Python Genotype.addDerivesFrom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 addDerivesFrom [as 别名]

#.........这里部分代码省略.........
                        affected = 'affected'
                    elif affected == 'No':
                        affected = 'unaffected'
                    gender = gender.lower()
                    patient_label = ' '.join((affected, gender, relprob))
                    if relprob == 'proband':
                        patient_label = \
                            ' '.join(
                                (patient_label.strip(), 'with', short_desc))
                    else:
                        patient_label = \
                            ' '.join(
                                (patient_label.strip(), 'of proband with',
                                 short_desc))

                    # #############    BUILD THE CELL LINE    #############

                    # Adding the cell line as a typed individual.
                    cell_line_reagent_id = 'CLO:0000031'

                    gu.addIndividualToGraph(
                        g, cell_line_id, line_label, cell_line_reagent_id)

                    # add the equivalent id == dna_ref
                    if dna_ref != '' and dna_ref != catalog_id:
                        equiv_cell_line = 'Coriell:'+dna_ref
                        # some of the equivalent ids are not defined
                        # in the source data; so add them
                        gu.addIndividualToGraph(
                            g, equiv_cell_line, None, cell_line_reagent_id)
                        gu.addSameIndividual(g, cell_line_id, equiv_cell_line)

                    # Cell line derives from patient
                    geno.addDerivesFrom(cell_line_id, patient_id)
                    geno.addDerivesFrom(cell_line_id, cell_type)

                    # Cell line a member of repository
                    gu.addMember(g, repository, cell_line_id)

                    if cat_remark != '':
                        gu.addDescription(g, cell_line_id, cat_remark)

                    # Cell age_at_sampling
                    # TODO add the age nodes when modeled properly in #78
                    # if (age != ''):
                        # this would give a BNode that is an instance of Age.
                        # but i don't know how to connect
                        # the age node to the cell line? we need to ask @mbrush
                        # age_id = '_'+re.sub('\s+','_',age)
                        # gu.addIndividualToGraph(
                        #   g,age_id,age,self.terms['age'])
                        # gu.addTriple(
                        #   g,age_id,self.properties['has_measurement'],age,
                        #   True)

                    # #############    BUILD THE PATIENT    #############

                    # Add the patient ID as an individual.
                    gu.addPerson(g, patient_id, patient_label)
                    # TODO map relationship to proband as a class
                    # (what ontology?)

                    # Add race of patient
                    # FIXME: Adjust for subcategories based on ethnicity field
                    # EDIT: There are 743 different entries for ethnicity...
                    # Too many to map?

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

        # 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, and break our system; replace these with underscores
                colony_id = '_'+re.sub('[<>\s]', '_', colony)
                if self.nobnodes:
                    colony_id = ':'+colony_id

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

                ##############    BUILD THE COLONY    #############
                # first, let's describe the colony that the animals come from
                # The Colony ID refers to the ES cell clone used to generate a mouse strain.
                # Terry sez: we use this clone ID to track ES cell -> mouse strain -> mouse phenotyping.
                # The same ES clone maybe used at multiple centers, so we have to concatenate the two to have a
                # unique ID.
                # some useful reading about generating mice from ES cells:
                # http://ki.mit.edu/sbc/escell/services/details

                # here, we'll make a genotype that derives from an ES cell with a given allele.  the strain is not
                # really attached to the colony.

                # the colony/clone is reflective of the allele, with unknown zygosity
                stem_cell_class = 'CL:0000034'
                gu.addIndividualToGraph(g, colony_id, colony, stem_cell_class)

                # vslc of the colony has unknown zygosity
                # note that we will define the allele (and it's relationship to the marker, etc.) later
                vslc_colony = '_'+allele_accession_id+geno.zygosity['indeterminate']
                vslc_colony = re.sub(':', '', vslc_colony)
                if self.nobnodes:
                    vslc_colony = ':'+vslc_colony
                vslc_colony_label = allele_symbol+'/<?>'
                gu.addIndividualToGraph(g, vslc_colony, vslc_colony_label,
                                        geno.genoparts['variant_single_locus_complement'])
                geno.addPartsToVSLC(vslc_colony, allele_accession_id, None, geno.zygosity['indeterminate'],
                                    geno.object_properties['has_alternate_part'])
                gu.addTriple(g, colony_id, geno.object_properties['has_genotype'], vslc_colony)

                ##############    BUILD THE ANNOTATED GENOTYPE    #############
                # now, we'll build the genotype of the individual that derives from the colony/clone
                # genotype that is attached to phenotype = colony_id + strain + zygosity + sex
                # (and is derived from a colony)

                genotype_id = self.make_id((colony_id+phenotyping_center+zygosity+strain_accession_id))
                geno.addDerivesFrom(genotype_id, colony_id)

                # 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 = variant_locus_name = sequence_alteration_name = None

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

                if marker_accession_id is not None and marker_accession_id != '':
                    variant_locus_id = allele_accession_id
#.........这里部分代码省略.........