def get_contigs(data):
contigs = [x.name for x in shared.get_noalt_contigs(data)]
keep = [
x for x in contigs
if chromhacks.is_autosomal(x) or chromhacks.is_sex(x)
]
return keep
def depth_freq_filter(line, tumor_index, aligner):
"""Command line to filter VarDict calls based on depth, frequency and quality.
Looks at regions with low depth for allele frequency (AF * DP < 6, the equivalent
of < 13bp for heterogygote calls, but generalized. Within these calls filters if a
calls has:
- Low mapping quality and multiple mismatches in a read (NM)
For bwa only: MQ < 55.0 and NM > 1.0 or MQ < 60.0 and NM > 2.0
- Low depth (DP < 10)
- Low QUAL (QUAL < 45)
Also filters in low allele frequency regions with poor quality, if all of these are
true:
- Allele frequency < 0.2
- Quality < 55
- P-value (SSF) > 0.06
"""
if line.startswith("#CHROM"):
headers = [('##FILTER=<ID=LowAlleleDepth,Description="Low depth per allele frequency '
'along with poor depth, quality, mapping quality and read mismatches.">'),
('##FILTER=<ID=LowFreqQuality,Description="Low frequency read with '
'poor quality and p-value (SSF).">')]
return "\n".join(headers) + "\n" + line
elif line.startswith("#"):
return line
else:
parts = line.split("\t")
sample_ft = {a: v for (a, v) in zip(parts[8].split(":"), parts[9 + tumor_index].split(":"))}
qual = utils.safe_to_float(parts[5])
dp = utils.safe_to_float(sample_ft.get("DP"))
af = utils.safe_to_float(sample_ft.get("AF"))
nm = utils.safe_to_float(sample_ft.get("NM"))
mq = utils.safe_to_float(sample_ft.get("MQ"))
ssfs = [x for x in parts[7].split(";") if x.startswith("SSF=")]
pval = utils.safe_to_float(ssfs[0].split("=")[-1] if ssfs else None)
fname = None
if not chromhacks.is_sex(parts[0]) and dp is not None and af is not None:
if dp * af < 6:
if aligner == "bwa" and nm is not None and mq is not None:
if (mq < 55.0 and nm > 1.0) or (mq < 60.0 and nm > 2.0):
fname = "LowAlleleDepth"
if dp < 10:
fname = "LowAlleleDepth"
if qual is not None and qual < 45:
fname = "LowAlleleDepth"
if af is not None and qual is not None and pval is not None:
if af < 0.2 and qual < 45 and pval > 0.06:
fname = "LowFreqQuality"
if fname:
if parts[6] in set([".", "PASS"]):
parts[6] = fname
else:
parts[6] += ";%s" % fname
line = "\t".join(parts)
return line
def _goleft_indexcov(bam_file, data, out_dir):
"""Use goleft indexcov to estimate coverage distributions using BAM index.
Only used for whole genome runs as captures typically don't have enough data
to be useful for index-only summaries.
"""
if not dd.get_coverage_interval(data) == "genome":
return []
out_dir = utils.safe_makedir(os.path.join(out_dir, "indexcov"))
out_files = [
os.path.join(out_dir,
"%s-indexcov.%s" % (dd.get_sample_name(data), ext))
for ext in ["roc", "ped", "bed.gz"]
]
if not utils.file_uptodate(out_files[-1], bam_file):
with transaction.tx_tmpdir(data) as tmp_dir:
tmp_dir = utils.safe_makedir(
os.path.join(tmp_dir, dd.get_sample_name(data)))
gender_chroms = [
x.name for x in ref.file_contigs(dd.get_ref_file(data))
if chromhacks.is_sex(x.name)
]
gender_args = "--sex %s" % (
",".join(gender_chroms)) if gender_chroms else ""
# XXX Skip gender args until we can correctly specify #1793
gender_args = ""
cmd = "goleft indexcov --directory {tmp_dir} {gender_args} -- {bam_file}"
try:
do.run(cmd.format(**locals()), "QC: goleft indexcov")
except subprocess.CalledProcessError as msg:
if not ("indexcov: no usable" in str(msg) or
("indexcov: expected" in str(msg)
and "sex chromosomes, found:" in str(msg))):
raise
for out_file in out_files:
orig_file = os.path.join(tmp_dir, os.path.basename(out_file))
if utils.file_exists(orig_file):
utils.copy_plus(orig_file, out_file)
# MultiQC needs non-gzipped/BED inputs so unpack the file
out_bed = out_files[-1].replace(".bed.gz", ".tsv")
if utils.file_exists(out_files[-1]) and not utils.file_exists(out_bed):
with transaction.file_transaction(data, out_bed) as tx_out_bed:
cmd = "gunzip -c %s > %s" % (out_files[-1], tx_out_bed)
do.run(cmd, "Unpack indexcov BED file")
out_files[-1] = out_bed
return [x for x in out_files if utils.file_exists(x)]
def _goleft_indexcov(bam_file, data, out_dir):
"""Use goleft indexcov to estimate coverage distributions using BAM index.
Only used for whole genome runs as captures typically don't have enough data
to be useful for index-only summaries.
"""
if not dd.get_coverage_interval(data) == "genome":
return []
out_dir = utils.safe_makedir(os.path.join(out_dir, "indexcov"))
out_files = [os.path.join(out_dir, "%s-indexcov.%s" % (dd.get_sample_name(data), ext))
for ext in ["roc", "ped", "bed.gz"]]
if not utils.file_uptodate(out_files[-1], bam_file):
with transaction.tx_tmpdir(data) as tmp_dir:
tmp_dir = utils.safe_makedir(os.path.join(tmp_dir, dd.get_sample_name(data)))
gender_chroms = [x.name for x in ref.file_contigs(dd.get_ref_file(data)) if chromhacks.is_sex(x.name)]
gender_args = "--sex %s" % (",".join(gender_chroms)) if gender_chroms else ""
cmd = "goleft indexcov --directory {tmp_dir} {gender_args} -- {bam_file}"
try:
do.run(cmd.format(**locals()), "QC: goleft indexcov")
except subprocess.CalledProcessError as msg:
if not ("indexcov: no usable" in str(msg) or
("indexcov: expected" in str(msg) and "sex chromosomes, found:" in str(msg))):
raise
for out_file in out_files:
orig_file = os.path.join(tmp_dir, os.path.basename(out_file))
if utils.file_exists(orig_file):
utils.copy_plus(orig_file, out_file)
# MultiQC needs non-gzipped/BED inputs so unpack the file
out_bed = out_files[-1].replace(".bed.gz", ".tsv")
if utils.file_exists(out_files[-1]) and not utils.file_exists(out_bed):
with transaction.file_transaction(data, out_bed) as tx_out_bed:
cmd = "gunzip -c %s > %s" % (out_files[-1], tx_out_bed)
do.run(cmd, "Unpack indexcov BED file")
out_files[-1] = out_bed
return [x for x in out_files if utils.file_exists(x)]
