def run(bam_file, data, out_dir):
"""Run qualimap to assess alignment quality metrics.
"""
# Qualimap results should be saved to a directory named after sample.
# MultiQC (for parsing additional data) picks the sample name after the dir as follows:
# <sample name>/raw_data_qualimapReport/insert_size_histogram.txt
results_dir = os.path.join(out_dir, dd.get_sample_name(data))
resources = config_utils.get_resources("qualimap", data["config"])
options = " ".join(resources.get("options", ""))
results_file = os.path.join(results_dir, "genome_results.txt")
report_file = os.path.join(results_dir, "qualimapReport.html")
utils.safe_makedir(results_dir)
pdf_file = "qualimapReport.pdf"
if not utils.file_exists(results_file) and not utils.file_exists(os.path.join(results_dir, pdf_file)):
if "qualimap_full" in tz.get_in(("config", "algorithm", "tools_on"), data, []):
logger.info("Full qualimap analysis for %s may be slow." % bam_file)
ds_bam = bam_file
else:
ds_bam = bam.downsample(bam_file, data, 1e7, work_dir=out_dir)
bam_file = ds_bam if ds_bam else bam_file
if options.find("PDF") > -1:
options = "%s -outfile %s" % (options, pdf_file)
num_cores = data["config"]["algorithm"].get("num_cores", 1)
qualimap = config_utils.get_program("qualimap", data["config"])
max_mem = config_utils.adjust_memory(resources.get("memory", "1G"),
num_cores)
with file_transaction(data, results_dir) as tx_results_dir:
utils.safe_makedir(tx_results_dir)
export = "%s%s export JAVA_OPTS='-Xms32m -Xmx%s -Djava.io.tmpdir=%s' && " % (
utils.java_freetype_fix(), utils.local_path_export(), max_mem, tx_results_dir)
cmd = ("unset DISPLAY && {export} {qualimap} bamqc -bam {bam_file} -outdir {tx_results_dir} "
"--skip-duplicated --skip-dup-mode 0 "
"-nt {num_cores} {options}")
species = None
if (tz.get_in(("genome_resources", "aliases", "human"), data, "")
or dd.get_genome_build(data).startswith(("hg", "GRCh"))):
species = "HUMAN"
elif dd.get_genome_build(data).startswith(("mm", "GRCm")):
species = "MOUSE"
if species in ["HUMAN", "MOUSE"]:
cmd += " -gd {species}"
regions = (dd.get_coverage(data) if dd.get_coverage(data) not in [None, False, "None"]
else dd.get_variant_regions_merged(data))
if regions:
regions = bedutils.merge_overlaps(bedutils.clean_file(regions, data), data)
bed6_regions = _bed_to_bed6(regions, out_dir)
cmd += " -gff {bed6_regions}"
bcbio_env = utils.get_bcbio_env()
do.run(cmd.format(**locals()), "Qualimap: %s" % dd.get_sample_name(data), env=bcbio_env)
tx_results_file = os.path.join(tx_results_dir, "genome_results.txt")
cmd = "sed -i 's/bam file = .*/bam file = %s.bam/' %s" % (dd.get_sample_name(data), tx_results_file)
do.run(cmd, "Fix Name Qualimap for {}".format(dd.get_sample_name(data)))
# Qualimap output folder (results_dir) needs to be named after the sample (see comments above). However, in order
# to keep its name after upload, we need to put the base QC file (results_file) into the root directory (out_dir):
base_results_file = os.path.join(out_dir, os.path.basename(results_file))
shutil.copyfile(results_file, base_results_file)
return {"base": base_results_file,
"secondary": _find_qualimap_secondary_files(results_dir, base_results_file)}
def assign_interval(data):
"""Identify coverage based on percent of genome covered and relation to targets.
Classifies coverage into 3 categories:
- genome: Full genome coverage
- regional: Regional coverage, like exome capture, with off-target reads
- amplicon: Amplication based regional coverage without off-target reads
"""
if not dd.get_coverage_interval(data):
vrs = dd.get_variant_regions_merged(data)
callable_file = dd.get_sample_callable(data)
if vrs:
callable_size = pybedtools.BedTool(vrs).total_coverage()
else:
callable_size = pybedtools.BedTool(callable_file).total_coverage()
total_size = sum([c.size for c in ref.file_contigs(dd.get_ref_file(data), data["config"])])
genome_cov_pct = callable_size / float(total_size)
if genome_cov_pct > GENOME_COV_THRESH:
cov_interval = "genome"
offtarget_pct = 0.0
elif not vrs:
cov_interval = "regional"
offtarget_pct = 0.0
else:
offtarget_pct = _count_offtarget(data, dd.get_align_bam(data) or dd.get_work_bam(data),
vrs or callable_file, "variant_regions")
if offtarget_pct > OFFTARGET_THRESH:
cov_interval = "regional"
else:
cov_interval = "amplicon"
logger.info("%s: Assigned coverage as '%s' with %.1f%% genome coverage and %.1f%% offtarget coverage"
% (dd.get_sample_name(data), cov_interval, genome_cov_pct * 100.0, offtarget_pct * 100.0))
data["config"]["algorithm"]["coverage_interval"] = cov_interval
return data
def _get_maxcov_downsample(data):
"""Calculate maximum coverage downsampling for whole genome samples.
Returns None if we're not doing downsampling.
