chrom_class_id) # Add variant coordinates in reference to chromosome self._add_feature_with_coords(variant_id,genome_pos_start, genome_pos_end, chrom_instance_id, chrom_region_id) # Add mutation coordinates in reference to gene self._add_feature_with_coords(variant_id, bp_pos, bp_pos, transcript_curie, cdna_region_id) # Add nucleotide mutation gu.addTriple(self.graph, variant_id, geno.properties['reference_nucleotide'], ref_base, is_literal) gu.addTriple(self.graph, variant_id, geno.properties['altered_nucleotide'], variant_base, is_literal) """ Here we update any internal cgd variant IDS with a cosmic ID or dbSNP ID. Alternatively we could do this using sql rather than a sparql update which may be safer """ # Add SNP xrefs if cosmic_id is not None: cosmic_id_list = cosmic_id.split(', ') cosmic_curie_list = [] for c_id in cosmic_id_list: cosmic_curie = re.sub(r'COSM(\d+)', r'COSMIC:\1', c_id) cosmic_curie_list.append(cosmic_curie) gu.addIndividualToGraph(self.graph, cosmic_curie, c_id, geno.genoparts['missense_variant']) # If there are multiple ids set them equivalent to the first for curie in cosmic_curie_list[1:]: gu.addSameIndividual(self.graph, cosmic_curie_list[0], curie) self._replace_entity(self.graph, variant_id, cosmic_curie_list[0], self.bindings) if db_snp_id is not None: db_snp_curie = re.sub(r'rs(\d+)', r'dbSNP:\1', db_snp_id) gu.addIndividualToGraph(self.graph, db_snp_curie, db_snp_id, geno.genoparts['missense_variant']) if cosmic_id is None: self._replace_entity(self.graph, variant_id, db_snp_curie, self.bindings) else: cosmic_id_list = cosmic_id.split(', ') for c_id in cosmic_id_list: cosmic_curie = re.sub(r'COSM(\d+)', r'COSMIC:\1', c_id) gu.addSameIndividual(self.graph, cosmic_curie, db_snp_curie) return
def _add_variant_protein_variant_assoc_to_graph(self, row): """ Generates relationships between variants and protein variants given a row of data :param iterable: row of data, see add_variant_info_to_graph() docstring for expected structure :return None """ gu = GraphUtils(curie_map.get()) geno = Genotype(self.graph) is_missense = False is_literal = True (variant_key, variant_label, amino_acid_variant, amino_acid_position, transcript_id, transcript_priority, protein_variant_type, functional_impact, stop_gain_loss, transcript_gene, protein_variant_source) = row[0:11] variant_id = self.make_cgd_id('variant{0}'.format(variant_key)) transcript_curie = self._make_transcript_curie(transcript_id) uniprot_curie = self._make_uniprot_polypeptide_curie(transcript_id) ncbi_protein_curie = self._make_ncbi_polypeptide_curie(transcript_id) geno.addGenotype(variant_id, variant_label, geno.genoparts['sequence_alteration']) # Make fake amino acid sequence in case we # can't get a CCDS to Uniprot and/or NCBI Protein mapping aa_seq_id = self.make_cgd_id('transcript{0}'.format(amino_acid_variant)) # Add Transcript: geno.addTranscript(variant_id, transcript_curie, transcript_id, geno.genoparts['transcript']) # Add polypeptide if ncbi_protein_curie is not None: geno.addPolypeptide(ncbi_protein_curie, self.transcript_xrefs['RefSeq'][transcript_id], transcript_curie) aa_seq_id = ncbi_protein_curie if uniprot_curie is not None: geno.addPolypeptide(uniprot_curie, self.transcript_xrefs['UniProt'][transcript_id], transcript_curie) # Overrides ncbi_protein_curie, # but we set them as equal individuals below aa_seq_id = uniprot_curie if ncbi_protein_curie is not None and uniprot_curie is not None: gu.addSameIndividual(self.graph, ncbi_protein_curie, uniprot_curie) else: aa_seq_id = self.make_cgd_id('transcript{0}'.format(amino_acid_variant)) if protein_variant_type == 'nonsynonymous - missense' \ or re.search(r'missense', variant_label): is_missense = True geno.addGenotype(variant_id, variant_label, geno.genoparts['missense_variant']) # Get gene ID from gene map self._add_variant_gene_relationship(variant_id, transcript_gene) amino_acid_regex = re.compile(r'^p\.([A-Za-z]{1,3})(\d+)([A-Za-z]{1,3})$') if is_missense: match = re.match(amino_acid_regex, amino_acid_variant.rstrip()) else: match = None if match is not None: ref_amino_acid = match.group(1) position = match.group(2) altered_amino_acid = match.group(3) else: logger.debug("Could not parse amino acid information" " from {0} variant:" " {1} type: {2}".format(amino_acid_variant, variant_label, protein_variant_type)) # Add amino acid change to model if is_missense is True and match is not None: gu.addTriple(self.graph, variant_id, geno.properties['reference_amino_acid'], ref_amino_acid, is_literal) gu.addTriple(self.graph, variant_id, geno.properties['results_in_amino_acid_change'], altered_amino_acid, is_literal) aa_region_id = ":_{0}{1}{2}Region".format(position, position, aa_seq_id) self._add_feature_with_coords(variant_id, position, position, aa_seq_id, aa_region_id) return
class OMIA(Source): """ This is the parser for the [Online Mendelian Inheritance in Animals (OMIA)](http://www.http://omia.angis.org.au), from which we process inherited disorders, other (single-locus) traits, and genes in >200 animal species (other than human and mouse and rats). We generate the omia graph to include the following information: * genes * animal taxonomy, and breeds as instances of those taxa (breeds are akin to "strains" in other taxa) * animal diseases, along with species-specific subtypes of those diseases * publications (and their mapping to PMIDs, if available) * gene-to-phenotype associations (via an anonymous variant-locus * breed-to-phenotype associations We make links between OMIA and OMIM in two ways: 1. mappings between OMIA and OMIM are created as OMIA --> hasdbXref OMIM 2. mappings between a breed and OMIA disease are created to be a model for the mapped OMIM disease, IF AND ONLY IF it is a 1:1 mapping. there are some 1:many mappings, and these often happen if the OMIM item is a gene. Because many of these species are not covered in the PANTHER orthology datafiles, we also pull any orthology relationships from the gene_group files from NCBI. """ files = { 'data': { 'file': 'omia.xml.gz', 'url': 'http://omia.angis.org.au/dumps/omia.xml.gz'}, } def __init__(self): Source.__init__(self, 'omia') self.load_bindings() self.dataset = Dataset( 'omia', 'Online Mendelian Inheritance in Animals', 'http://omia.angis.org.au', None, None, 'http://sydney.edu.au/disclaimer.shtml') self.id_hash = { 'article': {}, 'phene': {}, 'breed': {}, 'taxon': {}, 'gene': {} } self.label_hash = {} self.gu = GraphUtils(curie_map.get()) # used to store the omia to omim phene mappings self.omia_omim_map = {} # used to store the unique genes that have phenes # (for fetching orthology) self.annotated_genes = set() self.test_ids = { 'disease': [ 'OMIA:001702', 'OMIA:001867', 'OMIA:000478', 'OMIA:000201', 'OMIA:000810', 'OMIA:001400'], 'gene': [ 492297, 434, 492296, 3430235, 200685834, 394659996, 200685845, 28713538, 291822383], 'taxon': [9691, 9685, 9606, 9615, 9913, 93934, 37029, 9627, 9825], # to be filled in during parsing of breed table # for lookup by breed-associations 'breed': [] } # to store a map of omia ids and any molecular info # to write a report for curation self.stored_omia_mol_gen = {} self.g = self.graph self.geno = Genotype(self.g) return def fetch(self, is_dl_forced=False): """ :param is_dl_forced: :return: """ self.get_files(is_dl_forced) ncbi = NCBIGene() # ncbi.fetch() gene_group = ncbi.files['gene_group'] self.fetch_from_url( gene_group['url'], '/'.join((ncbi.rawdir, gene_group['file'])), False) return def parse(self, limit=None): # names of tables to iterate - probably don't need all these: # Article_Breed, Article_Keyword, Article_Gene, Article_Keyword, # Article_People, Article_Phene, Articles, Breed, Breed_Phene, # Genes_gb, Group_Categories, Group_MPO, Inherit_Type, Keywords, # Landmark, Lida_Links, OMIA_Group, OMIA_author, Omim_Xref, People, # Phene, Phene_Gene, Publishers, Resources, Species_gb, Synonyms self.scrub() if limit is not None: logger.info("Only parsing first %d rows", limit) logger.info("Parsing files...") if self.testOnly: self.testMode = True if self.testMode: self.g = self.testgraph else: self.g = self.graph self.geno = Genotype(self.g) # we do three passes through the file # first process species (two others reference this one) self.process_species(limit) # then, process the breeds, genes, articles, and other static stuff self.process_classes(limit) # next process the association data self.process_associations(limit) # process the vertebrate orthology for genes # that are annotated with phenotypes ncbi = NCBIGene() ncbi.add_orthologs_by_gene_group(self.g, self.annotated_genes) self.load_core_bindings() self.load_bindings() logger.info("Done parsing.") self.write_molgen_report() return def scrub(self): """ The XML file seems to have mixed-encoding; we scrub out the control characters from the file for processing. :return: """ logger.info( "Scrubbing out the nasty characters that break our parser.") myfile = '/'.join((self.rawdir, self.files['data']['file'])) tmpfile = '/'.join((self.rawdir, self.files['data']['file']+'.tmp.gz')) t = gzip.open(tmpfile, 'wb') du = DipperUtil() with gzip.open(myfile, 'rb') as f: filereader = io.TextIOWrapper(f, newline="") for l in filereader: l = du.remove_control_characters(l) + '\n' t.write(l.encode('utf-8')) t.close() # move the temp file logger.info("Replacing the original data with the scrubbed file.") shutil.move(tmpfile, myfile) return # ###################### XML LOOPING FUNCTIONS ################## def process_species(self, limit): """ Loop through the xml file and process the species. We add elements to the graph, and store the id-to-label in the label_hash dict. :param limit: :return: """ myfile = '/'.join((self.rawdir, self.files['data']['file'])) f = gzip.open(myfile, 'rb') filereader = io.TextIOWrapper(f, newline="") filereader.readline() # remove the xml declaration line for event, elem in ET.iterparse(filereader): # Species ids are == genbank species ids! self.process_xml_table( elem, 'Species_gb', self._process_species_table_row, limit) f.close() return def process_classes(self, limit): """ Loop through the xml file and process the articles, breed, genes, phenes, and phenotype-grouping classes. We add elements to the graph, and store the id-to-label in the label_hash dict, along with the internal key-to-external id in the id_hash dict. The latter are referenced in the association processing functions. :param limit: :return: """ myfile = '/'.join((self.rawdir, self.files['data']['file'])) f = gzip.open(myfile, 'rb') filereader = io.TextIOWrapper(f, newline="") filereader.readline() # remove the xml declaration line parser = ET.XMLParser(encoding='utf-8') for event, elem in ET.iterparse(filereader, parser=parser): self.process_xml_table( elem, 'Articles', self._process_article_row, limit) self.process_xml_table( elem, 'Breed', self._process_breed_row, limit) self.process_xml_table( elem, 'Genes_gb', self._process_gene_row, limit) self.process_xml_table( elem, 'OMIA_Group', self._process_omia_group_row, limit) self.process_xml_table( elem, 'Phene', self._process_phene_row, limit) self.process_xml_table( elem, 'Omim_Xref', self._process_omia_omim_map, limit) f.close() # post-process the omia-omim associations to filter out the genes # (keep only phenotypes/diseases) self.clean_up_omim_genes() return def process_associations(self, limit): """ Loop through the xml file and process the article-breed, article-phene, breed-phene, phene-gene associations, and the external links to LIDA. :param limit: :return: """ myfile = '/'.join((self.rawdir, self.files['data']['file'])) f = gzip.open(myfile, 'rb') filereader = io.TextIOWrapper(f, newline="") filereader.readline() # remove the xml declaration line for event, elem in ET.iterparse(filereader): self.process_xml_table( elem, 'Article_Breed', self._process_article_breed_row, limit) self.process_xml_table( elem, 'Article_Phene', self._process_article_phene_row, limit) self.process_xml_table( elem, 'Breed_Phene', self._process_breed_phene_row, limit) self.process_xml_table( elem, 'Lida_Links', self._process_lida_links_row, limit) self.process_xml_table( elem, 'Phene_Gene', self._process_phene_gene_row, limit) self.process_xml_table( elem, 'Group_MPO', self._process_group_mpo_row, limit) f.close() return # ############ INDIVIDUAL TABLE-LEVEL PROCESSING FUNCTIONS ################ def _process_species_table_row(self, row): # gb_species_id, sci_name, com_name, added_by, date_modified tax_id = 'NCBITaxon:'+str(row['gb_species_id']) sci_name = row['sci_name'] com_name = row['com_name'] if self.testMode and \ (int(row['gb_species_id']) not in self.test_ids['taxon']): return self.gu.addClassToGraph(self.g, tax_id, sci_name) if com_name != '': self.gu.addSynonym(self.g, tax_id, com_name) self.label_hash[tax_id] = com_name # for lookup later else: self.label_hash[tax_id] = sci_name return def _process_breed_row(self, row): # in test mode, keep all breeds of our test species if self.testMode and \ (int(row['gb_species_id']) not in self.test_ids['taxon']): return # save the breed keys in the test_ids for later processing self.test_ids['breed'] += [int(row['breed_id'])] breed_id = self.make_breed_id(row['breed_id']) self.id_hash['breed'][row['breed_id']] = breed_id tax_id = 'NCBITaxon:'+str(row['gb_species_id']) breed_label = row['breed_name'] species_label = self.label_hash.get(tax_id) if species_label is not None: breed_label = breed_label + ' ('+species_label+')' self.gu.addIndividualToGraph(self.g, breed_id, breed_label, tax_id) self.label_hash[breed_id] = breed_label return def _process_phene_row(self, row): phenotype_id = None sp_phene_label = row['phene_name'] if sp_phene_label == '': sp_phene_label = None if 'omia_id' not in row: logger.info("omia_id not present for %s", row['phene_id']) omia_id = self._make_internal_id('phene', phenotype_id) else: omia_id = 'OMIA:'+str(row['omia_id']) if self.testMode and not\ (int(row['gb_species_id']) in self.test_ids['taxon'] and omia_id in self.test_ids['disease']): return # add to internal hash store for later lookup self.id_hash['phene'][row['phene_id']] = omia_id descr = row['summary'] if descr == '': descr = None # omia label omia_label = self.label_hash.get(omia_id) # add the species-specific subclass (TODO please review this choice) gb_species_id = row['gb_species_id'] if gb_species_id != '': sp_phene_id = '-'.join((omia_id, gb_species_id)) else: logger.error( "No species supplied in species-specific phene table for %s", omia_id) return species_id = 'NCBITaxon:'+str(gb_species_id) # use this instead species_label = self.label_hash.get('NCBITaxon:'+gb_species_id) if sp_phene_label is None and \ omia_label is not None and species_label is not None: sp_phene_label = ' '.join((omia_label, 'in', species_label)) self.gu.addClassToGraph( self.g, sp_phene_id, sp_phene_label, omia_id, descr) # add to internal hash store for later lookup self.id_hash['phene'][row['phene_id']] = sp_phene_id