Python ExternalTrackManager.ExternalTrackManager类代码示例

    def createRSquareGraph(cls, ldGraphTrackName, r2_threshold):
        """
        Creates a dictionary of all pairs in a linked point track.
        Variants in LD must have rsquare >= the rsquare threshold passed to the function.

        :param ldGraphTrackName: linked point track, as chosen in tool (choices.ldtrack)
        :param r2_threshold: Lower limit of square value
        :return: Dictionary of all ld-pairs with sorted key = (rsid1, rsid2), value = rSquare
        """
        from quick.application.ExternalTrackManager import ExternalTrackManager
        from gold.origdata.GtrackGenomeElementSource import GtrackGenomeElementSource

        fileName = ExternalTrackManager.extractFnFromGalaxyTN(ldGraphTrackName)
        suffix = ExternalTrackManager.extractFileSuffixFromGalaxyTN(ldGraphTrackName)
        gtSource = GtrackGenomeElementSource(fileName, suffix=suffix)

        r2graph = {}

        for ge in gtSource:
            rsid = ge.id
            edges = ge.edges
            weights = ge.weights

            for i in range(0, len(edges)):
                ldRsid = edges[i]
                r2 = weights[i]

                if r2 >= float(r2_threshold):
                    cls.addEdge(r2graph, rsid, ldRsid, r2)

        return r2graph

 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.
     '''
     
     try:
         historyInputTN = choices[0].split(':') #from history
         historyGalaxyFn = ExternalTrackManager.extractFnFromGalaxyTN( historyInputTN) #same as galaxyFn in execute of create benchmark..
         randomStatic = RunSpecificPickleFile(historyGalaxyFn) #finds path to static file created for a previous history element, and directs to a pickle file
         myInfo = randomStatic.loadPickledObject()
     except:
         return None
     
     galaxyTN = myInfo[3].split(':')
     myFileName = ExternalTrackManager.extractFnFromGalaxyTN(galaxyTN)
     genome = myInfo[0]
     
     gtrackSource = GtrackGenomeElementSource(myFileName, genome)
     regionList = []
     
     for obj in gtrackSource:
         regionList.append(GenomeRegion(obj.genome, obj.chr, obj.start, obj.end))
     
     extractor = TrackExtractor()
             
     fn = extractor.extract(GenomeInfo.getSequenceTrackName(genome), regionList, galaxyFn, 'fasta')

    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.gtr
        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.
        '''
        resultLines = []

        outputFile=open(galaxyFn,"w")
        fnSource = ExternalTrackManager.extractFnFromGalaxyTN(choices[2].split(':'))
        fnDB = ExternalTrackManager.extractFnFromGalaxyTN(choices[3].split(':'))
        intersectingFactor = 'id' if choices[4] == 'Element id' else 'position'
        
        colsToAdd = []
        colsToAddDict = choices[5]
        for key in colsToAddDict:
            if colsToAddDict[key]:
                colsToAdd.append(key)

        genome = choices[1] if choices[0] == 'Yes' else None
        
        try:
            complementGtrackFileAndWriteToFile(fnSource, fnDB, galaxyFn, intersectingFactor, colsToAdd, genome)
        except Exception, e:
            import sys
            print >> sys.stderr, e

    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.
        '''
        # get population format
        if choices.format == 'File':
            pop = [];
            popfile = choices.population;
            inFn = ExternalTrackManager.extractFnFromGalaxyTN(popfile.split(":"));
            infile = open(inFn);
            for line in infile:
                pop.append(line.rstrip('\n'));
        else:
            pop = map(str.strip,choices.population.split(","));

        # read in file
        inFn = ExternalTrackManager.extractFnFromGalaxyTN(choices.vcf.split(":"));
        data = open(inFn).read();

        # convert and write to GTrack file
        outfile = open(galaxyFn, 'w');
        outfile.write(addHeader(choices.genome));
        outfile.write(convertToGtrackFile(data, pop, choices.genome));
        outfile.close();

 def _collectTracks(self):
     tracks = [self._track, self._track2]
     if 'trackNameIntensity' in self._kwArgs:
         assert not 'extraTracks' in self._kwArgs
         self._kwArgs['extraTracks'] = self._kwArgs['trackNameIntensity']
         
     if 'extraTracks' in self._kwArgs:
         from gold.track.Track import PlainTrack
         import re
         from config.Config import MULTIPLE_EXTRA_TRACKS_SEPARATOR
         extraTracks = self._kwArgs['extraTracks']
         if type(extraTracks) == str:
             extraTracks = extraTracks.split(MULTIPLE_EXTRA_TRACKS_SEPARATOR)
         for extraT in extraTracks:
             if type(extraT) == str:
                 #extraT = extraT.split('|')
                 #extraT = re.split('\^|\|',extraT)                    
                 extraT = convertTNstrToTNListFormat(extraT)
             if type(extraT) == list:
                 #print 'TEMP1: ', extraT
                 from urllib import unquote
                 extraT = [unquote(part) for part in extraT]
                 from quick.application.ExternalTrackManager import ExternalTrackManager
                 if ExternalTrackManager.isGalaxyTrack(extraT):
                     extraT = ExternalTrackManager.getPreProcessedTrackFromGalaxyTN(self.getGenome(), extraT)
                 extraT = PlainTrack(extraT)
                 tracks.append(extraT)
             
     return tracks

 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.gtr
     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.
     '''
     outputFile=open(galaxyFn,"w")
     fnSource = ExternalTrackManager.extractFnFromGalaxyTN(choices[0].split(':'))
     inputFile = open(ExternalTrackManager.extractFnFromGalaxyTN(choices[0].split(':')), 'r')
     
     if choices[2] == 'Filter on exact values':    
         if choices[3]!='Select column..':
             column = int(choices[3][7:])
             filterSet = set([key for key,val in choices[4].items() if val])
             for i in inputFile:
                 if i.split('\t')[column] in filterSet:
                     print>>outputFile, i
             
     else:
         for i in inputFile:
             temptab = i.split('\t')
             for index in range(len(temptab)):
                 locals()['c'+str(index)] = temptab[index]
             if eval(choices[5]):
                 print>>outputFile, i
                 
     inputFile.close()
     outputFile.close()    

    def findOverrepresentedTFsFromGeneSet(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
        galaxyId = extractIdFromGalaxyFn(galaxyFn)
        uniqueWebPath = getUniqueWebPath(extractIdFromGalaxyFn(galaxyFn))

        assert genome == 'hg18'
        
        tfTrackNameMappings = TfInfo.getTfTrackNameMappings(genome)
        tfTrackName = tfTrackNameMappings[tfSource]
        
        
        #Get gene track
        assert geneSource == 'Ensembl'
        targetGeneRegsTempFn = uniqueWebPath + os.sep + 'geneRegs.bed'
        geneRegsTrackName = GenomeInfo.getStdGeneRegsTn(genome)
        geneRegsFn = getOrigFn(genome, geneRegsTrackName, '.category.bed')
        GalaxyInterface.getGeneTrackFromGeneList(genome, geneRegsTrackName, ensembleGeneIdList, targetGeneRegsTempFn )
        
        assert upFlankSize == downFlankSize == 0 #Should instead extend regions to include flanks
        
        tcGeneRegsTempFn = uniqueWebPath + os.sep + 'tcGeneRegs.targetcontrol.bedgraph'
        #Think this will be okay, subtraction not necessary as targets are put first:
        controlGeneRegsTempFn = geneRegsFn
        #print targetGeneRegsTempFn, controlGeneRegsTempFn, tcGeneRegsTempFn
        GalaxyInterface.combineToTargetControl(targetGeneRegsTempFn, controlGeneRegsTempFn, tcGeneRegsTempFn)
        
        #tcGeneRegsExternalTN = ['external'] +galaxyId +  [tcGeneRegsTempFn]
        tcGeneRegsExternalTN = ExternalTrackManager.createStdTrackName(galaxyId, 'tempTc')
        
        #tcGeneRegsExternalTN = ['external'] +targetGalaxyId +  [tcGeneRegsTempFn]
        #tcGeneRegsExternalTN = ['galaxy', externalId, tcGeneRegsTempFn]
        
        targetGeneRegsExternalTN = ExternalTrackManager.createStdTrackName(galaxyId, 'tempTc', '1')
        controlGeneRegsExternalTN = ExternalTrackManager.createStdTrackName(galaxyId, 'tempTc', '0')
        
        #pre-process
        print 'Pre-processing file: %s, with trackname: %s ' % (tcGeneRegsTempFn, tcGeneRegsExternalTN)
        ExternalTrackManager.preProcess(tcGeneRegsTempFn, tcGeneRegsExternalTN, 'targetcontrol.bedgraph',genome)
        print 'Pre-processing TN: ', targetGeneRegsExternalTN
        ExternalTrackManager.preProcess(targetGeneRegsTempFn, targetGeneRegsExternalTN, 'bed',genome)
        print 'Pre-processing TN: ', controlGeneRegsExternalTN
        ExternalTrackManager.preProcess(controlGeneRegsTempFn, controlGeneRegsExternalTN, 'bed',genome)
        
        #print tcGeneRegsExternalTN
        trackName1, trackName2 = tfTrackName, tcGeneRegsExternalTN
        
        analysisDef = 'Categories differentially located in targets?: Which categories of track1-points fall more inside case than control track2-segments? [rawStatistic:=PointCountInsideSegsStat:]' +\
                  '[tf1:=SegmentToStartPointFormatConverter:] [tf2:=TrivialFormatConverter:]' +\
                  '-> DivergentRowsInCategoryMatrixStat'
        regSpec, binSpec = '*','*'
        
        #print 'skipping preproc!!'
        #ExternalTrackManager.preProcess(tcGeneRegsExternalTN[-1], tcGeneRegsExternalTN, 'targetcontrol.bedgraph', genome)
        #ExternalTrackManager.preProcess(targetGeneRegsTempFn, targetGeneRegsExternalTN, 'bed', genome)
        
        GalaxyInterface.runManual([trackName1, trackName2], analysisDef, regSpec, binSpec, genome, printResults=True, printHtmlWarningMsgs=False)

    def createLinkedPointTrack(cls, rsids, isUndirected, trackFn, r2):
        from quick.webtools.clustering.CreateLDTrack import CreateLDTrack
        from quick.application.ExternalTrackManager import ExternalTrackManager

        # Create file for GTrack
        galaxyTN = ExternalTrackManager.constructGalaxyTnFromSuitedFn(trackFn, fileEnding='gtrack', name='ld_graph')
        fn = ExternalTrackManager.extractFnFromGalaxyTN(galaxyTN)
        f = open(fn, 'w')

        # Get LD information and create linked point track
        ldDict = CreateLDTrack.getLDDict(r2)
        expansionDict = CreateLDTrack.getExpansionDict(rsids, ldDict)
        f.write(CreateLDTrack.formatLinkedPointTrack(expansionDict, isUndirected))

 def getOptionsBox6(prevChoices):
     if prevChoices[3]:
         extraDbColumnsDict = OrderedDict()
         fnSource = ExternalTrackManager.extractFnFromGalaxyTN(prevChoices[2].split(':'))
         fnDB = ExternalTrackManager.extractFnFromGalaxyTN(prevChoices[3].split(':'))
         
         gtrackDB = GtrackGenomeElementSource(fnDB)
         gtrackSource = GtrackGenomeElementSource(fnSource)
         
         extraDbColumns = [v for v in gtrackDB.getColumns() if not v in gtrackSource.getColumns()] #list(set(gtrackDBColumnSpec) - set(gtrackSourceColumnSpec))
         for column in extraDbColumns:
             extraDbColumnsDict[column] = False
         return extraDbColumnsDict

    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.
        '''
        from time import time
        startTime = time()
        from quick.application.ExternalTrackManager import ExternalTrackManager
        from quick.util.StaticFile import GalaxyRunSpecificFile
        import os

        motifFn = ExternalTrackManager.extractFnFromGalaxyTN( choices[0].split(':'))
        observedFasta = ExternalTrackManager.extractFnFromGalaxyTN( choices[1].split(':'))

        randomGalaxyTN = choices[2].split(':')
        randomName = ExternalTrackManager.extractNameFromHistoryTN(randomGalaxyTN)
        randomGalaxyFn = ExternalTrackManager.extractFnFromGalaxyTN( randomGalaxyTN)
        randomStatic = GalaxyRunSpecificFile(['random'],randomGalaxyFn) #finds path to static file created for a previous history element (randomFn), and directs to a folder containing several files..
        #print os.listdir(randomStatic.getDiskPath())
        randomFastaPath = randomStatic.getDiskPath()

        #motifFn, observedFasta, randomFastaPath = '/Users/sandve/egne_dokumenter/_faglig/NullModels/DnaSeqExample/liver.pwm', 'liver.fa', 'randomFastas'
        testStatistic = choices[3]
        if testStatistic == 'Average of max score per sequence':
            scoreFunc = scoreMotifOnFastaAsAvgOfBestScores
        elif testStatistic == 'Sum of scores across all positions of all sequences':
            scoreFunc = scoreMotifOnFastaAsSumOfAllScores
        elif testStatistic == 'Score of Frith et al. (2004)':
            scoreFunc = lr4
        elif testStatistic == 'Product of max per sequence':
            scoreFunc = scoreMotifOnFastaAsProductOfBestScores
        else:
            raise
        
        pvals = mcPvalFromMotifAndFastas(motifFn, observedFasta, randomFastaPath, scoreFunc)
        print 'Pvals for motifs (%s) against observed (%s) vs random (%s - %s) sequences.' % (motifFn, observedFasta, randomName, randomFastaPath)
        for motif,pval in sorted(pvals.items()):
            print motif+'\t'+('%.4f'%pval)
            
        from quick.util.StaticFile import GalaxyRunSpecificFile
        from gold.application.RSetup import r, robjects
        histStaticFile = GalaxyRunSpecificFile(['pvalHist.png'],galaxyFn)
        #histStaticFile.openRFigure()
        histStaticFile.plotRHist(pvals.values(), [x/40.0 for x in range(41)], 'Histogram of p-values', xlim=robjects.FloatVector([0.0, 1.0]))
        #r.hist(robjects.FloatVector(pvals.values()), breaks=robjects.FloatVector([x/40.0 for x in range(41)]), xlim=robjects.FloatVector([0.0, 1.0]), main='Histogram of p-values' )
        #histStaticFile.closeRFigure()
        print histStaticFile.getLink('Histogram')
        print 'Time (s):', time()-startTime

 def getRedirectURL(choices):
     
     genome = choices[0]
     track1file = ExternalTrackManager.createSelectValueFromGalaxyTN(choices[1].split(':'))
     track2file = ExternalTrackManager.createSelectValueFromGalaxyTN(choices[2].split(':'))
     return createHyperBrowserURL(genome, trackName1=['galaxy'], trackName2=['galaxy'], \
                                  track1file=track1file, track2file=track2file, \
                                  analysis='Category pairs differentially co-located?', \
                                  configDict={'Method of counting points': 'Only 1 count per bin (binary)',\
                                              'Normalize counts': 'Differentially in both directions' if \
                                              choices[3] == 'Both rows and columns (focusing on column differences)'\
                                              else 'Differentially for points only',\
                                              'P-value threshold for significance': '0.01'},\
                                  method='__chrs__')

 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.gtr
     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.
     '''
     genome = choices[1] if choices[0] == 'Yes' else None
     suffix = ExternalTrackManager.extractFileSuffixFromGalaxyTN(choices[2].split(':'))
     inFn = ExternalTrackManager.extractFnFromGalaxyTN(choices[2].split(':'))
     
     try:
         standardizeGtrackFileAndWriteToFile(inFn, galaxyFn, genome, suffix=suffix)
     except Exception, e:
         import sys
         print >> sys.stderr, e

    def getOptionsBoxFileContentsInfo(prevChoices):
        if prevChoices.history or prevChoices.input:
            if prevChoices.history:
                inputFile = open(ExternalTrackManager.extractFnFromGalaxyTN(prevChoices.history.split(':')), 'r')
            else:
                inputFile = StringIO(prevChoices.input)
            
