def createRSquareGraph(cls, ldGraphTrackName, r2_threshold):
"""
Creates a dictionary of all pairs in a linked point track.
Variants in LD must have rsquare >= the rsquare threshold passed to the function.
:param ldGraphTrackName: linked point track, as chosen in tool (choices.ldtrack)
:param r2_threshold: Lower limit of square value
:return: Dictionary of all ld-pairs with sorted key = (rsid1, rsid2), value = rSquare
"""
from quick.application.ExternalTrackManager import ExternalTrackManager
from gold.origdata.GtrackGenomeElementSource import GtrackGenomeElementSource
fileName = ExternalTrackManager.extractFnFromGalaxyTN(ldGraphTrackName)
suffix = ExternalTrackManager.extractFileSuffixFromGalaxyTN(ldGraphTrackName)
gtSource = GtrackGenomeElementSource(fileName, suffix=suffix)
r2graph = {}
for ge in gtSource:
rsid = ge.id
edges = ge.edges
weights = ge.weights
for i in range(0, len(edges)):
ldRsid = edges[i]
r2 = weights[i]
if r2 >= float(r2_threshold):
cls.addEdge(r2graph, rsid, ldRsid, r2)
return r2graph
def _collectTracks(self):
tracks = [self._track, self._track2]
if 'trackNameIntensity' in self._kwArgs:
assert not 'extraTracks' in self._kwArgs
self._kwArgs['extraTracks'] = self._kwArgs['trackNameIntensity']
if 'extraTracks' in self._kwArgs:
from gold.track.Track import PlainTrack
import re
from config.Config import MULTIPLE_EXTRA_TRACKS_SEPARATOR
extraTracks = self._kwArgs['extraTracks']
if type(extraTracks) == str:
extraTracks = extraTracks.split(MULTIPLE_EXTRA_TRACKS_SEPARATOR)
for extraT in extraTracks:
if type(extraT) == str:
#extraT = extraT.split('|')
#extraT = re.split('\^|\|',extraT)
extraT = convertTNstrToTNListFormat(extraT)
if type(extraT) == list:
#print 'TEMP1: ', extraT
from urllib import unquote
extraT = [unquote(part) for part in extraT]
from quick.application.ExternalTrackManager import ExternalTrackManager
if ExternalTrackManager.isGalaxyTrack(extraT):
extraT = ExternalTrackManager.getPreProcessedTrackFromGalaxyTN(self.getGenome(), extraT)
extraT = PlainTrack(extraT)
tracks.append(extraT)
return tracks
def execute(choices, galaxyFn=None, username=''):
'''Is called when execute-button is pushed by web-user.
Should print output as HTML to standard out, which will be directed to a results page in Galaxy history. If getOutputFormat is anything else than HTML, the output should be written to the file with path galaxyFn.gtr
If needed, StaticFile can be used to get a path where additional files can be put (e.g. generated image files).
choices is a list of selections made by web-user in each options box.
'''
resultLines = []
outputFile=open(galaxyFn,"w")
fnSource = ExternalTrackManager.extractFnFromGalaxyTN(choices[2].split(':'))
fnDB = ExternalTrackManager.extractFnFromGalaxyTN(choices[3].split(':'))
intersectingFactor = 'id' if choices[4] == 'Element id' else 'position'
colsToAdd = []
colsToAddDict = choices[5]
for key in colsToAddDict:
if colsToAddDict[key]:
colsToAdd.append(key)
genome = choices[1] if choices[0] == 'Yes' else None
try:
complementGtrackFileAndWriteToFile(fnSource, fnDB, galaxyFn, intersectingFactor, colsToAdd, genome)
except Exception, e:
import sys
print >> sys.stderr, e
def execute(choices, galaxyFn=None, username=''):
'''Is called when execute-button is pushed by web-user.
Should print output as HTML to standard out, which will be directed to a results page in Galaxy history. If getOutputFormat is anything else than HTML, the output should be written to the file with path galaxyFn.gtr
If needed, StaticFile can be used to get a path where additional files can be put (e.g. generated image files).
choices is a list of selections made by web-user in each options box.
'''
outputFile=open(galaxyFn,"w")
fnSource = ExternalTrackManager.extractFnFromGalaxyTN(choices[0].split(':'))
inputFile = open(ExternalTrackManager.extractFnFromGalaxyTN(choices[0].split(':')), 'r')
if choices[2] == 'Filter on exact values':
if choices[3]!='Select column..':
column = int(choices[3][7:])
filterSet = set([key for key,val in choices[4].items() if val])
for i in inputFile:
if i.split('\t')[column] in filterSet:
print>>outputFile, i
else:
for i in inputFile:
temptab = i.split('\t')
for index in range(len(temptab)):
locals()['c'+str(index)] = temptab[index]
if eval(choices[5]):
print>>outputFile, i
inputFile.close()
outputFile.close()
def execute(choices, galaxyFn=None, username=''):
'''
Is called when execute-button is pushed by web-user. Should print
output as HTML to standard out, which will be directed to a results page
in Galaxy history. If getOutputFormat is anything else than HTML, the
output should be written to the file with path galaxyFn. If needed,
StaticFile can be used to get a path where additional files can be put
(e.g. generated image files). choices is a list of selections made by
web-user in each options box.
