def rnaseq_vardict_variant_calling(data):
sample = dd.get_sample_name(data)
variation_dir = os.path.join(dd.get_work_dir(data), "variation")
safe_makedir(variation_dir)
out_file = os.path.join(variation_dir, sample + "-vardict.vcf.gz")
if file_exists(out_file):
data = dd.set_vrn_file(data, out_file)
return data
vardict_cmd = vardict.get_vardict_command(data)
strandbias = "teststrandbias.R"
var2vcf = "var2vcf_valid.pl"
vcfstreamsort = config_utils.get_program("vcfstreamsort", data)
compress_cmd = "| bgzip -c"
freq = float(dd.get_min_allele_fraction(data, 20) / 100.0)
var2vcf_opts = "-v 50"
fix_ambig = vcfutils.fix_ambiguous_cl()
remove_dup = vcfutils.remove_dup_cl()
r_setup = ("unset R_HOME && export PATH=%s:$PATH && "
% os.path.dirname(Rscript_cmd()))
ref_file = dd.get_ref_file(data)
bamfile = dd.get_work_bam(data)
bed_file = gtf.gtf_to_bed(dd.get_gtf_file(data))
opts = " -c 1 -S 2 -E 3 -g 4 "
with file_transaction(out_file) as tx_out_file:
jvm_opts = vardict._get_jvm_opts(data, tx_out_file)
cmd = ("{r_setup}{jvm_opts}{vardict_cmd} -G {ref_file} -f {freq} "
"-N {sample} -b {bamfile} {opts} {bed_file} "
"| {strandbias}"
"| {var2vcf} -N {sample} -E -f {freq} {var2vcf_opts} "
"| {fix_ambig} | {remove_dup} | {vcfstreamsort} {compress_cmd} "
"> {tx_out_file}")
message = "Calling RNA-seq variants with VarDict"
do.run(cmd.format(**locals()), message)
data = dd.set_vrn_file(data, out_file)
return data
def gatk_rnaseq_calling(data):
"""
use GATK to perform variant calling on RNA-seq data
"""
broad_runner = broad.runner_from_config(dd.get_config(data))
ref_file = dd.get_ref_file(data)
split_bam = dd.get_split_bam(data)
out_file = os.path.splitext(split_bam)[0] + ".gvcf"
num_cores = dd.get_num_cores(data)
if file_exists(out_file):
data = dd.set_vrn_file(data, out_file)
return data
with file_transaction(out_file) as tx_out_file:
params = ["-T", "HaplotypeCaller",
"-R", ref_file,
"-I", split_bam,
"-o", tx_out_file,
"-nct", str(num_cores),
"--emitRefConfidence", "GVCF",
"--variant_index_type", "LINEAR",
"--variant_index_parameter", "128000",
"-dontUseSoftClippedBases",
"-stand_call_conf", "20.0",
"-stand_emit_conf", "20.0"]
broad_runner.run_gatk(params)
data = dd.set_vrn_file(data, out_file)
return data
def run_rnaseq_variant_calling(data):
"""
run RNA-seq variant calling, variation file is stored in `vrn_file`
in the datadict
"""
variantcaller = dd.get_variantcaller(data)
if isinstance(variantcaller, list) and len(variantcaller) > 1:
logger.error("Only one variantcaller can be run for RNA-seq at "
"this time. Post an issue here "
"(https://github.com/bcbio/bcbio-nextgen/issues) "
"if this is something you need to do.")
sys.exit(1)
if variantcaller:
if "gatk-haplotype" in variantcaller:
data = variation.rnaseq_gatk_variant_calling(data)
if vardict.get_vardict_command(data):
data = variation.rnaseq_vardict_variant_calling(data)
if dd.get_vrn_file(data):
ann_file = vcfanno.run_vcfanno(dd.get_vrn_file(data), ["rnaedit"],
data)
if ann_file:
data = dd.set_vrn_file(data, ann_file)
ann_file = population.run_vcfanno(dd.get_vrn_file(data), data,
population.do_db_build([data]))
if ann_file:
data = dd.set_vrn_file(data, ann_file)
return [[data]]
def run_rnaseq_ann_filter(data):
"""Run RNA-seq annotation and filtering.
"""
ann_file = vcfanno.run_vcfanno(dd.get_vrn_file(data), ["rnaedit"], data)
if ann_file:
dd.set_vrn_file(data, ann_file)
filter_file = variation.gatk_filter_rnaseq(dd.get_vrn_file(data), data)
dd.set_vrn_file(data, filter_file)
return [[data]]
def run_rnaseq_ann_filter(data):
"""Run RNA-seq annotation and filtering.
