def apply_recal(data):
"""Apply recalibration tables to the sorted aligned BAM, producing recalibrated BAM.
"""
orig_bam = dd.get_align_bam(data) or dd.get_work_bam(data)
had_work_bam = "work_bam" in data
if dd.get_recalibrate(data) in [True, "gatk"]:
logger.info("Applying BQSR recalibration with GATK: %s " %
str(dd.get_sample_name(data)))
data["work_bam"] = _gatk_apply_bqsr(data)
elif dd.get_recalibrate(data) == "sentieon":
logger.info("Applying BQSR recalibration with sentieon: %s " %
str(dd.get_sample_name(data)))
data["work_bam"] = sentieon.apply_bqsr(data)
elif dd.get_recalibrate(data):
raise NotImplementedError("Unsupported recalibration type: %s" %
(dd.get_recalibrate(data)))
# CWL does not have work/alignment BAM separation
if not had_work_bam and dd.get_work_bam(data):
data["align_bam"] = dd.get_work_bam(data)
if orig_bam != dd.get_work_bam(data) and orig_bam != dd.get_align_bam(
data):
utils.save_diskspace(orig_bam,
"BAM recalibrated to %s" % dd.get_work_bam(data),
data["config"])
return data
def prep_recal(data):
"""Do pre-BQSR recalibration, calculation of recalibration tables.
"""
if dd.get_recalibrate(data) in [True, "gatk"]:
logger.info("Prepare BQSR tables with GATK: %s " %
str(dd.get_sample_name(data)))
dbsnp_file = tz.get_in(("genome_resources", "variation", "dbsnp"),
data)
if not dbsnp_file:
logger.info(
"Skipping GATK BaseRecalibrator because no VCF file of known variants was found."
)
return data
broad_runner = broad.runner_from_config(data["config"])
data["prep_recal"] = _gatk_base_recalibrator(
broad_runner, dd.get_align_bam(data), dd.get_ref_file(data),
dd.get_platform(data), dbsnp_file, dd.get_variant_regions(data),
data)
elif dd.get_recalibrate(data) == "sentieon":
logger.info("Prepare BQSR tables with sentieon: %s " %
str(dd.get_sample_name(data)))
data["prep_recal"] = sentieon.bqsr_table(data)
elif dd.get_recalibrate(data):
raise NotImplementedError("Unsupported recalibration type: %s" %
(dd.get_recalibrate(data)))
return data
def prep_recal(data):
"""Perform a GATK recalibration of the sorted aligned BAM, producing recalibrated BAM.
"""
if dd.get_recalibrate(data) in [True, "gatk"]:
logger.info("Recalibrating %s with GATK" % str(dd.get_sample_name(data)))
ref_file = data["sam_ref"]
config = data["config"]
dbsnp_file = tz.get_in(("genome_resources", "variation", "dbsnp"), data)
if not dbsnp_file:
logger.info("Skipping GATK BaseRecalibrator because no VCF file of known variants was found.")
return [[data]]
platform = config["algorithm"].get("platform", "illumina")
broad_runner = broad.runner_from_path("picard", config)
broad_runner.run_fn("picard_index_ref", ref_file)
if config["algorithm"].get("mark_duplicates", True):
(dup_align_bam, _) = broad_runner.run_fn("picard_mark_duplicates", data["work_bam"])
else:
dup_align_bam = data["work_bam"]
bam.index(dup_align_bam, config)
intervals = config["algorithm"].get("variant_regions", None)
data["work_bam"] = dup_align_bam
broad_runner = broad.runner_from_config(config)
data["prep_recal"] = _gatk_base_recalibrator(broad_runner, dup_align_bam, ref_file,
platform, dbsnp_file, intervals, data)
return [[data]]
def prep_recal(data):
"""Perform a GATK recalibration of the sorted aligned BAM, producing recalibrated BAM.
"""
if dd.get_recalibrate(data) in [True, "gatk"]:
logger.info("Recalibrating %s with GATK" %
str(dd.get_sample_name(data)))
ref_file = data["sam_ref"]
config = data["config"]
dbsnp_file = tz.get_in(("genome_resources", "variation", "dbsnp"),
data)
if not dbsnp_file:
logger.info(
"Skipping GATK BaseRecalibrator because no VCF file of known variants was found."
)
return [[data]]
platform = config["algorithm"].get("platform", "illumina")
broad_runner = broad.runner_from_path("picard", config)
broad_runner.run_fn("picard_index_ref", ref_file)
if config["algorithm"].get("mark_duplicates", True):
(dup_align_bam, _) = broad_runner.run_fn("picard_mark_duplicates",
data["work_bam"])
else:
dup_align_bam = data["work_bam"]
bam.index(dup_align_bam, config)
intervals = config["algorithm"].get("variant_regions", None)
data["work_bam"] = dup_align_bam
broad_runner = broad.runner_from_config(config)
data["prep_recal"] = _gatk_base_recalibrator(broad_runner,
dup_align_bam, ref_file,
platform, dbsnp_file,
intervals, data)
return [[data]]
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 prep_recal(data):
"""Do pre-BQSR recalibration, calculation of recalibration tables.
"""
if dd.get_recalibrate(data) in [True, "gatk"]:
logger.info("Prepare BQSR tables with GATK: %s " % str(dd.get_sample_name(data)))
dbsnp_file = tz.get_in(("genome_resources", "variation", "dbsnp"), data)
if not dbsnp_file:
logger.info("Skipping GATK BaseRecalibrator because no VCF file of known variants was found.")
return data
broad_runner = broad.runner_from_config(data["config"])
data["prep_recal"] = _gatk_base_recalibrator(broad_runner, dd.get_align_bam(data),
dd.get_ref_file(data), dd.get_platform(data),
dbsnp_file, dd.get_variant_regions(data), data)
elif dd.get_recalibrate(data) == "sentieon":
logger.info("Prepare BQSR tables with sentieon: %s " % str(dd.get_sample_name(data)))
data["prep_recal"] = sentieon.bqsr_table(data)
elif dd.get_recalibrate(data):
raise NotImplementedError("Unsupported recalibration type: %s" % (dd.get_recalibrate(data)))
return data
def apply_recal(data):
"""Apply recalibration tables to the sorted aligned BAM, producing recalibrated BAM.
"""
orig_bam = dd.get_align_bam(data) or dd.get_work_bam(data)
had_work_bam = "work_bam" in data
if dd.get_recalibrate(data) in [True, "gatk"]:
if data.get("prep_recal"):
logger.info("Applying BQSR recalibration with GATK: %s " % str(dd.get_sample_name(data)))
data["work_bam"] = _gatk_apply_bqsr(data)
elif dd.get_recalibrate(data) == "sentieon":
if data.get("prep_recal"):
logger.info("Applying BQSR recalibration with sentieon: %s " % str(dd.get_sample_name(data)))
data["work_bam"] = sentieon.apply_bqsr(data)
elif dd.get_recalibrate(data):
raise NotImplementedError("Unsupported recalibration type: %s" % (dd.get_recalibrate(data)))
# CWL does not have work/alignment BAM separation
if not had_work_bam and dd.get_work_bam(data):
data["align_bam"] = dd.get_work_bam(data)
if orig_bam != dd.get_work_bam(data) and orig_bam != dd.get_align_bam(data):
utils.save_diskspace(orig_bam, "BAM recalibrated to %s" % dd.get_work_bam(data), data["config"])
return data
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"])
