Python GenomeInfo.getChrList方法代码示例

# 需要导入模块: from quick.util.GenomeInfo import GenomeInfo [as 别名]
# 或者: from quick.util.GenomeInfo.GenomeInfo import getChrList [as 别名]
 def execute(cls, choices, galaxyFn=None, username=''):
     start = time.time()
     genome = choices[0]
     trackName = choices[1].split(':')
     outFn = galaxyFn
     if choices[5] == 'Write to Standardised file':
         outFn = createOrigPath(genome, choices[-1].split(':'), 'collapsed_result.bedgraph')
         ensurePathExists(outFn[:outFn.rfind('/')+1])
             
     combineMethod = choices[2]
     category = choices[3] if choices[3] else ''
     numSamples = choices[4] if choices[4] else '1'
     
     analysisDef = 'dummy [combineMethod=%s] %s [numSamples=%s] -> ConvertToNonOverlappingCategorySegmentsPythonStat' % \
                     (combineMethod, '[category=%s]' % category if category != '' else '', numSamples) #'Python'
                                               
     for regSpec in  GenomeInfo.getChrList(genome):
         res = GalaxyInterface.runManual([trackName], analysisDef, regSpec, '*', genome, username=username, \
                                         printResults=False, printHtmlWarningMsgs=False)
         
         from gold.origdata.TrackGenomeElementSource import TrackViewGenomeElementSource
         from gold.origdata.BedComposer import CategoryBedComposer
         for resDict in res.values():
             tvGeSource = TrackViewGenomeElementSource(genome, resDict['Result'], trackName)
             CategoryBedComposer(tvGeSource).composeToFile(outFn)

# 需要导入模块: from quick.util.GenomeInfo import GenomeInfo [as 别名]
# 或者: from quick.util.GenomeInfo.GenomeInfo import getChrList [as 别名]
 def createNmerChains(self, n):
     for chr in GenomeInfo.getChrList(self._genome):
         print 'Creating chains of nmers of length ', n, ' for chromosome ', chr
         chrLen = GenomeInfo.getChrLen(self._genome,chr)
         chrReg = GenomeRegion( self._genome, chr, 0, chrLen )
         seqTV = PlainTrack( GenomeInfo.getSequenceTrackName(self._genome) ).getTrackView(chrReg)
         
         #nmersAsInts = NmerAsIntSlidingWindow(n, FuncValTvWrapper(seqTV))
         nmersAsInts = NmerAsIntSlidingWindow(n, seqTV.valsAsNumpyArray())
         SameValueIndexChainsFactory.generate( nmersAsInts, chrLen, 4**n, self._createPath(n), chr )

# 需要导入模块: from quick.util.GenomeInfo import GenomeInfo [as 别名]
# 或者: from quick.util.GenomeInfo.GenomeInfo import getChrList [as 别名]
    def execute(cls, choices, galaxyFn=None, username=''):
        start = time.time()
        genome = choices[0]
        trackName = choices[1].split(':')
        #outFn = open(NONSTANDARD_DATA_PATH+'/hg19/Private/Sigven/resultat.bed','w')
        analysisDef = '-> ConvertToNonOverlappingCategorySegmentsPythonStat' #'Python'
        for regSpec in  GenomeInfo.getChrList(genome):
            res = GalaxyInterface.runManual([trackName], analysisDef, regSpec, '*', genome, username=username, \
                                            printResults=False, printHtmlWarningMsgs=False)

            from gold.origdata.TrackGenomeElementSource import TrackViewGenomeElementSource
            from gold.origdata.BedComposer import CategoryBedComposer
            for resDict in res.values():
                tvGeSource = TrackViewGenomeElementSource(genome, resDict['Result'], trackName)
                CategoryBedComposer(tvGeSource).composeToFile(outFn)

