def parse_arguments():
"""
Creat parser instance and parse command-line arguments passed to the pipeline
:return argparse.Namespace: parsed arguments namespace
"""
parser = VersionInHelpParser(prog="PEPATAC_collator",
description='PEPATAC collator',
version=__version__)
parser = pypiper.add_pypiper_args(parser, groups=['pypiper', 'looper'])
parser.add_argument("-n",
"--name",
help="Name of the project to use.",
type=str)
parser.add_argument("-r",
"--results",
help="Output results sub directory path.",
type=str)
parser.add_argument("--skip-consensus",
action='store_true',
dest="skip_consensus",
default=False,
help="Do not calculate consensus peaks.")
parser.add_argument("--skip-table",
action='store_true',
dest="skip_table",
default=False,
help="Do not calculate peak counts table.")
args = parser.parse_args()
return args
def _parse_cmdl(cmdl):
parser = ArgumentParser(description="Automatic GEO SRA data downloader")
parser.add_argument(
"-b", "--bamfolder",
default=safe_echo("SRABAM"),
help="Optional: Specify a location to store bam files "
"[Default: $SRABAM:" + safe_echo("SRABAM") + "]")
parser.add_argument(
"-s", "--srafolder", default=safe_echo("SRARAW"),
help="Optional: Specify a location to store sra files "
"[Default: $SRARAW:" + safe_echo("SRARAW") + "]")
# parser.add_argument(
# "--picard", dest="picard_path", default=safe_echo("PICARD"),
# help="Specify a path to the picard jar, if you want to convert "
# "fastq to bam [Default: $PICARD:" + safe_echo("PICARD") + "]")
parser.add_argument(
"-r", "--srr", required=True, nargs="+",
help="SRR files")
parser = pypiper.add_pypiper_args(parser, groups=["pypiper", "config"])
return parser.parse_args(cmdl)
def main():
# Parse command-line arguments
parser = ArgumentParser(
prog="hic-pipeline",
description="Hi-C pipeline."
)
parser = arg_parser(parser)
parser = pypiper.add_pypiper_args(parser, groups=["ngs", "looper", "resource", "pypiper"])
args = parser.parse_args()
# Read in yaml configs
series = pd.Series(yaml.load(open(args.sample_config, "r")))
# looper 0.6/0.7 compatibility:
if "protocol" in series.index:
key = "protocol"
elif "library" in series.index:
key = "library"
else:
raise KeyError(
"Sample does not contain either a 'protocol' or 'library' attribute!")
# Create Sample object
if series[key] != "HiChIP":
sample = HiCSample(series)
else:
sample = HiChIPSample(series)
# Check if merged
if len(sample.data_path.split(" ")) > 1:
sample.merged = True
else:
sample.merged = False
sample.prj = AttributeDict(sample.prj)
sample.paths = AttributeDict(sample.paths.__dict__)
# Check read type if not provided
if not hasattr(sample, "ngs_inputs"):
sample.ngs_inputs = [sample.data_source]
if not hasattr(sample, "read_type"):
sample.set_read_type()
# Shorthand for read_type
if sample.read_type == "paired":
sample.paired = True
else:
sample.paired = False
# Set file paths
sample.set_file_paths()
# sample.make_sample_dirs() # should be fixed to check if values of paths are strings and paths indeed
# Start Pypiper object
# Best practice is to name the pipeline with the name of the script;
# or put the name in the pipeline interface.
pipe_manager = pypiper.PipelineManager(name="hic", outfolder=sample.paths.sample_root, args=args)
pipe_manager.config.tools.scripts_dir = os.path.join(os.path.dirname(os.path.realpath(__file__)), "tools")
# Start main function
process(sample, pipe_manager, args)
def _parse_args(cmdl):
from argparse import ArgumentParser
parser = ArgumentParser(description='Pipeline')
# First, add arguments from Pypiper, including
# 1. pypiper options, 2. looper connections, 3. common options,
# using the all_args=True flag (you can customize this).
# Adds options including; for details, see:
# http://github.com/epigen/pypiper/command_line_args.md
parser = pypiper.add_pypiper_args(parser, all_args=True)
# Add any pipeline-specific arguments
parser.add_argument("-t",
"--trimgalore",
dest="trimgalore",
action="store_true",
help='Use trimgalore instead of trimmomatic?')
parser.add_argument("-e",
"--epilog",
dest='epilog',
action="store_true",
help='Use epilog for meth calling?')
parser.add_argument("--pdr",
dest="pdr",
action="store_true",
help='Calculate Proportion of Discordant Reads (PDR)?')
parser.add_argument(
"--rrbs-fill",
dest="rrbs_fill",
type=int,
default=4,
help=
"Number of bases from read end to regard as unreliable and ignore due to RRBS chemistry"
)
parser.add_argument(
"--dark-bases",
type=int,
default=None,
help="Number of bases from to prepend to R1 from R2 for dark sequencing"
)
args = parser.parse_args(cmdl)
if args.rrbs_fill < 0:
raise ValueError("Negative RRBS fill-in value: {}".format(
args.rrbs_fill))
# Translate pypiper method of read type specification into flag-like option.
if args.single_or_paired == "paired":
args.paired_end = True
else:
args.paired_end = False
# Input is required.
if not args.input:
parser.print_help()
raise SystemExit
return args
def main():
# Parse command-line arguments
parser = ArgumentParser(prog="atacseq-pipeline",
description="ATAC-seq pipeline.")
parser = arg_parser(parser)
parser = pypiper.add_pypiper_args(
parser, groups=["ngs", "looper", "resource", "pypiper"])
args = parser.parse_args()
if args.sample_config is None or args.output_parent is None:
parser.print_help()
return 1
# Read in yaml configs
series = pd.Series(yaml.safe_load(open(args.sample_config, "r")))
series["sample_root"] = args.output_parent
print(series)
# Create Sample object
if series["protocol"] != "DNase-seq":
sample = ATACseqSample(series)
else:
sample = DNaseSample(series)
print(sample)
# Check if merged
if (type(sample.data_source) == list) & (len(sample.data_source) > 1):
sample.merged = True
else:
sample.merged = False
sample.paths = AttributeDict(sample.__dict__)
# Check read type if not provided
if not hasattr(sample, "ngs_inputs"):
sample.ngs_inputs = [sample.data_source]
if not hasattr(sample, "read_type"):
sample.set_read_type()
# Shorthand for read_type
if sample.read_type == "paired":
sample.paired = True
else:
sample.paired = False
# Set file paths
sample.set_file_paths()
# Start Pypiper object
# Best practice is to name the pipeline with the name of the script;
# or put the name in the pipeline interface.
pipe_manager = pypiper.PipelineManager(name="atacseq",
outfolder=sample.sample_root,
args=args)
pipe_manager.config.tools.scripts_dir = pjoin(
os.path.dirname(os.path.realpath(__file__)), "tools")
# Start main function
process(sample, pipe_manager, args)
def main():
# Parse command-line arguments
parser = ArgumentParser(prog="chipseq-pipeline",
description="ChIP-seq pipeline.")
