Mercurial > repos > earlhaminst > ensembl_get_sequences

comparison get_sequences.py @ 1:e5dd4bd78bbc draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/TGAC/earlham-galaxytools/tree/master/tools/Ensembl-REST commit aaf8d501c3a92ed415fdf9293a65468c72aae984-dirty
author earlhaminst
date Mon, 12 Dec 2016 07:47:42 -0500
parents
children 4b7261f484bb
comparison
equal deleted inserted replaced
0:76b2c482f1e8 1:e5dd4bd78bbc
1 # A simple tool to connect to the Ensembl server and retrieve sequences using
2 # the Ensembl REST API.
3 import json
4 import optparse
5 from itertools import islice
6 from urlparse import urljoin
7
8 import requests
9
10 parser = optparse.OptionParser()
11 parser.add_option('-i', '--input', help='List of Ensembl IDs')
12
13 parser.add_option('-s', '--species', type='choice',
14 choices=['ensembl', 'ensemblgenomes'], default='ensembl',
15 help='Specify the genome databases for vertebrates and other eukaryotic species')
16
17 parser.add_option('-t', '--type', type='choice',
18 choices=['genomic', 'cds', 'cdna', 'protein'],
19 default='genomic', help='Type of sequence')
20 parser.add_option('--expand_3prime', type='int', default=0,
21 help='Expand the sequence downstream of the sequence by this many basepairs. Only available when using genomic sequence type')
22 parser.add_option('--expand_5prime', type='int', default=0,
23 help='Expand the sequence upstream of the sequence by this many basepairs. Only available when using genomic sequence type')
24 options, args = parser.parse_args()
25 if options.input is None:
26 raise Exception('-i option must be specified')
27
28 server = 'http://rest.%s.org' % options.species
29 ext = 'sequence/id'
30
31 headers = {'Content-Type': 'text/x-fasta', 'Accept': 'text/x-fasta'}
32 params = dict((k, getattr(options, k)) for k in ['type', 'expand_3prime', 'expand_5prime'])
33 with open(options.input) as f:
34 # Need to split the file in chunks of 50 lines because of the limit imposed by Ensembl
35 while True:
36 ids = [line.strip() for line in islice(f, 50)]
37 if not ids:
38 break
39 data = {'ids': ids}
40 r = requests.post(urljoin(server, ext), params=params, headers=headers,
41 data=json.dumps(data))
42
43 if not r.ok:
44 r.raise_for_status()
45
46 print r.text