Taxonomy fixer

taxonomy_fixer.py

#!/usr/bin/env python
"""Usage: python taxonomy_fixer.py [FILE]

Converts an ITS taxonomy file to eliminate taxa marked as unidentified,
swaps [kpcofg]__unidentified;s__Fungi to k__Fungi, and eliminates species
taxa that are simply s__[genus]_sp.

Writes to stdout.
"""
# Erik Clarke <ecl@mail.med.upenn.edu>

import sys

try:
    inf = open(sys.argv[1]) if len(sys.argv) > 1 else sys.stdin
except:
    print(__doc__)
    sys.exit(1)

for line in inf:
    if not line:
        continue
    else:
        line = line.strip('\n')
    otu, taxa = line.split('\t')
    taxa = taxa.split(';')
    sys.stdout.write(otu + '\t')
    for i, taxon in enumerate(taxa):
        if taxon == 'k__unidentified':
            sys.stdout.write('k__Fungi')
            break
        elif 'unidentified' in taxon or 'uncultured' in taxon:
            break
        elif i == 6 and taxon.endswith('_sp.'):
            break
        else:
            sys.stdout.write(';') if i > 0 else None
            sys.stdout.write(taxon)
    sys.stdout.write('\n')
        
inf.close()