comparison tools/protein_analysis/wolf_psort.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

Additionally in order to take full advantage of multiple cores, by subdividing
the input FASTA file multiple copies of WoLF PSORT are run in parallel. I would
normally use Python's multiprocessing library in this situation but it requires
at least Python 2.6 and at the time of writing Galaxy still supports Python 2.4.
"""
import sys
import os
from seq_analysis_utils import split_fasta, run_jobs, thread_count

FASTA_CHUNK = 500
exe = "runWolfPsortSummary"

"""

For more details on this workaround, see:
https://lists.galaxyproject.org/pipermail/galaxy-dev/2015-December/023386.html
"""

if len(sys.argv) != 5:
    sys.exit("Require four arguments, organism, threads, input protein FASTA file & output tabular file")

organism = sys.argv[1]
if organism not in ["animal", "plant", "fungi"]:

        for rank, comp_data in enumerate(data.split(",")):
            comp, score = comp_data.split()
            out_handle.write("%s\t%s\t%s\t%i\n"
                             % (name, comp, score, rank + 1))

fasta_files = split_fasta(fasta_file, tabular_file, n=FASTA_CHUNK)
temp_files = [f + ".out" for f in fasta_files]
assert len(fasta_files) == len(temp_files)
jobs = ["%s %s < %s > %s" % (exe, organism, fasta, temp)
        for (fasta, temp) in zip(fasta_files, temp_files)]

def clean_up(file_list):
    for f in file_list:
        if os.path.isfile(f):
            os.remove(f)

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)
assert len(fasta_files) == len(temp_files) == len(jobs)
for fasta, temp, cmd in zip(fasta_files, temp_files, jobs):
    error_level = results[cmd]
    try:

20:a19b3ded8f33

Additionally in order to take full advantage of multiple cores, by subdividing
the input FASTA file multiple copies of WoLF PSORT are run in parallel. I would
normally use Python's multiprocessing library in this situation but it requires
at least Python 2.6 and at the time of writing Galaxy still supports Python 2.4.
"""

from __future__ import print_function

import os
import sys

from seq_analysis_utils import run_jobs, split_fasta, thread_count

FASTA_CHUNK = 500
exe = "runWolfPsortSummary"

"""

For more details on this workaround, see:
https://lists.galaxyproject.org/pipermail/galaxy-dev/2015-December/023386.html
"""

if "-v" in sys.argv or "--version" in sys.argv:
    sys.exit("WoLF-PSORT wrapper version 0.0.11")

if len(sys.argv) != 5:
    sys.exit("Require four arguments, organism, threads, input protein FASTA file & output tabular file")

organism = sys.argv[1]
if organism not in ["animal", "plant", "fungi"]:

        for rank, comp_data in enumerate(data.split(",")):
            comp, score = comp_data.split()
            out_handle.write("%s\t%s\t%s\t%i\n"
                             % (name, comp, score, rank + 1))


fasta_files = split_fasta(fasta_file, tabular_file, n=FASTA_CHUNK)
temp_files = [f + ".out" for f in fasta_files]
assert len(fasta_files) == len(temp_files)
jobs = ["%s %s < %s > %s" % (exe, organism, fasta, temp)
        for (fasta, temp) in zip(fasta_files, temp_files)]

def clean_up(file_list):
    for f in file_list:
        if os.path.isfile(f):
            os.remove(f)


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)
assert len(fasta_files) == len(temp_files) == len(jobs)
for fasta, temp, cmd in zip(fasta_files, temp_files, jobs):
    error_level = results[cmd]
    try: