def test_bedcov_split_lines():
bam_filename = "./pysam_data/ex1.bam"
bed_filename = "./pysam_data/ex1.bed"
lines = pysam.bedcov(bed_filename, bam_filename, split_lines=True) # Test pysam 0.8.X style output, which returns a list of lines
for line in lines:
fields = line.split('\t')
assert len(fields) in [4, 5], "bedcov should give tab delimited output with 4 or 5 fields. Split line (%s) gives %d fields." % (fields, len(fields))
def bedcov(bed_fname, bam_fname):
"""Calculate depth of all regions in a BED file via samtools (pysam) bedcov.
i.e. mean pileup depth across each region.
"""
# Count bases in each region; exclude 0-MAPQ reads
try:
lines = pysam.bedcov(bed_fname, bam_fname, '-Q', '1')
except pysam.SamtoolsError as exc:
raise ValueError("Failed processing %r coverages in %r regions. PySAM error: %s"
% (bam_fname, bed_fname, exc))
if not lines:
raise ValueError("BED file %r sequence IDs don't match any in BAM file %r"
% (bed_fname, bam_fname))
# Return an iterable...
for line in lines:
try:
chrom, start_s, end_s, name, basecount_s = line.split('\t')
except:
raise RuntimeError("Bad line from bedcov:\n" + line)
start, end, basecount = map(int, (start_s, end_s, basecount_s.strip()))
span = end - start
if span > 0:
# Algebra from above
count = basecount / READ_LEN
mean_depth = basecount / span
else:
# User-supplied bins might be oddly constructed
count = mean_depth = 0
yield chrom, start, end, name, count, mean_depth
def bedcov(bed_fname, bam_fname, min_mapq):
"""Calculate depth of all regions in a BED file via samtools (pysam) bedcov.
i.e. mean pileup depth across each region.
"""
# Count bases in each region; exclude low-MAPQ reads
if min_mapq > 0:
bedcov_args = ['-Q', str(min_mapq)]
else:
bedcov_args = []
try:
lines = pysam.bedcov(bed_fname, bam_fname, *bedcov_args)
except pysam.SamtoolsError as exc:
raise ValueError("Failed processing %r coverages in %r regions. PySAM error: %s"
% (bam_fname, bed_fname, exc))
if not lines:
raise ValueError("BED file %r sequence IDs don't match any in BAM file %r"
% (bed_fname, bam_fname))
# Return an iterable...
for line in lines:
try:
chrom, start_s, end_s, name, basecount_s = line.split('\t')
except:
raise RuntimeError("Bad line from bedcov:\n" + line)
start, end, basecount = map(int, (start_s, end_s, basecount_s.strip()))
span = end - start
if span > 0:
# Algebra from above
count = basecount / READ_LEN
mean_depth = basecount / span
else:
# User-supplied bins might be oddly constructed
count = mean_depth = 0
yield chrom, start, end, name, count, mean_depth
def parallelCov(cov_args):
(bam, bed) = cov_args
sampleCov = []
output = {}
mq = 0 #can param min mapping quality if desired
id = os.path.basename(bam)
id = id.split('_')[0]
print("Generating coverage metrics for: " + id)
sys.stdout.flush()
id = id + "_mean_cvg"
cmd = [bed, bam]
cmd.extend(['-Q', bytes(mq)])
bstring = pysam.bedcov(*cmd, split_lines=False)
lines = bstring.splitlines()
targets = []
for line in lines:
fields = line.split('\t')
chr = fields[0]
start = int(fields[1])
end = int(fields[2])
target = fields[3]
coverage = int(fields[4])
intlen = float(end - start)
meancov = str(coverage / intlen)
target = chr + ":" + str(start) + "-" + str(end)
targets.append(target)
sampleCov.append(meancov)
output.update({id: sampleCov})
output.update({'Target': targets})
return (output)
def test_bedcov():
bam_filename = "./pysam_data/ex1.bam"
bed_filename = "./pysam_data/ex1.bed"
