Python GraphUtils.addDeprecatedIndividual方法代码示例

# 需要导入模块: from dipper.utils.GraphUtils import GraphUtils [as 别名]
# 或者: from dipper.utils.GraphUtils.GraphUtils import addDeprecatedIndividual [as 别名]
    def _get_process_allelic_variants(self, entry, g):
        gu = GraphUtils(curie_map.get())
        geno = Genotype(g)
        du = DipperUtil()
        if entry is not None:
            publist = {}  # to hold the entry-specific publication mentions for the allelic variants
            entry_num = entry['mimNumber']

            # process the ref list just to get the pmids
            ref_to_pmid = self._get_pubs(entry, g)

            if 'allelicVariantList' in entry:
                allelicVariantList = entry['allelicVariantList']
                for al in allelicVariantList:
                    al_num = al['allelicVariant']['number']
                    al_id = 'OMIM:'+str(entry_num)+'.'+str(al_num).zfill(4)
                    al_label = None
                    al_description = None
                    if al['allelicVariant']['status'] == 'live':
                        publist[al_id] = set()
                        if 'mutations' in al['allelicVariant']:
                            al_label = al['allelicVariant']['mutations']
                        if 'text' in al['allelicVariant']:
                            al_description = al['allelicVariant']['text']
                            m = re.findall('\{(\d+)\:', al_description)
                            publist[al_id] = set(m)
                        geno.addAllele(al_id, al_label, geno.genoparts['variant_locus'], al_description)
                        geno.addAlleleOfGene(al_id, 'OMIM:'+str(entry_num),
                                             geno.object_properties['is_sequence_variant_instance_of'])
                        for r in publist[al_id]:
                            pmid = ref_to_pmid[int(r)]
                            gu.addTriple(g, pmid, gu.object_properties['is_about'], al_id)
                        # look up the pubmed id in the list of references
                        if 'dbSnps' in al['allelicVariant']:
                            dbsnp_ids = re.split(',', al['allelicVariant']['dbSnps'])
                            for dnum in dbsnp_ids:
                                did = 'dbSNP:'+dnum.strip()
                                gu.addIndividualToGraph(g, did, None)
                                gu.addEquivalentClass(g, al_id, did)
                        if 'clinvarAccessions' in al['allelicVariant']:
                            # clinvarAccessions triple semicolon delimited, each lik eRCV000020059;;1
                            rcv_ids = re.split(';;;', al['allelicVariant']['clinvarAccessions'])
                            rcv_ids = [(re.match('(RCV\d+)\;\;', r)).group(1) for r in rcv_ids]
                            for rnum in rcv_ids:
                                rid = 'ClinVar:'+rnum
                                gu.addXref(g, al_id, rid)
                        gu.addPage(g, al_id, "http://omim.org/entry/"+str(entry_num)+"#"+str(al_num).zfill(4))
                    elif re.search('moved', al['allelicVariant']['status']):
                        # for both 'moved' and 'removed'
                        moved_ids = None
                        if 'movedTo' in al['allelicVariant']:
                            moved_id = 'OMIM:'+al['allelicVariant']['movedTo']
                            moved_ids = [moved_id]
                        gu.addDeprecatedIndividual(g, al_id, moved_ids)
                    else:
                        logger.error('Uncaught alleleic variant status %s', al['allelicVariant']['status'])
                # end loop allelicVariantList

        return

# 需要导入模块: from dipper.utils.GraphUtils import GraphUtils [as 别名]
# 或者: from dipper.utils.GraphUtils.GraphUtils import addDeprecatedIndividual [as 别名]
    def _get_gene_history(self, limit):
        """
        Loops through the gene_history file and adds the old gene ids
        as deprecated classes, where the new gene id is the replacement for it.
        The old gene symbol is added as a synonym to the gene.
        :param limit:
        :return:

        """
        gu = GraphUtils(curie_map.get())
        if self.testMode:
            g = self.testgraph
        else:
            g = self.graph

        logger.info("Processing Gene records")
        line_counter = 0
        myfile = '/'.join((self.rawdir, self.files['gene_history']['file']))
        logger.info("FILE: %s", myfile)
        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, discontinued_num, discontinued_symbol,
                 discontinued_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 gene_num == '-' or discontinued_num == '-':
                    continue

                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))
                discontinued_gene_id = ':'.join(('NCBIGene', discontinued_num))

                # add the two genes
                if self.class_or_indiv.get(gene_id) == 'C':
                    gu.addClassToGraph(g, gene_id, None)
                    gu.addClassToGraph(
                        g, discontinued_gene_id, discontinued_symbol)

                    # add the new gene id to replace the old gene id
                    gu.addDeprecatedClass(g, discontinued_gene_id, [gene_id])
                else:
                    gu.addIndividualToGraph(g, gene_id, None)
                    gu.addIndividualToGraph(
                        g, discontinued_gene_id, discontinued_symbol)
                    gu.addDeprecatedIndividual(
                        g, discontinued_gene_id, [gene_id])

                # also add the old symbol as a synonym of the new gene
                gu.addSynonym(g, gene_id, discontinued_symbol)

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

        return

# 需要导入模块: from dipper.utils.GraphUtils import GraphUtils [as 别名]
# 或者: from dipper.utils.GraphUtils.GraphUtils import addDeprecatedIndividual [as 别名]

#.........这里部分代码省略.........
                    if risk_allele_frequency != '' and \
                            risk_allele_frequency != 'NR':
                        snp_description = \
                            str(risk_allele_frequency) + \
                            ' [risk allele frequency]'

                    f = Feature(
                        rs_id, strongest_snp_risk_allele.strip(),
                        Feature.types[r'SNP'], snp_description)
                    if chrom_num != '' and chrom_pos != '':
                        f.addFeatureStartLocation(chrom_pos, chrom_id)
                        f.addFeatureEndLocation(chrom_pos, chrom_id)
                    f.addFeatureToGraph(g)
                    f.addTaxonToFeature(g, tax_id)
                    # TODO consider adding allele frequency as property;
                    # but would need background info to do that

                    # also want to add other descriptive info about
                    # the variant from the context
                    for c in re.split(r';', context):
                        cid = self._map_variant_type(c.strip())
                        if cid is not None:
                            gu.addType(g, rs_id, cid)

                    # 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'
                        if loc is not None:
                            loc_to_id_hash[loc].append(current_rs_id)
                        current_rs_id += str(snp_id_current)
                        gu.addDeprecatedIndividual(g, rs_id, current_rs_id)
                        # TODO check on this
                        # should we add the annotations to the current
                        # or orig?
                        gu.makeLeader(g, current_rs_id)
                    else:
                        gu.makeLeader(g, rs_id)

                    # add the feature as a sequence alteration
                    # affecting various genes
                    # note that intronic variations don't necessarily list
                    # the genes such as for rs10448080  FIXME
                    if snp_gene_nums != '':
                        for s in re.split(r',', snp_gene_nums):
                            s = s.strip()
                            # still have to test for this,
                            # because sometimes there's a leading comma
                            if s != '':
                                gene_id = 'NCBIGene:'+s
                                geno.addAlleleOfGene(rs_id, gene_id)

                    # add the up and downstream genes if they are available
                    if upstream_gene_num != '':
                        downstream_gene_id = 'NCBIGene:'+downstream_gene_num
                        gu.addTriple(
                            g, rs_id,
                            Feature.object_properties[
                                r'upstream_of_sequence_of'],
                            downstream_gene_id)
                    if downstream_gene_num != '':
                        upstream_gene_id = 'NCBIGene:'+upstream_gene_num
                        gu.addTriple(
                            g, rs_id,