Mercurial > repos > iuc > concoct_extract_fasta_bins

comparison merge_cut_up_clustering.py @ 1:a04028a8181d 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/concoct commit 40a09cbfd6052f7b0295946621db1bdf58228b09"
author iuc
date Sun, 13 Mar 2022 08:44:08 +0000
parents
children
comparison
equal deleted inserted replaced
0:1bc8fd1b3ed0 1:a04028a8181d
1 #!/usr/bin/env python
2
3 import argparse
4 import re
5 import sys
6 from collections import Counter
7 from collections import defaultdict
8
9
10 CONTIG_PART_EXPR = re.compile(r'(.*)\.concoct_part_([0-9]*)')
11
12
13 def original_contig_name_special(contig_id):
14 try:
15 original_id, part_index = CONTIG_PART_EXPR.match(contig_id).group(1, 2)
16 return original_id, part_index
17 except AttributeError:
18 # No matches for concoct_part regex.
19 return contig_id, 0
20
21
22 parser = argparse.ArgumentParser()
23 parser.add_argument("--input", action="store", dest="input", help="Tabular file with cut up clusters")
24 parser.add_argument("--output", action="store", dest="output", help="Output file with merged clusters")
25
26 args = parser.parse_args()
27
28 # Get cut up clusters
29 all_seqs = {}
30 all_originals = defaultdict(dict)
31 with open(args.input, 'r') as ifh:
32 for i, line in enumerate(ifh):
33 if i == 0:
34 if 'contig_id' not in line:
35 sys.stderr.write("ERROR nvalid clustering file, 'contig_id' is not found in the header.")
36 sys.exit(-1)
37 # Skip header.
38 continue
39 line = line.rstrip('\r\n')
40 contig_id, cluster_id = line.split('\t')
41 original_contig_name, part_id = original_contig_name_special(contig_id)
42 all_originals[original_contig_name][part_id] = cluster_id
43
44 # Merge cut up clusters.
45 with open(args.output, 'w') as ofh:
46 ofh.write("contig_id\tcluster_id\n")
47 for original_contig_id, part_ids_d in all_originals.items():
48 if len(part_ids_d) > 1:
49 c = Counter(part_ids_d.values())
50 cluster_id = c.most_common(1)[0][0]
51 c_string = [(a, b) for a, b in c.items()]
52 # Here if len(c.values()) > 1,
53 # then no cluster for contig.
54 else:
55 cluster_id = list(part_ids_d.values())[0]
56 ofh.write(f"{original_contig_id}\t{cluster_id}\n")