bedcov_string = pysam.bedcov(bed_filename, bam_filename, split_lines=False) # Test pysam 0.9.X style output, which returns a string that needs to be split by \n
lines = bedcov_string.splitlines()
for line in lines:
fields = line.split('\t')
assert len(fields) in [4, 5], "bedcov should give tab delimited output with 4 or 5 fields. Split line (%s) gives %d fields." % (fields, len(fields))
def compute_coverage_with_samtools(args, input_bam, mean_coverage):
# Generate GC and chromosome normalized coverage for the entire BAM file
# Based on https://www.biostars.org/p/92744/
logging.info(
"Computing chromosome and GC normalized coverage for %s with samtools and bedtools",
input_bam,
)
with tempfile.NamedTemporaryFile(mode="w", suffix=".bed",
dir=args.tempdir) as window_bed_file:
# pylint: disable=unexpected-keyword-arg
windows_bed = bed.BedTool().window_maker(g=args.genome,
w=args.gc_window_size,
output=window_bed_file.name)
windows_table = (
# pylint: disable=no-member,unexpected-keyword-arg
bed.BedTool(pysam.bedcov(window_bed_file.name, input_bam,
"--reference", args.reference),
from_string=True).nucleotide_content(
fi=args.reference).to_dataframe(
index_col=False,
header=0,
usecols=[0, 1, 2, 3, 7, 8, 10, 11, 12],
names=[
"chrom",
"start",
"end",
"bases",
"num_C",
"num_G",
"num_N",
"num_oth",
"seq_len",
],
dtype={"chrom": str},
))
# Remove windows with no alignable data
windows_table["align_len"] = (windows_table.seq_len - windows_table.num_N -
windows_table.num_oth)
windows_table = windows_table[windows_table.align_len != 0]
# Compute normalized coverage by chromosome
norm_coverage_by_chrom = (windows_table.groupby("chrom").apply(
samtools_norm_coverage_group, mean_coverage).to_dict())
# Compute normalized coverage by GC bin
gc_fraction = np.round(
(windows_table.num_G + windows_table.num_C) / windows_table.align_len,
2)
norm_coverage = (windows_table.bases /
windows_table.align_len) / mean_coverage
norm_coverage_by_gc = (norm_coverage.groupby(gc_fraction).agg(
["count", "mean"]).to_dict())
return norm_coverage_by_chrom, norm_coverage_by_gc
def test_bedcov_split_lines():
bam_filename = os.path.join(BAM_DATADIR, "ex1.bam")
bed_filename = os.path.join(BAM_DATADIR, "ex1.bed")
# Test pysam 0.8.X style output, which returns a list of lines
lines = pysam.bedcov(bed_filename, bam_filename, split_lines=True)
for line in lines:
fields = line.split('\t')
assert len(fields) in [4, 5], \
("bedcov should give tab delimited output with 4 or 5 fields. "
"Split line (%s) gives %d fields." % (fields, len(fields)))
def test_bedcov_split_lines():
bam_filename = os.path.join(BAM_DATADIR, "ex1.bam")
bed_filename = os.path.join(BAM_DATADIR, "ex1.bed")
# Test pysam 0.8.X style output, which returns a list of lines
lines = pysam.bedcov(bed_filename, bam_filename, split_lines=True)
for line in lines:
fields = line.split('\t')
assert len(fields) in [4, 5], \
("bedcov should give tab delimited output with 4 or 5 fields. "
"Split line (%s) gives %d fields." % (fields, len(fields)))
def test_bedcov():
bam_filename = os.path.join(BAM_DATADIR, "ex1.bam")
bed_filename = os.path.join(BAM_DATADIR, "ex1.bed")
# Test pysam 0.9.X style output, which returns a string that needs to be split by \n
bedcov_string = pysam.bedcov(bed_filename, bam_filename, split_lines=False)
lines = bedcov_string.splitlines()
for line in lines:
fields = line.split('\t')
assert len(fields) in [4, 5], \
("bedcov should give tab delimited output with 4 or 5 fields. "
"Split line (%s) gives %d fields." % (fields, len(fields)))
def test_bedcov():
bam_filename = os.path.join(BAM_DATADIR, "ex1.bam")
bed_filename = os.path.join(BAM_DATADIR, "ex1.bed")
# Test pysam 0.9.X style output, which returns a string that needs to be split by \n
bedcov_string = pysam.bedcov(bed_filename, bam_filename, split_lines=False)
lines = bedcov_string.splitlines()
for line in lines:
fields = line.split('\t')
assert len(fields) in [4, 5], \
("bedcov should give tab delimited output with 4 or 5 fields. "
"Split line (%s) gives %d fields." % (fields, len(fields)))
def test_bedcov_split_lines():
bam_filename = "./pysam_data/ex1.bam"
bed_filename = "./pysam_data/ex1.bed"
lines = pysam.bedcov(
bed_filename, bam_filename, split_lines=True
) # Test pysam 0.8.X style output, which returns a list of lines
for line in lines:
fields = line.split('\t')
assert len(fields) in [
4, 5
], "bedcov should give tab delimited output with 4 or 5 fields. Split line (%s) gives %d fields." % (
fields, len(fields))
def test_bedcov():
bam_filename = "./pysam_data/ex1.bam"
bed_filename = "./pysam_data/ex1.bed"
bedcov_string = pysam.bedcov(
bed_filename, bam_filename, split_lines=False
) # Test pysam 0.9.X style output, which returns a string that needs to be split by \n
lines = bedcov_string.splitlines()
for line in lines:
fields = line.split('\t')
assert len(fields) in [
4, 5
], "bedcov should give tab delimited output with 4 or 5 fields. Split line (%s) gives %d fields." % (
fields, len(fields))
def pysam_depth(bam, bed):
"get number of total base in bed region"
if not os.path.isfile(bam + '.bai'):
raise Exception('index for BAM file %s isn\'t found' %(bam))
cmd = [bed, bam]# ,'-Q', bytes(5)]
try:
raw = pysam.bedcov(*cmd, split_lines=False)
except pysam.SamtoolsError as exc:
raise ValueError("Failed processing %r coverages in %r regions. "
"PySAM error: %s" % (bam, bed, exc))
return map(lambda x: int(x.split('\t')[-1]), raw.rstrip().split('\n'))
def bedcov(bed_fname, bam_fname, min_mapq):
"""Calculate depth of all regions in a BED file via samtools (pysam) bedcov.
i.e. mean pileup depth across each region.
"""
# Count bases in each region; exclude low-MAPQ reads
if min_mapq > 0:
bedcov_args = ['-Q', str(min_mapq)]
else:
bedcov_args = []
try:
lines = pysam.bedcov(bed_fname, bam_fname, *bedcov_args)
except pysam.SamtoolsError as exc:
raise ValueError("Failed processing %r coverages in %r regions. PySAM error: %s"
% (bam_fname, bed_fname, exc))
if not lines:
raise ValueError("BED file %r sequence IDs don't match any in BAM file %r"
% (bed_fname, bam_fname))
# Return an iterable...
if isinstance(lines, basestring):
lines = lines.splitlines()
for line in lines:
fields = line.split('\t', 5)
if len(fields) == 5:
chrom, start_s, end_s, gene, basecount_s = fields
elif len(fields) == 4:
chrom, start_s, end_s, basecount_s = fields
gene = "-"
else:
raise RuntimeError("Bad line from bedcov:\n" + line)
start, end, basecount = list(map(int, (start_s, end_s, basecount_s.strip())))
span = end - start
if span > 0:
# Algebra from above
count = basecount / READ_LEN
mean_depth = basecount / span
else:
# User-supplied bins might be oddly constructed
count = mean_depth = 0
row = (chrom, start, end, gene,
math.log(mean_depth, 2) if mean_depth else NULL_LOG2_COVERAGE,
mean_depth)
yield count, row
def bedcov(bed_fname, bam_fname, min_mapq):
"""Calculate depth of all regions in a BED file via samtools (pysam) bedcov.
i.e. mean pileup depth across each region.
