def umi_consensus(data):
"""Convert UMI grouped reads into fastq pair for re-alignment.
"""
align_bam = dd.get_work_bam(data)
umi_method, umi_tag = _check_umi_type(align_bam)
f1_out = "%s-cumi-1.fq.gz" % utils.splitext_plus(align_bam)[0]
f2_out = "%s-cumi-2.fq.gz" % utils.splitext_plus(align_bam)[0]
avg_coverage = coverage.get_average_coverage("rawumi", dd.get_variant_regions(data), data)
if not utils.file_uptodate(f1_out, align_bam):
with file_transaction(data, f1_out, f2_out) as (tx_f1_out, tx_f2_out):
jvm_opts = _get_fgbio_jvm_opts(data, os.path.dirname(tx_f1_out), 2)
# Improve speeds by avoiding compression read/write bottlenecks
io_opts = "--async-io=true --compression=0"
est_options = _estimate_fgbio_defaults(avg_coverage)
group_opts, cons_opts, filter_opts = _get_fgbio_options(data, est_options, umi_method)
cons_method = "CallDuplexConsensusReads" if umi_method == "paired" else "CallMolecularConsensusReads"
tempfile = "%s-bamtofastq-tmp" % utils.splitext_plus(f1_out)[0]
ref_file = dd.get_ref_file(data)
cmd = ("unset JAVA_HOME && "
"fgbio {jvm_opts} {io_opts} GroupReadsByUmi {group_opts} -t {umi_tag} -s {umi_method} "
"-i {align_bam} | "
"fgbio {jvm_opts} {io_opts} {cons_method} {cons_opts} --sort-order=:none: "
"-i /dev/stdin -o /dev/stdout | "
"fgbio {jvm_opts} {io_opts} FilterConsensusReads {filter_opts} -r {ref_file} "
"-i /dev/stdin -o /dev/stdout | "
"bamtofastq collate=1 T={tempfile} F={tx_f1_out} F2={tx_f2_out} tags=cD,cM,cE gz=1")
do.run(cmd.format(**locals()), "UMI consensus fastq generation")
return f1_out, f2_out, avg_coverage
def _prep_real_counts(bam_file, data, samtools_stats):
out = {}
if dd.get_coverage(data) and dd.get_coverage(data) not in ["None"]:
bed = dd.get_coverage_merged(data)
target_name = "coverage"
elif dd.get_coverage_interval(data) != "genome":
bed = dd.get_variant_regions_merged(data) or dd.get_sample_callable(
data)
target_name = "variant_regions"
else:
bed = None
target_name = "genome"
dedupped = utils.get_in(data, ("config", "algorithm", "mark_duplicates"),
True)
if bed:
out["Preseq_genome_size"] = pybedtools.BedTool(bed).total_coverage()
out["Preseq_read_count"] = readstats.number_of_mapped_reads(
data,
bam_file,
keep_dups=True,
bed_file=bed,
target_name=target_name)
ontrg_unique_depth = cov.get_average_coverage(target_name, bed, data,
bam_file)
if dedupped:
out["Preseq_unique_count"] = readstats.number_of_mapped_reads(
data,
bam_file,
keep_dups=False,
bed_file=bed,
target_name=target_name)
# Counting average on-target alignment length, based on the equation:
# avg depth ~~ num (unique) on-target alignments * avg on-target aln length / target size
total_alignments = out.get(
"Preseq_unique_count") or out["Preseq_read_count"]
out["Preseq_read_length"] = ontrg_unique_depth * out[
"Preseq_genome_size"] // total_alignments
else: # WGS
out["Preseq_genome_size"] = sum([
c.size
for c in ref.file_contigs(dd.get_ref_file(data), data["config"])
])
out["Preseq_read_count"] = int(samtools_stats["Total_reads"])
out["Preseq_read_length"] = int(samtools_stats["Average_read_length"])
if dedupped:
out["Preseq_unique_count"] = out["Preseq_read_count"] - int(
samtools_stats["Duplicates"])
return out
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
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
def _prep_real_counts(bam_file, data, samtools_stats):
out = {}
if dd.get_coverage(data) and dd.get_coverage(data) not in ["None"]:
bed = dd.get_coverage_merged(data)
target_name = "coverage"
elif dd.get_coverage_interval(data) != "genome":
bed = dd.get_variant_regions_merged(data)
target_name = "variant_regions"
else:
bed = None
target_name = "genome"
dedupped = utils.get_in(data, ("config", "algorithm", "mark_duplicates"), True)
if bed:
out["Preseq_genome_size"] = pybedtools.BedTool(bed).total_coverage()
out["Preseq_read_count"] = readstats.number_of_mapped_reads(
data, bam_file, keep_dups=True, bed_file=bed, target_name=target_name)
ontrg_unique_depth = cov.get_average_coverage(target_name, bed, data, bam_file)
if dedupped:
out["Preseq_unique_count"] = readstats.number_of_mapped_reads(
data, bam_file, keep_dups=False, bed_file=bed, target_name=target_name)
# Counting average on-target alignment length, based on the equation:
# avg depth ~~ num (unique) on-target alignments * avg on-target aln length / target size
total_alignments = out.get("Preseq_unique_count") or out["Preseq_read_count"]
out["Preseq_read_length"] = ontrg_unique_depth * out["Preseq_genome_size"] // total_alignments
else: # WGS
out["Preseq_genome_size"] = sum([c.size for c in ref.file_contigs(dd.get_ref_file(data), data["config"])])
out["Preseq_read_count"] = int(samtools_stats["Total_reads"])
out["Preseq_read_length"] = int(samtools_stats["Average_read_length"])
if dedupped:
out["Preseq_unique_count"] = out["Preseq_read_count"] - int(samtools_stats["Duplicates"])
return out
def run(bam_file, data, out_dir):
"""Run coverage QC analysis
"""
out = dict()
out_dir = utils.safe_makedir(out_dir)
if dd.get_coverage(data) and dd.get_coverage(data) not in ["None"]:
merged_bed_file = bedutils.clean_file(dd.get_coverage_merged(data),
data,
prefix="cov-",
simple=True)
target_name = "coverage"
elif dd.get_coverage_interval(data) != "genome":
merged_bed_file = dd.get_variant_regions_merged(data)
target_name = "variant_regions"
else:
merged_bed_file = None
target_name = "genome"
avg_depth = cov.get_average_coverage(target_name, merged_bed_file, data)
if target_name == "coverage":
out_files = cov.coverage_region_detailed_stats(target_name,
merged_bed_file, data,
out_dir)
else:
out_files = []
out['Avg_coverage'] = avg_depth
samtools_stats_dir = os.path.join(out_dir, os.path.pardir, 'samtools')
from bcbio.qc import samtools
samtools_stats = samtools.run(bam_file, data,
samtools_stats_dir)["metrics"]
out["Total_reads"] = total_reads = int(samtools_stats["Total_reads"])
out["Mapped_reads"] = mapped = int(samtools_stats["Mapped_reads"])
out["Mapped_paired_reads"] = int(samtools_stats["Mapped_paired_reads"])
out['Duplicates'] = dups = int(samtools_stats["Duplicates"])
if total_reads:
out["Mapped_reads_pct"] = 100.0 * mapped / total_reads
if mapped:
out['Duplicates_pct'] = 100.0 * dups / mapped
if dd.get_coverage_interval(data) == "genome":
mapped_unique = mapped - dups
else:
mapped_unique = readstats.number_of_mapped_reads(data,
bam_file,
keep_dups=False)
out['Mapped_unique_reads'] = mapped_unique
if merged_bed_file:
ontarget = readstats.number_of_mapped_reads(data,
bam_file,
keep_dups=False,
bed_file=merged_bed_file,
target_name=target_name)
out["Ontarget_unique_reads"] = ontarget
if mapped_unique:
out["Ontarget_pct"] = 100.0 * ontarget / mapped_unique
out['Offtarget_pct'] = 100.0 * (mapped_unique -
ontarget) / mapped_unique
if dd.get_coverage_interval(data) != "genome":
# Skip padded calculation for WGS even if the "coverage" file is specified
# the padded statistic makes only sense for exomes and panels
padded_bed_file = bedutils.get_padded_bed_file(
out_dir, merged_bed_file, 200, data)
ontarget_padded = readstats.number_of_mapped_reads(
data,
bam_file,
keep_dups=False,
bed_file=padded_bed_file,
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
indexcov_files = _goleft_indexcov(bam_file, data, out_dir)
out_files += [x for x in indexcov_files if x and utils.file_exists(x)]
out = {"metrics": out}
if len(out_files) > 0:
out["base"] = out_files[0]
out["secondary"] = out_files[1:]
return out
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
def _run_coverage_qc(bam_file, data, out_dir):
"""Run coverage QC analysis"""
out = dict()
samtools_stats_dir = os.path.join(out_dir, os.path.pardir, out_dir)
from bcbio.qc import samtools
samtools_stats = samtools.run(bam_file, data, samtools_stats_dir)
if "Total_reads" not in samtools_stats:
return
out["Total_reads"] = total_reads = int(samtools_stats["Total_reads"])
if not total_reads:
return
if "Mapped_reads_raw" not in samtools_stats or "Mapped_reads" not in samtools_stats:
return
out["Mapped_reads"] = mapped = int(samtools_stats["Mapped_reads"])
out["Mapped_reads_pct"] = 100.0 * mapped / total_reads
if not mapped:
return out
if "Duplicates" in samtools_stats:
out['Duplicates'] = dups = int(samtools_stats["Duplicates"])
out['Duplicates_pct'] = 100.0 * dups / int(samtools_stats["Mapped_reads_raw"])
else:
dups = 0
if dd.get_coverage(data) and dd.get_coverage(data) not in ["None"]:
cov_bed_file = bedutils.clean_file(dd.get_coverage(data), data, prefix="cov-", simple=True)
merged_bed_file = bedutils.merge_overlaps(cov_bed_file, data)
target_name = "coverage"
elif dd.get_coverage_interval(data) != "genome":
merged_bed_file = dd.get_variant_regions_merged(data)
target_name = "variant_regions"
else:
merged_bed_file = None
target_name = "genome"
# Whole genome runs do not need detailed on-target calculations, use total unique mapped
if dd.get_coverage_interval(data) == "genome":
mapped_unique = mapped - dups
else:
out['Mapped_unique_reads'] = mapped_unique = sambamba.number_of_mapped_reads(data, bam_file, keep_dups=False)
if merged_bed_file:
ontarget = sambamba.number_of_mapped_reads(
data, bam_file, keep_dups=False, bed_file=merged_bed_file, 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
if dd.get_coverage_interval(data) != "genome":
# Skip padded calculation for WGS even if the "coverage" file is specified
# the padded statistic makes only sense for exomes and panels
padded_bed_file = bedutils.get_padded_bed_file(merged_bed_file, 200, data)
ontarget_padded = sambamba.number_of_mapped_reads(
data, bam_file, keep_dups=False, bed_file=padded_bed_file, 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_depth = cov.get_average_coverage(data, bam_file, merged_bed_file, target_name)
out['Avg_coverage'] = avg_depth
region_coverage_file = cov.coverage_region_detailed_stats(data, out_dir,
extra_cutoffs=set([max(1, int(avg_depth * 0.8))]))
return out
def _run_coverage_qc(bam_file, data, out_dir):
"""Run coverage QC analysis"""
out = dict()
samtools_stats_dir = os.path.join(out_dir, os.path.pardir, out_dir)
from bcbio.qc import samtools
samtools_stats = samtools.run(bam_file, data, samtools_stats_dir)
if "Total_reads" not in samtools_stats:
return
out["Total_reads"] = total_reads = int(samtools_stats["Total_reads"])
if not total_reads:
return
if "Mapped_reads_raw" not in samtools_stats or "Mapped_reads" not in samtools_stats:
return
out["Mapped_reads"] = mapped = int(samtools_stats["Mapped_reads"])
out["Mapped_reads_pct"] = 100.0 * mapped / total_reads
if not mapped:
return out
if "Duplicates" in samtools_stats:
out['Duplicates'] = dups = int(samtools_stats["Duplicates"])
out['Duplicates_pct'] = 100.0 * dups / int(
samtools_stats["Mapped_reads_raw"])
else:
dups = 0
if dd.get_coverage(data):
cov_bed_file = bedutils.clean_file(dd.get_coverage(data),
data,
prefix="cov-",
simple=True)
merged_bed_file = bedutils.merge_overlaps(cov_bed_file, data)
target_name = "coverage"
elif dd.get_coverage_interval(data) != "genome":
merged_bed_file = dd.get_variant_regions_merged(data)
target_name = "variant_regions"
else:
merged_bed_file = None
target_name = "genome"
