def getGsuiteFromRandomRows(self, count=10):
random.seed(9001)
rItem = self.VOCABULARY[random.randint(0, len(self.VOCABULARY) - 1)]
rRows = self.getRandomRows(rItem, count)
gSuite = GSuite()
self.appendGsuiteFromRows(gSuite, rRows, rItem)
return gSuite
def getTrackView(self, region):
assert self._origRegion == region
allChrArmRegs = GenomeInfo.getContainingChrArms(region)
if len(allChrArmRegs) != 1:
raise CentromerError
chrArm = allChrArmRegs[0]
buffer = self._getIndepencyBufferSize(region)
sourceRegs = chrArm.exclude( copy(region).extend(-buffer).extend(buffer) )
assert len(sourceRegs) in [1,2]
if not any(len(sourceReg) >= self.MIN_SOURCE_TO_SAMPLE_SIZE_RATIO * len(region) for sourceReg in sourceRegs):
raise TooLargeBinError('Source region lengths of ' + str([len(x) for x in sourceRegs]) +
' are too small compared to region length of ' + str(len(region)) +
' according to MIN_SOURCE_TO_SAMPLE_SIZE_RATIO: ' + str(self.MIN_SOURCE_TO_SAMPLE_SIZE_RATIO))
if len(sourceRegs) == 1:
sourceReg = sourceRegs[0]
else:
firstSourceProportion = (len(sourceRegs[0])-len(region)) / sum(len(sourceRegs[i])-len(region) for i in range(2))
sourceReg = sourceRegs[0] if random.random() < firstSourceProportion else sourceRegs[1]
randOffset = random.randint( 0, len(sourceReg) - len(region) )
start = sourceReg.start + randOffset
end = start + len(region)
randRegion = GenomeRegion(region.genome, region.chr, start, end)
rawData = RawDataStat(randRegion, self._origTrack, self._trackFormatReq)
tv = rawData.getResult()
assert region != tv.genomeAnchor
return tv
def _getTrackView(self, region):
from gold.util.RandomUtil import random
#if not hasattr(self, '_minimalRegion'):
# from quick.application.UserBinSource import MinimalBinSource
# minimalBinList = MinimalBinSource(region.genome)
# self._minimalRegion = minimalBinList[0] if minimalBinList is not None else None
#
#if self._minimalRegion == region:
# return self._origTrack.getTrackView(region)
allChrArmRegs = GenomeInfo.getContainingChrArms(region)
if len(allChrArmRegs) != 1:
raise CentromerError
chrArm = allChrArmRegs[0]
buffer = self._getIndependencyBufferSize(region)
sourceRegs = chrArm.exclude(
region.getCopy().extend(-buffer).extend(buffer))
assert len(sourceRegs) in [
1, 2
], "Source region must be smaller than a tenth of a chromosome arm: %s" % region
if not any(
len(sourceReg) >= self.MIN_SOURCE_TO_SAMPLE_SIZE_RATIO *
len(region) for sourceReg in sourceRegs):
raise TooLargeBinError(
'Source region lengths of ' + str([len(x)
for x in sourceRegs]) +
' are too small compared to region length of ' +
str(len(region)) +
' according to MIN_SOURCE_TO_SAMPLE_SIZE_RATIO: ' +
str(self.MIN_SOURCE_TO_SAMPLE_SIZE_RATIO))
if len(sourceRegs) == 1:
sourceReg = sourceRegs[0]
else:
firstSourceProportion = (len(sourceRegs[0]) - len(region)) / sum(
len(sourceRegs[i]) - len(region) for i in range(2))
sourceReg = sourceRegs[0] if random.random(
) < firstSourceProportion else sourceRegs[1]
randOffset = random.randint(0, len(sourceReg) - len(region))
start = sourceReg.start + randOffset
end = start + len(region)
randRegion = GenomeRegion(region.genome, region.chr, start, end)
#rawData = RawDataStat(randRegion, self._origTrack, self._trackFormatReq)
#tv = rawData.getResult()
tv = self._origTrack.getTrackView(randRegion)
assert tv.genomeAnchor != region, (region, tv.genomeAnchor,
getClassName(region),
getClassName(tv.genomeAnchor))
return tv
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 execute(choices, galaxyFn=None, username=''):
if username =='':
username = ''.join([chr(random.randint(97,122)) for i in range(6)])
dirForDataset = UploadDataToStorebio.STOREBIO_ROOT_PATH+username + '_'.join([str(v) for v in time.localtime()[:6]]) + str(time.time()).split('.')[-1]
print dirForDataset
makedirs(dirForDataset)
#if choices[0] == 'from tracks':
#
# sourceLink = createOrigPath(genome=choices[1], trackName=choices[2].split(':'))
# #symboliclink = dirForDataset + sep + choices[2].split(':')[-1]
# #copytree(sourceLink, symboliclink)# symlink(sourceLink, symboliclink)
#
#else:
# pass
# sourceLink = dirForDataset
# galaxyTnList = [unquote(v).split(':') for v in choices[1].values() if v]
#
# for galaxyTn in galaxyTnList:
#
# fnSource = ExternalTrackManager.extractFnFromGalaxyTN(galaxyTn)
# fnDestination = dirForDataset+'/' + galaxyTn[-1].replace(' ','_')+'.'+galaxyTn[1]
# print fnSource, fnDestination
# copyfile(fnSource, fnDestination)
projectList = UploadDataToStorebio.ProjectList
print choices
projName = choices[3]
projInfo = [ (i[1], i[2]) for i in projectList if i[0] == projName ][0]
#(self, name, quotaId, type, url ,resourceType, userName, password, description=None, projectAccessControlList=None):
url = dirForDataset #'scp://invitro.titan.uio.no:'+ dirForDataset
print 'Url: ', url
print projectList
print projInfo
name, quotaId, dsType = choices[-3], projInfo[1], choices[-1]
userName, password = choices[0], choices[1]
projectAccessControlList = [projInfo[0], 'true']
description = choices[-2] if choices[-2] not in ['', None] else ''
params = ['username:='******'password:='******'operation:=CreateDataSet', 'class:=dataStorageService',\
'params:='+'<#>'.join([name, quotaId, dsType, description, repr(projectAccessControlList)])]
from quick.extra.WsStoreBioInfo import messageSep
UploadDataToStorebio.socket.send_unicode(messageSep.join(params))
message = UploadDataToStorebio.socket.recv_unicode().encode('utf-8')#, 'ignore'
if message != 'something went wrong...':
print 'Dataset successfully upploaded to Storebio server'
else:
print message
print '<a href="http://hyperbrowser.uio.no/dev2/hyper?mako=generictool&tool_id=hb_add_files_to_storebioinfo_dataset">Start adding data to newly created dataset</a>'
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.
'''
if username =='':
username = ''.join([chr(random.randint(97,122)) for i in range(6)])
dirForDataset = AddFilesToStorebioinfoDataset.STOREBIO_ROOT_PATH+username + '_'.join([str(v) for v in time.localtime()[:6]]) + str(time.time()).split('.')[-1]
print dirForDataset
makedirs(dirForDataset)
url = 'scp://invitro.titan.uio.no:'
if choices[0] == 'from tracks':
sourceLink = createOrigPath(genome=choices[1], trackName=choices[2].split(':'))
symboliclink = dirForDataset + sep + choices[2].split(':')[-1]
copytree(sourceLink, symboliclink)# symlink(sourceLink, symboliclink)
else:
sourceLink = dirForDataset
galaxyTnList = [unquote(v).split(':') for v in choices[1].values() if v]
for galaxyTn in galaxyTnList:
fnSource = ExternalTrackManager.extractFnFromGalaxyTN(galaxyTn)
fnDestination = dirForDataset+'/' + galaxyTn[-1].replace(' ','_')+'.'+galaxyTn[1]
copyfile(fnSource, fnDestination)
url = url + fnDestination
#AddFileToDataSet(dataSetId, subtype, pathInSubtype, url, userName, password)
#['Username','password', 'Select dataset', 'select subtype', 'write path in subtype', 'UIO username', 'UIO password']
userName, password = choices[3], choices[4]
#uioUser, uioPwd = choices[-2], choices[-1]
dataSetId, subtype = choices[5].split('(')[-1].split(')')[0] , choices[6]
pathInSubtype = choices[7] if choices[7] else ''
params = ['username:='******'password:='******'operation:=AddFileToDataSet', 'class:=dataStorageService',\
'params:='+'<#>'.join([dataSetId, subtype, pathInSubtype, url])]
print params
AddFilesToStorebioinfoDataset.socket.send(messageSep.join(params))
message = AddFilesToStorebioinfoDataset.socket.recv_unicode().encode('utf-8')#, 'ignore'
if message != 'something went wrong...':
print 'Dataset successfully upploaded to Storebio server'
else:
print message
def getRandomTracks(gSuite, number, seed=9001):
from gold.util.RandomUtil import random
randomTrackList = []
trackList = [t for t in gSuite.allTracks()]
trackIndexList = [i for i in range(len(trackList))]
random.seed(seed)
for i in range(number):
if len(trackIndexList) == 0:
break
index = random.randint(0, len(trackIndexList)-1)
randomTrackList.append(trackList[trackIndexList[index]])
trackIndexList.pop(index)
return randomTrackList
def getRandomRows(self, item, count=10, fileTypes=[]):
#rows = self.getRows(item)
#rows = []
#for item in items:
# rows.extend(self.filterRowsByFileTypes(self.getRows(item),fileTypes))
rows = self.filterRowsByFileTypes(self.getRows(item), fileTypes)
if len(rows) == 0:
return []
rRows = []
random.seed(9001)
for i in range(count):
if len(rows) == 0:
break
index = random.randint(0, len(rows) - 1)
rRows.append(rows[index])
rows.pop(index)
return rRows
def execute(cls, choices, galaxyFn=None, username=''):
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 ['marked.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 getRandomNode(self):
from gold.util.RandomUtil import random
index = random.randint(0, len(self._id2index))
return self.getNode(self._id2index.keys()[index])
def getRandStrandList(size): return array([random.randint(0, 1) for i in xrange(size)], dtype='bool8')
def getRandomNode(self):
from gold.util.RandomUtil import random
index = random.randint(0, len(self._id2index))
return self.getNode( self._id2index.keys()[index])
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 quick.extra.WsStoreBioInfo import *
if username == '':
username = ''.join(
[chr(random.randint(97, 122)) for i in range(6)])
dirForDataset = cls.STOREBIO_ROOT_PATH + username + '_'.join(
[str(v)
for v in time.localtime()[:6]]) + str(time.time()).split('.')[-1]
print dirForDataset
makedirs(dirForDataset)
url = '' #'scp://invitro.titan.uio.no:'
if choices[0] == 'from tracks':
sourceLink = createOrigPath(genome=choices[1],
trackName=choices[2].split(':'))
folder = (dirForDataset + '/' + choices[-1] + '/').replace(
'//', '/')
symboliclink = folder + choices[2].split(':')[-1]
if not os.path.isdir(folder):
os.makedirs(folder)
copytree(sourceLink,
symboliclink) # symlink(sourceLink, symboliclink)
else:
sourceLink = dirForDataset
galaxyTnList = [
unquote(v).split(':') for v in choices[1].values() if v
]
for galaxyTn in galaxyTnList:
fnSource = ExternalTrackManager.extractFnFromGalaxyTN(galaxyTn)
folder = (dirForDataset + '/' + choices[-1] + '/').replace(
'//', '/')
fnDestination = folder + galaxyTn[-1].replace(
' ', '_') + '.' + galaxyTn[1]
if not os.path.isdir(folder):
os.makedirs(folder)
copyfile(fnSource, fnDestination)
url = url + fnDestination
#AddFileToDataSet(dataSetId, subtype, pathInSubtype, url, userName, password)
#['Username','password', 'Select dataset', 'select subtype', 'write path in subtype', 'UIO username', 'UIO password']
userName, password = choices[3], choices[4]
#uioUser, uioPwd = choices[-2], choices[-1]
dataSetId, subtype = choices[5].split('(')[-1].split(
')')[0], choices[6]
pathInSubtype = choices[7] if choices[7] else ''
params = ['username:='******'password:='******'operation:=AddFileToDataSet', 'class:=dataStorageService',\
'params:='+'<#>'.join([dataSetId, subtype, pathInSubtype, dirForDataset])]
print params
cls.socket.send(messageSep.join(params))
message = cls.socket.recv_unicode().encode('utf-8') #, 'ignore'
if message != 'something went wrong...':
print 'Dataset successfully upploaded to Storebio server'
else:
print message
def getRandStrandList(size):
from gold.util.RandomUtil import random
return array([random.randint(0, 1) for i in xrange(size)], dtype='bool8')
def getRandStrandList(size):
return array([random.randint(0, 1) for i in xrange(size)], dtype='bool8')