'''
# get population format
if choices.format == 'File':
pop = [];
popfile = choices.population;
inFn = ExternalTrackManager.extractFnFromGalaxyTN(popfile.split(":"));
infile = open(inFn);
for line in infile:
pop.append(line.rstrip('\n'));
else:
pop = map(str.strip,choices.population.split(","));
# read in file
inFn = ExternalTrackManager.extractFnFromGalaxyTN(choices.vcf.split(":"));
data = open(inFn).read();
# convert and write to GTrack file
outfile = open(galaxyFn, 'w');
outfile.write(addHeader(choices.genome));
outfile.write(convertToGtrackFile(data, pop, choices.genome));
outfile.close();
def execute(cls, choices, galaxyFn=None, username=''):
'''
Is called when execute-button is pushed by web-user. Should print
output as HTML to standard out, which will be directed to a results page
in Galaxy history. If getOutputFormat is anything else than HTML, the
output should be written to the file with path galaxyFn. If needed,
StaticFile can be used to get a path where additional files can be put
(e.g. generated image files). choices is a list of selections made by
web-user in each options box.
'''
try:
historyInputTN = choices[0].split(':') #from history
historyGalaxyFn = ExternalTrackManager.extractFnFromGalaxyTN( historyInputTN) #same as galaxyFn in execute of create benchmark..
randomStatic = RunSpecificPickleFile(historyGalaxyFn) #finds path to static file created for a previous history element, and directs to a pickle file
myInfo = randomStatic.loadPickledObject()
except:
return None
galaxyTN = myInfo[3].split(':')
myFileName = ExternalTrackManager.extractFnFromGalaxyTN(galaxyTN)
genome = myInfo[0]
gtrackSource = GtrackGenomeElementSource(myFileName, genome)
regionList = []
for obj in gtrackSource:
regionList.append(GenomeRegion(obj.genome, obj.chr, obj.start, obj.end))
extractor = TrackExtractor()
fn = extractor.extract(GenomeInfo.getSequenceTrackName(genome), regionList, galaxyFn, 'fasta')
def findOverrepresentedTFsFromGeneSet(genome, tfSource, ensembleGeneIdList,upFlankSize, downFlankSize, geneSource, galaxyFn):
#galaxyFn = '/usit/insilico/web/lookalike/galaxy_dist-20090924-dev/database/files/003/dataset_3347.dat'
#print 'overriding galaxyFN!: ', galaxyFn
galaxyId = extractIdFromGalaxyFn(galaxyFn)
uniqueWebPath = getUniqueWebPath(extractIdFromGalaxyFn(galaxyFn))
assert genome == 'hg18'
tfTrackNameMappings = TfInfo.getTfTrackNameMappings(genome)
tfTrackName = tfTrackNameMappings[tfSource]
#Get gene track
assert geneSource == 'Ensembl'
targetGeneRegsTempFn = uniqueWebPath + os.sep + 'geneRegs.bed'
geneRegsTrackName = GenomeInfo.getStdGeneRegsTn(genome)
geneRegsFn = getOrigFn(genome, geneRegsTrackName, '.category.bed')
GalaxyInterface.getGeneTrackFromGeneList(genome, geneRegsTrackName, ensembleGeneIdList, targetGeneRegsTempFn )
assert upFlankSize == downFlankSize == 0 #Should instead extend regions to include flanks
tcGeneRegsTempFn = uniqueWebPath + os.sep + 'tcGeneRegs.targetcontrol.bedgraph'
#Think this will be okay, subtraction not necessary as targets are put first:
controlGeneRegsTempFn = geneRegsFn
#print targetGeneRegsTempFn, controlGeneRegsTempFn, tcGeneRegsTempFn
GalaxyInterface.combineToTargetControl(targetGeneRegsTempFn, controlGeneRegsTempFn, tcGeneRegsTempFn)
#tcGeneRegsExternalTN = ['external'] +galaxyId + [tcGeneRegsTempFn]
tcGeneRegsExternalTN = ExternalTrackManager.createStdTrackName(galaxyId, 'tempTc')
#tcGeneRegsExternalTN = ['external'] +targetGalaxyId + [tcGeneRegsTempFn]
#tcGeneRegsExternalTN = ['galaxy', externalId, tcGeneRegsTempFn]
targetGeneRegsExternalTN = ExternalTrackManager.createStdTrackName(galaxyId, 'tempTc', '1')
controlGeneRegsExternalTN = ExternalTrackManager.createStdTrackName(galaxyId, 'tempTc', '0')
#pre-process
print 'Pre-processing file: %s, with trackname: %s ' % (tcGeneRegsTempFn, tcGeneRegsExternalTN)
ExternalTrackManager.preProcess(tcGeneRegsTempFn, tcGeneRegsExternalTN, 'targetcontrol.bedgraph',genome)
print 'Pre-processing TN: ', targetGeneRegsExternalTN
ExternalTrackManager.preProcess(targetGeneRegsTempFn, targetGeneRegsExternalTN, 'bed',genome)
print 'Pre-processing TN: ', controlGeneRegsExternalTN
ExternalTrackManager.preProcess(controlGeneRegsTempFn, controlGeneRegsExternalTN, 'bed',genome)
#print tcGeneRegsExternalTN
trackName1, trackName2 = tfTrackName, tcGeneRegsExternalTN
analysisDef = 'Categories differentially located in targets?: Which categories of track1-points fall more inside case than control track2-segments? [rawStatistic:=PointCountInsideSegsStat:]' +\
'[tf1:=SegmentToStartPointFormatConverter:] [tf2:=TrivialFormatConverter:]' +\
'-> DivergentRowsInCategoryMatrixStat'
regSpec, binSpec = '*','*'
#print 'skipping preproc!!'