# 需要导入模块: from quick.util.GenomeInfo import GenomeInfo [as 别名]
# 或者: from quick.util.GenomeInfo.GenomeInfo import getChrList [as 别名]
 def execute(cls, choices, galaxyFn=None, username=''):
     outputFile =  open(galaxyFn, 'w')
     genome = choices[0]
     histItem = choices[2]
     trackItem = choices[3]
     chromRegsPath = GenomeInfo.getChrRegsFn(genome)
     
     chrSizeDict =  dict([ ( chrom, GenomeInfo.getChrLen(genome, chrom)) for chrom in GenomeInfo.getChrList(genome)])
     geSource = headLinesStr = None
     if choices[1] == 'History':
         
         trackType = choices[2].split(':')[1]
         username = ''.join([chr(random.randint(97,122)) for i in range(6)]) 
         tempFn = createCollectedPath(genome, [], username+'_'.join([str(v) for v in time.localtime()[:6]])+'.'+trackType)
         fnSource = ExternalTrackManager.extractFnFromGalaxyTN(choices[2].split(':'))
         open(tempFn,'w').write(open(fnSource,'r').read())
         
         
         if trackType in ['marked.bed', 'category.bed', 'bed']:
             geSource = GenomeElementSorter(BedGenomeElementSource(tempFn, genome=genome)).__iter__()
         
         elif trackType == 'gtrack':
             geSource = GenomeElementSorter(GtrackGenomeElementSource(tempFn, genome=genome)).__iter__()
             headLinesStr = geSource.getHeaderLines().replace('##','\n##')
         
         cls.WriteExpandedElementsToFile(geSource, chrSizeDict, outputFile, headLinesStr, writeHeaderFlag=True)
         os.remove(tempFn)
     
     else:
         writeHeaderFlag = True
         for chrom in GenomeInfo.getChrList(genome):
             gRegion = GenomeRegion(genome, chrom, 0, chrSizeDict[chrom])
             plTrack = PlainTrack(trackItem.split(':'))
             geSource = GenomeElementTvWrapper(plTrack.getTrackView(gRegion)).__iter__()
             cls.WriteExpandedElementsToFile(geSource, chrSizeDict, outputFile, headLinesStr, writeHeaderFlag)
             writeHeaderFlag = False    
     outputFile.close()

# 需要导入模块: from quick.util.GenomeInfo import GenomeInfo [as 别名]
# 或者: from quick.util.GenomeInfo.GenomeInfo import getChrList [as 别名]
    def execute(cls, choices, galaxyFn=None, username=''):
        from quick.application.GalaxyInterface import GalaxyInterface

        fileformat = choices[9];
        outputFile = open(galaxyFn, "w")
        
        if fileformat == "html":
            print GalaxyInterface.getHtmlBeginForRuns(galaxyFn)
            print GalaxyInterface.getHtmlForToggles(withRunDescription=False)
            t = calendar.timegm(time.gmtime())
            htmlfile = GalaxyRunSpecificFile(["css", str(t)], galaxyFn);


        genome = choices[0]
        track1 = choices[1].split(":")
        track2 = choices[2].split(":")
        tn1 = ExternalTrackManager.getPreProcessedTrackFromGalaxyTN(genome, track1)
        tn2 = ExternalTrackManager.getPreProcessedTrackFromGalaxyTN(genome, track2)

        compare = choices[3] != "Count individual SNP-differences in window"
        if choices[4] == "Classical MDS":
            mds = 0;
        elif choices[4] == "SMACOF":
            mds = 1;
        else:
            mds = 2;
        windowSize = int(choices[5])
        windowStep = int(choices[6])
        
        mcTreshold = int(choices[7])
        mcRuns = int(choices[8])

        outputFile.write("#seqid\tstart\tscore\tp\n")
        if fileformat == "html":
            text = "#seqid\tstart\tscore\tp\n";

