def findTFsOccurringInRegions(cls, genome, tfSource, regionsBedFn, upFlankSize, downFlankSize, galaxyFn): uniqueWebPath = getUniqueWebPath(extractIdFromGalaxyFn(galaxyFn)) #assert genome == 'hg18' #other genomes not supported. TF id links do not specify genome for pre-selection of analysis tfTrackNameMappings = TfInfo.getTfTrackNameMappings(genome) assert tfTrackNameMappings != {}, 'No TF info for genome: %s' % genome tfTrackName = tfTrackNameMappings[tfSource] if (upFlankSize == downFlankSize == 0): flankedRegionsFn = regionsBedFn else: flankedRegionsFn= uniqueWebPath + os.sep + 'flankedRegs.bed' GalaxyInterface.expandBedSegments(regionsBedFn, flankedRegionsFn, genome, upFlankSize, downFlankSize) regSpec, binSpec = 'bed', flankedRegionsFn res = cls._runCategoryPointCount(genome, regSpec, binSpec, tfTrackName) tfNames = res.getResDictKeys() #print 'RES: ', res.getGlobalResult()[tfNames[0]], type(res.getGlobalResult()[tfNames[0]]) import third_party.safeshelve as safeshelve pwm2tfids = safeshelve.open(os.sep.join([HB_SOURCE_CODE_BASE_DIR,'data','pwm2TFids.shelf']), 'r') tf2class = safeshelve.open(os.sep.join([HB_SOURCE_CODE_BASE_DIR,'data','TfId2Class.shelf']), 'r') pwmName2id= safeshelve.open(os.sep.join([HB_SOURCE_CODE_BASE_DIR,'data','pwmName2id.shelf']), 'r') #print tfNames[0],tfNames[1], ' VS ', pwm2tfids.keys()[0], len(pwm2tfids) #tfs = list(reversed(sorted([(res.getGlobalResult()[tf], tf, '%s (%i hits (class %s))'%(tf, res.getGlobalResult()[tf]), '/'.join([tf2class[x] for x in pwm2tfids[tf]]) ) for tf in tfNames]))) #num hits, tfName, tfTextInclHits tfs = list(reversed(sorted([(res.getGlobalResult()[tf], tf, '%s (%i hits )'%(tf, res.getGlobalResult()[tf]) + \ (' (class: %s)'%'/'.join(set([str(tf2class.get(x)) for x in pwm2tfids[pwmName2id[tf]] if x in tf2class]))\ if (tf in pwmName2id and pwmName2id[tf] in pwm2tfids and any([x in tf2class for x in pwm2tfids[pwmName2id[tf]]]))\ else '') ) \ for tf in tfNames])) ) #num hits, tfName, tfTextInclHits tfsPlural = 's' if len(tfs)!=1 else '' print '<p>There are %i TF%s targeting your regions of interest, using "%s" as source of TF occurrences.</p>' % (len(tfs), tfsPlural, tfSource) expansionStr = ' flanked' if not (upFlankSize == downFlankSize == 0) else '' idHtmlFileNamer = GalaxyRunSpecificFile(['allTfIds.html'],galaxyFn) idHtmlFileNamer.writeTextToFile('<br>'.join(['<a href=/hbdev/hyper?track1=%s&track2=>%s</a>'%( quote(':'.join(tfTrackName+[tf[1]])), tf[2]) for tf in tfs])) print '<p>', idHtmlFileNamer.getLink('Inspect html file'), ' of all TF IDs occurring 1 or more times within your%s regions of interest, with each TF ID linking to analysis with this TF pre-selected.</p>' % (expansionStr) idFileNamer = GalaxyRunSpecificFile(['allTfIds.txt'],galaxyFn) idFileNamer.writeTextToFile(os.linesep.join([tf[2] for tf in tfs]) + os.linesep) print '<p>', idFileNamer.getLink('Inspect text file'), ' listing all TF IDs occurring 1 or more times within your%s regions of interest.</p>' % (expansionStr) extractedTfbsFileNamer = GalaxyRunSpecificFile(['tfbsInGeneRegions.bed'],galaxyFn) GalaxyInterface.extractTrackManyBins(genome, tfTrackName, regSpec, binSpec, True, 'bed', False, False, extractedTfbsFileNamer.getDiskPath(), True) print '<p>', extractedTfbsFileNamer.getLoadToHistoryLink('Inspect bed-file'), 'of all TF binding sites occurring within your%s regions of interest.</p>' % (expansionStr) for dummy,tf,dummy2 in tfs: extractedTfbsFileNamer = GalaxyRunSpecificFile([tf+'_tfbsInGeneRegions.bed'],galaxyFn) GalaxyInterface.extractTrackManyBins(genome, tfTrackName+[tf], regSpec, binSpec, True, 'bed', False, False, extractedTfbsFileNamer.getDiskPath()) print '<p>', extractedTfbsFileNamer.getLoadToHistoryLink('Binding sites of the TF %s' %tf, 'bed'), 'occurring within your%s regions of interest (bed-file).</p>' % (expansionStr)