self.label_hash[sp_phene_id] = sp_phene_label # add each of the following descriptions, # if they are populated, with a tag at the end. for item in [ 'clin_feat', 'history', 'pathology', 'mol_gen', 'control']: if row[item] is not None and row[item] != '': self.gu.addDescription( self.g, sp_phene_id, row[item] + ' ['+item+']') # if row['symbol'] is not None: # species-specific # CHECK ME - sometimes spaces or gene labels # gu.addSynonym(g, sp_phene, row['symbol']) self.gu.addOWLPropertyClassRestriction( self.g, sp_phene_id, self.gu.object_properties['in_taxon'], species_id) # add inheritance as an association inheritance_id = self._map_inheritance_term_id(row['inherit']) if inheritance_id is not None: assoc = DispositionAssoc(self.name, sp_phene_id, inheritance_id) assoc.add_association_to_graph(self.g) if row['characterised'] == 'Yes': self.stored_omia_mol_gen[omia_id] = { 'mol_gen': row['mol_gen'], 'map_info': row['map_info'], 'species': row['gb_species_id']} return def write_molgen_report(self): import csv logger.info("Writing G2P report for OMIA") f = '/'.join((self.outdir, 'omia_molgen_report.txt')) with open(f, 'w', newline='\n') as csvfile: writer = csv.writer(csvfile, delimiter='\t') # write header h = ['omia_id', 'molecular_description', 'mapping_info', 'species'] writer.writerow(h) for phene in self.stored_omia_mol_gen: writer.writerow((str(phene), self.stored_omia_mol_gen[phene]['mol_gen'], self.stored_omia_mol_gen[phene]['map_info'], self.stored_omia_mol_gen[phene]['species'])) logger.info( "Wrote %d potential G2P descriptions for curation to %s", len(self.stored_omia_mol_gen), f) return def _process_article_row(self, row): # don't bother in test mode if self.testMode: return iarticle_id = self._make_internal_id('article', row['article_id']) self.id_hash['article'][row['article_id']] = iarticle_id rtype = None if row['journal'] != '': rtype = Reference.ref_types['journal_article'] r = Reference(iarticle_id, rtype) if row['title'] is not None: r.setTitle(row['title'].strip()) if row['year'] is not None: r.setYear(row['year']) r.addRefToGraph(self.g) if row['pubmed_id'] is not None: pmid = 'PMID:'+str(row['pubmed_id']) self.id_hash['article'][row['article_id']] = pmid self.gu.addSameIndividual(self.g, iarticle_id, pmid) self.gu.addComment(self.g, pmid, iarticle_id) return def _process_omia_group_row(self, row): omia_id = 'OMIA:'+row['omia_id'] if self.testMode and omia_id not in self.test_ids['disease']: return group_name = row['group_name'] group_summary = row['group_summary'] disease_id = None group_category = row.get('group_category') disease_id = \ self.map_omia_group_category_to_ontology_id(group_category) if disease_id is not None: self.gu.addClassToGraph(self.g, disease_id, None) if disease_id == 'MP:0008762': # embryonic lethal # add this as a phenotype association # add embryonic onset assoc = D2PAssoc(self.name, omia_id, disease_id) assoc.add_association_to_graph(self.g) disease_id = None else: logger.info( "No disease superclass defined for %s: %s", omia_id, group_name) # default to general disease FIXME this may not be desired disease_id = 'DOID:4' if group_summary == '': group_summary = None if group_name == '': group_name = None self.gu.addClassToGraph( self.g, omia_id, group_name, disease_id, group_summary) self.label_hash[omia_id] = group_name return def _process_gene_row(self, row): if self.testMode and row['gene_id'] not in self.test_ids['gene']: return gene_id = 'NCBIGene:'+str(row['gene_id']) self.id_hash['gene'][row['gene_id']] = gene_id gene_label = row['symbol'] self.label_hash[gene_id] = gene_label tax_id = 'NCBITaxon:'+str(row['gb_species_id']) gene_type_id = NCBIGene.map_type_of_gene(row['gene_type']) self.gu.addClassToGraph(self.g, gene_id, gene_label, gene_type_id) self.geno.addTaxon(tax_id, gene_id) return def _process_article_breed_row(self, row): # article_id, breed_id, added_by # don't bother putting these into the test... too many! # and int(row['breed_id']) not in self.test_ids['breed']: if self.testMode: return article_id = self.id_hash['article'].get(row['article_id']) breed_id = self.id_hash['breed'].get(row['breed_id']) # there's some missing data (article=6038). in that case skip if article_id is not None: self.gu.addTriple( self.g, article_id, self.gu.object_properties['is_about'], breed_id) else: logger.warning("Missing article key %s", str(row['article_id'])) return def _process_article_phene_row(self, row): """ Linking articles to species-specific phenes. :param row: :return: """ # article_id, phene_id, added_by # look up the article in the hashmap phenotype_id = self.id_hash['phene'].get(row['phene_id']) article_id = self.id_hash['article'].get(row['article_id']) omia_id = self._get_omia_id_from_phene_id(phenotype_id) if self.testMode and omia_id not in self.test_ids['disease'] \ or phenotype_id is None or article_id is None: return # make a triple, where the article is about the phenotype self.gu.addTriple( self.g, article_id, self.gu.object_properties['is_about'], phenotype_id) return def _process_breed_phene_row(self, row): # Linking disorders/characteristic to breeds # breed_id, phene_id, added_by breed_id = self.id_hash['breed'].get(row['breed_id']) phene_id = self.id_hash['phene'].get(row['phene_id']) # get the omia id omia_id = self._get_omia_id_from_phene_id(phene_id) if (self.testMode and not ( omia_id in self.test_ids['disease'] and int(row['breed_id']) in self.test_ids['breed']) or breed_id is None or phene_id is None): return # FIXME we want a different relationship here assoc = G2PAssoc( self.name, breed_id, phene_id, self.gu.object_properties['has_phenotype']) assoc.add_association_to_graph(self.g) # add that the breed is a model of the human disease # use the omia-omim mappings for this # we assume that we have already scrubbed out the genes # from the omim list, so we can make the model associations here omim_ids = self.omia_omim_map.get(omia_id) eco_id = "ECO:0000214" # biological aspect of descendant evidence if omim_ids is not None and len(omim_ids) > 0: if len(omim_ids) > 1: logger.info( "There's 1:many omia:omim mapping: %s, %s", omia_id, str(omim_ids)) for i in omim_ids: assoc = G2PAssoc( self.name, breed_id, i, self.gu.object_properties['model_of']) assoc.add_evidence(eco_id) assoc.add_association_to_graph(self.g) aid = assoc.get_association_id() breed_label = self.label_hash.get(breed_id) if breed_label is None: breed_label = "this breed" m = re.search(r'\((.