Python GraphUtils.addOWLPropertyClassRestriction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 addOWLPropertyClassRestriction [as 别名]

#.........这里部分代码省略.........
        # using the full graph as the test here
        self.testgraph = self.graph
        logger.info("Found %d nodes", len(self.graph))
        logger.info("Done parsing files.")

        return

    def _get_chrbands(self, limit, taxon):
        """
        For the given taxon, it will fetch the chr band file.
        We will not deal with the coordinate information with this parser.
        Here, we only are concerned with building the partonomy.
        :param limit:
        :return:

        """
        line_counter = 0
        myfile = '/'.join((self.rawdir, self.files[taxon]['file']))
        logger.info("Processing Chr bands from FILE: %s", myfile)
        geno = Genotype(self.graph)

        # build the organism's genome from the taxon
        genome_label = self.files[taxon]['genome_label']
        taxon_id = 'NCBITaxon:'+taxon

        # add the taxon as a class.  adding the class label elsewhere
        self.gu.addClassToGraph(self.graph, taxon_id, None)
        self.gu.addSynonym(self.graph, taxon_id, genome_label)

        self.gu.loadObjectProperties(self.graph, Feature.object_properties)

        genome_id = geno.makeGenomeID(taxon_id)
        geno.addGenome(taxon_id, genome_label)
        self.gu.addOWLPropertyClassRestriction(
            self.graph, genome_id, Genotype.object_properties['in_taxon'],
            taxon_id)

        with gzip.open(myfile, 'rb') as f:
            for line in f:
                # skip comments
                line = line.decode().strip()
                if re.match(r'^#', line):
                    continue

                # chr13	4500000	10000000	p12	stalk
                (chrom, start, stop, band, rtype) = line.split('\t')
                line_counter += 1

                # NOTE
                # some less-finished genomes have placed and unplaced scaffolds
                # * Placed scaffolds:
                #    Scaffold has an oriented location within a chromosome.
                # * Unlocalized scaffolds:
                #     scaffold 's chromosome  is known,
                #     scaffold's position, orientation or both is not known.
                # *Unplaced scaffolds:
                #   it is not known which chromosome the scaffold belongs to.

                # find out if the thing is a full on chromosome, or a scaffold:
                # ex: unlocalized scaffold: chr10_KL568008v1_random
                # ex: unplaced scaffold: chrUn_AABR07022428v1
                placed_scaffold_pattern = r'chr(\d+|X|Y|Z|W|MT|M)'

                # TODO unused
                # unlocalized_scaffold_pattern = \
                #    placed_scaffold_pattern + r'_(\w+)_random'

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

#.........这里部分代码省略.........
        # add the species-specific subclass (TODO please review this choice)
        gb_species_id = row['gb_species_id']

        if gb_species_id != '':
            sp_phene_id = '-'.join((omia_id, gb_species_id))
        else:
            logger.error(
                "No species supplied in species-specific phene table for %s",
                omia_id)
            return

        species_id = 'NCBITaxon:'+str(gb_species_id)
        # use this instead
        species_label = self.label_hash.get('NCBITaxon:'+gb_species_id)
        if sp_phene_label is None and \
                omia_label is not None and species_label is not None:
            sp_phene_label = ' '.join((omia_label, 'in', species_label))
        self.gu.addClassToGraph(
            self.g, sp_phene_id, sp_phene_label, omia_id, descr)
        # add to internal hash store for later lookup
        self.id_hash['phene'][row['phene_id']] = sp_phene_id
        self.label_hash[sp_phene_id] = sp_phene_label
        # add each of the following descriptions,
        # if they are populated, with a tag at the end.
        for item in [
                'clin_feat', 'history', 'pathology', 'mol_gen', 'control']:
            if row[item] is not None and row[item] != '':
                self.gu.addDescription(
                    self.g, sp_phene_id, row[item] + ' ['+item+']')
        # if row['symbol'] is not None:  # species-specific
        # CHECK ME - sometimes spaces or gene labels
        #     gu.addSynonym(g, sp_phene, row['symbol'])

        self.gu.addOWLPropertyClassRestriction(
            self.g, sp_phene_id, self.gu.object_properties['in_taxon'],
            species_id)

        # add inheritance as an association
        inheritance_id = self._map_inheritance_term_id(row['inherit'])
        if inheritance_id is not None:
            assoc = DispositionAssoc(self.name, sp_phene_id, inheritance_id)
            assoc.add_association_to_graph(self.g)

        if row['characterised'] == 'Yes':
            self.stored_omia_mol_gen[omia_id] = {
                'mol_gen': row['mol_gen'],
                'map_info': row['map_info'],
                'species': row['gb_species_id']}

        return

    def write_molgen_report(self):
        import csv
        logger.info("Writing G2P report for OMIA")
        f = '/'.join((self.outdir, 'omia_molgen_report.txt'))

        with open(f, 'w', newline='\n') as csvfile:
            writer = csv.writer(csvfile, delimiter='\t')
            # write header
            h = ['omia_id', 'molecular_description', 'mapping_info', 'species']
            writer.writerow(h)
            for phene in self.stored_omia_mol_gen:
                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']))