            for i in xrange(TabularToGtrackTool._getNumSkipLines(prevChoices)):
                inputFile.readline()
            
            table = []
            splitChar = TabularToGtrackTool._getSplitChar(prevChoices)
            numCols = None
            error = None
            for i,line in enumerate(inputFile):
                row = [x.strip() for x in line.strip().split(splitChar)]
                if numCols == None:
                    numCols = len(row)
                elif numCols != len(row):
                    numCols = max(numCols, len(row))
#                    error = 'Error: the number of columns varies over the rows of the tabular file.'
                    
                table.append(row)
                if i == TabularToGtrackTool.NUM_ROWS_IN_TABLE:
                    break
            
            numCols = max(len(row) for row in table) if len(table) > 0 else 0
            
            if error is None:
                if numCols > TabularToGtrackTool.NUM_COLUMN_FUNCTIONS:
                    error = 'Error: the tabular file has more columns than is allowed by the tool (%s > %s).' % (numCols, TabularToGtrackTool.NUM_COLUMN_FUNCTIONS)
                
            return ('__hidden__', FileContentsInfo(table=table, numCols=numCols, error=error))

 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.gtr
     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.
     '''
     genome = choices.genome if choices.selectGenome == 'Yes' else None
     onlyNonDefault = choices.allHeaders == 'Only non-default headers'
     
     
     try:
         if choices.history:
             inFn = ExternalTrackManager.extractFnFromGalaxyTN(choices.history.split(':'))
             expandHeadersOfGtrackFileAndWriteToFile(inFn, galaxyFn, genome, onlyNonDefault)
         else:
             if choices.whitespace == 'Keep whitespace exact':
                 input = choices.input
             else:
                 input = ''
                 for line in choices.input.split(os.linesep):
                     line = line.strip()
                     if (line.startswith('###') and len(line) > 3 and line[3] != '#') \
                         or not line.startswith('#'):
                         line = line.replace(' ', '\t')
                     else:
                         line = line.replace('\t', ' ')
                     input += line + os.linesep
         
             composer = expandHeadersOfGtrackFileAndReturnComposer('', genome, strToUseInsteadOfFn=input)
             composer.composeToFile(galaxyFn, onlyNonDefault=onlyNonDefault)
     except Exception, e:
         import sys
         print >> sys.stderr, e

    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.
        '''
        genome = choices[0]
        trackName = choices[1].split(':')
        
        galaxyOutTrackName = 'galaxy:hbfunction:%s:Create function track of distance to nearest segment' % galaxyFn
        outTrackName = ExternalTrackManager.getStdTrackNameFromGalaxyTN(galaxyOutTrackName.split(':'))
        
        if choices[2] == 'No transformation':
            valTransformation = 'None'
        elif choices[2] =='Logarithmic (log10(x))':
            valTransformation = 'log10'
        elif choices[2] == 'Fifth square root (x**0.2)':
            valTransformation = 'power0.2'
        
        analysisDef ='[dataStat=MakeDistanceToNearestSegmentStat] [valTransformation=%s][outTrackName=' % valTransformation \
                     + '^'.join(outTrackName) + '] -> CreateFunctionTrackStat'
        #userBinSource, fullRunArgs = GalaxyInterface._prepareRun(trackName, None, analysisDef, '*', '*', genome)
        #
        #for el in userBinSource:
        #    print el.chr, el.start, el.end
            
        from quick.application.GalaxyInterface import GalaxyInterface

        print GalaxyInterface.getHbFunctionOutputBegin(galaxyFn, withDebug=False)
        
        GalaxyInterface.runManual([trackName], analysisDef, '*', '*', genome, username=username, printResults=False, printHtmlWarningMsgs=False)
        #job = AnalysisDefJob(analysisDef, trackName, None, userBinSource).run()
        
        print GalaxyInterface.getHbFunctionOutputEnd('A custom track has been created by finding the bp-distance to the nearest segment', withDebug=False)