def extract_feature(self, genome, track, ref, option) :
'''
this function return the relation of clusterTrack to referenceTrack
option is the statistical function used, should be named feature
track, ref is clusterTrack and referenceTrack
'''
validFeature = FeatureCatalog.getFeaturesFromTracks(genome,track,ref)[option] #validFeature contains analysisDef and the key to get the needed number from the global result
if option == 'Prop. of tr1-points falling inside segments of tr2' and cls.getTrackFormat(genome, track) in ['Segments', 'Valued segments'] :
analysisDef = 'dummy [tf1=SegmentToMidPointFormatConverter] -> DerivedPointCountsVsSegsStat'
else :
analysisDef = validFeature[0] #or any other statistic from the HB collection
if self.params.get("compare_in") == "Chromosomes" :
regSpec = "__chrs__"
binSpec = self.params.get("Chromosomes")
elif self.params.get("compare_in") == "Chromosome arms" :
regSpec = "__chrArms__"
binSpec = self.params.get("Chromosome_arms")
elif self.params.get("compare_in") == "Cytobands" :
regSpec = "__chrBands__"
binSpec = self.params.get("Cytobands")
else :
regSpec = self.params.get("region")
binSpec = self.params.get("binsize")
#regSpec = self.params.get("region")
#binSpec = self.params.get("binsize")
#regSpec = 'chr1' #could also be e.g. 'chr1' for the whole chromosome or '*' for the whole genome
#binSpec = '10m' #could also be e.g.'100', '1k' or '*' for whole regions/chromosomes as bins
#genome = 'hg18'
userBinSource = GalaxyInterface._getUserBinSource(regSpec,binSpec,genome)
if option == 'Prop. of tr2 covered by tr1' : #because the confuse of refTrack and clusterTrack in this statistics
result = AnalysisDefJob(analysisDef, ref, track, userBinSource).run()
else :
result = AnalysisDefJob(analysisDef, track, ref, userBinSource).run()
mainResultDict = result.getGlobalResult()
return mainResultDict[validFeature[1]]
def createSplittedChrArms(genome, binSize, outFn):
"""genome binsize outFn.bed"""
outFile = open(outFn, 'w')
from quick.application.GalaxyInterface import GalaxyInterface
chrArms = GalaxyInterface._getUserBinSource('__chrArms__', '*', genome)
chrArmBins = AutoBinner(chrArms, int(binSize))
for bin in chrArmBins:
outFile.write('\t'.join([bin.chr, str(bin.start), str(bin.end)]) + os.linesep)
outFile.close()
def handleRegionClustering(self, genome, tracks, clusterMethod, extra_option):
region_cluster_track = self.getHistoryTrackDef('track1')
print region_cluster_track
region_ref_track = self.params.get('reftrack1')
if region_cluster_track[0] == 'galaxy' :
file_type = region_cluster_track[1]
track_path = region_cluster_track[2]
userBinSource = GalaxyInterface._getUserBinSource('bed', track_path, genome)
validFeature = SplittedRegionsAsFeaturesCatalog.getValidAnalyses(genome,region_ref_track,[])
analysisDef = validFeature[0]
result = AnalysisDefJob(analysisDef, region_ref_track, [], userBinSource).run()
print [result[localKey][validFeature[1]] for localKey in sorted(result.keys())]
def computeDistance(cls, genome, track1, track2, feature, regSpec, binSpec): #direct distance between track1, track2
'''
track1 and track2 are two lists like : ['Sequence','Repeating elements','LINE']
feature specifies how the distance between track1 and track2 is defined
'''
validFeature = DirectDistanceCatalog.getValidAnalyses(genome, track1, track2)[feature]
analysisDef = validFeature[0] #'bla bla -> PropFreqOfTr1VsTr2Stat' #or any other statistic from the HB collection
userBinSource = GalaxyInterface._getUserBinSource(regSpec,binSpec,genome)
result = AnalysisDefJob(analysisDef, track1, track2, userBinSource).run()
mainResultDict = result.getGlobalResult()
return mainResultDict[validFeature[1]]
def build_feature_vector(genome, ctrack, feature, regSpec, binSpec):
'''
this function create a feature vector for ctrack
feature specifies how the vector is constructed
'''
#print 'Feauter:', LocalResultsAsFeaturesCatalog.getValidAnalyses(genome, ctrack, [])
validFeature = LocalResultsAsFeaturesCatalog.getValidAnalyses(genome, ctrack, [])[feature]
analysisDef = validFeature[0]
#regSpec = self.params.get("region")
#binSpec = self.params.get("binsize")
