예제 #1
0
def _run_coverage_qc(bam_file, data, out_dir):
    """Run coverage QC analysis"""
    priority = cov.priority_coverage(data, out_dir)
    cov.priority_total_coverage(data, out_dir)
    coverage = cov.coverage(data, out_dir)
    problem_regions = dd.get_problem_region_dir(data)
    annotated = None
    if problem_regions and priority:
        annotated = cov.decorate_problem_regions(priority, problem_regions)
    return None
예제 #2
0
def _run_coverage_qc(bam_file, data, out_dir):
    """Run coverage QC analysis"""
    priority = cov.priority_coverage(data, out_dir)
    cov.priority_total_coverage(data, out_dir)
    coverage = cov.coverage(data, out_dir)
    problem_regions = dd.get_problem_region_dir(data)
    annotated = None
    if problem_regions and priority:
        annotated = cov.decorate_problem_regions(priority, problem_regions)
    return None
예제 #3
0
def _run_coverage_qc(bam_file, data, out_dir):
    """Run coverage QC analysis"""
    out = dict()

    total_reads = sambamba.number_of_reads(data, bam_file)
    out['Total_reads'] = total_reads
    mapped = sambamba.number_of_mapped_reads(data, bam_file)
    out['Mapped_reads'] = mapped
    if total_reads:
        out['Mapped_reads_pct'] = 100.0 * mapped / total_reads
    if mapped:
        mapped_unique = sambamba.number_of_mapped_reads(data, bam_file, keep_dups=False)
        out['Mapped_unique_reads'] = mapped
        mapped_dups = mapped - mapped_unique
        out['Duplicates'] = mapped_dups
        out['Duplicates_pct'] = 100.0 * mapped_dups / mapped

        if dd.get_coverage(data):
            cov_bed_file = clean_file(dd.get_coverage(data), data, prefix="cov-", simple=True)
            merged_bed_file = bedutils.merge_overlaps(cov_bed_file, data)
            target_name = "coverage"
        else:
            merged_bed_file = dd.get_variant_regions_merged(data)
            target_name = "variant_regions"

        ontarget = sambamba.number_mapped_reads_on_target(
            data, merged_bed_file, bam_file, keep_dups=False, target_name=target_name)
        if mapped_unique:
            out["Ontarget_unique_reads"] = ontarget
            out["Ontarget_pct"] = 100.0 * ontarget / mapped_unique
            out['Offtarget_pct'] = 100.0 * (mapped_unique - ontarget) / mapped_unique
            padded_bed_file = bedutils.get_padded_bed_file(merged_bed_file, 200, data)
            ontarget_padded = sambamba.number_mapped_reads_on_target(
                data, padded_bed_file, bam_file, keep_dups=False, target_name=target_name + "_padded")
            out["Ontarget_padded_pct"] = 100.0 * ontarget_padded / mapped_unique
        if total_reads:
            out['Usable_pct'] = 100.0 * ontarget / total_reads

        avg_coverage = get_average_coverage(data, bam_file, merged_bed_file, target_name)
        out['Avg_coverage'] = avg_coverage

    priority = cov.priority_coverage(data, out_dir)
    cov.priority_total_coverage(data, out_dir)
    region_coverage_file = cov.coverage_region_detailed_stats(data, out_dir)
    # Re-enable with annotations from internally installed
    # problem region directory
    # if priority:
    #    annotated = cov.decorate_problem_regions(priority, problem_regions)

    return out
예제 #4
0
def _run_coverage_qc(bam_file, data, out_dir):
    """Run coverage QC analysis"""
    out = dict()
    if dd.get_coverage(data):
        bed_file = bedutils.merge_overlaps(dd.get_coverage(data), data)
        target_name = "coverage"
    elif dd.get_variant_regions_merged(data):
        bed_file = dd.get_variant_regions_merged(data)
        target_name = "variant_regions"
    else:
        bed_file = None
        target_name = "wgs"

    bed_file = clean_file(bed_file, data, prefix="cov-", simple=True)
    offtarget_stats_file = calculate_offtarget_stats(bam_file, data, bed_file,
                                                     target_name)
    if offtarget_stats_file and utils.file_exists(offtarget_stats_file):
        with open(offtarget_stats_file) as in_handle:
            stats = yaml.safe_load(in_handle)
        offtarget = stats.get('offtarget')
        mapped_unique = stats['mapped_unique']
        if offtarget and mapped_unique:
            out['offtarget_rate'] = 1.0 * offtarget / mapped_unique
        mapped = stats['mapped']
        if mapped:
            out['Duplicates'] = mapped - mapped_unique
            out['Duplicates_pct'] = 1.0 * (mapped - mapped_unique) / mapped
        total_reads = stats['total_reads']
        if total_reads:
            out['usable_rate'] = 1.0 * (mapped_unique -
                                        offtarget) / total_reads

    avg_coverage = get_average_coverage(data, bam_file, bed_file, target_name)
    out['avg_coverage'] = avg_coverage

    priority = cov.priority_coverage(data, out_dir)
    cov.priority_total_coverage(data, out_dir)
    region_coverage_file = cov.coverage_region_detailed_stats(data, out_dir)
    # Re-enable with annotations from internally installed
    # problem region directory
    # if priority:
    #    annotated = cov.decorate_problem_regions(priority, problem_regions)

    return out
예제 #5
0
def coverage_report(data):
    """
    Run heavy coverage and variants process in parallel
    """
    data = cov.coverage(data)
    data = cov.variants(data)
    data = cov.priority_coverage(data)
    data = cov.priority_total_coverage(data)
    problem_regions = dd.get_problem_region_dir(data)
    name = dd.get_sample_name(data)
    if "coverage" in data:
        coverage = data['coverage']
        annotated = None
        if problem_regions and coverage:
             annotated = cov.decorate_problem_regions(coverage, problem_regions)
        data['coverage'] = {'all': coverage, 'problems': annotated}

    return [[data]]
예제 #6
0
def _run_coverage_qc(bam_file, data, out_dir):
    """Run coverage QC analysis"""
    out = dict()

    total_reads = sambamba.number_of_reads(data, bam_file)
    out['Total_reads'] = total_reads
    mapped = sambamba.number_of_mapped_reads(data, bam_file)
    out['Mapped_reads'] = mapped
    if total_reads:
        out['Mapped_reads_pct'] = 100.0 * mapped / total_reads
    if mapped:
        mapped_unique = sambamba.number_of_mapped_reads(data,
                                                        bam_file,
                                                        keep_dups=False)
        out['Mapped_unique_reads'] = mapped
        mapped_dups = mapped - mapped_unique
        out['Duplicates'] = mapped_dups
        out['Duplicates_pct'] = 100.0 * mapped_dups / mapped

        if dd.get_coverage(data):
            cov_bed_file = clean_file(dd.get_coverage(data),
                                      data,
                                      prefix="cov-",
                                      simple=True)
            merged_bed_file = bedutils.merge_overlaps(cov_bed_file, data)
            target_name = "coverage"
        else:
            merged_bed_file = dd.get_variant_regions_merged(data)
            target_name = "variant_regions"

        ontarget = sambamba.number_mapped_reads_on_target(
            data,
            merged_bed_file,
            bam_file,
            keep_dups=False,
            target_name=target_name)
        if mapped_unique:
            out["Ontarget_unique_reads"] = ontarget
            out["Ontarget_pct"] = 100.0 * ontarget / mapped_unique
            out['Offtarget_pct'] = 100.0 * (mapped_unique -
                                            ontarget) / mapped_unique
            padded_bed_file = bedutils.get_padded_bed_file(
                merged_bed_file, 200, data)
            ontarget_padded = sambamba.number_mapped_reads_on_target(
                data,
                padded_bed_file,
                bam_file,
                keep_dups=False,
                target_name=target_name + "_padded")
            out["Ontarget_padded_pct"] = 100.0 * ontarget_padded / mapped_unique
        if total_reads:
            out['Usable_pct'] = 100.0 * ontarget / total_reads

        avg_coverage = get_average_coverage(data, bam_file, merged_bed_file,
                                            target_name)
        out['Avg_coverage'] = avg_coverage

    priority = cov.priority_coverage(data, out_dir)
    cov.priority_total_coverage(data, out_dir)
    region_coverage_file = cov.coverage_region_detailed_stats(data, out_dir)
    # Re-enable with annotations from internally installed
    # problem region directory
    # if priority:
    #    annotated = cov.decorate_problem_regions(priority, problem_regions)

    return out
예제 #7
0
def _run_coverage_qc(bam_file, data, out_dir):
    """Run coverage QC analysis"""
    priority = cov.priority_coverage(data, out_dir)
    cov.priority_total_coverage(data, out_dir)
    coverage = cov.coverage(data, out_dir)