	print "chrs:"+str(GenomeInfo.getChrList(genome))
        reg = "*"
        bins = "*"
        analysisDef = "Dummy: dummy name ([wStep=%g] [wSize=%s] [func=%s] [mds=%s] [mcT=%s] [mcR=%s])-> CategoryClusterSeparationStat" % (windowStep, windowSize, compare, mds, mcTreshold, mcRuns)
        userBinSource = GalaxyInterface._getUserBinSource(reg, bins, genome)
        result = GalaxyInterface.runManual([tn1, tn2], analysisDef, reg, bins, genome, galaxyFn=galaxyFn)
        for key in result.getAllRegionKeys():
            chrom = str(key).split(":")[0];
            r = result[key];
            if 'Result' not in r.keys():
                print "skipping chr:", chrom, r;
                continue;
            r = r['Result'];
            scores = r[0];
            stddev = r[1];
            for i in range(len(scores)):
                if scores[i] != 0:
                    pos = i*windowStep;
                    if fileformat == "tabular":
                        outputFile.write("%s\t%s\t%s\t%s\n" % (str(chrom), pos, str(scores[i]), str(stddev[i])))
                    else:
                        text += "%s\t%s\t%s\t%s\n" % (str(chrom), pos, str(scores[i]), str(stddev[i]));
        if fileformat == "html":
            htmlfile.writeTextToFile(text);
            print htmlfile.getLink("Result file");
            print GalaxyInterface.getHtmlEndForRuns()
        
        outputFile.close();

# 需要导入模块: from quick.util.GenomeInfo import GenomeInfo [as 别名]
# 或者: from quick.util.GenomeInfo.GenomeInfo import getChrList [as 别名]
 def createGwTrack(cls, genome, iterClass, *iterParams):
     for chr in GenomeInfo.getChrList(genome):
         cls.createChrTrack(genome, chr, iterClass, *iterParams)

# 需要导入模块: from quick.util.GenomeInfo import GenomeInfo [as 别名]
# 或者: from quick.util.GenomeInfo.GenomeInfo import getChrList [as 别名]
 def __new__(cls, genome):
     from gold.track.GenomeRegion import GenomeRegion
     from quick.util.GenomeInfo import GenomeInfo
     return [GenomeRegion(genome, GenomeInfo.getChrList(genome)[0], 0, 1)]

# 需要导入模块: from quick.util.GenomeInfo import GenomeInfo [as 别名]
# 或者: from quick.util.GenomeInfo.GenomeInfo import getChrList [as 别名]
 def __iter__(self):
     for chr in GenomeInfo.getChrList(self.genome).__iter__():
         yield CustomTrackCreatorPickleWrapper(self, chr)

# 需要导入模块: from quick.util.GenomeInfo import GenomeInfo [as 别名]
# 或者: from quick.util.GenomeInfo.GenomeInfo import getChrList [as 别名]
 def createTrackGW(cls, genome, inTrackName, outTrackName, windowSize, func, username):
     cls._createTrackCommon(genome, inTrackName, outTrackName, windowSize, func, username, GenomeInfo.getChrList(genome))

# 需要导入模块: from quick.util.GenomeInfo import GenomeInfo [as 别名]
# 或者: from quick.util.GenomeInfo.GenomeInfo import getChrList [as 别名]
    def execute(cls, choices, galaxyFn=None, username=""):
        """Is called when execute-button is pushed by web-user.
        Should print output as HTML to standard out, which will be directed to a results page in Galaxy history.
        If getOutputFormat is anything else than HTML, the output should be written to the file with path galaxyFn.
        If needed, StaticFile can be used to get a path where additional files can be put (e.g. generated image files).
        choices is a list of selections made by web-user in each options box.
        """
        print "Executing..."
        genome = choices[0]
        infile = choices[1]
        windowSize = int(choices[2])
        normquantile = float(choices[3])
        percentile = float(choices[4])

        inFn = ExternalTrackManager.extractFnFromGalaxyTN(infile.split(":"))
        data = open(inFn, "r").read()
        fetVals, addr = cls.preProcessPvalues(data, 2)
        stddevs, addr = cls.preProcessPvalues(data, 3)
        output = open(galaxyFn, "w")
        # Tuva changed sorted elms to FALSE
        output.write(
            "##gtrack version: 1.0\n"
            + "##track type: segments\n"
            + "##uninterrupted data lines: true\n"
            + "##sorted elements: false\n"
            + "##no overlapping elements: true\n"
            + "###seqid\tstart\tend\n"
        )

