Mercurial > repos > jowong > prince_galaxy

comparison prince_postprocess.py @ 8:63f3743c2ae4 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload
author jowong
date Tue, 13 Nov 2018 12:19:53 -0500
parents 82569b47df8d
children 5b816b501285
comparison
equal deleted inserted replaced
7:0032da940600 8:63f3743c2ae4
6 parser = ap.ArgumentParser(prog='prince_postprocess', conflict_handler='resolve', 6 parser = ap.ArgumentParser(prog='prince_postprocess', conflict_handler='resolve',
7 description="Postprocess galaxy PRINCE output") 7 description="Postprocess galaxy PRINCE output")
8 8
9 input = parser.add_argument_group('Input', '') 9 input = parser.add_argument_group('Input', '')
10 input.add_argument('-i', '--input', nargs=1, required=True, help="PRINCE OUTPUT") 10 input.add_argument('-i', '--input', nargs=1, required=True, help="PRINCE OUTPUT")
11 input.add_argument('-s', '--sample', nargs='*', required=True, help="Sample names") 11 input.add_argument('-s', '--sample', nargs='+', required=True, help="Sample names")
12 12 input.add_argument('-f', '--file', nargs='+', required=True, help="File of forward reads in galaxy convention")
13 if len(sys.argv) == 0: 13 if len(sys.argv) == 0:
14 parser.print_usage() 14 parser.print_usage()
15 sys.exit(1) 15 sys.exit(1)
16 16
17 args = parser.parse_args() 17 args = parser.parse_args()
18 18
19 #print(args.input) 19 #print(args.input)
20 #sample_name = re.sub('(_1.fastq(.gz)*|_2.fastq(.gz)*|.fastq(.gz)*)', '', args.label.rstrip().lstrip()) 20 #sample_name = re.sub('(_1.fastq(.gz)*|_2.fastq(.gz)*|.fastq(.gz)*)', '', args.label.rstrip().lstrip())
21 sample_dict={}
22 path_index = 0
23 for path in args.file:
24 with open(path) as f:
25 for line in f:
26 sample_dict[re.sub(".*/","",line)] = sample[path_index]
27 path_index += 1
28
29
30
31
32
33
21 34
22 with open(args.input[0]) as prince_output: 35 with open(args.input[0]) as prince_output:
23 with open('prince_postprocess_output.txt', 'w') as output: 36 with open('prince_postprocess_output.txt', 'w') as output:
24 x = 1 37 x = 1
25 index = 0 38 index = 0
26 for line in prince_output: 39 for line in prince_output:
27 if x%2 == 0: 40 if x%2 == 0:
28 sample = re.sub('(_1.fastq(.gz)*|_2.fastq(.gz)*|.fastq(.gz)*)', '', args.sample[index]) 41 entries =line.rstrip().split(',')
29 output.write(re.sub('.*.dat', sample, line)) 42 sample = re.sub('(_1.fastq(.gz)*|_2.fastq(.gz)*|.fastq(.gz)*)', '', sample_dict[entries[0]])
43 output.write(re.sub(entries[0], sample, line))
30 index += 1 44 index += 1
31 else: 45 else:
32 output.write(line) 46 output.write(line)
33 x += 1 47 x += 1
34 #output.write("\n") 48 #output.write("\n")