def writeTrackData(choices, genome, tn):
from gold.util.RandomUtil import random
from gold.util.CommonFunctions import createCollectedPath
from quick.util.CommonFunctions import ensurePathExists
trackFn = createCollectedPath(genome, tn,
'simulatedTracks.category.bed')
ensurePathExists(trackFn)
trackFile = open(trackFn, 'w')
#determinePossibilities
numPossiblePositions = int(choices[2])
spacingBetweenPositions = 1e3
possiblePositions = [
i * spacingBetweenPositions
for i in range(1, int(numPossiblePositions))
]
numHighProbPositions = int(choices[3])
highProbPossiblePositions = possiblePositions[0:numHighProbPositions]
lowProbPossiblePositions = possiblePositions[numHighProbPositions:]
largestPossiblePosition = possiblePositions[-1]
print 'largestPossiblePosition: ', largestPossiblePosition / 1e6, 'M'
assert largestPossiblePosition < 1.5e8 #just due to hardcoded analysis region below..
sizePerPosition = 591 #empirical across all VDR binding sites..
print 'Total BpCoverage: ', len(possiblePositions) * sizePerPosition
#make samples
numExperiments = int(choices[0])
proportionFromHighProbPositions = float(choices[4])
fixedNumFromHighProbPositions = int(choices[5])
#numPositionsPerExperiment = [3000]*9
numPositionsPerExperiment = [
int(x) for x in choices[1].split(',')
] #[3073, 7118, 5290, 3059, 4051, 1021, 200, 610, 573]
for experimentIndex in range(numExperiments):
#sampledPositions = random.sample(possiblePositions, numPositionsPerExperiment[experimentIndex])
numHighProbSamples = int(numPositionsPerExperiment[experimentIndex]
* proportionFromHighProbPositions
) + fixedNumFromHighProbPositions
numLowProbSamples = numPositionsPerExperiment[
experimentIndex] - numHighProbSamples
print 'numHighProbSamples: %i, out of numHighProbPossiblePositions: %i' % (
numHighProbSamples, len(highProbPossiblePositions))
sampledPositions = random.sample(highProbPossiblePositions, numHighProbSamples ) \
+ random.sample(lowProbPossiblePositions, numLowProbSamples )
sampledSegments = [(position, position + sizePerPosition)
for position in sampledPositions]
for seg in sampledSegments:
trackFile.write('\t'.join([
'chr1',
'%i' % seg[0],
'%i' % seg[1],
'T%i' % experimentIndex
]) + '\n')
trackFile.close()
def getRandSegments(size, start, end):
segments = sorted(random.sample(xrange(start*2, end*2), size*2))
starts, ends = [], []
for i in xrange(size):
starts.append(segments[i*2]/2)
ends.append((segments[i*2+1]+1)/2)
return [array(starts), array(ends)]
def getRandSegments(size, start, end):
segments = sorted(random.sample(xrange(start * 2, end * 2), size * 2))
starts, ends = [], []
for i in xrange(size):
starts.append(segments[i * 2] / 2)
ends.append((segments[i * 2 + 1] + 1) / 2)
return [array(starts), array(ends)]
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.
'''
#print os.getcwd()
from config.Config import HB_SOURCE_CODE_BASE_DIR
numRandomPwms = int(choices[2])
pwms = parseTransfacMatrixFile(HB_SOURCE_CODE_BASE_DIR+'/data/all_PWMs.txt')
if choices[1]=='All PWMs':
selectedPwms = pwms
elif choices[1] == 'Random subset':
from gold.util.RandomUtil import random
selectedPwmKeys = random.sample(pwms.keys(),numRandomPwms)
selectedPwms = dict([(x,pwms[x]) for x in selectedPwmKeys])
writeTransfacMatrixFile(selectedPwms, galaxyFn)
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.
'''
#print os.getcwd()
from config.Config import HB_SOURCE_CODE_BASE_DIR
pwms = parseTransfacMatrixFile(HB_SOURCE_CODE_BASE_DIR+'/data/all_PWMs.txt')
if choices[1]=='All PWMs':
selectedPwms = pwms
elif choices[1] == 'Random subset':
numRandomPwms = int(choices[2])
from gold.util.RandomUtil import random
selectedPwmKeys = random.sample(pwms.keys(),numRandomPwms)
selectedPwms = dict([(x,pwms[x]) for x in selectedPwmKeys])
writeTransfacMatrixFile(selectedPwms, galaxyFn)