def _variant_filtration_indel(snp_file, ref_file, vrn_files, config):
"""Filter indel variant calls using GATK best practice recommendations.
"""
broad_runner = broad.runner_from_config(config)
filter_type = "INDEL"
variantcaller = config["algorithm"].get("variantcaller", "gatk")
if not config_utils.use_vqsr([config["algorithm"]]):
return vfilter.jexl_hard(broad_runner, snp_file, ref_file, filter_type,
["QD < 2.0", "ReadPosRankSum < -20.0", "FS > 200.0"])
else:
# also check if we've failed recal and needed to do strict filtering
filter_file = "{base}-filter{ext}.vcf".format(base=os.path.splitext(snp_file)[0], ext=filter_type)
if file_exists(filter_file):
config["algorithm"]["coverage_interval"] = "regional"
return _variant_filtration_indel(snp_file, ref_file, vrn_files, config)
assert "train_indels" in vrn_files, "Need indel training file specified"
params, recal_file, tranches_file = _shared_variant_filtration(
filter_type, snp_file, ref_file, vrn_files, variantcaller)
if not file_exists(recal_file):
with file_transaction(recal_file, tranches_file) as (tx_recal, tx_tranches):
params.extend(["--recal_file", tx_recal,
"--tranches_file", tx_tranches])
if LooseVersion(broad_runner.get_gatk_version()) >= LooseVersion("2.7"):
params.extend(["--numBadVariants", "3000"])
try:
broad_runner.new_resources("gatk-vqsr")
broad_runner.run_gatk(params, log_error=False)
except:
logger.info("VQSR failed due to lack of training data. Using hard filtering.")
config["algorithm"]["coverage_interval"] = "regional"
return _variant_filtration_indel(snp_file, ref_file, vrn_files, config)
return _apply_variant_recal(broad_runner, snp_file, ref_file, recal_file,
tranches_file, filter_type)
def _variant_filtration_snp(snp_file, ref_file, vrn_files, config):
"""Filter SNP variant calls using GATK best practice recommendations.
"""
broad_runner = broad.runner_from_config(config)
filter_type = "SNP"
variantcaller = config["algorithm"].get("variantcaller", "gatk")
filters = [
"QD < 2.0", "MQ < 40.0", "FS > 60.0", "MQRankSum < -12.5",
"ReadPosRankSum < -8.0"
]
# GATK Haplotype caller (v2.2) appears to have much larger HaplotypeScores
# resulting in excessive filtering, so avoid this metric
if variantcaller not in ["gatk-haplotype"]:
filters.append("HaplotypeScore > 13.0")
if not config_utils.use_vqsr([config["algorithm"]]):
return vfilter.jexl_hard(broad_runner, snp_file, ref_file, filter_type,
filters)
else:
# also check if we've failed recal and needed to do strict filtering
filter_file = "{base}-filter{ext}.vcf".format(
base=os.path.splitext(snp_file)[0], ext=filter_type)
if file_exists(filter_file):
config["algorithm"]["coverage_interval"] = "regional"
return _variant_filtration_snp(snp_file, ref_file, vrn_files,
config)
assert "train_hapmap" in vrn_files and "train_1000g_omni" in vrn_files, \
"Need HapMap and 1000 genomes training files"
params, recal_file, tranches_file = _shared_variant_filtration(
filter_type, snp_file, ref_file, vrn_files, variantcaller)
if not file_exists(recal_file):
with file_transaction(recal_file,
tranches_file) as (tx_recal, tx_tranches):
params.extend(
["--recal_file", tx_recal, "--tranches_file", tx_tranches])
try:
broad_runner.new_resources("gatk-vqsr")
broad_runner.run_gatk(params, log_error=False)
# Can fail to run if not enough values are present to train. Rerun with regional
# filtration approach instead
except:
logger.info(
"VQSR failed due to lack of training data. Using hard filtering."
)
config["algorithm"]["coverage_interval"] = "regional"
return _variant_filtration_snp(snp_file, ref_file,
vrn_files, config)
return _apply_variant_recal(broad_runner, snp_file, ref_file,
recal_file, tranches_file, filter_type)
def _variant_filtration_indel(snp_file, ref_file, vrn_files, config):
"""Filter indel variant calls using GATK best practice recommendations.
