bx-python / scripts / maf_filter_max_wc.py

#!/usr/bin/env python

"""
Filter maf blocks for presence of wildcard columns. Blocks must meet the 
criteria of having at least `min_good` columns, each of which has more than
`min_species` rows that are NOT wildcard bases ('*').

TODO: Allow specifying the character of the wildcard base.

usage: %prog min_good min_species < maf > maf
"""

from __future__ import division

import psyco_full

import sys

import sys
from bx.align import maf
from optparse import OptionParser

def main():

    min_good = int( sys.argv[1] )
    min_species = int( sys.argv[2] )

    maf_reader = maf.Reader( sys.stdin )
    maf_writer = maf.Writer( sys.stdout )

    for m in maf_reader:
        good = 0
        for col in m.column_iter():
            if col.count( '*' ) <= min_species:
                good += 1   
        if good >= min_good: 
            maf_writer.write( m )

if __name__ == "__main__": 
    main()
Tip: Filter by directory path e.g. /media app.js to search for public/media/app.js.
Tip: Use camelCasing e.g. ProjME to search for ProjectModifiedEvent.java.
Tip: Filter by extension type e.g. /repo .js to search for all .js files in the /repo directory.
Tip: Separate your search with spaces e.g. /ssh pom.xml to search for src/ssh/pom.xml.
Tip: Use ↑ and ↓ arrow keys to navigate and return to view the file.
Tip: You can also navigate files with Ctrl+j (next) and Ctrl+k (previous) and view the file with Ctrl+o.
Tip: You can also navigate files with Alt+j (next) and Alt+k (previous) and view the file with Alt+o.