示例#1
0
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)
示例#2
0
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)
示例#3
0
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)