"""
data = to_single_data(data)
if dd.get_vrn_file(data):
ann_file = population.run_vcfanno(dd.get_vrn_file(data), data)
if ann_file:
data = dd.set_vrn_file(data, ann_file)
variantcaller = dd.get_variantcaller(data)
if variantcaller and ("gatk-haplotype" in variantcaller):
filter_file = variation.gatk_filter_rnaseq(dd.get_vrn_file(data), data)
data = dd.set_vrn_file(data, filter_file)
return [[data]]
def gatk_rnaseq_calling(data):
"""Use GATK to perform gVCF variant calling on RNA-seq data
"""
from bcbio.bam import callable
data = utils.deepish_copy(data)
tools_on = dd.get_tools_on(data)
if not tools_on:
tools_on = []
tools_on.append("gvcf")
data = dd.set_tools_on(data, tools_on)
data = dd.set_jointcaller(data, ["%s-joint" % v for v in dd.get_variantcaller(data)])
out_dir = utils.safe_makedir(os.path.join(dd.get_work_dir(data),
"variation", "rnaseq", "gatk-haplotype"))
data = _setup_variant_regions(data, out_dir)
out_file = os.path.join(out_dir, "%s-gatk-haplotype.vcf.gz" % dd.get_sample_name(data))
if not utils.file_exists(out_file):
region_files = []
regions = []
for cur_region in callable.get_split_regions(dd.get_variant_regions(data), data):
str_region = "_".join([str(x) for x in cur_region])
region_file = os.path.join(utils.safe_makedir(os.path.join(dd.get_work_dir(data),
"variation", "rnaseq", "gatk-haplotype",
"regions")),
"%s-%s-gatk-haplotype.vcf.gz" % (dd.get_sample_name(data), str_region))
region_file = gatk.haplotype_caller([dd.get_split_bam(data)], [data], dd.get_ref_file(data), {},
region=cur_region, out_file=region_file)
region_files.append(region_file)
regions.append(cur_region)
out_file = vcfutils.concat_variant_files(region_files, out_file, regions,
dd.get_ref_file(data), data["config"])
return dd.set_vrn_file(data, out_file)
def gatk_rnaseq_calling(data):
"""Use GATK to perform gVCF variant calling on RNA-seq data
"""
from bcbio.bam import callable
data = utils.deepish_copy(data)
tools_on = dd.get_tools_on(data)
if not tools_on:
tools_on = []
tools_on.append("gvcf")
data = dd.set_tools_on(data, tools_on)
data = dd.set_jointcaller(data, ["%s-joint" % v for v in dd.get_variantcaller(data)])
out_dir = utils.safe_makedir(os.path.join(dd.get_work_dir(data),
"variation", "rnaseq", "gatk-haplotype"))
data = _setup_variant_regions(data, out_dir)
out_file = os.path.join(out_dir, "%s-gatk-haplotype.vcf.gz" % dd.get_sample_name(data))
if not utils.file_exists(out_file):
region_files = []
regions = []
for cur_region in callable.get_split_regions(dd.get_variant_regions(data), data):
str_region = "_".join([str(x) for x in cur_region])
region_file = os.path.join(utils.safe_makedir(os.path.join(dd.get_work_dir(data),
"variation", "rnaseq", "gatk-haplotype",
"regions")),
"%s-%s-gatk-haplotype.vcf.gz" % (dd.get_sample_name(data), str_region))
region_file = gatk.haplotype_caller([dd.get_split_bam(data)], [data], dd.get_ref_file(data), {},
region=cur_region, out_file=region_file)
region_files.append(region_file)
regions.append(cur_region)
out_file = vcfutils.concat_variant_files(region_files, out_file, regions,
dd.get_ref_file(data), data["config"])
return dd.set_vrn_file(data, out_file)
def rnaseq_vardict_variant_calling(data):
sample = dd.get_sample_name(data)
out_dir = utils.safe_makedir(
os.path.join(dd.get_work_dir(data), "variation", "rnaseq", "vardict"))
out_file = os.path.join(out_dir, sample + "-vardict.vcf.gz")
if file_exists(out_file):
data = dd.set_vrn_file(data, out_file)
return data
vardict_cmd = vardict.get_vardict_command(data)
strandbias = "teststrandbias.R"
var2vcf = "var2vcf_valid.pl"