def singleSimulation(self, numH0, numH1, replicateIndex, verbose=False): tests = MultipleTestCollection(numH0, numH1, self._maxNumSamples, self._h, self._fdrThreshold,self._a,self._b) tests.addSamples(self.NUM_SAMPLES_INITIALLY) while not tests.allTestsAreDetermined(): tests.addSamples(self.NUM_SAMPLES_PER_CHUNK) #if verbose: #print tests.getTotalNumSamples() #As sampling is now anyway over, we set fdrThreshold to a threshold used after computations are finished (i.e. affects final rejection/acception, but not stopping of samples) tests.setFdrThresholdAtAllCounters(self._postFdrThreshold) #print 'FINALLY, #samples: ', if self._galaxyFn is not None: if self._h is None: scheme = 'Basic' elif self._fdrThreshold is None: scheme = 'Sequential' else: scheme = 'McFdr' staticFile = GalaxyRunSpecificFile([scheme,str(numH1),str(replicateIndex),'PandQvals.txt'], self._galaxyFn) tests.writeAllPandQVals(staticFile.getFile() ) linkToRaw = staticFile.getLink('Raw p and q-vals') + ' under %s scheme with %i true H1, (replication %i)' % (scheme, numH1, replicateIndex) figStaticFile = GalaxyRunSpecificFile([scheme,str(numH1),str(replicateIndex),'PandQvals.png'], self._galaxyFn) figStaticFile.openRFigure() tests.makeAllPandQValsFigure() figStaticFile.closeRFigure() linkToFig = figStaticFile.getLink(' (p/q-figure) ') + '<br>' figNumSamplesStaticFile = GalaxyRunSpecificFile([scheme,str(numH1),str(replicateIndex),'NumSamples.png'], self._galaxyFn) figNumSamplesStaticFile.openRFigure() tests.makeNumSamplesFigure() figNumSamplesStaticFile.closeRFigure() linkToNumSamplesFig = figNumSamplesStaticFile.getLink(' (numSamples-figure) ') + '<br>' catalogStaticFile = GalaxyRunSpecificFile([str(numH1),'cat.html'], self._galaxyFn) catalogStaticFile.writeTextToFile(linkToRaw + linkToFig + linkToNumSamplesFig, mode='a') #if verbose: #print sorted(tests.getFdrVals()) #print 'NumS ign Below 0.2: ', sum([1 if t<0.2 else 0 for t in tests.getFdrVals()]) #return tests.getTotalNumSamples(), tests.getTotalNumRejected() return tests.getTotalNumSamples(), tests.getTotalNumRejected(), tests.getClassificationSummaries()
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();
def execute(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. ''' import subprocess import os from quick.util.StaticFile import GalaxyRunSpecificFile from config.Config import HB_SOURCE_CODE_BASE_DIR from quick.application.ExternalTrackManager import ExternalTrackManager tempInStaticFile = GalaxyRunSpecificFile(['tempIn.txt'], galaxyFn) outStaticFile = GalaxyRunSpecificFile(['tempOut.fasta'], galaxyFn) #print os.getcwd() inFn = ExternalTrackManager.extractFnFromGalaxyTN( choices[0].split(':') ) #print inFn tempOutFn = outStaticFile.getDiskPath(True) #print tempOutFn os.chdir(HB_SOURCE_CODE_BASE_DIR + '/third_party/nonpython') #print outStaticFile.getLink('output') markovOrder = int(choices[1]) seqs = [] for line in open(inFn): if line.startswith('>'): seqs.append( [line[1:].strip(),[]] ) else: seqs[-1][1].append(line.strip()) for seq in seqs: seq[1] = ''.join(seq[1]) pureSequence = ''.join( [seq[1] for seq in seqs]) totalSeqLen = len(pureSequence) #pureSequence = ''.join([line.replace('\n','') for line in open(inFn) if not line.startswith('>')]) tempInStaticFile.writeTextToFile(pureSequence) numSamples = int(choices[2]) if numSamples>1: zipOutStatic = GalaxyRunSpecificFile(['randomFastas.zip'], galaxyFn) zipOut = zipfile.ZipFile(zipOutStatic.getDiskPath(True),'w') for iteration in range(numSamples): if numSamples>1: fastaOutStatic = GalaxyRunSpecificFile(['random','s%s.fa'%iteration], galaxyFn) fastaOutFn = fastaOutStatic.getDiskPath(True) else: fastaOutFn = galaxyFn #fastaOutStatic = GalaxyRunSpecificFile(['random%s'%iteration], galaxyFn) #subprocess.call('javac',shell=True) #subprocess.call('javac',shell=False) #subprocess.call('javac MarkovModel.java',shell=True) subprocess.call('java MarkovModel %s %s %s >%s' % (tempInStaticFile.getDiskPath(), markovOrder, totalSeqLen, tempOutFn), shell=True ) #subprocess.call('javac third_party/nonpython/MarkovModel.java') #subprocess.call('java third_party/nonpython/MarkovModel.java') pureMarkovSequence = open(tempOutFn).readline().strip() pmsIndex = 0 fastaOutF = open(fastaOutFn,'w') for seq in seqs: fastaOutF.write('>'+seq[0]+os.linesep) nextPmsIndex = pmsIndex+len(seq[1]) #seq.append(pureMarkovSequence[pmsIndex:nextPmsIndex]) fastaOutF.write( pureMarkovSequence[pmsIndex:nextPmsIndex] + os.linesep) pmsIndex = nextPmsIndex fastaOutF.close() assert pmsIndex == totalSeqLen == len(pureMarkovSequence), (pmsIndex, totalSeqLen , len(pureMarkovSequence)) if numSamples>1: #print 'Adding %s to archive' % fastaOutFn.split('/')[-1] zipOut.write(fastaOutFn, fastaOutFn.split('/')[-1]) if numSamples>1: zipOut.close() print zipOutStatic.getLink('Zipped random sequences')
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()
def getGeneIdStaticFileWithContent(self): targetBins = self.getIntersectedReferenceBins() idFileNamer = GalaxyRunSpecificFile(['allGeneIds.txt'],self._galaxyFn) idFileNamer.writeTextToFile(os.linesep.join([str(bin.val).split('|')[0] for bin in targetBins]) + os.linesep) return idFileNamer
def runBinaryClassificationSuiteEvaluation(self, algorithmNames, predictionTrackNames, answerTrackNames, regionTrackNames, overlapAnalysisDef, ROCanalysisDef): # Number of test sets and number of algorithms to evaluate nTestSets = len(answerTrackNames) nAlgorithms = len(predictionTrackNames)/nTestSets # Initialize list data structures resultFiles = [] globalOverlapResults = [] globalEqOverlapResults = [] globalRocResults = [] tmpAlgorithmNames = [] number = 1000000000000 statPlot = StatisticPlot() globalResultFile = GalaxyRunSpecificFile(['globalResults.html'], self._galaxyFn) # Initialize the global result lists, which collects localResults across all test sets for i in range(0, nAlgorithms): tmpAlgorithmNames.append(algorithmNames[i*nTestSets]) globalOverlapResults.append(OrderedDict(zip(['Neither','Only1','Only2','Both'] , (0,0,0,0)))) globalEqOverlapResults.append(OrderedDict(zip(['Neither','Only1','Only2','Both'] , (0,0,0,0)))) globalRocResults.append({'Result': []}) algorithmNames = tmpAlgorithmNames # For all test sets... for i in range(0, nTestSets): # Create a result file for this test set resultFile = GalaxyRunSpecificFile(['testset%d.html' % i], self._galaxyFn) localOverlapResults = [] localRocResults = [] answerTrackName = answerTrackNames[i] regionTrackName = regionTrackNames[i] # Evaluate the predictions for every algorithm for this test set for j in range(0, nAlgorithms): predictionTrackName = predictionTrackNames[(j*nTestSets)+i] # Run statistics for to compute overlap and ROC values localOverlapResult = self._runSingleStatistic(regionTrackName, overlapAnalysisDef, predictionTrackName, answerTrackName) if self._isRocCurveCompatible(predictionTrackName): localRocResult = self._runSingleStatistic(regionTrackName, ROCanalysisDef, predictionTrackName, answerTrackName) else: localRocResult = None # Collect the local results and global add to global results localOverlapResults.append(localOverlapResult) localRocResults.append(localRocResult) globalOverlapResults[j]['Neither'] = globalOverlapResults[j]['Neither'] + localOverlapResult['Neither'] globalOverlapResults[j]['Only1'] = globalOverlapResults[j]['Only1'] + localOverlapResult['Only1'] globalOverlapResults[j]['Only2'] = globalOverlapResults[j]['Only2'] + localOverlapResult['Only2'] globalOverlapResults[j]['Both'] = globalOverlapResults[j]['Both'] + localOverlapResult['Both'] testSetLength = localOverlapResult['Neither'] + localOverlapResult['Only1'] + localOverlapResult['Only2'] + localOverlapResult['Both'] globalEqOverlapResults[j]['Neither'] = globalEqOverlapResults[j]['Neither'] + long(localOverlapResult['Neither']*number)/testSetLength globalEqOverlapResults[j]['Only1'] = globalEqOverlapResults[j]['Only1'] + long(localOverlapResult['Only1']*number)/testSetLength globalEqOverlapResults[j]['Only2'] = globalEqOverlapResults[j]['Only2'] + long(localOverlapResult['Only2']*number)/testSetLength globalEqOverlapResults[j]['Both'] = globalEqOverlapResults[j]['Both'] + long(localOverlapResult['Both']*number)/testSetLength if localRocResult != None: globalRocResults[j]['Result'] = globalRocResults[j]['Result'] + localRocResult['Result'] # Create statistics for this test set localStatisticsLink = statPlot.createBinaryClassificationStatistics(i, algorithmNames, localOverlapResults, self._galaxyFn, 'Benchmark statistics') totalPositives, totalNegatives = self._getTotalNegativesAndPositivesFromOverlapResults(localOverlapResults) localRocCurveLink = statPlot.createROCCurve(i, algorithmNames, totalPositives, totalNegatives, localRocResults, self._galaxyFn) # Write statistical information for this test set to file resultFile.writeTextToFile('%s</br>%s' % (localStatisticsLink, localRocCurveLink), 'w') resultFiles.append(resultFile) # Create statistics for all test sets globalStatisticsLink = statPlot.createBinaryClassificationStatistics(nTestSets, algorithmNames, globalOverlapResults, self._galaxyFn, 'Benchmark statistics (sum, longer test set has higher weight)') globalEqStatisticsLink = statPlot.createBinaryClassificationStatistics(nTestSets+1, algorithmNames, globalEqOverlapResults, self._galaxyFn, 'Benchmark statistics (same weight for each test set)') totalPositives, totalNegatives = self._getTotalNegativesAndPositivesFromOverlapResults(globalOverlapResults) globalRocCurveLink = statPlot.createROCCurve(nTestSets, algorithmNames, totalPositives, totalNegatives, globalRocResults, self._galaxyFn) # Write statistical information for all test sets to file globalResultFile.writeTextToFile('%s</br>%s</br>%s' % (globalStatisticsLink, globalEqStatisticsLink, globalRocCurveLink), 'w') # Add all result files to a result list, and return results = [] results.append(globalResultFile.getLink('Global results\n\n')) for i in range(0, len(resultFiles)): results.append(resultFiles[i].getLink('Test set %d' % (i+1))) return results
def findTFsTargetingGenes(cls, genome, tfSource, ensembleGeneIdList,upFlankSize, downFlankSize, geneSource, galaxyFn): #galaxyFn = '/usit/insilico/web/lookalike/galaxy_dist-20090924-dev/database/files/003/dataset_3347.dat' #print 'overriding galaxyFN!: ', galaxyFn uniqueWebPath = getUniqueWebPath(extractIdFromGalaxyFn(galaxyFn)) assert genome in ['mm9','hg18'] #other genomes not supported. TF id links do not specify genome for pre-selection of analysis #if tfSource == 'UCSC tfbs conserved': # tfTrackName = ['Gene regulation','TFBS','UCSC prediction track'] #else: # raise tfTrackNameMappings = TfInfo.getTfTrackNameMappings(genome) tfTrackName = tfTrackNameMappings[tfSource] #Get gene track #targetGeneRegsTempFn = uniqueWebPath + os.sep + 'geneRegs.bed' #geneRegsTrackName = GenomeInfo.getStdGeneRegsTn(genome) #geneRegsFn = getOrigFn(genome, geneRegsTrackName, '.category.bed') #GalaxyInterface.getGeneTrackFromGeneList(genome, geneRegsTrackName, ensembleGeneIdList, targetGeneRegsTempFn ) if not (upFlankSize == downFlankSize == 0): unflankedGeneRegsTempFn = uniqueWebPath + os.sep + '_geneRegs.bed' flankedGeneRegsTempFn = uniqueWebPath + os.sep + 'flankedGeneRegs.bed' geneRegsTrackName = GenomeInfo.getStdGeneRegsTn(genome) #geneRegsFn = getOrigFn(genome, geneRegsTrackName, '.category.bed') GalaxyInterface.getGeneTrackFromGeneList(genome, geneRegsTrackName, ensembleGeneIdList, unflankedGeneRegsTempFn ) GalaxyInterface.expandBedSegments(unflankedGeneRegsTempFn, flankedGeneRegsTempFn, genome, upFlankSize, downFlankSize) #flankedGeneRegsExternalTN = ['external'] +galaxyId + [flankedGeneRegsTempFn] regSpec, binSpec = 'file', flankedGeneRegsTempFn else: regSpec, binSpec = '__genes__', ','.join(ensembleGeneIdList) res = cls._runCategoryPointCount(genome, regSpec, binSpec, tfTrackName) #trackName1 = tfTrackName # #analysisDef = 'Category point count: Number of elements each category of track1 (with overlaps)'+\ # '[tf1:=SegmentToStartPointFormatConverter:]'+\ # '-> FreqByCatStat' ##assert len(ensembleGeneIdList)==1 ##geneId = ensembleGeneIdList[0] # #print '<div class="debug">' #userBinSource, fullRunArgs = GalaxyInterface._prepareRun(trackName1, None, analysisDef, regSpec, binSpec, genome) #res = AnalysisDefJob(analysisDef, trackName1, None, userBinSource, **fullRunArgs).run() # #print res ##GalaxyInterface._viewResults([res], galaxyFn) #print '</div>' tfs = res.getResDictKeys() genesPlural = 's' if len(ensembleGeneIdList)>1 else '' tfsPlural = 's' if len(tfs)!=1 else '' print '<p>There are %i TF%s targeting your gene%s of interest (%s), using "%s" as source of TF occurrences.</p>' % (len(tfs), tfsPlural, genesPlural, ','.join(ensembleGeneIdList), tfSource) expansionStr = ' flanked' if not (upFlankSize == downFlankSize == 0) else '' idHtmlFileNamer = GalaxyRunSpecificFile(['allTfIds.html'],galaxyFn) idHtmlFileNamer.writeTextToFile('<br>'.join(['<a href=%s/hyper?dbkey=%s&track1=%s&track2=>%s</a>'%(URL_PREFIX, genome, quote(':'.join(tfTrackName+[tf])), tf) for tf in tfs])) #idHtmlFileNamer.writeTextToFile('<br>'.join(['<a href=/hbdev/hyper?track1=%s&track2=>%s</a>'%( ':'.join(tfTrackName+[tf]), tf) for tf in tfs])) print '<p>', idHtmlFileNamer.getLink('Inspect html file'), ' of all TF IDs occurring 1 or more times within your%s gene region%s of interest, with each TF ID linking to analysis with this TF pre-selected.</p>' % (expansionStr, genesPlural) idFileNamer = GalaxyRunSpecificFile(['allTfIds.txt'],galaxyFn) idFileNamer.writeTextToFile(os.linesep.join(tfs) + os.linesep) print '<p>', idFileNamer.getLink('Inspect text file'), ' listing all TF IDs occurring 1 or more times within your%s gene region%s of interest.</p>' % (expansionStr, genesPlural) extractedTfbsFileNamer = GalaxyRunSpecificFile(['tfbsInGeneRegions.bed'],galaxyFn) GalaxyInterface.extractTrackManyBins(genome, tfTrackName, regSpec, binSpec, True, 'bed', False, False, extractedTfbsFileNamer.getDiskPath()) print '<p>', extractedTfbsFileNamer.getLink('Inspect bed-file'), 'of all TF binding sites occurring within your%s gene region%s of interest.</p>' % (expansionStr, genesPlural) #idFile = idFileNamer.getFile() #idFile.write(', '.join([str(bin.val) for bin in targetBins if res[bin][resDictKey]>0]) + os.sep) #idFile.close() #print idFileNamer.getLink('Text file'), ' of TF IDs' #GalaxyInterface.run(tfTrackName, tcGeneRegsExternalTN, analysisDef, regSpec, binSpec, genome, galaxyFn) #GalaxyInterface.run(':'.join(tfTrackName), ':'.join(tcGeneRegsExternalTN), analysisDef, regSpec, binSpec, genome, galaxyFn)
