Mercurial > repos > boris > getalleleseq

comparison getalleleseq.py @ 0:c542b3075f29 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded repo.tar.gz
author boris
date Mon, 03 Feb 2014 13:07:13 -0500
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:c542b3075f29
1 #!/usr/bin/env python
2 # Boris Rebolledo-Jaramillo (boris-at-bx.psu.edu)
3 #
4 #usage: getalleleseq.py [-h] [-l INT] [-j FILE] [-d DIR] alleles
5 #
6 #Given a table with minor and major alleles per position, it generates the
7 #minor and major allele sequences in FASTA format
8 #
9 #positional arguments:
10 # alleles Table containing minor and major allele base per
11 # position. cols: [id, chr, pos, A, C, G, T, cvrg,
12 # plody, major, minor, freq_minor]
13 #
14 #optional arguments:
15 # -h, --help show this help message and exit
16 # -l INT, --seq-length INT
17 # Background sequence length. Bases in an artifical
18 # all-N-sequence of length INT will be replaced by
19 # either the major or minor allele base accordingly
20 # -j FILE, --major-seq FILE
21 # File to write major allele sequences in FASTA multiple
22 # alignment format.
23 # -d DIR, --minor-dir DIR
24 # Per sample minor allele sequences will be written to
25 # this directory
26 #
27 # The expected columns in the alleles table follow Nicholas Stoler's
28 # Variant Annotator tool format. See Variant Annotator in Galaxy's tool shed
29 # http://testtoolshed.g2.bx.psu.edu/repos/nick/allele_counts_1 for more details
30 #
31 # Expected columns:
32 # 1. sample_id
33 # 2. chr
34 # 3. position
35 # 4 counts for A's
36 # 5. counts for C's
37 # 6. counts for G's
38 # 7. counts for T's
39 # 8. Coverage
40 # 9. Number of alleles passing a given criteria
41 # 10. Major allele
42 # 11. Minor allele
43 # 12. Minor allele frequency in position
44
45 import sys
46 import os
47 import argparse
48
49 def createseq(sample, allele, seq_size, table):
50 """Generate major or minor allele sequence"""
51 out_sequence = ['N' for i in range(seq_size)]
52 sample_data = [line for line in table if line[0] == sample]
53
54 for entry in sample_data:
55 position = int(entry[2])
56 number_of_alleles = int(entry[8])
57 major_allele = entry[9].strip()
58 minor_allele = entry[10].strip()
59
60 if allele == 'major':
61 out_sequence[position-1] = major_allele
62 elif allele == 'minor':
63 if number_of_alleles == 2:
64 out_sequence[position-1] = minor_allele
65 else:
66 out_sequence[position-1] = major_allele
67 return out_sequence
68
69 def printseq(sample,allele,seq,output):
70 """Print out sequence"""
71 #print >> output, '>{0}_{1}'.format(sample,allele)
72 print >> output, '>{0}{1}'.format(sample,allele)
73 for i in range(0,len(seq),70):
74 print >> output, ''.join(seq[i:i+70])
75
76 def main():
77 parser = argparse.ArgumentParser(description='Given a table with minor and major alleles per position, it generates the minor and major allele sequences in FASTA format', epilog='Boris Rebolledo-Jaramillo (boris-at-bx.psu.edu)')
78 parser.add_argument('alleles', type=str, help='Table containing minor and major allele base per position. cols: [id, chr, pos, A, C, G, T, cvrg, plody, major, minor, freq_minor] ')
79 parser.add_argument('-l','--seq-length', type=int, metavar='INT', help='Background sequence length. Bases in an artifical all-N-sequence of length INT will be replaced by either the major or minor allele base accordingly')
80 parser.add_argument('-j','--major-seq', type=str, metavar='FILE', help='File to write major allele sequences in FASTA multiple alignment format.')
81 parser.add_argument('-d', '--minor-dir', type=str, metavar='DIR', default='.', help="Per sample minor allele sequences will be written to this directory (Default: current directory)")
82 parser.add_argument('-p', '--minor-prefix', type=str, metavar='STR', nargs='?', const='', default='', help=argparse.SUPPRESS) #Galaxy compatibility
83 args = parser.parse_args()
84
85
86 try:
87 table = [line.strip().split('\t') for line in list(open(args.alleles)) if "#" not in line]
88 samples = sorted(list(set([ line[0] for line in table ])))
89 except:
90 sys.exit('\nERROR: Could not open %s\n' % args.alleles)
91 try:
92 major_out = open(args.major_seq, 'w+')
93 except:
94 sys.exit('\nCould not create %s\n' % args.major_seq)
95
96 # Single file for all major allele sequences in FASTA multiple alignment
97 for sample in samples:
98 sequence = createseq(sample,'major',args.seq_length,table)
99 #printseq(sample,'major',sequence,major_out)
100 printseq(sample,'',sequence,major_out)
101 major_out.close()
102
103 # Sample specific minor allele sequence in FASTA format
104 try:
105 os.makedirs(args.minor_dir)
106 except:
107 pass
108
109 for sample in samples:
110 if args.minor_prefix: # to fit Galaxy requirements
111 name = sample.replace('_','')
112 minor_name = "%s_%s_%s" % ('primary',args.minor_prefix,name+'-minor_visible_fasta')
113 else: # for non-Galaxy
114 minor_name = sample+'-minor.fa'
115 minor_out = open(os.path.join(args.minor_dir, minor_name), 'w+')
116 sequence = createseq(sample,'minor',args.seq_length,table)
117 #printseq(sample,'minor',sequence,minor_out)
118 printseq(sample,'_minor',sequence,minor_out)
119 minor_out.close()
120
121 if __name__ == "__main__": main()