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 plainRun(analysisDef, genome, track1Fn, track2Fn):
'''
Currently under development, not yet functioning.
Note that file names (track1Fn, track2Fn) must either be a valid .dat-file from a Galaxy system,
or be located in a path where the two deepest levels are numerical values above 1000, and unique between different runs by this tool'''
#GalaxyInterface.runManual(trackNames, analysisDef, regSpec, binSpec, genome, galaxyFn=None, trackNameIntensity=None, username='', \
#printResults=True, printProgress=True, printHtmlWarningMsgs=True, applyBoundaryFilter=False, printRunDescription=True, **kwArgs):
from quick.application.ExternalTrackManager import ExternalTrackManager
#fixme: is this correct?
assert all(
idPart > 1000
for idPart in ExternalTrackManager.extractIdFromGalaxyFn(track1Fn))
tn1 = ExternalTrackManager.constructGalaxyTnFromSuitedFn(track1Fn)
assert all(
idPart > 1000
for idPart in ExternalTrackManager.extractIdFromGalaxyFn(track2Fn))
tn2 = ExternalTrackManager.constructGalaxyTnFromSuitedFn(track2Fn)
from quick.application.GalaxyInterface import GalaxyInterface
userBinSource = GalaxyInterface._getUserBinSource('chrs', '*', genome, tn1,
tn2)
from gold.application.StatRunner import AnalysisDefJob
job = AnalysisDefJob(analysisDef, tn1, tn2, userBinSource)
result = job.run(printProgress=False)
return result
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 self.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 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 runJob(batchLine, genome, fullAccess, galaxyFn=None, printProgress=True):
bc = BatchRunner.parseBatchLine(batchLine, genome, fullAccess)
if bc.errorResult is not None:
return bc.errorResult
#Try a full run, and return either results or an exception
try:
#track = Track(trackName1)
#track2 = Track(trackName2)
#if 'tf1' in paramDict:
# track.setFormatConverter(formatConverter)
#results = StatRunner.run(userBinSource , Track(trackName1), Track(trackName2), \
# wrapClass(STAT_CLASS_DICT[statClassName], keywords=paramDict) )
#results = StatRunner.run(userBinSource , track, track2, \
# wrapClass(STAT_CLASS_DICT[statClassName], keywords=paramDict) )
fullRunParams = {}
if USE_PARALLEL:
#if galaxyFn == None: #then this is a test
uniqueId = time.time()
#else:
#uniqueId = extractIdFromGalaxyFn(galaxyFn)[1]
fullRunParams["uniqueId"] = uniqueId
if bc.cleanedTrackNameIntensity is not None:
fullRunParams['trackNameIntensity'] = '|'.join(tuple(bc.cleanedTrackNameIntensity))
analysisDefParams = [ '[' + key + '=' + value + ']' for key,value in bc.paramDict.items()]
analysisDef = ''.join(analysisDefParams) + '->' + bc.statClassName
from quick.application.GalaxyInterface import GalaxyInterface
GalaxyInterface._tempAnalysisDefHacks(analysisDef)
if printProgress:
print 'Corresponding batch command line:<br>' + \
GalaxyInterface._revEngBatchLine(bc.trackName1, bc.trackName2, bc.trackNameIntensity, analysisDef, bc.regSpec, bc.binSpec, genome) + '<br><br>'
results = AnalysisDefJob(analysisDef, bc.cleanedTrackName1, bc.cleanedTrackName2, bc.userBinSource, galaxyFn=galaxyFn, **fullRunParams).run(printProgress)
presCollectionType = results.getPresCollectionType()
if len(results.getResDictKeys()) > 0 and GalaxyInterface.APPEND_ASSEMBLY_GAPS and presCollectionType=='standard':
if USE_PARALLEL:
gapRes = AssemblyGapJob(bc.userBinSource, genome, uniqueId=uniqueId).run(printProgress)
else:
gapRes = AssemblyGapJob(bc.userBinSource, genome).run(printProgress)
results.includeAdditionalResults(gapRes, ensureAnalysisConsistency=False)
except Exception, e:
#print 'NOWAG BExc'
results = Results(bc.cleanedTrackName1, bc.cleanedTrackName2, bc.statClassName)
results.addError(e)
logException(e,message='Error in batch run')
if DebugConfig.PASS_ON_BATCH_EXCEPTIONS:
raise
return results
def doAnalysisFromDefTwo(cls, tracks, analysisDef, regSpec, binSpec,
genome, flag):
userBinSource = UserBinSource(regSpec, binSpec, genome)
job = AnalysisDefJob(analysisDef.getDefAfterChoices(),
tracks[0].trackName,
tracks[1].trackName,
userBinSource,
galaxyFn=None)
result = job.run()
unorderedResults = [(str(key), result[key])
for key in result.getAllRegionKeys()]
return list(cls.sortDictionaries(unorderedResults, flag))
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 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 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 testCreateIntensityTrack(self):
regions = [GenomeRegion(self._genome, self._chr, 1000, 5000),\
GenomeRegion(self._genome, self._chr, 6000, 7000),\
GenomeRegion(self._genome, self._chr, 10000, 16000)]
job = AnalysisDefJob('[dataStat=SimpleBpIntensityStat] [outTrackName=' + '^'.join(self._trackName) + '] [numDiscreteVals=10] -> CreateFunctionTrackStat', \
['nums'], ['points'], regions, genome=self._genome)
for x in range(2):
job.run()
brShelve = BoundingRegionShelve(self._genome,
self._trackName,
allowOverlaps=False)
self.assertRaises(OutsideBoundingRegionError, \
brShelve.getBoundingRegionInfo, GenomeRegion(self._genome, self._chr, 0, 1))
#self.assertEquals(BoundingRegionInfo(0, 1, 0, 0, 0, 0),
# brShelve.getBoundingRegionInfo(GenomeRegion(self._genome, self._chr, 0, 1)))
self.assertEquals(
BoundingRegionInfo(1000, 5000, 0, 4000, 0, 0),
brShelve.getBoundingRegionInfo(
GenomeRegion(self._genome, self._chr, 2000, 2001)))
self.assertRaises(OutsideBoundingRegionError, \
brShelve.getBoundingRegionInfo, GenomeRegion(self._genome, self._chr, 5500, 5501))
#self.assertEquals(BoundingRegionInfo(5500, 5501, 0, 0, 0, 0),
# brShelve.getBoundingRegionInfo(GenomeRegion(self._genome, self._chr, 5500, 5501)))
self.assertEquals(
BoundingRegionInfo(6000, 7000, 4000, 5000, 0, 0),
brShelve.getBoundingRegionInfo(
GenomeRegion(self._genome, self._chr, 6500, 6501)))
self.assertRaises(OutsideBoundingRegionError, \
brShelve.getBoundingRegionInfo, GenomeRegion(self._genome, self._chr, 8000, 8001))
#self.assertEquals(BoundingRegionInfo(8000, 8001, 0, 0, 0, 0),
# brShelve.getBoundingRegionInfo(GenomeRegion(self._genome, self._chr, 8000, 8001)))
self.assertEquals(
BoundingRegionInfo(10000, 16000, 5000, 11000, 0, 0),
brShelve.getBoundingRegionInfo(
GenomeRegion(self._genome, self._chr, 11000, 11001)))
self.assertRaises(OutsideBoundingRegionError, \
brShelve.getBoundingRegionInfo, GenomeRegion(self._genome, self._chr, 16500, 16501))
#self.assertEquals(BoundingRegionInfo(16500, 16501, 0, 0, 0, 0),
# brShelve.getBoundingRegionInfo(GenomeRegion(self._genome, self._chr, 16500, 16501)))
trackData = TrackSource().getTrackData(self._trackName, self._genome,
None, False)
self.assertListsOrDicts(['val'], trackData.keys())
self.assertListsOrDicts((11000, ), trackData['val'].shape)
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 doAnalysis(analysisSpec, analysisBins, tracks):
'''Performs an analysis,
as specified by analysisSpec object,
in each bin specified by analysisBins,
on data sets specified in tracks.