def executeReferenceTrack(cls, genome, tracks, track_names, clusterMethod, extra_option, distanceType, kmeans_alg, galaxyFn, regSpec, binSpec, numreferencetracks=None, refTracks=None, refFeatures=None, yesNo=None, howMany=None, upFlank=None, downFlank=None): from gold.application.RSetup import r jobFile = open(galaxyFn, 'w') print>>jobFile, 'PARAMS: ', dict(zip('genome, tracks, track_names, clusterMethod, extra_option, distanceType, kmeans_alg, regSpec, binSpec'.split(','), [repr(v)+'<br>'for v in [genome, tracks, track_names, clusterMethod, extra_option, distanceType, kmeans_alg, regSpec, binSpec]])) print>>jobFile, '<br><br>To run:<br>', '$clusterByReference', (genome, '$'.join([':'.join(t) for t in tracks]), ':'.join(track_names) , clusterMethod, extra_option, distanceType, kmeans_alg, regSpec, binSpec,numreferencetracks, refTracks, refFeatures, yesNo, howMany, upFlank, downFlank), '<br><br>' print>>jobFile, 'signature of method clusterByReference:<br>', 'clusterByReference(genome, tracksStr, track_namesStr, clusterMethod, extra_option, distanceType, kmeans_alg, regSpec, binSpec, numreferencetracks=None, refTracks=None, refFeatures=None, yesNo=None, howMany=None, upFlank=None, downFlank=None)<br><br><br>' prettyTrackNames = [v[-1].replace("RoadMap_","").replace('.H3K4me1','') for v in tracks] #prettyTrackNames = [prettyPrintTrackName(v) for v in tracks] #paramNames = ['numreferencetracks', 'refTracks', 'refFeatures', 'yesNo', 'howMany', 'upFlank', 'downFlank'] #for index, value in enumerate([numreferencetracks, refTracks, refFeatures, yesNo, howMany, upFlank, downFlank]): # if value != None: # print paramNames[index]+'='+ str(value), #print '' reftrack_names = [] #for use in creating the heatmap (as the column names) options = [] #for the case using refTracks, options contains feature for every refTrack, chosen by user. if numreferencetracks : for i in range(int(numreferencetracks)): ref_i = refTracks[i].split(":") #name of refTrack is being used to construct the name of expanded refTrack #refTracks.append(ref_i) #put the refTrack into refTracks list reftrack_names.append(ref_i[-1]) temp_opt1 = 'ref'+str(i)+'feature' options+= [] if refFeatures[i] == None else [refFeatures[i]] if yesNo[i] == "Yes" and howMany[i] != '--select--': for expan in range(int(howMany[i])) : reftrack_names.append(ref_i[-1]+'_'+ upFlank[i][expan]) upFlank = int(upFlank[i][expan]) downFlank = int(downFlank[i][expan]) withinRunId = str(i+1)+' expansion '+str(expan + 1) outTrackName = GalaxyInterface.expandBedSegmentsFromTrackNameUsingGalaxyFn(ref_i, genome, upFlank, downFlank, galaxyFn, withinRunId) #outTrackName is unique for run refTracks.append(outTrackName) #put the expanded track into refTracks list options.append(options[-1]) # use chosen feature for refTack as valid feature for the expanded for index, track in enumerate(refTracks) : #print track, '<br>' if type(track) == str : track = track.split(":") refTracks[index] = track[:-1] if track[-1] == "-- All subtypes --" else track if len(refTracks) > 0: trackFormats = [TrackInfo(genome,track).trackFormatName for track in tracks] trackLen = len(tracks) refLen = len(refTracks) f_matrix = zeros((trackLen, refLen)) for i in range(trackLen): for j in range(refLen): #print 'len(options), refLen, len(tracks), trackLen, len(trackFormats):', len(options), refLen, len(tracks), trackLen, len(trackFormats) f_matrix[i,j] = cls.extract_feature(genome,tracks[i],refTracks[j],options[j], regSpec, binSpec, trackFormats[i]) r.assign('track_names',prettyTrackNames) #use as track names, will be shown in clustering figure r.assign('reftrack_names',reftrack_names) r.assign('f_matrix',f_matrix) r.assign('distanceType',distanceType) r('row.names(f_matrix) <- track_names') r('colnames(f_matrix) <- reftrack_names') if clusterMethod == 'Hierarchical clustering' and extra_option != "--select--": figure = GalaxyRunSpecificFile(['cluster_tracks_result_figure.pdf'], galaxyFn) figurepath = figure.getDiskPath(True) r.pdf(figurepath, 8,8) r('d <- dist(f_matrix, method=distanceType)') #print r.f_matrix #print r.d r_f_matrixFile = GalaxyRunSpecificFile(['f-matrix.robj'], galaxyFn) r.assign('f_matrix_fn', r_f_matrixFile.getDiskPath(True)) r('dput(f_matrix, f_matrix_fn)') print>>jobFile, r_f_matrixFile.getLink('feature_matrix') r_f_matrixFile = GalaxyRunSpecificFile(['f-matrix.txt'], galaxyFn) r_f_matrixFile.writeTextToFile(str(f_matrix)+'\n\n'+str(r.d)) print>>jobFile, r_f_matrixFile.getLink('r.f_matrix & r.d') r.assign('extra_option',extra_option) r('hr <- hclust(d, method=extra_option, members=NULL)') r('plot(hr, ylab="Distance", hang=-1)') r('dev.off()') print>>jobFile, figure.getLink('clustering results figure<br>') elif clusterMethod == 'K-means clustering' and extra_option != "--select--" and kmeans_alg != "--select--": textFile = GalaxyRunSpecificFile(['result_of_kmeans_clustering.txt'], galaxyFn) textFilePath = textFile.getDiskPath(True) extra_option = int(extra_option) r.assign('extra_option',extra_option) r.assign('kmeans_alg',kmeans_alg) r('hr <- kmeans(f_matrix,extra_option,algorithm=kmeans_alg)') #the number of cluster is gotten from clusterMethod+ tag, instead of 3 used here kmeans_output = open(textFilePath,'w') clusterSizes = r('hr$size') #size of every cluster withinSS = r('hr$withinss') clusters = array(r('hr$cluster')) #convert to array in order to handle the index more easily track_names = array(track_names) for index1 in range(extra_option) : #extra_option actually the number of clusters trackInCluster = [k for k,val in clusters.items() if val == index1] print>>kmeans_output, 'Cluster %i(%s objects) : ' % (index1+1, str(clusterSizes[index1])) for name in trackInCluster : print>>kmeans_output, name print>>kmeans_output, 'Sum of square error for this cluster is : '+str(withinSS[index1])+'\n' kmeans_output.close() print>>jobFile, textFile.getLink('Detailed result of kmeans clustering <br>') heatmap = GalaxyRunSpecificFile(['heatmap_figure.png'], galaxyFn) heatmap_path = heatmap.getDiskPath(True) r.png(heatmap_path, width=800, height=700) r('heatmap(f_matrix, col=cm.colors(256), Colv=NA, scale="none", xlab="", ylab="", margins=c(10,10))')#Features cluster tracks r('dev.off()') print>>jobFile, heatmap.getLink('heatmap figure <br>') cls.print_data(f_matrix, jobFile) else : print 'Have to specify a set of refTracks'
def MakeHeatmapFromTracks(cls, galaxyFn, **trKwArgs): tr1 = trKwArgs.get('tr1') tr2 = trKwArgs.get('tr2') tr3 = trKwArgs.get('tr3') tableRowEntryTemplate = """<tr><td>%s</td><td><a href="%s"><img src="%s" /></a></td></tr>""" #htmlTemplate = '''<head><link rel="stylesheet" type="text/css" href="image_zoom/styles/stylesheet.css" /><script language="javascript" type="text/javascript" src="image_zoom/scripts/mootools-1.2.1-core.js"></script><script language="javascript" type="text/javascript" src="image_zoom/scripts/mootools-1.2-more.js"></script><script language="javascript" type="text/javascript" src="image_zoom/scripts/ImageZoom.js"></script> # <script language="javascript" type="text/javascript" > # liste = %s; # function point_it(event){ # pos_x = event.offsetX?(event.offsetX):event.pageX-document.getElementById("zoomer_image").offsetLeft; # pos_y = event.offsetY?(event.offsetY):event.pageY-document.getElementById("zoomer_image").offsetTop; # pos_x = Math.floor(pos_x/10); # pos_y = Math.floor(pos_y/10); # alert("Hello World!, you clicked: " +liste[pos_y][pos_x]); # }</script> # </head><body><div id="container"><!-- Image zoom start --><div id="zoomer_big_container"></div><div id="zoomer_thumb"> <a href="%s" target="_blank" ><img src="%s" /></a></div><!-- Image zoom end --></div></body></html>''' javaScriptCode = ''' liste = %s; function point_it(event){ pos_x = event.offsetX?(event.offsetX):event.pageX-document.getElementById("zoomer_image").offsetLeft; pos_y = event.offsetY?(event.offsetY):event.pageY-document.getElementById("zoomer_image").offsetTop; pos_x = Math.floor(pos_x/10); pos_y = Math.floor(pos_y/10); alert("Hello World!, you clicked: " +liste[pos_y][pos_x]); } ''' ResultDicts = [cls.getValuesFromBedFile(tr1,colorPattern=(1,0,0))] ResultDicts += [cls.getValuesFromBedFile(tr2,colorPattern=(0,1,0))] if tr2 else [] ResultDicts += [cls.getValuesFromBedFile(tr3,colorPattern=(0,0,1))] if tr3 else [] htmlTableContent = [] resultDict = cls.syncResultDict(ResultDicts) for chrom, valList in resultDict.items(): areaList = [] #For doing recursive pattern picture posMatrix = cls.getResult(len(valList), 2,2) javaScriptList = [[0 for v in xrange(len(posMatrix[0])) ] for t in xrange(len(posMatrix))] rowLen = len(posMatrix[0]) im = Image.new("RGB", (rowLen, len(posMatrix)), "white") for yIndex, row in enumerate(posMatrix): for xIndex, elem in enumerate(row): im.putpixel((xIndex, yIndex), valList[elem]) region = yIndex*rowLen + xIndex javaScriptList[yIndex][xIndex] = chrom+':'+str(elem*10)+'-'+str((elem+1)*10)+': '+repr([ round((255-v)/255.0 ,2 ) for v in valList[elem]]) #areaList.append(areaTemplate % (xIndex*10, yIndex*10, xIndex*11, yIndex*11, repr(valList[elem]))) im2 = im.resize((len(posMatrix[0])*10, len(posMatrix)*10)) origSegsFile = GalaxyRunSpecificFile([chrom+'smallPic.png'], galaxyFn) origSegsFn = origSegsFile.getDiskPath(True) bigSegsFile = GalaxyRunSpecificFile([chrom+'BigPic.png'], galaxyFn) bigSegsFn = bigSegsFile.getDiskPath(True) im.save(origSegsFn) im2.save(bigSegsFn) #open('Recursive/'+chrom+'Zooming.html','w').write(htmlTemplate % (str(javaScriptList), chrom+'Big.png',chrom+'.png')) core = HtmlCore() core.begin( extraJavaScriptFns=['mootools-1.2.1-core.js', 'mootools-1.2-more.js', 'ImageZoom.js'], extraJavaScriptCode=javaScriptCode % str(javaScriptList), extraCssFns=['image_zoom.css'] ) core.styleInfoBegin(styleId='container') core.styleInfoBegin(styleId='zoomer_big_container') core.styleInfoEnd() core.styleInfoBegin(styleId='zoomer_thumb') core.link(url=bigSegsFile.getURL(), text=str(HtmlCore().image(origSegsFile.getURL())), popup=True) core.styleInfoEnd() core.styleInfoEnd() core.end() htmlfile = GalaxyRunSpecificFile([chrom+'.html'], galaxyFn) htmlfile.writeTextToFile(str(core)) htmlTableContent.append(tableRowEntryTemplate % (chrom, htmlfile.getURL(), origSegsFile.getURL())) #return str(core) #htmlTemplate % (str(javaScriptList), bigSegsFn, origSegsFn) ####### # FOr doing normal picture #columns = int(round((len(valList)/1000)+0.5)) #im = Image.new("RGB", (1000, columns), "white") #y=-1 #for index, valuTuple in enumerate(valList): # x = index%1000 # # if x == 0: # y+=1 # try: # im.putpixel((x, y), valuTuple) # except: # pass #im.save(chrom+'.png') #htmlTableContent.append(tableRowEntryTemplate % (chrom, chrom+'.png')) htmlPageTemplate = """<html><body><table border="1">%s</table></body></html>""" return htmlPageTemplate % ('\n'.join(htmlTableContent))