import argparse
import subprocess
import time
import tempfile
from collections import defaultdict
from ruffus import *
import yaml
from ccrngspy.tasks import FastQC
from ccrngspy import utils
from ccrngspy.pipeline import fastqc_helpers
from ccrngspy.pipeline import dummy_helpers
logger = utils.make_local_logger("FastQC logging", level="debug", color="green")
parser = argparse.ArgumentParser(description="Run fastqc on files.")
parser.add_argument("--print_only", dest="print_only", action="store_true", default=False,
help="Don't run the pipeline, just print what will be run.")
parser.add_argument('--verbose', type=int, default=3,
help="Verbosity when using print only mode.")
parser.add_argument('--config_file', dest="config_file", type=str,
help="A YAML configuration file for pipeline.")
parser.add_argument('--sample_file', dest="sample_file", type=str,
help="A YAML configuration file for pipeline.")
"""Wrapper for RUM (RNAseq Unified Mapper).
Kenny Daily, 2012
"""
import subprocess
import argparse
import os
import Task
from ccrngspy import utils
logger = utils.make_local_logger("RUM logging", level="debug", color="green")
class RUMrunner(Task.Task):
"""Container for RUM tasks.
"""
_cmd = "RUM_runner.pl"
_opt_lookup = dict(output_directory="-o %s",
threads="-t %s",
casava="--casava")
def __init__(self,
config_file=None,
name=None,
input_file_list=None,
import sys
import os
import argparse
import subprocess
import time
import tempfile
from collections import defaultdict
from ruffus import *
import yaml
from ccrngspy.tasks import BFAST
from ccrngspy.pipeline import bfast_helpers
from ccrngspy import utils
logger = utils.make_local_logger("Ruffus BFAST QC Logger", level="debug", color=True)
parser = argparse.ArgumentParser(description="Run bfast on files.")
parser.add_argument('--config_file', dest="config_file", type=str,
help="A YAML configuration file for pipeline.")
parser.add_argument('--verbose', type=int, default=3,
help="Verbosity when using print only mode.")
parser.add_argument('--sample_file', dest="sample_file", type=str,
help="A tab separated file about the samples to run.")
parser.add_argument("--print_only", dest="print_only", action="store_true", default=False,
help="Don't run the pipeline, just print what will be run.")
import sys
import os
import argparse
import subprocess
import time
import tempfile
from collections import defaultdict
from ruffus import *
import yaml
# from ccrngspy.tasks import BFAST
# from ccrngspy.pipeline import bfast_helpers
from ccrngspy import utils
logger = utils.make_local_logger("Ruffus Breakdancer QC Logger", level="debug", color=True)
parser = argparse.ArgumentParser(description="Run breakdancer on BAM files.")
parser.add_argument('--config_file', dest="config_file", type=str,
help="A YAML configuration file for pipeline.")
parser.add_argument('--verbose', type=int, default=3,
help="Verbosity when using print only mode.")
parser.add_argument('--sample_file', dest="sample_file", type=str,
help="A tab separated file about the samples to run.")
parser.add_argument("--print_only", dest="print_only", action="store_true", default=False,
help="Don't run the pipeline, just print what will be run.")
"""Helper files for pipeline fastqc steps.
"""
import os
import csv
from ccrngspy import utils
logger = utils.make_local_logger("Picard helper logging", level="debug", color="green")
def make_picard_param_list(samples, config, params=None):
"""Helper function to turn the sample file into a list of files.
Needs to be a list of [[input1, input2], output, params]; for the fastqc script.
The output is a log file (a sentinel that can be used to check completion),
while the params are taken from the global opts variable
(and possibly from the YAML config file).
