unmap2virus_bams = extract_bam(sorted_bams,'unmap',seqType,thread) # [file.sort.unmap2host.sort.unmap.bam]
# rename files
for f in map2virus_bams: os.rename(f,f[:-29]+'.only2virus.bam')
map2virus_bams = [f[:-29]+'.only2virus.bam' for f in map2virus_bams] # [file.only2virus.bam]
for f in unmap2virus_bams: os.rename(f,f[:-31]+'.map2neither.bam') # [file.map2neither.bam]
unmap2virus_bams = [f[:-31]+'.map2neither.bam' for f in unmap2virus_bams]
print 'extract map and unmap2virus_bams succeed'
print 'map2virus_bams is: ',map2virus_bams,'unmap2virus_bams is: ',unmap2virus_bams
remove(sorted_bams)
except:
print 'extract map and unmap2virus_bams failed'
Message('extract map and unmap2virus_bams failed',email)
raise
#======== (4) transfer the mapped and unmapped to virus bam to fastq =======
try:
map2virus_fq_gzs = sam2fastq(picard,map2virus_bams,seqType) # [[file.only2virus.fq.gz]]
unmap2virus_fq_gzs = sam2fastq(picard,unmap2virus_bams,seqType) # [[file.map2neither.fq.gz]]
print 'transfer from bam to fq succeed'
print 'map2virus_fq_gzs is: ',map2virus_fq_gzs,'unmap2virus_fq_gzs',unmap2virus_fq_gzs
remove(map2virus_bams);remove(unmap2virus_bams)
except:
print 'transfer from bam to fq failed'
Message('transfer from bam to fq failed',email)
raise
#======== (5) transfer the unmapped to virus fastq to fasta =================
try:
only2virus_faFiles = fq2fa(map2virus_fq_gzs) # [file.only2virus.fa.gz]
map2neither_faFiles = fq2fa(unmap2virus_fq_gzs) # [file.map2neither.fa.gz]
print 'fq files to fa files succeed'
print 'only2virus_faFiles is: ',only2virus_faFiles,'map2neither_faFiles is: ',map2neither_faFiles
remove(map2virus_fq_gzs); remove(unmap2virus_fq_gzs)
#======== (5) extract unmapped reads =============================
try:
unmap2host_bams = extract_bam(sorted_bams,'unmap',seqType,thread) # [file.sort.unmap.bam]
print 'extract unmap2host_bams succeed'
print 'unmap2host_bams is: ',unmap2host_bams
remove(sorted_bams)
# rename files
for f in unmap2host_bams: os.rename(f,f[:-4]+'2host.bam')
unmap2host_bams = [f[:-4]+'2host.bam' for f in unmap2host_bams] # [file.sort.unmap2host.bam]
except:
print 'extract unmap2host_bams failed'
Message('extract unmap2host_bams failed',email)
raise
#======== (6) unmap2host_bams to fastq ============================
try:
unmap2host_fqs = sam2fastq(picard,unmap2host_bams,seqType) # [[file.sort.unmap2host.fq.gz]]
print 'unmap2host_fq succeed'
print 'unmap2host_fqs is: ',unmap2host_fqs
remove(unmap2host_bams)
except:
print 'unmap2host_fq failed'
Message('unmap2host_fq failed',email)
raise
#===========================================================================
# 2. Map to virus reference genome
#===========================================================================
#======== (1) align unmap2host_fq to virus =========================
try:
if aligner == 'gsnap':
map_files = gsnap(unmap2host_fqs,virus_alignerDb, virus_gsnapDbName,virus_gsnapAnnotation,thread)
else: