annotate cluster_table2krona_format.py @ 17:d14b68e9fd1d draft

Uploaded - new tools added

#!/usr/bin/env python
import sys
import re
from collections import defaultdict
import argparse

parser = argparse.ArgumentParser()
parser.add_argument("-i" ,"--input", type=argparse.FileType('r'), help="path to file CLUSTER_table.csv")
parser.add_argument("-o" ,"--output", type=argparse.FileType('w'), help="output file name")
parser.add_argument("-m", "--use_manual", action='store_true', default=False)

args = parser.parse_args()

column = 6 if args.use_manual else 4


header = False
clust_info = {}
counts = defaultdict(lambda: 0)
top_clusters = 0
with open(args.input.name, 'r') as f:
    for l in f:
        parts = l.split()
        if re.match('.*Cluster.+Supercluster.+Size.+Size_adjusted.+Automatic_annotation.+TAREAN_annotation.+Final_annotation', l):
            print("header detected")
            header = True
            continue
        if header:
            classification = "Top_clusters\t" + "\t".join(parts[column].split("/")[1:]).replace('"','')
            counts[classification] += int(parts[3])
            top_clusters += int(parts[3])

        elif len(parts) >= 2:
            clust_info[parts[0].replace('"', '')] = int(parts[1])

counts['Singlets'] = clust_info['Number_of_singlets']
counts['Small_cluster'] = int(clust_info['Number_of_reads_in_clusters']) - top_clusters

with open(args.output.name, 'w') as fout:
    for cls_line, nreads in counts.items():
        fout.write(str(nreads) +"\t" + cls_line + "\n")