"""
from bcbio.bam import ref
from bcbio.ngsalign import alignprep, bwa
from bcbio.variation import coverage
params = {"min_coverage_for_downsampling": 10,
"maxcov_downsample_multiplier": dd.get_maxcov_downsample(data)}
fastq_file = data["files"][0]
num_reads = alignprep.total_reads_from_grabix(fastq_file)
if num_reads and params["maxcov_downsample_multiplier"] and params["maxcov_downsample_multiplier"] > 0:
vrs = dd.get_variant_regions_merged(data)
total_size = sum([c.size for c in ref.file_contigs(dd.get_ref_file(data), data["config"])])
if vrs:
callable_size = pybedtools.BedTool(vrs).total_coverage()
genome_cov_pct = callable_size / float(total_size)
else:
callable_size = total_size
genome_cov_pct = 1.0
if (genome_cov_pct > coverage.GENOME_COV_THRESH
and dd.get_coverage_interval(data) in ["genome", None, False]):
total_counts, total_sizes = 0, 0
for count, size in bwa.fastq_size_output(fastq_file, 5000):
total_counts += int(count)
total_sizes += (int(size) * int(count))
read_size = float(total_sizes) / float(total_counts)
avg_cov = float(num_reads * read_size) / callable_size
if avg_cov >= params["min_coverage_for_downsampling"]:
return int(avg_cov * params["maxcov_downsample_multiplier"])
return None
def _regions_for_coverage(data, region, ref_file, out_file):
"""Retrieve BED file of regions we need to calculate coverage in.
Checks for variant region specifications that do not overlap contigs
(in which case we do not calculate coverage) and regions smaller than
callable_min_size (in which case we assign everything as callable).
callable_min_size avoids calculations for small chromosomes we won't
split on later, saving computation and disk IO.
"""
variant_regions = dd.get_variant_regions_merged(data)
ready_region = shared.subset_variant_regions(variant_regions, region, out_file)
custom_file = "%s-coverageregions.bed" % utils.splitext_plus(out_file)[0]
region_size = _get_region_size(ref_file, data, region)
if variant_regions is None and region_size is not None and region_size < dd.get_callable_min_size(data):
coverage_str = "CALLABLE" if realign.has_aligned_reads(dd.get_work_bam(data), region) else "NO_COVERAGE"
custom_file = _write_all_chrom_file(coverage_str, custom_file, ref_file, region, data)
return custom_file, False
elif not ready_region:
get_ref_bedtool(ref_file, data["config"]).saveas(custom_file)
return custom_file, True
elif os.path.isfile(ready_region):
return ready_region, True
elif isinstance(ready_region, (list, tuple)):
c, s, e = ready_region
pybedtools.BedTool("%s\t%s\t%s\n" % (c, s, e), from_string=True).saveas(custom_file)
return custom_file, True
else:
custom_file = _write_all_chrom_file("NO_COVERAGE", custom_file, ref_file, region, data)
return custom_file, variant_regions is None
def calculate_offtarget(bam_file, ref_file, data):
"""Generate file of offtarget read counts for inputs with variant regions.
"""
vrs_file = dd.get_variant_regions_merged(data)
if vrs_file:
out_file = "%s-offtarget-stats.yaml" % os.path.splitext(bam_file)[0]
if not utils.file_exists(out_file):
with file_transaction(data, out_file) as tx_out_file:
offtarget_regions = "%s-regions.bed" % utils.splitext_plus(
out_file)[0]
ref_bed = get_ref_bedtool(ref_file, data["config"])
ref_bed.subtract(pybedtools.BedTool(vrs_file),
nonamecheck=True).saveas(offtarget_regions)
cmd = (
"samtools view -u {bam_file} -L {offtarget_regions} | "
"bedtools intersect -abam - -b {offtarget_regions} -f 1.0 -bed | wc -l"
)
offtarget_count = int(
subprocess.check_output(cmd.format(**locals()),
shell=True))
cmd = "samtools idxstats {bam_file} | awk '{{s+=$3}} END {{print s}}'"
mapped_count = int(
subprocess.check_output(cmd.format(**locals()),
shell=True))
with open(tx_out_file, "w") as out_handle:
yaml.safe_dump(
{
"mapped": mapped_count,
"offtarget": offtarget_count
},
out_handle,
allow_unicode=False,
default_flow_style=False)
return out_file
def calculate(bam_file, data):
"""Calculate coverage in parallel using mosdepth.
Removes duplicates and secondary reads from the counts:
if ( b->core.flag & (BAM_FUNMAP | BAM_FSECONDARY | BAM_FQCFAIL | BAM_FDUP) ) continue;
"""
params = {"min": dd.get_coverage_depth_min(data)}
variant_regions = dd.get_variant_regions_merged(data)
if not variant_regions:
variant_regions = _create_genome_regions(data)
# Back compatible with previous pre-mosdepth callable files
callable_file = os.path.join(utils.safe_makedir(os.path.join(dd.get_work_dir(data), "align",
dd.get_sample_name(data))),
"%s-coverage.callable.bed" % (dd.get_sample_name(data)))
if not utils.file_uptodate(callable_file, bam_file):
vr_quantize = ("0:1:%s:" % (params["min"]), ["NO_COVERAGE", "LOW_COVERAGE", "CALLABLE"])
to_calculate = [("variant_regions", variant_regions, vr_quantize, None),
("sv_regions", regions.get_sv_bed(data), None, None),
("coverage", dd.get_coverage(data), None, DEPTH_THRESHOLDS)]
depth_files = {}
for target_name, region_bed, quantize, thresholds in to_calculate:
if region_bed:
cur_depth = {}
depth_info = run_mosdepth(data, target_name, region_bed, quantize=quantize, thresholds=thresholds)
for attr in ("dist", "regions", "thresholds"):
val = getattr(depth_info, attr, None)
if val:
cur_depth[attr] = val
depth_files[target_name] = cur_depth
if target_name == "variant_regions":
callable_file = depth_info.quantize
else:
depth_files = {}
final_callable = _subset_to_variant_regions(callable_file, variant_regions, data)
return final_callable, depth_files
def _regions_for_coverage(data, region, ref_file, out_file):
"""Retrieve BED file of regions we need to calculate coverage in.
Checks for variant region specifications that do not overlap contigs
(in which case we do not calculate coverage) and regions smaller than
callable_min_size (in which case we assign everything as callable).
callable_min_size avoids calculations for small chromosomes we won't
split on later, saving computation and disk IO.
"""
variant_regions = dd.get_variant_regions_merged(data)
ready_region = shared.subset_variant_regions(variant_regions, region,
out_file)
custom_file = "%s-coverageregions.bed" % utils.splitext_plus(out_file)[0]
region_size = _get_region_size(ref_file, data, region)
if variant_regions is None and region_size is not None and region_size < dd.get_callable_min_size(
data):
coverage_str = "CALLABLE" if realign.has_aligned_reads(
dd.get_work_bam(data), region) else "NO_COVERAGE"
custom_file = _write_all_chrom_file(coverage_str, custom_file,
ref_file, region, data)
return custom_file, False
elif not ready_region:
get_ref_bedtool(ref_file, data["config"]).saveas(custom_file)
return custom_file, True
elif os.path.isfile(ready_region):
return ready_region, True
elif isinstance(ready_region, (list, tuple)):
c, s, e = ready_region
pybedtools.BedTool("%s\t%s\t%s\n" % (c, s, e),
from_string=True).saveas(custom_file)
return custom_file, True
else:
custom_file = _write_all_chrom_file("NO_COVERAGE", custom_file,
ref_file, region, data)
return custom_file, variant_regions is None
def run(bam_file, data, out_dir):
"""Run qualimap to assess alignment quality metrics.
"""
# Qualimap results should be saved to a directory named after sample.
# MultiQC (for parsing additional data) picks the sample name after the dir as follows:
# <sample name>/raw_data_qualimapReport/insert_size_histogram.txt
results_dir = os.path.join(out_dir, dd.get_sample_name(data))
resources = config_utils.get_resources("qualimap", data["config"])
options = " ".join(resources.get("options", ""))
report_file = os.path.join(results_dir, "qualimapReport.html")
utils.safe_makedir(results_dir)
pdf_file = "qualimapReport.pdf"
if not utils.file_exists(report_file) and not utils.file_exists(
os.path.join(results_dir, pdf_file)):
if "qualimap_full" in tz.get_in(("config", "algorithm", "tools_on"),
data, []):
logger.info("Full qualimap analysis for %s may be slow." %
bam_file)
ds_bam = bam_file
else:
ds_bam = bam.downsample(bam_file, data, 1e7, work_dir=out_dir)
bam_file = ds_bam if ds_bam else bam_file
if options.find("PDF") > -1:
options = "%s -outfile %s" % (options, pdf_file)
num_cores = data["config"]["algorithm"].get("num_cores", 1)
qualimap = config_utils.get_program("qualimap", data["config"])
max_mem = config_utils.adjust_memory(resources.get("memory", "1G"),
num_cores)
# Fixing the file name: MultiQC picks sample name from BAM file name.
fixed_bam_fname = os.path.join(out_dir,
dd.get_sample_name(data) + ".bam")
if not os.path.islink(fixed_bam_fname):
os.symlink(bam_file, fixed_bam_fname)
export = utils.local_path_export()
cmd = (
"unset DISPLAY && {export} {qualimap} bamqc -bam {fixed_bam_fname} -outdir {results_dir} "
"--skip-duplicated --skip-dup-mode 0 "
"-nt {num_cores} --java-mem-size={max_mem} {options}")
species = None
if tz.get_in(("genome_resources", "aliases", "human"), data, ""):
species = "HUMAN"
elif any(
tz.get_in("genome_build", data, "").startswith(k)
for k in ["mm", "GRCm"]):
species = "MOUSE"
if species in ["HUMAN", "MOUSE"]:
cmd += " -gd {species}"
regions = bedutils.merge_overlaps(
dd.get_coverage(data), data) or dd.get_variant_regions_merged(data)
if regions:
bed6_regions = _bed_to_bed6(regions, out_dir)
cmd += " -gff {bed6_regions}"
do.run(cmd.format(**locals()),
"Qualimap: %s" % dd.get_sample_name(data))
# return _parse_qualimap_metrics(report_file, data)
return dict()
def _get_maxcov_downsample(data):
"""Calculate maximum coverage downsampling for whole genome samples.
Returns None if we're not doing downsampling.
"""
from bcbio.bam import ref
from bcbio.ngsalign import alignprep, bwa
from bcbio.variation import coverage
fastq_file = data["files"][0]
params = alignprep.get_downsample_params(data)
if params:
num_reads = alignprep.total_reads_from_grabix(fastq_file)
if num_reads:
vrs = dd.get_variant_regions_merged(data)
total_size = sum([c.size for c in ref.file_contigs(dd.get_ref_file(data), data["config"])])
if vrs:
callable_size = pybedtools.BedTool(vrs).total_coverage()
genome_cov_pct = callable_size / float(total_size)
else:
callable_size = total_size
genome_cov_pct = 1.0
if (genome_cov_pct > coverage.GENOME_COV_THRESH
and dd.get_coverage_interval(data) in ["genome", None, False]):
total_counts, total_sizes = 0, 0
for count, size in bwa.fastq_size_output(fastq_file, 5000):
total_counts += int(count)
total_sizes += (int(size) * int(count))
read_size = float(total_sizes) / float(total_counts)
avg_cov = float(num_reads * read_size) / callable_size
if avg_cov >= params["min_coverage_for_downsampling"]:
return int(avg_cov * params["maxcov_downsample_multiplier"])
return None
def run(bam_file, data, out_dir):
"""Run qualimap to assess alignment quality metrics.