userBinSource = GalaxyInterface._getUserBinSource(regSpec,binSpec,genome)
result = AnalysisDefJob(analysisDef, ctrack, [], userBinSource).run()
return [result[localKey][validFeature[1]] for localKey in sorted(result.keys())]
def extract_feature(cls, genome, track, ref, option, regSpec, binSpec, trackFormat) :
#print 'genome, track, ref, option, regSpec, binSpec, trackFormat: ', genome, track, ref, option, regSpec, binSpec, trackFormat
validFeature = FeatureCatalog.getFeaturesFromTracks(genome,track,ref)[option] #validFeature contains analysisDef and the key to get the needed number from the global result
if option == 'Prop. of tr1-points falling inside segments of tr2' and trackFormat in ['Segments', 'Valued segments'] :
analysisDef = 'dummy [tf1=SegmentToMidPointFormatConverter] -> DerivedPointCountsVsSegsStat'
else :
analysisDef = validFeature[0] #or any other statistic from the HB collection
userBinSource = GalaxyInterface._getUserBinSource(regSpec,binSpec,genome)
result = AnalysisDefJob(analysisDef, ref, track, userBinSource).run() if option == 'Prop. of tr2 covered by tr1' else AnalysisDefJob(analysisDef, track, ref, userBinSource).run()
validAnalysisDef = validFeature[1]
assert result.getGlobalResult() is not None, 'Did not get any global result for analysisDef: '+validAnalysisDef
return result.getGlobalResult()[validAnalysisDef]
def computeDistance(track1, track2, feature='direct distance'):
'''
track1 and track2 are two lists like : ['Sequence','Repeating elements','LINE']
feature specifies how the distance between track1 and track2 is defined
'''
analysisDef = 'bla bla -> PropFreqOfTr1VsTr2Stat' #or any other statistic from the HB collection
regSpec = 'chr1' #could also be e.g. 'chr1' for the whole chromosome or '*' for the whole genome
binSpec = '10m' #could also be e.g.'100', '1k' or '*' for whole regions/chromosomes as bins
genome = 'hg18' # path /../../..../genome
#allRepeats = GalaxyInterface.getSubTrackNames(genome,['Sequence','Repeating elements'],False) #all elements in 'Repeating elements' directory
#GalaxyInterface.run(trackName1, trackName2, question, regSpec, binSpec, genome='hg18')
userBinSource = GalaxyInterface._getUserBinSource(regSpec,binSpec,genome)
result = AnalysisDefJob(analysisDef, track1, track2, userBinSource).run()
#result er av klassen Results..
#from gold.result.Results import Results
mainResultDict = result.getGlobalResult()
#from PropFreqOfTr1VsTr2Stat:...
#self._result = {'Track1Prop':ratio,'CountTrack1':c1, 'CountTrack2':c2,'Variance':variance}
mainValueOfInterest = mainResultDict['Variance']
return mainValueOfInterest
def computeDistance(self, genome, track1, track2, feature): #direct distance between track1, track2
'''
track1 and track2 are two lists like : ['Sequence','Repeating elements','LINE']
feature specifies how the distance between track1 and track2 is defined
'''
validFeature = DirectDistanceCatalog.getValidAnalyses(genome, track1, track2)[feature]
analysisDef = validFeature[0] #'bla bla -> PropFreqOfTr1VsTr2Stat' #or any other statistic from the HB collection
if self.params.get("compare_in") == "Chromosomes" :
regSpec = "__chrs__"
binSpec = self.params.get("Chromosomes")
elif self.params.get("compare_in") == "Chromosome arms" :
regSpec = "__chrArms__"
binSpec = self.params.get("Chromosome_arms")
elif self.params.get("compare_in") == "Cytobands" :
regSpec = "__chrBands__"
binSpec = self.params.get("Cytobands")
else :
regSpec = self.params.get("region")
binSpec = self.params.get("binsize")
#regSpec = 'chr1' #could also be e.g. 'chr1' for the whole chromosome or '*' for the whole genome
#binSpec = '10m' #could also be e.g.'100', '1k' or '*' for whole regions/chromosomes as bins
#genome = 'hg18' # path /../../..../genome
#allRepeats = GalaxyInterface.getSubTrackNames(genome,['Sequence','Repeating elements'],False)
#GalaxyInterface.run(trackName1, trackName2, question, regSpec, binSpec, genome='hg18')
userBinSource = GalaxyInterface._getUserBinSource(regSpec,binSpec,genome)
result = AnalysisDefJob(analysisDef, track1, track2, userBinSource).run()
#result er av klassen Results..
