comparison extract_fasta_bins.py @ 0:06c0eb033025 draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/concoct commit 49b42f61ff37c3c33dd15c195e5705e1db066c37"
author iuc
date Fri, 18 Feb 2022 14:18:11 +0000
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:06c0eb033025
1 #!/usr/bin/env python
2
3 import argparse
4 import gzip
5 import os
6 import sys
7 from collections import defaultdict
8 from functools import partial
9
10 import pandas as pd
11 from Bio import SeqIO
12
13 parser = argparse.ArgumentParser(description=__doc__)
14
15 parser.add_argument('--gzipped', action='store_true', dest='gzipped', help='Input files are gzipped')
16 parser.add_argument("--input_fasta", action="store", dest="input_fasta", help="Input Fasta file")
17 parser.add_argument("--input_cluster", action="store", dest="input_cluster", help="Concoct output cluster file")
18 parser.add_argument("--output_path", help="Output directory")
19
20 args = parser.parse_args()
21
22 all_seqs = {}
23 if args.gzipped:
24 _open = partial(gzip.open, mode='rt')
25 else:
26 _open = open
27
28 with _open(args.input_fasta) as fh:
29 for seq in SeqIO.parse(fh, "fasta"):
30 all_seqs[seq.id] = seq
31
32 # Make sure we're reading the file as tabular!
33 df = pd.read_csv(args.input_cluster, sep='\t')
34 try:
35 assert df.columns[0] == 'contig_id'
36 assert df.columns[1] == 'cluster_id'
37 except AssertionError:
38 sys.stderr.write("ERROR! Header line was not 'contig_id, cluster_id', please adjust your input file. Exiting!\n")
39 sys.exit(-1)
40
41 cluster_to_contigs = defaultdict(list)
42 for i, row in df.iterrows():
43 cluster_to_contigs[row['cluster_id']].append(row['contig_id'])
44
45 for cluster_id, contig_ids in cluster_to_contigs.items():
46 output_file = os.path.join(args.output_path, "{0}.fa".format(cluster_id))
47 seqs = [all_seqs[contig_id] for contig_id in contig_ids]
48 with open(output_file, 'w') as ofh:
49 SeqIO.write(seqs, ofh, 'fasta')