*)\)', breed_label) if m: sp_label = m.group(1) else: sp_label = '' phene_label = self.label_hash.get(phene_id) if phene_label is None: phene_label = "phenotype" elif phene_label.endswith(sp_label): # some of the labels we made already include the species; # remove it to make a cleaner desc phene_label = re.sub(r' in '+sp_label, '', phene_label) desc = ' '.join( ("High incidence of", phene_label, "in", breed_label, "suggests it to be a model of disease", i + ".")) self.gu.addDescription(self.g, aid, desc) return def _process_lida_links_row(self, row): # lidaurl, omia_id, added_by omia_id = 'OMIA:'+row['omia_id'] lidaurl = row['lidaurl'] if self.testMode and omia_id not in self.test_ids['disease']: return self.gu.addXref(self.g, omia_id, lidaurl, True) return def _process_phene_gene_row(self, row): gene_id = self.id_hash['gene'].get(row['gene_id']) phene_id = self.id_hash['phene'].get(row['phene_id']) omia_id = self._get_omia_id_from_phene_id(phene_id) if self.testMode and not ( omia_id in self.test_ids['disease'] and row['gene_id'] in self.test_ids['gene']) or\ gene_id is None or phene_id is None: return # occasionally some phenes are missing! (ex: 406) if phene_id is None: logger.warning("Phene id %s is missing", str(row['phene_id'])) return gene_label = self.label_hash[gene_id] # some variant of gene_id has phenotype d vl = '_'+re.sub(r'NCBIGene:', '', str(gene_id)) + 'VL' if self.nobnodes: vl = ':'+vl self.geno.addAllele(vl, 'some variant of ' + gene_label) self.geno.addAlleleOfGene(vl, gene_id) assoc = G2PAssoc(self.name, vl, phene_id) assoc.add_association_to_graph(self.g) # add the gene id to the set of annotated genes # for later lookup by orthology self.annotated_genes.add(gene_id) return def _process_omia_omim_map(self, row): """ Links OMIA groups to OMIM equivalents. :param row: :return: """ # omia_id, omim_id, added_by omia_id = 'OMIA:'+row['omia_id'] omim_id = 'OMIM:'+row['omim_id'] # also store this for use when we say that a given animal is # a model of a disease if omia_id not in self.omia_omim_map: self.omia_omim_map[omia_id] = set() self.omia_omim_map[omia_id].add(omim_id) if self.testMode and omia_id not in self.test_ids['disease']: return self.gu.addXref(self.g, omia_id, omim_id) return def map_omia_group_category_to_ontology_id(self, category_num): """ Using the category number in the OMIA_groups table, map them to a disease id. This may be superceeded by other MONDO methods. Platelet disorders will be more specific once https://github.com/obophenotype/human-disease-ontology/issues/46 is fulfilled. :param category_num: :return: """ category_map = { 1: 'DOID:0014667', # Inborn error of metabolism 2: 'MESH:D004392', # Dwarfism 3: 'DOID:1682', # congenital heart disease 4: 'DOID:74', # blood system disease 5: 'DOID:3211', # lysosomal storage disease 6: 'DOID:16', # integumentary system disease # --> retinal degeneration ==> OMIA:000830 7: 'DOID:8466', # progressive retinal atrophy 8: 'DOID:0050572', # Cone–rod dystrophy 9: 'MESH:C536122', # stationary night blindness 10: 'Orphanet:98553', # developmental retinal disorder 11: 'DOID:5679', # retinal disorder 12: 'Orphanet:90771', # Disorder of Sex Development # - what to do about this one? 13: 'MP:0008762', # embryonic lethal # - not sure what to do with this 14: None, # blood group # FIXME make me more specific 15: 'DOID:2218', # intrinsic platelet disorder # FIXME make me more specific 16: 'DOID:2218', # extrinsic platelet disorder 17: None # transgenic ??? } disease_id = None if category_num is not None and int(category_num) in category_map: disease_id = category_map.get(int(category_num)) logger.info( "Found %s for category %s", str(disease_id), str(category_num)) else: logger.info( "There's a group category I don't know anything about: %s", str(category_num)) return disease_id def _process_group_mpo_row(self, row): """ Make OMIA to MP associations :param row: :return: """ omia_id = 'OMIA:'+row['omia_id'] mpo_num = int(row['MPO_no']) mpo_id = 'MP:'+str(mpo_num).zfill(7) assoc = D2PAssoc(self.name, omia_id, mpo_id) assoc.add_association_to_graph(self.g) return def clean_up_omim_genes(self): omim = OMIM() # get all the omim ids allomimids = set() for omia in self.omia_omim_map: allomimids.update(self.omia_omim_map[omia]) entries_that_are_phenotypes = omim.process_entries( list(allomimids), filter_keep_phenotype_entry_ids, None, None) logger.info( "Filtered out %d/%d entries that are genes or features", len(allomimids)-len(entries_that_are_phenotypes), len(allomimids)) # now iterate again and remove those non-phenotype ids removed_count = 0 for omia in self.omia_omim_map: ids = self.omia_omim_map[omia] cleanids = set() for i in ids: if i in entries_that_are_phenotypes: cleanids.add(i) else: removed_count += 1 # keep track of how many we've removed self.omia_omim_map[omia] = cleanids logger.info( "Removed %d omim ids from the omia-to-omim map", removed_count) return def _make_internal_id(self, prefix, key): iid = '_'+''.join(('omia', prefix, 'key', str(key))) if self.nobnodes: iid = ':'+iid return iid def make_breed_id(self, key): breed_id = 'OMIA-breed:'+str(key) return breed_id @staticmethod def _get_omia_id_from_phene_id(phene_id): omia_id = None if phene_id is not None: m = re.match(r'OMIA:\d+', str(phene_id)) if m: omia_id = m.group(0) return omia_id @staticmethod def _map_inheritance_term_id(inheritance_symbol): inherit_map = { 'A': None, # Autosomal 'ACD': 'GENO:0000143', # Autosomal co-dominant 'ADV': None, # autosomal dominant with variable expressivity 'AID': 'GENO:0000259', # autosomal incompletely dominant 'ASD': 'GENO:0000145', # autosomal semi-dominant # autosomal recessive, semi-lethal # using generic autosomal recessive 'ASL': 'GENO:0000150', 'D': 'GENO:0000147', # autosomal dominant 'M': None, # multifactorial 'MAT': None, # Maternal # probably autosomal recessive # using generic autosomal recessive 'PR': 'GENO:0000150', 'R': 'GENO:0000150', # Autosomal Recessive # Recessive Embryonic Lethal # using plain recessive 'REL': 'GENO:0000148', # Autosomal Recessive Lethal # using plain autosomal recessive 'RL': 'GENO:0000150', 'S': 'GENO:0000146', # Sex-linked <--using allosomal dominant 'SLi': None, # Sex-limited 'UD': 'GENO:0000144', # Dominant 'X': None, # x-linked # HP:0001417 ? # X-linked Dominant <-- temp using allosomal dominant FIXME 'XLD': 'GENO:0000146', # X-linked Recessive <-- temp using allosomal recessive FIXME 'XLR': 'GENO:0000149', 'Y': None, # Y-linked 'Z': None, # Z-linked # Z-linked recessive <-- temp using allosomal recessive FIXME 'ZR': 'GENO:0000149', '999': None, # Z-linked incompletely dominant } inheritance_id = inherit_map.get(inheritance_symbol) if inheritance_id is None and inheritance_symbol is not None: logger.warning( "No inheritance id is mapped for %s", inheritance_symbol) return inheritance_id def getTestSuite(self): import unittest from tests.test_omia import OMIATestCase test_suite = unittest.TestLoader().loadTestsFromTestCase(OMIATestCase) return test_suite
def _get_gene_info(self, limit): """ Currently loops through the gene_info file and creates the genes as classes, typed with SO. It will add their label, any alternate labels as synonyms, alternate ids as equivlaent classes. HPRDs get added as protein products. The chromosome and chr band get added as blank node regions, and the gene is faldo:located on the chr band. :param limit: :return: """ gu = GraphUtils(curie_map.get()) if self.testMode: g = self.testgraph else: g = self.graph geno = Genotype(g) # not unzipping the file logger.info("Processing Gene records") line_counter = 0 myfile = '/'.join((self.rawdir, self.files['gene_info']['file'])) logger.info("FILE: %s", myfile) # Add taxa and genome classes for those in our filter for tax_num in self.tax_ids: tax_id = ':'.join(('NCBITaxon', str(tax_num))) # tax label can get added elsewhere geno.addGenome(tax_id, str(tax_num)) # label added elsewhere gu.addClassToGraph(g, tax_id, None) with gzip.open(myfile, 'rb') as f: for line in f: # skip comments line = line.decode().strip() if re.match(r'^#', line): continue (tax_num, gene_num, symbol, locustag, synonyms, xrefs, chrom, map_loc, desc, gtype, authority_symbol, name, nomenclature_status, other_designations, modification_date) = line.split('\t') # ##set filter=None in init if you don't want to have a filter # if self.filter is not None: # if ((self.filter == 'taxids' and \ # (int(tax_num) not in self.tax_ids)) # or (self.filter == 