#ExternalTrackManager.preProcess(tcGeneRegsExternalTN[-1], tcGeneRegsExternalTN, 'targetcontrol.bedgraph', genome)
#ExternalTrackManager.preProcess(targetGeneRegsTempFn, targetGeneRegsExternalTN, 'bed', genome)
GalaxyInterface.runManual([trackName1, trackName2], analysisDef, regSpec, binSpec, genome, printResults=True, printHtmlWarningMsgs=False)
def getOptionsBox6(prevChoices):
if prevChoices[3]:
extraDbColumnsDict = OrderedDict()
fnSource = ExternalTrackManager.extractFnFromGalaxyTN(prevChoices[2].split(':'))
fnDB = ExternalTrackManager.extractFnFromGalaxyTN(prevChoices[3].split(':'))
gtrackDB = GtrackGenomeElementSource(fnDB)
gtrackSource = GtrackGenomeElementSource(fnSource)
extraDbColumns = [v for v in gtrackDB.getColumns() if not v in gtrackSource.getColumns()] #list(set(gtrackDBColumnSpec) - set(gtrackSourceColumnSpec))
for column in extraDbColumns:
extraDbColumnsDict[column] = False
return extraDbColumnsDict
def createLinkedPointTrack(cls, rsids, isUndirected, trackFn, r2):
from quick.webtools.clustering.CreateLDTrack import CreateLDTrack
from quick.application.ExternalTrackManager import ExternalTrackManager
# Create file for GTrack
galaxyTN = ExternalTrackManager.constructGalaxyTnFromSuitedFn(trackFn, fileEnding='gtrack', name='ld_graph')
fn = ExternalTrackManager.extractFnFromGalaxyTN(galaxyTN)
f = open(fn, 'w')
# Get LD information and create linked point track
ldDict = CreateLDTrack.getLDDict(r2)
expansionDict = CreateLDTrack.getExpansionDict(rsids, ldDict)
f.write(CreateLDTrack.formatLinkedPointTrack(expansionDict, isUndirected))
def execute(choices, galaxyFn=None, username=''):
'''Is called when execute-button is pushed by web-user.
Should print output as HTML to standard out, which will be directed to a results page in Galaxy history.
If getOutputFormat is anything else than HTML, the output should be written to the file with path galaxyFn.
If needed, StaticFile can be used to get a path where additional files can be put (e.g. generated image files).
choices is a list of selections made by web-user in each options box.
'''
from time import time
startTime = time()
from quick.application.ExternalTrackManager import ExternalTrackManager
from quick.util.StaticFile import GalaxyRunSpecificFile
import os
motifFn = ExternalTrackManager.extractFnFromGalaxyTN( choices[0].split(':'))
observedFasta = ExternalTrackManager.extractFnFromGalaxyTN( choices[1].split(':'))
randomGalaxyTN = choices[2].split(':')
randomName = ExternalTrackManager.extractNameFromHistoryTN(randomGalaxyTN)
randomGalaxyFn = ExternalTrackManager.extractFnFromGalaxyTN( randomGalaxyTN)
randomStatic = GalaxyRunSpecificFile(['random'],randomGalaxyFn) #finds path to static file created for a previous history element (randomFn), and directs to a folder containing several files..
#print os.listdir(randomStatic.getDiskPath())
randomFastaPath = randomStatic.getDiskPath()
#motifFn, observedFasta, randomFastaPath = '/Users/sandve/egne_dokumenter/_faglig/NullModels/DnaSeqExample/liver.pwm', 'liver.fa', 'randomFastas'
testStatistic = choices[3]
if testStatistic == 'Average of max score per sequence':
scoreFunc = scoreMotifOnFastaAsAvgOfBestScores
elif testStatistic == 'Sum of scores across all positions of all sequences':
scoreFunc = scoreMotifOnFastaAsSumOfAllScores
elif testStatistic == 'Score of Frith et al. (2004)':
scoreFunc = lr4
elif testStatistic == 'Product of max per sequence':
scoreFunc = scoreMotifOnFastaAsProductOfBestScores
else:
raise
pvals = mcPvalFromMotifAndFastas(motifFn, observedFasta, randomFastaPath, scoreFunc)
print 'Pvals for motifs (%s) against observed (%s) vs random (%s - %s) sequences.' % (motifFn, observedFasta, randomName, randomFastaPath)
for motif,pval in sorted(pvals.items()):
print motif+'\t'+('%.4f'%pval)
from quick.util.StaticFile import GalaxyRunSpecificFile
from gold.application.RSetup import r, robjects
histStaticFile = GalaxyRunSpecificFile(['pvalHist.png'],galaxyFn)
#histStaticFile.openRFigure()
histStaticFile.plotRHist(pvals.values(), [x/40.0 for x in range(41)], 'Histogram of p-values', xlim=robjects.FloatVector([0.0, 1.0]))
#r.hist(robjects.FloatVector(pvals.values()), breaks=robjects.FloatVector([x/40.0 for x in range(41)]), xlim=robjects.FloatVector([0.0, 1.0]), main='Histogram of p-values' )
#histStaticFile.closeRFigure()
print histStaticFile.getLink('Histogram')
print 'Time (s):', time()-startTime
def getRedirectURL(choices):
genome = choices[0]
track1file = ExternalTrackManager.createSelectValueFromGalaxyTN(choices[1].split(':'))
track2file = ExternalTrackManager.createSelectValueFromGalaxyTN(choices[2].split(':'))
return createHyperBrowserURL(genome, trackName1=['galaxy'], trackName2=['galaxy'], \
track1file=track1file, track2file=track2file, \
analysis='Category pairs differentially co-located?', \
configDict={'Method of counting points': 'Only 1 count per bin (binary)',\
'Normalize counts': 'Differentially in both directions' if \
choices[3] == 'Both rows and columns (focusing on column differences)'\
else 'Differentially for points only',\
'P-value threshold for significance': '0.01'},\
method='__chrs__')
def execute(choices, galaxyFn=None, username=''):
'''Is called when execute-button is pushed by web-user.
