|
96
|
1 #!/usr/bin/env python
|
|
|
2 import argparse
|
|
|
3 import os
|
|
|
4 import shutil
|
|
|
5 import subprocess
|
|
131
|
6
|
|
|
7 import utils
|
|
|
8
|
|
96
|
9
|
|
|
10 BUFF_SIZE = 1048576
|
|
|
11 OUTPUT_DIR = 'geneFamilyClassification_dir'
|
|
|
12
|
|
|
13 parser = argparse.ArgumentParser()
|
|
|
14 parser.add_argument('--input', dest='input', help="Input dataset")
|
|
|
15 parser.add_argument('--scaffold', dest='scaffold', default='mode', help='Orthogroups or gene families proteins scaffold')
|
|
|
16 parser.add_argument('--method', dest='method', help='Protein clustering method')
|
|
|
17 parser.add_argument('--classifier', dest='classifier', help='Protein classification method')
|
|
|
18 parser.add_argument('--config_dir', dest='config_dir', help='Directory containing default configuration files')
|
|
|
19 parser.add_argument('--num_threads', dest='num_threads', type=int, help='Number of threads to use for execution')
|
|
|
20 parser.add_argument('--super_orthogroups', dest='super_orthogroups', default=None, help='Super orthogroups clustering specification')
|
|
|
21 parser.add_argument('--single_copy_custom', dest='single_copy_custom', default=None, help='Custom single copy orthogroup configuration')
|
|
|
22 parser.add_argument('--single_copy_taxa', dest='single_copy_taxa', type=int, default=None, help='"Minimum single copy taxa required in orthogroup')
|
|
|
23 parser.add_argument('--taxa_present', dest='taxa_present', type=int, default=None, help='Minimum taxa required in single copy orthogroup')
|
|
|
24 parser.add_argument('--orthogroup_fasta', dest='orthogroup_fasta', default=None, help='Flag to create orthogroup sequences')
|
|
|
25 parser.add_argument('--coding_sequences', dest='coding_sequences', default=None, help='Flag to create orthogroup coding sequences')
|
|
|
26 parser.add_argument('--save_hmmscan_log', dest='save_hmmscan_log', default=None, help='Flag to save the hmmscan log')
|
|
|
27 parser.add_argument('--hmmscan_log', dest='hmmscan_log', default=None, help='hmmscan log file')
|
|
|
28 parser.add_argument('--output_ptortho', dest='output_ptortho', default=None, help='Output for orthogroups')
|
|
101
|
29 parser.add_argument('--output_ptortho_dir', dest='output_ptortho_dir', default=None, help='output_ptortho.files_path')
|
|
96
|
30 parser.add_argument('--output_ptorthocs', dest='output_ptorthocs', default=None, help='Output for orthogroups with corresponding coding sequences')
|
|
101
|
31 parser.add_argument('--output_ptorthocs_dir', dest='output_ptorthocs_dir', default=None, help='output_ptorthocs.files_path')
|
|
96
|
32 parser.add_argument('--output_ptsco', dest='output_ptsco', default=None, help='Output for single copy orthogroups')
|
|
101
|
33 parser.add_argument('--output_ptsco_dir', dest='output_ptsco_dir', default=None, help='output_ptsco.files_path')
|
|
96
|
34
|
|
|
35 args = parser.parse_args()
|
|
|
36
|
|
|
37
|
|
|
38 # Build the command line.
|
|
|
39 cmd = 'GeneFamilyClassifier'
|
|
|
40 cmd += ' --proteins %s' % args.input
|
|
|
41 cmd += ' --scaffold %s' % args.scaffold
|
|
|
42 cmd += ' --method %s' % args.method
|
|
|
43 cmd += ' --classifier %s' % args.classifier
|
|
|
44 cmd += ' --config_dir %s' % args.config_dir
|
|
|
45 cmd += ' --num_threads %d' % args.num_threads
|
|
|
46 if args.super_orthogroups is not None:
|
|
|
47 cmd += ' --super_orthogroups %s' % args.super_orthogroups
|
|
|
48 if args.single_copy_custom is not None:
|
|
|
49 cmd += ' --single_copy_custom %s' % args.single_copy_custom
|
|
|
50 if args.single_copy_taxa is not None:
|
|
|
51 cmd += ' --single_copy_taxa %d' % args.single_copy_taxa
|
|
|
52 if args.taxa_present is not None:
|
|
|
53 cmd += ' --taxa_present %d' % args.taxa_present
|
|
|
54 if args.orthogroup_fasta is None:
|
|
|
55 create_ortho_sequences = False
|
|
|
56 else:
|
|
|
57 create_ortho_sequences = True
|
|
|
58 cmd += ' --orthogroup_fasta'
|
|
|
59 if args.coding_sequences is None:
|
|
|
60 create_corresponding_coding_sequences = False
|
|
|
61 else:
|
|
|
62 create_corresponding_coding_sequences = True
|
|
|
63 cmd += ' --coding_sequences %s' % args.coding_sequences
|
|
|
64 # Run the command.
|
|
131
|
65 proc = subprocess.Popen(args=cmd, stderr=subprocess.PIPE, stdout=subprocess.PIPE, shell=True)
|
|
96
|
66 rc = proc.wait()
|
|
131
|
67 utils.check_execution_errors(rc, proc.stderr)
|
|
96
|
68 # Handle hmmscan.log output.
|
|
|
69 if args.classifier in ['hmmscan', 'both']:
|
|
|
70 src_hmmscan_log = os.path.join(OUTPUT_DIR, 'hmmscan.log')
|
|
|
71 if os.path.exists(src_hmmscan_log):
|
|
|
72 if args.save_hmmscan_log is None:
|
|
113
|
73 os.remove(src_hmmscan_log)
|
|
96
|
74 else:
|
|
|
75 shutil.move(src_hmmscan_log, args.hmmscan_log)
|
|
|
76 # Handle orthogroups outputs.
|
|
|
77 if create_ortho_sequences:
|
|
|
78 if create_corresponding_coding_sequences:
|
|
|
79 out_file = args.output_ptorthocs
|
|
101
|
80 orthogroups_fasta_dest_dir = args.output_ptorthocs_dir
|
|
109
|
81 title = 'Orthogroups and corresponding coding sequences files'
|
|
96
|
82 else:
|
|
|
83 out_file = args.output_ptortho
|
|
101
|
84 orthogroups_fasta_dest_dir = args.output_ptortho_dir
|
|
109
|
85 title = 'Orthogroups files'
|
|
96
|
86 orthogroups_fasta_src_dir = os.path.join(OUTPUT_DIR, 'orthogroups_fasta')
|
|
131
|
87 utils.move_directory_files(orthogroups_fasta_src_dir, orthogroups_fasta_dest_dir)
|
|
|
88 utils.write_html_output(out_file, title, orthogroups_fasta_dest_dir)
|
|
96
|
89 # Handle single copy orthogroup outputs.
|
|
|
90 if args.output_ptsco is not None:
|
|
|
91 single_copy_fasta_src_dir = os.path.join(OUTPUT_DIR, 'single_copy_fasta')
|
|
101
|
92 single_copy_fasta_dest_dir = args.output_ptsco_dir
|
|
109
|
93 title = 'Single copy orthogroups files'
|
|
131
|
94 utils.move_directory_files(single_copy_fasta_src_dir, single_copy_fasta_dest_dir)
|
|
|
95 utils.write_html_output(args.output_ptsco, title, single_copy_fasta_dest_dir)
|
