Mercurial > repos > bgruening > bismark

annotate bismark_methylation_extractor.py @ 37:79df147da633 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 2d8f9bfd501f1cd82b5cf0429c1b02b3784392ab"
author bgruening
date Fri, 04 Oct 2019 11:33:01 -0400
parents a5faad9e4138
children b2d0e92f81c2
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
25
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
1 #!/usr/bin/env python
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
2
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
3 import argparse
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
4 import logging
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
5 import math
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
6 import os
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
7 import re
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
8 import shutil
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
9 import subprocess
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
10 import sys
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
11 import tempfile
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
12 import zipfile
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
13 from glob import glob
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
14
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
15
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
16 def stop_err(logger, msg):
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
17 logger.critical(msg)
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
18 sys.exit(1)
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
19
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
20
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
21 def log_subprocess_output(logger, pipe):
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
22 for line in iter(pipe.readline, b''):
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
23 logger.debug(line.decode().rstrip())
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
24
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
25
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
26 def zipper(dir, zip_file):
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
27 output_files_regex = re.compile('^(Non_)?C[pH][GH]_.*')
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
28 bedgraph_regex = re.compile('.*bedGraph.gz')
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
29 zip = zipfile.ZipFile(zip_file, 'w', compression=zipfile.ZIP_DEFLATED)
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
30 root_len = len(os.path.abspath(dir))
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
31 for root, dirs, files in os.walk(dir):
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
32 archive_root = os.path.abspath(root)[root_len:]
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
33 for f in files:
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
34 if re.search(output_files_regex, f) or re.search(bedgraph_regex, f):
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
35 fullpath = os.path.join(root, f)
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
36 archive_name = os.path.join(archive_root, f)
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
37 zip.write(fullpath, archive_name, zipfile.ZIP_DEFLATED)
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
38 zip.close()
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
39 return zip_file
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
40
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
41
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
42 def build_genome_dir(genome_file):
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
43 tmp_genome_dir = tempfile.mkdtemp(prefix='tmp')
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
44 genome_path = os.path.join(tmp_genome_dir, '.'.join(os.path.split(genome_file)[1].split('.')[:-1]))
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
45 try:
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
46 # Create a hard link pointing to genome_file named 'genome_path'.fa.
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
47 os.symlink(genome_file, genome_path + '.fa')
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
48 except Exception as e:
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
49 if os.path.exists(tmp_genome_dir):
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
50 shutil.rmtree(tmp_genome_dir)
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
51 stop_err('Error in linking the reference database!\n%s' % e)
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
52 return tmp_genome_dir
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
53
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
54
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
55 def __main__():
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
56 # Parse Command Line
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
57 parser = argparse.ArgumentParser(description='Wrapper for the bismark methylation caller.')
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
58
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
59 # input options
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
60 parser.add_argument('--infile', help='Input file in SAM or BAM format.')
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
61 parser.add_argument('--single-end', dest='single_end', action="store_true")
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
62 parser.add_argument('--paired-end', dest='paired_end', action="store_true")
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
63
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
64 parser.add_argument('--multicore', dest='multicore', type=int, default=1)
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
65 parser.add_argument('--splitting_report', dest='splitting_report')
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
66 parser.add_argument('--mbias_report', dest='mbias_report')
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
67 parser.add_argument('--cytosine_report', dest="cytosine_report")
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
68 parser.add_argument('--genome_file', dest="genome_file")
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
69 parser.add_argument('--cx_context', action="store_true")
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
70
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
71 parser.add_argument('--comprehensive', action="store_true")
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
72 parser.add_argument('--merge-non-cpg', dest='merge_non_cpg', action="store_true")
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
73 parser.add_argument('--no-overlap', dest='no_overlap', action="store_true")
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
74 parser.add_argument('--compress', dest='compress')
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
75 parser.add_argument('--ignore', dest='ignore', type=int)
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
76 parser.add_argument('--ignore_r2', dest='ignore_r2', type=int)
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
77 parser.add_argument('--ignore_3prime', dest='ignore_3prime', type=int)
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
78 parser.add_argument('--ignore_3prime_r2', dest='ignore_3prime_r2', type=int)
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
79 parser.add_argument('--log_report', dest='log_report', metavar='log_filename', type=str)
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
80 args = parser.parse_args()
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
81
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
82 logger = logging.getLogger('bismark_methylation_extractor_wrapper')
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
83 logger.setLevel(logging.DEBUG)
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
84 ch = logging.StreamHandler(sys.stdout)
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
85 if args.log_report:
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
86 ch.setLevel(logging.WARNING)
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
87 handler = logging.FileHandler(args.log_report)
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
88 handler.setLevel(logging.DEBUG)
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
89 logger.addHandler(handler)
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
90 else:
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
91 ch.setLevel(logging.DEBUG)
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
92 logger.addHandler(ch)
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
93
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
94 # Build methylation extractor command
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
95 output_dir = tempfile.mkdtemp()
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
96 cmd = ['bismark_methylation_extractor', '--no_header', '-o', output_dir]
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
97 # Set up all options
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
98 if args.multicore > 3:
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
99 # divide multicore by 3 here since bismark will spawn ~3 jobs.
