31 lines
1.2 KiB
Python
31 lines
1.2 KiB
Python
|
#!/usr/bin/env python3
|
||
|
|
import sys
|
||
|
|
from collections import defaultdict
|
||
|
|
if len(sys.argv) != 5:
|
||
|
|
sys.exit(f"python3 {sys.argv[0]} <genome.len> <mcscanx.gff> <tandem.pair> <genelist> > out.mct")
|
||
|
|
len_file, gff_file, tandem_file, ids_file = sys.argv[1:]
|
||
|
|
lengths = {}
|
||
|
|
with open(len_file, encoding='utf-8', errors='replace') as fh:
|
||
|
|
for line in fh:
|
||
|
|
f = line.split()
|
||
|
|
if len(f) >= 2: lengths[f[0]] = float(f[1])
|
||
|
|
ids = {}
|
||
|
|
with open(ids_file, encoding='utf-8', errors='replace') as fh:
|
||
|
|
for line in fh:
|
||
|
|
f = line.split()
|
||
|
|
if f: ids[f[0]] = 1
|
||
|
|
bed = defaultdict(dict)
|
||
|
|
with open(gff_file, encoding='utf-8', errors='replace') as fh:
|
||
|
|
for line in fh:
|
||
|
|
f = line.split()
|
||
|
|
if len(f) >= 4 and f[1] in ids: bed[f[0]][int(f[2])] = f
|
||
|
|
with open(tandem_file, encoding='utf-8', errors='replace') as fh:
|
||
|
|
for line in fh:
|
||
|
|
for gene in line.rstrip('\n').split(','):
|
||
|
|
if gene in ids: ids[gene] = 'tandem'
|
||
|
|
for chrom in sorted(bed):
|
||
|
|
print(f"chrom {chrom} S=0 E={lengths[chrom]/1000000}")
|
||
|
|
for pos in sorted(bed[chrom]):
|
||
|
|
rec = bed[chrom][pos]; gid = rec[1]; mid = (int(rec[3]) + pos) / 2 / 1000000
|
||
|
|
print(f"{gid} {mid} {'C2' if ids.get(gid) == 'tandem' else 'C4'}")
|