Python Genotype.addGene方法代码示例

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

#.........这里部分代码省略.........
                        re.match(r'rs', peak_mark.strip()):
                    dbsnp_id = 'dbSNP:'+peak_mark.strip()

                    model.addIndividualToGraph(
                        dbsnp_id, None,
                        self.globaltt['sequence_alteration'])
                    model.addXref(qtl_id, dbsnp_id)

                gene_id = gene_id.replace('uncharacterized ', '').strip()
                if gene_id is not None and gene_id != '' and gene_id != '.'\
                        and re.fullmatch(r'[^ ]*', gene_id) is not None:

                    # we assume if no src is provided and gene_id is an integer,
                    # then it is an NCBI gene ... (okay, lets crank that back a notch)
                    if gene_id_src == '' and gene_id.isdigit() and \
                            gene_id in self.gene_info:
                        # LOG.info(
                        #    'Warm & Fuzzy saying %s is a NCBI gene for %s',
                        #    gene_id, common_name)
                        gene_id_src = 'NCBIgene'
                    elif gene_id_src == '' and gene_id.isdigit():
                        LOG.warning(
                            'Cold & Prickely saying %s is a NCBI gene for %s',
                            gene_id, common_name)
                        gene_id_src = 'NCBIgene'
                    elif gene_id_src == '':
                        LOG.error(
                            ' "%s" is a NOT NCBI gene for %s', gene_id, common_name)
                        gene_id_src = None

                    if gene_id_src == 'NCBIgene':
                        gene_id = 'NCBIGene:' + gene_id
                        # we will expect that these will get labels elsewhere
                        geno.addGene(gene_id, None)
                        # FIXME what is the right relationship here?
                        geno.addAffectedLocus(qtl_id, gene_id)

                        if dbsnp_id is not None:
                            # add the rsid as a seq alt of the gene_id
                            vl_id = '_:' + re.sub(
                                r':', '', gene_id) + '-' + peak_mark.strip()
                            geno.addSequenceAlterationToVariantLocus(
                                dbsnp_id, vl_id)
                            geno.addAffectedLocus(vl_id, gene_id)

                # add the trait
                model.addClassToGraph(trait_id, trait_name)

                # Add publication
                reference = None
                if re.match(r'ISU.*', pubmed_id):
                    pub_id = 'AQTLPub:'+pubmed_id.strip()
                    reference = Reference(graph, pub_id)
                elif pubmed_id != '':
                    pub_id = 'PMID:' + pubmed_id.strip()
                    reference = Reference(
                        graph, pub_id, self.globaltt['journal article'])

                if reference is not None:
                    reference.addRefToGraph()

                # make the association to the QTL
                assoc = G2PAssoc(
                    graph, self.name, qtl_id, trait_id, self.globaltt['is marker for'])
                assoc.add_evidence(eco_id)
                assoc.add_source(pub_id)

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

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

            # now that we've collected all of the variant information, build it
            # we don't know their zygosities
            for s in self.strain_hash:
                h = self.strain_hash.get(s)
                variants = h['variants']
                genes = h['genes']
                vl_set = set()
                # make variant loci for each gene
                if len(variants) > 0:
                    for v in variants:
                        vl_id = v
                        vl_symbol = self.id_label_hash[vl_id]
                        geno.addAllele(vl_id, vl_symbol,
                                       geno.genoparts['variant_locus'])
                        vl_set.add(vl_id)
                        if len(variants) == 1 and len(genes) == 1:
                            for gene in genes:
                                geno.addAlleleOfGene(vl_id, gene)
                        else:
                            geno.addAllele(vl_id, vl_symbol)
                else:  # len(vars) == 0
                    # it's just anonymous variants in some gene
                    for gene in genes:
                        vl_id = '_'+gene+'-VL'
                        vl_id = re.sub(r':', '', vl_id)
                        if self.nobnodes:
                            vl_id = ':'+vl_id
                        vl_symbol = self.id_label_hash[gene]+'<?>'
                        self.id_label_hash[vl_id] = vl_symbol
                        geno.addAllele(vl_id, vl_symbol,
                                       geno.genoparts['variant_locus'])
                        geno.addGene(gene, self.id_label_hash[gene])
                        geno.addAlleleOfGene(vl_id, gene)
                        vl_set.add(vl_id)