        # Calculate limit for FET:
        m = stats.cmedian(fetVals)
        upperquant = stats.scoreatpercentile(stddevs, percentile)
        qnorm = stats.norm.ppf(normquantile)
        limit = m + qnorm * upperquant
        print "Windows found", sum(fetVals >= limit)
        print "percentile", percentile, "normquantile", normquantile
        print "mean", m, "upperquant", upperquant, "qnorm", qnorm
        print "Limit", limit
        addrs = numpy.array(addr)
        filteredaddrs = addrs[fetVals >= limit]

        print GenomeInfo.getChrList(genome)

        curchrom = ""
        start = ""
        end = sys.maxint
        prevAddr = -1000000.0
        for addr in filteredaddrs:
            addrList = addr.split("\t")
            if addrList[0] != curchrom or int(addrList[1]) - windowSize > prevAddr:
                if curchrom != "":
                    newend = prevAddr + windowSize if prevAddr + windowSize < end else end
                    output.write(start + "\t" + str(newend) + "\n")
                start = addr
                curchrom = addrList[0]
                end = int(GenomeInfo.getChrLen(genome, curchrom)) - 1

            prevAddr = int(addr.split("\t")[1])

        newend = prevAddr + windowSize if prevAddr + windowSize < end else end
        output.write(start + "\t" + str(newend) + "\n")
        output.close()

# 需要导入模块: from quick.util.GenomeInfo import GenomeInfo [as 别名]
# 或者: from quick.util.GenomeInfo.GenomeInfo import getChrList [as 别名]
    def execute(cls, choices, galaxyFn=None, username=""):

        from quick.application.GalaxyInterface import GalaxyInterface

        fileformat = choices[6]
        outputFile = open(galaxyFn, "w")

        if fileformat == "html":
            print GalaxyInterface.getHtmlBeginForRuns(galaxyFn)
            print GalaxyInterface.getHtmlForToggles(withRunDescription=False)
            t = calendar.timegm(time.gmtime())
            htmlfile = GalaxyRunSpecificFile(["fet", str(t)], galaxyFn)

        genome = choices[0]
        track1 = choices[1].split(":")
        track2 = choices[2].split(":")
        tn1 = ExternalTrackManager.getPreProcessedTrackFromGalaxyTN(genome, track1)
        tn2 = ExternalTrackManager.getPreProcessedTrackFromGalaxyTN(genome, track2)

        windowSize = int(choices[3])
        windowStep = int(choices[4])
        percentile = float(choices[5])

        # results = {}

        # TODO: why this?
        # tr = Track(tn1)
        # tr.addFormatReq(TrackFormatReq(dense=False, allowOverlaps=True))

        outputFile.write("#seqid\tstart\tscore\tstddev\n")

        if fileformat == "html":
            text = "#seqid\tstart\tscore\tstddev\n"
        print "chrs:", str(GenomeInfo.getChrList(genome))
        reg = "*"
        bins = "*"
        analysisDef = "Dummy: dummy name ([wStep=%g] [wSize=%g] [percentile=%g])-> FisherExactScoreStat" % (
            windowStep,
            windowSize,
            percentile,
        )
        userBinSource = GalaxyInterface._getUserBinSource(reg, bins, genome)
        result = GalaxyInterface.runManual([tn1, tn2], analysisDef, reg, bins, genome, galaxyFn=galaxyFn)
        for key in result.getAllRegionKeys():
            chrom = str(key).split(":")[0]
            r = result[key]
            if "Result" not in r.keys():
                print "skipping chr:", chrom, r
                continue
            r = r["Result"]
            scores = r[0]
            stddev = r[1]
            for i in range(len(scores)):
                if scores[i] != 0:
                    pos = i * windowStep
                    # if choices[5] == "html":
                    # print "%s\t%s\t%s\t%s\n" % (str(chrom), pos, str(scores[i]), str(stddev[i]))
                    if fileformat == "tabular":
                        outputFile.write("%s\t%s\t%s\t%s\n" % (str(chrom), pos, str(scores[i]), str(stddev[i])))
                    else:
                        text += "%s\t%s\t%s\t%s\n" % (str(chrom), pos, str(scores[i]), str(stddev[i]))

        if fileformat == "html":
            htmlfile.writeTextToFile(text)
            print htmlfile.getLink("Result file")
            print GalaxyInterface.getHtmlEndForRuns()

        outputFile.close()

