def merge_tad_bins(hic, boundary_id_list, filename):
"""
Reduces the HiCMatrix by merging the counts of tad bins.
:param hic: HiCMatrix object
:param boundary_id_list list of tad boundary bin ids
:param filename Name to save the resulting matrix
:return: HiCMatrix object
"""
from hicexplorer.reduceMatrix import reduce_matrix
hic.restoreMaskedBins()
ref_name_list, start_list, end_list, coverage_list = zip(
*hic.cut_intervals)
new_bins = []
bins_to_merge = []
prev_ref = ref_name_list[0]
# prepare new intervals
idx_start = 0
new_start = start_list[0]
count = 0
for idx, ref in enumerate(ref_name_list):
if (count > 0 and idx in boundary_id_list) or ref != prev_ref:
coverage = np.mean(coverage_list[idx_start:idx])
new_bins.append((ref_name_list[idx_start], new_start,
end_list[idx - 1], coverage))
bins_to_merge.append(list(range(idx_start, idx)))
idx_start = idx
new_start = start_list[idx]
count = 0
prev_ref = ref
count += 1
# check that the previous for loop ran, otherwise
# some variables may not be set
if len(bins_to_merge) > 0:
coverage = np.mean(coverage_list[idx_start:])
new_bins.append((ref, new_start, end_list[idx], coverage))
bins_to_merge.append(list(range(idx_start, idx + 1)))
# remove correction factors otherwise they are
# saved but they no longer correspond to the
# size of the matrix.
hic.correction_factors = None
hic.update_matrix(
reduce_matrix(hic.matrix, bins_to_merge, diagonal=True), new_bins)
hic.save(filename)
else:
log.info("Nothing to merge.")
def merge_bins(hic, num_bins):
"""
Merge the bins using the specified number of bins. This
functions takes care to make new intervals
Parameters
----------
hic : HiCMatrix object
num_bins : number of consecutive bins to merge.
Returns
-------
A sparse matrix.
Set up a Hi-C test matrix
>>> from scipy.sparse import csr_matrix
>>> row, col = np.triu_indices(5)
>>> cut_intervals = [('a', 0, 10, 0.5), ('a', 10, 20, 1),
... ('a', 20, 30, 1), ('a', 30, 40, 0.1), ('b', 40, 50, 1)]
>>> hic = hm.hiCMatrix()
>>> hic.nan_bins = []
>>> matrix = np.array([
... [ 50, 10, 5, 3, 0],
... [ 0, 60, 15, 5, 1],
... [ 0, 0, 80, 7, 3],
... [ 0, 0, 0, 90, 1],
... [ 0, 0, 0, 0, 100]], dtype=np.int32)
make the matrix symmetric:
>>> from scipy.sparse import dia_matrix
>>> dia = dia_matrix(([matrix.diagonal()], [0]), shape=matrix.shape)
>>> hic.matrix = csr_matrix(matrix + matrix.T - dia)
>>> hic.setMatrix(hic.matrix, cut_intervals)
run merge_matrix
>>> merge_matrix = merge_bins(hic, 2)
>>> merge_matrix.cut_intervals
[('a', 0, 20, 0.75), ('a', 20, 40, 0.55000000000000004), ('b', 40, 50, 1.0)]
>>> merge_matrix.matrix.todense()
matrix([[120, 28, 1],
[ 28, 177, 4],
[ 1, 4, 100]], dtype=int32)
"""
hic = remove_nans_if_needed(hic)
# get the bins to merge
ref_name_list, start_list, end_list, coverage_list = zip(
*hic.cut_intervals)
new_bins = []
bins_to_merge = []
prev_ref = ref_name_list[0]
# prepare new intervals
idx_start = 0
new_start = start_list[0]
count = 0
for idx, ref in enumerate(ref_name_list):
if (count > 0 and count % num_bins == 0) or ref != prev_ref:
if count < num_bins / 2:
log.debug("{} has few bins ({}). Skipping it\n".format(
prev_ref, count))
else:
coverage = np.mean(coverage_list[idx_start:idx])
new_bins.append((ref_name_list[idx_start], new_start,
end_list[idx - 1], coverage))
bins_to_merge.append(list(range(idx_start, idx)))
idx_start = idx
new_start = start_list[idx]
count = 0
prev_ref = ref
count += 1
coverage = np.mean(coverage_list[idx_start:])
new_bins.append((ref, new_start, end_list[idx], coverage))
bins_to_merge.append(list(range(idx_start, idx + 1)))
hic.matrix = reduce_matrix(hic.matrix, bins_to_merge, diagonal=True)
hic.matrix.eliminate_zeros()
hic.setCutIntervals(new_bins)
hic.nan_bins = np.flatnonzero(hic.matrix.sum(0).A == 0)
return hic