"""
# Qualimap results should be saved to a directory named after sample.
# MultiQC (for parsing additional data) picks the sample name after the dir as follows:
# <sample name>/raw_data_qualimapReport/insert_size_histogram.txt
results_dir = os.path.join(out_dir, dd.get_sample_name(data))
resources = config_utils.get_resources("qualimap", data["config"])
options = " ".join(resources.get("options", ""))
results_file = os.path.join(results_dir, "genome_results.txt")
report_file = os.path.join(results_dir, "qualimapReport.html")
utils.safe_makedir(results_dir)
pdf_file = "qualimapReport.pdf"
if not utils.file_exists(results_file) and not utils.file_exists(os.path.join(results_dir, pdf_file)):
if "qualimap_full" in tz.get_in(("config", "algorithm", "tools_on"), data, []):
logger.info("Full qualimap analysis for %s may be slow." % bam_file)
ds_bam = bam_file
else:
ds_bam = bam.downsample(bam_file, data, 1e7, work_dir=out_dir)
bam_file = ds_bam if ds_bam else bam_file
if options.find("PDF") > -1:
options = "%s -outfile %s" % (options, pdf_file)
num_cores = data["config"]["algorithm"].get("num_cores", 1)
qualimap = config_utils.get_program("qualimap", data["config"])
max_mem = config_utils.adjust_memory(resources.get("memory", "1G"),
num_cores)
with file_transaction(data, results_dir) as tx_results_dir:
utils.safe_makedir(tx_results_dir)
export = "%s%s export JAVA_OPTS='-Xms32m -Xmx%s -Djava.io.tmpdir=%s' && " % (
utils.java_freetype_fix(), utils.local_path_export(), max_mem, tx_results_dir)
cmd = ("unset DISPLAY && {export} {qualimap} bamqc -bam {bam_file} -outdir {tx_results_dir} "
"--skip-duplicated --skip-dup-mode 0 "
"-nt {num_cores} {options}")
species = None
if (tz.get_in(("genome_resources", "aliases", "human"), data, "")
or dd.get_genome_build(data).startswith(("hg", "GRCh"))):
species = "HUMAN"
elif dd.get_genome_build(data).startswith(("mm", "GRCm")):
species = "MOUSE"
if species in ["HUMAN", "MOUSE"]:
cmd += " -gd {species}"
regions = (dd.get_coverage(data) if dd.get_coverage(data) not in [None, False, "None"]
else dd.get_variant_regions_merged(data))
if regions:
regions = bedutils.merge_overlaps(bedutils.clean_file(regions, data), data)
bed6_regions = _bed_to_bed6(regions, out_dir)
cmd += " -gff {bed6_regions}"
bcbio_env = utils.get_bcbio_env()
do.run(cmd.format(**locals()), "Qualimap: %s" % dd.get_sample_name(data), env=bcbio_env)
tx_results_file = os.path.join(tx_results_dir, "genome_results.txt")
cmd = "sed -i 's/bam file = .*/bam file = %s.bam/' %s" % (dd.get_sample_name(data), tx_results_file)
do.run(cmd, "Fix Name Qualimap for {}".format(dd.get_sample_name(data)))
# Qualimap output folder (results_dir) needs to be named after the sample (see comments above). However, in order
# to keep its name after upload, we need to put the base QC file (results_file) into the root directory (out_dir):
base_results_file = os.path.join(out_dir, os.path.basename(results_file))
shutil.copyfile(results_file, base_results_file)
return {"base": base_results_file,
"secondary": _find_qualimap_secondary_files(results_dir, base_results_file)}
def calculate(bam_file, data):
"""Calculate coverage in parallel using mosdepth.
Removes duplicates and secondary reads from the counts:
if ( b->core.flag & (BAM_FUNMAP | BAM_FSECONDARY | BAM_FQCFAIL | BAM_FDUP) ) continue;
"""
params = {"min": dd.get_coverage_depth_min(data)}
variant_regions = dd.get_variant_regions_merged(data)
if not variant_regions:
variant_regions = _create_genome_regions(data)
# Back compatible with previous pre-mosdepth callable files
callable_file = os.path.join(utils.safe_makedir(os.path.join(dd.get_work_dir(data), "align",
dd.get_sample_name(data))),
"%s-coverage.callable.bed" % (dd.get_sample_name(data)))
if not utils.file_uptodate(callable_file, bam_file):
vr_quantize = ("0:1:%s:" % (params["min"]), ["NO_COVERAGE", "LOW_COVERAGE", "CALLABLE"])
to_calculate = [("variant_regions", variant_regions, vr_quantize, None),
("sv_regions", bedutils.clean_file(regions.get_sv_bed(data), data), None, None),
("coverage", bedutils.clean_file(dd.get_coverage(data), data), None, DEPTH_THRESHOLDS)]
depth_files = {}
for target_name, region_bed, quantize, thresholds in to_calculate:
if region_bed:
cur_depth = {}
depth_info = run_mosdepth(data, target_name, region_bed, quantize=quantize, thresholds=thresholds)
for attr in ("dist", "regions", "thresholds"):
val = getattr(depth_info, attr, None)
if val:
cur_depth[attr] = val
depth_files[target_name] = cur_depth
if target_name == "variant_regions":
callable_file = depth_info.quantize
else:
depth_files = {}
final_callable = _subset_to_variant_regions(callable_file, variant_regions, data)
return final_callable, depth_files
def assign_interval(data):
"""Identify coverage based on percent of genome covered and relation to targets.
