def decodeChoice(self, opts, id, choice):
if opts == '__track__':
tn = str(choice).split(':')
GalaxyInterface.cleanUpTrackName(tn)
choice = ':'.join(tn)
else:
choice = super(HyperBrowserControllerMixin, self).decodeChoice(opts, id, choice)
return choice
def execute(self):
self.stdoutToHistory()
#print self.params
#tracks = self.params['track1'].split(':')
username = self.params['userEmail'] if self.params.has_key('userEmail') else ''
track = self.params['track1'] if self.params.has_key('track1') else []
print 'GalaxyInterface.startPreProcessing', (self.genome, track, username)
GalaxyInterface.startPreProcessing(self.genome, track, username)
def execute(self):
self.stdoutToHistory()
#print self.params
#tracks = self.params['track1'].split(':')
username = self.params['userEmail'] if self.params.has_key(
'userEmail') else ''
track = self.params['track1'] if self.params.has_key('track1') else []
print 'GalaxyInterface.startPreProcessing', (self.genome, track,
username)
GalaxyInterface.startPreProcessing(self.genome, track, username)
def testGetStatOptions(self):
if self.VERBOSE:
DebugConfig.VERBOSE = True
DebugConfig.PASS_ON_COMPUTE_EXCEPTIONS = True
prevVal = DebugConfig.PASS_ON_VALIDSTAT_EXCEPTIONS
DebugConfig.PASS_ON_VALIDSTAT_EXCEPTIONS= False
self.assertTrue(len( GalaxyInterface.getStatOptions('TestGenome',['segsMany'], ['segs'], 'Hypothesis testing') ) > 0)
self.assertTrue(len( GalaxyInterface.getStatOptions('TestGenome',['segsMany'], ['nums'], 'Hypothesis testing') ) > 0)
DebugConfig.PASS_ON_VALIDSTAT_EXCEPTIONS= prevVal
def testGetStatOptions(self):
if self.VERBOSE:
DebugConfig.VERBOSE = True
DebugConfig.PASS_ON_COMPUTE_EXCEPTIONS = True
prevVal = DebugConfig.PASS_ON_VALIDSTAT_EXCEPTIONS
DebugConfig.PASS_ON_VALIDSTAT_EXCEPTIONS= False
self.assertTrue(len( GalaxyInterface.getStatOptions('TestGenome',['segsMany'], ['segs'], 'Hypothesis testing') ) > 0)
self.assertTrue(len( GalaxyInterface.getStatOptions('TestGenome',['segsMany'], ['nums'], 'Hypothesis testing') ) > 0)
DebugConfig.PASS_ON_VALIDSTAT_EXCEPTIONS= prevVal
def reinstallGenomes(genomeList, username, genomeListIsFn='True', verbose='False'):
"genomeList username genomeListIsFn=True verbose=False"
from quick.application.GalaxyInterface import GalaxyInterface
from gold.util.CustomExceptions import PreprocessError
from quick.extra.StandardizeTrackFiles import PlainMover
from config.Config import DebugConfig
genomeListIsFn = ast.literal_eval(genomeListIsFn)
verbose = ast.literal_eval(verbose)
prevPassOnPreprocessExceptions = DebugConfig.PASS_ON_PREPROCESS_EXCEPTIONS
prevVerbose = DebugConfig.VERBOSE
DebugConfig.PASS_ON_PREPROCESS_EXCEPTIONS = True
DebugConfig.VERBOSE = verbose
track_cats = ['Sequence:DNA', 'Genome build properties', 'Genes and gene subsets', 'Sample data']
if genomeListIsFn:
genomes = [_.strip() for _ in open(genomeList)]
else:
genomes = genomeList.split(',')
for genome in genomes:
genome = genome.strip()
print genome
if GenomeInfo(genome).installed and GenomeInfo._queryShelveWithKey(genome, 'r', old=False) is not None:
# Trigger installation double-check
gi = GenomeInfo(genome)
gi.installed = False
gi.store()
if gi.isInstalled():
print '\n**Genome "{}" was alread installed in the new shelve. Skipping!**\n'.format(genome)
continue
for track_cat in track_cats:
try:
GalaxyInterface.startPreProcessing(genome, track_cat.split(':'), username)
except PreprocessError, e:
traceback.print_exc()
print
match = re.search(r'trackName="([^"]+)"', str(e))
if match:
trackName = match.group(1).split(':')
PlainMover.parseFiles(genome, trackName, 'std_to_error')
print '\n\n**Moved track "{}" to "parsingErrorTracks" file structure**\n'.format(':'.join(trackName))
genome_info = GenomeInfo(genome)
installed = genome_info.flagAsInstalled(username)
if installed:
print '\n**Genome "{}" was reinstalled successfully!**\n'.format(genome)
else:
print '\n**Genome "{}" was not reinstalled!**\n'.format(genome)
def getTrackElement(self, id, label, history=False, ucsc=False, tracks=None):
datasets = []
if history:
try:
datasets = self.galaxy.getHistory(GalaxyInterface.getSupportedGalaxyFileFormats())
except Exception, e:
print e
def _assertExpandBedSegments(self, inContents, outContents, upFlank, downFlank,
treatTrackAs, removeChrBorderCrossing, suffix):
from tempfile import NamedTemporaryFile
with NamedTemporaryFile(suffix=suffix) as inFile:
inFile.write(inContents)
inFile.flush()
with NamedTemporaryFile(suffix=suffix) as outFile:
GalaxyInterface.expandBedSegments(inFile.name, outFile.name, 'TestGenome', upFlank, downFlank,
treatTrackAs, removeChrBorderCrossing, suffix)
expandedContents = outFile.read()
self.assertEquals(outContents, expandedContents)
def getInputValueForTrack(self, id, name):
try:
# assert False
cachedTracks = self.getCacheData(id)
track = self.getTrackElement(id, name, tracks=cachedTracks)
except:
print 'track cache is empty'
track = self.getTrackElement(id, name)
self.putCacheData(id, track.tracks)
self.trackElements[id] = track
tn = track.definition(False)
GalaxyInterface.cleanUpTrackName(tn)
val = ':'.join(tn)
# val = track.asString()
return val
def getTrackElement(self, id, label, history=False, ucsc=False):
datasets = []
if history:
try:
datasets = self.galaxy.getHistory(GalaxyInterface.getSupportedGalaxyFileFormats())
except Exception, e:
print e
def makeLowercaseName2NameShelfFromTnSubTypes(genome, trackName, shelfFn):
'genome trackName shelfFn'
trackName = re.split('/|:', trackName)
from gold.application.GalaxyInterface import GalaxyInterface
analysisDef = "-> ListOfPresentCategoriesStat"
results = GalaxyInterface.runManual([trackName, None],
analysisDef,
'*',
'*',
genome,
printResults=False,
printHtmlWarningMsgs=False)
categories = results.getGlobalResult()['Result']
shelf = safeshelve.open(shelfFn)
for cat in categories:
shelf[cat.lower()] = cat
##basePath = createDirPath(trackName, genome)
#basePath = gcf.createOrigPath(genome, trackName)
#shelf = safeshelve.open(shelfFn)
#
#for fn in os.listdir(basePath):
# if os.path.isdir(os.sep.join([basePath, fn])) and not any([fn.startswith(x) for x in ['_','.'] + GenomeInfo.getExtendedChrList(genome)]):
# shelf[fn.lower()] = fn
shelf.close()
def updateAllTrackInfoToVersion15():
from quick.application.GalaxyInterface import GalaxyInterface
from gold.origdata.PreProcessUtils import PreProcessUtils
for genomeTuple in GalaxyInterface.getAllGenomes():
genome = genomeTuple[1]
updateGenomeTrackInfoToVersion15(genome)
def _assertRunEqual(self, target, *args, **kwArgs):
if self.VERBOSE:
DebugConfig.PASS_ON_COMPUTE_EXCEPTIONS = True
print '\n***\n' + str(self.id()) + '\n***'
args = list(args)
analysisDef = [x.strip() for x in args[2].split('->')]
if len(analysisDef) == 1:
analysisDef.append(analysisDef[0])
analysisDef[0] += ' [randomSeed:=0]'
args[2] = analysisDef[0] + " -> " + analysisDef[1]
for diskMemo in [False, True]:
gold.statistic.ResultsMemoizer.LOAD_DISK_MEMOIZATION = diskMemo
if self._usesProfiling():
gold.application.StatRunner.USE_PROFILING = True
res = GalaxyInterface.run(*args, **{'genome':'TestGenome'})
self._assertEqualResults(target, res)
if kwArgs.get('globalTarget') != None:
self._assertEqualGlobalResults(kwArgs['globalTarget'], res)
if self._usesProfiling():
self._storeProfile(diskMemo)
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 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 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]
genes = choices[1]
genelist = []
for geneLine in genes.split('\n'):
for gene in geneLine.split(','):
gene = gene.strip()
if gene != '':
genelist.append(gene)
GalaxyInterface.getEnsemblGenes(genome, genelist, galaxyFn)
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 getValidAnalyses(cls, genome, trackName1, trackName2):
trackNames = [trackName1, trackName2]
allFeatures = cls.getAllFeatures()
validFeatures = {}
trackNames = GalaxyInterface._cleanUpTracks(trackNames, genome, realPreProc=False)
#trackName1 = trackName1[1:] #FixMe, temp, Boris..
#genome='hg19'
#print 'TEMP3: ', (genome, trackName1, trackName2)
if not GalaxyInterface.areTrackNamesValid(genome, trackNames):
return {}
#print 'TEMP2: ', allFeatures
for key in allFeatures:
analysisDef = allFeatures[key][0]
#print AnalysisManager._tryAnalysisDefForValidity(analysisDef, genome, trackName1, trackName2, tryReversed=False)
if AnalysisManager._tryAnalysisDefForValidity(analysisDef, genome, trackName1, trackName2, tryReversed=False)[0] is not None: #maybe also try reversed..
validFeatures[key] = allFeatures[key]
#print "Valid: %s (for trackNames: %s and %s)" % (validFeatures, trackName1, trackName2)
return validFeatures
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 testRunValid(self):
self.assertEqual(True, GalaxyInterface.runValid(["segsLen1"],["segs"],'RawOverlapStat','chr21:1-4001','2000','TestGenome'))
self.assertNotEqual(True, GalaxyInterface.runValid(["segsLen1"],["segs"],'','TestGenome:chr21:1-4001','2000','TestGenome'))
self.assertNotEqual(True, GalaxyInterface.runValid(["segsLen1"],["segs"],'RawOverlapStat','1-4001','2000','TestGenome'))
self.assertNotEqual(True, GalaxyInterface.runValid(["segsLen1"],["segs"],'RawOverlapStat','TestGenome:chr21:1-4001','default','TestGenome'))
self.assertNotEqual(True, GalaxyInterface.runValid(["segs"],["segs"],'','TestGenome:chr21:1-4001','default','TestGenome'))
self.assertNotEqual(True, GalaxyInterface.runValid(["segs"],["segs"],'','TestGenome:chr21:1-4001','default','hg18'))
def testRunValid(self):
self.assertEqual(True, GalaxyInterface.runValid(["segsLen1"],["segs"],'RawOverlapStat','chr21:1-4001','2000','TestGenome'))
self.assertNotEqual(True, GalaxyInterface.runValid(["segsLen1"],["segs"],'','TestGenome:chr21:1-4001','2000','TestGenome'))
self.assertNotEqual(True, GalaxyInterface.runValid(["segsLen1"],["segs"],'RawOverlapStat','1-4001','2000','TestGenome'))
self.assertNotEqual(True, GalaxyInterface.runValid(["segsLen1"],["segs"],'RawOverlapStat','TestGenome:chr21:1-4001','default','TestGenome'))
self.assertNotEqual(True, GalaxyInterface.runValid(["segs"],["segs"],'','TestGenome:chr21:1-4001','default','TestGenome'))
self.assertNotEqual(True, GalaxyInterface.runValid(["segs"],["segs"],'','TestGenome:chr21:1-4001','default','hg18'))
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 _assertRunEqual(self, target, *args, **kwArgs):
if DebugConfig.VERBOSE:
print '\n***\n' + str(self.id()) + '\n***'
args = list(args)
analysisDef = [x.strip() for x in args[2].split('->')]
if len(analysisDef) == 1:
analysisDef.append(analysisDef[0])
analysisDef[0] += ' [randomSeed:=0:]'
args[2] = analysisDef[0] + " -> " + analysisDef[1]
for runType in self._runTypeGenerator():
# if self._usesProfiling():
# DebugConfig.USE_PROFILING = True
res = GalaxyInterface.run(*args, **{'genome': 'TestGenome'})