Should print output as HTML to standard out, which will be directed to a results page in Galaxy history. If getOutputFormat is anything else than HTML, the output should be written to the file with path galaxyFn.gtr
If needed, StaticFile can be used to get a path where additional files can be put (e.g. generated image files).
choices is a list of selections made by web-user in each options box.
'''
genome = choices[1] if choices[0] == 'Yes' else None
suffix = ExternalTrackManager.extractFileSuffixFromGalaxyTN(choices[2].split(':'))
inFn = ExternalTrackManager.extractFnFromGalaxyTN(choices[2].split(':'))
try:
standardizeGtrackFileAndWriteToFile(inFn, galaxyFn, genome, suffix=suffix)
except Exception, e:
import sys
print >> sys.stderr, e
def execute(choices, galaxyFn=None, username=''):
'''Is called when execute-button is pushed by web-user.
Should print output as HTML to standard out, which will be directed to a results page in Galaxy history. If getOutputFormat is anything else than HTML, the output should be written to the file with path galaxyFn.gtr
If needed, StaticFile can be used to get a path where additional files can be put (e.g. generated image files).
choices is a list of selections made by web-user in each options box.
'''
fnSource = ExternalTrackManager.extractFnFromGalaxyTN(choices[2].split(':'))
core = HtmlCore()
core.begin()
valid = False
try:
core.header('Validating GTrack headers')
core.styleInfoBegin(styleClass='debug')
print str(core)
core = HtmlCore()
gtrackSource = GtrackGenomeElementSource(fnSource, choices[1] if choices[0]=='Yes' else None, printWarnings=True)
core.append('Done')
core.styleInfoEnd()
core.header('Validating complete GTrack file')
core.styleInfoBegin(styleClass='debug')
print str(core)
core = HtmlCore()
try:
for ge in gtrackSource:
pass
except Exception, e:
pass
else:
def execute(choices, galaxyFn=None, username=''):
#'Genome:','Source of seed TF:','Seed TF: ','Flank size: ', 'Source of potentially cooperative TFs:'
#genome
genome = choices[0]
seedSource = choices[1]
seedTfTnInput = choices[2]
if seedSource == 'TFBS from history':
seedFn = ExternalTrackManager.extractFnFromGalaxyTN(seedTfTnInput.split(':'))
else:
tfTrackNameMappings = TfInfo.getTfTrackNameMappings(genome)
seedTfTn = tfTrackNameMappings[seedSource] + [seedTfTnInput]
#tfTrackName = tfTrackNameMappings[tfSource] + [selectedTF]
seedFns = getOrigFns(genome, seedTfTn, '')
assert len(seedFns) == 1
seedFn = seedFns[0]
flankSize = choices[3]
flankSize = int(flankSize) if flankSize != '' else 0
cooperativeTfSource = choices[4]
#flankSize = int(choices[4])
#TFsFromGenes.findOverrepresentedTFsFromGeneSet('hg18', 'UCSC tfbs conserved', ['ENSGflankSizeflankSizeflankSizeflankSizeflankSize2flankSize8234','ENSGflankSizeflankSizeflankSizeflankSizeflankSize199674'],flankSize, flankSize, galaxyFn)
#TFsFromGenes.findOverrepresentedTFsFromGeneSet('hg18', tfSource, choices[5].split(','),flankSize, flankSize, 'Ensembl', galaxyFn)
#TFsFromRegions.findOverrepresentedTFsFromGeneSet(genome, tfSource, ensembleGeneIdList,upFlankSize, downFlankSize, geneSource, galaxyFn)
#TFsFromGenes.findTFsTargetingGenes('hg18', tfSource, choices[5].split(','),flankSize, flankSize, 'Ensembl', galaxyFn)
TFsFromRegions.findTFsOccurringInRegions(genome, cooperativeTfSource, seedFn, flankSize, flankSize, galaxyFn)
def _getHeaders(prevChoices):
numCols = TabularToGtrackTool._getFileContentsInfo(prevChoices).numCols
if prevChoices.columnSelection == 'Select individual columns':
header = []
for i in xrange(numCols):
if hasattr(prevChoices, 'column%s' % i):
colHeader = getattr(prevChoices, 'column%s' % i)
if colHeader is None or colHeader == '-- ignore --':
header.append('')
elif colHeader == '-- custom --':
header.append(getattr(prevChoices, 'customColumn%s' % i).strip())
else:
header.append(colHeader)
else:
header.append('')
return header
else:
genome = prevChoices.genome if prevChoices.selectGenome == 'Yes' else None
inFn = ExternalTrackManager.extractFnFromGalaxyTN(prevChoices.colSpecFile.split(':'))
try:
geSource = GtrackGenomeElementSource(inFn, genome=genome)
geSource.parseFirstDataLine()
return geSource.getColumns()[:numCols]
except Exception, e:
return []
def getOptionsBoxFileContentsInfo(prevChoices):
if prevChoices.history or prevChoices.input:
if prevChoices.history:
inputFile = open(ExternalTrackManager.extractFnFromGalaxyTN(prevChoices.history.split(':')), 'r')
else:
inputFile = StringIO(prevChoices.input)
for i in xrange(TabularToGtrackTool._getNumSkipLines(prevChoices)):
inputFile.readline()
table = []
splitChar = TabularToGtrackTool._getSplitChar(prevChoices)
numCols = None
error = None
for i,line in enumerate(inputFile):
row = [x.strip() for x in line.strip().split(splitChar)]
if numCols == None:
numCols = len(row)
elif numCols != len(row):
numCols = max(numCols, len(row))