                # make the vslcs
                vl_list = sorted(vl_set)
                vslc_list = []
                for vl in vl_list:
                    # for unknown zygosity
                    vslc_id = '_'+re.sub(r'^_', '', vl)+'U'
                    vslc_id = re.sub(r':', '', vslc_id)
                    if self.nobnodes:
                        vslc_id = ':' + vslc_id
                    vslc_label = self.id_label_hash[vl] + '/?'
                    self.id_label_hash[vslc_id] = vslc_label
                    vslc_list.append(vslc_id)
                    geno.addPartsToVSLC(
                        vslc_id, vl, None, geno.zygosity['indeterminate'],
                        geno.object_properties['has_alternate_part'], None)
                    gu.addIndividualToGraph(
                        g, vslc_id, vslc_label,
                        geno.genoparts['variant_single_locus_complement'])
                if len(vslc_list) > 0:
                    if len(vslc_list) > 1:
                        gvc_id = '-'.join(vslc_list)
                        gvc_id = re.sub(r':', '', gvc_id)
                        if self.nobnodes:
                            gvc_id = ':'+gvc_id
                        gvc_label = \
                            '; '.join(self.id_label_hash[v] for v in vslc_list)
                        gu.addIndividualToGraph(
                            g, gvc_id, gvc_label,
                            geno.genoparts['genomic_variation_complement'])

# 需要导入模块: from dipper.models.Genotype import Genotype [as 别名]
# 或者: from dipper.models.Genotype.Genotype import addGene [as 别名]
    def _process_genes(self, limit=None):
        """
        This method processes the KEGG gene IDs.
        The label for the gene is pulled as the first symbol in the list of gene symbols; the rest
        are added as synonyms.  The long-form of the gene name is added as a definition.
        This is hardcoded to just processes human genes.

        Triples created:
        <gene_id> is a SO:gene
        <gene_id> rdfs:label <gene_name>

        :param limit:
        :return:
        """

        logger.info("Processing genes")
        if self.testMode:
            g = self.testgraph
        else:
            g = self.graph
        line_counter = 0
        gu = GraphUtils(curie_map.get())
        geno = Genotype(g)
        raw = '/'.join((self.rawdir, self.files['hsa_genes']['file']))
        with open(raw, 'r', encoding="iso-8859-1") as csvfile:
            filereader = csv.reader(csvfile, delimiter='\t', quotechar='\"')
            for row in filereader:
                line_counter += 1
                (gene_id, gene_name) = row

                gene_id = 'KEGG-'+gene_id.strip()

                # the gene listing has a bunch of labels that are delimited, like:
                # DST, BP240, BPA, BPAG1, CATX-15, CATX15, D6S1101, DMH, DT, EBSB2, HSAN6, MACF2; dystonin; K10382 dystonin
                # it looks like the list is semicolon delimited (symbol, name, gene_class)
                # where the symbol is a comma-delimited list

                # here, we split them up.  we will take the first abbreviation and make it the symbol
                # then take the rest as synonyms

                gene_stuff = re.split(';', gene_name)
                symbollist = re.split(',', gene_stuff[0])
                first_symbol = symbollist[0].strip()

                if gene_id not in self.label_hash:
                    self.label_hash[gene_id] = first_symbol

                if self.testMode and gene_id not in self.test_ids['genes']:
                    continue

                # Add the gene as a class.
                geno.addGene(gene_id, first_symbol)

                # add the long name as the description
                if len(gene_stuff) > 1:
                    description = gene_stuff[1].strip()
                    gu.addDefinition(g, gene_id, description)

                # add the rest of the symbols as synonyms
                for i in enumerate(symbollist, start=1):
                    gu.addSynonym(g, gene_id, i[1].strip())

                # TODO add the KO here?

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

        logger.info("Done with genes")
        return

# 需要导入模块: from dipper.models.Genotype import Genotype [as 别名]
# 或者: from dipper.models.Genotype.Genotype import addGene [as 别名]
    def _process_omim2gene(self, limit=None):
        """
        This method maps the OMIM IDs and KEGG gene ID. Currently split based on the link_type field.
        Equivalent link types are mapped as gene XRefs.
        Reverse link types are mapped as disease to gene associations.
        Original link types are currently skipped.