#from gold.result.Results import Results
mainResultDict = result.getGlobalResult()
#from PropFreqOfTr1VsTr2Stat:...
#self._result = {'Track1Prop':ratio,'CountTrack1':c1, 'CountTrack2':c2,'Variance':variance}
#mainValueOfInterest = mainResultDict['Variance']
return mainResultDict[validFeature[1]]
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 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...'
#print choices
#trackName1 = ['Sequence','Repeating elements','LINE'] #a list of subdirectories from 'genome' to the repeat file
#trackName2 = ['Sequence','Repeating elements','SINE']
#allRepeats = GalaxyInterface.getSubTrackNames(genome,['Sequence','Repeating elements'],False) #all elements in 'Repeating elements' directory
#analysisDef = 'bla bla -> PropFreqOfTr1VsTr2Stat' #or any other statistic from the HB collection
#regSpec = 'chr1' #could also be e.g. 'chr1' for the whole chromosome or '*' for the whole genome
#binSpec = '10m' #could also be e.g.'100', '1k' or '*' for whole regions/chromosomes as bins
genome = 'hg18' # path /../../..../genome
allRepeats = GalaxyInterface.getSubTrackNames(genome,['Sequence','Repeating elements'],False) #all elements in 'Repeating elements' directory
#GalaxyInterface.run(trackName1, trackName2, question, regSpec, binSpec, genome='hg18')
#userBinSource = GalaxyInterface._getUserBinSource(regSpec,binSpec,genome)
#result = AnalysisDefJob(analysisDef, trackName1, trackName2, userBinSource).run()
#result er av klassen Results..
#from gold.result.Results import Results
#mainResultDict = result.getGlobalResult()
#from PropFreqOfTr1VsTr2Stat:...
#self._result = {'Track1Prop':ratio,'CountTrack1':c1, 'CountTrack2':c2,'Variance':variance}
#mainValueOfInterest = mainResultDict['Variance']
#print 'first repeat', allRepeats[0]
#print '\n all repeats', allRepeats
#minValue = HiepsTool.computeDistance(trackName1,trackName2)
#print minValue
#choicedTracks = [['Sequence','Repeating elements',name] for name in choices]
#print '\n choiced tracks', choicedTracks
#d_matrix = HiepsTool.constructDistMatrix(choicedTracks)
#tree = treecluster(distancematrix=d_matrix, method='s')
#print tree
#figure = StaticFile(['hiepln','dendro'],'jpg')
#filepath = figure.getDiskPath()
#print filepath
#draw_dendrogram(tree,choices,filepath)
#print figure.getLink('clustring result')
track1 = ['Sequence','Repeating elements', 'DNA']
track2 = ['Gene regulation', 'TFBS', 'High Throughput']
analysisDef = 'bla bla -> DerivedOverlapStat' #or any other statistic from the HB collection
regSpec = 'chr1' #could also be e.g. 'chr1' for the whole chromosome or '*' for the whole genome
binSpec = '10m' #could also be e.g.'100', '1k' or '*' for whole regions/chromosomes as bins
genome = 'hg18' # path /../../..../genome
#allRepeats = GalaxyInterface.getSubTrackNames(genome,['Sequence','Repeating elements'],False) #all elements in 'Repeating elements' directory
#GalaxyInterface.run(trackName1, trackName2, question, regSpec, binSpec, genome='hg18')
userBinSource = GalaxyInterface._getUserBinSource(regSpec,binSpec,genome)
result = AnalysisDefJob(analysisDef, track1, track2, userBinSource).run()
#result er av klassen Results..
#from gold.result.Results import Results
mainResultDict = result.getGlobalResult()
#keys = result.getResDictKeys()
#print keys
#print mainResultDict['2in1']
print '<ol>'
for key in mainResultDict.keys() :
print '<li>key:%s,value:%s </li>'%(key,mainResultDict[key])
print '</ol>'
from gold.application.GalaxyInterface import GalaxyInterface
from gold.application.StatRunner import AnalysisDefJob
trackName1 = ['Sequence', 'Repeating elements', 'LINE']
trackName2 = ['Sequence', 'Repeating elements', 'SINE']
#GalaxyInterface.getSubTrackNames(['Sequence','Repeating elements'],False)
analysisDef = 'bla bla -> PropFreqOfTr1VsTr2Stat' #or any other statistic from the HB collection
regSpec = 'chr1' #could also be e.g. 'chr1' for the whole chromosome or '*' for the whole genome
binSpec = '10m' #could also be e.g.'100', '1k' or '*' for whole regions/chromosomes as bins
genome = 'hg18'
#GalaxyInterface.run(trackName1, trackName2, question, regSpec, binSpec, genome='hg18')
userBinSource = GalaxyInterface._getUserBinSource(regSpec, binSpec, genome)
result = AnalysisDefJob(analysisDef, trackName1, trackName2,
userBinSource).run()
#result er av klassen Results..
#from gold.result.Results import Results
mainResultDict = result.getGlobalResult()
#from PropFreqOfTr1VsTr2Stat:...
#self._result = {'Track1Prop':ratio,'CountTrack1':c1, 'CountTrack2':c2,'Variance':variance}
mainValueOfInterest = mainResultDict['Variance']
print 'The ..variance..: ', mainValueOfInterest
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 executeSelfFeature(cls, genome, tracks, track_names, clusterMethod, extra_option, feature, distanceType, kmeans_alg, galaxyFn, regSpec, binSpec):
from gold.application.RSetup import r
#regSpec, binSpec = 'bed', '/usit/invitro/data/galaxy/galaxy-dist-hg-dev/./database/files/017/dataset_17084.dat'
jobFile = open(galaxyFn, 'w')
print>>jobFile, 'PARAMS: ', dict(zip('genome, tracks, track_names, clusterMethod, extra_option, feature, distanceType, kmeans_alg, regSpec, binSpec'.split(','), [repr(v)+'<br>'for v in [genome, tracks, track_names, clusterMethod, extra_option, feature, distanceType, kmeans_alg,regSpec, binSpec]]))
print>>jobFile, '<br><br>To run:<br>$clusterBySelfFeature', (genome, '$'.join([':'.join(t) for t in tracks]), ':'.join(track_names) , clusterMethod, extra_option, feature, distanceType, kmeans_alg, regSpec, binSpec), '<br><br>'
print>>jobFile, 'signature of method clusterBySelfFeature:<br>', 'clusterBySelfFeature(genome, tracksStr, track_namesStr, clusterMethod, extra_option, feature, distanceType, kmeans_alg, regSpec, binSpec):<br><br><br>'
prettyTrackNames = [v[-1].replace('RoadMap_','').replace('.H3K4me1','') for v in tracks]
#prettyTrackNames = [prettyPrintTrackName(v, shortVersion=True) for v in tracks]
f_matrix = cls.construct_feature_matrix(genome, tracks, feature, regSpec, binSpec)
print>>jobFile, 'dir f_matrix: ', dir(f_matrix), regSpec, binSpec
userBinSource = GalaxyInterface._getUserBinSource(regSpec,binSpec,genome)
r.assign('bin_names',[str(bin) for binIndex, bin in enumerate(sorted(list(userBinSource)))])
r.assign('track_names',prettyTrackNames) #use as track names, will be shown in clustering figure
r.assign('f_matrix',f_matrix)
r.assign('distanceType',distanceType)
r('row.names(f_matrix) <- track_names')
r('colnames(f_matrix) <- bin_names')
