Python GraphUtils.digest_id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 digest_id [as 别名]
    def make_association_id(definedby, sub, pred, obj, attributes=None):
        """
        A method to create unique identifiers for OBAN-style associations,
        based on all the parts of the association
        If any of the items is empty or None, it will convert it to blank.
        It effectively digests the  string of concatonated values.
        Subclasses of Assoc can submit an additional array of attributes
        that will be appeded to the ID.

        Note this is equivalent to a RDF blank node

        :param definedby: The (data) resource that provided the annotation
        :param subject:
        :param predicate:
        :param object:
        :param attributes:

        :return:

        """

        items_to_hash = [definedby, sub, pred, obj]
        if attributes is not None and len(attributes) > 0:
            items_to_hash += attributes

        items_to_hash = [x for x in items_to_hash if x is not None]

        assoc_id = ':'.join(('MONARCH', GraphUtils.digest_id('+'.join(items_to_hash))))
        assert assoc_id is not None
        return assoc_id

# 需要导入模块: from dipper.utils.GraphUtils import GraphUtils [as 别名]
# 或者: from dipper.utils.GraphUtils.GraphUtils import digest_id [as 别名]
    def get_uniprot_entrez_id_map(self):
        taxon_digest = GraphUtils.digest_id(str(self.tax_ids))
        id_map = {}
        smallfile = '/'.join((self.rawdir, 'id_map_' + taxon_digest + '.yaml'))
        bigfile = '/'.join((self.rawdir, self.files['id-map']['file']))

        # if processed smallfile exists and is newer use it instesd
        if os.path.isfile(smallfile) and \
                os.path.getctime(smallfile) > os.path.getctime(bigfile):
            LOG.info("Using the cheap mapping file %s", smallfile)
            with open(smallfile, 'r') as fh:
                id_map = yaml.safe_load(fh)
        else:
            LOG.info(
                "Expensive Mapping from Uniprot ids to Entrez/ENSEMBL gene ids for %s",
                str(self.tax_ids))
            self.fetch_from_url(self.files['id-map']['url'], bigfile)
            with gzip.open(bigfile, 'rb') as csvfile:
                csv.field_size_limit(sys.maxsize)
                filereader = csv.reader(  # warning this file is over 10GB unzipped
                    io.TextIOWrapper(
                        csvfile, newline=""), delimiter='\t', quotechar='\"')
                for row in filereader:
                    (uniprotkb_ac, uniprotkb_id, geneid, refseq, gi, pdb, go,
                     uniref100, unifref90, uniref50, uniparc, pir, ncbitaxon, mim,
                     unigene, pubmed, embl, embl_cds, ensembl, ensembl_trs,
                     ensembl_pro, other_pubmed) = row
                    if int(ncbitaxon) not in self.tax_ids:
                        continue
                    genid = geneid.strip()
                    if geneid != '' and ';' not in genid:
                        id_map[uniprotkb_ac.strip()] = 'NCBIGene:' + genid
                    elif ensembl.strip() != '' and ';' not in ensembl:
                        id_map[uniprotkb_ac.strip()] = 'ENSEMBL:' + ensembl.strip()

            LOG.info("Writing id_map out as %s", smallfile)
            with open(smallfile, 'w') as fh:
                yaml.dump(id_map, fh)

        LOG.info(
            "Acquired %i 1:1 uniprot to [entrez|ensembl] mappings", len(id_map.keys()))

        return id_map