'geneids' and \ # (int(gene_num) not in self.gene_ids))): # continue # #### end filter if self.testMode and int(gene_num) not in self.gene_ids: continue if not self.testMode and int(tax_num) not in self.tax_ids: continue line_counter += 1 gene_id = ':'.join(('NCBIGene', gene_num)) tax_id = ':'.join(('NCBITaxon', tax_num)) gene_type_id = self.map_type_of_gene(gtype.strip()) if symbol == 'NEWENTRY': label = None else: label = symbol # sequence feature, not a gene if gene_type_id == 'SO:0000110': self.class_or_indiv[gene_id] = 'I' else: self.class_or_indiv[gene_id] = 'C' if not self.testMode and \ limit is not None and line_counter > limit: continue if self.class_or_indiv[gene_id] == 'C': gu.addClassToGraph(g, gene_id, label, gene_type_id, desc) # NCBI will be the default leader, # so we will not add the leader designation here. else: gu.addIndividualToGraph( g, gene_id, label, gene_type_id, desc) # in this case, they aren't genes. # so we want someone else to be the leader. if name != '-': gu.addSynonym(g, gene_id, name) if synonyms.strip() != '-': for s in synonyms.split('|'): gu.addSynonym( g, gene_id, s.strip(), Assoc.annotation_properties['hasRelatedSynonym']) if other_designations.strip() != '-': for s in other_designations.split('|'): gu.addSynonym( g, gene_id, s.strip(), Assoc.annotation_properties['hasRelatedSynonym']) # deal with the xrefs # MIM:614444|HGNC:HGNC:16851|Ensembl:ENSG00000136828|HPRD:11479|Vega:OTTHUMG00000020696 if xrefs.strip() != '-': for r in xrefs.strip().split('|'): fixedr = self._cleanup_id(r) if fixedr is not None and fixedr.strip() != '': if re.match(r'HPRD', fixedr): # proteins are not == genes. gu.addTriple( g, gene_id, self.properties[ 'has_gene_product'], fixedr) else: # skip some of these for now if fixedr.split(':')[0] not in [ 'Vega', 'IMGT/GENE-DB']: if self.class_or_indiv.get(gene_id) == 'C': gu.addEquivalentClass( g, gene_id, fixedr) else: gu.addSameIndividual( g, gene_id, fixedr) # edge cases of id | symbol | chr | map_loc: # 263 AMD1P2 X|Y with Xq28 and Yq12 # 438 ASMT X|Y with Xp22.3 or Yp11.3 # in PAR # no idea why there's two bands listed - possibly 2 assemblies # 419 ART3 4 with 4q21.1|4p15.1-p14 # 28227 PPP2R3B X|Y Xp22.33; Yp11.3 # in PAR # this is of "unknown" type == susceptibility # 619538 OMS 10|19|3 10q26.3;19q13.42-q13.43;3p25.3 # unlocated scaffold # 101928066 LOC101928066 1|Un -\ # mouse --> 2C3 # 11435 Chrna1 2 2 C3|2 43.76 cM # mouse --> 11B1.1 # 11548 Adra1b 11 11 B1.1|11 25.81 cM # 11717 Ampd3 7 7 57.85 cM|7 E2-E3 # mouse # 14421 B4galnt1 10 10 D3|10 74.5 cM # mouse # 323212 wu:fb92e12 19|20 - # fish # 323368 ints10 6|18 - # fish # 323666 wu:fc06e02 11|23 - # fish # feel that the chr placement can't be trusted in this table # when there is > 1 listed # with the exception of human X|Y, # we will only take those that align to one chr # FIXME remove the chr mapping below # when we pull in the genomic coords if str(chrom) != '-' and str(chrom) != '': if re.search(r'\|', str(chrom)) and \ str(chrom) not in ['X|Y', 'X; Y']: # means that there's uncertainty in the mapping. # so skip it # TODO we'll need to figure out how to deal with # >1 loc mapping logger.info( '%s is non-uniquely mapped to %s.' + ' Skipping for now.', gene_id, str(chr)) continue # X|Y Xp22.33;Yp11.3 # if(not re.match( # r'(\d+|(MT)|[XY]|(Un)$',str(chr).strip())): # print('odd chr=',str(chr)) if str(chrom) == 'X; Y': chrom = 'X|Y' # rewrite the PAR regions for processing # do this in a loop to allow PAR regions like X|Y for c in re.split(r'\|', str(chrom)): # assume that the chromosome label is added elsewhere geno.addChromosomeClass(c, tax_id, None) mychrom = makeChromID(c, tax_num, 'CHR') # temporarily use taxnum for the disambiguating label mychrom_syn = makeChromLabel(c, tax_num) gu.addSynonym(g, mychrom, mychrom_syn) band_match = re.match( r'[0-9A-Z]+[pq](\d+)?(\.\d+)?$', map_loc) if band_match is not None and \ len(band_match.groups()) > 0: # if tax_num != '9606': # continue # this matches the regular kind of chrs, # so make that kind of band # not sure why this matches? # chrX|Y or 10090chr12|Un" # TODO we probably need a different regex # per organism # the maploc_id already has the numeric chromosome # in it, strip it first bid = re.sub(r'^'+c, '', map_loc) # the generic location (no coordinates) maploc_id = makeChromID(c+bid, tax_num, 'CHR') # print(map_loc,'-->',bid,'-->',maploc_id) # Assume it's type will be added elsewhere band = Feature(maploc_id, None, None) band.addFeatureToGraph(g) # add the band as the containing feature gu.addTriple( g, gene_id, Feature.object_properties['is_subsequence_of'], maploc_id) else: # TODO handle these cases: examples are: # 15q11-q22,Xp21.2-p11.23,15q22-qter,10q11.1-q24, # 12p13.3-p13.2|12p13-p12,1p13.3|1p21.3-p13.1, # 12cen-q21,22q13.3|22q13.3 logger.debug( 'not regular band pattern for %s: %s', gene_id, map_loc) # add the gene as a subsequence of the chromosome gu.addTriple( g, gene_id, Feature.object_properties['is_subsequence_of'], mychrom) geno.addTaxon(tax_id, gene_id) gu.loadProperties(g, Feature.object_properties, gu.OBJPROP) gu.loadProperties(g, Feature.data_properties, gu.DATAPROP) gu.loadProperties(g, Genotype.object_properties, gu.OBJPROP) gu.loadAllProperties(g) return
class UCSCBands(Source): """ This will take the UCSC defintions of cytogenic bands and create the nested structures to enable overlap and containment queries. We use ```Monochrom.py``` to create the OWL-classes of the chromosomal parts. Here, we simply worry about the instance-level values for particular genome builds. Given a chr band definition, the nested containment structures look like: 13q21.31 ==> 13q21.31, 13q21.3, 13q21, 13q2, 13q, 13 We determine the containing regions of the band by parsing the band-string; since each alphanumeric is a significant "place", we can split it with the shorter strings being parents of the longer string Here we create build-specific chroms, which are instances of the classes produced from ```Monochrom.py```. You can instantiate any number of builds for a genome. We leverage the Faldo model here for region definitions, and map each of the chromosomal parts to SO. We differentiate the build by adding the build id to the identifier prior to the chromosome number. These then are instances of the species-specific chromosomal class. The build-specific chromosomes are created like: <pre> <build number>chr<num><band> with triples for a given band like: :hg19chr1p36.33 rdf[type] SO:chromosome_band, faldo:Region, CHR:9606chr1p36.33 :hg19chr1p36.33 subsequence_of :hg19chr1p36.3 :hg19chr1p36.33 faldo:location [ a faldo:BothStrandPosition faldo:begin 0, faldo:end 2300000, faldo:reference 'hg19'] </pre> where any band in the file is an instance of a chr_band (or a more specific type), is a subsequence of it's containing region, \ and is located in the specified coordinates. We do not have a separate graph for testing. TODO: any species by commandline argument """ files = { # TODO accommodate multiple builds per species '9606': { 'file': 'hg19cytoBand.txt.gz', 'url': 'http://hgdownload.cse.ucsc.edu/goldenPath/hg19/database/cytoBand.txt.gz', 'build_num': 'hg19', 'genome_label': 'Human' }, '10090': { 'file': 'mm10cytoBand.txt.gz', 'url': 'http://hgdownload.cse.ucsc.edu/goldenPath/mm10/database/cytoBandIdeo.txt.gz', 'build_num': 'mm10', 'genome_label': 'Mouse' }, # Note that there are no bands, # arms or staining components for the species below at the moment '7955': { 'file': 'danRer10cytoBand.txt.gz', 'url': 'http://hgdownload.cse.ucsc.edu/goldenPath/danRer10/database/cytoBandIdeo.txt.gz', 'build_num': 'danRer10', 'genome_label': 'Zebrafish' }, '9913': { 'file': 'bosTau7cytoBand.txt.gz', 'url': 'http://hgdownload.cse.ucsc.edu/goldenPath/bosTau7/database/cytoBandIdeo.txt.gz', 'build_num': 'bosTau7', 'genome_label': 'cow' }, '9031': { 'file': 'galGal4cytoBand.txt.gz', 'url': 'http://hgdownload.cse.ucsc.edu/goldenPath/galGal4/database/cytoBandIdeo.txt.gz', 'build_num': 'galGal4', 'genome_label': 'chicken' }, '9823': { 'file': 'susScr3cytoBand.txt.gz', 'url': 'http://hgdownload.cse.ucsc.edu/goldenPath/susScr3/database/cytoBandIdeo.txt.gz', 'build_num': 'susScr3', 'genome_label': 'pig' }, '9940': { 'file': 'oviAri3cytoBand.txt.gz', 'url': 'http://hgdownload.cse.ucsc.edu/goldenPath/oviAri3/database/cytoBandIdeo.txt.gz', 'build_num': 'oviAri3', 'genome_label': 'sheep' }, '9796': { 'file': 'equCab2cytoBand.txt.gz', 'url': 'http://hgdownload.cse.ucsc.edu/goldenPath/equCab2/database/cytoBandIdeo.txt.gz', 'build_num': 'equCab2', 'genome_label': 'horse' }, # TODO rainbow trout, 8022, when available } def __init__(self, tax_ids=None): super().__init__('ucscbands') self.tax_ids = tax_ids self.load_bindings() self.gu = GraphUtils(curie_map.get()) # Defaults if self.tax_ids is None: # self.tax_ids = [9606, 10090, 7955] self.tax_ids = [9606, 10090, 7955, 9913, 9031, 9823, 9940, 9796] # TODO add other species as defaults self._check_tax_ids() self.dataset = Dataset('ucscbands', 'UCSC Cytogenic Bands', 'http://hgdownload.cse.ucsc.edu', None, 'http://genome.ucsc.edu/license/') # data-source specific warnings # (will be removed when issues are cleared) return def fetch(self, is_dl_forced=False): self.get_files(is_dl_forced) return def parse(self, limit=None): if limit is not None: logger.info("Only parsing first %d rows", limit) logger.info("Parsing files...") if self.testOnly: self.testMode = True for taxon in self.tax_ids: self._get_chrbands(limit, str(taxon)) self._create_genome_builds() self.load_core_bindings() self.load_bindings() # using the full graph as the test here self.testgraph = self.graph logger.info("Found %d nodes", len(self.graph)) logger.info("Done parsing files.") return def _get_chrbands(self, limit, taxon): """ :param limit: :return: """ # TODO PYLINT figure out what limit was for and why it is unused line_counter = 0 myfile = '/'.join((self.rawdir, self.files[taxon]['file'])) logger.info("Processing Chr bands from FILE: %s", myfile) geno = Genotype(self.graph) monochrom = Monochrom() # used to hold band definitions for a chr # in order to compute extent of encompasing bands mybands = {} # build the organism's genome from the taxon genome_label = self.files[taxon]['genome_label'] taxon_id = 'NCBITaxon:'+taxon # add the taxon as a class. adding the class label elsewhere self.gu.addClassToGraph(self.graph, taxon_id, None) self.gu.addSynonym(self.graph, taxon_id, genome_label) self.gu.loadObjectProperties(self.graph, Feature.object_properties) self.gu.loadProperties(self.graph, Feature.data_properties, self.gu.DATAPROP) self.gu.loadAllProperties(self.graph) geno.addGenome(taxon_id, genome_label) # add the build and the taxon it's in build_num = self.files[taxon]['build_num'] build_id = 'UCSC:'+build_num geno.addReferenceGenome(build_id, build_num, taxon_id) # process the bands with gzip.open(myfile, 'rb') as f: for line in f: # skip comments line = line.decode().strip() if re.match('^#', line): continue # chr13 4500000 10000000 p12 stalk (scaffold, start, stop, band_num, rtype) = line.split('\t') line_counter += 1 # NOTE some less-finished genomes have # placed and unplaced scaffolds # * Placed scaffolds: # the scaffolds have been placed within a chromosome. # * Unlocalized scaffolds: # although the chromosome within which the scaffold occurs # is known, the scaffold's position or orientation # is not known. # * Unplaced scaffolds: # it is not known which chromosome the scaffold belongs to # # find out if the thing is a full on chromosome, or a scaffold: # ex: unlocalized scaffold: chr10_KL568008v1_random # ex: unplaced scaffold: chrUn_AABR07022428v1 placed_scaffold_pattern = r'(chr(?:\d+|X|Y|Z|W|M))' unlocalized_scaffold_pattern = placed_scaffold_pattern+r'_(\w+)_random' unplaced_scaffold_pattern = r'chr(Un(?:_\w+)?)' m = re.match(placed_scaffold_pattern+r'$', scaffold) if m is not None and len(m.groups()) == 1: # the chromosome is the first match of the pattern chrom_num = m.group(1) else: # skip over anything that isn't a placed_scaffold # at the class level logger.info("Found non-placed chromosome %s", scaffold) chrom_num = None m_chr_unloc = re.match(unlocalized_scaffold_pattern, scaffold) m_chr_unplaced = re.match(unplaced_scaffold_pattern, scaffold) scaffold_num = None if m: pass elif m_chr_unloc is not None and len(m_chr_unloc.groups()) == 2: chrom_num = m_chr_unloc.group(1) scaffold_num = chrom_num+'_'+m_chr_unloc.group(2) elif m_chr_unplaced is not None and len(m_chr_unplaced.groups()) == 1: scaffold_num = m_chr_unplaced.group(1) else: logger.error("There's a chr pattern that we aren't matching: %s", scaffold) if chrom_num is not None: # the chrom class (generic) id chrom_class_id = makeChromID(chrom_num, taxon, 'CHR') # first, add the chromosome class (in the taxon) geno.addChromosomeClass(chrom_num, taxon_id, self.files[taxon]['genome_label']) # then, add the chromosome instance (from the given build) geno.addChromosomeInstance(chrom_num, build_id, build_num, chrom_class_id) # add the chr to the hashmap of coordinates for this build # the chromosome coordinate space is itself if chrom_num not in mybands.keys(): mybands[chrom_num] = {'min': 0, 'max': int(stop), 'chr': chrom_num, 'ref': build_id, 'parent': None, 'stain': None, 'type': Feature.types['chromosome']} if scaffold_num is not None: # this will put the coordinates of the scaffold # in the scaffold-space and make sure that the scaffold # is part of the correct parent. # if chrom_num is None, # then it will attach it to the genome, # just like a reg chrom mybands[scaffold_num] = {'min': start, 'max': stop, 'chr': scaffold_num, 'ref': build_id, 'parent': chrom_num, 'stain': None, 'type': Feature.types['assembly_component'], 'synonym': scaffold} if band_num is not None and band_num.strip() != '': # add the specific band mybands[chrom_num+band_num] = {'min': start, 'max': stop, 'chr': chrom_num, 'ref': build_id, 'parent': None, 'stain': None, 'type': None} # add the staining intensity of the band if re.match(r'g(neg|pos|var)', rtype): mybands[chrom_num+band_num]['stain'] = Feature.types.get(rtype) # get the parent bands, and make them unique parents = list(monochrom.make_parent_bands(band_num, set())) # alphabetical sort will put them in smallest to biggest, # so we reverse parents.sort(reverse=True) # print('parents of',chrom,band,':',parents) if len(parents) > 0: mybands[chrom_num+band_num]['parent'] = chrom_num+parents[0] else: # TODO PYLINT why is 'parent' # a list() a couple of lines up and a set() here? parents = set() # loop through the parents and add them to the hash # add the parents to the graph, in hierarchical order # TODO PYLINT Consider using enumerate # instead of iterating with range and len for i in range(len(parents)): rti = getChrPartTypeByNotation(parents[i]) pnum = chrom_num+parents[i] sta = int(start) sto = int(stop) if pnum not in mybands.keys(): # add the parental band to the hash b = {'min': min(sta, sto), 'max': max(sta, sto), 'chr': chrom_num, 'ref': build_id, 'parent': None, 'stain': None, 'type': rti} mybands[pnum] = b else: # band already in the hash means it's a grouping band # need to update the min/max coords b = mybands.get(pnum) b['min'] = min(sta, sto, b['min']) b['max'] = max(sta, sto, b['max']) mybands[pnum] = b # also, set the max for the chrom c = mybands.get(chrom_num) c['max'] = max(sta, sto, c['max']) mybands[chrom_num] = c # add the parent relationships to each if i < len(parents) - 1: mybands[pnum]['parent'] = chrom_num+parents[i+1] else: # add the last one (p or q usually) # as attached to the chromosome mybands[pnum]['parent'] = chrom_num f.close() # end looping through file # loop through the hash and add the bands to the graph for b in mybands.keys(): myband = mybands.get(b) band_class_id = makeChromID(b, taxon, 'CHR') band_class_label = makeChromLabel(b, genome_label) band_build_id = makeChromID(b, build_num, 'MONARCH') band_build_label = makeChromLabel(b, build_num) # the build-specific chrom chrom_in_build_id = makeChromID(myband['chr'], build_num, 'MONARCH') # if it's != part, then add the class if myband['type'] != Feature.types['assembly_component']: self.gu.addClassToGraph(self.graph, band_class_id, band_class_label, myband['type']) bfeature = Feature(band_build_id, band_build_label, band_class_id) else: bfeature = Feature(band_build_id, band_build_label, myband['type']) if 'synonym' in myband: self.gu.addSynonym(self.graph, band_build_id, myband['synonym']) if myband['parent'] is None: if myband['type'] == Feature.types['assembly_component']: # since we likely don't know the chr, # add it as a part of the build geno.addParts(band_build_id, build_id) elif myband['type'] == Feature.types['assembly_component']: # geno.addParts(band_build_id, chrom_in_build_id) parent_chrom_in_build = makeChromID(myband['parent'], build_num, 'MONARCH') bfeature.addSubsequenceOfFeature(self.graph, parent_chrom_in_build) # add the band as a feature # (which also instantiates the owl:Individual) bfeature.addFeatureStartLocation(myband['min'], chrom_in_build_id) bfeature.addFeatureEndLocation(myband['max'], chrom_in_build_id) if 'stain' in myband and myband['stain'] is not None: # TODO TEC I recall 'has_staining_intensity' being dropped by MB bfeature.addFeatureProperty(self.graph, Feature.properties['has_staining_intensity'], myband['stain']) # type the band as a faldo:Region directly (add_region=False) # bfeature.setNoBNodes(self.nobnodes) # to come when we merge in ZFIN.py bfeature.addFeatureToGraph(self.graph, False) return def _create_genome_builds(self): """ Various resources will map variations to either UCSC (hg*) or to NCBI assemblies. Here we create the equivalences between them. Data taken from: https://genome.ucsc.edu/FAQ/FAQreleases.html#release1 :return: """ # TODO add more species ucsc_assembly_id_map = { "9606": { "UCSC:hg38": "NCBIGenome:GRCh38", "UCSC:hg19": "NCBIGenome:GRCh37", "UCSC:hg18": "NCBIGenome:36.1", "UCSC:hg17": "NCBIGenome:35", "UCSC:hg16": "NCBIGenome:34", "UCSC:hg15": "NCBIGenome:33", }, "7955": { "UCSC:danRer10": "NCBIGenome:GRCz10", "UCSC:danRer7": "NCBIGenome:Zv9", "UCSC:danRer6": "NCBIGenome:Zv8", }, "10090": { "UCSC:mm10": "NCBIGenome:GRCm38", "UCSC:mm9": "NCBIGenome:37" }, "9031": { "UCSC:galGal4": "NCBIAssembly:317958", }, "9913": { "UCSC:bosTau7": "NCBIAssembly:GCF_000003205.5", }, "9823": { "UCSC:susScr3": "NCBIAssembly:304498", }, "9940": { "UCSC:oviAri3": "NCBIAssembly:GCF_000298735.1", }, "9796": { "UCSC:equCab2": "NCBIAssembly:GCF_000002305.2", } } g = self.graph geno = Genotype(g) logger.info("Adding equivalent assembly identifiers") for sp in ucsc_assembly_id_map: tax_num = sp tax_id = 'NCBITaxon:'+tax_num mappings = ucsc_assembly_id_map[sp] for i in mappings: ucsc_id = i ucsc_label = re.split(':', i)[1] mapped_id = mappings[i] mapped_label = re.split(':', mapped_id)[1] mapped_label = 'NCBI build '+str(mapped_label) geno.addReferenceGenome(ucsc_id, ucsc_label, tax_id) geno.addReferenceGenome(mapped_id, mapped_label, tax_id) self.gu.addSameIndividual(g, ucsc_id, mapped_id) return def _check_tax_ids(self): for taxon in self.tax_ids: if str(taxon) not in self.files: raise Exception("Taxon " + str(taxon) + " not supported" " by source UCSCBands") def getTestSuite(self): import unittest from tests.test_ucscbands import UCSCBandsTestCase test_suite = unittest.TestLoader().loadTestsFromTestCase(UCSCBandsTestCase) return test_suite
def _get_variants(self, limit): """ Currently loops through the variant_summary file. :param limit: :return: """ gu = GraphUtils(curie_map.get()) if self.testMode: g = self.testgraph else: g = self.graph geno = Genotype(g) gu.loadAllProperties(g) f = Feature(None, None, None) f.loadAllProperties(g) gu.loadAllProperties(g) # add the taxon and the genome tax_num = '9606' # HARDCODE tax_id = 'NCBITaxon:'+tax_num tax_label = 'Human' gu.addClassToGraph(g, tax_id, None) geno.addGenome(tax_id, None) # label gets added elsewhere # not unzipping the file logger.info("Processing Variant records") line_counter = 0 myfile = '/'.join((self.rawdir, self.files['variant_summary']['file'])) with gzip.open(myfile, 'rb') as f: for line in f: # skip comments line = line.decode().strip() if re.match('^#', line): continue # AlleleID integer value as stored in the AlleleID field in ClinVar (//Measure/@ID in the XML) # Type character, the type of variation # Name character, the preferred name for the variation # GeneID integer, GeneID in NCBI's Gene database # GeneSymbol character, comma-separated list of GeneIDs overlapping the variation # ClinicalSignificance character, comma-separated list of values of clinical significance reported for this variation # for the mapping between the terms listed here and the integers in the .VCF files, see # http://www.ncbi.nlm.nih.gov/clinvar/docs/clinsig/ # RS# (dbSNP) integer, rs# in dbSNP # nsv (dbVar) character, the NSV identifier for the region in dbVar # RCVaccession character, list of RCV accessions that report this variant # TestedInGTR character, Y/N for Yes/No if there is a test registered as specific to this variation in the NIH Genetic Testing Registry (GTR) # PhenotypeIDs character, list of db names and identifiers for phenotype(s) reported for this variant # Origin character, list of all allelic origins for this variation # Assembly character, name of the assembly on which locations are based # Chromosome character, chromosomal location # Start integer, starting location, in pter->qter orientation # Stop integer, end location, in pter->qter orientation # Cytogenetic character, ISCN band # ReviewStatus character, highest review status for reporting this measure. For the key to the terms, # and their relationship to the star graphics ClinVar displays on its web pages, # see http://www.ncbi.nlm.nih.gov/clinvar/docs/variation_report/#interpretation # HGVS(c.) character, RefSeq cDNA-based HGVS expression # HGVS(p.) character, RefSeq protein-based HGVS expression # NumberSubmitters integer, number of submissions with this variant # LastEvaluated datetime, the latest time any submitter reported clinical significance # Guidelines character, ACMG only right now, for the reporting of incidental variation in a Gene # (NOTE: if ACMG, not a specific to the allele but to the Gene) # OtherIDs character, list of other identifiers or sources of information about this variant # VariantID integer, the value used to build the URL for