Typical usage:
analysisSpec = AnalysisSpec(AvgSegLenStat)
analysisSpec.addParameter("withOverlaps","no")
analysisBins = GlobalBinSource('hg18')
tracks = [ Track(['Genes and gene subsets','Genes','Refseq']) ]
results = doAnalysis(analysisSpec, analysisBins, tracks)
'''
# TODO: handle multiple tracks analysis
# assert len(tracks) in [1,2] #for now..
# in an API setting, exceptions should not generally be hidden.
# Maybe this should be optional.
# setupDebugModeAndLogging()
silenceRWarnings()
silenceNumpyWarnings()
if len(tracks) > 2:
from gold.util.CommonConstants import MULTIPLE_EXTRA_TRACKS_SEPARATOR
analysisSpec.addParameter(
'extraTracks',
MULTIPLE_EXTRA_TRACKS_SEPARATOR.join([
'^'.join([quote(part) for part in x.trackName])
for x in tracks[2:]
]))
job = AnalysisDefJob(analysisSpec.getDefAfterChoices(),
tracks[0].trackName,
tracks[1].trackName if len(tracks) > 1 else None,
analysisBins,
galaxyFn=None)
res = job.run(printProgress=False) # printProgress should be optional?
return res
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 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(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 runJob(batchLine, genome, fullAccess, galaxyFn=None, printProgress=True):
bc = BatchRunner.parseBatchLine(batchLine, genome, fullAccess)
if bc.errorResult is not None:
return bc.errorResult
#Try a full run, and return either results or an exception
try:
#track = Track(trackName1)
#track2 = Track(trackName2)
#if 'tf1' in paramDict:
# track.setFormatConverter(formatConverter)
#results = StatRunner.run(userBinSource , Track(trackName1), Track(trackName2), \
# wrapClass(STAT_CLASS_DICT[statClassName], keywords=paramDict) )
#results = StatRunner.run(userBinSource , track, track2, \
# wrapClass(STAT_CLASS_DICT[statClassName], keywords=paramDict) )
fullRunParams = {}
if USE_PARALLEL:
# TODO: Requirements for parallel runs should not be added in places like these. Parallelization
# should be a feature of the job runner somehow
#if galaxyFn == None: #then this is a test
uniqueId = time.time()
#else:
#uniqueId = extractIdFromGalaxyFn(galaxyFn)[1]
fullRunParams["uniqueId"] = uniqueId
from quick.application.GalaxyInterface import GalaxyInterface
analysisDefParams = [ '[' + key + '=' + value + ']' for key,value in bc.paramDict.items()]
analysisDef = ''.join(analysisDefParams) + '->' + bc.statClassName
# TODO: Keeping the ugly accesses to private methods in GalaxyInterface for now. To be refactored.
trackNames, analysisDef = GalaxyInterface._cleanUpAnalysisDef(bc.cleanedTrackNames, analysisDef)
if printProgress:
revEngBatchLine = RunDescription.getRevEngBatchLine(
analysisDef, bc.trackNames, bc.cleanedTrackNames, bc.regSpec, bc.binSpec, genome
)
print 'Corresponding batch command line:<br>{}<br><br>'.format(revEngBatchLine)
results = AnalysisDefJob(analysisDef, bc.cleanedTrackNames[0], bc.cleanedTrackNames[1], bc.userBinSource, galaxyFn=galaxyFn, **fullRunParams).run(printProgress)
presCollectionType = results.getPresCollectionType()
if len(results.getResDictKeys()) > 0 and GalaxyInterface.APPEND_ASSEMBLY_GAPS and presCollectionType=='standard':
if USE_PARALLEL:
gapRes = AssemblyGapJob(bc.userBinSource, genome, uniqueId=uniqueId).run(printProgress)
else:
gapRes = AssemblyGapJob(bc.userBinSource, genome).run(printProgress)
results.includeAdditionalResults(gapRes, ensureAnalysisConsistency=False)
except Exception, e:
#print 'NOWAG BExc'
results = Results(bc.cleanedTrackNames[0], bc.cleanedTrackNames[1], bc.statClassName)
results.addError(e)
logException(e,message='Error in batch run')
if DebugConfig.PASS_ON_BATCH_EXCEPTIONS:
raise
return results
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