def process_TAD(hic_data, perc_zero, reso, cpus, outdir, bins):
# Get poor bins
print 'Get poor bins...'
try:
hic_data.filter_columns(perc_zero=perc_zero, by_mean=True)
except ValueError:
perc_zero = 100
hic_data.filter_columns(perc_zero=perc_zero, by_mean=True)
binsrev = {y:x for x,y in bins.iteritems()}
bad_file = outdir + 'bad_rows_%s_%d.tsv' % (nice(reso), perc_zero)
bads = [binsrev[i][0] + "\t" + str(binsrev[i][1] * reso) + "\t" + str(i) for i in hic_data.bads.keys()]
compress(bads, bad_file)
# Identify biases
print 'Get biases using ICE...'
hic_data.normalize_hic(silent=False, max_dev=0.1, iterations=0,
factor=1) # cells of the matrix have a mean of 1
bias_file = outdir + 'bias_%s.tsv' % nice(reso)
bias = [binsrev[i][0] + "\t" + str(binsrev[i][1] * reso) + "\t" + '%d\t%f' % (i, hic_data.bias[i]) for i in hic_data.bias]
compress(bias, bias_file)
# percentage of cis interactions
print 'Getting percentage of cis interactions...'
cis_trans_N_D = hic_data.cis_trans_ratio(normalized=True , diagonal=True )
cis_trans_n_D = hic_data.cis_trans_ratio(normalized=False, diagonal=True )
cis_trans_N_d = hic_data.cis_trans_ratio(normalized=True , diagonal=False)
cis_trans_n_d = hic_data.cis_trans_ratio(normalized=False, diagonal=False)
cistrans_file = outdir + 'cis_trans_ratio_%s.tsv' % nice(reso)
out_cistrans = open(cistrans_file, "w")
out_cistrans.write("Cis/trans_ratio\tnormalized\twith_diagonal\t" + str(cis_trans_N_D) + "\n")
out_cistrans.write("Cis/trans_ratio\tnormalized\twithout_diagonal\t" + str(cis_trans_N_d) + "\n")
out_cistrans.write("Cis/trans_ratio\traw\twith_diagonal\t" + str(cis_trans_n_D) + "\n")
out_cistrans.write("Cis/trans_ratio\traw\twithout_diagonal\t" + str(cis_trans_n_d) + "\n")
out_cistrans.close()
# Compute expected
print 'Get expected counts ...'
hic_data.expected = expected(hic_data, bads = hic_data.bads)
# store matrices
print 'Store matrices'
write_matrices(hic_data, outdir, reso)
# getting TAD borders
print 'Searching TADs'
for crm in hic_data.chromosomes:
print ' - %s' % crm
matrix = hic_data.get_matrix(focus=crm)
beg, end = hic_data.section_pos[crm]
size = len(matrix)
if size < 10:
print " Chromosome too short (%d bins), skipping..." % size
continue
# transform bad column in chromosome referential
remove = tuple([1 if i in hic_data.bads else 0 for i in xrange(beg, end)])
# maximum size of a TAD
max_tad_size = size
result = tadbit([matrix], remove=remove,
n_cpus=cpus, verbose=False,
max_tad_size=max_tad_size,
no_heuristic=0)
tads = load_tad_height(result, size, beg, end, hic_data)
table = ''
table += '%s\t%s\t%s\t%s%s\n' % ('#', 'start', 'end', 'score', 'density')
for tad in tads:
table += '%s\t%s\t%s\t%s%s\n' % (
tad, int(tads[tad]['start'] + 1), int(tads[tad]['end'] + 1),
abs(tads[tad]['score']), '\t%s' % (round(
float(tads[tad]['height']), 3)))
out_tad = outdir + 'tads_%s_%s.tsv' % (
crm, nice(reso))
out = open(out_tad, 'w')
out.write(table)
out.close()
def find_compartments(self, crms=None, savefig=None, savedata=None,
show=False, **kwargs):
"""
Search for A/B copartments in each chromsome of the Hi-C matrix.
Hi-C matrix is normalized by the number interaction expected at a given
distance, and by visibility (one iteration of ICE). A correlation matrix
is then calculated from this normalized matrix, and its first
eigenvector is used to identify compartments. Changes in sign marking
boundaries between compartments.
