def __obs_exp(pSubmatrix, pLengthChromosome, pChromosomeCount):
exp_obs_matrix_ = exp_obs_matrix_lieberman(pSubmatrix, pLengthChromosome,
pChromosomeCount)
exp_obs_matrix_ = convertNansToZeros(csr_matrix(exp_obs_matrix_))
exp_obs_matrix_ = convertInfsToZeros(csr_matrix(exp_obs_matrix_)).todense()
return exp_obs_matrix_
def main(args=None):
args = parse_arguments().parse_args(args)
if int(args.numberOfEigenvectors) != len(args.outputFileName):
log.error(
"Number of output file names and number of eigenvectors does not match. Please"
"provide the name of each file.\nFiles: {}\nNumber of eigenvectors: {}"
.format(args.outputFileName, args.numberOfEigenvectors))
exit(1)
ma = hm.hiCMatrix(args.matrix)
ma.maskBins(ma.nan_bins)
if args.chromosomes:
ma.keepOnlyTheseChr(args.chromosomes)
vecs_list = []
chrom_list = []
start_list = []
end_list = []
# PCA is computed per chromosome
length_chromosome = 0
chromosome_count = len(ma.getChrNames())
if args.pearsonMatrix:
trasf_matrix_pearson = lil_matrix(ma.matrix.shape)
if args.obsexpMatrix:
trasf_matrix_obsexp = lil_matrix(ma.matrix.shape)
for chrname in ma.getChrNames():
chr_range = ma.getChrBinRange(chrname)
length_chromosome += chr_range[1] - chr_range[0]
for chrname in ma.getChrNames():
chr_range = ma.getChrBinRange(chrname)
submatrix = ma.matrix[chr_range[0]:chr_range[1],
chr_range[0]:chr_range[1]]
if args.norm:
exp_obs_matrix_ = exp_obs_matrix_norm(submatrix, length_chromosome,
chromosome_count)
exp_obs_matrix_ = convertNansToZeros(
csr_matrix(exp_obs_matrix_)).todense()
exp_obs_matrix_ = convertInfsToZeros(
csr_matrix(exp_obs_matrix_)).todense()
else:
exp_obs_matrix_ = exp_obs_matrix_lieberman(submatrix,
length_chromosome,
chromosome_count)
exp_obs_matrix_ = convertNansToZeros(
csr_matrix(exp_obs_matrix_)).todense()
exp_obs_matrix_ = convertInfsToZeros(
csr_matrix(exp_obs_matrix_)).todense()
if args.obsexpMatrix:
trasf_matrix_obsexp[chr_range[0]:chr_range[1],
chr_range[0]:chr_range[1]] = lil_matrix(
exp_obs_matrix_)
pearson_correlation_matrix = np.corrcoef(exp_obs_matrix_)
pearson_correlation_matrix = convertNansToZeros(
csr_matrix(pearson_correlation_matrix)).todense()
pearson_correlation_matrix = convertInfsToZeros(
csr_matrix(pearson_correlation_matrix)).todense()
if args.pearsonMatrix:
trasf_matrix_pearson[chr_range[0]:chr_range[1],
chr_range[0]:chr_range[1]] = lil_matrix(
pearson_correlation_matrix)
corrmatrix = np.cov(pearson_correlation_matrix)
corrmatrix = convertNansToZeros(csr_matrix(corrmatrix)).todense()
corrmatrix = convertInfsToZeros(csr_matrix(corrmatrix)).todense()
evals, eigs = linalg.eig(corrmatrix)
k = args.numberOfEigenvectors
chrom, start, end, _ = zip(
*ma.cut_intervals[chr_range[0]:chr_range[1]])
vecs_list += eigs[:, :k].tolist()
chrom_list += chrom
start_list += start
end_list += end
if args.pearsonMatrix:
file_type = 'cool'
if args.pearsonMatrix.endswith('.h5'):
file_type = 'h5'
matrixFileHandlerOutput = MatrixFileHandler(pFileType=file_type)
matrixFileHandlerOutput.set_matrix_variables(
trasf_matrix_pearson.tocsr(), ma.cut_intervals, ma.nan_bins,
ma.correction_factors, ma.distance_counts)
matrixFileHandlerOutput.save(args.pearsonMatrix,
pSymmetric=True,
pApplyCorrection=False)
if args.obsexpMatrix:
file_type = 'cool'
if args.obsexpMatrix.endswith('.h5'):
file_type = 'h5'
matrixFileHandlerOutput = MatrixFileHandler(pFileType=file_type)
matrixFileHandlerOutput.set_matrix_variables(
trasf_matrix_obsexp.tocsr(), ma.cut_intervals, ma.nan_bins,
ma.correction_factors, ma.distance_counts)
matrixFileHandlerOutput.save(args.obsexpMatrix,
pSymmetric=True,
pApplyCorrection=False)
if args.geneTrack:
vecs_list = correlateEigenvectorWithGeneTrack(ma, vecs_list,
args.geneTrack)
if args.format == 'bedgraph':
for idx, outfile in enumerate(args.outputFileName):
assert (len(vecs_list) == len(chrom_list))
with open(outfile, 'w') as fh:
for i, value in enumerate(vecs_list):
if len(value) == args.numberOfEigenvectors:
if isinstance(value[idx], np.complex):
value[idx] = value[idx].real
fh.write("{}\t{}\t{}\t{:.12f}\n".format(
toString(chrom_list[i]), start_list[i],
end_list[i], value[idx]))
elif args.format == 'bigwig':
if not pyBigWig.numpy == 1:
log.error(
"ERROR: Your version of pyBigWig is not supporting numpy: {}".
format(pyBigWig.__file__))
exit(1)
old_chrom = chrom_list[0]
header = []
for i, _chrom in enumerate(chrom_list):
if old_chrom != _chrom:
header.append((toString(old_chrom), end_list[i - 1]))
old_chrom = _chrom
header.append((toString(chrom_list[-1]), end_list[-1]))
for idx, outfile in enumerate(args.outputFileName):
log.debug("bigwig: len(vecs_list) {}".format(len(vecs_list)))
log.debug("bigwig: len(chrom_list) {}".format(len(chrom_list)))
assert (len(vecs_list) == len(chrom_list))
_chrom_list = []
_start_list = []
_end_list = []
values = []
bw = pyBigWig.open(outfile, 'w')
# set big wig header
bw.addHeader(header)
# create entry lists
for i, value in enumerate(vecs_list):
# it can happen that some 'value' is having less dimensions than it should
if len(value) == args.numberOfEigenvectors:
if isinstance(value[idx], np.complex):
value[idx] = value[idx].real
values.append(value[idx])
_chrom_list.append(toString(chrom_list[i]))
_start_list.append(start_list[i])
_end_list.append(end_list[i])
# write entries
bw.addEntries(_chrom_list,
_start_list,
ends=_end_list,
values=values)
bw.close()
else:
log.error("Output format not known: {}".format(args.format))
exit(1)
def main(args=None):
args = parse_arguments().parse_args(args)
if int(args.numberOfEigenvectors) != len(args.outputFileName):
log.error(
"Number of output file names and number of eigenvectors does not match. Please"
"provide the name of each file.\nFiles: {}\nNumber of eigenvectors: {}"
.format(args.outputFileName, args.numberOfEigenvectors))
exit(1)
ma = hm.hiCMatrix(args.matrix)
ma.maskBins(ma.nan_bins)
if args.chromosomes:
ma.keepOnlyTheseChr(args.chromosomes)
vecs_list = []
chrom_list = []
start_list = []
end_list = []
# PCA is computed per chromosome
length_chromosome = 0
chromosome_count = len(ma.getChrNames())
for chrname in ma.getChrNames():
chr_range = ma.getChrBinRange(chrname)
length_chromosome += chr_range[1] - chr_range[0]
for chrname in ma.getChrNames():
chr_range = ma.getChrBinRange(chrname)
log.debug("Computing pca for chromosome: {}".format(chrname))
submatrix = ma.matrix[chr_range[0]:chr_range[1],
chr_range[0]:chr_range[1]]
exp_obs_matrix_ = exp_obs_matrix_lieberman(submatrix,
length_chromosome,
chromosome_count)
exp_obs_matrix_ = convertNansToZeros(
csr_matrix(exp_obs_matrix_)).todense()
exp_obs_matrix_ = convertInfsToZeros(
csr_matrix(exp_obs_matrix_)).todense()
pearson_correlation_matrix = np.corrcoef(exp_obs_matrix_)
pearson_correlation_matrix = convertNansToZeros(
csr_matrix(pearson_correlation_matrix)).todense()
pearson_correlation_matrix = convertInfsToZeros(
csr_matrix(pearson_correlation_matrix)).todense()
corrmatrix = np.cov(pearson_correlation_matrix)
corrmatrix = convertNansToZeros(csr_matrix(corrmatrix)).todense()
corrmatrix = convertInfsToZeros(csr_matrix(corrmatrix)).todense()
evals, eigs = linalg.eig(corrmatrix)
k = args.numberOfEigenvectors
chrom, start, end, _ = zip(
*ma.cut_intervals[chr_range[0]:chr_range[1]])
vecs_list += eigs[:, :k].tolist()
chrom_list += chrom
start_list += start
end_list += end
if args.format == 'bedgraph':
for idx, outfile in enumerate(args.outputFileName):
assert (len(vecs_list) == len(chrom_list))
with open(outfile, 'w') as fh:
for i, value in enumerate(vecs_list):
if len(value) == args.numberOfEigenvectors:
if isinstance(value[idx], np.complex):
value[idx] = value[idx].real
fh.write("{}\t{}\t{}\t{:.12f}\n".format(
toString(chrom_list[i]), start_list[i],
end_list[i], value[idx]))
elif args.format == 'bigwig':
if not pyBigWig.numpy == 1:
log.error(
"ERROR: Your version of pyBigWig is not supporting numpy: {}".
format(pyBigWig.__file__))
exit(1)
old_chrom = chrom_list[0]
header = []
for i, chrom_ in enumerate(chrom_list):
if old_chrom != chrom_:
header.append((toString(old_chrom), end_list[i - 1]))
old_chrom = chrom_
header.append((toString(chrom_list[-1]), end_list[-1]))
for idx, outfile in enumerate(args.outputFileName):
log.debug("bigwig: len(vecs_list) {}".format(len(vecs_list)))
log.debug("bigwig: len(chrom_list) {}".format(len(chrom_list)))
assert (len(vecs_list) == len(chrom_list))
chrom_list_ = []
start_list_ = []
end_list_ = []
values = []
bw = pyBigWig.open(outfile, 'w')
# set big wig header
bw.addHeader(header)
# create entry lists
for i, value in enumerate(vecs_list):
# it can happen that some 'value' is having less dimensions than it should
if len(value) == args.numberOfEigenvectors:
if isinstance(value[idx], np.complex):
value[idx] = value[idx].real
values.append(value[idx])
chrom_list_.append(toString(chrom_list[i]))
start_list_.append(start_list[i])
end_list_.append(end_list[i])
# write entries
bw.addEntries(chrom_list_,
start_list_,
ends=end_list_,
values=values)
bw.close()
else:
log.error("Output format not known: {}".format(args.format))
exit(1)