parser = arg_parser(parser)
parser = pypiper.add_pypiper_args(
parser, groups=["ngs", "looper", "resource", "pypiper"])
args = parser.parse_args()
if args.sample_config is None:
parser.print_help()
return 1
# Read in yaml configs
series = pd.Series(yaml.safe_load(open(args.sample_config, "r")))
# Create Sample object
if series["protocol"] == "ChIPmentation":
sample = ChIPmentation(series)
else:
sample = ChIPseqSample(series)
# Check if merged
if len(sample.data_source.split(" ")) > 1:
sample.merged = True
else:
sample.merged = False
sample.prj = AttributeDict(sample.prj)
sample.paths = AttributeDict(sample.paths.__dict__)
# Check read type if not provided
if not hasattr(sample, "ngs_inputs"):
sample.ngs_inputs = [sample.data_source]
if not hasattr(sample, "read_type"):
sample.set_read_type()
# Shorthand for read_type
if sample.read_type == "paired":
sample.paired = True
else:
sample.paired = False
# Set file paths
sample.set_file_paths(sample.prj)
# Start Pypiper object
# Best practice is to name the pipeline with the name of the script;
# or put the name in the pipeline interface.
pipe_manager = pypiper.PipelineManager(name="chipseq",
outfolder=sample.paths.sample_root,
args=args)
# Start main function
process(sample, pipe_manager, args)
def main():
# Parse command-line arguments
parser = ArgumentParser(prog="rnaKallisto",
description="Kallisto pipeline")
parser = arg_parser(parser)
parser = pypiper.add_pypiper_args(parser, all_args=True)
args = parser.parse_args()
# Read in yaml configs
sample = AttributeDict(yaml.load(open(args.sample_config, "r")))
path_conf_file = os.path.join(os.path.dirname(__file__), args.config_file)
pipeline_config = AttributeDict(yaml.load(open(path_conf_file), "r"))
# Start main function
process(sample, pipeline_config, args)
def main():
# Parse command-line arguments
parser = ArgumentParser(prog="starrseq-pipeline",
description="STARR-seq pipeline.")
parser = arg_parser(parser)
parser = pypiper.add_pypiper_args(
parser, groups=["ngs", "looper", "resource", "pypiper"])
args = parser.parse_args()
# Read in yaml configs
sample = STARRSeqSample(pd.Series(yaml.load(open(args.sample_config,
"r"))))
# Check if merged
if len(sample.data_path.split(" ")) > 1:
sample.merged = True
else:
sample.merged = False
sample.prj = AttributeDict(sample.prj)
sample.paths = AttributeDict(sample.paths.__dict__)
# Check read type if not provided
if not hasattr(sample, "ngs_inputs"):
sample.ngs_inputs = [sample.data_source]
if not hasattr(sample, "read_type"):
sample.set_read_type()
# Shorthand for read_type
if sample.read_type == "paired":
sample.paired = True
else:
sample.paired = False
# Set file paths
sample.set_file_paths()
# sample.make_sample_dirs() # should be fixed to check if values of paths are strings and paths indeed
# Start Pypiper object
# Best practice is to name the pipeline with the name of the script;
# or put the name in the pipeline interface.
pipe_manager = pypiper.PipelineManager(name="starrseq",
outfolder=sample.paths.sample_root,
args=args)
pipe_manager.config.tools.scripts_dir = os.path.join(
os.path.dirname(os.path.realpath(__file__)), "tools")
# Start main function
process(sample, pipe_manager, args)
def main():
# Parse command-line arguments
parser = ArgumentParser(
prog="rnaseq-pipeline",
description="RNA-seq pipeline.")
parser = arg_parser(parser)
parser = pypiper.add_pypiper_args(parser, groups=["ngs", "looper", "resource", "pypiper"])
args = parser.parse_args()
# Read in yaml configs
sample = RNASeqSample(pd.Series(yaml.load(open(args.sample_config, "r"))))
# Check if merged
if len(sample.data_path.split(" ")) > 1:
sample.merged = True
else:
sample.merged = False
sample.prj = AttributeDict(sample.prj)
sample.paths = AttributeDict(sample.paths.__dict__)
# Check read type if not provided
if not hasattr(sample, "ngs_inputs"):
sample.ngs_inputs = [sample.data_source]
if not hasattr(sample, "read_type"):
sample.set_read_type()
# Shorthand for read_type
if sample.read_type == "paired":
sample.paired = True
else:
sample.paired = False
# Set file paths
sample.set_file_paths()
# sample.make_sample_dirs() # should be fixed to check if values of paths are strings and paths indeed
# Start Pypiper object
# Best practice is to name the pipeline with the name of the script;
# or put the name in the pipeline interface.
pipe_manager = pypiper.PipelineManager(
name="rnaseq", outfolder=sample.paths.sample_root, args=args)
pipe_manager.config.tools.scripts_dir = os.path.join(
os.path.dirname(os.path.realpath(__file__)), "tools")
# Start main function
process(sample, pipe_manager, args)
def main():
# Parse command-line arguments
parser = ArgumentParser(
prog="dropseq-pipeline",
description="Drop-seq pipeline."
)
parser = arg_parser(parser)
parser = pypiper.add_pypiper_args(parser, groups=["ngs", "looper", "resource", "pypiper"])
args = parser.parse_args()
if args.sample_config is None:
parser.print_help()
return 1
# Read in yaml configs
sample = AttributeDict(yaml.load(open(args.sample_config, "r")))
pipeline_config = AttributeDict(yaml.load(open(os.path.join(os.path.dirname(__file__), args.config_file), "r")))
# Start main function
process(sample, pipeline_config, args)
def main():
# Parse command-line arguments
parser = ArgumentParser(prog="starrseq-pipeline",
description="STARR-seq pipeline.")