Result is stored as a dictionary of compartment boundaries, keys being
chromsome names.
:param 99 perc_zero: to filter bad columns
:param 0.05 signal_to_noise: to calculate expected interaction counts,
if not enough reads are observed at a given distance the observations
of the distance+1 are summed. a signal to noise ratio of < 0.05
corresponds to > 400 reads.
:param None crms: only runs these given list of chromosomes
:param None savefig: path to a directory to store matrices with
compartment predictions, one image per chromosome, stored under
'chromosome-name.png'.
:param False show: show the plot
:param None savedata: path to a new file to store compartment
predictions, one file only.
:param -1 vmin: for the color scale of the plotted map
:param 1 vmax: for the color scale of the plotted map
TODO: this is really slow...
Notes: building the distance matrix using the amount of interactions
instead of the mean correlation, gives generally worse results.
"""
if not self.bads:
if kwargs.get('verbose', True):
print 'Filtering bad columns %d' % 99
self.filter_columns(perc_zero=kwargs.get('perc_zero', 99),
by_mean=False, silent=True)
if not self.expected:
if kwargs.get('verbose', True):
print 'Normalizing by expected values'
self.expected = expected(self, bads=self.bads, **kwargs)
if not self.bias:
if kwargs.get('verbose', True):
print 'Normalizing by ICE (1 round)'
self.normalize_hic(iterations=0)
if savefig:
mkdir(savefig)
cmprts = {}
for sec in self.section_pos:
if crms and sec not in crms:
continue
if kwargs.get('verbose', False):
print 'Processing chromosome', sec
warn('Processing chromosome %s' % (sec))
matrix = [[(float(self[i,j]) / self.expected[abs(j-i)]
/ self.bias[i] / self.bias[j])
for i in xrange(*self.section_pos[sec])
if not i in self.bads]
for j in xrange(*self.section_pos[sec])
if not j in self.bads]
if not matrix: # MT chromosome will fall there
warn('Chromosome %s is probably MT :)' % (sec))
cmprts[sec] = []
continue
for i in xrange(len(matrix)):
for j in xrange(i+1, len(matrix)):
matrix[i][j] = matrix[j][i]
matrix = [list(m) for m in corrcoef(matrix)]
try:
# This eighs is very very fast, only ask for one eigvector
_, evect = eigsh(array(matrix), k=1)
except LinAlgError:
warn('Chromosome %s too small to compute PC1' % (sec))
cmprts[sec] = [] # Y chromosome, or so...
continue
first = list(evect[:, -1])
beg, end = self.section_pos[sec]
bads = [k - beg for k in self.bads if beg <= k <= end]
_ = [first.insert(b, 0) for b in bads]
_ = [matrix.insert(b, [float('nan')] * len(matrix[0]))
for b in bads]
_ = [matrix[i].insert(b, float('nan'))
for b in bads for i in xrange(len(first))]
breaks = [0] + [i for i, (a, b) in
enumerate(zip(first[1:], first[:-1]))
if a * b < 0] + [len(first)]
breaks = [{'start': b, 'end': breaks[i+1]}
for i, b in enumerate(breaks[: -1])]
cmprts[sec] = breaks
# calculate compartment internal density
for k, cmprt in enumerate(cmprts[sec]):
beg = self.section_pos[sec][0]
beg1, end1 = cmprt['start'] + beg, cmprt['end'] + beg
sec_matrix = [(self[i,j] / self.expected[abs(j-i)]
/ self.bias[i] / self.bias[j])
for i in xrange(beg1, end1) if not i in self.bads
for j in xrange(i, end1) if not j in self.bads]
try:
cmprt['dens'] = sum(sec_matrix) / len(sec_matrix)
except ZeroDivisionError:
cmprt['dens'] = 0.
try:
meanh = sum([cmprt['dens'] for cmprt in cmprts[sec]]) / len(cmprts[sec])
except ZeroDivisionError:
meanh = 1.
for cmprt in cmprts[sec]:
try:
cmprt['dens'] /= meanh
except ZeroDivisionError:
cmprt['dens'] = 1.