        Triples created:
        <kegg_gene_id> is a Gene
        <omim_gene_id> is a Gene
        <kegg_gene_id>> hasXref <omim_gene_id>

        <assoc_id> has subject <omim_disease_id>
        <assoc_id> has object <kegg_gene_id>
        :param limit:
        :return:
        """

        logger.info("Processing OMIM to KEGG gene")
        if self.testMode:
            g = self.testgraph
        else:
            g = self.graph
        line_counter = 0
        geno = Genotype(g)
        gu = GraphUtils(curie_map.get())
        raw = '/'.join((self.rawdir, self.files['omim2gene']['file']))
        with open(raw, 'r', encoding="iso-8859-1") as csvfile:
            filereader = csv.reader(csvfile, delimiter='\t', quotechar='\"')
            for row in filereader:
                line_counter += 1
                (kegg_gene_id, omim_id, link_type) = row

                if self.testMode and kegg_gene_id not in self.test_ids['genes']:
                    continue

                kegg_gene_id = 'KEGG-'+kegg_gene_id.strip()
                omim_id = re.sub('omim', 'OMIM', omim_id)
                if link_type == 'equivalent':
                    # these are genes!  so add them as a class then make equivalence
                    gu.addClassToGraph(g, omim_id, None)
                    geno.addGene(kegg_gene_id, None)
                    gu.addEquivalentClass(g, kegg_gene_id, omim_id)
                elif link_type == 'reverse':
                    # make an association between an OMIM ID and the KEGG gene ID
                    # we do this with omim ids because they are more atomic than KEGG ids

                    alt_locus_id = self._make_variant_locus_id(kegg_gene_id, omim_id)
                    alt_label = self.label_hash[alt_locus_id]
                    gu.addIndividualToGraph(g, alt_locus_id, alt_label, geno.genoparts['variant_locus'])
                    geno.addAlleleOfGene(alt_locus_id, kegg_gene_id)

                    # Add the disease to gene relationship.
                    rel = gu.object_properties['is_marker_for']
                    assoc = G2PAssoc(self.name, alt_locus_id, omim_id, rel)
                    assoc.add_association_to_graph(g)

                elif link_type == 'original':
                    # these are sometimes a gene, and sometimes a disease
                    logger.info('Unable to handle original link for %s-%s', kegg_gene_id, omim_id)
                else:
                    # don't know what these are
                    logger.warn('Unhandled link type for %s-%s: %s', kegg_gene_id, omim_id, link_type)

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

        logger.info("Done with OMIM to KEGG gene")
        gu.loadProperties(g, G2PAssoc.annotation_properties, G2PAssoc.ANNOTPROP)
        gu.loadProperties(g, G2PAssoc.datatype_properties, G2PAssoc.DATAPROP)
        gu.loadProperties(g, G2PAssoc.object_properties, G2PAssoc.OBJECTPROP)

        return

# 需要导入模块: from dipper.models.Genotype import Genotype [as 别名]
# 或者: from dipper.models.Genotype.Genotype import addGene [as 别名]
    def _process_data(self, raw, limit=None):
        logger.info("Processing Data from %s", raw)
        gu = GraphUtils(curie_map.get())

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

        geno = Genotype(g)
        line_counter = 0
        gu.loadAllProperties(g)
        gu.loadObjectProperties(g, geno.object_properties)

        # Add the taxon as a class
        taxon_id = 'NCBITaxon:10090'  # map to Mus musculus
        gu.addClassToGraph(g, taxon_id, None)

        # with open(raw, 'r', encoding="utf8") as csvfile:
        with gzip.open(raw, 'rt') as csvfile:
            filereader = csv.reader(csvfile, delimiter=',', quotechar='\"')
            next(filereader, None)  # skip the header row
            for row in filereader:
                line_counter += 1

                (marker_accession_id, marker_symbol, phenotyping_center,
                 colony, sex, zygosity, allele_accession_id, allele_symbol,
                 allele_name, strain_accession_id, strain_name, project_name,
                 project_fullname, pipeline_name, pipeline_stable_id,
                 procedure_stable_id, procedure_name, parameter_stable_id,
                 parameter_name, top_level_mp_term_id, top_level_mp_term_name,
                 mp_term_id, mp_term_name, p_value, percentage_change,
                 effect_size, statistical_method, resource_name) = row

                if self.testMode and marker_accession_id not in self.test_ids:
                    continue

