Python GraphUtils.addSameIndividual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 addSameIndividual [as 别名]
    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

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

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

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

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

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

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

#.........这里部分代码省略.........
                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']:

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

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

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

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