def convertPs(psfile):
"""Utility function to convert ps file to pdf
during test
"""
if os.path.isfile(psfile):
cmd = "ps2pdf %s" % (psfile)
runCommand(cmd, "T")
else:
pass
return
def trim_Ad1_Ad2(input_fq, trimleft, trimright, output_fq):
"""Trim TEMPOseq adaptors from the fastq file, both 3' and 5' adaptors are 17 nc"""
cmds = [
'seqtk trimfq',
'-b ', str(trimleft),
'-e ', str(trimright),
input_fq,
'> ', output_fq,
]
cmds = ' '.join(cmds)
runCommand(cmds, True)
def createQuality(input, output):
"""Check quality of the fastqfile
Arguments:
-`input`: The input fastq file
-`output`: The output folder for the analysis
"""
cmds = [
'fastqc',
input,
'-o', output,
]
cmds = ' '.join(cmds)
cmds += " 2>&1 | tee -a " + output + "/analysis_quality.log"
runCommand(cmds, True)
return
def split_well_barcode(wellbarcode, fastqFile, inputDir, prefixWell, suffix):
"""split fastq based on plate barcode"""
cmds = [
'cat', fastqFile, '|',
'fastx_barcode_splitter.pl',
'--bcfile',wellbarcode,
'--prefix', prefixWell,
'--suffix', suffix,
'--bol',
'--partial', str(1),
'--mismatches', str(1),
]
welllog = prefixWell + "wellsplit_barcode.log"
cmds =' '.join(cmds)
cmds +=" 2>&1 | tee " + welllog
runCommand(cmds, True)
return
def split_plate_barcode(barcodes,fastqFile, outDir, prefixPlate,suffix):
"""split fastq based on plate barcode"""
platebc = barcodes[0]
cmds = [
'cat', fastqFile, '|',
'fastx_barcode_splitter.pl',
'--bcfile', platebc,
'--prefix', prefixPlate,
'--suffix', suffix,
'--eol',
'--partial', str(1),
'--mismatches', str(1),
]
plateLog = prefixPlate + "platesplit_barcode.log"
cmds =' '.join(cmds)
cmds +=" 2>&1 | tee " + plateLog
runCommand(cmds, True)
return
def map_seq_to_probes(fastq, genomeDir, numCPU, outPrefix):
"""Map the sequence to the probes genome file using STAR"""
cmds = [
'STAR',
'--genomeDir', genomeDir,
'--readFilesIn', fastq,
'--readFilesCommand zcat',
'--runThreadN ', str(numCPU),
'--outFileNamePrefix', outPrefix,
'--outSAMtype SAM',
'--scoreDelOpen -10000',
'--scoreInsOpen -10000',
'--outFilterMismatchNmax 2',
'--outSAMunmapped Within',
'--outSAMattributes AS nM',
' --genomeLoad NoSharedMemory',
]
cmds = ' '.join(cmds)
runCommand(cmds, True)
def index_db_file(input, output, cpuNum, gtfFile):
"""Index the probe fastfile to use as db file"""
with open(input) as myfile:
head = [next(myfile) for x in xrange(2)]
#print head
seq = head[1].strip()
seqLen = len(seq)
print seqLen
print input
cmd = [
'grep',
'">"',
input,
'| wc -l',
]
cmd = ' '.join(cmd)
totalProbes = runCommand(cmd, True)
totalProbes = totalProbes[0].strip()
print totalProbes
genomeSize = int(seqLen) * int(totalProbes)
print genomeSize
scale_factor = np.fmin(14, np.log2(genomeSize) / 2 - 1)
scale_factor = np.round(scale_factor).astype(int)
print scale_factor
cmds = [
'STAR',
'--runMode genomeGenerate',
'--genomeDir',
output,
'--genomeFastaFiles',
input,
'--sjdbGTFfile',
gtfFile,
'--sjdbGTFfeatureExon exon',
'--runThreadN',
str(cpuNum),
'--genomeSAindexNbases',
str(scale_factor),
]
cmds = ' '.join(cmds)
cmds += " 2>&1 | tee -a " + output + "/index_STAR_genomeFile.log"
runCommand(cmds, True)
return
def count_mapped(bamFile, outfile, gtfFile):
"""count mapped reads mapped to genome features
-m union, intersection-nonempty
"""
cmds = [
'htseq-count',
'-f sam',
'-s no',
'-a 10',
'-t exon',
'-i gene_id',
'-m intersection-nonempty',
bamFile,
gtfFile,
'>', outfile,
]
cmds = ' '.join(cmds)
runCommand(cmds, True)
def sameTissueBamMerge(input, output):
if len(input) > 1:
inFile = " ".join(input)
myDir, baseFile = os.path.split(output)
cmds = [
'samtools merge',
baseFile,
inFile,
]
cmds = ' '.join(cmds)
