def _evaluate_multi(calls, truth_svtypes, work_dir, data):
base = os.path.join(work_dir, "%s-sv-validate" % (dd.get_sample_name(data)))
out_file = base + ".csv"
df_file = base + "-df.csv"
if any((not utils.file_uptodate(out_file, x["vrn_file"])
or not utils.file_uptodate(df_file, x["vrn_file"])) for x in calls):
with file_transaction(data, out_file) as tx_out_file:
with open(tx_out_file, "w") as out_handle:
with open(df_file, "w") as df_out_handle:
writer = csv.writer(out_handle)
dfwriter = csv.writer(df_out_handle)
writer.writerow(["svtype", "size", "caller", "sensitivity", "precision"])
dfwriter.writerow(["svtype", "size", "caller", "metric", "value", "label"])
for svtype, truth in truth_svtypes.items():
for size in EVENT_SIZES:
str_size = "%s-%s" % size
for call in calls:
call_bed = convert.to_bed(call, dd.get_sample_name(data), work_dir, calls, data)
if utils.file_exists(call_bed):
evalout = _evaluate_one(call["variantcaller"], svtype, size, call_bed,
truth, data)
writer.writerow([svtype, str_size, call["variantcaller"],
evalout["sensitivity"]["label"], evalout["precision"]["label"]])
for metric in ["sensitivity", "precision"]:
dfwriter.writerow([svtype, str_size, call["variantcaller"], metric,
evalout[metric]["val"], evalout[metric]["label"]])
return out_file, df_file
def _evaluate_multi(calls, truth_svtypes, work_dir, data):
base = os.path.join(work_dir, "%s-sv-validate" % (dd.get_sample_name(data)))
out_file = base + ".csv"
df_file = base + "-df.csv"
if any((not utils.file_uptodate(out_file, x["vrn_file"])
or not utils.file_uptodate(df_file, x["vrn_file"])) for x in calls):
with file_transaction(data, out_file) as tx_out_file:
with open(tx_out_file, "w") as out_handle:
with open(df_file, "w") as df_out_handle:
writer = csv.writer(out_handle)
dfwriter = csv.writer(df_out_handle)
writer.writerow(["svtype", "size", "caller", "sensitivity", "precision"])
dfwriter.writerow(["svtype", "size", "caller", "metric", "value", "label"])
for svtype, truth in truth_svtypes.items():
for size in EVENT_SIZES:
str_size = "%s-%s" % size
for call in calls:
call_bed = convert.to_bed(call, dd.get_sample_name(data), work_dir, calls, data)
if utils.file_exists(call_bed):
evalout = _evaluate_one(call["variantcaller"], svtype, size, call_bed,
truth, data)
writer.writerow([svtype, str_size, call["variantcaller"],
evalout["sensitivity"]["label"], evalout["precision"]["label"]])
for metric in ["sensitivity", "precision"]:
dfwriter.writerow([svtype, str_size, call["variantcaller"], metric,
evalout[metric]["val"], evalout[metric]["label"]])
return out_file, df_file
