comparison tools/protein_analysis/tmhmm2.py @ 20:a19b3ded8f33 draft

v0.2.11 Job splitting fast-fail; RXLR tools supports HMMER2 from BioConda; Capture more version information; misc internal changes

19:f3ecd80850e2

Also tmhmm2 can fail without returning an error code, for example if run on a
64 bit machine with only the 32 bit binaries installed. This script will spot
when there is no output from tmhmm2, and raise an error.
"""
import sys
import os
import tempfile
from seq_analysis_utils import split_fasta, run_jobs, thread_count

FASTA_CHUNK = 500

if len(sys.argv) != 4:
    sys.exit("Require three arguments, number of threads (int), input protein FASTA file & output tabular file")

num_threads = thread_count(sys.argv[1], default=4)

        assert predhel.startswith("PredHel="), line
        predhel = predhel[8:]
        assert topology.startswith("Topology="), line
        topology = topology[9:]
        out_handle.write("%s\t%s\t%s\t%s\t%s\t%s\n"
                   % (identifier, length, exp_aa, first60, predhel, topology))
        count += 1
    return count

# Note that if the input FASTA file contains no sequences,
# split_fasta returns an empty list (i.e. zero temp files).
fasta_files = split_fasta(fasta_file, os.path.join(tmp_dir, "tmhmm"), FASTA_CHUNK)
temp_files = [f + ".out" for f in fasta_files]

    try:
        os.rmdir(tmp_dir)
    except Exception:
        pass

if len(jobs) > 1 and num_threads > 1:
    # A small "info" message for Galaxy to show the user.
    print "Using %i threads for %i tasks" % (min(num_threads, len(jobs)), len(jobs))
results = run_jobs(jobs, num_threads)
for fasta, temp, cmd in zip(fasta_files, temp_files, jobs):
    error_level = results[cmd]
    if error_level:
        try:

20:a19b3ded8f33

Also tmhmm2 can fail without returning an error code, for example if run on a
64 bit machine with only the 32 bit binaries installed. This script will spot
when there is no output from tmhmm2, and raise an error.
"""

from __future__ import print_function

import os
import sys
import tempfile

from seq_analysis_utils import run_jobs, split_fasta, thread_count

FASTA_CHUNK = 500

if "-v" in sys.argv or "--version" in sys.argv:
    sys.exit("TMHMM wrapper version 0.0.16")

if len(sys.argv) != 4:
    sys.exit("Require three arguments, number of threads (int), input protein FASTA file & output tabular file")

num_threads = thread_count(sys.argv[1], default=4)

        assert predhel.startswith("PredHel="), line
        predhel = predhel[8:]
        assert topology.startswith("Topology="), line
        topology = topology[9:]
        out_handle.write("%s\t%s\t%s\t%s\t%s\t%s\n"
                         % (identifier, length, exp_aa, first60, predhel, topology))
        count += 1
    return count


# Note that if the input FASTA file contains no sequences,
# split_fasta returns an empty list (i.e. zero temp files).
fasta_files = split_fasta(fasta_file, os.path.join(tmp_dir, "tmhmm"), FASTA_CHUNK)
temp_files = [f + ".out" for f in fasta_files]

    try:
        os.rmdir(tmp_dir)
    except Exception:
        pass


if len(jobs) > 1 and num_threads > 1:
    # A small "info" message for Galaxy to show the user.
    print("Using %i threads for %i tasks" % (min(num_threads, len(jobs)), len(jobs)))
results = run_jobs(jobs, num_threads)
for fasta, temp, cmd in zip(fasta_files, temp_files, jobs):
    error_level = results[cmd]
    if error_level:
        try: