Mercurial > repos > greg > gene_family_aligner

comparison gene_family_aligner.py @ 7:529f4635ddb4 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author greg
date Mon, 10 Apr 2017 09:37:45 -0400
parents
children 43341e97bb08
comparison
equal deleted inserted replaced
6:badd2d0f1689 7:529f4635ddb4
1 #!/usr/bin/env python
2 import argparse
3 import os
4 import subprocess
5
6 import utils
7
8 OUTPUT_DIR = 'geneFamilyAlignments_dir'
9
10 parser = argparse.ArgumentParser()
11 parser.add_argument('--alignment_method', dest='alignment_method', help='Multiple sequence alignments method')
12 parser.add_argument('--automated_trimming', dest='automated_trimming', default=None, help="Trims alignments using trimAl's ML heuristic trimming approach")
13 parser.add_argument('--codon_alignments', dest='codon_alignments', default=None, help="Flag for constructing orthogroup multiple codon alignments")
14 parser.add_argument('--gap_trimming', dest='gap_trimming', default=None, type=float, help='Remove sites in alignments with gaps of')
15 parser.add_argument('--iterative_realignment', dest='iterative_realignment', type=int, default=None, help='"Maximum number of iterations')
16 parser.add_argument('--method', dest='method', help='Protein clustering method')
17 parser.add_argument('--num_threads', dest='num_threads', type=int, help='Number of threads to use for execution')
18 parser.add_argument('--orthogroup_faa', dest='orthogroup_faa', help="Directory of input fasta datasets")
19 parser.add_argument('--output', dest='output', help="Output dataset")
20 parser.add_argument('--output_dir', dest='output_dir', help="Output dataset file_path directory")
21 parser.add_argument('--pasta_iter_limit', dest='pasta_iter_limit', type=int, default=None, help='"Maximum number of iteration that the PASTA algorithm will execute')
22 parser.add_argument('--pasta_script_path', dest='pasta_script_path', default=None, help='Path to script for executing pasta')
23 parser.add_argument('--remove_sequences', dest='remove_sequences', default=None, type=float, help='Remove sequences with gaps of')
24 parser.add_argument('--scaffold', dest='scaffold', help='Orthogroups or gene families proteins scaffold')
25
26 args = parser.parse_args()
27
28 # Build the command line.
29 cmd = 'GeneFamilyAligner'
30 cmd += ' --orthogroup_faa %s' % args.orthogroup_faa
31 cmd += ' --scaffold %s' % args.scaffold
32 cmd += ' --method %s' % args.method
33 cmd += ' --alignment_method %s' % args.alignment_method
34 if args.alignment_method == 'pasta':
35 if args.pasta_script_path is not None:
36 cmd += ' --pasta_script_path %s' % args.pasta_script_path
37 if args.pasta_iter_limit is not None:
38 cmd += ' --pasta_iter_limit %d' % args.pasta_iter_limit
39 cmd += ' --num_threads %d' % args.num_threads
40 if args.codon_alignments is not None:
41 cmd += ' --codon_alignments'
42 if args.automated_trimming is not None:
43 cmd += ' --automated_trimming'
44 if args.gap_trimming is not None:
45 cmd += ' --gap_trimming %4f' % args.gap_trimming
46 if args.remove_sequences is not None:
47 cmd += ' --remove_sequences %4f' % args.remove_sequences
48 if args.iterative_realignment is not None:
49 cmd += ' --iterative_realignment %d' % args.iterative_realignment
50 # Run the command.
51 proc = subprocess.Popen(args=cmd, stderr=subprocess.PIPE, stdout=subprocess.PIPE, shell=True)
52 rc = proc.wait()
53 utils.check_execution_errors(rc, proc.stderr)
54 if args.codon_alignments is None:
55 src_output_dir = OUTPUT_DIR
56 else:
57 src_output_dir = os.path.join(OUTPUT_DIR, 'orthogroups_aln')
58 utils.move_directory_files(src_output_dir, args.output_dir)
59 utils.write_html_output(args.output, 'Aligned gene family sequences', args.output_dir)