Python Model.makeLeader方法代码示例

# 需要导入模块: from dipper.models.Model import Model [as 别名]
# 或者: from dipper.models.Model.Model import makeLeader [as 别名]
    def parse(self, limit=None):
        zfin_parser = ZFIN(self.graph_type, self.are_bnodes_skized)
        model = Model(self.graph)
        zp_file = '/'.join((self.rawdir, self.files['zpmap']['file']))
        g2p_file = '/'.join((self.rawdir, self.files['g2p_clean']['file']))
        zfin_parser.zp_map = zfin_parser._load_zp_mappings(zp_file)

        with open(g2p_file, 'r', encoding="utf8") as csvfile:
            filereader = csv.reader(csvfile, delimiter='\t', quotechar='\"')
            for row in filereader:

                (internal_id, symbol, gene_id, subterm1_id, subterm1_label,
                 pc_rel_id, pc_rel_label, superterm1_id, superterm1_label,
                 quality_id, quality_name, modifier, subterm2_id,
                 subterm2_label, pc_rel2_id, pc_rel2_id, superterm2_id,
                 superterm2_label, fish_id, fish_label, start_stage, end_stage,
                 environment, pub_id, figure_id, unknown_field) = row

                zp_id = zfin_parser._map_sextuple_to_phenotype(
                    superterm1_id, subterm1_id, quality_id, superterm2_id,
                    subterm2_id, modifier)

                gene_curie = "ZFIN:{0}".format(gene_id)
                model.makeLeader(gene_curie)
                pub_curie = "ZFIN:{0}".format(pub_id)
                if zp_id:
                    assoc = G2PAssoc(self.graph, self.name, gene_curie, zp_id)
                    if pub_id:
                        reference = Reference(self.graph, pub_curie,
                                              Reference.ref_types['document'])
                        reference.addRefToGraph()
                        assoc.add_source(pub_curie)

                    assoc.add_evidence('ECO:0000059')
                    assoc.add_association_to_graph()

# 需要导入模块: from dipper.models.Model import Model [as 别名]
# 或者: from dipper.models.Model.Model import makeLeader [as 别名]
 def _add_deprecated_snp(
         self, snp_id, snp_id_current, merged, chrom_num, chrom_pos):
     if self.test_mode:
         graph = self.testgraph
     else:
         graph = self.graph
     model = Model(graph)
     location = self._make_location_curie(chrom_num, chrom_pos)
     # add deprecation information
     if merged == '1' and str(snp_id_current.strip()) != '':
         # get the current rs_id
         current_rs_id = 'dbSNP:'
         if not re.match(r'rs', snp_id_current):
             current_rs_id += 'rs'
         current_rs_id += str(snp_id_current)
         if location is not None:
             if location not in self.id_location_map:
                 self.id_location_map[location] = set(current_rs_id)
             else:
                 self.id_location_map[location].add(current_rs_id)
         model.addDeprecatedIndividual(snp_id, current_rs_id)
         # TODO check on this
         # should we add the annotations to the current
         # or orig?
         model.makeLeader(current_rs_id)
     else:
         model.makeLeader(snp_id)

# 需要导入模块: from dipper.models.Model import Model [as 别名]
# 或者: from dipper.models.Model.Model import makeLeader [as 别名]
    def _add_gene_equivalencies(self, xrefs, gene_id, taxon):
        """
        Add equivalentClass and sameAs relationships

        Uses external resource map located in
        /resources/clique_leader.yaml to determine
        if an NCBITaxon ID space is a clique leader
        """

        clique_map = self.open_and_parse_yaml(self.resources['clique_leader'])

        if self.test_mode:
            graph = self.testgraph
        else:
            graph = self.graph
        model = Model(graph)
        filter_out = ['Vega', 'IMGT/GENE-DB', 'Araport']

        # deal with the dbxrefs
        # MIM:614444|HGNC:HGNC:16851|Ensembl:ENSG00000136828|HPRD:11479|Vega:OTTHUMG00000020696

        for dbxref in xrefs.strip().split('|'):
            prefix = ':'.join(dbxref.split(':')[:-1]).strip()
            if prefix in self.localtt:
                prefix = self.localtt[prefix]
            dbxref_curie = ':'.join((prefix, dbxref.split(':')[-1]))

            if dbxref_curie is not None and prefix != '':
                if prefix == 'HPRD':  # proteins are not == genes.
                    model.addTriple(
                        gene_id, self.globaltt['has gene product'], dbxref_curie)
                    continue
                    # skip some of these for now based on curie prefix
                if prefix in filter_out:
                    continue

                if prefix == 'ENSEMBL':
                    model.addXref(gene_id, dbxref_curie)
                if prefix == 'OMIM':
                    if dbxref_curie in self.omim_replaced:
                        repl = self.omim_replaced[dbxref_curie]
                        for omim in repl:
                            if omim in self.omim_type and \
                                    self.omim_type[omim] == self.globaltt['gene']:
                                dbxref_curie = omim
                    if dbxref_curie in self.omim_type and \
                            self.omim_type[dbxref_curie] != self.globaltt['gene']:
                        continue
                try:
                    if self.class_or_indiv.get(gene_id) == 'C':
                        model.addEquivalentClass(gene_id, dbxref_curie)
                        if taxon in clique_map:
                            if clique_map[taxon] == prefix:
                                model.makeLeader(dbxref_curie)
                            elif clique_map[taxon] == gene_id.split(':')[0]:
                                model.makeLeader(gene_id)
                    else:
                        model.addSameIndividual(gene_id, dbxref_curie)
                except AssertionError as err:
                    LOG.warning("Error parsing %s: %s", gene_id, err)

# 需要导入模块: from dipper.models.Model import Model [as 别名]
# 或者: from dipper.models.Model.Model import makeLeader [as 别名]
    def _add_gene_equivalencies(self, xrefs, gene_id, taxon):
        """
        Add equivalentClass and sameAs relationships

        Uses external resource map located in
        /resources/clique_leader.yaml to determine
        if an ID space is a clique leader
        """

        clique_map = self.open_and_parse_yaml(self.resources['clique_leader'])

        if self.testMode:
            graph = self.testgraph
        else:
            graph = self.graph

        filter_out = ['Vega', 'IMGT/GENE-DB', 'Araport']
        taxon_spec_filters = {
            '10090': ['ENSEMBL']
        }
        if taxon in taxon_spec_filters:
            filter_out += taxon_spec_filters[taxon]

        model = Model(graph)
        # deal with the xrefs
        # MIM:614444|HGNC:HGNC:16851|Ensembl:ENSG00000136828|HPRD:11479|Vega:OTTHUMG00000020696
        for ref in xrefs.strip().split('|'):
            xref_curie = self._cleanup_id(ref)
            if xref_curie is not None and xref_curie.strip() != '':
                if re.match(r'HPRD', xref_curie):
                    # proteins are not == genes.
                    model.addTriple(
                        gene_id,
                        self.properties['has_gene_product'], xref_curie)
                    continue
                    # skip some of these for now
                if xref_curie.split(':')[0] in filter_out:
                    continue
                if re.match(r'^OMIM', xref_curie):
                    if DipperUtil.is_omim_disease(xref_curie):
                        continue
                try:
                    if self.class_or_indiv.get(gene_id) == 'C':
                        model.addEquivalentClass(
                            gene_id, xref_curie)
                        if int(taxon) in clique_map:
                            if clique_map[int(taxon)] == xref_curie.split(':')[0]:
                                model.makeLeader(xref_curie)
                            elif clique_map[int(taxon)] == gene_id.split(':')[0]:
                                model.makeLeader(gene_id)
                    else:
                        model.addSameIndividual(gene_id, xref_curie)
                except AssertionError as e:
                    logger.warn("Error parsing {0}: {1}".format(gene_id, e))
        return

# 需要导入模块: from dipper.models.Model import Model [as 别名]
# 或者: from dipper.models.Model.Model import makeLeader [as 别名]
    def _get_var_citations(self, limit):