                # ##### cleanup some of the identifiers ######
                zygosity_id = self._map_zygosity(zygosity)

                # colony ids sometimes have <> in them, spaces,
                # or other non-alphanumerics and break our system;
                # replace these with underscores
                colony_id = '_'+re.sub(r'\W+', '_', colony)
                if self.nobnodes:
                    colony_id = ':'+colony_id

                if not re.match(r'MGI', allele_accession_id):
                    allele_accession_id = \
                        '_IMPC-'+re.sub(r':', '', allele_accession_id)
                    if self.nobnodes:
                        allele_accession_id = ':'+allele_accession_id
                if re.search(r'EUROCURATE', strain_accession_id):
                    # the eurocurate links don't resolve at IMPC
                    strain_accession_id = '_'+strain_accession_id
                    if self.nobnodes:
                        strain_accession_id = ':'+strain_accession_id
                elif not re.match(r'MGI', strain_accession_id):
                    logger.info(
                        "Found a strange strain accession...%s",
                        strain_accession_id)
                    strain_accession_id = 'IMPC:'+strain_accession_id

                ######################
                # first, add the marker and variant to the graph as with MGI,
                # the allele is the variant locus.  IF the marker is not known,
                # we will call it a sequence alteration.  otherwise,
                # we will create a BNode for the sequence alteration.
                sequence_alteration_id = variant_locus_id = None
                variant_locus_name = sequence_alteration_name = None

                # extract out what's within the <> to get the symbol
                if re.match(r'.*<.*>', allele_symbol):
                    sequence_alteration_name = \
                        re.match(r'.*<(.*)>', allele_symbol).group(1)
                else:
                    sequence_alteration_name = allele_symbol

                if marker_accession_id is not None and \
                        marker_accession_id == '':
                    logger.warning(
                        "Marker unspecified on row %d", line_counter)
                    marker_accession_id = None

                if marker_accession_id is not None:
                    variant_locus_id = allele_accession_id
                    variant_locus_name = allele_symbol
                    variant_locus_type = geno.genoparts['variant_locus']
                    geno.addGene(marker_accession_id, marker_symbol,
                                 geno.genoparts['gene'])
                    geno.addAllele(variant_locus_id, variant_locus_name,
                                   variant_locus_type, None)
                    geno.addAlleleOfGene(variant_locus_id, marker_accession_id)

                    sequence_alteration_id = \
                        '_seqalt'+re.sub(r':', '', allele_accession_id)
                    if self.nobnodes:
                        sequence_alteration_id = ':'+sequence_alteration_id
                    geno.addSequenceAlterationToVariantLocus(
                        sequence_alteration_id, variant_locus_id)
#.........这里部分代码省略.........

# 需要导入模块: from dipper.models.Genotype import Genotype [as 别名]
# 或者: from dipper.models.Genotype.Genotype import addGene [as 别名]
    def _process_omim2gene(self, limit=None):
        """
        This method maps the OMIM IDs and KEGG gene ID.
        Currently split based on the link_type field.
        Equivalent link types are mapped as gene XRefs.
        Reverse link types are mapped as disease to gene associations.
        Original link types are currently skipped.

        Triples created:
        <kegg_gene_id> is a Gene
        <omim_gene_id> is a Gene
        <kegg_gene_id>> hasXref <omim_gene_id>

        <assoc_id> has subject <omim_disease_id>
        <assoc_id> has object <kegg_gene_id>
        :param limit:

        :return:
        """

        LOG.info("Processing OMIM to KEGG gene")
        if self.test_mode:
            graph = self.testgraph
        else:
            graph = self.graph
        model = Model(graph)
        geno = Genotype(graph)
        raw = '/'.join((self.rawdir, self.files['omim2gene']['file']))
        with open(raw, 'r', encoding="iso-8859-1") as csvfile:
            reader = csv.reader(csvfile, delimiter='\t', quotechar='\"')
            for row in reader:
                (kegg_gene_id, omim_id, link_type) = row

                if self.test_mode and kegg_gene_id not in self.test_ids['genes']:
                    continue

                kegg_gene_id = 'KEGG-' + kegg_gene_id.strip()
                omim_id = re.sub(r'omim', 'OMIM', omim_id)
                if link_type == 'equivalent':
                    # these are genes!
                    # so add them as a class then make equivalence
                    model.addClassToGraph(omim_id, None)
                    geno.addGene(kegg_gene_id, None)

