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 _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 testCountStat(self):
#self._assertRunEqual([[('Result', 119121)], [('Result', 0)]],\
GalaxyInterface.run(["segsMany"],["segs"],'CountStat','TestGenome:chr21:10000000-10004000','2000')
# 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'
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 test3():
GalaxyInterface.run(['repeats','SINE'],['repeats'],\
'[scriptFn:='+fn+':] -> CustomRStat',\
'chr1:1-100000000','10m')
def testCountStat(self):
#self._assertRunEqual([[('Result', 119121)], [('Result', 0)]],\
GalaxyInterface.run(["segsMany"], ["segs"], 'CountStat',
'TestGenome:chr21:10000000-10004000', '2000')
# 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')
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'
