biomart_id_lookup.py

import csv
import requests

def build_ensembl_biomart_dict(dataset_name, key_attr, val_attr):
    # see http://ensembl.org/biomart/martview/ for the web application
    biomart_request_url_template = \
        '''http://ensembl.org/biomart/martservice?query=''' \
        '''<?xml version="1.0" encoding="UTF-8"?>''' \
        '''<!DOCTYPE Query>''' \
        '''<Query virtualSchemaName="default" formatter="CSV" header="0" uniqueRows="0" count="" datasetConfigVersion="0.6">''' \
        '''<Dataset name="{}" interface="default">''' \
        '''<Attribute name="{}"/>''' \
        '''<Attribute name="{}"/>''' \
        '''</Dataset>''' \
        '''</Query>'''
    biomart_request_url = biomart_request_url_template.format(dataset_name, key_attr, val_attr)
    req = requests.get(biomart_request_url, stream=True)

    return dict(csv.reader(req.iter_lines()))


def main():
    nm_to_trans_dict = build_ensembl_biomart_dict(
        'hsapiens_gene_ensembl',
        'refseq_mrna',
        'ensembl_transcript_id')
    trans_to_gene_dict = build_ensembl_biomart_dict(
        'hsapiens_gene_ensembl',
        'ensembl_transcript_id',
        'ensembl_gene_id')


    nm_ids = ('NM_005665', 'NM_021797', 'NM_020440', 'NM_001039703',
              'NM_001009931', 'NM_002963', 'NM_001204087', 'NM_002455',
              'NM_001105205', 'NM_005598')
    for nm_id in nm_ids:
        trans_id = nm_to_trans_dict[nm_id]
        gene_id = trans_to_gene_dict[trans_id]
        print('NM ID: {}, transcript: {}, gene: {}'.format(nm_id, trans_id, gene_id))

if __name__ == '__main__':
    main()

resulting output:

NM ID: NM_005665, transcript: ENST00000370331, gene: ENSG00000067208
NM ID: NM_021797, transcript: ENST00000430615, gene: ENSG00000134216
NM ID: NM_020440, transcript: ENST00000393203, gene: ENSG00000134247
NM ID: NM_001039703, transcript: ENST00000583866, gene: ENSG00000271425
NM ID: NM_001009931, transcript: ENST00000368801, gene: ENSG00000197915
NM ID: NM_002963, transcript: ENST00000368723, gene: ENSG00000143556
NM ID: NM_001204087, transcript: ENST00000618040, gene: ENSG00000143603
NM ID: NM_002455, transcript: ENST00000368376, gene: ENSG00000173171
NM ID: NM_001105205, transcript: ENST00000368347, gene: ENSG00000160753
NM ID: NM_005598, transcript: ENST00000302101, gene: ENSG00000171786