def rm_unmapped_lowq_reads_se(bam, multimapping, mapq_thresh, nth, out_dir):
prefix = os.path.join(out_dir,
os.path.basename(strip_ext_bam(bam)))
filt_bam = '{}.filt.bam'.format(prefix)
if multimapping:
qname_sort_bam = samtools_name_sort(bam, nth, out_dir)
cmd2 = 'samtools view -h {} | '
cmd2 += '$(which assign_multimappers.py) -k {} | '
cmd2 += 'samtools view -F 1804 -Su /dev/stdin | '
cmd2 += 'samtools sort /dev/stdin -o {} -T {} -@ {}'
cmd2 = cmd2.format(
qname_sort_bam,
multimapping,
filt_bam,
prefix,
nth)
run_shell_cmd(cmd2)
rm_f(qname_sort_bam) # remove temporary files
else:
cmd = 'samtools view -F 1804 -q {} -u {} | '
cmd += 'samtools sort /dev/stdin -o {} -T {} -@ {}'
cmd = cmd.format(
mapq_thresh,
bam,
filt_bam,
prefix,
nth)
run_shell_cmd(cmd)
return filt_bam
def pbc_qc_pe(bam, mito_chr_name, nth, out_dir):
prefix = os.path.join(out_dir, os.path.basename(strip_ext_bam(bam)))
pbc_qc = '{}.lib_complexity.qc'.format(prefix)
nmsrt_bam = samtools_name_sort(bam, nth, out_dir)
cmd3 = 'bedtools bamtobed -bedpe -i {} | '
cmd3 += 'awk \'BEGIN{{OFS="\\t"}}{{print $1,$2,$4,$6,$9,$10}}\' | '
cmd3 += 'grep -v "^{}\\s" | sort | uniq -c | '
cmd3 += 'awk \'BEGIN{{mt=0;m0=0;m1=0;m2=0}} ($1==1){{m1=m1+1}} '
cmd3 += '($1==2){{m2=m2+1}} {{m0=m0+1}} {{mt=mt+$1}} END{{m1_m2=-1.0; '
cmd3 += 'if(m2>0) m1_m2=m1/m2; m0_mt=0; '
cmd3 += 'if (mt>0) m0_mt=m0/mt; m1_m0=0; if (m0>0) m1_m0=m1/m0; '
cmd3 += 'printf "%d\\t%d\\t%d\\t%d\\t%f\\t%f\\t%f\\n"'
cmd3 += ',mt,m0,m1,m2,m0_mt,m1_m0,m1_m2}}\' > {}'
cmd3 = cmd3.format(nmsrt_bam, mito_chr_name, pbc_qc)
run_shell_cmd(cmd3)
rm_f(nmsrt_bam)
return pbc_qc
def rm_unmapped_lowq_reads_se(bam, multimapping, mapq_thresh, nth, mem_gb,
out_dir):
"""There are pipes with multiple samtools commands.
For such pipes, use multiple threads (-@) for only one of them.
Priority is on sort > index > fixmate > view.
"""
prefix = os.path.join(out_dir, os.path.basename(strip_ext_bam(bam)))
filt_bam = '{}.filt.bam'.format(prefix)
if multimapping:
qname_sort_bam = samtools_name_sort(bam, nth, mem_gb, out_dir)
run_shell_cmd(
'samtools view -h {qname_sort_bam} | '
'$(which assign_multimappers.py) -k {multimapping} | '
'samtools view -F 1804 -Su /dev/stdin | '
'samtools sort /dev/stdin -o {filt_bam} -T {prefix} {res_param}'.
format(
qname_sort_bam=qname_sort_bam,
multimapping=multimapping,
filt_bam=filt_bam,
prefix=prefix,
res_param=get_samtools_res_param('sort',
nth=nth,
mem_gb=mem_gb),
))
rm_f(qname_sort_bam) # remove temporary files
else:
run_shell_cmd(
'samtools view -F 1804 -q {mapq_thresh} -u {bam} | '
'samtools sort /dev/stdin -o {filt_bam} -T {prefix} {res_param}'.
format(
mapq_thresh=mapq_thresh,
bam=bam,
filt_bam=filt_bam,
prefix=prefix,
res_param=get_samtools_res_param('sort',
nth=nth,
mem_gb=mem_gb),
))
return filt_bam
def pbc_qc_pe(bam, mito_chr_name, nth, mem_gb, out_dir):
prefix = os.path.join(out_dir, os.path.basename(strip_ext_bam(bam)))
pbc_qc = '{}.lib_complexity.qc'.format(prefix)
nmsrt_bam = samtools_name_sort(bam, nth, mem_gb, out_dir)
run_shell_cmd(
'bedtools bamtobed -bedpe -i {nmsrt_bam} | '
'awk \'BEGIN{{OFS="\\t"}}{{print $1,$2,$4,$6,$9,$10}}\' | '
'grep -v "^{mito_chr_name}\\s" | sort {sort_param} | uniq -c | '
'awk \'BEGIN{{mt=0;m0=0;m1=0;m2=0}} ($1==1){{m1=m1+1}} '
'($1==2){{m2=m2+1}} {{m0=m0+1}} {{mt=mt+$1}} END{{m1_m2=-1.0; '
'if(m2>0) m1_m2=m1/m2; m0_mt=0; '
'if (mt>0) m0_mt=m0/mt; m1_m0=0; if (m0>0) m1_m0=m1/m0; '
'printf "%d\\t%d\\t%d\\t%d\\t%f\\t%f\\t%f\\n"'
',mt,m0,m1,m2,m0_mt,m1_m0,m1_m2}}\' > {pbc_qc}'.format(
nmsrt_bam=nmsrt_bam,
mito_chr_name=mito_chr_name,
sort_param=get_gnu_sort_param(mem_gb * 1024**3, ratio=0.5),
pbc_qc=pbc_qc,
))
rm_f(nmsrt_bam)
return pbc_qc
def bam2ta_pe(bam, nth, out_dir):
prefix = os.path.join(out_dir, os.path.basename(strip_ext_bam(bam)))
ta = '{}.tagAlign.gz'.format(prefix)
# intermediate files
bedpe = '{}.bedpe.gz'.format(prefix)
nmsrt_bam = samtools_name_sort(bam, nth, out_dir)
cmd1 = 'LC_COLLATE=C bedtools bamtobed -bedpe -mate1 -i {} | '
# cmd1 += 'sort -k1,1 -k2,2n -k3,3n | '
cmd1 += 'gzip -nc > {}'
cmd1 = cmd1.format(nmsrt_bam, bedpe)
run_shell_cmd(cmd1)
rm_f(nmsrt_bam)
cmd2 = 'zcat -f {} | '
cmd2 += 'awk \'BEGIN{{OFS="\\t"}}'
cmd2 += '{{printf "%s\\t%s\\t%s\\tN\\t1000\\t%s\\n'
cmd2 += '%s\\t%s\\t%s\\tN\\t1000\\t%s\\n",'
cmd2 += '$1,$2,$3,$9,$4,$5,$6,$10}}\' | '
cmd2 += 'gzip -nc > {}'
cmd2 = cmd2.format(bedpe, ta)
run_shell_cmd(cmd2)
rm_f(bedpe)
return ta