Classifies coverage into 3 categories:
- genome: Full genome coverage
- regional: Regional coverage, like exome capture, with off-target reads
- amplicon: Amplication based regional coverage without off-target reads
"""
if not dd.get_coverage_interval(data):
vrs = dd.get_variant_regions_merged(data)
callable_file = dd.get_sample_callable(data)
if vrs:
callable_size = pybedtools.BedTool(vrs).total_coverage()
else:
callable_size = pybedtools.BedTool(callable_file).total_coverage()
total_size = sum([c.size for c in ref.file_contigs(dd.get_ref_file(data), data["config"])])
genome_cov_pct = callable_size / float(total_size)
if genome_cov_pct > GENOME_COV_THRESH:
cov_interval = "genome"
offtarget_pct = 0.0
elif not vrs:
cov_interval = "regional"
offtarget_pct = 0.0
else:
offtarget_pct = _count_offtarget(data, dd.get_align_bam(data) or dd.get_work_bam(data),
vrs or callable_file, "variant_regions")
if offtarget_pct > OFFTARGET_THRESH:
cov_interval = "regional"
else:
cov_interval = "amplicon"
logger.info("%s: Assigned coverage as '%s' with %.1f%% genome coverage and %.1f%% offtarget coverage"
% (dd.get_sample_name(data), cov_interval, genome_cov_pct * 100.0, offtarget_pct * 100.0))
data["config"]["algorithm"]["coverage_interval"] = cov_interval
return data
def calculate(bam_file, data):
"""Calculate coverage in parallel using samtools depth through goleft.
samtools depth removes duplicates and secondary reads from the counts:
if ( b->core.flag & (BAM_FUNMAP | BAM_FSECONDARY | BAM_FQCFAIL | BAM_FDUP) ) continue;
"""
params = {"window_size": 5000, "parallel_window_size": 1e5, "min": dd.get_coverage_depth_min(data),
"high_multiplier": 20}
prefix = os.path.join(
utils.safe_makedir(os.path.join(dd.get_work_dir(data), "align", dd.get_sample_name(data))),
"%s-coverage" % (dd.get_sample_name(data)))
depth_file = prefix + ".depth.bed"
callable_file = prefix + ".callable.bed"
variant_regions = dd.get_variant_regions_merged(data)
variant_regions_avg_cov = get_average_coverage(data, bam_file, variant_regions, "variant_regions")
if not utils.file_uptodate(callable_file, bam_file):
cmd = ["goleft", "depth", "--q", "1", "--mincov", str(params["min"]),
"--processes", str(dd.get_num_cores(data)), "--ordered"]
max_depth = _get_max_depth(variant_regions_avg_cov, params, data)
if max_depth:
cmd += ["--maxmeandepth", str(int(max_depth))]
with file_transaction(data, depth_file) as tx_depth_file:
with utils.chdir(os.path.dirname(tx_depth_file)):
tx_callable_file = tx_depth_file.replace(".depth.bed", ".callable.bed")
prefix = tx_depth_file.replace(".depth.bed", "")
bam_ref_file = "%s-bamref.fa" % utils.splitext_plus(bam_file)[0]
bam.fai_from_bam(dd.get_ref_file(data), bam_file, bam_ref_file + ".fai", data)
cmd += ["--reference", bam_ref_file]
cmd += ["--prefix", prefix, bam_file]
bcbio_env = utils.get_bcbio_env()
msg = "Calculate coverage: %s" % dd.get_sample_name(data)
do.run(cmd, msg, env=bcbio_env)
shutil.move(tx_callable_file, callable_file)
final_callable = _subset_to_variant_regions(callable_file, variant_regions, data)
return depth_file, final_callable, _extract_highdepth(final_callable, data), variant_regions_avg_cov
def _get_variant_regions(data):
out = dd.get_variant_regions(data) or dd.get_sample_callable(data)
if merged:
merged_out = dd.get_variant_regions_merged(data)
if merged_out:
out = merged_out
else:
out = merge_overlaps(out, data)
return out
def calculate(bam_file, data):
"""Calculate coverage in parallel using samtools depth through goleft.
samtools depth removes duplicates and secondary reads from the counts:
if ( b->core.flag & (BAM_FUNMAP | BAM_FSECONDARY | BAM_FQCFAIL | BAM_FDUP) ) continue;
"""
params = {
"window_size": 5000,
"parallel_window_size": 1e5,
"min": dd.get_coverage_depth_min(data),
"high_multiplier": 20
}
prefix = os.path.join(
utils.safe_makedir(
os.path.join(dd.get_work_dir(data), "align",
dd.get_sample_name(data))),
"%s-coverage" % (dd.get_sample_name(data)))
out_file = prefix + ".depth.bed"
callable_file = prefix + ".callable.bed"
variant_regions = dd.get_variant_regions_merged(data)
variant_regions_avg_cov = get_average_coverage(data,
bam_file,
variant_regions,
"variant_regions",
file_prefix=prefix)
if not utils.file_uptodate(out_file, bam_file):
ref_file = dd.get_ref_file(data)
cmd = [
"goleft", "depth", "--windowsize",
str(params["window_size"]), "--q", "1", "--mincov",
str(params["min"]), "--reference", ref_file, "--processes",
str(dd.get_num_cores(data)), "--stats", "--ordered"
]
if variant_regions:
window_file = "%s-tocalculate-windows.bed" % utils.splitext_plus(
out_file)[0]
if not utils.file_uptodate(window_file, bam_file):
with file_transaction(data, window_file) as tx_out_file:
pybedtools.BedTool().window_maker(
w=params["parallel_window_size"],
b=pybedtools.BedTool(variant_regions)).saveas(
tx_out_file)
cmd += ["--bed", window_file]
max_depth = _get_max_depth(variant_regions_avg_cov, params, data)
if max_depth:
cmd += ["--maxmeandepth", str(int(max_depth))]
with file_transaction(data, out_file) as tx_out_file:
with utils.chdir(os.path.dirname(tx_out_file)):
tx_callable_file = tx_out_file.replace(".depth.bed",
".callable.bed")
prefix = tx_out_file.replace(".depth.bed", "")
cmd += ["--prefix", prefix, bam_file]
do.run(cmd,
"Calculate coverage: %s" % dd.get_sample_name(data))
shutil.move(tx_callable_file, callable_file)
return out_file, callable_file, _extract_highdepth(
callable_file, data), variant_regions_avg_cov
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 _get_variant_regions(data):
out = dd.get_variant_regions(data) or dd.get_sample_callable(data)
# Only need to merge for variant region inputs, not callable BED regions which don't overlap
if merged and dd.get_variant_regions(data):
merged_out = dd.get_variant_regions_merged(data)
if merged_out:
out = merged_out
else:
out = merge_overlaps(out, data)
return out
def _get_variant_regions(data):
out = dd.get_variant_regions(data) or dd.get_sample_callable(data)
# Only need to merge for variant region inputs, not callable BED regions which don't overlap
if merged and dd.get_variant_regions(data):
merged_out = dd.get_variant_regions_merged(data)
if merged_out:
out = merged_out
else:
out = merge_overlaps(out, data)
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) 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(bam_file, data, out_dir):
"""Run qualimap to assess alignment quality metrics.
