ChromosomeBot.py 文件源码

def get_assembly_report(self, taxid):
        if self.ass_sum is None:
            self.get_assembly_summaries()
        df = self.ass_sum.query("taxid == {} & refseq_category == 'reference genome'".format(taxid))
        if len(df) == 0:
            # try "representative genome" (needed for mouse and rat)
            df = self.ass_sum.query("taxid == {} & refseq_category == 'representative genome'".format(taxid))
        if len(df) != 1:
            raise ValueError("unknown reference: {}".format(df))
        print(df)
        ftp_path = list(df.ftp_path)[0]
        assembly = os.path.split(ftp_path)[1]
        url = os.path.join(ftp_path, assembly + "_assembly_report.txt")
        print(url)
        # read the column names from the file
        table = request.urlopen(request.Request(url)).read().decode()
        names = [x for x in table.split("\n") if x.startswith("#")][-1].strip().replace("# ", "").split("\t")
        self.chr_df[taxid] = pd.read_csv(StringIO(table), sep="\t", names=names, comment='#')
        self.chr_df[taxid] = self.chr_df[taxid].rename(columns={'Sequence-Name': 'SequenceName', 'Sequence-Role': 'SequenceRole',
                                                                'Assigned-Molecule': 'AssignedMolecule',
                                                                'Assigned-Molecule-Location/Type': 'AssignedMoleculeLocationType',
                                                                'GenBank-Accn': 'GenBankAccn', 'RefSeq-Accn': 'RefSeqAccn',
                                                                'UCSC-style-name': 'UCSCstylename'})
        #print(self.chr_df[taxid].query("SequenceRole == 'assembled-molecule'"))