        # Generated weekly, the first of the week
        # A tab-delimited report of citations associated with data in ClinVar,
        # connected to the AlleleID, the VariationID, and either rs# from dbSNP
        # or nsv in dbVar.
        #
        # AlleleID          int value  (xpath //Measure/@ID )
        # VariationID       ID ClinVar uses to anchor default display.
        #                   (xpath  //MeasureSet/@ID)
        # rs			    rs identifier from dbSNP
        # nsv				nsv identifier from dbVar
        # citation_source	The source of the citation, either PubMed,
        #                   PubMedCentral, or the NCBI Bookshelf
        # citation_id		The identifier used by that source

        logger.info("Processing Citations for variants")
        line_counter = 0
        myfile = \
            '/'.join((self.rawdir, self.files['variant_citations']['file']))
        if self.testMode:
            g = self.testgraph
        else:
            g = self.graph
        model = Model(g)

        with open(myfile, 'r', encoding="utf8") as f:
            filereader = csv.reader(f, delimiter='\t', quotechar='\"')

            for line in filereader:
                # skip comments
                line = line
                if re.match(r'^#', line[0]):
                    continue
                (allele_num, variant_num, rs_num, nsv_num, citation_source,
                 citation_id) = line

                line_counter += 1

                if self.testMode:
                    if int(variant_num) not in self.variant_ids:
                        continue

                if citation_id.strip() == '':
                    logger.info(
                        "Skipping blank citation for ClinVarVariant:%s",
                        str(variant_num))
                    continue

                # the citation for a variant is made to some kind of
                # combination of the ids here.
                # but i'm not sure which, we don't know what the
                # citation is for exactly, other than the variant.
                # so use mentions

                var_id = 'ClinVarVariant:'+variant_num

                # citation source: PubMed | PubMedCentral | citation_source
                # citation id:
                # format the citation id:
                ref_id = None
                if citation_source == 'PubMed':
                    ref_id = 'PMID:'+str(citation_id.replace(" ", ""))
                    model.makeLeader(ref_id)
                elif citation_source == 'PubMedCentral':
                    ref_id = 'PMCID:'+str(citation_id)
                if ref_id is not None:
                    r = Reference(
                        self.graph, ref_id,
                        Reference.ref_types['journal_article'])
                    r.addRefToGraph()
                    g.addTriple(
                        ref_id, self.properties['is_about'], var_id)

                if not self.testMode \
                        and (limit is not None and line_counter > limit):
                    break

        logger.info("Finished processing citations for variants")

        return

# 需要导入模块: from dipper.models.Model import Model [as 别名]
# 或者: from dipper.models.Model.Model import makeLeader [as 别名]

#.........这里部分代码省略.........

                seqalt_id = ':'.join(('ClinVarVariant', variant_num))
                gene_id = None

                # they use -1 to indicate unknown gene
                if str(gene_num) != '-1' and str(gene_num) != 'more than 10':
                    if re.match(r'^Gene:', gene_num):
                        gene_num = "NCBI" + gene_num
                    else:
                        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()
                f.addTaxonToFeature(tax_id)
                # make the ClinVarVariant the clique leader
                model.makeLeader(seqalt_id)

                if bandinbuild_id is not None:
                    f.addSubsequenceOfFeature(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() != '':
                    model.addSynonym(seqalt_id, hgvs_c)
                if hgvs_p != '-' and hgvs_p.strip() != '':
                    model.addSynonym(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)
                    model.addIndividualToGraph(dbsnp_id, None)
                    model.addSameIndividual(seqalt_id, dbsnp_id)
                if dbvar_num != '-':
                    dbvar_id = 'dbVar:'+dbvar_num
                    model.addIndividualToGraph(dbvar_id, None)
                    model.addSameIndividual(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(r';', rcv_nums):
                        rcv_id = 'ClinVar:' + rcv_num
                        model.addIndividualToGraph(rcv_id, None)
                        model.addXref(seqalt_id, rcv_id)

