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 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 variant_filtration(call_file, ref_file, vrn_files, data, items):
"""Filter variant calls using Variant Quality Score Recalibration.
Newer GATK with Haplotype calling has combined SNP/indel filtering.
"""
caller = data["config"]["algorithm"].get("variantcaller")
if "gvcf" not in dd.get_tools_on(data):
call_file = ploidy.filter_vcf_by_sex(call_file, items)
if caller in ["freebayes"]:
return vfilter.freebayes(call_file, ref_file, vrn_files, data)
elif caller in ["platypus"]:
return vfilter.platypus(call_file, data)
elif caller in ["samtools"]:
return vfilter.samtools(call_file, data)
elif caller in ["gatk", "gatk-haplotype", "haplotyper"]:
if dd.get_analysis(data).lower().find("rna-seq") >= 0:
from bcbio.rnaseq import variation as rnaseq_variation
return rnaseq_variation.gatk_filter_rnaseq(call_file, data)
else:
return gatkfilter.run(call_file, ref_file, vrn_files, data)
# no additional filtration for callers that filter as part of call process
else:
return call_file