the current default report, # e.g. http://www.ncbi.nlm.nih.gov/clinvar/variation/1756/ # # a crude check that there's an expected number of cols. if not, error out because something changed. num_cols = len(line.split('\t')) expected_numcols = 28 if num_cols != expected_numcols: logger.error("Unexpected number of columns in raw file (%d actual vs %d expected)", num_cols, expected_numcols) (allele_num, allele_type, allele_name, gene_num, gene_symbol, clinical_significance, dbsnp_num, dbvar_num, rcv_nums, tested_in_gtr, phenotype_ids, origin, assembly, chr, start, stop, cytogenetic_loc, review_status, hgvs_c, hgvs_p, number_of_submitters, last_eval, guidelines, other_ids, variant_num, reference_allele, alternate_allele, categories) = line.split('\t') # #### set filter=None in init if you don't want to have a filter # if self.filter is not None: # if ((self.filter == 'taxids' and (int(tax_num) not in self.tax_ids)) # or (self.filter == 'geneids' and (int(gene_num) not in self.gene_ids))): # continue # #### end filter line_counter += 1 pheno_list = [] if phenotype_ids != '-': # trim any leading/trailing semicolons/commas phenotype_ids = re.sub('^[;,]', '', phenotype_ids) phenotype_ids = re.sub('[;,]$', '', phenotype_ids) pheno_list = re.split('[,;]', phenotype_ids) if self.testMode: # get intersection of test disease ids and these phenotype_ids intersect = list(set([str(i) for i in self.disease_ids]) & set(pheno_list)) if int(gene_num) not in self.gene_ids and int(variant_num) not in self.variant_ids \ and len(intersect) < 1: continue # TODO may need to switch on assembly to create correct assembly/build identifiers build_id = ':'.join(('NCBIGenome', assembly)) # make the reference genome build geno.addReferenceGenome(build_id, assembly, tax_id) allele_type_id = self._map_type_of_allele(allele_type) bandinbuild_id = None if str(chr) == '': # check cytogenic location if str(cytogenetic_loc).strip() != '': # use cytogenic location to get the approximate location # strangely, they still put an assembly number even when there's no numeric location if not re.search('-',str(cytogenetic_loc)): band_id = makeChromID(re.split('-',str(cytogenetic_loc)), tax_num, 'CHR') geno.addChromosomeInstance(cytogenetic_loc, build_id, assembly, band_id) bandinbuild_id = makeChromID(re.split('-',str(cytogenetic_loc)), assembly, 'MONARCH') else: # can't deal with ranges yet pass else: # add the human chromosome class to the graph, and add the build-specific version of it chr_id = makeChromID(str(chr), tax_num, 'CHR') geno.addChromosomeClass(str(chr), tax_id, tax_label) geno.addChromosomeInstance(str(chr), build_id, assembly, chr_id) chrinbuild_id = makeChromID(str(chr), assembly, 'MONARCH') seqalt_id = ':'.join(('ClinVarVariant', variant_num)) gene_id = None if str(gene_num) != '-1' and str(gene_num) != 'more than 10': # they use -1 to indicate unknown gene gene_id = ':'.join(('NCBIGene', str(gene_num))) # FIXME there are some "variants" that are actually haplotypes # probably will get taken care of when we switch to processing the xml # for example, variant_num = 38562 # but there's no way to tell if it's a haplotype in the csv data # so the dbsnp or dbvar should probably be primary, and the variant num be the vslc, # with each of the dbsnps being added to it # todo clinical significance needs to be mapped to a list of terms # first, make the variant: f = Feature(seqalt_id, allele_name, allele_type_id) if start != '-' and start.strip() != '': f.addFeatureStartLocation(start, chrinbuild_id) if stop != '-' and stop.strip() != '': f.addFeatureEndLocation(stop, chrinbuild_id) f.addFeatureToGraph(g) if bandinbuild_id is not None: f.addSubsequenceOfFeature(g, bandinbuild_id) # CHECK - this makes the assumption that there is only one affected chromosome per variant # what happens with chromosomal rearrangement variants? shouldn't both chromosomes be here? # add the hgvs as synonyms if hgvs_c != '-' and hgvs_c.strip() != '': gu.addSynonym(g, seqalt_id, hgvs_c) if hgvs_p != '-' and hgvs_p.strip() != '': gu.addSynonym(g, seqalt_id, hgvs_p) # add the dbsnp and dbvar ids as equivalent if dbsnp_num != '-' and int(dbsnp_num) != -1: dbsnp_id = 'dbSNP:rs'+str(dbsnp_num) gu.addIndividualToGraph(g, dbsnp_id, None) gu.addSameIndividual(g, seqalt_id, dbsnp_id) if dbvar_num != '-': dbvar_id = 'dbVar:'+dbvar_num gu.addIndividualToGraph(g, dbvar_id, None) gu.addSameIndividual(g, seqalt_id, dbvar_id) # TODO - not sure if this is right... add as xref? # the rcv is like the combo of the phenotype with the variant if rcv_nums != '-': for rcv_num in re.split(';',rcv_nums): rcv_id = 'ClinVar:'+rcv_num gu.addIndividualToGraph(g, rcv_id, None) gu.addXref(g, seqalt_id, rcv_id) if gene_id is not None: # add the gene gu.addClassToGraph(g, gene_id, gene_symbol) # make a variant locus vl_id = '_'+gene_num+'-'+variant_num if self.nobnodes: vl_id = ':'+vl_id vl_label = allele_name gu.addIndividualToGraph(g, vl_id, vl_label, geno.genoparts['variant_locus']) geno.addSequenceAlterationToVariantLocus(seqalt_id, vl_id) geno.addAlleleOfGene(vl_id, gene_id) else: # some basic reporting gmatch = re.search('\(\w+\)', allele_name) if gmatch is not None and len(gmatch.groups()) > 0: logger.info("Gene found in allele label, but no id provided: %s", gmatch.group(1)) elif re.match('more than 10', gene_symbol): logger.info("More than 10 genes found; need to process XML to fetch (variant=%d)", int(variant_num)) else: logger.info("No gene listed for variant %d", int(variant_num)) # parse the list of "phenotypes" which are diseases. add them as an association # ;GeneReviews:NBK1440,MedGen:C0392514,OMIM:235200,SNOMED CT:35400008;MedGen:C3280096,OMIM:614193;MedGen:CN034317,OMIM:612635;MedGen:CN169374 # the list is both semicolon delimited and comma delimited, but i don't know why! # some are bad, like: Orphanet:ORPHA ORPHA319705,SNOMED CT:49049000 if phenotype_ids != '-': for p in pheno_list: m = re.match("(Orphanet:ORPHA(?:\s*ORPHA)?)", p) if m is not None and len(m.groups()) > 0: p = re.sub(m.group(1), 'Orphanet:', p.strip()) elif re.match('SNOMED CT', p): p = re.sub('SNOMED CT', 'SNOMED', p.strip()) assoc = G2PAssoc(self.name, seqalt_id, p.strip()) assoc.add_association_to_graph(g) if other_ids != '-': id_list = other_ids.split(',') # process the "other ids" # ex: CFTR2:F508del,HGMD:CD890142,OMIM Allelic Variant:602421.0001 # TODO make more xrefs for xrefid in id_list: prefix = xrefid.split(':')[0].strip() if prefix == 'OMIM Allelic Variant': xrefid = 'OMIM:'+xrefid.split(':')[1] gu.addIndividualToGraph(g, xrefid, None) gu.addSameIndividual(g, seqalt_id, xrefid) elif prefix == 'HGMD': gu.addIndividualToGraph(g, xrefid, None) gu.addSameIndividual(g, seqalt_id, xrefid) elif prefix == 'dbVar' and dbvar_num == xrefid.split(':')[1].strip(): pass # skip over this one elif re.search('\s', prefix): pass # logger.debug('xref prefix has a space: %s', xrefid) else: # should be a good clean prefix # note that HGMD variants are in here as Xrefs because we can't resolve URIs for them # logger.info("Adding xref: %s", xrefid) # gu.addXref(g, seqalt_id, xrefid) # logger.info("xref prefix to add: %s", xrefid) pass if not self.testMode and limit is not None and line_counter > limit: break gu.loadProperties(g, G2PAssoc.object_properties, gu.OBJPROP) gu.loadProperties(g, G2PAssoc.annotation_properties, gu.ANNOTPROP) gu.loadProperties(g, G2PAssoc.datatype_properties, gu.DATAPROP) logger.info("Finished parsing variants") return