def _get_prep_params(data):
"""Retrieve configuration parameters with defaults for preparing BAM files.
"""
recal_param = dd.get_recalibrate(data)
recal_param = "gatk" if recal_param is True else recal_param
realign_param = dd.get_realign(data)
realign_param = "gatk" if realign_param is True else realign_param
return {"recal": recal_param, "realign": realign_param}
def _get_prep_params(data):
"""Retrieve configuration parameters with defaults for preparing BAM files.
"""
recal_param = dd.get_recalibrate(data)
recal_param = "gatk" if recal_param is True else recal_param
realign_param = dd.get_realign(data)
realign_param = "gatk" if realign_param is True else realign_param
return {"recal": recal_param, "realign": realign_param}
def parallel_prep_region(samples, run_parallel):
"""Perform full pre-variant calling BAM prep work on regions.
"""
file_key = "work_bam"
split_fn = _split_by_regions("bamprep", "-prep.bam", file_key)
# identify samples that do not need preparation -- no recalibration or realignment
extras = []
torun = []
for data in [x[0] for x in samples]:
if data.get("work_bam"):
data["align_bam"] = data["work_bam"]
if (not dd.get_recalibrate(data) and not dd.get_realign(data) and not dd.get_variantcaller(data)):
extras.append([data])
elif not data.get(file_key):
extras.append([data])
else:
torun.append([data])
return extras + parallel_split_combine(torun, split_fn, run_parallel,
"piped_bamprep", _add_combine_info, file_key, ["config"])
