def run(items):
paired = vcfutils.get_paired(items)
# paired is PairedInfo of one T/N pair (or just T) - named tuple, paired.tumor_config
if not paired:
logger.info("Skipping PureCN; no somatic tumor calls in batch: %s" %
" ".join([dd.get_sample_name(d) for d in items]))
return items
work_dir = _sv_workdir(paired.tumor_data)
normaldb = tz.get_in(["algorithm", "background", "cnv_reference", "purecn_normaldb"], paired.tumor_config)
# the right way of running purecn is with normaldb
if normaldb:
purecn_out = _run_purecn_normaldb(paired, work_dir)
purecn_out = _run_purecn_dx(purecn_out, paired)
else:
purecn_out = _run_purecn(paired, work_dir)
out = []
if paired.normal_data:
out.append(paired.normal_data)
if purecn_out:
purecn_out["variantcaller"] = "purecn"
if "loh" in purecn_out:
from bcbio.structural import titancna
purecn_out["vrn_file"] = titancna.to_vcf(purecn_out["loh"], "PureCN", _get_header, _loh_to_vcf,
paired.tumor_data, sep=",")
purecn_out["lohsummary"] = loh.summary_status(purecn_out, paired.tumor_data)
if "sv" not in paired.tumor_data:
paired.tumor_data["sv"] = []
paired.tumor_data["sv"].append(purecn_out)
out.append(paired.tumor_data)
return out
def run(items):
paired = vcfutils.get_paired(items)
if not paired:
logger.info("Skipping PureCN; no somatic tumor calls in batch: %s" %
" ".join([dd.get_sample_name(d) for d in items]))
return items
work_dir = _sv_workdir(paired.tumor_data)
purecn_out = _run_purecn(paired, work_dir)
# XXX Currently finding edge case failures with Dx calling, needs additional testing
# purecn_out = _run_purecn_dx(purecn_out, paired)
out = []
if paired.normal_data:
out.append(paired.normal_data)
if purecn_out:
purecn_out["variantcaller"] = "purecn"
if "loh" in purecn_out:
from bcbio.structural import titancna
purecn_out["vrn_file"] = titancna.to_vcf(purecn_out["loh"],
"PureCN",
_get_header,
_loh_to_vcf,
paired.tumor_data,
sep=",")
purecn_out["lohsummary"] = loh.summary_status(
purecn_out, paired.tumor_data)
if "sv" not in paired.tumor_data:
paired.tumor_data["sv"] = []
paired.tumor_data["sv"].append(purecn_out)
out.append(paired.tumor_data)
return out
def run(items):
paired = vcfutils.get_paired(items)
if not paired:
logger.info("Skipping PureCN; no somatic tumor calls in batch: %s" %
" ".join([dd.get_sample_name(d) for d in items]))
return items
work_dir = _sv_workdir(paired.tumor_data)
purecn_out = _run_purecn(paired, work_dir)
# XXX Currently finding edge case failures with Dx calling, needs additional testing
# purecn_out = _run_purecn_dx(purecn_out, paired)
out = []
if paired.normal_data:
out.append(paired.normal_data)
if purecn_out:
purecn_out["variantcaller"] = "purecn"
if "loh" in purecn_out:
from bcbio.structural import titancna
purecn_out["vrn_file"] = titancna.to_vcf(purecn_out["loh"], "PureCN", _get_header, _loh_to_vcf,
paired.tumor_data, sep=",")
purecn_out["lohsummary"] = loh.summary_status(purecn_out, paired.tumor_data)
if "sv" not in paired.tumor_data:
paired.tumor_data["sv"] = []
paired.tumor_data["sv"].append(purecn_out)
out.append(paired.tumor_data)
return out
def _finalize_sv(solution_file, data):
"""Add output files from TitanCNA calling optional solution.
"""
out = {"variantcaller": "titancna"}
with open(solution_file) as in_handle:
solution = dict(
zip(in_handle.readline().strip("\r\n").split("\t"),
in_handle.readline().strip("\r\n").split("\t")))
if solution.get("path"):
out["purity"] = solution["purity"]
out["ploidy"] = solution["ploidy"]
out["cellular_prevalence"] = [
x.strip() for x in solution["cellPrev"].split(",")
]
base = os.path.basename(solution["path"])
out["plot"] = dict([(n, solution["path"] + ext) for (n, ext) in [(
"rplots",
".Rplots.pdf"), ("cf", "/%s_CF.pdf" %
base), ("cna", "/%s_CNA.pdf" %
base), ("loh", "/%s_LOH.pdf" % base)]
if os.path.exists(solution["path"] + ext)])
out["subclones"] = "%s.segs.txt" % solution["path"]
out["hetsummary"] = solution_file
out["vrn_file"] = to_vcf(out["subclones"], "TitanCNA", _get_header,
_seg_to_vcf, data)
out["lohsummary"] = loh.summary_status(out, data)
return out