                    # previous: if omim type is not disease-ish then use
                    # now is:   if omim type is gene then use

                    if omim_id in self.omim_replaced:
                        repl = self.omim_replaced[omim_id]
                        for omim in repl:
                            if omim in self.omim_type and \
                                    self.omim_type[omim] == self.globaltt['gene']:
                                omim_id = omim
                    if omim_id in self.omim_type and \
                            self.omim_type[omim_id] == self.globaltt['gene']:
                        model.addEquivalentClass(kegg_gene_id, omim_id)
                elif link_type == 'reverse':
                    # make an association between an OMIM ID & the KEGG gene ID
                    # we do this with omim ids because
                    # they are more atomic than KEGG ids

                    alt_locus_id = self._make_variant_locus_id(kegg_gene_id, omim_id)
                    alt_label = self.label_hash[alt_locus_id]
                    model.addIndividualToGraph(
                        alt_locus_id, alt_label, self.globaltt['variant_locus'])
                    geno.addAffectedLocus(alt_locus_id, kegg_gene_id)
                    model.addBlankNodeAnnotation(alt_locus_id)

                    # Add the disease to gene relationship.
                    rel = self.globaltt['is marker for']
                    assoc = G2PAssoc(graph, self.name, alt_locus_id, omim_id, rel)
                    assoc.add_association_to_graph()

                elif link_type == 'original':
                    # these are sometimes a gene, and sometimes a disease
                    LOG.info(
                        'Unable to handle original link for %s-%s',
                        kegg_gene_id, omim_id)
                else:
                    # don't know what these are
                    LOG.warning(
                        'Unhandled link type for %s-%s: %s',
                        kegg_gene_id, omim_id, link_type)

                if (not self.test_mode) and (
                        limit is not None and reader.line_num > limit):
                    break
        LOG.info("Done with OMIM to KEGG gene")

# 需要导入模块: from dipper.models.Genotype import Genotype [as 别名]
# 或者: from dipper.models.Genotype.Genotype import addGene [as 别名]
    def _process_genes(self, limit=None):
        """
        This method processes the KEGG gene IDs.
        The label for the gene is pulled as
        the first symbol in the list of gene symbols;
        the rest are added as synonyms.
        The long-form of the gene name is added as a definition.
        This is hardcoded to just processes human genes.

        Triples created:
        <gene_id> is a SO:gene
        <gene_id> rdfs:label <gene_name>

        :param limit:
        :return:

        """

        LOG.info("Processing genes")
        if self.test_mode:
            graph = self.testgraph
        else:
            graph = self.graph
        model = Model(graph)
        family = Family(graph)
        geno = Genotype(graph)
        raw = '/'.join((self.rawdir, self.files['hsa_genes']['file']))
        with open(raw, 'r', encoding="iso-8859-1") as csvfile:
            reader = csv.reader(csvfile, delimiter='\t', quotechar='\"')
            for row in reader:
                (gene_id, gene_name) = row

                gene_id = 'KEGG-'+gene_id.strip()

                # the gene listing has a bunch of labels
                # that are delimited, as:
                # DST, BP240, BPA, BPAG1, CATX-15, CATX15, D6S1101, DMH, DT,
                # EBSB2, HSAN6, MACF2; dystonin; K10382 dystonin
                # it looks like the list is semicolon delimited
                # (symbol, name, gene_class)
                # where the symbol is a comma-delimited list

                # here, we split them up.
                # we will take the first abbreviation and make it the symbol
                # then take the rest as synonyms

                gene_stuff = re.split('r;', gene_name)
                symbollist = re.split(r',', gene_stuff[0])
                first_symbol = symbollist[0].strip()

                if gene_id not in self.label_hash:
                    self.label_hash[gene_id] = first_symbol

                if self.test_mode and gene_id not in self.test_ids['genes']:
                    continue

                # Add the gene as a class.
                geno.addGene(gene_id, first_symbol)

                # add the long name as the description
                if len(gene_stuff) > 1:
                    description = gene_stuff[1].strip()
                    model.addDefinition(gene_id, description)