# 需要导入模块: from dipper.models.Model import Model [as 别名]
# 或者: from dipper.models.Model.Model import makeLeader [as 别名]
    def _process_genes(self, limit=None):

        if self.test_mode:
            graph = self.testgraph
        else:
            graph = self.graph

        geno = Genotype(graph)
        model = Model(graph)

        raw = '/'.join((self.rawdir, self.files['genes']['file']))
        col = self.files['genes']['columns']
        LOG.info("Processing HGNC genes")

        chr_pattern = re.compile(r'(\d+|X|Y|Z|W|MT)[pq$]')
        band_pattern = re.compile(r'([pq][A-H\d]?\d?(?:\.\d+)?)')

        with open(raw, 'r', encoding="utf8") as csvfile:
            filereader = csv.reader(csvfile, delimiter='\t', quotechar='\"')

            row = next(filereader)
            if not self.check_fileheader(col, row):
                exit(-1)

            for row in filereader:
                # To generate:
                # head -1 hgnc_complete_set.txt.1 | tr '\t' '\n' |
                # sed "s/\(.*\)/\1 = row[col.index(\'\1\')]/g"

                hgnc_id = row[col.index('hgnc_id')].strip()
                symbol = row[col.index('symbol')].strip()
                name = row[col.index('name')].strip()
                # locus_group = row[col.index('locus_group')]
                locus_type = row[col.index('locus_type')].strip()
                # status = row[col.index('status')]
                location = row[col.index('location')].strip()
                # location_sortable = row[col.index('location_sortable')]
                # alias_symbol = row[col.index('alias_symbol')]
                # alias_name = row[col.index('alias_name')]
                # prev_symbol = row[col.index('prev_symbol')]
                # prev_name = row[col.index('prev_name')]
                # gene_family = row[col.index('gene_family')]
                # gene_family_id = row[col.index('gene_family_id')]
                # date_approved_reserved = row[col.index('date_approved_reserved')]
                # date_symbol_changed = row[col.index('date_symbol_changed')]
                # date_name_changed = row[col.index('date_name_changed')]
                # date_modified = row[col.index('date_modified')]
                entrez_id = row[col.index('entrez_id')].strip()
                ensembl_gene_id = row[col.index('ensembl_gene_id')].strip()
                # vega_id = row[col.index('vega_id')]
                # ucsc_id = row[col.index('ucsc_id')]
                # ena = row[col.index('ena')]
                # refseq_accession = row[col.index('refseq_accession')]
                # ccds_id = row[col.index('ccds_id')]
                # uniprot_ids = row[col.index('uniprot_ids')]
                pubmed_ids = row[col.index('pubmed_id')].strip()  # pipe seperated!
                # mgd_id = row[col.index('mgd_id')]
                # rgd_id = row[col.index('rgd_id')]
                # lsdb = row[col.index('lsdb')]
                # cosmic = row[col.index('cosmic')]
                omim_ids = row[col.index('omim_id')].strip()  # pipe seperated!
                # mirbase = row[col.index('mirbase')]
                # homeodb = row[col.index('homeodb')]
                # snornabase = row[col.index('snornabase')]
                # bioparadigms_slc = row[col.index('bioparadigms_slc')]
                # orphanet = row[col.index('orphanet')]
                # pseudogene.org = row[col.index('pseudogene.org')]
                # horde_id = row[col.index('horde_id')]
                # merops = row[col.index('merops')]
                # imgt = row[col.index('imgt')]
                # iuphar = row[col.index('iuphar')]
                # kznf_gene_catalog = row[col.index('kznf_gene_catalog')]
                # mamit_trnadb = row[col.index('mamit-trnadb')]
                # cd = row[col.index('cd')]
                # lncrnadb = row[col.index('lncrnadb')]
                # enzyme_id = row[col.index('enzyme_id')]
                # intermediate_filament_db = row[col.index('intermediate_filament_db')]
                # rna_central_ids = row[col.index('rna_central_ids')]
                # lncipedia = row[col.index('lncipedia')]
                # gtrnadb = row[col.index('gtrnadb')]

                if self.test_mode and entrez_id != '' and \
                        entrez_id not in self.gene_ids:
                    continue

                if name == '':
                    name = None

                if locus_type == 'withdrawn':
                    model.addDeprecatedClass(hgnc_id)
                else:
                    gene_type_id = self.resolve(locus_type, False)  # withdrawn -> None?
                    if gene_type_id != locus_type:
                        model.addClassToGraph(hgnc_id, symbol, gene_type_id, name)
                    model.makeLeader(hgnc_id)

                if entrez_id != '':
                    model.addEquivalentClass(hgnc_id, 'NCBIGene:' + entrez_id)

                if ensembl_gene_id != '':
#.........这里部分代码省略.........

