def execute(cls, choices, galaxyFn=None, username=''):
from quick.webtools.clustering.GSuitePrimaryTrackModifier import GSuitePrimaryTrackModifier
# Set analysis environment
gSuite = getGSuiteFromGalaxyTN(choices.gSuite)
outGSuite = GSuite()
errorGSuite = GSuite()
progressViewer = ProgressViewer([('Manipulate tracks', gSuite.numTracks() + 24)],
cls.extraGalaxyFn[cls.HISTORY_PROGRESS_TITLE])
hiddenStorageFn = cls.extraGalaxyFn[cls.HISTORY_HIDDEN_TRACK_STORAGE]
# Get rsID map for the chosen reference genome
rsidMap = RsidMapper.createRsidMappingFromStaticFiles(progressViewer, choices.refGenome)
# Lift over all tracks
for track in gSuite.allTracks():
fileName = cls.getFilenameWithGTrackSuffix(track.path)
title = getTitleWithSuffixReplaced(track.title, 'gtrack')
try:
uri = GalaxyGSuiteTrack.generateURI(
galaxyFn=hiddenStorageFn,
extraFileName=fileName,
suffix='gtrack'
)
gSuiteTrack = GSuiteTrack(
uri,
title=title,
genome=track.genome,
trackType=track.trackType,
attributes=track.attributes
)
trackFn = gSuiteTrack.path
GSuitePrimaryTrackModifier.liftOverGTrack(track.path, trackFn, rsidMap)
outGSuite.addTrack(gSuiteTrack)
except Exception as e:
track.comment = 'An error occurred for the following track: ' + str(e)
errorGSuite.addTrack(track)
progressViewer.update()
# Update reference genome of all tracks and write to file
outGSuite.setGenomeOfAllTracks(choices.refGenome)
composeToFile(outGSuite, galaxyFn)
composeToFile(errorGSuite, cls.extraGalaxyFn[cls.HISTORY_ERROR_TITLE])
writeGSuiteHiddenTrackStorageHtml(hiddenStorageFn)
def execute(cls, choices, galaxyFn=None, username=''):
from quick.webtools.clustering.CreateLDTrack import CreateLDTrack
from quick.webtools.clustering.RsidMapper import RsidMapper
gSuite = getGSuiteFromGalaxyTN(choices.gSuite)
outGSuite = GSuite()
errorGSuite = GSuite()
progressViewer = ProgressViewer([('Manipulate tracks', gSuite.numTracks() + 24)],
cls.extraGalaxyFn[cls.HISTORY_PROGRESS_TITLE])
ldDict = CreateLDTrack.getLDDict(float(choices.rsquare))
rsidDict = RsidMapper.createRsidMappingFromStaticFiles(progressViewer, choices.refGenome)
hiddenStorageFn = cls.extraGalaxyFn[cls.HISTORY_HIDDEN_TRACK_STORAGE]
for track in gSuite.allTracks():
fileName = cls.getFilenameWithGTrackSuffix(track.path)
title = getTitleWithSuffixReplaced(track.title, 'gtrack')
try:
uri = GalaxyGSuiteTrack.generateURI(
galaxyFn=hiddenStorageFn,
extraFileName=fileName,
suffix='gtrack'
)
gSuiteTrack = GSuiteTrack(
uri,
title=title,
genome=track.genome,
trackType='points',
attributes=track.attributes
)
trackFn = gSuiteTrack.path
CreateLDTrack.parseFileIntoPointTrack(track.path, trackFn, ldDict, rsidDict)
outGSuite.addTrack(gSuiteTrack)
except Exception as e:
track.comment = 'An error occurred for the following track: ' + str(e)
errorGSuite.addTrack(track)
progressViewer.update()
outGSuite.setGenomeOfAllTracks(choices.refGenome)
composeToFile(outGSuite, galaxyFn)
composeToFile(errorGSuite, cls.extraGalaxyFn[cls.HISTORY_ERROR_TITLE])
writeGSuiteHiddenTrackStorageHtml(hiddenStorageFn)
def testFullCompose(self):
gSuite = GSuite()
gSuite.addTrack(GSuiteTrack('ftp://server.somewhere.com/path/to/file1.bed',
title='Track', \
attributes=OrderedDict([('cell', 'k562'),
('antibody', 'cMyb')])))
gSuite.addTrack(GSuiteTrack('http://server.other.com/path/to/file2.bed',
title='Track2', \
attributes=OrderedDict([('cell', 'GM12878'),
('antibody', 'cMyc')])))
gSuite.addTrack(
GSuiteTrack('https://server.other.com/path/to/file3.bed',
attributes=OrderedDict([('cell', 'GM12878'),
('antibody', 'cMyb')])))
gSuite.addTrack(GSuiteTrack('rsync://server.other.com/path/to/file4;wig',
title='Track4', \
attributes=OrderedDict([('cell', 'NHFL')])))
gSuite.addTrack(GSuiteTrack('hb:/track/name/hierarchy', title='Track'))
gSuite.addTrack(GSuiteTrack('galaxy:/ad123dd12fg;btrack?track=track:name',
title='Track', \
attributes=OrderedDict([('cell', 'k562'),
('antibody', 'cMyb')])))
gSuite.addTrack(GSuiteTrack('file:/path/to/file.btrack?track=track:name',
title='Track name7', \
attributes=OrderedDict([('antibody', 'cMyb'),
('extra', 'yes')])))
gSuite.setGenomeOfAllTracks('hg18')
output = GSuiteComposer.composeToString(gSuite)
targetOutput = \
'##location: multiple\n' \
'##file format: multiple\n' \
'##track type: unknown\n' \
'##genome: hg18\n' \
'###uri\ttitle\tfile_format\tcell\tantibody\textra\n' \
'ftp://server.somewhere.com/path/to/file1.bed\tTrack\tprimary\tk562\tcMyb\t.\n' \
'http://server.other.com/path/to/file2.bed\tTrack2\tprimary\tGM12878\tcMyc\t.\n' \
'https://server.other.com/path/to/file3.bed\tfile3.bed\tprimary\tGM12878\tcMyb\t.\n' \
'rsync://server.other.com/path/to/file4;wig\tTrack4\tprimary\tNHFL\t.\t.\n' \
'hb:/track/name/hierarchy\tTrack (2)\tpreprocessed\t.\t.\t.\n' \
'galaxy:/ad123dd12fg;btrack?track=track%3Aname\tTrack (3)\tpreprocessed\tk562\tcMyb\t.\n' \
'file:/path/to/file.btrack?track=track%3Aname\tTrack name7\tpreprocessed\t.\tcMyb\tyes\n'
self.assertEquals(targetOutput, output)
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.
'''
from gold.gsuite.GSuite import GSuite
from gold.gsuite.GSuiteTrack import GalaxyGSuiteTrack, GSuiteTrack
from gold.gsuite.GSuiteComposer import composeToFile
from gold.gsuite.GSuiteFunctions import getTitleWithSuffixReplaced
from quick.gsuite.GSuiteHbIntegration import \
writeGSuiteHiddenTrackStorageHtml
from quick.extra.ProgressViewer import ProgressViewer
from quick.util.CommonFunctions import ensurePathExists
gSuite = getGSuiteFromGalaxyTN(choices.history)
outGSuite = GSuite()
errorGSuite = GSuite()
progressViewer = ProgressViewer(
[('Manipulate tracks', gSuite.numTracks())], galaxyFn)
hiddenStorageFn = cls.extraGalaxyFn[getGSuiteHistoryOutputName(
'storage', cls.OUTPUT_DESCRIPTION, choices.history)]
for track in gSuite.allTracks():
newSuffix = cls._getSuffix(choices, track)
fileName = os.path.basename(track.path)
fileName = changeSuffixIfPresent(fileName,
oldSuffix=track.suffix,
newSuffix=newSuffix)
title = getTitleWithSuffixReplaced(track.title, newSuffix)
try:
if fileName.endswith('.' + newSuffix):
uri = GalaxyGSuiteTrack.generateURI(
galaxyFn=hiddenStorageFn, extraFileName=fileName)
else:
uri = GalaxyGSuiteTrack.generateURI(
galaxyFn=hiddenStorageFn,
extraFileName=fileName,
suffix=newSuffix)
gSuiteTrack = GSuiteTrack(uri,
title=title,
genome=track.genome,
attributes=track.attributes)
trackFn = gSuiteTrack.path
ensurePathExists(trackFn)
cls._runOperation(choices, track.path, trackFn)
outGSuite.addTrack(gSuiteTrack)
except Exception as e:
track.comment = 'An error occurred for the following track: ' + str(
e).partition('\n')[0]
errorGSuite.addTrack(track)
progressViewer.update()
primaryFn = cls.extraGalaxyFn[getGSuiteHistoryOutputName(
'primary', cls.OUTPUT_DESCRIPTION, choices.history)]
composeToFile(outGSuite, primaryFn)
errorFn = cls.extraGalaxyFn[getGSuiteHistoryOutputName(
'nomanipulate', datasetInfo=choices.history)]
composeToFile(errorGSuite, errorFn)
writeGSuiteHiddenTrackStorageHtml(hiddenStorageFn)
def printGSuite(cls, choices, cols, rows, colListString, outFile):
#print cols
from quick.extra.ProgressViewer import ProgressViewer
from gold.gsuite.GSuite import GSuite
from gold.gsuite.GSuiteTrack import GSuiteTrack, GalaxyGSuiteTrack
import gold.gsuite.GSuiteComposer as GSuiteComposer
from gold.origdata.GtrackGenomeElementSource import GtrackGenomeElementSource
from gold.origdata.GtrackComposer import ExtendedGtrackComposer
from gold.origdata.GESourceWrapper import ListGESourceWrapper
from gold.origdata.GenomeElement import GenomeElement
from collections import defaultdict
from copy import copy
from urllib import quote
from unidecode import unidecode
from pyliftover import LiftOver
gSuite = GSuite()
diseaseColIndex = cols.index(cls.DISEASE_COLUMN_NAME)
chrColIndex = cols.index(cls.CHR_COLUMN_NAME)
startColIndex = cols.index(cls.START_COLUMN_NAME)
valColIndex = cols.index(cls.VAL_COLUMN_NAME)
orderedExtraKeys = copy(cols)
extraIndexes = range(len(cols))
for colName in [cls.DISEASE_COLUMN_NAME, cls.CHR_COLUMN_NAME,
cls.START_COLUMN_NAME, cls.VAL_COLUMN_NAME]:
extraIndexes.remove(cols.index(colName))
orderedExtraKeys.remove(colName)
orderedExtraKeys = [cls._fixColNameForGTrack(key) for key in orderedExtraKeys]
diseaseToRowsDict = defaultdict(list)
for row in rows:
disease = row[diseaseColIndex]
if isinstance(disease, unicode):
disease = unidecode(disease).replace('\x00', '')
diseaseToRowsDict[disease].append(row)
progressViewer = ProgressViewer([('Create GWAS tracks for diseases/traits', len(diseaseToRowsDict))],
cls.extraGalaxyFn[cls.HISTORY_PROGRESS_TITLE] )
for disease in sorted(diseaseToRowsDict.keys()):
uri = GalaxyGSuiteTrack.generateURI(galaxyFn=cls.extraGalaxyFn[cls.HISTORY_HIDDEN_TRACK_STORAGE],
extraFileName=disease.replace('/', '_') + '.gtrack')
gSuiteTrack = GSuiteTrack(uri, title=disease, genome=cls.OUTPUT_GENOME)
gSuite.addTrack(gSuiteTrack)
shouldLiftOver = cls.DATABASE_GENOME != cls.OUTPUT_GENOME
if shouldLiftOver:
liftOver = LiftOver(cls.DATABASE_GENOME, cls.OUTPUT_GENOME)
geList = []
for row in diseaseToRowsDict[disease]:
extra = {}
for col, index in zip(orderedExtraKeys, extraIndexes):
cell = row[index].strip()
if isinstance(cell, unicode):
cell = unidecode(cell)
extra[col] = cell if cell != '' else '.'
chrom = 'chr' + row[chrColIndex]
if chrom == 'chr23':
chrom = 'chrX'
if chrom == 'chr24':
chrom = 'chrY'
if chrom == 'chrMT':
chrom = 'chrM'
start = int(row[startColIndex])
if shouldLiftOver:
newPosList = liftOver.convert_coordinate(chrom, start)
if newPosList is None or len(newPosList) != 1:
print 'SNP with position %s on chromosome %s ' % (chrom, start) +\
'could not be lifted over from reference genome ' +\
'%s to %s (for disease/trait "%s")' % \
(cls.DATABASE_GENOME, cls.OUTPUT_GENOME, disease)
else:
chrom, start = newPosList[0][0:2]
#print extra
geList.append(GenomeElement(chr=chrom, start=start,
val=row[valColIndex], orderedExtraKeys=orderedExtraKeys,
extra=extra))
geSource = GtrackGenomeElementSource(cls.GTRACK_BLUEPRINT_PATH)
wrappedGeSource = ListGESourceWrapper(geSource, geList)
composer = ExtendedGtrackComposer(wrappedGeSource)
composer.composeToFile(gSuiteTrack.path)
progressViewer.update()
GSuiteComposer.composeToFile(gSuite, outFile)
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.
'''
import gold.gsuite.GSuiteComposer as GSuiteComposer
from gold.gsuite.GSuite import GSuite
from gold.gsuite.GSuiteTrack import GSuiteTrack, HbGSuiteTrack
from gold.origdata.TrackGenomeElementSource import TrackViewListGenomeElementSource
from gold.origdata.FileFormatComposer import getComposerClsFromFileSuffix
from quick.multitrack.MultiTrackCommon import getGSuiteFromGalaxyTN
from quick.application.ExternalTrackManager import ExternalTrackManager
from quick.application.GalaxyInterface import GalaxyInterface
from quick.application.UserBinSource import UserBinSource
from quick.extra.TrackExtractor import TrackExtractor
genome = choices.genome
gSuite = getGSuiteFromGalaxyTN(choices.gSuite)
if choices.withOverlaps == cls.NO_OVERLAPS:
if choices.trackSource == cls.FROM_HISTORY_TEXT:
filterTrackName = ExternalTrackManager.getPreProcessedTrackFromGalaxyTN(genome, choices.trackHistory)
else:
filterTrackName = choices.track.split(':')
else:
if choices.trackSource == cls.FROM_HISTORY_TEXT:
regSpec = ExternalTrackManager.extractFileSuffixFromGalaxyTN(choices.trackHistory)
binSpec = ExternalTrackManager.extractFnFromGalaxyTN(choices.trackHistory)
else:
regSpec = 'track'
binSpec = choices.track
userBinSource = UserBinSource(regSpec, binSpec, genome)
desc = cls.OUTPUT_GSUITE_DESCRIPTION
emptyFn = cls.extraGalaxyFn \
[getGSuiteHistoryOutputName('nointersect', description=desc, datasetInfo=choices.gSuite)]
primaryFn = cls.extraGalaxyFn \
[getGSuiteHistoryOutputName('primary', description=desc, datasetInfo=choices.gSuite)]
errorFn = cls.extraGalaxyFn \
[getGSuiteHistoryOutputName('nopreprocessed', description=desc, datasetInfo=choices.gSuite)]
preprocessedFn = cls.extraGalaxyFn \
[getGSuiteHistoryOutputName('preprocessed', description=desc, datasetInfo=choices.gSuite)]
hiddenStorageFn = cls.extraGalaxyFn \
[getGSuiteHistoryOutputName('storage', description=desc, datasetInfo=choices.gSuite)]
analysisDef = '-> TrackIntersectionStat'
# analysisDef = '-> TrackIntersectionWithValStat'
numTracks = gSuite.numTracks()
progressViewer = ProgressViewer([(cls.PROGRESS_INTERSECT_MSG, numTracks),
(cls.PROGRESS_PREPROCESS_MSG, numTracks)], galaxyFn)
emptyGSuite = GSuite()
primaryGSuite = GSuite()
for track in gSuite.allTracks():
newSuffix = cls.OUTPUT_TRACKS_SUFFIX
extraFileName = os.path.sep.join(track.trackName)
extraFileName = changeSuffixIfPresent(extraFileName, newSuffix=newSuffix)
title = getTitleWithSuffixReplaced(track.title, newSuffix)
primaryTrackUri = GalaxyGSuiteTrack.generateURI(
galaxyFn=hiddenStorageFn, extraFileName=extraFileName,
suffix=newSuffix if not extraFileName.endswith(newSuffix) else '')
primaryTrack = GSuiteTrack(primaryTrackUri, title=title,
genome=track.genome, attributes=track.attributes)
if choices.withOverlaps == cls.NO_OVERLAPS:
res = GalaxyInterface.runManual([track.trackName, filterTrackName], analysisDef, '*', '*',
genome=genome, galaxyFn=galaxyFn, username=username)
trackViewList = [res[key]['Result'] for key in sorted(res.keys())]
tvGeSource = TrackViewListGenomeElementSource(genome, trackViewList)
composerCls = getComposerClsFromFileSuffix(cls.OUTPUT_TRACKS_SUFFIX)
composerCls(tvGeSource).composeToFile(primaryTrack.path)
else:
TrackExtractor.extractOneTrackManyRegsToOneFile( \
track.trackName, userBinSource, primaryTrack.path, fileFormatName=cls.OUTPUT_TRACKS_SUFFIX, \
globalCoords=True, asOriginal=False, allowOverlaps=True)
# Temporary hack until better solution for empty result tracks have been implemented
from gold.origdata.GenomeElementSource import GenomeElementSource
geSource = GenomeElementSource(primaryTrack.path, genome=genome, suffix=cls.OUTPUT_TRACKS_SUFFIX)
try:
geSource.parseFirstDataLine()
primaryGSuite.addTrack(primaryTrack)
except Exception, e: # Most likely empty file
primaryTrack.comment = e.message
emptyGSuite.addTrack(primaryTrack)
numTracks -= 1
progressViewer.updateProgressObjectElementCount(
cls.PROGRESS_PREPROCESS_MSG, numTracks)
#
progressViewer.update()
def testAddGSuiteTracks(self):
gSuite = GSuite()
gSuite.setGenomeOfAllTracks('hg18')
self.assertEqual('unknown', gSuite.genome)
gSuite.addTrack(
GSuiteTrack('ftp://server.somewhere.com/path/to/file1.bed',
title='Track1',
attributes=OrderedDict([('cell', 'k562'),
('antibody', 'cMyb')])))
gSuite.addTrack(
GSuiteTrack('http://server.other.com/path/to/file2.bed',
title='Track2',
attributes=OrderedDict([('cell', 'GM12878'),
('antibody', 'cMyc')])))
gSuite.addTrack(
GSuiteTrack('https://server.other.com/path/to/file3.bed',
attributes=OrderedDict([('cell', 'GM12878'),
('antibody', 'cMyb')])))
gSuite.addTrack(
GSuiteTrack(
'rsync://server.other.com/other/path/to/file3.bed;bed9',
attributes=OrderedDict([('cell', 'NHFL')])))
gSuite.setGenomeOfAllTracks('hg18')
self.assertEqual('remote', gSuite.location)
self.assertEqual('primary', gSuite.fileFormat)
self.assertEqual('unknown', gSuite.trackType)
self.assertEqual('hg18', gSuite.genome)
self.assertEqual(['cell', 'antibody'], gSuite.attributes)
self.assertEqual(False, gSuite.isPreprocessed())
self.assertEqual(True, gSuite.hasCustomTitles())
self.assertEqual(4, gSuite.numTracks())
self.assertEqual(['hg18'] * 4, [x.genome for x in gSuite.allTracks()])
self.assertEqual(['Track1', 'Track2', 'file3.bed', 'file3.bed (2)'],
gSuite.allTrackTitles())
self.assertEqual(['unknown'], gSuite.allTrackTypes())
gSuite.addTrack(
GSuiteTrack('hb:/track/name/hierarchy',
title='Track1',
genome='hg19',
trackType='segments'))
self.assertEqual('multiple', gSuite.genome)
gSuite.addTrack(
GSuiteTrack('galaxy:/ad123dd12fg;btrack?track=track:name',
title='Track2',
attributes=OrderedDict([('cell', 'k562'),
('antibody', 'cMyb')])))
gSuite.addTrack(
GSuiteTrack('file:/path/to/file.btrack?track=track:name',
title='Track2',
attributes=OrderedDict([('antibody', 'cMyb'),
('extra', 'yes')])))
self.assertEqual('multiple', gSuite.location)
self.assertEqual('multiple', gSuite.fileFormat)
self.assertEqual('unknown', gSuite.trackType)
self.assertEqual('unknown', gSuite.genome)
self.assertEqual(['cell', 'antibody', 'extra'], gSuite.attributes)
self.assertEqual(False, gSuite.isPreprocessed())
self.assertEqual(True, gSuite.hasCustomTitles())
self.assertEqual(7, gSuite.numTracks())
self.assertEqual(['hg18'] * 4 + ['hg19'] + ['unknown'] * 2,
[x.genome for x in gSuite.allTracks()])
self.assertEqual([
'Track1', 'Track2', 'file3.bed', 'file3.bed (2)', 'Track1 (2)',
'Track2 (2)', 'Track2 (3)'
], gSuite.allTrackTitles())
self.assertEqual(['segments', 'unknown'], gSuite.allTrackTypes())
self.assertRaises(
InvalidFormatError,
gSuite.addTrack,
GSuiteTrack('https://server.third.com/path/to/file3.bed'),
allowDuplicateTitles=False)
def testSimpleTitleDuplicate(self):
gSuite = GSuite()
gSuite.addTrack(
GSuiteTrack('ftp://server.somewhere.com/path/to/file1.bed'))
gSuite.addTrack(
GSuiteTrack('ftp://server.somewhere.com/other/path/to/file1.bed'))
gSuite.addTrack(
GSuiteTrack('ftp://server.somewhere.com/third/path/to/file1.bed'))
gSuite.addTrack(
GSuiteTrack('ftp://server.somewhere.com/last/path/to/file1.bed'))
self.assertEqual(
['file1.bed', 'file1.bed (2)', 'file1.bed (3)', 'file1.bed (4)'],
gSuite.allTrackTitles())
def execute(cls, choices, galaxyFn=None, username=''):
import os
gsuite = getGSuiteFromGalaxyTN(choices.gsuite)
# match = int(choices.match)
# mismatch = int(choices.mismatch)
# delta = int(choices.delta)
# pm = int(choices.pm)
# pi = int(choices.pi)
# minscore = int(choices.minscore)
# maxperiod = int(choices.maxperiod)
minConsensusLength = int(choices.minconsensus) if choices.minconsensus.isdigit() else None
maxConsensusLength = int(choices.maxconsensus) if choices.maxconsensus.isdigit() else None
minCopyNumber = int(choices.mincopynumber) if choices.mincopynumber.isdigit() else None
parameters = [choices.match, choices.mismatch, choices.delta, choices.pm,
choices.pi, choices.minscore, choices.maxperiod]
resultsDict = OrderedDict()
for gsTrack in gsuite.allTracks():
resFile = GalaxyRunSpecificFile(['trf', gsTrack.title, gsTrack.title + '.tmp'], galaxyFn)
ensurePathExists(resFile.getDiskPath())
trackDirName = os.path.dirname(os.path.realpath(resFile.getDiskPath()))
# parameters = ["2", "5", "7", "80", "10", "50", "300"] #Madeleine suggestion
instruction = [cls.TRF_PATH, gsTrack.path] + parameters + ["-d", "-h"]
pipe = subprocess.Popen(instruction, cwd=trackDirName, stdin=subprocess.PIPE, stdout=subprocess.PIPE,
stderr=subprocess.PIPE)
results, errors = pipe.communicate()
outFileName = ".".join([os.path.basename(gsTrack.path)] + parameters + ["dat"])
outFilePath = os.path.join(trackDirName, outFileName)
# print outFilePath
resultList = cls.parseTRFResultFile(outFilePath, minConsensusLength, maxConsensusLength, minCopyNumber)
if resultList:
resultsDict[gsTrack.title] = resultList
if choices.regionsGSuite:
repeatRegionsBedTracksGSuite = GSuite()
for trackName, trfResultList in resultsDict.iteritems():
trackUri = GalaxyGSuiteTrack.generateURI(galaxyFn=galaxyFn,
extraFileName=("Repeat_regions_"+trackName),
suffix='bed')
gsTrack = GSuiteTrack(trackUri, title=("Repeat regions " + trackName), genome=gsuite.genome)
ensurePathExists(gsTrack.path)
with open(gsTrack.path, 'w') as bedFile:
header = 'track name="' + trackName + '" description="' + trackName + '" priority=1'
bedFile.write(header + os.linesep)
for trfResult in trfResultList:
for repeatRegion in trfResult._repeatRegionList:
# if not repeatRegion.strand:
# DebugUtil.insertBreakPoint()
endPosition = repeatRegion.endPositionFullCopies if choices.rrCutoff == cls.CUTOFF_REPEAT_REGION else repeatRegion.endPosition
bedFile.write('\t'.join([repeatRegion.chromosome,
str(repeatRegion.startPosition),
str(endPosition),
repeatRegion.bedName,
'0',
str(repeatRegion.strand)]) + os.linesep)
repeatRegionsBedTracksGSuite.addTrack(gsTrack)
GSuiteComposer.composeToFile(repeatRegionsBedTracksGSuite, cls.extraGalaxyFn['Repeat regions (bed) GSuite'])
if choices.monomersGSuite:
monomersBedTracksGSuite = GSuite()
for trackName, trfResultList in resultsDict.iteritems():
trackUri = GalaxyGSuiteTrack.generateURI(galaxyFn=galaxyFn,
extraFileName=("Repeat_monomers_"+trackName),
suffix='bed')
gsTrack = GSuiteTrack(trackUri, title=("Repeat monomers " + trackName), genome=gsuite.genome)
ensurePathExists(gsTrack.path)
with open(gsTrack.path, 'w') as bedFile:
header = 'track name="' + trackName + '" description="' + trackName + '" priority=1'
bedFile.write(header + os.linesep)
for trfResult in trfResultList:
for repeatRegion in trfResult._repeatRegionList:
# if not repeatRegion.strand:
# DebugUtil.insertBreakPoint()
for repeatMonomer in repeatRegion._monomers:
# endPosition = repeatRegion.endPositionFullCopies if choices.rrCutoff == cls.CUTOFF_REPEAT_REGION else repeatRegion.endPosition
bedFile.write('\t'.join([repeatRegion.chromosome,
str(repeatMonomer.startPosition),
str(repeatMonomer.endPosition),
repeatMonomer.bedName,
'0',
str(repeatRegion.strand)]) + os.linesep)
monomersBedTracksGSuite.addTrack(gsTrack)
GSuiteComposer.composeToFile(monomersBedTracksGSuite, cls.extraGalaxyFn['Repeat monomers (bed) GSuite'])
###################
analysisParamsTableColumnTitles = ['Parameter', 'Selected value']
analysisParamsDict = OrderedDict()
analysisParamsDict['Tandem Repeat Finder tool version'] = cls.TRF_VERSION
analysisParamsDict.update(
OrderedDict([
('Match', choices.match),
('Mismatch', choices.mismatch),
('Delta', choices.delta),
('Matching probability (Pm)', choices.pm),
('Indel probability (Pi)', choices.pi),
('Min score', choices.minscore),
('Max period', choices.maxperiod),
('Min consensus length', choices.minconsensus),
('Max consensus length', choices.maxconsensus),
('Min copy number', choices.mincopynumber)]
)
)
###################
###################
countTableColumnTitles = ['Name', 'Nr of repeat regions', 'Avg copy number', 'Min copy number',
'Max copy number', 'Avg consensus length', 'Min consensus length',
'Max consensus length']
countTableDict = OrderedDict()
from numpy import mean
for trackName, trfResultList in resultsDict.iteritems():
countTableDict[trackName] = []
repeatRegionsNr = sum([x.repeatRegionsCount for x in trfResultList])
countTableDict[trackName].append(repeatRegionsNr)
copyNumberList =[]
for trfRes in trfResultList:
copyNumberList += trfRes.copyNumberList if \
choices.rrCutoff == cls.CUTOFF_REPEAT_REGION else trfRes.realCopyNumberList
countTableDict[trackName].append(mean(copyNumberList))
countTableDict[trackName].append(min(copyNumberList))
countTableDict[trackName].append(max(copyNumberList))
consensusLengthList = []
for trfRes in trfResultList:
consensusLengthList += trfRes.consensusLengths
countTableDict[trackName].append(mean(consensusLengthList))
countTableDict[trackName].append(min(consensusLengthList))
countTableDict[trackName].append(max(consensusLengthList))
###################
core = HtmlCore()
core.begin()
core.divBegin()
# core.paragraph('''This tool reports repeat regions discovered by the TRF tool
# ''')
core.tableFromDictionary(analysisParamsDict, columnNames=analysisParamsTableColumnTitles, sortable=False)
core.divEnd()
core.divBegin()
core.tableFromDictionary(countTableDict, columnNames=countTableColumnTitles,
tableId='repeatCounts', sortable=True, presorted=0)
core.divEnd()
# core.divBegin()
# for k, v in resultsDict.iteritems():
# core.line('track: ' + k)
#
# for val in v:
# core.line(str(val))
# core.divEnd()
core.end()
print core
def selectRowsFromGSuiteByIndex(gSuite, idxList):
trackList = list(gSuite.allTracks())
reducedTrackList = [trackList[i] for i in idxList]
reducedGSuite = GSuite(trackList=reducedTrackList)
return reducedGSuite
def selectRowsFromGSuiteByTitle(gSuite, titleList):
reducedTrackList = [gSuite.getTrackFromTitle(title) for title in titleList]
reducedGSuite = GSuite(trackList=reducedTrackList)
return reducedGSuite
from collections import OrderedDict
from gold.gsuite.GSuite import GSuite
from gold.gsuite.GSuiteTrack import GSuiteTrack, FtpGSuiteTrack, HbGSuiteTrack
import gold.gsuite.GSuiteComposer as GSuiteComposer
import gold.gsuite.GSuiteParser as GSuiteParser
gSuite = GSuite()
uri1 = FtpGSuiteTrack.generateURI(netloc='server.com', path='file.bed')
gSuite.addTrack(
GSuiteTrack(uri1,
title='Track1',
attributes=OrderedDict([('a', 'yes'), ('b', 'no')])))
uri2 = HbGSuiteTrack.generateURI(
trackName=['Genes and gene subsets', 'Genes', 'Refseq'])
gSuite.addTrack(
GSuiteTrack(uri2, attributes=OrderedDict([('b', 'no'), ('c', 'yes')])))
gSuite.setGenomeOfAllTracks('hg19')
contents = GSuiteComposer.composeToString(gSuite)
print 'GSuite file contents'
print '--------------------'
print contents
gSuite2 = GSuiteParser.parseFromString(contents)
print 'Various ways of direct access'
print '-----------------------------'