vcfstreamsort = config_utils.get_program("vcfstreamsort", data)
compress_cmd = "| bgzip -c"
freq = float(dd.get_min_allele_fraction(data, 20) / 100.0)
var2vcf_opts = "-v 50"
fix_ambig = vcfutils.fix_ambiguous_cl()
remove_dup = vcfutils.remove_dup_cl()
r_setup = get_R_exports()
ref_file = dd.get_ref_file(data)
bamfile = dd.get_work_bam(data)
data = _setup_variant_regions(data, out_dir)
opts, _ = vardict._vardict_options_from_config(
[data],
data["config"],
out_file,
dd.get_variant_regions(data),
is_rnaseq=True)
cores = dd.get_num_cores(data)
if cores and cores > 1:
opts += " -th %s" % str(cores)
with file_transaction(data, out_file) as tx_out_file:
jvm_opts = vardict._get_jvm_opts(data, tx_out_file)
cmd = ("{r_setup} && {jvm_opts}{vardict_cmd} -G {ref_file} -f {freq} "
"-N {sample} -b {bamfile} {opts} "
"| {strandbias}"
"| {var2vcf} -N {sample} -E -f {freq} {var2vcf_opts} "
"| {fix_ambig} | {remove_dup} | {vcfstreamsort} {compress_cmd} "
"> {tx_out_file}")
message = "Calling RNA-seq variants with VarDict"
do.run(cmd.format(**locals()), message)
out_file = vcfutils.bgzip_and_index(out_file, data["config"])
data = dd.set_vrn_file(data, out_file)
return data
def run_rnaseq_ann_filter(data):
"""Run RNA-seq annotation and filtering.
"""
data = to_single_data(data)
if dd.get_vrn_file(data):
eff_file = effects.add_to_vcf(dd.get_vrn_file(data), data)[0]
if eff_file:
data = dd.set_vrn_file(data, eff_file)
ann_file = population.run_vcfanno(dd.get_vrn_file(data), data)
if ann_file:
data = dd.set_vrn_file(data, ann_file)
variantcaller = dd.get_variantcaller(data)
if variantcaller and ("gatk-haplotype" in variantcaller):
filter_file = variation.gatk_filter_rnaseq(dd.get_vrn_file(data), data)
data = dd.set_vrn_file(data, filter_file)
# remove variants close to splice junctions
vrn_file = dd.get_vrn_file(data)
vrn_file = variation.filter_junction_variants(vrn_file, data)
data = dd.set_vrn_file(data, vrn_file)
return [[data]]
def run_rnaseq_ann_filter(data):
"""Run RNA-seq annotation and filtering.
"""
data = to_single_data(data)
if dd.get_vrn_file(data):
eff_file = effects.add_to_vcf(dd.get_vrn_file(data), data)[0]
if eff_file:
data = dd.set_vrn_file(data, eff_file)
ann_file = population.run_vcfanno(dd.get_vrn_file(data), data)
if ann_file:
data = dd.set_vrn_file(data, ann_file)
variantcaller = dd.get_variantcaller(data)
if variantcaller and ("gatk-haplotype" in variantcaller):
filter_file = variation.gatk_filter_rnaseq(dd.get_vrn_file(data), data)
data = dd.set_vrn_file(data, filter_file)
# remove variants close to splice junctions
vrn_file = dd.get_vrn_file(data)
vrn_file = variation.filter_junction_variants(vrn_file, data)
data = dd.set_vrn_file(data, vrn_file)
return [[data]]
def rnaseq_vardict_variant_calling(data):
sample = dd.get_sample_name(data)
out_dir = utils.safe_makedir(os.path.join(dd.get_work_dir(data),
"variation", "rnaseq", "vardict"))
out_file = os.path.join(out_dir, sample + "-vardict.vcf.gz")
if file_exists(out_file):
data = dd.set_vrn_file(data, out_file)
return data
vardict_cmd = vardict.get_vardict_command(data)
strandbias = "teststrandbias.R"
var2vcf = "var2vcf_valid.pl"
vcfstreamsort = config_utils.get_program("vcfstreamsort", data)
compress_cmd = "| bgzip -c"
freq = float(dd.get_min_allele_fraction(data, 20) / 100.0)
var2vcf_opts = "-v 50"
fix_ambig = vcfutils.fix_ambiguous_cl()
remove_dup = vcfutils.remove_dup_cl()
r_setup = get_R_exports()
ref_file = dd.get_ref_file(data)
bamfile = dd.get_work_bam(data)
data = _setup_variant_regions(data, out_dir)
opts, _ = vardict._vardict_options_from_config([data], data["config"], out_file, dd.get_variant_regions(data),
