def parse_args():
# setup the parser
add_subparsers()
parser = base.get_parser()
subpars = base.get_subparser()
subpars.required = True
args = parser.parse_args()
# parse directory file list
# (requires input_directory_parser to be included)
try:
args.find_files(args)
except AttributeError:
pass
# protect file names
protect = ['summary', 'root_dir', 'data_dir']
for p in protect:
try:
setattr(args, p, path.protect(getattr(args, p)))
except TypeError:
pass # arg might not be set (is None)
return args
def test_write_script_sets_pbs_file_directory(self):
bp = BasePipe(job_name='foo')
bp.write_script(directory='~')
self.assertEqual(
bp.pbs_file, os.path.join(
path.protect('~'), 'foo_{}.pbs'.format(bp.timestamp)
)
)
def _create_pbs_file_name(self, dir_str):
try:
self.pbs_file = os.path.join(
path.protect(dir_str),
'_'.join([self.job_name, self.timestamp]) + '.pbs'
)
except (TypeError, AssertionError):
raise AssertionError('Pipe attribute "job_name" is undefined')
return
def _get_files_from_summary(self, fh, data_dir=None):
'''Reads a summary file and returns a list of names and files
Expected format:
<name> <file> [<file> ...]
The first two columns should be the name of the sample
and the file. Paired-end should be listed on the same line.
'''
rows = [line.rstrip().split() for line in fh]
names = [cols[0] for cols in rows]
if not data_dir:
data_dir = fh.name
try:
r1 = [path.protect(cols[1]) for cols in rows]
r2 = [path.protect(cols[2]) for cols in rows]
# HACK
r1 = [os.path.join(os.path.dirname(data_dir), r) for r in r1]
r2 = [os.path.join(os.path.dirname(data_dir), r) for r in r2]
except IndexError:
r1 = [path.protect(cols[1]) for cols in rows]
# HACK
r1 = [os.path.join(os.path.dirname(data_dir), r) for r in r1]
# check for valid paired end in third column
# try:
# r2_0 = os.path.join(os.path.dirname(fh.name), r2[0])
# if not os.path.isfile(r2[0]) and not os.path.isfile(r2_0):
# raise IndexError()
# except IndexError:
# pass
try:
return list(zip(names, r1, r2))
except UnboundLocalError:
return list(zip(names, r1))
def main():
global ROOT_DIR
args = parse_args()
summary = read_summary(args)
force = args.force
if args.root_dir:
ROOT_DIR = path.protect(args.root_dir)
genome = args.genome
project_name = args.project if args.project else 'new_project'
project_dir = os.path.join(ROOT_DIR, project_name, 'samples')
run_pipe(summary, genome, project_dir, force=force)
def read_summary(args):
'''Reads a summary file and returns a list of names and files
Expected format:
<name> <file> [<file> ...]
The first two columns should be the name of the sample
and the file. Paired-end should be listed on the same line.
'''
with open(args.summary, 'r') as fh:
rows = [line.rstrip().split() for line in fh]
data_dir = (args.data_dir
if args.data_dir else os.path.dirname(fh.name))
# add and protect path to second (and third) columns in rows
for row in rows:
row[1:] = [
path.protect(os.path.join(data_dir, col))
for col in row[1:]
]
return rows
import subprocess
import sys
import time
sys.path.append("../remsci/")
import remsci.scripted.base as base
from remsci.lib.utility import path
from libpipe.pipes.genomics import NestedGenomicsPipe
from libpipe.parsers.fastq import FastqScripted
# from libpipe.cmds import (
# SkewerCmd, HisatCmd, Bowtie2Cmd, FastqcCmd,
# SamtoolsSortCmd, SamtoolsIndexCmd, BedtoolsMulticovCmd,
# )
ROOT_DIR = path.protect('~/work/projects')
PIPE_PBS_TEMPLATE = ''
def add_subparsers():
'''Use this function to add subparsers from modules'''
subparser = base.get_subparser()
fastq_parser = FastqScripted(subparser)
fastq_parser.setup()
def setup_logger():
# setup logger
import logging
from remsci.lib.utility import customLogging
customLogging.config()
import subprocess
import sys
import time
sys.path.append("../remsci/")
import remsci.scripted.base as base
from remsci.lib.utility import path
from libpipe.pipes.base import BasePipe
from libpipe.parsers.fastq import FastqScripted
from libpipe.cmds import (
SkewerCmd, HisatCmd, Bowtie2Cmd, FastqcCmd,
SamtoolsSortCmd, SamtoolsIndexCmd, BedtoolsMulticovCmd,
)
ROOT_DIR = path.protect('~/data/rempipe')
PIPE_PBS_TEMPLATE = ''
DO_RUN = lambda x: not _has_output(x)
def add_subparsers():
'''Use this function to add subparsers from modules'''
subparser = base.get_subparser()
fastq_parser = FastqScripted(subparser)
fastq_parser.setup()
def pipe(file_list, genome, project_dir, force=False):
timestamp = time.strftime("%y%m%d-%H%M%S")