# Whole genome runs do not need detailed on-target calculations, use total unique mapped
if dd.get_coverage_interval(data) == "genome":
mapped_unique = mapped - dups
else:
out['Mapped_unique_reads'] = mapped_unique = sambamba.number_of_mapped_reads(
data, bam_file, keep_dups=False)
if merged_bed_file:
ontarget = sambamba.number_of_mapped_reads(data,
bam_file,
keep_dups=False,
bed_file=merged_bed_file,
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
if dd.get_coverage_interval(data) != "genome":
# Skip padded calculation for WGS even if the "coverage" file is specified
# the padded statistic makes only sense for exomes and panels
padded_bed_file = bedutils.get_padded_bed_file(
merged_bed_file, 200, data)
ontarget_padded = sambamba.number_of_mapped_reads(
data,
bam_file,
keep_dups=False,
bed_file=padded_bed_file,
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_depth = cov.get_average_coverage(data, bam_file, merged_bed_file,
target_name)
out['Avg_coverage'] = avg_depth
region_coverage_file = cov.coverage_region_detailed_stats(
data, out_dir, extra_cutoffs=set([max(1, int(avg_depth * 0.8))]))
return out
def run(bam_file, data, out_dir):
"""Run coverage QC analysis
"""
out = dict()
if dd.get_coverage(data) and dd.get_coverage(data) not in ["None"]:
merged_bed_file = dd.get_coverage_merged(data)
target_name = "coverage"
elif dd.get_coverage_interval(data) != "genome":
merged_bed_file = dd.get_variant_regions_merged(data)
target_name = "variant_regions"
else:
merged_bed_file = None
target_name = "genome"
avg_depth = cov.get_average_coverage(data, bam_file, merged_bed_file, target_name)
out['Avg_coverage'] = avg_depth
samtools_stats_dir = os.path.join(out_dir, os.path.pardir, 'samtools')
from bcbio.qc import samtools
samtools_stats = samtools.run(bam_file, data, samtools_stats_dir)
out["Total_reads"] = total_reads = int(samtools_stats["Total_reads"])
out["Mapped_reads"] = mapped = int(samtools_stats["Mapped_reads"])
out["Mapped_paired_reads"] = int(samtools_stats["Mapped_paired_reads"])
out['Duplicates'] = dups = int(samtools_stats["Duplicates"])
if total_reads:
out["Mapped_reads_pct"] = 100.0 * mapped / total_reads
if mapped:
out['Duplicates_pct'] = 100.0 * dups / mapped
if dd.get_coverage_interval(data) == "genome":
mapped_unique = mapped - dups
else:
mapped_unique = sambamba.number_of_mapped_reads(data, bam_file, keep_dups=False)
out['Mapped_unique_reads'] = mapped_unique
if merged_bed_file:
ontarget = sambamba.number_of_mapped_reads(
data, bam_file, keep_dups=False, bed_file=merged_bed_file, target_name=target_name)
out["Ontarget_unique_reads"] = ontarget
if mapped_unique:
out["Ontarget_pct"] = 100.0 * ontarget / mapped_unique
out['Offtarget_pct'] = 100.0 * (mapped_unique - ontarget) / mapped_unique
if dd.get_coverage_interval(data) != "genome":
# Skip padded calculation for WGS even if the "coverage" file is specified
# the padded statistic makes only sense for exomes and panels
padded_bed_file = bedutils.get_padded_bed_file(out_dir, merged_bed_file, 200, data)
ontarget_padded = sambamba.number_of_mapped_reads(
data, bam_file, keep_dups=False, bed_file=padded_bed_file, 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
out_files = cov.coverage_region_detailed_stats(data, out_dir,
extra_cutoffs=set([max(1, int(avg_depth * 0.8))]))
for ext in ["coverage.bed", "summary.bed"]:
out_files += [x for x in glob.glob(os.path.join(out_dir, "*%s" % ext)) if os.path.isfile(x)]
indexcov_files = _goleft_indexcov(bam_file, data, out_dir)
out_files += [x for x in indexcov_files if x and utils.file_exists(x)]
out = {"metrics": out}
if len(out_files) > 0:
out["base"] = out_files[0]
out["secondary"] = out_files[1:]
return out
