def makeGraph(baseName, lowRange, highRange):
        lowRange = int(lowRange)
        highRange = int(highRange)
        
        
        histDict = {}
        for i in range(lowRange, highRange + 1):
        
                f = open(baseName + str(i), 'r')
                for line in f:
                        targets = line.strip().split('\t')[4]
                        numTargets = len(targets.split(','))
                        try:
                                histDict[i].append(numTargets)
                        except KeyError:
                                histDict[i] = [numTargets]

                f.close()
        print histDict 
        
        for m in histDict:
                cgPlot.plotHistogram(histDict[m], name = str(m) + ' mismatches')
def makeFigure(fN, targetFN, alignmentFN, cName):
        #make targetDict
        f = open(targetFN, 'r')
        targetDict = {} # tID: tLoc
        for line in f:
                ls = line.strip().split('\t')
                targetDict[int(ls[0])] = ls[1]
        f.close()

        #make alignmentDict
        alignDict = {} # sid: {target: offset}
        f = open(alignmentFN, 'r')
        for line in f:
                ls = line.strip().split(' ')
                sID = int(ls[0])
                tID = int(ls[1])
                offset = int(ls[4])
                if not sID in alignDict:
                           alignDict[sID] = {}

                alignDict[sID][tID] = offset #assumes one source to target...
        f.close()

        f = open(fN, 'r')
        
        histoVals = []

        for line in f:
                ls = line.strip().split('\t')
                sID = int(ls[0])
                sLoc = ls[1]
                sChrom, sStrand, sStart, sEnd = bioLibCG.tccSplit(sLoc)
                sLen = sEnd - sStart
                tIDs = ls[4].split(',')

                for tID in tIDs:
                        tID = int(tID)
                        tLoc = targetDict[tID]
                        chrom, strand, start, end = bioLibCG.tccSplit(tLoc)
                        offset = alignDict[sID][tID]

                        if sStrand == '1':
                                start = start - 19 + offset
                                end = start + sLen
                        else:
                                end = end + 19 - offset
                                start = end - sLen

                        scanRange = bioLibCG.makeTcc(chrom, strand, start, end)
                                
                        stretch = cgPeaks.stretch(scanRange, cName)
                        highest = stretch.getHighestLevel()
                        sortedKeys = stretch.profile.keys()

                        if sStrand == '-1':
                                sortedKeys.reverse()

                        i = 0
                        for key in sortedKeys:
                                level = stretch.profile[key]
                                for j in range(0,level):
                                        histoVals.append(i)
                                i += 1




        cgPlot.plotHistogram(histoVals)
Beispiel #3
0
tcc = 'chr1:1:1102538:1103319'
stretch = cgPeaks.stretch(tcc, 'agoProfile.conf')
stretch.createContBlocks()

sortedKeys = stretch.profile.keys()
sortedKeys.sort()

for key in sortedKeys:
	print key, stretch.profile[key]

for block in stretch.blocks:
	print block
'''


'''
#histogram test
a = [5,5,5,5,5,5,4,4,4,3,3,2,1]
cgPlot.plotHistogram(a, name = 'testHistogram')
'''

#svCoord test

tcc = 'chr1:1:1103298:1103298'

eLevels = sv.svCoord([tcc], 'siPeaks.conf')
for coord in eLevels:
	print coord, eLevels[coord]

'''
tcc = 'chr1:1:1102539:1103319'
Beispiel #4
0
import cgPlot
import bioLibCG as cg

f = open('cb.20.ago', 'r')

lengths = []
for line in f:
	lengths.append(cg.getTccLength(line.strip()))

cgPlot.plotHistogram(lengths, name = 'cbLengths20')
def makeFigure(fN, targetFN, alignmentFN, cName):
    # make targetDict
    f = open(targetFN, "r")
    targetDict = {}  # tID: tLoc
    for line in f:
        ls = line.strip().split("\t")
        targetDict[int(ls[0])] = ls[1]
    f.close()

    # make alignmentDict
    alignDict = {}  # sid: {target: offset}
    f = open(alignmentFN, "r")
    for line in f:
        ls = line.strip().split(" ")
        sID = int(ls[0])
        tID = int(ls[1])
        offset = int(ls[4])
        if not sID in alignDict:
            alignDict[sID] = {}

        alignDict[sID][tID] = offset  # assumes one source to target...
    f.close()

    f = open(fN, "r")

    histoVals = []

    for line in f:
        ls = line.strip().split("\t")
        sID = int(ls[0])
        sLoc = ls[1]
        sChrom, sStrand, sStart, sEnd = bioLibCG.tccSplit(sLoc)
        sLen = sEnd - sStart
        tIDs = ls[4].split(",")

        for tID in tIDs:
            tID = int(tID)
            tLoc = targetDict[tID]
            chrom, strand, start, end = bioLibCG.tccSplit(tLoc)
            offset = alignDict[sID][tID]

            if sStrand == "1":
                start = start - 19 + offset
                end = start + sLen
            else:
                end = end + 19 - offset
                start = end - sLen

            scanRange = bioLibCG.makeTcc(chrom, strand, start, end)

            stretch = cgPeaks.stretch(scanRange, cName)
            highest = stretch.getHighestLevel()
            sortedKeys = stretch.profile.keys()

            if sStrand == "-1":
                sortedKeys.reverse()

            i = 0
            for key in sortedKeys:
                level = stretch.profile[key]
                for j in range(0, level):
                    histoVals.append(i)
                i += 1

    cgPlot.plotHistogram(histoVals)
Beispiel #6
0
import cgPlot
import bioLibCG as cg

f = open('cb.20.ago', 'r')

lengths = []
for line in f:
    lengths.append(cg.getTccLength(line.strip()))

cgPlot.plotHistogram(lengths, name='cbLengths20')