runCommand(cmds, True)
cmds2 = [
'mv',
baseFile,
myDir,
]
cmds2 = ' '.join(cmds2)
runCommand(cmds2, True)
return
else:
inFile = " ".join(input)
cmds = [
'cp ',
inFile,
output,
]
cmds = ' '.join(cmds)
runCommand(cmds, True)
return
def index_db_file(input, output, cpuNum, gtfFile):
"""Index the probe fastfile to use as db file"""
with open(input) as myfile:
head = [next(myfile) for x in xrange(2)]
#print head
seq = head[1].strip()
seqLen = len(seq)
print seqLen
print input
cmd = [
'grep',
'">"',
input,
'| wc -l',
]
cmd = ' '.join(cmd)
totalProbes= runCommand(cmd, True)
totalProbes = totalProbes[0].strip()
print totalProbes
genomeSize= int(seqLen)*int(totalProbes)
print genomeSize
scale_factor = np.fmin(14, np.log2(genomeSize)/2-1)
scale_factor = np.round(scale_factor).astype(int)
print scale_factor
cmds = [
'STAR',
'--runMode genomeGenerate',
'--genomeDir', output,
'--genomeFastaFiles', input,
'--sjdbGTFfile', gtfFile,
'--sjdbGTFfeatureExon exon',
'--runThreadN', str(cpuNum),
'--genomeSAindexNbases', str(scale_factor),
]
cmds = ' '.join(cmds)
cmds += " 2>&1 | tee -a " + output + "/index_STAR_genomeFile.log"
runCommand(cmds, True)
return
def trimFastq(input, output, trimLeft, proFastq):
"""Clean fastq file using trim_galore"""
cmds = [
'trim_galore',
'-q',
str(20),
'--stringency',
str(5),
'--trim1',
'--clip_R1',
str(trimLeft),
'--trim-n',
'--phred33',
'--gzip',
'--illumina',
input,
'-o',
proFastq,
]
cmds = ' '.join(cmds)
runCommand(cmds, True)
return
def map_seq_to_probes(fastq, genomeDir, numCPU, outPrefix):
"""Map the sequence to the probes genome file using STAR"""
cmds = [
'STAR',
'--genomeDir',
genomeDir,
'--readFilesIn',
fastq,
'--readFilesCommand zcat',
'--runThreadN ',
str(numCPU),
'--outFileNamePrefix',
outPrefix,
'--outSAMtype SAM',
'--scoreDelOpen -10000',
'--scoreInsOpen -10000',
'--outFilterMismatchNmax 2',
'--outSAMunmapped Within',
'--outSAMattributes NH HI AS nM',
' --genomeLoad NoSharedMemory',
]
cmds = ' '.join(cmds)
runCommand(cmds, True)
def split_well_barcode(wellbarcode, fastqFile, inputDir, prefixWell, suffix):
"""split fastq based on plate barcode"""
cmds = [
'cat',
fastqFile,
'|',
'fastx_barcode_splitter.pl',
'--bcfile',
wellbarcode,
'--prefix',
prefixWell,
'--suffix',
suffix,
'--bol',
'--partial',
str(1),
'--mismatches',
str(1),
]
welllog = prefixWell + "wellsplit_barcode.log"
cmds = ' '.join(cmds)
cmds += " 2>&1 | tee " + welllog
runCommand(cmds, True)
return
def index_bam_file(bamfile):
"""Index bam files"""
cmds = "samtools index %s" % (bamfile)
runCommand(cmds, True)
def sortBamFile(bamfile, outSuffix):
"""docstring for sortBamFile"""
cmds = "samtools sort -m 1000000000 %s %s" % (bamfile, outSuffix)
runCommand(cmds, True)
def convertSamToBam(samfile, bamfileout):
"""Convert sam file to bam file"""
cmds = "samtools view -b -S %s > %s" % (samfile, bamfileout)
runCommand(cmds, True)
def countReadsMappedToProbes(bamindex, outfile):
"""docstring for countReadsMappedToProbes"""
cmds = "samtools idxstats %s > %s " % (bamindex, outfile)
runCommand(cmds, True)
def countReadsMappedToProbes(bamindex, outfile):
"""docstring for countReadsMappedToProbes"""
cmds = "samtools idxstats %s > %s " %(bamindex, outfile)
runCommand(cmds, True)
def index_bam_file(bamfile):
"""Index bam files"""
cmds = "samtools index %s" %(bamfile)
runCommand(cmds, True)
def sortBamFile(bamfile, outSuffix):
"""docstring for sortBamFile"""
cmds = "samtools sort -m 1000000000 %s %s" %(bamfile, outSuffix)
runCommand(cmds, True)
def convertSamToBam(samfile, bamfileout):
"""Convert sam file to bam file"""
cmds = "samtools view -b -S %s > %s"%(samfile, bamfileout)
runCommand(cmds, True)