self._assertEqualResults(target, res)
if kwArgs.get('globalTarget') is not None:
self._assertEqualGlobalResults(kwArgs['globalTarget'], res)
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 _assertBatchEqual(self, target, *args):
for diskMemo in [False, True]:
gold.statistic.ResultsMemoizer.LOAD_DISK_MEMOIZATION = diskMemo
batchRes = GalaxyInterface.runBatchLines(*args)
for i in range(len(batchRes)):
self._assertEqualResults(target[i], batchRes[i])
def testCountStat(self):
#self._assertRunEqual([[('Result', 119121)], [('Result', 0)]],\
GalaxyInterface.run(["segsMany"], ["segs"], 'CountStat',
'TestGenome:chr21:10000000-10004000', '2000')
def _assertBatchEqual(self, target, *args):
for runType in self._runTypeGenerator():
batchRes = GalaxyInterface.runBatchLines(*args)
for i in range(len(batchRes)):
self._assertEqualResults(target[i], batchRes[i])
# Copyright (C) 2009, Geir Kjetil Sandve, Sveinung Gundersen and Morten Johansen # This file is part of The Genomic HyperBrowser. # # The Genomic HyperBrowser is free software: you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by # the Free Software Foundation, either version 3 of the License, or # (at your option) any later version. # # The Genomic HyperBrowser is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with The Genomic HyperBrowser. If not, see <http://www.gnu.org/licenses/>. from gold.application.GalaxyInterface import GalaxyInterface #first you need to create a statistic class. For this you will use a StatisticTemplate, and just add a few custom lines of code.. #In our example we will make a simple statistic that computes the number of bps covered by all segments of a single track (in a bin). #1: open the file StatisticTemplate.py #2: save this file with your own name in the folder "quick/statistic". Lets call it "BpCoverageStat.py". (By putting your new class here, it will automatically be loaded into the Hyperbrowser system.) #3: rename the classes according to your name for the statistic - the same as used for the file. The file should then have a class "BpCoverageStat" and a class "BpCoverageStatUnsplittable". (The system will automatically use the unsplittable class, and would in certain cases also automatically have used a corresponding splittable class if it had been defined..) #4: define what input your statistic will need. In our case we will simply need the raw track data. Add the following line in the method "_createChildren": #self._addChild( RawDataStat(self._region, self._track, TrackFormatReq()) ) #5: define how to compute the result. Add the following line under "_compute": #return sum( el.end() - el.start() for el in self._children[0].getResult()) #6: Now you can make a simple call that computes full genome-wide results based on your statistics code: GalaxyInterface.run(['genes','refseq'], ['repeats','LINE'], 'My new statistic -> BpCoverageStat', '*', '*', genome='hg18') #7: You can also very simply make your new statistic available on the web if you have a web system running against the Hyperbrowser. Simply add the following line somewhere inside the string variable "QUESTION_SPEC_STR" in the file "gold/description/AnalysisList.py": #'My new statistic -> BpCoverageStat'
from gold.application.GalaxyInterface import GalaxyInterface
#GalaxyInterface.run(['HCNE','density_mm8_90pc_50col'], ['genes','refseq'], '[altHyp:=ha1:]a -> PointPositioningPValStat','chr1','10m')
print GalaxyInterface.getTrackInfoRecord('hg18', ['Regulation', 'CpG islands'])
GalaxyInterface.setTrackInfoRecord('hg18', ['Regulation', 'CpG islands'],