"""
# Qualimap results should be saved to a directory named after sample.
# MultiQC (for parsing additional data) picks the sample name after the dir as follows:
# <sample name>/raw_data_qualimapReport/insert_size_histogram.txt
results_dir = os.path.join(out_dir, dd.get_sample_name(data))
resources = config_utils.get_resources("qualimap", data["config"])
options = " ".join(resources.get("options", ""))
report_file = os.path.join(results_dir, "qualimapReport.html")
utils.safe_makedir(results_dir)
pdf_file = "qualimapReport.pdf"
if not utils.file_exists(report_file) and not utils.file_exists(os.path.join(results_dir, pdf_file)):
if "qualimap_full" in tz.get_in(("config", "algorithm", "tools_on"), data, []):
logger.info("Full qualimap analysis for %s may be slow." % bam_file)
ds_bam = bam_file
else:
ds_bam = bam.downsample(bam_file, data, 1e7, work_dir=out_dir)
bam_file = ds_bam if ds_bam else bam_file
if options.find("PDF") > -1:
options = "%s -outfile %s" % (options, pdf_file)
num_cores = data["config"]["algorithm"].get("num_cores", 1)
qualimap = config_utils.get_program("qualimap", data["config"])
max_mem = config_utils.adjust_memory(resources.get("memory", "1G"),
num_cores)
# Fixing the file name: MultiQC picks sample name from BAM file name.
fixed_bam_fname = os.path.join(out_dir, dd.get_sample_name(data) + ".bam")
if not os.path.islink(fixed_bam_fname):
os.symlink(bam_file, fixed_bam_fname)
export = utils.local_path_export()
cmd = ("unset DISPLAY && {export} {qualimap} bamqc -bam {fixed_bam_fname} -outdir {results_dir} "
"--skip-duplicated --skip-dup-mode 0 "
"-nt {num_cores} --java-mem-size={max_mem} {options}")
species = None
if tz.get_in(("genome_resources", "aliases", "human"), data, ""):
species = "HUMAN"
elif any(tz.get_in("genome_build", data, "").startswith(k) for k in ["mm", "GRCm"]):
species = "MOUSE"
if species in ["HUMAN", "MOUSE"]:
cmd += " -gd {species}"
regions = bedutils.merge_overlaps(dd.get_coverage(data), data) or dd.get_variant_regions_merged(data)
if regions:
bed6_regions = _bed_to_bed6(regions, out_dir)
cmd += " -gff {bed6_regions}"
do.run(cmd.format(**locals()), "Qualimap: %s" % dd.get_sample_name(data))
# return _parse_qualimap_metrics(report_file, data)
return dict()
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 calculate(bam_file, data):
"""Calculate coverage in parallel using samtools depth through goleft.
samtools depth removes duplicates and secondary reads from the counts:
if ( b->core.flag & (BAM_FUNMAP | BAM_FSECONDARY | BAM_FQCFAIL | BAM_FDUP) ) continue;
"""
params = {"window_size": 5000, "parallel_window_size": 1e5, "min": dd.get_coverage_depth_min(data),
"high_multiplier": 20}
prefix = os.path.join(
utils.safe_makedir(os.path.join(dd.get_work_dir(data), "align", dd.get_sample_name(data))),
"%s-coverage" % (dd.get_sample_name(data)))
out_file = prefix + ".depth.bed"
callable_file = prefix + ".callable.bed"
variant_regions = dd.get_variant_regions_merged(data)
variant_regions_avg_cov = get_average_coverage(data, bam_file, variant_regions, "variant_regions")
if not utils.file_uptodate(out_file, bam_file):
ref_file = dd.get_ref_file(data)
cmd = ["goleft", "depth", "--windowsize", str(params["window_size"]), "--q", "1",
"--mincov", str(params["min"]), "--reference", ref_file,
"--processes", str(dd.get_num_cores(data)), "--stats", "--ordered"]
window_file = "%s-tocalculate-windows.bed" % utils.splitext_plus(out_file)[0]
if not utils.file_uptodate(window_file, bam_file):
with file_transaction(data, window_file) as tx_out_file:
if not variant_regions:
variant_regions = "%s-genome.bed" % utils.splitext_plus(tx_out_file)[0]
with open(variant_regions, "w") as out_handle:
for c in shared.get_noalt_contigs(data):
out_handle.write("%s\t%s\t%s\n" % (c.name, 0, c.size))
pybedtools.BedTool().window_maker(w=params["parallel_window_size"],
b=pybedtools.BedTool(variant_regions)).saveas(tx_out_file)
cmd += ["--bed", window_file]
max_depth = _get_max_depth(variant_regions_avg_cov, params, data)
if max_depth:
cmd += ["--maxmeandepth", str(int(max_depth))]
with file_transaction(data, out_file) as tx_out_file:
with utils.chdir(os.path.dirname(tx_out_file)):
tx_callable_file = tx_out_file.replace(".depth.bed", ".callable.bed")
prefix = tx_out_file.replace(".depth.bed", "")
cmd += ["--prefix", prefix, bam_file]
bcbio_env = utils.get_bcbio_env()
msg = "Calculate coverage: %s" % dd.get_sample_name(data)
do.run(cmd, msg, env=bcbio_env)
shutil.move(tx_callable_file, callable_file)
return out_file, callable_file, _extract_highdepth(callable_file, data), variant_regions_avg_cov
def calculate_offtarget(bam_file, ref_file, data):
"""Generate file of offtarget read counts for inputs with variant regions.
