Mercurial > repos > galaxyp > retrieve_ensembl_bed

comparison ensembl_rest.py @ 0:887e111c0919 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/proteogenomics/retrieve_ensembl_bed commit 3fd7be931712e7fa5b281bc8c48104c8583ef7f0
author galaxyp
date Sun, 14 Jan 2018 14:11:53 -0500
parents
children c3d600729b6f
comparison
equal deleted inserted replaced
-1:000000000000 0:887e111c0919
1 #!/usr/bin/env python
2 """
3 #
4 #------------------------------------------------------------------------------
5 # University of Minnesota
6 # Copyright 2017, Regents of the University of Minnesota
7 #------------------------------------------------------------------------------
8 # Author:
9 #
10 # James E Johnson
11 #
12 #------------------------------------------------------------------------------
13 """
14
15
16 import sys
17
18 from time import sleep
19
20 import requests
21
22
23 server = "https://rest.ensembl.org"
24 ext = "/info/assembly/homo_sapiens?"
25 max_region = 4000000
26 debug = False
27
28
29 def ensembl_rest(ext, headers):
30 if debug:
31 print >> sys.stderr, "%s" % ext
32 r = requests.get(server+ext, headers=headers)
33 if r.status_code == 429:
34 print >> sys.stderr, "response headers: %s\n" % r.headers
35 if 'Retry-After' in r.headers:
36 sleep(r.headers['Retry-After'])
37 r = requests.get(server+ext, headers=headers)
38 if not r.ok:
39 r.raise_for_status()
40 return r
41
42
43 def get_species():
44 results = dict()
45 ext = "/info/species"
46 req_header = {"Content-Type": "application/json"}
47 r = ensembl_rest(ext, req_header)
48 for species in r.json()['species']:
49 results[species['name']] = species
50 print >> sys.stdout,\
51 "%s\t%s\t%s\t%s\t%s"\
52 % (species['name'], species['common_name'],
53 species['display_name'],
54 species['strain'],
55 species['taxon_id'])
56 return results
57
58
59 def get_biotypes(species):
60 biotypes = []
61 ext = "/info/biotypes/%s?" % species
62 req_header = {"Content-Type": "application/json"}
63 r = ensembl_rest(ext, req_header)
64 for entry in r.json():
65 if 'biotype' in entry:
66 biotypes.append(entry['biotype'])
67 return biotypes
68
69
70 def get_toplevel(species):
71 coord_systems = dict()
72 ext = "/info/assembly/%s?" % species
73 req_header = {"Content-Type": "application/json"}
74 r = ensembl_rest(ext, req_header)
75 toplevel = r.json()
76 for seq in toplevel['top_level_region']:
77 if seq['coord_system'] not in coord_systems:
78 coord_systems[seq['coord_system']] = dict()
79 coord_system = coord_systems[seq['coord_system']]
80 coord_system[seq['name']] = int(seq['length'])
81 return coord_systems
82
83
84 def get_transcripts_bed(species, refseq, start, length, strand='',
85 params=None):
86 bed = []
87 param = params if params else ''
88 req_header = {"Content-Type": "text/x-bed"}
89 regions = range(start, length, max_region)
90 if not regions or regions[-1] < length:
91 regions.append(length)
92 for end in regions[1:]:
93 ext = "/overlap/region/%s/%s:%d-%d%s?feature=transcript;%s"\
94 % (species, refseq, start, end, strand, param)
95 start = end + 1
96 r = ensembl_rest(ext, req_header)
97 if r.text:
98 bed += r.text.splitlines()
99 return bed
100
101
102 def get_seq(id, seqtype, params=None):
103 param = params if params else ''
104 ext = "/sequence/id/%s?type=%s;%s" % (id, seqtype, param)
105 req_header = {"Content-Type": "text/plain"}
106 r = ensembl_rest(ext, req_header)
107 return r.text
108
109
110 def get_cdna(id, params=None):
111 return get_seq(id, 'cdna', params=params)
112
113
114 def get_cds(id, params=None):
115 return get_seq(id, 'cds', params=params)
116
117
118 def get_genomic(id, params=None):
119 return get_seq(id, 'genomic', params=params)
120
121
122 def get_transcript_haplotypes(species, transcript):
123 ext = "/transcript_haplotypes/%s/%s?aligned_sequences=1"\
124 % (species, transcript)
125 req_header = {"Content-Type": "application/json"}
126 r = ensembl_rest(ext, req_header)
127 decoded = r.json()
128 return decoded