# error = 'Error: the number of columns varies over the rows of the tabular file.'
table.append(row)
if i == TabularToGtrackTool.NUM_ROWS_IN_TABLE:
break
numCols = max(len(row) for row in table) if len(table) > 0 else 0
if error is None:
if numCols > TabularToGtrackTool.NUM_COLUMN_FUNCTIONS:
error = 'Error: the tabular file has more columns than is allowed by the tool (%s > %s).' % (numCols, TabularToGtrackTool.NUM_COLUMN_FUNCTIONS)
return ('__hidden__', FileContentsInfo(table=table, numCols=numCols, error=error))
def execute(choices, galaxyFn=None, username=''):
'''
Is called when execute-button is pushed by web-user. Should print
output as HTML to standard out, which will be directed to a results page
in Galaxy history. If getOutputFormat is anything else than HTML, the
output should be written to the file with path galaxyFn. 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.
'''
# Retrieve the pickled benchmark object from history
try:
historyInputTN = choices[0].split(':')
#same as galaxyFn in execute of create benchmark..
historyGalaxyFn = ExternalTrackManager.extractFnFromGalaxyTN(historyInputTN)
#finds path to static file created for a previous history element, and directs to a pickle file
randomStatic = RunSpecificPickleFile(historyGalaxyFn)
benchmarkSpecification = randomStatic.loadPickledObject()
except:
return None
genome = benchmarkSpecification[0]
benchmarkLevel = benchmarkSpecification[2]
regionTrackName = benchmarkSpecification[3]
benchmarkUtil = BenchmarkUtil(galaxyFn, genome)
if benchmarkLevel == 'Base pair probability level':
return benchmarkUtil.retrieveFeatureTrack(genome, galaxyFn, regionTrackName, benchmarkSpecification[5])
elif type(regionTrackName) is str: # If string, we're dealing with a single track so just retrieve it
return benchmarkUtil.retrieveTrack(regionTrackName, galaxyFn)
elif type(regionTrackName) is list: # If list, we're dealing with a benchmark suite which will have to be zipped
print benchmarkUtil.retrieveBenchmarkSuiteAsZipFile(regionTrackName)
else:
raise Exception('Invalid benchmark')
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...'
tempinfofile=ExternalTrackManager.extractFnFromGalaxyTN(choices[0].split(":"))
abbrv=GenomeImporter.getGenomeAbbrv(tempinfofile)
gi = GenomeInfo(abbrv)
chrNamesInFasta=gi.sourceChrNames
chromNamesDict={}
chrDict = InstallGenomeTool._getRenamedChrDictWithSelection(choices)
for i, key in enumerate(chrDict.keys()):
if chrDict[key]:
chromNamesDict[chrNamesInFasta[i]]=key
print 'All chromosomes chosen: ' + str(chromNamesDict)
stdChrDict = InstallGenomeTool._getRenamedChrDictWithSelection(choices, stdChrs=True)
stdChrs = [x for x in stdChrDict if stdChrDict[x]]
print 'Standard chromosomes chosen: ' + ", ".join(stdChrs)
GenomeImporter.createGenome(abbrv, gi.fullName, chromNamesDict, stdChrs, username=username)
gi.installedBy = username
gi.timeOfInstallation = datetime.now()
gi.store()
def _getTempChromosomeNames(galaxyTn):
if isinstance(galaxyTn, str):
galaxyTn = galaxyTn.split(":")
tempinfofile=ExternalTrackManager.extractFnFromGalaxyTN(galaxyTn)
abbrv=GenomeImporter.getGenomeAbbrv(tempinfofile)
return os.linesep.join(GenomeInfo(abbrv).sourceChrNames)
def execute(choices, galaxyFn=None, username=''):
'''Is called when execute-button is pushed by web-user.
Should print output as HTML to standard out, which will be directed to a results page in Galaxy history. If getOutputFormat is anything else than HTML, the output should be written to the file with path galaxyFn.gtr
If needed, StaticFile can be used to get a path where additional files can be put (e.g. generated image files).
choices is a list of selections made by web-user in each options box.
'''
genome = choices.genome if choices.selectGenome == 'Yes' else None
onlyNonDefault = choices.allHeaders == 'Only non-default headers'
try:
if choices.history:
inFn = ExternalTrackManager.extractFnFromGalaxyTN(choices.history.split(':'))
expandHeadersOfGtrackFileAndWriteToFile(inFn, galaxyFn, genome, onlyNonDefault)
else:
if choices.whitespace == 'Keep whitespace exact':
input = choices.input
else:
input = ''
for line in choices.input.split(os.linesep):
line = line.strip()
if (line.startswith('###') and len(line) > 3 and line[3] != '#') \
or not line.startswith('#'):
line = line.replace(' ', '\t')
else:
line = line.replace('\t', ' ')
input += line + os.linesep
composer = expandHeadersOfGtrackFileAndReturnComposer('', genome, strToUseInsteadOfFn=input)
composer.composeToFile(galaxyFn, onlyNonDefault=onlyNonDefault)
except Exception, e:
import sys
print >> sys.stderr, e
def execute(choices, galaxyFn=None, username=''):
'''Is called when execute-button is pushed by web-user.
Should print output as HTML to standard out, which will be directed to a results page in Galaxy history.
If getOutputFormat is anything else than HTML, the output should be written to the file with path galaxyFn.
If needed, StaticFile can be used to get a path where additional files can be put (e.g. generated image files).
choices is a list of selections made by web-user in each options box.
'''
genome = choices[0]
trackName = choices[1].split(':')
galaxyOutTrackName = 'galaxy:hbfunction:%s:Create function track of distance to nearest segment' % galaxyFn
outTrackName = ExternalTrackManager.getStdTrackNameFromGalaxyTN(galaxyOutTrackName.split(':'))
if choices[2] == 'No transformation':
valTransformation = 'None'
elif choices[2] =='Logarithmic (log10(x))':
valTransformation = 'log10'
elif choices[2] == 'Fifth square root (x**0.2)':
valTransformation = 'power0.2'
analysisDef ='[dataStat=MakeDistanceToNearestSegmentStat] [valTransformation=%s][outTrackName=' % valTransformation \
+ '^'.join(outTrackName) + '] -> CreateFunctionTrackStat'
#userBinSource, fullRunArgs = GalaxyInterface._prepareRun(trackName, None, analysisDef, '*', '*', genome)
#
#for el in userBinSource:
# print el.chr, el.start, el.end
from quick.application.GalaxyInterface import GalaxyInterface
print GalaxyInterface.getHbFunctionOutputBegin(galaxyFn, withDebug=False)
GalaxyInterface.runManual([trackName], analysisDef, '*', '*', genome, username=username, printResults=False, printHtmlWarningMsgs=False)
#job = AnalysisDefJob(analysisDef, trackName, None, userBinSource).run()
print GalaxyInterface.getHbFunctionOutputEnd('A custom track has been created by finding the bp-distance to the nearest segment', withDebug=False)
def getRegsAndBinsSpec(choices):
'''
Returns teh regSpec and binSpec for the choices made on the gui.
'''
regsMapper = {'Chromosome arms':'__chrArms__','Chromosomes':'__chrs__','Cytobands':'__chrBands__','Genes(Ensembl)':'__genes__','ENCODE Pilot regions':'__encode__'}
if choices.CompareIn == 'Custom specification':
regSpec = choices.CustomRegion
binSpec = choices.BinSize
elif regsMapper.get(choices.CompareIn):
regSpec = regsMapper[choices.CompareIn]
binSpec = choices.Bins
else:
histItem = choices.HistoryBins.split(':')
binSpec = ExternalTrackManager.extractFnFromGalaxyTN(histItem)
regSpec = ExternalTrackManager.extractFileSuffixFromGalaxyTN(histItem)
return regSpec, binSpec
def __new__(cls, trackName):
if len(trackName) == 0 or trackName is None:
return None
else:
if ExternalTrackManager.isVirtualTrack(trackName):
return VirtualMinimalPlainTrack.__new__(VirtualMinimalPlainTrack)
else:
return object.__new__(cls)
def retrieveFeatureTrack(self, genome, galaxyFn, regionTrackName, featureTrack):
regionTrackName = regionTrackName.split(':')
regionFileName = ExternalTrackManager.extractFnFromGalaxyTN(regionTrackName)
bins = GalaxyInterface._getUserBinSource('gtrack', regionFileName, genome, featureTrack.split(':'))
return self._extractor.extract(featureTrack.split(':'), bins, galaxyFn, 'gtrack')
def _getRawTrackView(self, region, borderHandling, allowOverlaps):
assert region.start == 0 and region.end == 1
from collections import OrderedDict
from gold.track.CommonMemmapFunctions import findEmptyVal
from gold.track.TrackView import TrackView
import numpy as np
geSource = ExternalTrackManager.getGESourceFromGalaxyOrVirtualTN(self.trackName, region.genome)
prefixList = geSource.getPrefixList()
valDataType = geSource.getValDataType()
valDim = geSource.getValDim()
weightDataType = geSource.getEdgeWeightDataType()
weightDim = geSource.getEdgeWeightDim()
startList, endList, valList, strandList, idList, edgesList, weightsList = [None]*7
extraLists=OrderedDict()
tf = TrackFormat.createInstanceFromPrefixList(prefixList, valDataType, valDim, \
