def _check_for_problem_somatic_batches(items, config):
"""Identify problem batch setups for somatic calling.
We do not support multiple tumors in a single batch and VarDict(Java) does not
handle pooled calling, only tumor/normal.
"""
to_check = []
for data in items:
data = copy.deepcopy(data)
data["config"] = config_utils.update_w_custom(config, data)
to_check.append(data)
data_by_batches = collections.defaultdict(list)
for data in to_check:
batches = dd.get_batches(data)
if batches:
for batch in batches:
data_by_batches[batch].append(data)
for batch, items in data_by_batches.items():
if vcfutils.get_paired(items):
vcfutils.check_paired_problems(items)
elif len(items) > 1:
vcs = vcfutils.get_somatic_variantcallers(items)
if "vardict" in vcs:
raise ValueError(
"VarDict does not support pooled non-tumor/normal calling, in batch %s: %s"
% (batch, [dd.get_sample_name(data) for data in items]))
elif "mutect" in vcs or "mutect2" in vcs:
raise ValueError(
"MuTect and MuTect2 require a 'phenotype: tumor' sample for calling, "
"in batch %s: %s" %
(batch, [dd.get_sample_name(data) for data in items]))
def _check_for_problem_somatic_batches(items, config):
"""Identify problem batch setups for somatic calling.
We do not support multiple tumors in a single batch and VarDict(Java) does not
handle pooled calling, only tumor/normal.
"""
to_check = []
for data in items:
data = copy.deepcopy(data)
data["config"] = config_utils.update_w_custom(config, data)
to_check.append(data)
data_by_batches = collections.defaultdict(list)
for data in to_check:
batches = dd.get_batches(data)
if batches:
for batch in batches:
data_by_batches[batch].append(data)
for batch, items in data_by_batches.items():
if vcfutils.get_paired(items):
vcfutils.check_paired_problems(items)
elif len(items) > 1:
vcs = vcfutils.get_somatic_variantcallers(items)
if "vardict" in vcs:
raise ValueError("VarDict does not support pooled non-tumor/normal calling, in batch %s: %s"
% (batch, [dd.get_sample_name(data) for data in items]))
elif "mutect" in vcs or "mutect2" in vcs:
raise ValueError("MuTect and MuTect2 require a 'phenotype: tumor' sample for calling, "
"in batch %s: %s"
% (batch, [dd.get_sample_name(data) for data in items]))
