output_path = param['htseqOutPath']
db_name = param['gsnapDbName']
gsnap_annotation = param['gsnapAnnotation']
Dict = param['symbolIDFile']
inputpath = file_path
#=========== (0) enter the directory ================
Message(startMessage, email)
os.chdir(file_path)
#=========== (1) reads files and trim ===============
fastqFiles = list_files(file_path)
if trim == 'True':
fastqFiles = Trimmomatic(trimmomatic, fastqFiles, phred, trimmoAdapter)
print 'list file succeed'
#=========== (2) run gsnap to do the mapping ========
if aligner == 'gsnap':
map_files = gsnap(fastqFiles, db_path, db_name, gsnap_annotation, thread)
else:
map_files = STAR(fastqFiles, db_path, thread)
print 'align succeed'
#=========== (3) samtools to sort the file ==========
sorted_bam = sam2bam_sort(map_files, thread)
print 'sorted succeed'
#=========== (4) htseq_count ========================
htseq_count(sorted_bam, annotation, file_path)
print 'htseq count succeed'
#=========== (5) htseq symbol to id =================
ID_Convert(Dict, output_path, inputpath)
print 'id convert succeed'
Message(endMessage, email)
output_path = param['htseqOutPath']
db_name = param['gsnapDbName']
gsnap_annotation = param['gsnapAnnotation']
Dict = param['symbolIDFile']
inputpath = file_path
#=========== (0) enter the directory ================
Message(startMessage,email)
os.chdir(file_path)
#=========== (1) reads files and trim ===============
fastqFiles = list_files(file_path)
if trim == 'True':
fastqFiles = Trimmomatic(trimmomatic,fastqFiles,phred,trimmoAdapter)
print 'list file succeed'
#=========== (2) run gsnap to do the mapping ========
if aligner == 'gsnap':
map_files = gsnap(fastqFiles,db_path, db_name,gsnap_annotation,thread)
else:
map_files = STAR(fastqFiles,db_path,thread)
print 'align succeed'
#=========== (3) samtools to sort the file ==========
sorted_bam = sam2bam_sort(map_files,thread)
print 'sorted succeed'
#=========== (4) htseq_count ========================
htseq_count(sorted_bam,annotation,file_path)
print 'htseq count succeed'
#=========== (5) htseq symbol to id =================
ID_Convert(Dict,output_path,inputpath)
print 'id convert succeed'
Message(endMessage,email)
except:
print 'host align failed'
Message('host align failed',email)
raise
#======== (3) sam to bam and sort ================================
try:
sorted_bams = sam2bam_sort(map_files,thread) # [file.sort.bam]
print 'host sorted succeed'
print 'sorted_bam is: ',sorted_bams
except:
print 'host sorted failed'
Message('host sorted failed',email)
raise
#======== (4) get htseq Count to host ============================
try:
htseq_count(sorted_bams,host_annotation,host_htseqFolder,host_AnnotationSource)
print 'host htseqCount succeed'
except:
print 'host htseq count failed'
Message('host htseq count failed',email)
raise
#======== (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 'sorted_bam is: ',sorted_bams
except:
print 'sorted failed'
Message('sorted failed',email)
raise
#=========== (4) get mapping stats ==================
try:
flagstat(sorted_bams)
print 'flagstat succeed'
except:
print 'flagstat failed'
Message('flagstat failed',email)
raise
#=========== (4) htseq_count ========================
try:
htseq_count(sorted_bams,annotation,output_path,dataSource,htseqBatch)
print 'htseq count succeed'
except:
print 'htseq count failed'
Message('htseq count failed',email)
raise
#=========== (5) htseq symbol to id =================
if dataSource == 'ncbi':
try:
geneSymbol2EntrezID(Dict,output_path,output_path)
print 'id convert succeed'
except:
print 'id convert failed'
Message('id convert failed',email)
raise
Message(endMessage,email)