                # add the rest of the symbols as synonyms
                for i in enumerate(symbollist, start=1):
                    model.addSynonym(gene_id, i[1].strip())

                if len(gene_stuff) > 2:
                    ko_part = gene_stuff[2]
                    ko_match = re.search(r'K\d+', ko_part)
                    if ko_match is not None and len(ko_match.groups()) == 1:
                        ko = 'KEGG-ko:'+ko_match.group(1)
                        family.addMemberOf(gene_id, ko)

                if not self.test_mode and limit is not None and reader.line_num > limit:
                    break

        LOG.info("Done with genes")

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

#.........这里部分代码省略.........

                if not self.test_mode and (
                        limit is not None and reader.line_num > limit):
                    break

            # now that we've collected all of the variant information, build it
            # we don't know their zygosities
            for s in self.strain_hash:
                h = self.strain_hash.get(s)
                variants = h['variants']
                genes = h['genes']
                vl_set = set()
                # make variant loci for each gene
                if len(variants) > 0:
                    for var in variants:
                        vl_id = var.strip()
                        vl_symbol = self.id_label_hash[vl_id]
                        geno.addAllele(
                            vl_id, vl_symbol, self.globaltt['variant_locus'])
                        vl_set.add(vl_id)
                        if len(variants) == 1 and len(genes) == 1:
                            for gene in genes:
                                geno.addAlleleOfGene(vl_id, gene)
                        else:
                            geno.addAllele(vl_id, vl_symbol)
                else:  # len(vars) == 0
                    # it's just anonymous variants in some gene
                    for gene in genes:
                        vl_id = '_:' + re.sub(r':', '', gene) + '-VL'
                        vl_symbol = self.id_label_hash[gene]+'<?>'
                        self.id_label_hash[vl_id] = vl_symbol
                        geno.addAllele(
                            vl_id, vl_symbol, self.globaltt['variant_locus'])
                        geno.addGene(gene, self.id_label_hash[gene])
                        geno.addAlleleOfGene(vl_id, gene)
                        vl_set.add(vl_id)

                # make the vslcs
                vl_list = sorted(vl_set)
                vslc_list = []
                for vl in vl_list:
                    # for unknown zygosity
                    vslc_id = re.sub(r'^_', '', vl)+'U'
                    vslc_id = re.sub(r':', '', vslc_id)
                    vslc_id = '_:' + vslc_id
                    vslc_label = self.id_label_hash[vl] + '/?'
                    self.id_label_hash[vslc_id] = vslc_label
                    vslc_list.append(vslc_id)
                    geno.addPartsToVSLC(
                        vslc_id, vl, None, self.globaltt['indeterminate'],
                        self.globaltt['has_variant_part'], None)
                    model.addIndividualToGraph(
                        vslc_id, vslc_label,
                        self.globaltt['variant single locus complement'])
                if len(vslc_list) > 0:
                    if len(vslc_list) > 1:
                        gvc_id = '-'.join(vslc_list)
                        gvc_id = re.sub(r'_|:', '', gvc_id)
                        gvc_id = '_:'+gvc_id
                        gvc_label = '; '.join(self.id_label_hash[v] for v in vslc_list)
                        model.addIndividualToGraph(
                            gvc_id, gvc_label,
                            self.globaltt['genomic_variation_complement'])
                        for vslc_id in vslc_list:
                            geno.addVSLCtoParent(vslc_id, gvc_id)
                    else:

# 需要导入模块: from dipper.models.Genotype import Genotype [as 别名]
# 或者: from dipper.models.Genotype.Genotype import addGene [as 别名]
    def _process_QTLs_genetic_location(self, raw, taxon_id, common_name, limit=None):
        """
        This function processes

        Triples created:

        :param limit:
        :return:
        """
        if self.testMode:
            g = self.testgraph
        else:
            g = self.graph
        line_counter = 0
        geno = Genotype(g)
        gu = GraphUtils(curie_map.get())
        eco_id = "ECO:0000061"  # Quantitative Trait Analysis Evidence

        logger.info("Processing genetic location for %s", taxon_id)
        with open(raw, 'r', encoding="iso-8859-1") as csvfile:
            filereader = csv.reader(csvfile, delimiter='\t', quotechar='\"')
            for row in filereader:
                line_counter += 1
                (qtl_id, qtl_symbol, trait_name, assotype, empty, chromosome, position_cm, range_cm,
                 flankmark_a2, flankmark_a1, peak_mark, flankmark_b1, flankmark_b2, exp_id, model, test_base,
                 sig_level, lod_score, ls_mean, p_values, f_statistics, variance, bayes_value, likelihood_ratio,
                 trait_id, dom_effect, add_effect, pubmed_id, gene_id, gene_id_src, gene_id_type, empty2) = row

                if self.testMode and int(qtl_id) not in self.test_ids:
                    continue

                qtl_id = 'AQTL:'+qtl_id
                trait_id = 'AQTLTrait:'+trait_id

                # Add QTL to graph
                f = Feature(qtl_id, qtl_symbol, geno.genoparts['QTL'])
                f.addTaxonToFeature(g, taxon_id)

                # deal with the chromosome
                chrom_id = makeChromID(chromosome, taxon_id, 'CHR')

                # add a version of the chromosome which is defined as the genetic map
                build_id = 'MONARCH:'+common_name.strip()+'-linkage'
                build_label = common_name+' genetic map'
                geno.addReferenceGenome(build_id, build_label, taxon_id)
                chrom_in_build_id = makeChromID(chromosome, build_id, 'MONARCH')
                geno.addChromosomeInstance(chromosome, build_id, build_label, chrom_id)
                start = stop = None
                if re.search('-', range_cm):
                    range_parts = re.split('-', range_cm)
                    # check for poorly formed ranges
                    if len(range_parts) == 2 and range_parts[0] != '' and range_parts[1] != '':
                        (start, stop) = [int(float(x.strip())) for x in re.split('-', range_cm)]
                    else:
                        logger.info("There's a cM range we can't handle for QTL %s: %s", qtl_id, range_cm)
                elif position_cm != '':
                    start = stop = int(float(position_cm))

                # FIXME remove converion to int for start/stop when schema can handle floats
                # add in the genetic location based on the range
                f.addFeatureStartLocation(start, chrom_in_build_id, None, [Feature.types['FuzzyPosition']])
                f.addFeatureEndLocation(stop, chrom_in_build_id, None, [Feature.types['FuzzyPosition']])
                f.addFeatureToGraph(g)

                # sometimes there's a peak marker, like a rsid.  we want to add that as a variant of the gene,
                # and xref it to the qtl.
                dbsnp_id = None
                if peak_mark != '' and peak_mark != '.' and re.match('rs', peak_mark.strip()):
                    dbsnp_id = 'dbSNP:'+peak_mark.strip()

                    gu.addIndividualToGraph(g, dbsnp_id, None, geno.genoparts['sequence_alteration'])
                    gu.addXref(g, qtl_id, dbsnp_id)

                if gene_id is not None and gene_id != '' and gene_id != '.':
                    if gene_id_src == 'NCBIgene' or gene_id_src == '':  # we assume if no src is provided, it's NCBI
                        gene_id = 'NCBIGene:'+gene_id.strip()
                        geno.addGene(gene_id, None)  # we will expect that these labels provided elsewhere
                        geno.addAlleleOfGene(qtl_id, gene_id, geno.object_properties['feature_to_gene_relation'])   # FIXME what is the right relationship here?

                        if dbsnp_id is not None:
                            # add the rsid as a seq alt of the gene_id
                            vl_id = '_' + re.sub(':', '', gene_id) + '-' + peak_mark
                            if self.nobnodes:
                                vl_id = ':' + vl_id
                            geno.addSequenceAlterationToVariantLocus(dbsnp_id, vl_id)
                            geno.addAlleleOfGene(vl_id, gene_id)

                # add the trait
                gu.addClassToGraph(g, trait_id, trait_name)

                # Add publication
                r = None
                if re.match('ISU.*', pubmed_id):
                    pub_id = 'AQTLPub:'+pubmed_id.strip()
                    r = Reference(pub_id)
                elif pubmed_id != '':
                    pub_id = 'PMID:'+pubmed_id.strip()
                    r = Reference(pub_id, Reference.ref_types['journal_article'])

                if r is not None:
#.........这里部分代码省略.........