{'description': 'Test'}, False)
print GalaxyInterface.getTrackInfoRecord('hg18', ['Regulation', 'CpG islands'])
GalaxyInterface.setTrackInfoRecord('hg18', ['Regulation', 'CpG islands'],
{'private': True}, False)
print GalaxyInterface.getTrackInfoRecord('hg18', ['Regulation', 'CpG islands'])
GalaxyInterface.setTrackInfoRecord('hg18', ['Regulation', 'CpG islands'],
{'description': ''}, False)
GalaxyInterface.setTrackInfoRecord('hg18', ['Regulation', 'CpG islands'],
{'private': False}, False)
print GalaxyInterface.getTrackInfoRecord('hg18', ['Regulation', 'CpG islands'])
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 __init__(self, trans, job):
BaseToolController.__init__(self, trans, job)
self.genomes = GalaxyInterface.getAllGenomes(self.galaxy.getUserName() \
if hasattr(self, 'galaxy') else '')
self.genome = self.params.get('dbkey', self.genomes[0][1])
def testGetRunDescription(self):
prevVal = DebugConfig.PASS_ON_VALIDSTAT_EXCEPTIONS
DebugConfig.PASS_ON_VALIDSTAT_EXCEPTIONS = False
analysisDef = 'Different frequency inside segments?:Are track1-points occurring [tail:Alternative hypothesis=different:with different frequency/more:more frequently/less:less frequently] inside track2-segment than outside? [rawStatistic:=PointCountInsideSegsStat:] [assumptions:_Assumptions=poissonPoints:Poisson-distributed points/_PermutedSegsAndSampledIntersegsTrack:Permuted segments, sampled spaces (MC)/_PermutedSegsAndIntersegsTrack:Permuted segments, permuted spaces (MC)/_RandomGenomeLocationTrack:Segments fetched from random genome location (MC)] [numResamplings:_Resamplings=20/200/2000] -> PointCountInSegsPvalStat, RandomizationManagerStat'
GalaxyInterface.getRunDescription(['segsMany'], ['segs'], analysisDef, 'chr21:2-4001','2000', 'TestGenome')
DebugConfig.PASS_ON_VALIDSTAT_EXCEPTIONS = prevVal
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$cluster')
for index1 in range(extra_option) : #extra_option actually the number of clusters
#trackInCluster = [k for k,val in clusters.items() if val == index1]
trackInCluster = [k+1 for k,val in enumerate(clusters) if val == index1+1] #IS THIS CORRECT, I.E. SAME AS ABOVE??
print>>kmeans_output, 'Cluster %i(%s objects) : ' % (index1+1, str(clusterSizes[index1]))
for name in trackInCluster :
print>>kmeans_output, name, '(This result may be a bit shaky afters some changes in rpy access)'
print>>kmeans_output, 'Sum of square error for this cluster is : '+str(withinSS[index1])+'\n'
kmeans_output.close()
print>>jobFile, textFile.getLink('Detailed result of kmeans clustering <br>')
cls.print_data(f_matrix, jobFile)
'''
def executeReferenceTrack(cls, genome, tracks, track_names, clusterMethod, extra_option, distanceType, kmeans_alg, galaxyFn, regSpec, binSpec, numreferencetracks=None, refTracks=None, refFeatures=None, yesNo=None, howMany=None, upFlank=None, downFlank=None):
from gold.application.RSetup import r
jobFile = open(galaxyFn, 'w')
print>>jobFile, 'PARAMS: ', dict(zip('genome, tracks, track_names, clusterMethod, extra_option, distanceType, kmeans_alg, regSpec, binSpec'.split(','), [repr(v)+'<br>'for v in [genome, tracks, track_names, clusterMethod, extra_option, distanceType, kmeans_alg, regSpec, binSpec]]))
print>>jobFile, '<br><br>To run:<br>', '$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 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 _getAllGenomes(self):
return [('----- Select -----', '', False)] + GalaxyInterface.getAllGenomes(self.galaxy.getUserName())
def main():
filename = sys.argv[1]
tool = None
if len(sys.argv) > 2:
tool = sys.argv[2]
job_params, params = hg.load_input_parameters(filename)
# print job_params, params
file_path = None
trackName1 = ""
trackName2 = ""
intensityTrackName = None
subName1 = ""
subName2 = ""
intensityTrackFile = None
intensityTrackFileType = None
statClassName = ""
binSize = "*"
region = "*"
userBins = None
output = filename
extractFile = None
customFile = None
statsFile = None
method = None
segLength = 0
overlaps = None
genome = 'hg18'
username = None
for o, a in params.items():
if a == "":
continue
a = str(a)
if o == "dbkey":
genome = a
elif o == "tool":
tool = a
elif o == "track1":
trackName1 = a
elif o == "track2":
trackName2 = a
elif o == "trackIntensity":
intensityTrackName = a
elif o == "grptrack1":
grpName1 = a
elif o == "grptrack2":
grpName2 = a
elif o == "subtrack1":
subName1 = a
elif o == "subtrack2":
subName2 = a
elif o == "stats":
statClassName = a
elif o == "binsize":
binSize = a
elif o == "seglength":
segLength = int(a)
elif o == "region":
region = a
elif o == "method":
method = a
elif o == "output":
output = a
# sys.stdout = open(a, "w", 0)
elif o == "extract":
extractFile = a
elif o == "custom":
sys.stdout = open(a, "w", 0)
customFile = a
elif o == "binfile":
region = "bed"
userBins = a
elif o == "statsfile":
statsFile = a
elif o == "file_path":
file_path = a
elif o == "overlaps":
overlaps = unquote(a)
elif o == "userEmail":
username = a
if method in ['__chrs__', '__chrBands__', '__chrArms__', '__genes__']:
region = method
binSize = params[method]
elif method == '__brs__':
region = method
binSize = '*'
if userBins:
if userBins[0] == 'galaxy': # For backwards compatibility
binSize = userBins[1]
region = userBins[2]
elif userBins.startswith('galaxy'):
binSize, region = getSecureIdAndExtFromDatasetInfoAsStr(userBins)
tracks1 = trackName1.split(':')
tracks2 = trackName2.split(':')
if intensityTrackName != None:
intensityTracks = intensityTrackName.split(':')
else:
intensityTracks = []
# if statClassName.startswith('galaxy'):
# statsFileId = statClassName.split(',')[1]
# statsFile = getGalaxyFnFromDatasetId(statsFileId)
# statClassName = '[scriptFn:=' + statsFile.encode('hex_codec') + ':] -> CustomRStat'
if tool == 'extract':
#print 'GalaxyInterface.parseExtFormatAndExtractTrackManyBins*', (genome, tracks1, region, binSize, True, overlaps, output)
if output != None:
sys.stdout = open(output, "w", 0)
if params.has_key('sepFilePrRegion'):
GalaxyInterface.parseExtFormatAndExtractTrackManyBinsToRegionDirsInZipFile(
genome, tracks1, region, binSize, True, overlaps, output)
else:
GalaxyInterface.parseExtFormatAndExtractTrackManyBins(
genome, tracks1, region, binSize, True, overlaps, output)
else: #run analysis
if output != None:
sys.stdout = open(output, "w", 0)
demoID = params['demoID'] if params.has_key('demoID') else None
GalaxyInterface.run(tracks1, tracks2, statClassName, region, binSize,
genome, output, intensityTracks, username, demoID)
def userIsOneOfUs(self):
return GalaxyInterface._userHasFullAccess(self.galaxy.getUserName())
def _getAllGenomes(self):
return [("----- Select -----", "", False)] + GalaxyInterface.getAllGenomes(self.galaxy.getUserName())
def getDictOfAllGenomes(self):
return OrderedDict([(x[0], False) for x in GalaxyInterface.getAllGenomes(self.galaxy.getUserName())])
return 1
def meltSeg(val,diff):
if diff < -0.13:
return -2
elif diff > 0.13:
return 2
elif -0.01 <= diff <= 0.01:
return 0
else:
return None
meltSegLines = '''
if diff < -0.13:
return -2
elif diff > 0.13:
return 2
elif -0.01 <= diff <= 0.01:
return 0
else:
return None
'''.split(os.linesep)
#FunctionCategorizer(['melting'], meltSeg).createNewTrack(['melting','meltMapSeg'])
GalaxyInterface.createSegmentation('hg18',['melting'], ['melting','meltMapSeg2'], meltSegLines)
#exec( os.linesep.join( ['def categorizerMethod(val,diff):'] + meltSegLines) )
#a = categorizerMethod
#print a(3,-1)
def __init__(self, trans, job):
BaseToolController.__init__(self, trans, job)
self.genomes = GalaxyInterface.getAllGenomes(self.galaxy.getUserName() \
if hasattr(self, 'galaxy') else '')
self.genome = self.params.get('dbkey', '')
# Copyright (C) 2009, Geir Kjetil Sandve, Sveinung Gundersen and Morten Johansen
# This file is part of The Genomic HyperBrowser.
#
# The Genomic HyperBrowser is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# The Genomic HyperBrowser is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with The Genomic HyperBrowser. If not, see <http://www.gnu.org/licenses/>.
from gold.application.GalaxyInterface import GalaxyInterface
#GalaxyInterface.run(['HCNE','density_mm8_90pc_50col'], ['genes','refseq'], '[altHyp:=ha1:]a -> PointPositioningPValStat','chr1','10m')
print GalaxyInterface.getTrackInfoRecord('hg18',['Regulation','CpG islands'])
GalaxyInterface.setTrackInfoRecord('hg18',['Regulation','CpG islands'], {'description':'Test'}, False)
print GalaxyInterface.getTrackInfoRecord('hg18',['Regulation','CpG islands'])
GalaxyInterface.setTrackInfoRecord('hg18',['Regulation','CpG islands'], {'private':True}, False)
print GalaxyInterface.getTrackInfoRecord('hg18',['Regulation','CpG islands'])
GalaxyInterface.setTrackInfoRecord('hg18',['Regulation','CpG islands'], {'description':''}, False)
GalaxyInterface.setTrackInfoRecord('hg18',['Regulation','CpG islands'], {'private':False}, False)
print GalaxyInterface.getTrackInfoRecord('hg18',['Regulation','CpG islands'])
def test3():
GalaxyInterface.run(['repeats','SINE'],['repeats'],\
'[scriptFn:='+fn+':] -> CustomRStat',\
'chr1:1-100000000','10m')
def meltSeg(val, diff):
if diff < -0.13:
return -2
elif diff > 0.13:
return 2
elif -0.01 <= diff <= 0.01:
return 0
else:
return None
meltSegLines = '''
if diff < -0.13:
return -2
elif diff > 0.13:
return 2
elif -0.01 <= diff <= 0.01:
return 0
else:
return None
'''.split(os.linesep)
#FunctionCategorizer(['melting'], meltSeg).createNewTrack(['melting','meltMapSeg'])
GalaxyInterface.createSegmentation('hg18', ['melting'],
['melting', 'meltMapSeg2'], meltSegLines)
#exec( os.linesep.join( ['def categorizerMethod(val,diff):'] + meltSegLines) )
#a = categorizerMethod
#print a(3,-1)
# Copyright (C) 2009, Geir Kjetil Sandve, Sveinung Gundersen and Morten Johansen # This file is part of The Genomic HyperBrowser. # # The Genomic HyperBrowser is free software: you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by # the Free Software Foundation, either version 3 of the License, or # (at your option) any later version. # # The Genomic HyperBrowser is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with The Genomic HyperBrowser. If not, see <http://www.gnu.org/licenses/>. from gold.application.GalaxyInterface import GalaxyInterface trackName1 = ['Genes and Gene Prediction Tracks','Genes','Refseq'] #or any other track that are precomputed on the server trackName2 = ['Sequence','Repeating elements'] question = 'Are track1-points occurring [tail:=different:with different frequency] inside track2-segment than outside? -> PointCountInSegsPvalStat' #or any other statistic from the HB collection regSpec = 'chr1:1-10000000' #could also be e.g. 'chr1' for the whole chromosome or '*' for the whole genome binSpec = '1m' #could also be e.g.'100', '1k' or '*' for whole regions/chromosomes as bins GalaxyInterface.run(trackName1, trackName2, question, regSpec, binSpec, genome='hg18')
def testGetRunDescription(self):