"""
# Count bases in each region; exclude low-MAPQ reads
cmd = [bed_fname, bam_fname]
if min_mapq and min_mapq > 0:
cmd.extend(['-Q', bytes(min_mapq)])
try:
raw = pysam.bedcov(*cmd, split_lines=False)
except pysam.SamtoolsError as exc:
raise ValueError("Failed processing %r coverages in %r regions. "
"PySAM error: %s" % (bam_fname, bed_fname, exc))
if not raw:
raise ValueError("BED file %r chromosome names don't match any in "
"BAM file %r" % (bed_fname, bam_fname))
columns = detect_bedcov_columns(raw)
table = pd.read_table(StringIO(raw), names=columns, usecols=columns)
return table
def bedcov(bed_fname, bam_fname, min_mapq):
"""Calculate depth of all regions in a BED file via samtools (pysam) bedcov.
i.e. mean pileup depth across each region.
"""
# Count bases in each region; exclude low-MAPQ reads
cmd = [bed_fname, bam_fname]
if min_mapq and min_mapq > 0:
cmd.extend(['-Q', bytes(min_mapq)])
try:
raw = pysam.bedcov(*cmd, split_lines=False)
except pysam.SamtoolsError as exc:
raise ValueError("Failed processing %r coverages in %r regions. "
"PySAM error: %s" % (bam_fname, bed_fname, exc))
if not raw:
raise ValueError("BED file %r chromosome names don't match any in "
"BAM file %r" % (bed_fname, bam_fname))
columns = detect_bedcov_columns(raw)
table = pd.read_table(StringIO(raw), names=columns, usecols=columns)
return table
def bedcov(bed_fname, bam_fname, min_mapq):
"""Calculate depth of all regions in a BED file via samtools (pysam) bedcov.
i.e. mean pileup depth across each region.
"""
# Count bases in each region; exclude low-MAPQ reads
if min_mapq > 0:
bedcov_args = ['-Q', str(min_mapq)]
else:
bedcov_args = []
try:
lines = pysam.bedcov(bed_fname, bam_fname, *bedcov_args)
except pysam.SamtoolsError as exc:
raise ValueError("Failed processing %r coverages in %r regions. PySAM error: %s"
% (bam_fname, bed_fname, exc))
if not lines:
raise ValueError("BED file %r sequence IDs don't match any in BAM file %r"
% (bed_fname, bam_fname))
# Return an iterable...
if isinstance(lines, basestring):
lines = lines.splitlines()
for line in lines:
fields = line.split('\t')
if len(fields) == 5:
chrom, start_s, end_s, name, basecount_s = fields
elif len(fields) == 4:
chrom, start_s, end_s, basecount_s = fields
name = "-"
else:
raise RuntimeError("Bad line from bedcov:\n" + line)
start, end, basecount = list(map(int, (start_s, end_s, basecount_s.strip())))
span = end - start
if span > 0:
# Algebra from above
count = basecount / READ_LEN
mean_depth = basecount / span
else:
# User-supplied bins might be oddly constructed
count = mean_depth = 0
yield chrom, start, end, name, count, mean_depth
outfile = os.fdopen(fd, "w")
outfile.close()
if k % chunk_size:
outfile.close()
yield name
def bedcov(bam_fname, bed_fname): ## pysam.bedcov ===> 'chr1\t200\t300\t2050\n'
"""Calculate depth of all regions in a BED file via samtools (pysam) bedcov.
i.e. mean pileup depth across each region.
"""
# Count bases in each region; exclude low-MAPQ reads
cmd = [bed_fname, bam_fname]
if min_mapq and min_mapq > 0:
cmd.extend(['-Q', bytes(min_mapq)])
try:
raw = pysam.bedcov(*cmd, split_lines=False)
except pysam.SamtoolsError as exc:
raise ValueError("Failed processing %r coverages in %r regions. "
"PySAM error: %s" % (bam_fname, bed_fname, exc))
if not raw:
raise ValueError("BED file %r chromosome names don't match any in "
"BAM file %r" % (bed_fname, bam_fname))
columns = detect_bedcov_columns(raw)
table = pd.read_csv(StringIO(raw), sep='\t', names=columns, usecols=columns) #******************
return table
def detect_bedcov_columns(text):
"""Determine which 'bedcov' output columns to keep.
Format is the input BED plus a final appended column with the count of
basepairs mapped within each row's region. The input BED might have 3