weightDataType, weightDim)
if allowOverlaps and (tf.isDense() or geSource.hasNoOverlappingElements()):
raise IncompatibleTracksError(prettyPrintTrackName(self.trackName) + ' with format: '\
+ str(tf) + ' does not satisfy ' + str(self._trackFormatReq))
denseAndInterval = tf.isDense() and tf.isInterval()
numEls = 2 if denseAndInterval else 1
if valDataType == 'S':
valDataType = 'S2'
if weightDataType == 'S':
weightDataType = 'S2'
for prefix in prefixList:
if prefix == 'start':
startList = np.array([-1], dtype='int32')
elif prefix == 'end':
if denseAndInterval:
endList = np.array([0, 1], dtype='int32')
else:
endList = np.array([0], dtype='int32')
elif prefix == 'val':
valList = np.array([findEmptyVal(valDataType)] * valDim * numEls, \
dtype=valDataType).reshape((numEls, valDim) if valDim > 1 else numEls)
elif prefix == 'strand':
strandList = np.array([1] * numEls, dtype='int8')
elif prefix == 'id':
idList = np.array([''] * numEls, dtype='S1')
elif prefix == 'edges':
edgesList = np.array([['']] * numEls, dtype='S1')
elif prefix == 'weights':
weightsList = np.array([[[findEmptyVal(weightDataType)]]] * weightDim * numEls, \
dtype=weightDataType).reshape((numEls, 1, weightDim) if weightDim > 1 else (numEls, 1))
else:
extraLists[prefix] = np.array([''] * numEls, dtype='S1')
return TrackView(region, startList, endList, valList, strandList, idList, edgesList, weightsList, borderHandling, allowOverlaps, extraLists)
def getOptionsBox2(prevChoices):
try:
historyInputTN = prevChoices[0].split(':') #from history
historyGalaxyFn = ExternalTrackManager.extractFnFromGalaxyTN( historyInputTN) #same as galaxyFn in execute of create benchmark..
randomStatic = RunSpecificPickleFile(historyGalaxyFn) #finds path to static file created for a previous history element, and directs to a pickle file
myInfo = randomStatic.loadPickledObject()
return [myInfo[0]]
except:
return None
def getOptionsBox3(prevChoices):
'''Returns a list of options to be displayed in the second options box, which will be displayed after a selection is made in the first box.
prevChoices is a list of selections made by the web-user in the previous input boxes (that is, list containing only one element for this case)
'''
if prevChoices[-2]!=None and prevChoices[0]:
try:
fnSource = ExternalTrackManager.extractFnFromGalaxyTN(prevChoices[0].split(':'))
return (open(fnSource,'r').readlines()[int(prevChoices[-2])], 2, True)
except:
pass
def _getResultsLists(histChoices):
if len([x for x in histChoices.values() if x!=None])==0:
return [],[]
#print 'histChoices',histChoices
#return []
galaxyTNs = [x.split(':') for x in histChoices.values() if x!=None]
galaxyFns = [ExternalTrackManager.extractFnFromGalaxyTN(tn) for tn in galaxyTNs]
historyNames= [ExternalTrackManager.extractNameFromHistoryTN(tn) for tn in galaxyTNs]
staticFiles = [GalaxyRunSpecificFile(['results.pickle'], gfn) for gfn in galaxyFns]
fileSpecificFile = [GalaxyRunSpecificFile([], gfn) for gfn in galaxyFns]
print 'Using pickles: ', [x.getDiskPath() for x in staticFiles]
paths = [x.getDiskPath()+'/0' for x in fileSpecificFile]
pngList = [[v for v in x[2] if v.find('.png')>0] for x in os.walk(paths[0])]
resultsLists = [load(sf.getFile('r')) for sf in staticFiles]
return resultsLists, historyNames
def execute(choices, galaxyFn=None, username=''):
historyInputTN = choices[0].split(':') #from history
historyGalaxyFn = ExternalTrackManager.extractFnFromGalaxyTN( historyInputTN) #same as galaxyFn in execute of create benchmark..
randomStatic = RunSpecificPickleFile(historyGalaxyFn) #finds path to static file created for a previous history element, and directs to a pickle file
myInfo = randomStatic.loadPickledObject()
if myInfo[1] == choices[2]:
print "Your answer was correct!"
else:
print "You answered %s but the right answer was %s" % (myInfo[1], choices[2])
def _getBoundingRegionShelve(self, trackName):
if trackName in [None, []] or ExternalTrackManager.isVirtualTrack(trackName):
brShelve = None
else:
brShelve = BoundingRegionShelve(self.genome, trackName, allowOverlaps=False)
if not brShelve.fileExists():
raise BoundingRegionsNotAvailableError('Bounding regions not available for track: ' + \
prettyPrintTrackName(trackName))
return brShelve
def execute(cls, choices, galaxyFn=None, username=''):
'''
Is called when execute-button is pushed by web-user. Should print
output as HTML to standard out, which will be directed to a results page
in Galaxy history. If getOutputFormat is anything else than HTML, the
output should be written to the file with path galaxyFn. If needed,
StaticFile can be used to get a path where additional files can be put
(e.g. generated image files). choices is a list of selections made by
web-user in each options box.
