def compare_to_rm(data):
"""Compare final variant calls against reference materials of known calls.
"""
toval_data = _get_validate(data)
if toval_data:
if isinstance(toval_data["vrn_file"], (list, tuple)):
raise NotImplementedError("Multiple input files for validation: %s" % toval_data["vrn_file"])
else:
vrn_file = os.path.abspath(toval_data["vrn_file"])
rm_file = normalize_input_path(toval_data["config"]["algorithm"]["validate"], toval_data)
rm_interval_file = _gunzip(normalize_input_path(toval_data["config"]["algorithm"].get("validate_regions"),
toval_data),
toval_data)
caller = _get_caller(toval_data)
sample = dd.get_sample_name(toval_data)
base_dir = utils.safe_makedir(os.path.join(toval_data["dirs"]["work"], "validate", sample, caller))
rm_file = naming.handle_synonyms(rm_file, dd.get_ref_file(data), data["genome_build"], base_dir, data)
rm_interval_file = (naming.handle_synonyms(rm_interval_file, dd.get_ref_file(data),
data["genome_build"], base_dir, data)
if rm_interval_file else None)
vmethod = tz.get_in(["config", "algorithm", "validate_method"], data, "rtg")
if vmethod == "rtg":
eval_files = _run_rtg_eval(vrn_file, rm_file, rm_interval_file, base_dir, toval_data)
data["validate"] = _rtg_add_summary_file(eval_files, base_dir, toval_data)
elif vmethod == "bcbio.variation":
data["validate"] = _run_bcbio_variation(vrn_file, rm_file, rm_interval_file, base_dir,
sample, caller, toval_data)
return [[data]]
def compare_to_rm(data):
"""Compare final variant calls against reference materials of known calls.
"""
if isinstance(data, (list, tuple)):
data = _normalize_cwl_inputs(data)
toval_data = _get_validate(data)
if toval_data:
caller = _get_caller(toval_data)
sample = dd.get_sample_name(toval_data)
base_dir = utils.safe_makedir(
os.path.join(toval_data["dirs"]["work"], "validate", sample,
caller))
if isinstance(toval_data["vrn_file"], (list, tuple)):
raise NotImplementedError(
"Multiple input files for validation: %s" %
toval_data["vrn_file"])
else:
vrn_file = os.path.abspath(toval_data["vrn_file"])
rm_file = normalize_input_path(
toval_data["config"]["algorithm"]["validate"], toval_data)
rm_interval_file = _gunzip(
normalize_input_path(
toval_data["config"]["algorithm"].get("validate_regions"),
toval_data), toval_data)
rm_interval_file = bedutils.clean_file(
rm_interval_file,
toval_data,
bedprep_dir=utils.safe_makedir(os.path.join(base_dir, "bedprep")))
rm_file = naming.handle_synonyms(rm_file, dd.get_ref_file(data),
data.get("genome_build"), base_dir,
data)
rm_interval_file = (naming.handle_synonyms(
rm_interval_file, dd.get_ref_file(data), data.get("genome_build"),
base_dir, data) if rm_interval_file else None)
vmethod = tz.get_in(["config", "algorithm", "validate_method"], data,
"rtg")
if not vcfutils.vcf_has_variants(vrn_file):
# RTG can fail on totally empty files. Skip these since we have nothing.
pass
# empty validation file, every call is a false positive
elif not vcfutils.vcf_has_variants(rm_file):
eval_files = _setup_call_fps(vrn_file, rm_interval_file, base_dir,
toval_data)
data["validate"] = _rtg_add_summary_file(eval_files, base_dir,
toval_data)
elif vmethod == "rtg":
eval_files = _run_rtg_eval(vrn_file, rm_file, rm_interval_file,
base_dir, toval_data)
data["validate"] = _rtg_add_summary_file(eval_files, base_dir,
toval_data)
elif vmethod == "hap.py":
data["validate"] = _run_happy_eval(vrn_file, rm_file,
rm_interval_file, base_dir,
toval_data)
elif vmethod == "bcbio.variation":
data["validate"] = _run_bcbio_variation(vrn_file, rm_file,
rm_interval_file, base_dir,
sample, caller, toval_data)
return [[data]]
def compare_to_rm(data):
"""Compare final variant calls against reference materials of known calls.