gammas = {}
for gamma in range(101):
gammas[gamma] = _find_ab_compartments(float(gamma)/100, matrix,
breaks, cmprts[sec],
save=False)
# print gamma, gammas[gamma]
gamma = min(gammas.keys(), key=lambda k: gammas[k][0])
_ = _find_ab_compartments(float(gamma)/100, matrix, breaks,
cmprts[sec], save=True)
if savefig or show:
vmin = kwargs.get('vmin', -1)
vmax = kwargs.get('vmax', 1)
if vmin == 'auto' == vmax:
vmax = max([abs(npmin(matrix)), abs(npmax(matrix))])
vmin = -vmax
plot_compartments(sec, first, cmprts, matrix, show,
savefig + '/chr' + sec + '.pdf',
vmin=vmin, vmax=vmax)
plot_compartments_summary(sec, cmprts, show,
savefig + '/chr' + sec + '_summ.pdf')
self.compartments = cmprts
if savedata:
self.write_compartments(savedata)
def process_AB(hic_data, perc_zero, reso, outdir, bins):
# Get poor bins
print 'Get poor bins...'
try:
hic_data.filter_columns(perc_zero=perc_zero, by_mean=True)
except ValueError:
perc_zero = 100
hic_data.filter_columns(perc_zero=perc_zero, by_mean=True)
binsrev = {y:x for x,y in bins.iteritems()}
bad_file = outdir + 'bad_rows_%s_%d.tsv' % (nice(reso), perc_zero)
bads = [binsrev[i][0] + "\t" + str(binsrev[i][1] * reso) + "\t" + str(i)
for i in hic_data.bads.keys()]
compress(bads, bad_file)
# Identify biases
print 'Get biases using ICE...'
hic_data.normalize_hic(silent=False, max_dev=0.1, iterations=0,
factor=1) # cells of the matrix have a mean of 1
bias_file = outdir + 'bias_%s.tsv' % nice(reso)
bias = [binsrev[i][0] + "\t" + str(binsrev[i][1] * reso) + "\t" + '%d\t%f' % (i, hic_data.bias[i])
for i in hic_data.bias]
compress(bias, bias_file)
# percentage of cis interactions
print 'Getting percentage of cis interactions...'
cis_trans_N_D = hic_data.cis_trans_ratio(normalized=True , diagonal=True )
cis_trans_n_D = hic_data.cis_trans_ratio(normalized=False, diagonal=True )
cis_trans_N_d = hic_data.cis_trans_ratio(normalized=True , diagonal=False)
cis_trans_n_d = hic_data.cis_trans_ratio(normalized=False, diagonal=False)
cistrans_file = outdir + 'cis_trans_ratio_%s.tsv' % nice(reso)
out_cistrans = open(cistrans_file, "w")
out_cistrans.write("Cis/trans_ratio\tnormalized\twith_diagonal\t" + str(cis_trans_N_D) + "\n")
out_cistrans.write("Cis/trans_ratio\tnormalized\twithout_diagonal\t" + str(cis_trans_N_d) + "\n")
out_cistrans.write("Cis/trans_ratio\traw\twith_diagonal\t" + str(cis_trans_n_D) + "\n")
out_cistrans.write("Cis/trans_ratio\traw\twithout_diagonal\t" + str(cis_trans_n_d) + "\n")
out_cistrans.close()
# Compute expected
print 'Get expected counts ...'
hic_data.expected = expected(hic_data, bads = hic_data.bads)
# store matrices
print 'Store matrices'
write_matrices(hic_data, outdir, reso)
# getting compartments
print 'Searching compartments'
ev = hic_data.find_compartments()
ev_file = outdir + 'ev_%s.tsv' % nice(reso)
out = []
chroms = ev.keys()
chroms.sort()
for ch in chroms:
for i in xrange(len(ev[ch][0]) - 1):
out.append("\t".join((ch, str(i * reso), str(ev[ch][0][i]), str(ev[ch][1][i]))))
compress(out, ev_file)
cmprt_file = outdir + 'compartments_%s.tsv' % nice(reso)
hic_data.write_compartments(cmprt_file)
def find_compartments(self,
crms=None,
savefig=None,
savedata=None,
show=False,
**kwargs):
"""
Search for A/B copartments in each chromsome of the Hi-C matrix.