37
79df147da633 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 2d8f9bfd501f1cd82b5cf0429c1b02b3784392ab"
bgruening
parents: 25
diff changeset
100 cmd.extend(['--multicore', str(int(math.floor(args.multicore / 3)))])
25
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
101 if args.single_end:
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
102 cmd.append('--single-end')
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
103 else:
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
104 cmd.append('--paired-end')
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
105 if args.no_overlap:
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
106 cmd.append('--no_overlap')
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
107 if args.ignore:
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
108 cmd.extend(['--ignore', str(args.ignore)])
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
109 if args.ignore_r2:
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
110 cmd.extend(['--ignore_r2', str(args.ignore_r2)])
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
111 if args.ignore_3prime:
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
112 cmd.extend(['--ignore_3prime', str(args.ignore_3prime)])
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
113 if args.ignore_3prime_r2:
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
114 cmd.extend(['--ignore_3prime_r2', str(args.ignore_3prime_r2)])
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
115 if args.comprehensive:
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
116 cmd.append('--comprehensive')
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
117 if args.merge_non_cpg:
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
118 cmd.append('--merge_non_CpG')
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
119 if args.splitting_report:
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
120 cmd.append('--report')
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
121 tmp_genome_dir = None
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
122 if args.cytosine_report:
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
123 tmp_genome_dir = build_genome_dir(args.genome_file)
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
124 if args.cx_context:
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
125 cmd.extend(
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
126 ['--bedGraph', '--CX_context', '--cytosine_report', '--CX_context', '--genome_folder', tmp_genome_dir])
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
127 else:
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
128 cmd.extend(['--bedGraph', '--cytosine_report', '--genome_folder', tmp_genome_dir])
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
129
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
130 cmd.append(args.infile)
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
131
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
132 # Run
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
133 logger.info("Methylation extractor run with: '%s'", " ".join(cmd))
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
134 prev_dir = os.getcwd()
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
135 os.chdir(output_dir) # needed due to a bug in bismark where the coverage file cannot be found
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
136 process = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
137 with process.stdout:
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
138 log_subprocess_output(logger, process.stdout)
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
139 exitcode = process.wait()
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
140 if exitcode != 0:
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
141 stop_err(logger, "Bismark methylation extractor error (also check the log file if any)!\n%s" % process.stderr)
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
142 logger.info("Finished methylation extractor.")
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
143 # collect and copy output files
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
144 logger.debug("Zip output files to '%s'.", args.compress)
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
145 os.chdir(prev_dir)
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
146 zipper(output_dir, args.compress)
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
147
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
148 # cytosine report
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
149 if args.cytosine_report:
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
150 logger.debug("Collecting cytosine report.")
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
151 if args.cx_context:
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
152 shutil.move(glob(os.path.join(output_dir, '*CX_report.txt'))[0], args.cytosine_report)
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
153 else:
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
154 shutil.move(glob(os.path.join(output_dir, '*CpG_report.txt'))[0], args.cytosine_report)
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
155 # splitting report
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
156 if args.splitting_report:
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
157 logger.debug("Collecting splitting report.")
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
158 shutil.move(glob(os.path.join(output_dir, '*_splitting_report.txt'))[0], args.splitting_report)
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
159 if args.mbias_report:
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
160 logger.debug("Collecting M-Bias file.")
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
161 shutil.move(glob(os.path.join(output_dir, '*M-bias.txt'))[0], args.mbias_report)
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
162
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
163 # Clean up temp dirs
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
164 logger.debug("Cleanup temp dirs.")
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
165 if os.path.exists(output_dir):
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
166 shutil.rmtree(output_dir)
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
167 if tmp_genome_dir and os.path.exists(tmp_genome_dir):
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
168 shutil.rmtree(tmp_genome_dir)
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
169 logger.info("Done.")
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
170
a5faad9e4138 planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/bismark commit 51299fa62f0566a4a897b1c149db564631282fff
bgruening
parents:
diff changeset
171 if __name__ == "__main__": __main__()