# 需要导入模块: from dipper.models.Model import Model [as 别名]
# 或者: from dipper.models.Model.Model import makeLeader [as 别名]
    def _process_genes(self, limit=None):

        if self.testMode:
            g = self.testgraph
        else:
            g = self.graph

        geno = Genotype(g)
        model = Model(g)
        raw = '/'.join((self.rawdir, self.files['genes']['file']))
        line_counter = 0
        logger.info("Processing HGNC genes")

        with open(raw, 'r', encoding="utf8") as csvfile:
            filereader = csv.reader(csvfile, delimiter='\t', quotechar='\"')
            # curl -s ftp://ftp.ebi.ac.uk/pub/databases/genenames/new/tsv/hgnc_complete_set.txt | head -1 | tr '\t' '\n' | grep -n  .
            for row in filereader:
                (hgnc_id,
                 symbol,
                 name,
                 locus_group,
                 locus_type,
                 status,
                 location,
                 location_sortable,
                 alias_symbol,
                 alias_name,
                 prev_symbol,
                 prev_name,
                 gene_family,
                 gene_family_id,
                 date_approved_reserved,
                 date_symbol_changed,
                 date_name_changed,
                 date_modified,
                 entrez_id,
                 ensembl_gene_id,
                 vega_id,
                 ucsc_id,
                 ena,
                 refseq_accession,
                 ccds_id,
                 uniprot_ids,
                 pubmed_id,
                 mgd_id,
                 rgd_id,
                 lsdb,
                 cosmic,
                 omim_id,
                 mirbase,
                 homeodb,
                 snornabase,
                 bioparadigms_slc,
                 orphanet,
                 pseudogene_org,
                 horde_id,
                 merops,
                 imgt,
                 iuphar,
                 kznf_gene_catalog,
                 mamit_trnadb,
                 cd,
                 lncrnadb,
                 enzyme_id,
                 intermediate_filament_db,
                 rna_central_ids) = row

                line_counter += 1

                # skip header
                if line_counter <= 1:
                    continue

                if self.testMode and entrez_id != '' \
                        and int(entrez_id) not in self.gene_ids:
                    continue

                if name == '':
                    name = None
                gene_type_id = self._get_gene_type(locus_type)
                model.addClassToGraph(hgnc_id, symbol, gene_type_id, name)
                if locus_type == 'withdrawn':
                    model.addDeprecatedClass(hgnc_id)
                else:
                    model.makeLeader(hgnc_id)
                if entrez_id != '':
                    model.addEquivalentClass(
                        hgnc_id, 'NCBIGene:' + entrez_id)
                if ensembl_gene_id != '':
                    model.addEquivalentClass(
                        hgnc_id, 'ENSEMBL:' + ensembl_gene_id)
                if omim_id != '' and "|" not in omim_id:
                    omim_curie = 'OMIM:' + omim_id
                    if not DipperUtil.is_omim_disease(omim_curie):
                        model.addEquivalentClass(hgnc_id, omim_curie)

                geno.addTaxon('NCBITaxon:9606', hgnc_id)

                # add pubs as "is about"
                if pubmed_id != '':
#.........这里部分代码省略.........

# 需要导入模块: from dipper.models.Model import Model [as 别名]
# 或者: from dipper.models.Model.Model import makeLeader [as 别名]

#.........这里部分代码省略.........
                # 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(

# 需要导入模块: from dipper.models.Model import Model [as 别名]
# 或者: from dipper.models.Model.Model import makeLeader [as 别名]

#.........这里部分代码省略.........
                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.strip()
                        vl_symbol = self.id_label_hash[vl_id]
                        geno.addAllele(vl_id, vl_symbol,