def gatk_filter_rnaseq(vrn_file, data):
"""
this incorporates filters listed here, dropping clusters of variants
within a 35 nucleotide window, high fischer strand values and low
quality by depth
https://software.broadinstitute.org/gatk/guide/article?id=3891
java -jar GenomeAnalysisTK.jar -T VariantFiltration -R hg_19.fasta -V
input.vcf -window 35 -cluster 3 -filterName FS -filter "FS > 30.0"
-filterName QD -filter "QD < 2.0" -o output.vcf
"""
out_file = "%s-filter%s" % utils.splitext_plus(vrn_file)
if not file_exists(out_file):
ref_file = dd.get_ref_file(data)
with file_transaction(data, out_file) as tx_out_file:
params = ["VariantFiltration",
"-R", ref_file,
"-V", vrn_file,
"--cluster-window-size", "35",
"--cluster-size", "3",
"--filter-expression", "'FS > 30.0'",
"--filter-name", "FS",
"--filter-expression", "'QD < 2.0'",
"--filter-name", "QD",
"--output", tx_out_file]
# Use GATK4 for filtering, tools_off is for variant calling
config = utils.deepish_copy(dd.get_config(data))
if "gatk4" in dd.get_tools_off({"config": config}):
config["algorithm"]["tools_off"].remove("gatk4")
jvm_opts = broad.get_gatk_opts(config, os.path.dirname(tx_out_file))
do.run(broad.gatk_cmd("gatk", jvm_opts, params, config), "Filter RNA-seq variants.")
return out_file
def gatk_filter_rnaseq(vrn_file, data):
"""
this incorporates filters listed here, dropping clusters of variants
within a 35 nucleotide window, high fischer strand values and low
quality by depth
https://software.broadinstitute.org/gatk/guide/article?id=3891
java -jar GenomeAnalysisTK.jar -T VariantFiltration -R hg_19.fasta -V
input.vcf -window 35 -cluster 3 -filterName FS -filter "FS > 30.0"
-filterName QD -filter "QD < 2.0" -o output.vcf
"""
out_file = "%s-filter%s" % utils.splitext_plus(vrn_file)
if not file_exists(out_file):
ref_file = dd.get_ref_file(data)
with file_transaction(data, out_file) as tx_out_file:
params = [
"VariantFiltration", "-R", ref_file, "-V", vrn_file,
"--cluster-window-size", "35", "--cluster-size", "3",
"--filter-expression", "'FS > 30.0'", "--filter-name", "FS",
"--filter-expression", "'QD < 2.0'", "--filter-name", "QD",
"--output", tx_out_file
]
jvm_opts = broad.get_gatk_opts(dd.get_config(data),
os.path.dirname(tx_out_file))
do.run(broad.gatk_cmd("gatk", jvm_opts, params),
"Filter RNA-seq variants.")
return out_file
def _filter_paired(tumor, normal, out_file, reference, data):
"""filter paired vcf file with GATK
:param tumor: (str) sample name for tumor
:param normal: (str) sample name for normal
:param out_file: (str) final vcf file
:param reference: (str) genome in fasta format
:param data: (dict) information from yaml file(items[0])
:returns: (str) name of final vcf file
"""
in_file = utils.splitext_plus(out_file)[0] + "-tmp.vcf"
shutil.move(out_file, in_file)
config = data["config"]
with file_transaction(data, out_file) as tx_out_file:
params = ["-T", "SomaticPindelFilter", "-V", in_file, "-o",
tx_out_file, "-TID", tumor, "-NID", normal, "-R", reference]
jvm_opts = broad.get_gatk_opts(config)
do.run(broad.gatk_cmd("gatk-framework", jvm_opts, params), "Filter pindel variants")
return out_file
def _filter_bad_reads(in_bam, ref_file, data):
"""Use GATK filter to remove problem reads which choke GATK and Picard.
"""
bam.index(in_bam, data["config"])
out_file = "%s-gatkfilter.bam" % os.path.splitext(in_bam)[0]
if not utils.file_exists(out_file):
with tx_tmpdir(data) as tmp_dir:
with file_transaction(data, out_file) as tx_out_file:
params = [
("FixMisencodedBaseQualityReads" if dd.get_quality_format(
data, "").lower() == "illumina" else "PrintReads"),
"-R", ref_file, "-I", in_bam, "-O", tx_out_file, "-RF",
"MatchingBasesAndQualsReadFilter", "-RF",
"SeqIsStoredReadFilter", "-RF", "CigarContainsNoNOperator"
]
jvm_opts = broad.get_gatk_opts(data["config"], tmp_dir)
do.run(broad.gatk_cmd("gatk", jvm_opts, params),
"Filter problem reads")
bam.index(out_file, data["config"])
return out_file
def _filter_bad_reads(in_bam, ref_file, data):
"""Use GATK filter to remove problem reads which choke GATK and Picard.
"""
bam.index(in_bam, data["config"])
out_file = "%s-gatkfilter.bam" % os.path.splitext(in_bam)[0]
if not utils.file_exists(out_file):
with tx_tmpdir(data) as tmp_dir:
with file_transaction(data, out_file) as tx_out_file:
params = [("FixMisencodedBaseQualityReads"
if dd.get_quality_format(data, "").lower() == "illumina"
else "PrintReads"),
"-R", ref_file,
"-I", in_bam,
"-O", tx_out_file,
"-RF", "MatchingBasesAndQualsReadFilter",
"-RF", "SeqIsStoredReadFilter",
"-RF", "CigarContainsNoNOperator"]
jvm_opts = broad.get_gatk_opts(data["config"], tmp_dir)
do.run(broad.gatk_cmd("gatk", jvm_opts, params), "Filter problem reads")
bam.index(out_file, data["config"])
return out_file