parser = arg_parser(parser)
parser = pypiper.add_pypiper_args(parser, all_args=True)
args = parser.parse_args()
if args.sample_config is None:
parser.print_help()
return 1
# Read in yaml config and create Sample object
sample = STARRseqSample(pd.Series(yaml.load(open(args.sample_config,
"r"))))
# Check if merged
if len(sample.data_source.split(" ")) > 1:
sample.merged = True
else:
sample.merged = False
sample.prj = AttributeDict(sample.prj)
sample.paths = AttributeDict(sample.paths.__dict__)
# Shorthand for read_type
if sample.read_type == "paired":
sample.paired = True
else:
sample.paired = False
# Set file paths
sample.set_file_paths()
sample.make_sample_dirs()
# Start Pypiper object
# Best practice is to name the pipeline with the name of the script;
# or put the name in the pipeline interface.
pipe_manager = pypiper.PipelineManager(name="starrseq",
outfolder=sample.paths.sample_root,
args=args)
# Start main function
process(sample, pipe_manager, args)
def _parse_args(cmdl):
from argparse import ArgumentParser
parser = ArgumentParser(description='Pipeline')
# First, add arguments from Pypiper, including
# 1. pypiper options, 2. looper connections, 3. common options,
# using the all_args=True flag (you can customize this).
# Adds options including; for details, see:
# http://github.com/epigen/pypiper/command_line_args.md
parser = pypiper.add_pypiper_args(parser, all_args=True)
parser.add_argument('-e',
'--epilog',
dest='epilog',
action="store_true",
default=False,
help='Use epilog for meth calling?')
parser.add_argument(
'--single2',
dest='single2',
action="store_true",
default=False,
help=
'Single secondary mode: any reads not mapping in paired-end mode will \
be aligned using single-end mode, and then analyzed. Only valid for \
paired-end mode. ')
args = parser.parse_args(cmdl)
if args.single_or_paired == "paired":
args.paired_end = True
else:
args.paired_end = False
if not args.input:
parser.print_help()
raise SystemExit
return args
def main():
# Parse command-line arguments
parser = ArgumentParser(prog="amplicon-pipeline",
description="Amplicon pipeline.")
parser = arg_parser(parser)
parser = pypiper.add_pypiper_args(parser,
groups=["ngs", "looper", "pypiper"])
args = parser.parse_args()
print(args)
print("Processing sample {}.".format(args.sample_name))
output_folder = os.path.abspath(args.output_parent)
# Create output directories if not existing
for path in [args.output_parent, output_folder]:
if not os.path.exists(path):
try:
os.mkdir(path)
except OSError("Cannot create directory '{}'".format(path)):
raise
# Count length of pattern matches
sizes = count_sizes(fastq_file=args.input,
amplicon=args.amplicon,
guide_rna=args.guide_rna)
# Calculate efficiency
efficiency = (sizes[sizes.index != 0].sum() / float(sizes.sum())) * 100
# Save
with open(
os.path.join(output_folder, args.sample_name + ".efficiency.csv"),
"w") as handle:
handle.write("{},{}\n".format(args.sample_name, efficiency))
print("Sample {} has an editing efficiency of {}.".format(
args.sample_name, efficiency))
print("Finished processing sample {}.".format(args.sample_name))
def build_argparser():
parser = ArgumentParser(
description=
"A pipeline to count the number of reads and file size. Accepts"
" BAM, fastq, or fastq.gz files.")
# First, add standard arguments from Pypiper.
# groups="pypiper" will add all the arguments that pypiper uses,
# and adding "common" adds arguments for --input and --sample--name
# and "output_parent". You can read more about your options for standard
# arguments in the pypiper docs (section "command-line arguments")
parser = pypiper.add_pypiper_args(
parser,
groups=["pypiper", "common", "ngs", "logmuse"],
args=["output-parent", "config"],
required=['sample-name', 'output-parent'])
# Add any pipeline-specific arguments if you like here.
# args for `output_parent` and `sample_name` were added by the standard
# `add_pypiper_args` function.
return parser
RNA NucSeq pipeline
"""
from argparse import ArgumentParser
import os
import sys
import yaml
import subprocess
import re
import pypiper
# Argument Parsing
# #######################################################################################
parser = ArgumentParser(description='Pypiper arguments.')
parser = pypiper.add_pypiper_args(parser, all_args=True)
# Add any pipeline-specific arguments
parser.add_argument('-e',
'--ercc',
default="ERCC92",
dest='ERCC_assembly',
type=str,
help='ERCC Assembly')
parser.add_argument(
'-em',
'--ercc-mix',
default="False",
dest='ERCC_mix',
help='ERCC mix. If False no ERCC analysis will be performed.')
def _parse_cmdl(cmdl):
description = """ The SRA data converter is a wrapper around sra-tools that
provides convenience functions for converting or deleting sra data in
various formats.
"""
parser = ArgumentParser(description=description)
# parser = pypiper.add_pypiper_args(parser, args=["output-parent"])
parser.add_argument(
"-m",
"--mode",
default="convert",
choices=["convert", "delete_sra", "delete_bam", "delete_fq"],
help="What do you want to do? Default: convert",
)
parser.add_argument(
"-f",
"--format",
default="fastq",
choices=["fastq", "bam"],
help="Convert to what format? Default: fastq",
)
parser.add_argument(
"-b",
"--bamfolder",
default=safe_echo("SRABAM"),
help="Optional: Specify a location to store bam files "
"[Default: $SRABAM:" + safe_echo("SRABAM") + "]",
)
parser.add_argument(
"-q",
"--fqfolder",
default=safe_echo("SRAFQ"),
help="Optional: Specify a location to store fastq files "
"[Default: $SRAFQ:" + safe_echo("SRAFQ") + "]",
)
parser.add_argument(
"-s",
"--srafolder",
default=safe_echo("SRARAW"),
help="Optional: Specify a location to store pipeline output "
"[Default: $SRARAW:" + safe_echo("SRARAW") + "]",
)
parser.add_argument(
"--keep-sra",
action="store_true",
default=False,
help="On convert mode, keep original sra data?",
)
parser.add_argument(
"-S",
"--sample-name",
required=False,
nargs="+",
help="Name for sample to run",
metavar="SAMPLE_NAME",
)
parser.add_argument("-r",
"--srr",
required=True,
nargs="+",
help="SRR files")
parser = pypiper.add_pypiper_args(parser,
groups=["config", "logmuse"],
args=["output-parent", "recover"])
return parser.parse_args(cmdl)
import os.path
import sys
from subprocess import call
import subprocess
import re
import pypiper
import yaml
from datetime import datetime
# Argument Parsing
# #######################################################################################
parser = ArgumentParser(description='Pypiper arguments.')
parser = pypiper.add_pypiper_args(parser, all_args=True)
#Add any pipeline-specific arguments
#parser.add_argument('-e', '--ercc', default="ERCC92",
#parser.add_argument('-em', '--ercc-mix',
#parser.add_argument('-f', dest='filter', action='store_false', default=True)
# Core-seq as optional parameter
#parser.add_argument('-cs', '--core-seq', default=False, dest='coreseq', action='store_true', help='CORE-seq Mode')
args = parser.parse_args()
if args.single_or_paired == "paired":
args.paired_end = True
else:
args.paired_end = False
###
def main():
# Parse command-line arguments
parser = ArgumentParser(prog="chipseq-pipeline",
description="ChIP-seq pipeline.")
parser = arg_parser(parser)
parser = pypiper.add_pypiper_args(parser, groups=["all"])
args = parser.parse_args()
if args.sample_config is None:
parser.print_help()
return 1
# Read in yaml configs
series = pd.Series(yaml.load(open(args.sample_config, "r")))
# looper 0.6/0.7 compatibility:
if "protocol" in series.index:
key = "protocol"
elif "library" in series.index:
key = "library"
else:
raise KeyError(
"Sample does not contain either a 'protocol' or 'library' attribute!"
)
# Create Sample object
if series[key] != "ChIPmentation":
sample = ChIPseqSample(series)
else:
sample = ChIPmentation(series)
# Check if merged
if len(sample.data_path.split(" ")) > 1:
sample.merged = True
else:
sample.merged = False
sample.prj = AttributeDict(sample.prj)
sample.paths = AttributeDict(sample.paths.__dict__)
# Check read type if not provided
if not hasattr(sample, "ngs_inputs"):
sample.ngs_inputs = [sample.data_source]
if not hasattr(sample, "read_type"):
sample.set_read_type()
# Shorthand for read_type
if sample.read_type == "paired":
sample.paired = True
else:
sample.paired = False
# Set file paths
sample.set_file_paths()
# sample.make_sample_dirs() # should be fixed to check if values of paths are strings and paths indeed
# Start Pypiper object
# Best practice is to name the pipeline with the name of the script;
# or put the name in the pipeline interface.
pipe_manager = pypiper.PipelineManager(name="chipseq",
outfolder=sample.paths.sample_root,
args=args)
# Start main function
if not args.only_peaks:
pipe_manager = process(sample, pipe_manager, args)
else:
print("Skipped processing sample '{}'.".format(sample.name))
# If sample does not have "ctrl" attribute, finish processing it.
if not hasattr(sample, "compare_sample"):
pipe_manager.stop_pipeline()
print("Finished processing sample '{}'.".format(sample.name))
return
# The pipeline will now wait for the comparison sample file to be completed
pipe_manager._wait_for_file(
sample.filtered.replace(sample.name, sample.compare_sample))
# Start peak calling function
call_peaks(sample, pipe_manager, args)
def main():
# Parse command-line arguments
parser = ArgumentParser(
prog="chipseq-pipeline",
description="ChIP-seq pipeline."
)
parser = arg_parser(parser)
parser = pypiper.add_pypiper_args(parser, groups=["ngs", "looper", "resource", "pypiper"])
args = parser.parse_args()
if args.sample_config is None:
parser.print_help()
return 1
# Read in yaml configs
series = pd.Series(yaml.load(open(args.sample_config, "r")))
# looper 0.6/0.7 compatibility:
if "protocol" in series.index:
key = "protocol"
elif "library" in series.index:
key = "library"
else:
raise KeyError(
"Sample does not contain either a 'protocol' or 'library' attribute!")
# Create Sample object
if series[key] != "ChIPmentation":
sample = ChIPseqSample(series)
else:
sample = ChIPmentation(series)
# Check if merged
if len(sample.data_path.split(" ")) > 1:
sample.merged = True
else:
sample.merged = False
sample.prj = AttributeDict(sample.prj)
sample.paths = AttributeDict(sample.paths.__dict__)
# Check read type if not provided
if not hasattr(sample, "ngs_inputs"):
sample.ngs_inputs = [sample.data_source]
if not hasattr(sample, "read_type"):
sample.set_read_type()
else:
if sample.read_type not in ['single', 'paired']:
sample.set_read_type()
# Shorthand for read_type
if sample.read_type == "paired":
sample.paired = True
else:
sample.paired = False
# Set file paths
sample.set_file_paths()
# sample.make_sample_dirs() # should be fixed to check if values of paths are strings and paths indeed
# Start Pypiper object
# Best practice is to name the pipeline with the name of the script;
# or put the name in the pipeline interface.
pipe_manager = pypiper.PipelineManager(name="chipseq", outfolder=sample.paths.sample_root, args=args)
# Start main function
if not args.only_peaks:
pipe_manager = process(sample, pipe_manager, args)
else:
print("Skipped processing sample '{}'.".format(sample.name))
# If sample does not have "ctrl" attribute, finish processing it.
if not hasattr(sample, "compare_sample"):
pipe_manager.stop_pipeline()
print("Finished processing sample '{}'.".format(sample.name))
return
# If compare_sample is empty string, finish processing.
if sample.compare_sample == "":
pipe_manager.stop_pipeline()
print("Finished processing sample '{}'.".format(sample.name))
return
# The pipeline will now wait for the comparison sample file to be completed
pipe_manager._wait_for_file(sample.filtered.replace(sample.name, sample.compare_sample))
# Start peak calling function
call_peaks(sample, pipe_manager, args)
import re
import pandas
import sys
import string
#' Part of the looper setup. We add two additional arguments to the parser, one is the sample id of
#' the currently processed sample and the second is the path to the bam file containing the mapped
#' reads (preferably with bsmap). These two arguments are passed through
#' config/pipeline_interface.yaml to map column names in the sample anntotation sheet to the name of
#' the argument here.
parser = argparse.ArgumentParser(description="Pipeline")
parser.add_argument("--sample_id", "-o", help="id of sample to be analyzed")
parser.add_argument("--bam_name",
help="path to bam file of sample to be analyzed")
parser = pypiper.add_pypiper_args(parser, groups=["pypiper", "looper"])
args = parser.parse_args()
manager = pypiper.PipelineManager(name="HETEROGENEITY",
outfolder=args.output_parent,
args=args)
pipe_folder = os.path.dirname(sys.argv[0]) + "/"
#####################################################################################################
#' PART I: Preprocessing
#####################################################################################################
if not os.path.exists(args.output_parent + "/" + args.sample_id):
os.makedirs(args.output_parent + "/" + args.sample_id)
sample_folder = args.output_parent + "/" + args.sample_id + "/"
def build_argparser():
"""
Builds argument parser.
:return argparse.ArgumentParser
"""
banner = "%(prog)s - reference genome asset manager"
additional_description = "\nhttps://refgenie.databio.org"
parser = VersionInHelpParser(prog="refgenie",
version=__version__,
description=banner,
epilog=additional_description)
subparsers = parser.add_subparsers(dest="command")
def add_subparser(cmd, description):
return subparsers.add_parser(cmd,
description=description,
help=description)
sps = {}
for cmd, desc in SUBPARSER_MESSAGES.items():
sps[cmd] = add_subparser(cmd, desc)
# It's required for init
sps[cmd].add_argument(
'-c',
'--genome-config',
required=(cmd == INIT_CMD),
dest="genome_config",
help=
"Path to local genome configuration file. Optional if {} environment variable is set."
.format(", ".join(refgenconf.CFG_ENV_VARS)))
sps[INIT_CMD].add_argument(
'-s',
'--genome-server',
nargs='+',
default=DEFAULT_SERVER,
help="URL(s) to use for the {} attribute in config file. Default: {}.".
format(DEFAULT_SERVER, CFG_SERVERS_KEY))
sps[BUILD_CMD] = pypiper.add_pypiper_args(
sps[BUILD_CMD], groups=None, args=["recover", "config", "new-start"])
# Add any arguments specific to subcommands.
sps[BUILD_CMD].add_argument(
'--tag-description',
required=False,
default=None,
type=str,
help="Add tag level description (e.g. built with version 0.3.2).")
sps[BUILD_CMD].add_argument(
'--genome-description',
required=False,
default=None,
type=str,
help=
"Add genome level description (e.g. The mouse mitochondrial genome, released in Dec 2013)."
)
sps[BUILD_CMD].add_argument(
"-d",
"--docker",
action="store_true",
help="Run all commands in the refgenie docker container.")
sps[BUILD_CMD].add_argument(
'--assets',
nargs="+",
action='append',
required=False,
default=None,
help='Override the default genome, asset and tag of the parents'
' (e.g. fasta=hg38/fasta:default gtf=mm10/gencode_gtf:default).')
sps[BUILD_CMD].add_argument(
'--files',
nargs="+",
action='append',
required=False,
default=None,
help=
'Provide paths to the required files (e.g. fasta=/path/to/file.fa.gz).'
)
sps[BUILD_CMD].add_argument(
'--params',
nargs="+",
action='append',
required=False,
default=None,
help='Provide required parameter values (e.g. param1=value1).')
sps[BUILD_CMD].add_argument(
'-v',
'--volumes',
nargs="+",
required=False,
default=None,
help='If using docker, also mount these folders as volumes.')
sps[BUILD_CMD].add_argument(
'-o',
'--outfolder',
dest='outfolder',
required=False,
default=None,
help='Override the default path to genomes folder, which is the '
'genome_folder attribute in the genome configuration file.')
sps[BUILD_CMD].add_argument(
"-q",
"--requirements",
action="store_true",
help="Show the build requirements for the specified asset and exit.")
sps[BUILD_CMD].add_argument("-r",
"--recipe",
required=False,
default=None,
type=str,
help="Provide a recipe to use.")
# add 'genome' argument to many commands
for cmd in [
PULL_CMD, GET_ASSET_CMD, BUILD_CMD, INSERT_CMD, REMOVE_CMD,
GETSEQ_CMD, TAG_CMD, ID_CMD
]:
# genome is not required for listing actions
sps[cmd].add_argument("-g",
"--genome",
required=cmd in GETSEQ_CMD,
help="Reference assembly ID, e.g. mm10.")
for cmd in LIST_REMOTE_CMD, LIST_LOCAL_CMD:
sps[cmd].add_argument("-g",
"--genome",
required=False,
type=str,
nargs="*",
help="Reference assembly ID, e.g. mm10.")
for cmd in [
PULL_CMD, GET_ASSET_CMD, BUILD_CMD, INSERT_CMD, REMOVE_CMD,
TAG_CMD, ID_CMD
]:
sps[cmd].add_argument(
"asset_registry_paths",
metavar="asset-registry-paths",
type=str,
nargs='+',
help=
"One or more registry path strings that identify assets (e.g. hg38/fasta or hg38/fasta:tag"
+ (" or hg38/fasta.fai:tag)." if cmd == GET_ASSET_CMD else ")."))
for cmd in [PULL_CMD, REMOVE_CMD, INSERT_CMD]:
sps[cmd].add_argument(
"-f",
"--force",
action="store_true",
help="Do not prompt before action, approve upfront.")
sps[PULL_CMD].add_argument("-u",
"--no-untar",
action="store_true",
help="Do not extract tarballs.")
sps[INSERT_CMD].add_argument("-p",
"--path",
required=True,
help="Relative local path to asset.")
sps[GETSEQ_CMD].add_argument(
"-l",
"--locus",
required=True,
help="Coordinates of desired sequence; e.g. 'chr1:50000-50200'.")
sps[GET_ASSET_CMD].add_argument(
"-e",
"--check-exists",
required=False,
action="store_true",
help="Whether the returned asset path should be checked for existence "
"on disk.")
group = sps[TAG_CMD].add_mutually_exclusive_group(required=True)
group.add_argument("-t",
"--tag",
type=str,
help="Tag to assign to an asset.")
group.add_argument("-d",
"--default",
action="store_true",
help="Set the selected asset tag as the default one.")
sps[SUBSCRIBE_CMD].add_argument(
"-r",
"--reset",
action="store_true",
help="Overwrite the current list of server URLs.")
for cmd in [SUBSCRIBE_CMD, UNSUBSCRIBE_CMD]:
sps[cmd].add_argument(
"-s",
"--genome-server",
nargs='+',
required=True,
help=
"One or more URLs to {action} the {key} attribute in config file.".
format(action="add to" if cmd == SUBSCRIBE_CMD else "remove from",
key=CFG_SERVERS_KEY))
return parser
def build_argparser():
"""
Builds argument parser.
:return argparse.ArgumentParser
"""
banner = "%(prog)s - builds and manages reference genome assemblies"
additional_description = "\nhttps://refgenie.databio.org"
parser = _VersionInHelpParser(description=banner,
epilog=additional_description)
parser.add_argument("-V",
"--version",
action="version",
version="%(prog)s {v}".format(v=__version__))
subparsers = parser.add_subparsers(dest="command")
def add_subparser(cmd, description):
return subparsers.add_parser(cmd,
description=description,
help=description)
subparser_messages = {
INIT_CMD: "Initialize a genome configuration.",
LIST_LOCAL_CMD: "List available local genomes.",
LIST_REMOTE_CMD: "List available genomes and assets on server.",
PULL_CMD: "Download assets.",
BUILD_CMD: "Build genome assets.",
GET_ASSET_CMD: "Get the path to a local asset.",
INSERT_CMD: "Insert a local asset into the configuration file."
}
sps = {}
for cmd, desc in subparser_messages.items():
sps[cmd] = add_subparser(cmd, desc)
# It's required for init
sps[cmd].add_argument('-c',
'--genome-config',
required=(cmd == INIT_CMD),
dest="genome_config",
help="Path to local genome configuration file.")
sps[INIT_CMD].add_argument(
'-s',
'--genome-server',
default=DEFAULT_SERVER,
help="URL to use for the genome_server attribute in config file."
" Defaults : {}".format(DEFAULT_SERVER))
sps[BUILD_CMD] = pypiper.add_pypiper_args(
sps[BUILD_CMD], groups=None, args=["recover", "config", "new-start"])
# Add any arguments specific to subcommands.
sps[BUILD_CMD].add_argument(
"-d",
"--docker",
action="store_true",
help="Run all commands in the refgenie docker container.")
sps[BUILD_CMD].add_argument(
'-v',
'--volumes',
nargs="+",
required=False,
default=None,
help='If using docker, also mount these folders as volumes')
sps[BUILD_CMD].add_argument(
'-o',
'--outfolder',
dest='outfolder',
required=False,
default=None,
help='Override the default path to genomes folder, which is the '
'genome_folder attribute in the genome configuration file.')
for cmd in [PULL_CMD, GET_ASSET_CMD, BUILD_CMD, INSERT_CMD]:
sps[cmd].add_argument("-g",
"--genome",
required=True,
help="Reference assembly ID, e.g. mm10")
sps[cmd].add_argument(
"-a",
"--asset",
required=True,
nargs='+',
help="Name of one or more assets (keys in genome config file)")
sps[PULL_CMD].add_argument("-u",
"--no-untar",
action="store_true",
help="Do not extract tarballs.")
sps[INSERT_CMD].add_argument("-p",
"--path",
required=True,
help="Relative path to asset")
# Finally, arguments to the build command to give the files needed to do
# the building. These should eventually move to a more flexible system that
# doesn't require them to be hard-coded here in order to be recognized
for arg in BUILD_SPECIFIC_ARGS:
sps[BUILD_CMD].add_argument("--{arg}".format(arg=arg),
required=False,
help=SUPPRESS)
# sps[BUILD_CMD].add_argument(
# '--fasta', required=False, help=SUPPRESS)
# help='Local path or URL to genome sequence file in .fa, .fa.gz, '
# 'or .2bit format.'
# sps[BUILD_CMD].add_argument(
# '--gtf', required=False, help=SUPPRESS)
# help='Path to GTF gene annotation file.'
return parser
import sys
import subprocess
import yaml
import pypiper
parser = ArgumentParser(
description="A pipeline to count the number of reads and file size. Accepts"
" BAM, fastq, or fastq.gz files.")
# First, add standard arguments from Pypiper.
# groups="pypiper" will add all the arguments that pypiper uses,
# and adding "common" adds arguments for --input and --sample--name
# and "output_parent". You can read more about your options for standard
# arguments in the pypiper docs (section "command-line arguments")
parser = pypiper.add_pypiper_args(parser, groups=["pypiper", "common", "ngs"],
args=["output-parent", "config"],
required=['sample-name', 'output-parent'])
# Add any pipeline-specific arguments if you like here.
args = parser.parse_args()
if not args.input or not args.output_parent:
parser.print_help()
raise SystemExit
if args.single_or_paired == "paired":
args.paired_end = True
else:
args.paired_end = False
def build_argparser():
"""
Builds argument parser.
:return argparse.ArgumentParser
"""
banner = "%(prog)s - reference genome asset manager"
additional_description = "\nhttps://refgenie.databio.org"
parser = VersionInHelpParser(
prog="refgenie",
version=f"{__version__} | refgenconf {rgc_version}",
description=banner,
epilog=additional_description,
)
subparsers = parser.add_subparsers(dest="command")
def add_subparser(cmd, msg, subparsers):
return subparsers.add_parser(
cmd,
description=msg,
help=msg,
formatter_class=lambda prog: HelpFormatter(
prog, max_help_position=40, width=90),
)
sps = {}
for cmd, desc in SUBPARSER_MESSAGES.items():
sps[cmd] = add_subparser(cmd, desc, subparsers)
# alias is nested and alias subcommands require config path
if cmd == ALIAS_CMD:
continue
# It's required for init
sps[cmd].add_argument(
"-c",
"--genome-config",
required=(cmd == INIT_CMD),
dest="genome_config",
metavar="C",
help=
"Path to local genome configuration file. Optional if {} environment variable is set."
.format(", ".join(CFG_ENV_VARS)),
)
sps[cmd].add_argument(
"--skip-read-lock",
required=False,
action="store_true",
help="Whether the config file should not be locked for reading",
)
# upgrade: upgrade config and alter file structure to the target version
sps[UPGRADE_CMD].add_argument(
"-v",
"--target-version",
required=True,
metavar="V",
help="Target config version for the upgrade.",
)
sps[UPGRADE_CMD].add_argument(
"-f",
"--force",
action="store_true",
help="Do not prompt before action, approve upfront.",
)
sps[INIT_CMD].add_argument(
"-s",
"--genome-server",
nargs="+",
default=[DEFAULT_SERVER],
help=
f"URL(s) to use for the {CFG_SERVERS_KEY} attribute in config file. Default: {DEFAULT_SERVER}.",
)
sps[INIT_CMD].add_argument(
"-f",
"--genome-folder",
help="Absolute path to parent folder refgenie-managed assets.",
)
sps[INIT_CMD].add_argument(
"-a",
"--genome-archive-folder",
help=
"Absolute path to parent archive folder refgenie-managed assets; used by refgenieserver.",
)
sps[INIT_CMD].add_argument(
"-b",
"--genome-archive-config",
help=
"Absolute path to desired archive config file; used by refgenieserver.",
)
sps[INIT_CMD].add_argument(
"-u",
"--remote-url-base",
help=
"URL to use as an alternative, remote archive location; used by refgenieserver.",
)
sps[INIT_CMD].add_argument(
"-j",
"--settings-json",
help="Absolute path to a JSON file with the key "
"value pairs to inialize the configuration "
"file with. Overwritten by itemized specifications.",
)
sps[BUILD_CMD] = pypiper.add_pypiper_args(
sps[BUILD_CMD], groups=None, args=["recover", "config", "new-start"])