"""
if isinstance(data, (list, tuple)) and cwlutils.is_cwl_run(utils.to_single_data(data[0])):
data = _normalize_cwl_inputs(data)
toval_data = _get_validate(data)
toval_data = cwlutils.unpack_tarballs(toval_data, toval_data)
if toval_data:
caller = _get_caller(toval_data)
sample = dd.get_sample_name(toval_data)
base_dir = utils.safe_makedir(os.path.join(toval_data["dirs"]["work"], "validate", sample, caller))
if isinstance(toval_data["vrn_file"], (list, tuple)):
raise NotImplementedError("Multiple input files for validation: %s" % toval_data["vrn_file"])
else:
vrn_file = os.path.abspath(toval_data["vrn_file"])
rm_file = normalize_input_path(toval_data["config"]["algorithm"]["validate"], toval_data)
rm_interval_file = _gunzip(normalize_input_path(toval_data["config"]["algorithm"].get("validate_regions"),
toval_data),
toval_data)
rm_interval_file = bedutils.clean_file(rm_interval_file, toval_data, prefix="validateregions-",
bedprep_dir=utils.safe_makedir(os.path.join(base_dir, "bedprep")))
rm_file = naming.handle_synonyms(rm_file, dd.get_ref_file(toval_data), data.get("genome_build"),
base_dir, data)
rm_interval_file = (naming.handle_synonyms(rm_interval_file, dd.get_ref_file(toval_data),
data.get("genome_build"), base_dir, data)
if rm_interval_file else None)
vmethod = tz.get_in(["config", "algorithm", "validate_method"], data, "rtg")
# RTG can fail on totally empty files. Call everything in truth set as false negatives
if not vcfutils.vcf_has_variants(vrn_file):
eval_files = _setup_call_false(rm_file, rm_interval_file, base_dir, toval_data, "fn")
data["validate"] = _rtg_add_summary_file(eval_files, base_dir, toval_data)
# empty validation file, every call is a false positive
elif not vcfutils.vcf_has_variants(rm_file):
eval_files = _setup_call_fps(vrn_file, rm_interval_file, base_dir, toval_data, "fp")
data["validate"] = _rtg_add_summary_file(eval_files, base_dir, toval_data)
elif vmethod in ["rtg", "rtg-squash-ploidy"]:
eval_files = _run_rtg_eval(vrn_file, rm_file, rm_interval_file, base_dir, toval_data, vmethod)
eval_files = _annotate_validations(eval_files, toval_data)
data["validate"] = _rtg_add_summary_file(eval_files, base_dir, toval_data)
elif vmethod == "hap.py":
data["validate"] = _run_happy_eval(vrn_file, rm_file, rm_interval_file, base_dir, toval_data)
elif vmethod == "bcbio.variation":
data["validate"] = _run_bcbio_variation(vrn_file, rm_file, rm_interval_file, base_dir,
sample, caller, toval_data)
return [[data]]
def compare_to_rm(data):
"""Compare final variant calls against reference materials of known calls.
"""
toval_data = _get_validate(data)
if toval_data:
if isinstance(toval_data["vrn_file"], (list, tuple)):
raise NotImplementedError(
"Multiple input files for validation: %s" %
toval_data["vrn_file"])
else:
vrn_file = os.path.abspath(toval_data["vrn_file"])
rm_file = normalize_input_path(
toval_data["config"]["algorithm"]["validate"], toval_data)
rm_interval_file = _gunzip(
normalize_input_path(
toval_data["config"]["algorithm"].get("validate_regions"),
toval_data), toval_data)
caller = _get_caller(toval_data)
sample = dd.get_sample_name(toval_data)
base_dir = utils.safe_makedir(
os.path.join(toval_data["dirs"]["work"], "validate", sample,
caller))
rm_file = naming.handle_synonyms(rm_file, dd.get_ref_file(data),
data["genome_build"], base_dir, data)
rm_interval_file = (naming.handle_synonyms(
rm_interval_file, dd.get_ref_file(data), data["genome_build"],
base_dir, data) if rm_interval_file else None)
vmethod = tz.get_in(["config", "algorithm", "validate_method"], data,
"rtg")
if vmethod == "rtg":
eval_files = _run_rtg_eval(vrn_file, rm_file, rm_interval_file,
base_dir, toval_data)
data["validate"] = _rtg_add_summary_file(eval_files, base_dir,
toval_data)
elif vmethod == "bcbio.variation":
data["validate"] = _run_bcbio_variation(vrn_file, rm_file,
rm_interval_file, base_dir,
sample, caller, toval_data)
return [[data]]