"""
vrs_file = dd.get_variant_regions_merged(data)
if vrs_file:
out_file = "%s-offtarget-stats.yaml" % os.path.splitext(bam_file)[0]
if not utils.file_exists(out_file):
with file_transaction(data, out_file) as tx_out_file:
offtarget_regions = "%s-regions.bed" % utils.splitext_plus(out_file)[0]
ref_bed = get_ref_bedtool(ref_file, data["config"])
ref_bed.subtract(pybedtools.BedTool(vrs_file), nonamecheck=True).saveas(offtarget_regions)
cmd = ("samtools view -u {bam_file} -L {offtarget_regions} | "
"bedtools intersect -abam - -b {offtarget_regions} -f 1.0 -bed | wc -l")
offtarget_count = int(subprocess.check_output(cmd.format(**locals()), shell=True))
cmd = "samtools idxstats {bam_file} | awk '{{s+=$3}} END {{print s}}'"
mapped_count = int(subprocess.check_output(cmd.format(**locals()), shell=True))
with open(tx_out_file, "w") as out_handle:
yaml.safe_dump({"mapped": mapped_count, "offtarget": offtarget_count}, out_handle,
allow_unicode=False, default_flow_style=False)
return out_file
def postprocess_alignment(data):
"""Perform post-processing steps required on full BAM files.
Prepares list of callable genome regions allowing subsequent parallelization.
"""
data = utils.to_single_data(data)
bam_file = data.get("align_bam") or data.get("work_bam")
if vmulti.bam_needs_processing(data) and bam_file and bam_file.endswith(
".bam"):
ref_file = dd.get_ref_file(data)
out_dir = utils.safe_makedir(
os.path.join(dd.get_work_dir(data), "align",
dd.get_sample_name(data)))
bam_file_ready = os.path.join(out_dir, os.path.basename(bam_file))
if not utils.file_exists(bam_file_ready):
utils.symlink_plus(bam_file, bam_file_ready)
bam.index(bam_file_ready, data["config"])
covinfo = callable.sample_callable_bed(bam_file_ready, ref_file, data)
callable_region_bed, nblock_bed, callable_bed = \
callable.block_regions(covinfo.callable, bam_file_ready, ref_file, data)
vrs_file = dd.get_variant_regions_merged(data)
offtarget_stats = callable.calculate_offtarget_stats(
bam_file_ready, data, vrs_file, "variant_regions")
data["regions"] = {
"nblock": nblock_bed,
"callable": callable_bed,
"highdepth": covinfo.highdepth,
"sample_callable": covinfo.callable,
"coverage_bed": covinfo.coverage,
"avg_coverage": covinfo.avg_coverage,
"offtarget_stats": offtarget_stats
}
data = coverage.assign_interval(data)
if (os.path.exists(callable_region_bed)
and not data["config"]["algorithm"].get("variant_regions")):
data["config"]["algorithm"][
"variant_regions"] = callable_region_bed
data = bedutils.clean_inputs(data)
data = _recal_no_markduplicates(data)
return [[data]]
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 _merge_target_information(samples, metrics_dir):
out_file = os.path.abspath(os.path.join(metrics_dir, "target_info.yaml"))
if utils.file_exists(out_file):
return samples
genomes = set(dd.get_genome_build(data) for data in samples)
coverage_beds = set(dd.get_coverage(data) for data in samples)
original_variant_regions = set(
dd.get_variant_regions_orig(data) for data in samples)
data = samples[0]
info = {}
# Reporting in MultiQC only if the genome is the same across all samples
if len(genomes) == 1:
info["genome_info"] = {
"name":
dd.get_genome_build(data),
"size":
sum([
c.size for c in ref.file_contigs(dd.get_ref_file(data),
data["config"])
]),
}
# Reporting in MultiQC only if the target is the same across all samples
vcr_orig = None
if len(original_variant_regions) == 1 and list(
original_variant_regions)[0] is not None:
vcr_orig = list(original_variant_regions)[0]
vcr_clean = bedutils.clean_file(vcr_orig, data)
info["variants_regions_info"] = {
"bed":
vcr_orig,
"size":
sum(
len(x) for x in pybedtools.BedTool(
dd.get_variant_regions_merged(data))),
"regions":
pybedtools.BedTool(vcr_clean).count(),
}
gene_num = annotate.count_genes(vcr_clean, data)
if gene_num is not None:
info["variants_regions_info"]["genes"] = gene_num
else:
info["variants_regions_info"] = {
"bed": "callable regions",
}
# Reporting in MultiQC only if the target is the same across samples
if len(coverage_beds) == 1:
cov_bed = list(coverage_beds)[0]
if cov_bed not in [None, "None"]:
if vcr_orig and vcr_orig == cov_bed:
info["coverage_bed_info"] = info["variants_regions_info"]
else:
clean_bed = bedutils.clean_file(cov_bed,
data,
prefix="cov-",
simple=True)
info["coverage_bed_info"] = {
"bed": cov_bed,
"size": pybedtools.BedTool(cov_bed).total_coverage(),
"regions": pybedtools.BedTool(clean_bed).count(),
}
gene_num = annotate.count_genes(clean_bed, data)
if gene_num is not None:
info["coverage_bed_info"]["genes"] = gene_num
else:
info["coverage_bed_info"] = info["variants_regions_info"]
coverage_intervals = set(data["config"]["algorithm"]["coverage_interval"]
for data in samples)
if len(coverage_intervals) == 1:
info["coverage_interval"] = list(coverage_intervals)[0]
if info:
with open(out_file, "w") as out_handle:
yaml.safe_dump(info, out_handle)
return samples
def _merge_target_information(samples, metrics_dir):
out_file = os.path.abspath(os.path.join(metrics_dir, "target_info.yaml"))
if utils.file_exists(out_file):
return samples
genomes = set(dd.get_genome_build(data) for data in samples)
coverage_beds = set(dd.get_coverage(data) for data in samples)
original_variant_regions = set(dd.get_variant_regions_orig(data) for data in samples)
data = samples[0]
info = {}
# Reporting in MultiQC only if the genome is the same across all samples
if len(genomes) == 1:
info["genome_info"] = {
"name": dd.get_genome_build(data),
"size": sum([c.size for c in ref.file_contigs(dd.get_ref_file(data), data["config"])]),
}
# Reporting in MultiQC only if the target is the same across all samples
vcr_orig = None
if len(original_variant_regions) == 1 and list(original_variant_regions)[0] is not None:
vcr_orig = list(original_variant_regions)[0]
vcr_clean = bedutils.clean_file(vcr_orig, data)
info["variants_regions_info"] = {
"bed": vcr_orig,
"size": sum(len(x) for x in pybedtools.BedTool(dd.get_variant_regions_merged(data))),
"regions": pybedtools.BedTool(vcr_clean).count(),
}
gene_num = annotate.count_genes(vcr_clean, data)
if gene_num is not None:
info["variants_regions_info"]["genes"] = gene_num
else:
info["variants_regions_info"] = {
"bed": "callable regions",
}
# Reporting in MultiQC only if the target is the same across samples
if len(coverage_beds) == 1:
cov_bed = list(coverage_beds)[0]
if cov_bed not in [None, "None"]:
if vcr_orig and vcr_orig == cov_bed:
info["coverage_bed_info"] = info["variants_regions_info"]
else:
clean_bed = bedutils.clean_file(cov_bed, data, prefix="cov-", simple=True)
info["coverage_bed_info"] = {
"bed": cov_bed,
"size": pybedtools.BedTool(cov_bed).total_coverage(),
"regions": pybedtools.BedTool(clean_bed).count(),
}
gene_num = annotate.count_genes(clean_bed, data)
if gene_num is not None:
info["coverage_bed_info"]["genes"] = gene_num
else:
info["coverage_bed_info"] = info["variants_regions_info"]
coverage_intervals = set(data["config"]["algorithm"]["coverage_interval"] for data in samples)
if len(coverage_intervals) == 1:
info["coverage_interval"] = list(coverage_intervals)[0]
if info:
with open(out_file, "w") as out_handle:
yaml.safe_dump(info, out_handle)
return samples
def _merge_target_information(samples):
out_file = os.path.join("metrics", "target_info.yaml")
if utils.file_exists(out_file):
return samples
genomes = set(dd.get_genome_build(data) for data in samples)
coverage_beds = set(dd.get_coverage(data) for data in samples)
variant_regions = set(dd.get_variant_regions(data) for data in samples)
data = samples[0]
info = {}
# Reporting in MultiQC only if the genome is the sample across samples
if len(genomes) == 1:
info["genome_info"] = {
"name":
dd.get_genome_build(data),
"size":
sum([
c.size for c in ref.file_contigs(dd.get_ref_file(data),
data["config"])
]),
}
# Reporting in MultiQC only if the target is the sample across samples
vcr = None
if len(variant_regions) == 1:
vcr = dd.get_variant_regions_orig(data)
vcr_merged = dd.get_variant_regions_merged(data)
vcr_ann = annotate.add_genes(vcr, data)
info["variants_regions_info"] = {
"bed":
variant_regions,
"size":
sum(len(x) for x in pybedtools.BedTool(vcr_merged)),
"regions":
pybedtools.BedTool(vcr).count(),
"genes":
len(
list(
set(r.name for r in pybedtools.BedTool(vcr_ann)
if r.name and r.name != "."))),
}
elif len(variant_regions) == 0:
info["variants_regions_info"] = {"bed": None}
# Reporting in MultiQC only if the target is the sample across samples
if len(coverage_beds) == 1:
bed = dd.get_coverage(data)
if vcr and vcr == bed:
info["coverage_bed_info"] = info["variants_regions_info"]
elif bed:
ann_bed = annotate.add_genes(bed, data)
info["coverage_bed_info"] = {
"bed":
bed,
"size":
pybedtools.BedTool(bed).total_coverage(),
"regions":
pybedtools.BedTool(bed).count(),
"genes":
len(
list(
set(r.name for r in pybedtools.BedTool(ann_bed)
if r.name and r.name != "."))),
}
if info:
with open(out_file, "w") as out_handle:
yaml.safe_dump(info, out_handle)
return samples
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
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_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