# Add any arguments specific to subcommands.
sps[BUILD_CMD].add_argument(
"--tag-description",
required=False,
default=None,
type=str,
help="Add tag level description (e.g. built with version 0.3.2).",
)
sps[BUILD_CMD].add_argument(
"--genome-description",
required=False,
default=None,
type=str,
help=
"Add genome level description (e.g. The mouse mitochondrial genome, released in Dec 2013).",
)
sps[BUILD_CMD].add_argument(
"-d",
"--docker",
action="store_true",
help="Run all commands in the refgenie docker container.",
)
sps[BUILD_CMD].add_argument(
"--map",
action="store_true",
help=
"Run the map procedure: build assets and store the metadata in separate configs.",
)
sps[BUILD_CMD].add_argument(
"--pull-parents",
action="store_true",
help=
"Automatically pull the default parent asset if required but not provided",
)
sps[BUILD_CMD].add_argument(
"--preserve-map-configs",
action="store_true",
help=
"Do not remove the genome configuration files produced in the potential map step of building",
)
sps[BUILD_CMD].add_argument(
"--reduce",
action="store_true",
help=
"Run the reduce procedure: gather the metadata produced with `refgenie build --map`.",
)
sps[BUILD_CMD].add_argument(
"--assets",
nargs="+",
action="append",
required=False,
default=None,
help="Override the default genome, asset and tag of the parents"
" (e.g. fasta=hg38/fasta:default gtf=mm10/gencode_gtf:default).",
)
sps[BUILD_CMD].add_argument(
"--files",
nargs="+",
action="append",
required=False,
default=None,
help=
"Provide paths to the required files (e.g. fasta=/path/to/file.fa.gz).",
)
sps[BUILD_CMD].add_argument(
"--params",
nargs="+",
action="append",
required=False,
default=None,
help="Provide required parameter values (e.g. param1=value1).",
)
sps[BUILD_CMD].add_argument(
"-v",
"--volumes",
nargs="+",
required=False,
default=None,
help="If using docker, also mount these folders as volumes.",
)
sps[BUILD_CMD].add_argument(
"-q",
"--requirements",
action="store_true",
help="Show the build requirements for the specified asset and exit.",
)
sps[BUILD_CMD].add_argument(
"-r",
"--recipe",
required=False,
default=None,
type=str,
help="Provide a recipe to use.",
)
alias_subparser = sps[ALIAS_CMD]
alias_subsubparsers = alias_subparser.add_subparsers(dest="subcommand")
alias_sps = {}
for cmd, desc in ALIAS_SUBPARSER_MESSAGES.items():
alias_sps[cmd] = add_subparser(cmd, desc, alias_subsubparsers)
alias_sps[cmd].add_argument(
"-c",
"--genome-config",
required=False,
dest="genome_config",
metavar="C",
help=
"Path to local genome configuration file. Optional if {} environment variable is set."
.format(", ".join(CFG_ENV_VARS)),
)
alias_sps[cmd].add_argument(
"--skip-read-lock",
required=False,
action="store_true",
help="Whether the config file should not be locked for reading",
)
alias_sps[ALIAS_SET_CMD].add_argument(
"-a",
"--aliases",
metavar="A",
required=False,
default=None,
type=str,
nargs="+",
help=
"Aliases to set; single if the digest is to be retrieved from the server.",
)
alias_sps[ALIAS_SET_CMD].add_argument(
"-d",
"--digest",
metavar="D",
required=False,
type=str,
help=
"Digest to set; leave out if the digest is to be retrieved from the server.",
)
alias_sps[ALIAS_SET_CMD].add_argument(
"-r",
"--reset",
action="store_true",
help=
"Whether all the aliases should be removed prior to setting new ones.",
)
alias_sps[ALIAS_SET_CMD].add_argument(
"-f",
"--force",
action="store_true",
help="Whether the action should be forced, if genome does not exist.",
)
alias_sps[ALIAS_REMOVE_CMD].add_argument(
"-a",
"--aliases",
metavar="A",
required=False,
default=None,
type=str,
nargs="+",
help="Aliases to remove.",
)
alias_sps[ALIAS_REMOVE_CMD].add_argument("-d",
"--digest",
metavar="D",
required=True,
type=str,
help="Digest to remove.")
alias_sps[ALIAS_GET_CMD].add_argument(
"-a",
"--aliases",
metavar="A",
required=False,
type=str,
nargs="+",
help="Aliases to get the digests for.",
)
sps[COMPARE_CMD].add_argument(
"genome1",
metavar="GENOME1",
type=str,
nargs=1,
help="First genome for compatibility check.",
)
sps[COMPARE_CMD].add_argument(
"genome2",
metavar="GENOME2",
type=str,
nargs=1,
help="Second genome for compatibility check.",
)
sps[COMPARE_CMD].add_argument(
"-e",
"--no-explanation",
action="store_true",
help="Do not print compatibility code explanation.",
)
sps[COMPARE_CMD].add_argument(
"-f",
"--flag-meanings",
action="store_true",
help="Display compatibility flag meanings.",
)
# add 'genome' argument to many commands
for cmd in [
PULL_CMD,
GET_ASSET_CMD,
GET_REMOTE_ASSET_CMD,
BUILD_CMD,
INSERT_CMD,
REMOVE_CMD,
GETSEQ_CMD,
TAG_CMD,
ID_CMD,
]:
# genome is not required for listing actions
sps[cmd].add_argument(
"-g",
"--genome",
required=cmd in GETSEQ_CMD,
metavar="G",
help="Reference assembly ID, e.g. mm10.",
)
for cmd in LIST_REMOTE_CMD, LIST_LOCAL_CMD:
sps[cmd].add_argument(
"-g",
"--genome",
required=False,
type=str,
metavar="G",
nargs="*",
help="Reference assembly ID, e.g. mm10.",
)
for cmd in [
PULL_CMD,
GET_ASSET_CMD,
GET_REMOTE_ASSET_CMD,
BUILD_CMD,
INSERT_CMD,
REMOVE_CMD,
TAG_CMD,
ID_CMD,
]:
build_arg_kwargs = dict(
metavar="asset-registry-paths",
type=str,
nargs="+",
help=
"One or more registry path strings that identify assets (e.g. hg38/fasta or hg38/fasta:tag"
+ (" or hg38/fasta.fai:tag)."
if cmd in [GET_ASSET_CMD, GET_REMOTE_ASSET_CMD] else ")."),
)
# make asset-registry-path argument optional for build command
# and require it manually in CLI when running a non-reduce build
if cmd == BUILD_CMD:
build_arg_kwargs.update({"nargs": "*", "default": None})
sps[cmd].add_argument("asset_registry_paths", **build_arg_kwargs)
sps[LIST_LOCAL_CMD].add_argument("-r",
"--recipes",
action="store_true",
help="List available recipes.")
for cmd in [REMOVE_CMD, INSERT_CMD]:
sps[cmd].add_argument(
"-f",
"--force",
action="store_true",
help="Do not prompt before action, approve upfront.",
)
sps[REMOVE_CMD].add_argument(
"-a",
"--aliases",
action="store_true",
help=
"Remove the genome alias if last asset for that genome is removed.",
)
force_group = sps[PULL_CMD].add_argument_group(
title="Prompt handling",
description="These flags configure the pull prompt responses.",
)
overwrite_group = force_group.add_mutually_exclusive_group()
overwrite_group.add_argument("--no-overwrite",
action="store_true",
help="Do not overwrite if asset exists.")
overwrite_group.add_argument("--force-overwrite",
action="store_true",
help="Overwrite if asset exists.")
large_group = force_group.add_mutually_exclusive_group()
large_group.add_argument("--no-large",
action="store_true",
help="Do not pull archives over 5GB.")
large_group.add_argument(
"--pull-large",
action="store_true",
help="Pull any archive, regardless of its size.",
)
force_group.add_argument(
"--size-cutoff",
type=float,
default=10,
metavar="S",
help=
"Maximum archive file size to download with no confirmation required (in GB, default: 10)",
)
force_group.add_argument(
"-b",
"--batch",
action="store_true",
help="Use batch mode: pull large archives, do no overwrite",
)
sps[INSERT_CMD].add_argument("-p",
"--path",
required=True,
metavar="P",
help="Relative local path to asset.")
sps[INSERT_CMD].add_argument(
"-s",
"--seek-keys",
required=False,
type=str,
metavar="S",
help="""
String representation of a JSON object with seek_keys,
e.g. '{"seek_key1": "file.txt"}'
""",
)
sps[GETSEQ_CMD].add_argument(
"-l",
"--locus",
required=True,
help="Coordinates of desired sequence; e.g. 'chr1:50000-50200'.",
)
sps[GET_ASSET_CMD].add_argument(
"-e",
"--check-exists",
required=False,
action="store_true",
help=
"Whether the returned asset path should be checked for existence on disk.",
)
sps[TAG_CMD].add_argument(
"-f",
"--force",
action="store_true",
help="Do not prompt before action, approve upfront.",
)
group = sps[TAG_CMD].add_mutually_exclusive_group(required=True)
group.add_argument("-t",
"--tag",
type=str,
help="Tag to assign to an asset.")
group.add_argument(
"-d",
"--default",
action="store_true",
help="Set the selected asset tag as the default one.",
)
sps[SUBSCRIBE_CMD].add_argument(
"-r",
"--reset",
action="store_true",
help="Overwrite the current list of server URLs.",
)
for cmd in [SUBSCRIBE_CMD, UNSUBSCRIBE_CMD]:
sps[cmd].add_argument(
"-s",
"--genome-server",
nargs="+",
required=True,
metavar="S",
help=
"One or more URLs to {action} the {key} attribute in config file.".
format(
action="add to" if cmd == SUBSCRIBE_CMD else "remove from",
key=CFG_SERVERS_KEY,
),
)
for cmd in [LIST_REMOTE_CMD, GET_REMOTE_ASSET_CMD, POPULATE_REMOTE_CMD]:
sps[cmd].add_argument(
"-s",
"--genome-server",
nargs="+",
required=False,
metavar="S",
help="One or more URLs to use. "
"This information will not persist in the genome config file.",
)
sps[cmd].add_argument(
"-p",
"--append-server",
action="store_true",
help="Whether the provided servers should be appended to the list.",
)
for cmd in [POPULATE_REMOTE_CMD, GET_REMOTE_ASSET_CMD]:
sps[cmd].add_argument(
"--remote-class",
metavar="RC",
type=str,
default="http",
help="Remote data provider class, e.g. 'http' or 's3'",
)
for cmd in [POPULATE_REMOTE_CMD, POPULATE_CMD]:
sps[cmd].add_argument("-f",
"--file",
metavar="F",
help="File with registry paths to populate")
return parser
'specificity plots')
parser.add_argument(
"--bedbase-config", dest="bedbase_config", type=str, default=None,
help="a path to the bedbase configuratiion file")
parser.add_argument(
"-y", "--sample-yaml", dest="sample_yaml", type=str, required=False,
help="a yaml config file with sample attributes to pass on more metadata "
"into the database")
exclusive_group = parser.add_mutually_exclusive_group()
exclusive_group.add_argument(
'--no-db-commit', action='store_true',
help='whether the JSON commit to the database should be skipped')
exclusive_group.add_argument(
'--just-db-commit', action='store_true',
help='whether just to commit the JSON to the database')
parser = pypiper.add_pypiper_args(parser,
groups=["pypiper", "common", "looper", "ngs"])
args = parser.parse_args()
bbc = bbconf.BedBaseConf(filepath=bbconf.get_bedbase_cfg(args.bedbase_config))
bed_digest = md5(open(args.bedfile, 'rb').read()).hexdigest()
bedfile_name = os.path.split(args.bedfile)[1]
# need to split twice since there are 2 exts
fileid = os.path.splitext(os.path.splitext(bedfile_name)[0])[0]
outfolder = os.path.abspath(os.path.join(
bbc[CFG_PATH_KEY][CFG_BEDSTAT_OUTPUT_KEY], bed_digest))
json_file_path = os.path.abspath(os.path.join(outfolder, fileid + ".json"))
if not args.just_db_commit:
pm = pypiper.PipelineManager(name="bedstat-pipeline", outfolder=outfolder,
action="store",
type=str,
nargs="*",
help=
"path to the chain file(s) ffacilitating conversion from one assembly to the other"
)
parser.add_argument(
"-f",
"--outfolder",
type=str,
required=True,
help="path to folder where pipeline logs and lifted files will be stored")
# add pypiper args
parser = pypiper.add_pypiper_args(parser,
groups=["pypiper"],
required=["--bedfile", "--genome"])
args = parser.parse_args()
# Set output folder
logs_name = "bedlifter_logs"
logs_dir = os.path.join(args.outfolder, logs_name)
if not os.path.exists(logs_dir):
print("bedlifter logs directory doesn't exist. Creating one...")
os.makedirs(logs_dir)
def main():
pm = pypiper.PipelineManager(name="bedlifter",
outfolder=logs_dir,
__author__ = "Martin Jaeger"
__copyright__ = "Copyright 2018, Martin Jaeger"
__credits__ = []
__license__ = "GPL3"
__version__ = "0.3"
__maintainer__ = "Martin Jaeger"
__email__ = "*****@*****.**"
__status__ = "development"
########################
### Argument Parsing ###
########################
parser = ArgumentParser(description='Pypiper arguments.')
parser = pypiper.add_pypiper_args(parser,
groups=["pypiper", "resource", "config"])
parser.add_argument(
'-y',
'--sample_yaml',
dest='sample_config',
help=
'yaml config file with sample attributes; this file will be generated by looper if submitting multiple jobs in parallel',
type=str)
parser.add_argument(
'-i',
'--input_file',
dest='input_file',
help=
'Path to input raw read BAM file(s). Space-separated paths will be merged before processing.',
nargs='+',
from argparse import ArgumentParser
import os, re
import sys
import os.path
import subprocess
import pypiper
import yaml
import shutil
from datetime import datetime
# Argument Parsing from yaml file
# #######################################################################################
parser = ArgumentParser(description='Pipeline')
parser = pypiper.add_pypiper_args(
parser,
groups=["config"],
args=["sample-name", "recover", "new-start", "output-parent", "genome"])
#Add any pipeline-specific arguments
parser.add_argument(
'-I',
'--input-dir',
required=True,
dest='input',
type=str,
help=
"path to directory containing input bam files (and narrowpeak files if applicable) (required)"
)
parser.add_argument('-gs',
'--genome-size',
default="hs",