"""
final_list = []
rum_dir = config['rum_params']['output_dir']
log_dir = config['general_params']['log_file_dir']
for sample in samples:
tmp = [os.path.join(fastq_dir, sample['samplename', RUM.sorted.sam]),
os.path.join(fastq_dir, sample['samplename', RUM.sam]),
os.path.join(log_dir, "%s.picard.LOG" % sample['samplename']),
params]
import sys
import os
import argparse
import subprocess
from ruffus import *
import yaml
from ccrngspy.tasks import FastQC
from ccrngspy.tasks import Picard
from ccrngspy.tasks import RUM
from ccrngspy.pipeline import fastqc_helpers
from ccrngspy.pipeline import rum_helpers
from ccrngspy import utils
logger = utils.make_local_logger("Ruffus RNASeq QC Logger", level="debug", color=True)
parser = argparse.ArgumentParser(description="Run fastqc on files.")
parser.add_argument("--print_only", dest="print_only", action="store_true", default=False,
help="Don't run the pipeline, just print what will be run.")
parser.add_argument("--no_log_dir", dest="no_create_log_dir", action="store_true", default=False,
help="Don't recreate the output log dir.")
parser.add_argument("--no_output_dir", dest="no_create_output_dir", action="store_true", default=False,
help="Don't recreate the output dirs.")
parser.add_argument('--config_file', dest="config_file", type=str,
help="A YAML configuration file for pipeline.")
"""Helper files for pipeline fastqc steps.
"""
import os
from ccrngspy import utils
logger = utils.make_local_logger("FastQC helper logging", level="debug", color="green")
def make_fastqc_param_list(samples, config, params=None):
"""Helper function to turn the sample file into a list of files.
Needs to be a list of [input, output, params]; for the fastqc script.
The output is a log file (a sentinel that can be used to check completion),
while the params are taken from the global opts variable
(and possibly from the YAML config file).
"""
final_list = []
fastq_dir = config['general_params']['fastq_input_dir']
output_dir = config['fastqc_params']['output_dir']
for sample in samples:
params = dict(sample=sample['samplename'])
tmp1 = [os.path.join(fastq_dir, sample['filename1']),
os.path.join(output_dir, "%s_fastqc.zip" % sample['sample1']),
"""Helper files for pipeline bowtie steps.
"""
import os
from ccrngspy import utils
logger = utils.make_local_logger("Bowtie helper logging", level="debug", color="green")
def make_bowtie_param_list(samples, config, params=None):
"""Helper function to turn the sample file into a list of files.
Needs to be a list of [[input1, input2], output, params]; for the fastqc script.
The output is the file bowtie2.sam.
while the params are taken from the global opts variable
(and possibly from the YAML config file).
"""
final_list = []
fastq_dir = config['general_params']['fastq_input_dir']
log_dir = config['general_params']['log_file_dir']
bowtie_dir = config['bowtie_params']['output_dir']
for sample in samples:
params = dict(sample=sample['samplename'])
import sys
import os
import argparse
import subprocess
import time
from ruffus import *
import yaml
from ccrngspy.tasks import Picard
from ccrngspy.tasks import RUM
from ccrngspy.pipeline import rum_helpers
from ccrngspy.pipeline import picard_helpers
from ccrngspy import utils
logger = utils.make_local_logger("Ruffus RNASeq RUM2 QC Logger", level="debug", color=True)
parser = argparse.ArgumentParser(description="Run RUM2 pipeline.")
parser.add_argument('--config_file', dest="config_file", type=str,
help="A YAML configuration file for pipeline.")
parser.add_argument('--sample_file', dest="sample_file", type=str,
help="A tab separated file about the samples to run.")
parser.add_argument("--print_only", dest="print_only", action="store_true", default=False,
help="Don't run the pipeline, just print what will be run.")
parser.add_argument("--no_output_dir", dest="no_create_output_dir", action="store_true", default=False,
help="Don't recreate the output dirs.")
"""Wrapper for Tophat.
Kenny Daily, 2012
"""
import subprocess
import argparse
import os
import Task
from ccrngspy import utils
logger = utils.make_local_logger("Tophat logging", level="debug", color="green")
class TophatRunner(Task.Task):
"""Container for Tophat tasks.
"""
_cmd = "/usr/local/tophat-2.0.4/bin/tophat2"
def __init__(self, index=None, mate_file_one=None, mate_file_two=None, output_dir=None, threads=1, other_params=None):
self.index = index
self.mate_file_one = mate_file_one
self.mate_file_two = mate_file_two
self.output_dir = output_dir
self.threads = threads
