comparison data_manager/data_manager_fetch_motifs.py @ 0:cab6e1cb4c2a draft default tip

Uploaded
author jeremyjliu
date Sat, 16 May 2015 17:23:06 -0400
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:cab6e1cb4c2a
1 #!/usr/bin/env python
2 # Jeremy Liu
3 # February 2015
4 # Adapted from Dan Blackenburg's sample data manager
5
6 import sys
7 import os
8 import tempfile
9 import shutil
10 import optparse
11 import urllib2
12 #import uuid
13 from ftplib import FTP
14 import tarfile
15 import zipfile
16 import gzip
17 import bz2
18
19 from galaxy.util.json import from_json_string, to_json_string
20
21 CHUNK_SIZE = 2**20 #1mb
22
23 def download_motif_databases( data_manager_dict, params, target_directory, motif_db ):
24
25 # Select download URL, file name, data table name, and path using motif_db selector variable
26 if motif_db == "encode":
27 BGZ = ['http://compbio.med.harvard.edu/motif-enrichment/pouya_motifs.bed.bgz',
28 "pouya_motifs.bed.bgz", "encode_bgz", "Encode Motifs (hg19) BGZ"]
29 TBI = ['http://compbio.med.harvard.edu/motif-enrichment/pouya_motifs.bed.bgz.tbi',
30 "pouya_motifs.bed.bgz.tbi", "encode_tbi", "Encode Motifs (hg19) TBI"]
31 PWM = ['http://compbio.med.harvard.edu/motif-enrichment/pwms/pouya.pwms.from.seq.meme.txt',
32 "pouya.pwms.from.seq.meme.txt", "encode_pwm", "Encode Motifs (hg19) PWM MEME"]
33 elif motif_db == "jaspar":
34 BGZ = ['http://compbio.med.harvard.edu/motif-enrichment/jaspar_jolma_motifs.bed.bgz',
35 "jaspar_jolma_motifs.bed.bgz", "jaspar_bgz", "Jaspar and Jolma Motifs (hg19) BGZ"]
36 TBI = ['http://compbio.med.harvard.edu/motif-enrichment/jaspar_jolma_motifs.bed.bgz.tbi',
37 "jaspar_jolma_motifs.bed.bgz.tbi", "jaspar_tbi", "Jaspar and Jolma Motifs (hg19) TBI"]
38 PWM = ['http://compbio.med.harvard.edu/motif-enrichment/pwms/jaspar.jolma.pwms.from.seq.meme.txt',
39 "jaspar.jolma.pwms.from.seq.meme.txt", "jaspar_pwm", "Jaspar and Jolma Motifs (hg19) PWM MEME"]
40 elif motif_db == "mouse":
41 BGZ = ['http://compbio.med.harvard.edu/motif-enrichment/mm9_motifs_split.bed.bgz',
42 "mm9_motifs_split.bed.bgz", "mouse_bgz", "Mouse Motifs (mm9) BGZ"]
43 TBI = ['http://compbio.med.harvard.edu/motif-enrichment/mm9_motifs_split.bed.bgz.tbi',
44 "mm9_motifs_split.bed.bgz.tbi", "mouse_tbi", "Mouse Motifs (mm9) TBI"]
45 PWM = ['http://compbio.med.harvard.edu/motif-enrichment/pwms/mm9.pwms.from.seq.meme.txt',
46 "mm9.pwms.from.seq.meme.txt", "mouse_pwm", "Mouse Motifs (mm9) PWM MEME"]
47 else:
48 BGZ = ['http://compbio.med.harvard.edu/motif-enrichment/pouya_test_motifs.bed.bgz',
49 "pouya_test_motifs.bed.bgz", "test_bgz", "Test Encode Motifs (hg19) BGZ"]
50 TBI = ['http://compbio.med.harvard.edu/motif-enrichment/pouya_test_motifs.bed.bgz.tbi',
51 "pouya_test_motifs.bed.bgz.tbi", "test_tbi", "Test Encode Motifs (hg19) TBI"]
52 PWM = ['http://compbio.med.harvard.edu/motif-enrichment/pwms/pouya.pwms.from.seq.meme.txt',
53 "pouya.pwms.from.seq.meme.txt", "test_pwm", "Test Encode Motifs (hg19) PWM MEME"]
54
55
56 # Save and add motif bgz file to motif_databases data table
57 bgz_reader = urllib2.urlopen( BGZ[0] )
58 bgz_data_table_entry = _stream_fasta_to_file( bgz_reader, target_directory, params,
59 BGZ[1], BGZ[2], BGZ[3] )
60 _add_data_table_entry( data_manager_dict, 'motif_databases', bgz_data_table_entry )
61
62 # Save and add motif tbi file to motif_databases data table
63 tbi_reader = urllib2.urlopen( TBI[0] )
64 tbi_data_table_entry = _stream_fasta_to_file( tbi_reader, target_directory, params,
65 TBI[1], TBI[2], TBI[3] )
66 _add_data_table_entry( data_manager_dict, 'motif_databases', tbi_data_table_entry )
67
68 # Save and add motif pwm file to motif_databases data table
69 tbi_reader = urllib2.urlopen( PWM[0] )
70 tbi_data_table_entry = _stream_fasta_to_file( tbi_reader, target_directory, params,
71 PWM[1], PWM[2], PWM[3] )
72 _add_data_table_entry( data_manager_dict, 'motif_databases', tbi_data_table_entry )
73
74 def _add_data_table_entry( data_manager_dict, data_table, data_table_entry ):
75 data_manager_dict['data_tables'] = data_manager_dict.get( 'data_tables', {} )
76 data_manager_dict['data_tables'][data_table] = data_manager_dict['data_tables'].get( data_table, [] )
77 data_manager_dict['data_tables'][data_table].append( data_table_entry )
78 return data_manager_dict
79
80 def _stream_fasta_to_file( fasta_stream, target_directory, params,
81 fasta_base_filename, value, name, close_stream=True ):
82 fasta_filename = os.path.join( target_directory, fasta_base_filename )
83 fasta_writer = open( fasta_filename, 'wb+' )
84
85 while True:
86 buffer = fasta_stream.read(CHUNK_SIZE)
87 if not buffer:
88 break
89
90 fasta_writer.write(buffer)
91
92 fasta_stream.close()
93 fasta_writer.close()
94
95 return dict( value=value, name=name, path=fasta_base_filename )
96
97 def main():
98 #Parse Command Line
99 parser = optparse.OptionParser()
100 parser.add_option( '-m', '--motif_db', dest='motif_db', action='store', type="string", default=None, help='motif_db' )
101 (options, args) = parser.parse_args()
102
103 filename = args[0]
104
105 params = from_json_string( open( filename ).read() )
106 target_directory = params[ 'output_data' ][0]['extra_files_path']
107 os.mkdir( target_directory )
108 data_manager_dict = {}
109
110 #Fetch the Motif Database
111 download_motif_databases( data_manager_dict, params, target_directory, options.motif_db )
112
113 #save info to json file
114 open( filename, 'wb' ).write( to_json_string( data_manager_dict ) )
115
116 if __name__ == "__main__": main()