Mercurial > repos > petr-novak > re_utils

comparison cluster_table2krona_format.py @ 17:d14b68e9fd1d draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded - new tools added
author petr-novak
date Wed, 28 Apr 2021 08:37:20 +0000
parents
children 2f1b5d5c5dd5
comparison
equal deleted inserted replaced
16:5376e1c9adec 17:d14b68e9fd1d
1 #!/usr/bin/env python
2 import sys
3 import re
4 from collections import defaultdict
5 import argparse
6
7 parser = argparse.ArgumentParser()
8 parser.add_argument("-i" ,"--input", type=argparse.FileType('r'), help="path to file CLUSTER_table.csv")
9 parser.add_argument("-o" ,"--output", type=argparse.FileType('w'), help="output file name")
10 parser.add_argument("-m", "--use_manual", action='store_true', default=False)
11
12 args = parser.parse_args()
13
14 column = 6 if args.use_manual else 4
15
16
17 header = False
18 clust_info = {}
19 counts = defaultdict(lambda: 0)
20 top_clusters = 0
21 with open(args.input.name, 'r') as f:
22 for l in f:
23 parts = l.split()
24 if re.match('.*Cluster.+Supercluster.+Size.+Size_adjusted.+Automatic_annotation.+TAREAN_annotation.+Final_annotation', l):
25 print("header detected")
26 header = True
27 continue
28 if header:
29 classification = "Top_clusters\t" + "\t".join(parts[column].split("/")[1:]).replace('"','')
30 counts[classification] += int(parts[3])
31 top_clusters += int(parts[3])
32
33 elif len(parts) >= 2:
34 clust_info[parts[0].replace('"', '')] = int(parts[1])
35
36 counts['Singlets'] = clust_info['Number_of_singlets']
37 counts['Small_cluster'] = int(clust_info['Number_of_reads_in_clusters']) - top_clusters
38
39 with open(args.output.name, 'w') as fout:
40 for cls_line, nreads in counts.items():
41 fout.write(str(nreads) +"\t" + cls_line + "\n")
42
43
44