def _run_cnvkit_shared(data, test_bams, background_bams, access_file, work_dir,
background_name=None):
"""Shared functionality to run CNVkit.
"""
ref_file = dd.get_ref_file(data)
raw_work_dir = os.path.join(work_dir, "raw")
out_base = os.path.splitext(os.path.basename(test_bams[0]))[0]
background_cnn = "%s_background.cnn" % (background_name if background_name else "flat")
if not utils.file_exists(os.path.join(raw_work_dir, "%s.cnr" % out_base)):
with tx_tmpdir(data, work_dir) as tx_work_dir:
target_bed = tz.get_in(["config", "algorithm", "variant_regions"], data)
cmd = ["batch"] + test_bams + ["-n"] + background_bams + ["-f", ref_file] + \
["--targets", target_bed, "--access", access_file,
"-d", raw_work_dir, "--split",
"-p", str(tz.get_in(["config", "algorithm", "num_cores"], data, 1)),
"--output-reference", os.path.join(raw_work_dir, background_cnn)]
at_avg, at_min, t_avg = _get_antitarget_size(access_file, target_bed)
if at_avg:
cmd += ["--antitarget-avg-size", str(at_avg), "--antitarget-min-size", str(at_min),
"--target-avg-size", str(t_avg)]
args = cnvlib_cmd.parse_args(cmd)
args.func(args)
shutil.move(tx_work_dir, raw_work_dir)
return {"cnr": os.path.join(raw_work_dir, "%s.cnr" % out_base),
"cns": os.path.join(raw_work_dir, "%s.cns" % out_base),
"back_cnn": os.path.join(raw_work_dir, background_cnn)}
def _run_cnvkit_shared(data, test_bams, background_bams, access_file, work_dir,
background_name=None):
"""Shared functionality to run CNVkit.
"""
ref_file = dd.get_ref_file(data)
raw_work_dir = os.path.join(work_dir, "raw")
out_base = os.path.splitext(os.path.basename(test_bams[0]))[0]
background_cnn = "%s_background.cnn" % (background_name if background_name else "flat")
if not utils.file_exists(os.path.join(raw_work_dir, "%s.cnr" % out_base)):
with tx_tmpdir(data, work_dir) as tx_work_dir:
target_bed = tz.get_in(["config", "algorithm", "variant_regions"], data)
cmd = ["batch"] + test_bams + ["-n"] + background_bams + ["-f", ref_file] + \
["--targets", target_bed, "--access", access_file,
"-d", raw_work_dir, "--split",
"-p", str(tz.get_in(["config", "algorithm", "num_cores"], data, 1)),
"--output-reference", os.path.join(raw_work_dir, background_cnn)]
at_avg, at_min, t_avg = _get_antitarget_size(access_file, target_bed)
if at_avg:
cmd += ["--antitarget-avg-size", str(at_avg), "--antitarget-min-size", str(at_min),
"--target-avg-size", str(t_avg)]
local_sitelib = os.path.join(install.get_defaults().get("tooldir", "/usr/local"),
"lib", "R", "site-library")
cmd += ["--rlibpath", local_sitelib]
args = cnvlib_cmd.parse_args(cmd)
args.func(args)
shutil.move(tx_work_dir, raw_work_dir)
return {"cnr": os.path.join(raw_work_dir, "%s.cnr" % out_base),
"cns": os.path.join(raw_work_dir, "%s.cns" % out_base),
"back_cnn": os.path.join(raw_work_dir, background_cnn)}
def _add_seg_to_output(out, items):
"""Export outputs to 'seg' format compatible with IGV and GenePattern.
"""
out_file = "%s.seg" % os.path.splitext(out["cns"])[0]
if not utils.file_exists(out_file):
with file_transaction(items[0], out_file) as tx_out_file:
cmd = ["export", "seg", "-o", tx_out_file, out["cns"]]
args = cnvlib_cmd.parse_args(cmd)
args.func(args)
out["seg"] = out_file
return out
def _add_seg_to_output(out, items):
"""Export outputs to 'seg' format compatible with IGV and GenePattern.
"""
out_file = "%s.seg" % os.path.splitext(out["cns"])[0]
if not utils.file_exists(out_file):
with file_transaction(items[0], out_file) as tx_out_file:
cmd = ["export", "seg", "-o", tx_out_file, out["cns"]]
args = cnvlib_cmd.parse_args(cmd)
args.func(args)
out["seg"] = out_file
return out
def _run_cnvkit_single(data, work_dir):
"""Process a single input file with a uniform background.
"""
ref_file = dd.get_ref_file(data)
access_file = _create_access_file(ref_file, work_dir)
raw_work_dir = os.path.join(work_dir, "raw")
if not utils.file_exists(os.path.join(raw_work_dir, "%s.cnr" %
os.path.splitext(os.path.basename(data["align_bam"]))[0])):
with utils.curdir_tmpdir(data, work_dir) as tx_work_dir:
cmd = ["batch", data["align_bam"], "-n", "-f", ref_file,
"--targets", tz.get_in(["config", "algorithm", "variant_regions"], data),
"--access", access_file,
"-d", tx_work_dir, "--split", "-p", str(tz.get_in(["config", "algorithm", "num_cores"], data, 1)),
# XXX Currently set for testing -- need to generalize
"--target-avg-size", "500", "--antitarget-avg-size", "500"]
args = cnvlib_cmd.parse_args(cmd)
args.func(args)
shutil.move(tx_work_dir, raw_work_dir)
raise NotImplementedError
#!/usr/bin/env python
"""Command-line interface for CNVkit, the Copy Number Variation toolkit."""
import logging
from cnvlib import commands
if __name__ == '__main__':
logging.basicConfig(level=logging.INFO, format="%(message)s")
args = commands.parse_args()
args.func(args)