if clusterMethod == 'Hierarchical clustering' and extra_option != "--select--" :
#print 'galaxyFn: ', galaxyFn
figure = GalaxyRunSpecificFile(['cluster_tracks_result_figure.pdf'], galaxyFn)
figurepath = figure.getDiskPath(True)
r.pdf(figurepath)
r('d <- dist(f_matrix, method=distanceType)')
r_f_matrixFile = GalaxyRunSpecificFile(['f-matrix.robj'], galaxyFn)
#', '.join([str(v) for v in row])
r.assign('f_matrix_fn', r_f_matrixFile.getDiskPath(True))
r('dput(f_matrix, f_matrix_fn)')
#r_f_matrixFile.writeTextToFile(', '.join(cls.getFlattenedMatrix(f_matrix)) + '\n\nTrack names: '+', '.join(prettyTrackNames)+'\n\nNumber of tracks: '+str(len(prettyTrackNames))+'\n\nbins: +)
#r_f_matrixFile.writeTextToFile()
#r_f_matrixFile.writeTextToFile(str(f_matrix)+'\n\n'+str(r.d))
print>>jobFile, r_f_matrixFile.getLink('feature_matrix')
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>')
heatmap = GalaxyRunSpecificFile(['heatmap_figure.pdf'], galaxyFn)
heatmap_path = heatmap.getDiskPath(True)
r.pdf(heatmap_path)
r('heatmap(f_matrix, col=cm.colors(256), distfun=function(c) dist(c, method=distanceType), hclustfun=function(c) hclust(c, method=extra_option, members=NULL),Colv=NA, scale="none", xlab="", ylab="", cexRow=0.5, cexCol=0.5, margin=c(8,10))')#Features cluster tracks
r('dev.off()')
print>>jobFile, r('dimnames(f_matrix)')
print>>jobFile, heatmap.getLink('heatmap 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('kmeans_alg',kmeans_alg)
r.assign('extra_option',extra_option)
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 = r('hr$cluster')
for index1 in range(extra_option) : #extra_option actually the number of clusters
#trackInCluster = [k for k,val in clusters.items() if val == index1]
trackInCluster = [k+1 for k,val in enumerate(clusters) if val == index1+1] #IS THIS CORRECT, I.E. SAME AS ABOVE??
print>>kmeans_output, 'Cluster %i(%s objects) : ' % (index1+1, str(clusterSizes[index1]))
for name in trackInCluster :
print>>kmeans_output, name, '(This result may be a bit shaky afters some changes in rpy access)'
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>')
cls.print_data(f_matrix, jobFile)
'''
from gold.application.GalaxyInterface import GalaxyInterface
from gold.application.StatRunner import AnalysisDefJob
trackName1 = ['Sequence','Repeating elements','LINE']
trackName2 = ['Sequence','Repeating elements','SINE']
#GalaxyInterface.getSubTrackNames(['Sequence','Repeating elements'],False)
analysisDef = 'bla bla -> PropFreqOfTr1VsTr2Stat' #or any other statistic from the HB collection
regSpec = 'chr1' #could also be e.g. 'chr1' for the whole chromosome or '*' for the whole genome
binSpec = '10m' #could also be e.g.'100', '1k' or '*' for whole regions/chromosomes as bins
genome = 'hg18'
#GalaxyInterface.run(trackName1, trackName2, question, regSpec, binSpec, genome='hg18')
userBinSource = GalaxyInterface._getUserBinSource(regSpec,binSpec,genome)
result = AnalysisDefJob(analysisDef, trackName1, trackName2, userBinSource).run()
#result er av klassen Results..
#from gold.result.Results import Results
mainResultDict = result.getGlobalResult()
#from PropFreqOfTr1VsTr2Stat:...
#self._result = {'Track1Prop':ratio,'CountTrack1':c1, 'CountTrack2':c2,'Variance':variance}
mainValueOfInterest = mainResultDict['Variance']
print 'The ..variance..: ', mainValueOfInterest
