def test_matrix_generation(self):
''' Test creation of matrix '''
genomeBin = interactionMatrix.genomeBin((self.chrFile,10,True))
countMatrix, logArray = interactionMatrix.generateMatrix(
self.inFrag, genomeBin, threads=4)
self.assertTrue(np.array_equal(countMatrix,
np.array([
[2,0,0,0,0,0,1],
[0,0,0,1,0,0,0],
[0,0,0,0,2,0,0],
[0,1,0,0,0,0,0],
[0,0,2,0,0,0,0],
[0,0,0,0,0,0,0],
[1,0,0,0,0,0,0]
])))
self.assertTrue(np.array_equal(logArray, np.array([10,2,3,5])))
# Create output file prefix
if args['--label']:
outPrefix = args['<outdir>'] + sampleName + '_' + args['--label']
else:
outPrefix = args['<outdir>'] + sampleName
# Create output file names
bedFile = outPrefix + '.bed'
matrixFile = outPrefix + '.countMatrix.gz'
biasFile = outPrefix + '.bias'
normMatrixFile = outPrefix + '.normMatrix.gz'
# Store file names required for normalisation
matrixFileList.append((matrixFile, biasFile, normMatrixFile))
# Save bed file
genomeBins.writeBed(bedFile)
# Create interaction matrix and save to file
countMatrix, logArray = interactionMatrix.generateMatrix(
f, genomeBins, args['--threads'])
np.savetxt(matrixFile, countMatrix, '%s', '\t',
header = '\t'.join(genomeBins.binNames), comments = '')
# Print Interaction Data
print '\n%s:\n Interaction Data:\n%s\n%s\n%s\n%s' %(
sampleName,
' total: %s' %(logArray[0]),
' accepted: %s' %(logArray[3]),
' no chromosome: %s' %(logArray[1]),
' no bin: %s' %(logArray[2])
)
# Find and process bins below minimum bin count
colSums = countMatrix.sum(axis=0)
binsBelowMin = colSums < args['<mincount>']
failedBins = np.logical_or(failedBins, binsBelowMin)
# Print bin data
'bin size equal: %s' %(args.equal),
'minimum bin count: %s' %(args.minCount)
)
else:
raise IOError('bed file or chromosome file and bin size must be provided')
# Create output files
args.bedFile = args.outPrefix + '.bed'
args.biasFile = args.outPrefix + '.bias'
args.countMatrix = args.outPrefix + '.countMatrix'
args.normMatrix = args.outPrefix + '.normMatrix'
# Create bin object and save bed
genomeBins = interactionMatrix.genomeBin(binData)
genomeBins.writeBed(args.bedFile)
# Count interactions
countMatrix, logArray = interactionMatrix.generateMatrix(
args.inFile, genomeBins, args.threads
)
# Save interactions
np.savetxt(args.countMatrix, countMatrix, '%s', '\t',
header = '\t'.join(genomeBins.binNames), comments = '')
# Print Interaction Data
print '\nInteraction Data\n\t%s\n\t%s\n\t%s\n\t%s' %(
'total: %s' %(logArray[0]),
'accepted: %s' %(logArray[3]),
'no chromosome: %s' %(logArray[1]),
'no bin: %s' %(logArray[2])
)
# Count number of bins above minimum
colSums = countMatrix.sum(axis=0)
binsAboveMin = sum(colSums >= args.minCount)
# Print bin data
