def getTotalAlignments(f):
runCommand("samtools idxstats " + f, open("temp", "w"))
total = 0
for line in open("temp").readlines():
total += int(line.split()[2])
runCommand("rm temp")
return total
def findBamAlignments(bamfile,chrom,start,end):
samtoolsViewRegion(bamfile,chrom,start,end,"temp")
alignRange = [start,end]
def rangeCheck(line):
if line[0] == "@":
return #header line
pieces = line.split()
seqname = pieces[0]
ch = pieces[2]
pos = int(pieces[3])
testnumber = int(pieces[1])
if testnumber&0x4 == 0x4:
pass
else:
if pos < alignRange[0]:
alignRange[0] = pos
if pos > alignRange[1]:
alignRange[1] = pos
efficientFileRead("temp",rangeCheck)
def lineCheck(line):
if line[0] == "@":
return #header line
pieces = line.split()
seqname = pieces[0]
ch = pieces[2]
pos = int(pieces[3])
testnumber = int(pieces[1])
if testnumber&0x4 == 0x4:
pass
elif ch == chrom:
ret[pos-start]+=1
ret = [0 for x in range(alignRange[1]-alignRange[0]+1)]
efficientFileRead("temp",lineCheck)
runCommand("rm temp")
return ret
def samtoolsViewRegion(bamfile,chrom,start,end,outfile): command = "samtools view " + bamfile + " " + chrom + ":" + str(start) + "-" + str(end) outf = open(outfile,"w") runCommand(command,outf,None) outf.close()
def samtoolsViewRegions(bamfile,outfile,regions): command = "samtools view -h " + bamfile + " " + regions outf = open(outfile,"w") runCommand(command,outf,None) outf.close()
def bedGraphToBigWig(align,chroms,out):
bash.runCommand("bedGraphToBigWig "+align+" "+chroms+" "+out)
def sortBedGraph(align,out):
bash.runCommand("sort -k1,1 -k2,2n "+align,open(out,"w"))
def bamToBedGraph(align,chroms,out):
bash.runCommand("genomeCoverageBed -bg -ibam "+align+" -g "+chroms,open(out,"w"))
import bash
def bamToBedGraph(align,chroms,out):
bash.runCommand("genomeCoverageBed -bg -ibam "+align+" -g "+chroms,open(out,"w"))
def sortBedGraph(align,out):
bash.runCommand("sort -k1,1 -k2,2n "+align,open(out,"w"))
def bedGraphToBigWig(align,chroms,out):
bash.runCommand("bedGraphToBigWig "+align+" "+chroms+" "+out)
if __name__=="__main__":
import sys, getopt
opts,args = getopt.getopt(sys.argv[1:],"")
align = args[0]
chroms = args[1]
out = args[2]
bamToBedGraph(align,chroms,"temp")
sortBedGraph("temp","temp.sorted")
bedGraphToBigWig("temp.sorted",chroms,out)
bash.runCommand("rm temp temp.sorted")
changeDir(tissueLocation+tissue+"/")
errfile = open(tissue+".rpkmPipeline.err","a")
totalAlignments = 1
commands1 = [
#Intersect tissue with uniqueome
("intersectBed -abam " + tissue+".sorted.bam -b " + uniqueomeBed + " -f 1.0", tissue+".unique.bam"),
#Sort and Index Bam file
("samtools sort " + tissue+".unique.bam " + tissue + ".unique.sorted",None),
("samtools index " + tissue + ".unique.sorted.bam",None),
("samtools idxstats " + tissue + ".unique.sorted.bam",tissue+".unique.idxstats.txt")
]
for command,outfile in commands1:
errfile.write("\n\nRUNNING: " + command + "\n")
if outfile == None:
runCommand(command,None,errfile)
else:
runCommand(command,open(outfile,"w"),errfile)
#runCommand(command,open(outfile,"w"),errfile)
#print command + " > " + str(outfile)
#Count total number of mapped reads
totalAlignments = countReadsAligned(tissue+".unique.idxstats.txt")
commands2 = [
#Collect reads in pseudogene locations
("intersectBed -abam " + tissue + ".unique.bam -b " + pseudogeneBed,tissue+".unique.pseudo.bam"),
("bamToBed -i " + tissue+".unique.pseudo.bam", tissue+".unique.pseudo.bed"),
#Count unique regions
("intersectBed -c -a " + pseudogeneBed + " -b " + tissue+".unique.pseudo.bed",tissue+".pseudo.align.bed"),
of2.writelines(file2Buffer[:ind])
of1.close()
of2.close()
#erase used buffer lines
if ind < len(file1Buffer):
file1Buffer = file1Buffer[ind:]
else:
file1Buffer = []
if ind < len(file2Buffer):
file2Buffer = file2Buffer[ind:]
else:
file2Buffer = []
#run diff
bash.runCommand("diff temp1.txt temp2.txt",open("diff.txt","w"),None)
#read result
result.extend(open("diff.txt").readlines())
#refill buffers
file1Buffer.extend(file1.readlines(readSize))
file2Buffer.extend(file2.readlines(readSize))
bash.runCommand("rm temp1.txt")
bash.runCommand("rm temp2.txt")
bash.runCommand("rm diff.txt")
for line in result:
print line.strip()