Runs RAxML in parallel on a bunch of sequences

raxml_runner.py

#!/usr/bin/env python

import argparse
import os.path
import os
import errno
import multiprocessing
import functools
import subprocess
import pdb

import dendropy

def mkdir_p(path):
    """Makes a directory if it doesn't exist, and does nothing if it does."""
    try:
        os.makedirs(path)
    except OSError as exc:
        if exc.errno == errno.EEXIST and os.path.isdir(path):
            pass
        else: raise

def get_args():
    parser = argparse.ArgumentParser(description="run raxml")

    parser.add_argument("align", nargs="+", help="alignments in phylip format")
    parser.add_argument("--prefix", help="directory prefix for output")

    return parser.parse_args()


def run(filename, outdir):
    cmd = "raxmlHPC-PTHREADS-SSE3 -m GTRCAT -n best -s {0} -N 10 -w {1}".format(filename, outdir)
    process = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
    stdout, stderr = process.communicate()


def main():
    args = get_args()
    if args.prefix:
        mkdir_p(args.prefix)
    pool = multiprocessing.Pool()
    pool.map(run, args.align)

if __name__ == "__main__":
    main()