def findGeneTargets(genome, regionsTn, upFlankSize, downFlankSize, galaxyFn):
assert genome == 'hg18'
#tfTrackNameMappings = TfInfo.getTfTrackNameMappings(genome)
#tfTrackName = tfTrackNameMappings[tfSource] + [selectedTF]
geneIntersection = GeneIntersection(genome, 'Ensembl', regionsTn, galaxyFn)
geneIntersection.expandReferenceTrack(upFlankSize, downFlankSize)
expansionStr = ' flanked' if not (upFlankSize == downFlankSize == 0) else ''
#print '<p>There are %i Ensemble genes being targets of your selected TF (%s), based on intersecting TF target positions with%s %sgene regions.</p>' % (geneIntersection.getNumberOfIntersectedBins(), selectedTF, expansionStr, 'Ensembl')
print '<p>There are %i Ensemble genes being targets of your selected regions, based on intersecting your supplied regions with%s %sgene regions.</p>' % (geneIntersection.getNumberOfIntersectedBins(), expansionStr, 'Ensembl')
idFileNamer = geneIntersection.getGeneIdStaticFileWithContent()
print '<p>', idFileNamer.getLink('Download list'), ' of all Ensemble IDs with 1 or more hits.</p>'
regFileNamer = geneIntersection.getIntersectedRegionsStaticFileWithContent()
print '<p>', regFileNamer.getLink('Download bed-file'), ' of all Ensembl gene regions with 1 or more hits.</p>'
targetBins = geneIntersection.getIntersectedReferenceBins()
res = geneIntersection.getIntersectionResult()
resDictKey = geneIntersection.getUniqueResDictKey()
setOfNumOccurrences = set([res[bin][resDictKey] for bin in targetBins])
byNumOccurrencesStaticFile = GalaxyRunSpecificFile(['genes_by_num_occurrences.html'], galaxyFn)
f = byNumOccurrencesStaticFile.getFile()
for numOccurrences in reversed(sorted(setOfNumOccurrences)):
f.write('Gene regions having %i occurrences:<br>' % numOccurrences + '<br>' + os.linesep)
f.write(', '.join([ '<a href=http://www.ensembl.org/Homo_sapiens/Gene/Summary?g='+str(bin.val).split('|')[0]+'>'+str(bin.val).split('|')[0]+'</a>' for bin in targetBins if res[bin][resDictKey]==numOccurrences]) + '<br><br>' + os.linesep)
f.close()
print '</p>Inspect list of all intersected genes (by ID), ', byNumOccurrencesStaticFile.getLink('ordered by number of occurrences') + ' inside, and with links to gene descriptions.<br>'
def convertToGTrack(self, filePath, fileFormat, galaxyFn, fastaFilePath=None, normalizeValues=False):
predictionFile = open(filePath, 'r')
out = GalaxyRunSpecificFile(['%smodified.gtrack' % filePath.split('/')[-1]], galaxyFn)
gtrackFile = out.getFile('w')
if fileFormat == 'weeder':
self._convertFromWeederToGTrack(predictionFile, gtrackFile)
elif fileFormat == 'meme':
self._convertFromMemeToGTrack(predictionFile, gtrackFile)
elif fileFormat == 'glimmer':
self._convertFromGlimmerToGTrack(predictionFile, gtrackFile)
elif fileFormat == 'prodigal':
self._convertFromProdigalToGTrack(predictionFile, gtrackFile)
elif fileFormat == 'genemark':
self._convertFromGenemarkToGTrack(predictionFile, gtrackFile)
elif fileFormat == 'blasthit':
self._convertFromBlastToGTrack(predictionFile, gtrackFile)
elif fileFormat == 'ymf':
fastaFile = open(fastaFilePath, 'r')
self._convertFromYMFToGTrack(fastaFile, predictionFile, gtrackFile)
elif fileFormat == 'gtrack' and normalizeValues == True:
self._normalizeGTrackValues(filePath, gtrackFile)
return out.getDiskPath(True)
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.
'''
if choices[2]=='Transfac TF ids':
mappingFn = 'pwm2TFids.shelf'
mapping = safeshelve.open(Tool1.MAPPING_SHELVES_PATH + os.sep + mappingFn )
elif choices[2]== 'Transfac TF readable names':
mappingFn = 'pwm2TFnamesNew.shelf'
mapping = safeshelve.open(Tool1.MAPPING_SHELVES_PATH + os.sep + mappingFn )
elif choices[2]== 'HGNC gene symbols':
mappingFn = 'PWM_to_HGNC.txt'
mapping = dict([line.strip().split() for line in open(Tool1.MAPPING_SHELVES_PATH + os.sep + mappingFn).readlines()])
else:
raise Exception(choices[2])
if galaxyFn==None:
for key in sorted(mapping.keys()):
print key + ':' + ','.join(mapping[key]) + os.linesep,
else:
mappingStaticFile = GalaxyRunSpecificFile(['mapping.txt'], galaxyFn)
f = mappingStaticFile.getFile()
for key in sorted(mapping.keys()):
if type(mapping[key]) in (list,tuple):
mapping[key] = ','.join(mapping[key])
f.write( key + ':' + mapping[key] + os.linesep )
f.close()
print mappingStaticFile.getLink('View/download mapping')
def storePickledResults(self):
try:
from cPickle import dump
pickleStaticFile = GalaxyRunSpecificFile(['results.pickle'],self._galaxyFn)
#print 'TEMP1: PATH: ',pickleStaticFile.getDiskPath(True)
from copy import copy
pickleList = [copy(res) for res in self._resultsList]
for res in pickleList:
res._analysis=None
dump(pickleList, pickleStaticFile.getFile())
#dump(self._resultsList, pickleStaticFile.getFile())
except Exception, e:
logException(e, message='Not able to pickle results object')
def singleSimulation(self, numH0, numH1, replicateIndex, verbose=False):
tests = MultipleTestCollection(numH0, numH1, self._maxNumSamples, self._h, self._fdrThreshold,self._a,self._b)
tests.addSamples(self.NUM_SAMPLES_INITIALLY)
while not tests.allTestsAreDetermined():
tests.addSamples(self.NUM_SAMPLES_PER_CHUNK)
#if verbose:
#print tests.getTotalNumSamples()
#As sampling is now anyway over, we set fdrThreshold to a threshold used after computations are finished (i.e. affects final rejection/acception, but not stopping of samples)
tests.setFdrThresholdAtAllCounters(self._postFdrThreshold)
#print 'FINALLY, #samples: ',
if self._galaxyFn is not None:
if self._h is None:
scheme = 'Basic'
elif self._fdrThreshold is None:
scheme = 'Sequential'
else:
scheme = 'McFdr'
staticFile = GalaxyRunSpecificFile([scheme,str(numH1),str(replicateIndex),'PandQvals.txt'], self._galaxyFn)
tests.writeAllPandQVals(staticFile.getFile() )
linkToRaw = staticFile.getLink('Raw p and q-vals') + ' under %s scheme with %i true H1, (replication %i)' % (scheme, numH1, replicateIndex)
figStaticFile = GalaxyRunSpecificFile([scheme,str(numH1),str(replicateIndex),'PandQvals.png'], self._galaxyFn)
figStaticFile.openRFigure()
tests.makeAllPandQValsFigure()
figStaticFile.closeRFigure()
linkToFig = figStaticFile.getLink(' (p/q-figure) ') + '<br>'
figNumSamplesStaticFile = GalaxyRunSpecificFile([scheme,str(numH1),str(replicateIndex),'NumSamples.png'], self._galaxyFn)
figNumSamplesStaticFile.openRFigure()
tests.makeNumSamplesFigure()
figNumSamplesStaticFile.closeRFigure()
linkToNumSamplesFig = figNumSamplesStaticFile.getLink(' (numSamples-figure) ') + '<br>'
catalogStaticFile = GalaxyRunSpecificFile([str(numH1),'cat.html'], self._galaxyFn)
catalogStaticFile.writeTextToFile(linkToRaw + linkToFig + linkToNumSamplesFig, mode='a')
#if verbose:
#print sorted(tests.getFdrVals())
#print 'NumS ign Below 0.2: ', sum([1 if t<0.2 else 0 for t in tests.getFdrVals()])
#return tests.getTotalNumSamples(), tests.getTotalNumRejected()
return tests.getTotalNumSamples(), tests.getTotalNumRejected(), tests.getClassificationSummaries()