is_rnaseq=True)
cores = dd.get_num_cores(data)
if cores and cores > 1:
opts += " -th %s" % str(cores)
with file_transaction(data, out_file) as tx_out_file:
jvm_opts = vardict._get_jvm_opts(data, tx_out_file)
cmd = ("{r_setup} && {jvm_opts}{vardict_cmd} -G {ref_file} -f {freq} "
"-N {sample} -b {bamfile} {opts} "
"| {strandbias}"
"| {var2vcf} -N {sample} -E -f {freq} {var2vcf_opts} "
"| {fix_ambig} | {remove_dup} | {vcfstreamsort} {compress_cmd} "
"> {tx_out_file}")
message = "Calling RNA-seq variants with VarDict"
do.run(cmd.format(**locals()), message)
out_file = vcfutils.bgzip_and_index(out_file, data["config"])
data = dd.set_vrn_file(data, out_file)
return data
def gatk_rnaseq_calling(data):
"""
use GATK to perform variant calling on RNA-seq data
"""
broad_runner = broad.runner_from_config(dd.get_config(data))
ref_file = dd.get_ref_file(data)
split_bam = dd.get_split_bam(data)
out_file = os.path.splitext(split_bam)[0] + ".vcf"
if file_exists(out_file):
data = dd.set_vrn_file(data, out_file)
return data
with file_transaction(out_file) as tx_out_file:
params = ["-T", "HaplotypeCaller",
"-R", ref_file,
"-I", split_bam,
"-o", tx_out_file,
"-dontUseSoftClippedBases",
"-stand_call_conf", "20.0",
"-stand_emit_conf", "20.0"]
broad_runner.run_gatk(params)
data = dd.set_vrn_file(data, out_file)
return data
def gatk_rnaseq_calling(data):
"""Use GATK to perform gVCF variant calling on RNA-seq data
"""
data = utils.deepish_copy(data)
tools_on = dd.get_tools_on(data)
if not tools_on:
tools_on = []
tools_on.append("gvcf")
data = dd.set_tools_on(data, tools_on)
data = dd.set_jointcaller(data, ["%s-joint" % v for v in dd.get_variantcaller(data)])
out_file = os.path.join(utils.safe_makedir(os.path.join("variation", "rnaseq", "gatk-haplotype")),
"%s-gatk-haplotype.vcf.gz" % dd.get_sample_name(data))
out_file = gatk.haplotype_caller([dd.get_split_bam(data)], [data], dd.get_ref_file(data), {},
out_file=out_file)
return dd.set_vrn_file(data, out_file)
def run_rnaseq_variant_calling(data):
"""
run RNA-seq variant calling, variation file is stored in `vrn_file`
in the datadict
"""
variantcaller = dd.get_variantcaller(data)
if isinstance(variantcaller, list) and len(variantcaller) > 1:
logger.error("Only one variantcaller can be run for RNA-seq at "
"this time. Post an issue here "
"(https://github.com/chapmanb/bcbio-nextgen/issues) "
"if this is something you need to do.")
sys.exit(1)
if variantcaller and "gatk" in variantcaller:
data = variation.rnaseq_gatk_variant_calling(data)
if vardict.get_vardict_command(data):
data = variation.rnaseq_vardict_variant_calling(data)
if dd.get_vrn_file(data):
vrn_file = vcfanno.run_vcfanno(dd.get_vrn_file(data), ["rnaedit"], data)
data = dd.set_vrn_file(data, vrn_file)
return [[data]]
def run_rnaseq_variant_calling(data):
"""
run RNA-seq variant calling, variation file is stored in `vrn_file`
in the datadict
"""
variantcaller = dd.get_variantcaller(data)
if isinstance(variantcaller, list) and len(variantcaller) > 1:
logger.error("Only one variantcaller can be run for RNA-seq at "
"this time. Post an issue here "
"(https://github.com/chapmanb/bcbio-nextgen/issues) "
"if this is something you need to do.")
sys.exit(1)
if variantcaller and "gatk" in variantcaller:
data = variation.rnaseq_gatk_variant_calling(data)
if vardict.get_vardict_command(data):
data = variation.rnaseq_vardict_variant_calling(data)
# annotate RNA-editing events with vcfanno
if dd.get_vrn_file(data):
vrn_file = vcfanno.run_vcfanno(dd.get_vrn_file(data), "rnaedit", data)
data = dd.set_vrn_file(data, vrn_file)
return [[data]]
