# parser.add_argument('--pipeline', "-p",
# type=str,
# choices = ['sim_pure', 'sim_contam','real_pure','test_pipe'],
# help="Defining which pipeline to run")
parser.add_argument('--config_file', "-cf",
type=str,
#metavar="config_file",
help="yaml file with pipeline parameters")
options = parser.parse_args()
## standard python logger which can be synchronised across concurrent Ruffus tasks
## define logging output with --log_file log_file_name
logger, logger_mutex = cmdline.setup_logging (__name__, options.log_file, options.verbose)
# if we are printing only
if not options.just_print and \
not options.flowchart and \
not options.touch_files_only:
config_file= file(options.config_file, 'r')
config = yaml.load(config_file)
pipeline1a = make_sipp(org_list = config['org_list'], config = config)
cmdline.run (options, logger = logger)
sys.exit()
annotations = parser.add_argument_group('annotations')
annotations.add_argument('--genome_fasta', type=str, help='genome fasta')
annotations.add_argument('--gtf', type=str, help='gtf')
annotations.add_argument("--suppl_annot", type=str, nargs="+", help="supplementary annotation file(s) for checking novel splice events")
args = parser.parse_args()
params = get_params(args, args.params)
check_params(args, params)
logs_dir = args.outdir + '/logs'
if not os.path.exists(logs_dir):
os.makedirs(logs_dir)
log_file = '%s/log.%s.txt' % (logs_dir, datetime.datetime.now().strftime("%Y-%m-%d_%H:%M:%S"))
logger, logging_mutex = cmdline.setup_logging(__name__,
log_file,
args.verbose)
print 'log_file:', log_file
cmdline.run(args)
read_pairs = []
if args.fq:
read_pairs = format_read_pairs(fqs=args.fq)
elif args.fq_list:
read_pairs = format_read_pairs(list_file=args.fq_list)
history_file = '%s/.ruffus_history.sqlite' % args.outdir
bbt_outdir = '%s/bbt_%s' % (args.outdir, get_version('bbt'))
assembly_outdir = '%s/rnabloom_%s' % (args.outdir, get_version('rnabloom'))
pv_outdir = '%s/pv_%s' % (args.outdir, get_version('pv'))
### start of pipeline
# setting the main working directory
home_dir = os.getcwd()
root_dir = "%s/%s" % (home_dir, args.name)
try:
os.mkdir(root_dir)
except OSError:
pass
### setting up logging
if not args.log_file:
logfile = "%s/%s" % (root_dir, "log_file.txt")
else:
logfile = "%s/%s" % (root_dir, args.log_file)
logger, logger_mutex = cmdline.setup_logging("CRAC_Pipeline_SE", logfile, 10)
### setting the starting files
startingfiles = [os.path.abspath(i) for i in args.forwardreads]
logger.info("analysing the following files:\n%s\n" % "\n".join(startingfiles))
### start of pipeline definition
pipeline = Pipeline(
name="Single-end data CRAC pipeline for multiplexed libraries")
logger.info("Trimming the reads")
pipeline.transform(
task_func=runFlexBar,
hisat_genome_index="$HOME/Scratch/reference/GRcm38/hisat2/grcm38_snp_tran"
genome="$HOME/Scratch/reference/GRcm38/GRCm38/Mus_musculus.GRCm38"
genome_name="Mus_musculus.GRCm38.dna.primary_assembly.fa"
mask="$HOME/Scratch/reference/GRcm38/gtf/Mus_musculus.GRCm38.84.ribo.mito.mask.gtf"
if hisat_check:
print "hisat check: " + str(hisat_check)
print(str(hisat_genome_index))
if stringtie_check:
print "stringtie check: " + str(stringtie_check)
print "STAR check: " + str(star_check)
print gtf
print "Basedir: " + basedir
# standard python logger which can be synchronised across concurrent Ruffus tasks
logger, logger_mutex = cmdline.setup_logging ("Chela", options.log_file, options.verbose)
if not aligner:
raise Exception ("Aligner not selected with --aligner")
files_list=options.input
if not files_list:
raise Exception ("No matching samples specified with --input.")
input_files=[]
with open(files_list, 'r') as f:
content = [line.decode('utf-8').rstrip('\n') for line in f]
for line in content:
#print(line)
line = line.rstrip()
#print(basedir + line)
# print "input " + str(glob.glob(basedir + line + "/replicate*/fastq_raw/*gz"))
import ruffus as rf
import ruffus.cmdline as cmdline
import pandas as pd
import numpy as np
import os, errno
import yaml
# import logging
from trio import triodb
# import warnings
# warnings.filterwarnings("ignore", message=".*deprecation.*")
# Configuration and command line options
parser = cmdline.get_argparse(description='Pipeline using the TPC-H example.')
parser.add_argument("--config")
options = parser.parse_args()
lg, lm = cmdline.setup_logging(__name__, options.log_file, options.verbose)
# lg.setLevel(logging.INFO)
if vars(options)['config'] == None:
print "No config supplied."
parser.print_help()
sys.exit()
with open(vars(options)['config'], 'r') as f:
cfg = yaml.load(f)
lg.info('pipeline:: ::config %s' % str(cfg))
SQL_PRINT_MAX = 1000
# =============================================================
# functions
# =============================================================
pipeline2.set_input(input=[pipeline1a, pipeline1b, pipeline1c])
import ruffus.cmdline as cmdline
parser = cmdline.get_argparse(
description='Demonstrates the new Ruffus syntax in version 2.6')
parser.add_argument('--cleanup',
"-C",
action="store_true",
help="Cleanup before and after.")
options = parser.parse_args()
# standard python logger which can be synchronised across concurrent Ruffus tasks
logger, logger_mutex = cmdline.setup_logging(__file__, options.log_file,
options.verbose)
logger.debug("\tRuffus Version = " + ruffus.__version__)
if options.cleanup:
try:
shutil.rmtree(tempdir)
except:
pass
correct = False
# if we are not printing but running
if not options.just_print and \
not options.flowchart and \
not options.touch_files_only:
### start of pipeline
# setting the main working directory
home_dir = os.getcwd()
root_dir = "%s/%s" % (home_dir, args.name)
try:
os.mkdir(root_dir)
except OSError:
pass
### setting up logging
if not args.log_file:
logfile = "%s/%s" % (root_dir, "log_file.txt")
else:
logfile = "%s/%s" % (root_dir, args.log_file)
logger, logger_mutex = cmdline.setup_logging("ChemModSeqPipeline", logfile, 10)
### starting the pipeline commands
pipeline = Pipeline(name="ChemModSeqPipeline")
args.forwardreads = [os.path.abspath(i) for i in args.forwardreads]
args.reversereads = [os.path.abspath(i) for i in args.reversereads]
startingfiles = zip(args.forwardreads, args.reversereads)
#print startingfiles
if args.adapter:
pipeline.transform(
task_func=runFlexBar,
input=startingfiles,
filter=formatter("^.+/([^/]+)_1.(san)?fastq$",
def __init__(self, prog_name, log_file, verbosity):
proxy, mutex = cmdline.setup_logging(__name__, log_file, verbosity)
self.proxy = proxy
self.mutex = mutex