# 需要导入模块: from quick.util.GenomeInfo import GenomeInfo [as 别名]
# 或者: from quick.util.GenomeInfo.GenomeInfo import getChrList [as 别名]
 def _createNmerTrack(self, nmerList, lowerOrder=None):
     nmerLengths = list(set([len(nmer) for nmer in nmerList]))
     assert len(nmerLengths)==1
     
     chainOrder = lowerOrder if lowerOrder is not None else nmerLengths[0]
     
     regionList = [GenomeRegion(self._genome, chr, 0, GenomeInfo.getChrLen(self._genome, chr) ) for chr in GenomeInfo.getChrList(self._genome)]
     
     for region in regionList:
         print '|',
         
         chains = SameValueIndexChainsFactory.load(self._createPath(chainOrder), region.chr)
         
         for nmer in nmerList:
             if len(nmerList) > 1:
                 print '.',
             
             if lowerOrder is not None:
                 nmerPrefix = nmer[0:chainOrder]
                 rawIndexGenerator = chains.getIndexGenerator(NmerTools.nmerAsInt(nmerPrefix))             
                 indexGenerator = LowerOrderChainWrapper(rawIndexGenerator, nmerPrefix, nmer, self._genome, region.chr)
             else:
                 indexGenerator = chains.getIndexGenerator(NmerTools.nmerAsInt(nmer)) 
     
             #print 'Length of lower order chain: %i and %i' % (sum(1 for x in indexGenerator), sum(1 for x in indexGenerator))
             #print 'Length of wrapped chain: %i and %i' % (sum(1 for x in wrappedIndexGenerator), sum(1 for x in wrappedIndexGenerator))            
             
             PreProcessCustomTrackJob(self._genome, self._createTrackName(nmer), [region], \
                                      self._getNmerGeSourceForChr, finalize=False, preProcess=True, \
                                      indexGenerator=indexGenerator).process()
                 
     for nmer in nmerList:
         try:
             PreProcessCustomTrackJob(self._genome, self._createTrackName(nmer), regionList, \
                                      self._getNmerGeSourceForChr, preProcess=False, finalize=True, \
                                      indexGenerator=[0]).process()
         except EmptyGESourceError:
             PreProcessCustomTrackJob(self._genome, self._createTrackName(nmer), [GenomeRegion(self._genome, regionList[0].chr, -1, 0)], \
                                      self._getNmerGeSourceForChr, preProcess=True, finalize=True, \
                                      indexGenerator=[-1]).process()
     
     return

# 需要导入模块: from quick.util.GenomeInfo import GenomeInfo [as 别名]
# 或者: from quick.util.GenomeInfo.GenomeInfo import getChrList [as 别名]
 def execute(cls, choices, galaxyFn=None, username=''):
     from quick.application.ExternalTrackManager import ExternalTrackManager
     
     genome = choices[0]
     preProcTN1 = ExternalTrackManager.getPreProcessedTrackFromGalaxyTN(genome, choices[2].split(':')) if choices[1] == 'History' else choices[2].split(':')
     chrSizeDict =  dict([ ( chrom, GenomeInfo.getChrLen(genome, chrom)) for chrom in GenomeInfo.getChrList(genome)])
     
     
     trackType = choices[3].split(':')[1]
     fnSource = ExternalTrackManager.extractFnFromGalaxyTN(choices[3].split(':'))
     
     if trackType in ['marked.bed', 'category.bed', 'bed']:
         geSource = GenomeElementSorter(BedGenomeElementSource(fnSource, genome=genome)).__iter__()
         
     elif trackType == 'gtrack':
         geSource = GenomeElementSorter(GtrackGenomeElementSource(fnSource, genome=genome)).__iter__()
         #headLinesStr = geSource.getHeaderLines().replace('##','\n##')
     else:
         raise InvalidFormatError('The Binning must be of the following formats: gtrack, marked.bed, category.bed ,bed ...')
         
         
     cls.PrintResultToHistItem( galaxyFn, geSource, preProcTN1, genome, username)