def get_genome_coverage(bam_fhands):
coverage_hist = IntCounter()
for bam_fhand in bam_fhands:
bam_fpath = bam_fhand.name
cmd = [get_binary_path('bedtools'), 'genomecov', '-ibam', bam_fpath]
cover_process = Popen(cmd, stdout=PIPE)
for line in cover_process.stdout:
if line.startswith('genome'):
cov, value = line.split('\t')[1:3]
coverage_hist[int(cov)] += int(value)
return coverage_hist
def get_genome_coverage(bam_fhands):
coverage_hist = IntCounter()
for bam_fhand in bam_fhands:
bam_fpath = bam_fhand.name
cmd = [get_binary_path('bedtools'), 'genomecov', '-ibam', bam_fpath]
cover_process = Popen(cmd, stdout=PIPE)
for line in cover_process.stdout:
if line.startswith('genome'):
cov, value = line.split('\t')[1: 3]
coverage_hist[int(cov)] += int(value)
return coverage_hist
def get_reference_counts(bam_fpath):
'Using samtools idxstats it generates dictionaries with read counts'
cmd = [get_binary_path('samtools'), 'idxstats', bam_fpath]
idx_process = Popen(cmd, stdout=PIPE)
# we're not using pysam.idxstats here because the stdout differed
# depending on how the tests were run
for line in idx_process.stdout:
ref_name, ref_length, mapped_reads, unmapped_reads = line.split()
if ref_name == '*':
ref_name = None
ref_length = None
else:
ref_length = int(ref_length)
yield {'reference': ref_name, 'length': ref_length,
'mapped_reads': int(mapped_reads),
'unmapped_reads': int(unmapped_reads)}
def get_reference_counts(bam_fpath):
'Using samtools idxstats it generates dictionaries with read counts'
cmd = [get_binary_path('samtools'), 'idxstats', bam_fpath]
idx_process = Popen(cmd, stdout=PIPE)
# we're not using pysam.idxstats here because the stdout differed
# depending on how the tests were run
for line in idx_process.stdout:
ref_name, ref_length, mapped_reads, unmapped_reads = line.split()
if ref_name == '*':
ref_name = None
ref_length = None
else:
ref_length = int(ref_length)
yield {
'reference': ref_name,
'length': ref_length,
'mapped_reads': int(mapped_reads),
'unmapped_reads': int(unmapped_reads)
}