'''
genome = choices[0]
trackList = choices[2].values()
print trackList
from quick.application.ExternalTrackManager import ExternalTrackManager
for track in trackList:
ExternalTrackManager.getPreProcessedTrackFromGalaxyTN(genome, track.split(':'))
print 'Executing...'
def execute(cls, choices, galaxyFn=None, username=''):
from gold.util.RandomUtil import random
outputFile = open(galaxyFn, 'w')
genome = choices[0]
histItem = choices[2]
trackItem = choices[3]
chromRegsPath = GenomeInfo.getChrRegsFn(genome)
chrSizeDict = dict([(chrom, GenomeInfo.getChrLen(genome, chrom))
for chrom in GenomeInfo.getChrList(genome)])
geSource = headLinesStr = None
if choices[1] == 'history':
trackType = choices[2].split(':')[1]
username = ''.join(
[chr(random.randint(97, 122)) for i in range(6)])
tempFn = createCollectedPath(
genome, [],
username + '_'.join([str(v) for v in time.localtime()[:6]]) +
'.' + trackType)
fnSource = ExternalTrackManager.extractFnFromGalaxyTN(
choices[2].split(':'))
open(tempFn, 'w').write(open(fnSource, 'r').read())
if trackType in ['valued.bed', 'category.bed', 'bed']:
geSource = GenomeElementSorter(
BedGenomeElementSource(tempFn, genome=genome)).__iter__()
#elif trackType == 'gtrack':
# geSource = GenomeElementSorter(GtrackGenomeElementSource(tempFn, genome=genome)).__iter__()
# headLinesStr = geSource.getHeaderLines().replace('##','\n##')
cls.WriteExpandedElementsToFile(geSource,
chrSizeDict,
outputFile,
headLinesStr,
writeHeaderFlag=True)
os.remove(tempFn)
else:
writeHeaderFlag = True
for chrom in GenomeInfo.getChrList(genome):
gRegion = GenomeRegion(genome, chrom, 0, chrSizeDict[chrom])
plTrack = PlainTrack(trackItem.split(':'))
geSource = GenomeElementTvWrapper(
plTrack.getTrackView(gRegion)).__iter__()
cls.WriteExpandedElementsToFile(geSource, chrSizeDict,
outputFile, headLinesStr,
writeHeaderFlag)
writeHeaderFlag = False
outputFile.close()
def validateAndReturnErrors(choices):
'''
Should validate the selected input parameters. If the parameters are not
valid, an error text explaining the problem should be returned. The GUI
then shows this text to the user (if not empty) and greys out the
execute button (even if the text is empty). If all parameters are valid,
the method should return None, which enables the execute button.
'''
if not choices.resultsFile:
return 'Please select a results file from history'
resultsFN = ExternalTrackManager.extractFnFromGalaxyTN(
choices.resultsFile)
errors = ExamResultsValidator.validateExamResultsDataFile(
resultsFN, IndividualTaskAnalysis.REQUIRED_COLUMNS,
IndividualTaskAnalysis.OPTIONAL_COLUMNS)
if errors:
if len(errors) > 5:
errors = errors[0:5]
return 'First 5 errors reported:<br><br>' + '<br>'.join(
[str(x) for x in errors]).replace('\n', '<br>')
selectedTasks = [key for key, val in choices.tasks.iteritems() if val]
if not selectedTasks:
return 'Please select at least one task'
if choices.analysis == IndividualTaskAnalysis.ANALYSIS_BIN_AVG_SMOOTHED_PLOT:
if not choices.bins:
return 'Please specify number of bins'
try:
bins = int(choices.bins)
if bins < 1:
return "Number of bins must be 1 or more"
except:
return "Bins must be an integer number"
if choices.analysis in [
IndividualTaskAnalysis.ANALYSIS_BIN_AVG_SMOOTHED_PLOT,
IndividualTaskAnalysis.ANALYSIS_MOVING_AVG_SMOOTHED_PLOT
]:
if not choices.spar:
return 'Please specify the smoothing parameter'
else:
try:
spar = float(choices.spar)
if spar < 0 or spar > 1:
return 'The smoothing parameter must be between 0.0 and 1.0'
except:
return 'The smoothing parameter must be a floating point number between 0.0 and 1.0'
return None
def visitGalaxyGSuiteTrack(self, gSuiteTrack):
self.genericVisit(gSuiteTrack)
from quick.application.ExternalTrackManager import ExternalTrackManager
from gold.description.TrackInfo import TrackInfo
if gSuiteTrack.hasExtraFileName():
baseFileName = os.path.basename(gSuiteTrack.uriWithoutSuffix)
else:
baseFileName = gSuiteTrack.title
galaxyTN = ExternalTrackManager.constructGalaxyTnFromSuitedFn(
gSuiteTrack.path, fileEnding=gSuiteTrack.suffix, name=baseFileName)
trackName = ExternalTrackManager.getPreProcessedTrackFromGalaxyTN(
gSuiteTrack.genome, galaxyTN, printErrors=False, printProgress=False,
renameExistingTracksIfNeeded=False)
trackType = TrackInfo(gSuiteTrack.genome, trackName).trackFormatName.lower()
hbUri = HbGSuiteTrack.generateURI(trackName=trackName)
return GSuiteTrack(hbUri, title=gSuiteTrack.title, trackType=trackType,
genome=gSuiteTrack.genome, attributes=gSuiteTrack.attributes,
comment=gSuiteTrack.comment)