def extractTestGenomeAndPreProcess(galaxy_dir):
hbPath = os.path.join(galaxy_dir, 'lib', 'hb')
from config.Config import ORIG_DATA_PATH
from gold.origdata.PreProcessTracksJob import PreProcessAllTracksJob
from setup.InstallFunctions import executeShellCmd
from gold.util.CommonFunctions import createDirPath
from quick.util.GenomeInfo import GenomeInfo
from quick.application.ProcTrackOptions import ProcTrackOptions
from gold.description.TrackInfo import TrackInfo
import shutil
testGenomeFn = os.sep.join([hbPath, 'data', 'TestGenome.tar.gz'])
executeShellCmd('tar xfz %s --keep-newer-files -C %s' % (testGenomeFn, ORIG_DATA_PATH), \
pipe=False, printError=True, onError='exit')
print 'OK: Extracted TestGenome files.'
PreProcessAllTracksJob.PASS_ON_EXCEPTIONS = True
try:
PreProcessAllTracksJob('TestGenome').process()
PreProcessAllTracksJob(
'TestGenome', GenomeInfo.getChrTrackName('TestGenome')).process()
print 'OK: Finished preprocessing TestGenome.'
except Exception, e:
print 'FAILED: Error when preprocessing TestGenome. Error:'
print ' ' + str(e).strip()
sys.exit(1)
def createNewTrack(self, outTrackName, username=''):
print 'Creating segmentation...'
self.extractToFile(
createOrigPath(self._genome, outTrackName, 'generated'),
outTrackName)
print 'Preprocessing segmentation...'
PreProcessAllTracksJob(self._genome, outTrackName,
username=username).process()
def _preProcess(self, trackName):
self._removeDir(
createDirPath(trackName, self.GENOME, allowOverlaps=False),
trackName)
self._removeDir(
createDirPath(trackName, self.GENOME, allowOverlaps=True),
trackName)
PreProcessAllTracksJob(self.GENOME, trackName,
username="******").process()
def createGenome(cls, genome, fullName, chromNamesDict, standardChromosomes, username=''):
basePath = cls.getBasePathSequence(genome)
trackName=GenomeInfo.getSequenceTrackName(genome)
print "Splitting genome file into chromosomes."
SplitFasta.parseFiles(genome, trackName, chromNamesDict=chromNamesDict)
print "Processing genome"
PreProcessAllTracksJob(genome).process()
#print "Writing name file.:", fullName
#nameFn=createOrigPath(genome,[], "_name.txt" if experimental else "#name.txt")
#ensurePathExists(nameFn)
#f=open(nameFn, "w")
#f.write(fullName)
#f.close()
print "Creating chromosome file"
createChromosomeFile(genome, ",".join(standardChromosomes))
print "Creating assembly gaps file"
createAssemblyGapsFile(genome)
print "Generating genome annotations (if any)"
cls.generateGenomeAnnotations(genome)
print "Processing genome"
PreProcessAllTracksJob(genome).process()
print genome + " genome added"
def _preProcess(self,
subTrackName,
noOverlapsFileCount=None,
withOverlapsFileCount=None,
noOverlapsChrElCount=None,
withOverlapsChrElCount=None):
trackName = self.TRACK_NAME_PREFIX + subTrackName
self._removePreprocessedTrackData(trackName)
# aeval = Interpreter()
# aeval.symtable.update({'PreProcessAllTracksJob': PreProcessAllTracksJob})
# cmd = "PreProcessAllTracksJob(" + repr(self.GENOME) + "," + \
# repr(trackName) + ", username='******').process()"
# aeval(cmd)
PreProcessAllTracksJob(self.GENOME, trackName,
username='******').process()
self._assertCounts(trackName, noOverlapsFileCount,
withOverlapsFileCount, noOverlapsChrElCount,
withOverlapsChrElCount)
self._assertHasTrackFormatHash(trackName)
def preProcessTrackData(genome, tn, username):
from gold.origdata.PreProcessTracksJob import PreProcessAllTracksJob
PreProcessAllTracksJob(genome,
tn,
username=username,
mergeChrFolders=True).process()