"""
broad_runner = broad.runner_from_config(config)
filter_type = "INDEL"
variantcaller = config["algorithm"].get("variantcaller", "gatk")
if not config_utils.use_vqsr([config["algorithm"]]):
return vfilter.jexl_hard(
broad_runner, snp_file, ref_file, filter_type,
["QD < 2.0", "ReadPosRankSum < -20.0", "FS > 200.0"])
else:
# also check if we've failed recal and needed to do strict filtering
filter_file = "{base}-filter{ext}.vcf".format(
base=os.path.splitext(snp_file)[0], ext=filter_type)
if file_exists(filter_file):
config["algorithm"]["coverage_interval"] = "regional"
return _variant_filtration_indel(snp_file, ref_file, vrn_files,
config)
assert "train_indels" in vrn_files, "Need indel training file specified"
params, recal_file, tranches_file = _shared_variant_filtration(
filter_type, snp_file, ref_file, vrn_files, variantcaller)
if not file_exists(recal_file):
with file_transaction(recal_file,
tranches_file) as (tx_recal, tx_tranches):
params.extend(
["--recal_file", tx_recal, "--tranches_file", tx_tranches])
if LooseVersion(broad_runner.get_gatk_version()
) >= LooseVersion("2.7"):
params.extend(["--numBadVariants", "3000"])
try:
broad_runner.new_resources("gatk-vqsr")
broad_runner.run_gatk(params, log_error=False)
except:
logger.info(
"VQSR failed due to lack of training data. Using hard filtering."
)
config["algorithm"]["coverage_interval"] = "regional"
return _variant_filtration_indel(snp_file, ref_file,
vrn_files, config)
return _apply_variant_recal(broad_runner, snp_file, ref_file,
recal_file, tranches_file, filter_type)
def _variant_filtration_snp(snp_file, ref_file, vrn_files, config):
"""Filter SNP variant calls using GATK best practice recommendations.
"""
broad_runner = broad.runner_from_config(config)
filter_type = "SNP"
variantcaller = config["algorithm"].get("variantcaller", "gatk")
filters = ["QD < 2.0", "MQ < 40.0", "FS > 60.0",
"MQRankSum < -12.5", "ReadPosRankSum < -8.0"]
# GATK Haplotype caller (v2.2) appears to have much larger HaplotypeScores
# resulting in excessive filtering, so avoid this metric
if variantcaller not in ["gatk-haplotype"]:
filters.append("HaplotypeScore > 13.0")
if not config_utils.use_vqsr([config["algorithm"]]):
return vfilter.jexl_hard(broad_runner, snp_file, ref_file, filter_type, filters)
else:
# also check if we've failed recal and needed to do strict filtering
filter_file = "{base}-filter{ext}.vcf".format(base=os.path.splitext(snp_file)[0], ext=filter_type)
if file_exists(filter_file):
config["algorithm"]["coverage_interval"] = "regional"
return _variant_filtration_snp(snp_file, ref_file, vrn_files, config)
assert "train_hapmap" in vrn_files and "train_1000g_omni" in vrn_files, \
"Need HapMap and 1000 genomes training files"
params, recal_file, tranches_file = _shared_variant_filtration(
filter_type, snp_file, ref_file, vrn_files, variantcaller)
if not file_exists(recal_file):
with file_transaction(recal_file, tranches_file) as (tx_recal, tx_tranches):
params.extend(["--recal_file", tx_recal,
"--tranches_file", tx_tranches])
try:
broad_runner.new_resources("gatk-vqsr")
broad_runner.run_gatk(params, log_error=False)
# Can fail to run if not enough values are present to train. Rerun with regional
# filtration approach instead
except:
logger.info("VQSR failed due to lack of training data. Using hard filtering.")
config["algorithm"]["coverage_interval"] = "regional"
return _variant_filtration_snp(snp_file, ref_file, vrn_files, config)
return _apply_variant_recal(broad_runner, snp_file, ref_file, recal_file,
tranches_file, filter_type)
