Mercurial > repos > crs4 > prokka

comparison prokka.py @ 0:95505a9fa26f draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author crs4
date Tue, 10 Sep 2013 13:11:26 -0400
parents
children 4b6f16a79fe4
comparison
equal deleted inserted replaced
-1:000000000000 0:95505a9fa26f
1 # -*- coding: utf-8 -*-
2 """
3 Wrapper for Prokka - Prokaryotic annotation tool
4 Author: Paolo Uva paolo dot uva at crs4 dot it
5 Date: February 14, 2013
6 Update: March 14, 2013 - Added more options
7 """
8
9 import optparse
10 import shutil
11 import subprocess
12 import sys
13
14
15 def __main__():
16 #Parse Command Line
17 parser = optparse.OptionParser()
18 parser.add_option('--cpus', dest='cpus', type='int', help='Number of CPUs to use [0=all]')
19 parser.add_option('--fasta', dest='fasta', help='FASTA file with contigs')
20 parser.add_option('--kingdom', dest='kingdom', choices=['Archaea', 'Bacteria', 'Viruses'], default='Bacteria', help='Kingdom')
21 parser.add_option('--mincontig', dest='mincontig', type='int', help='Minimun contig size')
22 parser.add_option('--rfam', action="store_true", dest="rfam", help="Enable searching for ncRNAs")
23 parser.add_option('--centre', dest="centre", default="CRS4", help="Sequencing centre")
24 parser.add_option('--gff', dest="gff", help="This is the master annotation in GFF3 format, containing both sequences and annotations. It can be viewed directly in Artemis or IGV")
25 parser.add_option('--gbk', dest="gbk", help="This is a standard Genbank file derived from the master .gff. If the input to prokka was a multi-FASTA, then this will be a multi-Genbank, with one record for each sequence")
26 parser.add_option('--fna', dest="fna", help="Nucleotide FASTA file of the input contig sequences")
27 parser.add_option('--faa', dest="faa", help="Protein FASTA file of the translated CDS sequences")
28 parser.add_option('--ffn', dest="ffn", help="Nucleotide FASTA file of all the annotated sequences, not just CDS")
29 parser.add_option('--sqn', dest="sqn", help="An ASN1 format Sequin file for submission to Genbank. It needs to be edited to set the correct taxonomy, authors, related publication etc")
30 parser.add_option('--fsa', dest="fsa", help="Nucleotide FASTA file of the input contig sequences, used by tbl2asn to create the .sqn file. It is mostly the same as the .fna file, but with extra Sequin tags in the sequence description lines")
31 parser.add_option('--tbl', dest="tbl", help="Feature Table file, used by tbl2asn to create the .sqn file")
32 parser.add_option('--err', dest="err", help="Unacceptable annotations - the NCBI discrepancy report")
33 parser.add_option('--log', dest="log", help="Contains all the output that Prokka produced during its run")
34 (options, args) = parser.parse_args()
35 if len(args) > 0:
36 parser.error('Wrong number of arguments')
37
38 # Build command
39 cpus = "--cpus %d" % (options.cpus) if options.cpus is not None else ''
40 rfam = '--rfam' if options.rfam else ''
41 mincontig = "--mincontig %d" % options.mincontig if options.mincontig is not None else ''
42
43 cl = "prokka --force --outdir . --prefix prokka --kingdom %s %s --centre %s %s %s %s" % (options.kingdom, mincontig, options.centre, rfam, cpus, options.fasta)
44 print '\nProkka command to be executed: \n %s' % cl
45
46 # Run command
47 log = open(options.log, 'w') if options.log else sys.stdout
48 try:
49 subprocess.check_call(cl, stdout=log, stderr=subprocess.STDOUT, shell=True) # need to redirect stderr because prokka writes many logging info there
50 finally:
51 if log != sys.stdout:
52 log.close()
53
54 # Rename output files
55 suffix = ['gbk', 'fna', 'faa', 'ffn', 'sqn', 'fsa', 'tbl', 'err', 'gff']
56 for s in suffix:
57 shutil.move( 'prokka.' + s, getattr(options, s))
58
59 if __name__ == "__main__":
60 __main__()