Mercurial > repos > iuc > cwpair2

comparison cwpair2.py @ 0:8600bfe7ed52 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/cwpair2 commit e96df94dba60050fa28aaf55b5bb095717a5f260
author iuc
date Tue, 22 Dec 2015 17:03:46 -0500
parents
children d843468aeb8f
comparison
equal deleted inserted replaced
-1:000000000000 0:8600bfe7ed52
1 """
2 cwpair2.py
3
4 Takes a list of called peaks on both strands and produces a list of matched pairs and a list
5 of unmatched orphans using a specified method for finding matched pairs. Methods for finding
6 matched pairs are mode, closest, largest or all, where the analysis is run for each method
7
8 Input: list of one or more gff format files
9
10 Output: files produced for each input/mode combination:
11 MP (matched_pair), D (details), O (orphans), P (frequency preview plot), F (frequency final plot),
12 C (statistics graph), statistics.tabular
13 """
14
15 import argparse
16 import csv
17 import cwpair2_util
18
19 if __name__ == '__main__':
20 parser = argparse.ArgumentParser()
21 parser.add_argument('--input', dest='inputs', action='append', nargs=2, help="Input datasets")
22 parser.add_argument('--method', dest='method', default='mode', help='Method of finding match.')
23 parser.add_argument('--up_distance', dest='up_distance', type=int, default=50, help='Distance upstream from a pair.')
24 parser.add_argument('--down_distance', dest='down_distance', type=int, default=100, help='Distance downstream of a pair.')
25 parser.add_argument('--binsize', dest='binsize', type=int, default=1, help='Width of bins for plots and mode.')
26 parser.add_argument('--threshold_format', dest='threshold_format', help='Percentage to filter the 95th percentile.')
27 parser.add_argument('--relative_threshold', dest='relative_threshold', type=float, default=0.0, help='Percentage to filter the 95th percentile.')
28 parser.add_argument('--absolute_threshold', dest='absolute_threshold', type=float, default=0.0, help='Absolute value to filter.')
29 parser.add_argument('--output_files', dest='output_files', default='matched_pair', help='Restrict output dataset collections.')
30 parser.add_argument('--statistics_output', dest='statistics_output', help='Statistics output file.')
31 args = parser.parse_args()
32
33 cwpair2_util.create_directories()
34
35 statistics = []
36 if args.absolute_threshold > 0:
37 threshold = args.absolute_threshold
38 elif args.relative_threshold > 0:
39 threshold = args.relative_threshold / 100.0
40 else:
41 threshold = 0
42 for (dataset_path, hid) in args.inputs:
43 stats = cwpair2_util.process_file(dataset_path,
44 hid,
45 args.method,
46 threshold,
47 args.up_distance,
48 args.down_distance,
49 args.binsize,
50 args.output_files)
51 statistics.extend(stats)
52 # Accumulate statistics.
53 by_file = {}
54 for stats in statistics:
55 # Skip "None" statistics from failed files
56 if not stats:
57 continue
58 path = stats['stats_path']
59 if path not in by_file:
60 by_file[path] = []
61 by_file[path].append(stats)
62 # Write tabular statistics file.
63 keys = ['fname', 'final_mode', 'preview_mode', 'perc95', 'paired', 'orphans']
64 statistics_out = csv.writer(open(args.statistics_output, 'wt'), delimiter='\t')
65 statistics_out.writerow(keys)
66 for file_path, statistics in by_file.items():
67 for stats in statistics:
68 statistics_out.writerow([stats[key] for key in keys])