prevVal = DebugConfig.PASS_ON_VALIDSTAT_EXCEPTIONS
DebugConfig.PASS_ON_VALIDSTAT_EXCEPTIONS = False
analysisDef = 'Different frequency inside segments?:Are track1-points occurring [tail:Alternative hypothesis=different:with different frequency/more:more frequently/less:less frequently] inside track2-segment than outside? [rawStatistic:=PointCountInsideSegsStat:] [assumptions:_Assumptions=poissonPoints:Poisson-distributed points/_PermutedSegsAndSampledIntersegsTrack:Permuted segments, sampled spaces (MC)/_PermutedSegsAndIntersegsTrack:Permuted segments, permuted spaces (MC)/_RandomGenomeLocationTrack:Segments fetched from random genome location (MC)] [numResamplings:_Resamplings=20/200/2000] -> PointCountInSegsPvalStat, RandomizationManagerStat'
GalaxyInterface.getRunDescription(['segsMany'], ['segs'], analysisDef, 'chr21:2-4001','2000', 'TestGenome')
DebugConfig.PASS_ON_VALIDSTAT_EXCEPTIONS = prevVal
def getExpandedTrackNameFromInTrackName(self, inTrackName, outTrackName,uniqueStaticId, genome, upFlank, downFlank):
GalaxyInterface.expandBedSegmentsFromTrackName(inTrackName, outTrackName, uniqueStaticId, genome, upFlank, downFlank)
return outTrackName
def userHasFullAccess(self):
return self.isPublic() or GalaxyInterface._userHasFullAccess(self.galaxy.getUserName())
from gold.application.GalaxyInterface import GalaxyInterface
#first you need to create a statistic class. For this you will use a StatisticTemplate, and just add a few custom lines of code..
#In our example we will make a simple statistic that computes the number of bps covered by all segments of a single track (in a bin).
#1: open the file StatisticTemplate.py
#2: save this file with your own name in the folder "quick/statistic". Lets call it "BpCoverageStat.py". (By putting your new class here, it will automatically be loaded into the Hyperbrowser system.)
#3: rename the classes according to your name for the statistic - the same as used for the file. The file should then have a class "BpCoverageStat" and a class "BpCoverageStatUnsplittable". (The system will automatically use the unsplittable class, and would in certain cases also automatically have used a corresponding splittable class if it had been defined..)
#4: define what input your statistic will need. In our case we will simply need the raw track data. Add the following line in the method "_createChildren":
#self._addChild( RawDataStat(self._region, self._track, TrackFormatReq()) )
#5: define how to compute the result. Add the following line under "_compute":
#return sum( el.end() - el.start() for el in self._children[0].getResult())
#6: Now you can make a simple call that computes full genome-wide results based on your statistics code:
GalaxyInterface.run(['genes', 'refseq'], ['repeats', 'LINE'],
'My new statistic -> BpCoverageStat',
'*',
'*',
genome='hg18')
#7: You can also very simply make your new statistic available on the web if you have a web system running against the Hyperbrowser. Simply add the following line somewhere inside the string variable "QUESTION_SPEC_STR" in the file "gold/description/AnalysisList.py":
#'My new statistic -> BpCoverageStat'
def testCountStat(self):
#self._assertRunEqual([[('Result', 119121)], [('Result', 0)]],\
GalaxyInterface.run(["segsMany"],["segs"],'CountStat','TestGenome:chr21:10000000-10004000','2000')
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()