Hi-C matrix is normalized by the number interaction expected at a given
distance, and by visibility (one iteration of ICE). A correlation matrix
is then calculated from this normalized matrix, and its first
eigenvector is used to identify compartments. Changes in sign marking
boundaries between compartments.
Result is stored as a dictionary of compartment boundaries, keys being
chromsome names.
:param 99 perc_zero: to filter bad columns
:param 0.05 signal_to_noise: to calculate expected interaction counts,
if not enough reads are observed at a given distance the observations
of the distance+1 are summed. a signal to noise ratio of < 0.05
corresponds to > 400 reads.
:param None crms: only runs these given list of chromosomes
:param None savefig: path to a directory to store matrices with
compartment predictions, one image per chromosome, stored under
'chromosome-name.png'.
:param False show: show the plot
:param None savedata: path to a new file to store compartment
predictions, one file only.
:param -1 vmin: for the color scale of the plotted map
:param 1 vmax: for the color scale of the plotted map
TODO: this is really slow...
Notes: building the distance matrix using the amount of interactions
instead of the mean correlation, gives generally worse results.
"""
if not self.bads:
if kwargs.get('verbose', True):
print 'Filtering bad columns %d' % 99
self.filter_columns(perc_zero=kwargs.get('perc_zero', 99),
by_mean=False,
silent=True)
if not self.expected:
if kwargs.get('verbose', True):
print 'Normalizing by expected values'
self.expected = expected(self, bads=self.bads, **kwargs)
if not self.bias:
if kwargs.get('verbose', True):
print 'Normalizing by ICE (1 round)'
self.normalize_hic(iterations=0)
if savefig:
mkdir(savefig)
cmprts = {}
for sec in self.section_pos:
if crms and sec not in crms:
continue
if kwargs.get('verbose', False):
print 'Processing chromosome', sec
warn('Processing chromosome %s' % (sec))
matrix = [[(float(self[i, j]) / self.expected[abs(j - i)] /
self.bias[i] / self.bias[j])
for i in xrange(*self.section_pos[sec])
if not i in self.bads]
for j in xrange(*self.section_pos[sec])
if not j in self.bads]
if not matrix: # MT chromosome will fall there
warn('Chromosome %s is probably MT :)' % (sec))
cmprts[sec] = []
continue
for i in xrange(len(matrix)):
for j in xrange(i + 1, len(matrix)):
matrix[i][j] = matrix[j][i]
matrix = [list(m) for m in corrcoef(matrix)]
try:
# This eighs is very very fast, only ask for one eigvector
_, evect = eigsh(array(matrix), k=1)
except LinAlgError:
warn('Chromosome %s too small to compute PC1' % (sec))
cmprts[sec] = [] # Y chromosome, or so...
continue
first = list(evect[:, -1])
beg, end = self.section_pos[sec]
bads = [k - beg for k in self.bads if beg <= k <= end]
_ = [first.insert(b, 0) for b in bads]
_ = [
matrix.insert(b, [float('nan')] * len(matrix[0])) for b in bads
]
_ = [
matrix[i].insert(b, float('nan')) for b in bads
for i in xrange(len(first))
]
breaks = [0] + [
i for i, (a, b) in enumerate(zip(first[1:], first[:-1]))
if a * b < 0
] + [len(first)]
breaks = [{
'start': b,
'end': breaks[i + 1]
} for i, b in enumerate(breaks[:-1])]
cmprts[sec] = breaks
# calculate compartment internal density
for k, cmprt in enumerate(cmprts[sec]):
beg = self.section_pos[sec][0]
beg1, end1 = cmprt['start'] + beg, cmprt['end'] + beg
sec_matrix = [(self[i, j] / self.expected[abs(j - i)] /
self.bias[i] / self.bias[j])
for i in xrange(beg1, end1) if not i in self.bads
for j in xrange(i, end1) if not j in self.bads]
try:
cmprt['dens'] = sum(sec_matrix) / len(sec_matrix)
except ZeroDivisionError:
cmprt['dens'] = 0.
try:
meanh = sum([cmprt['dens']
for cmprt in cmprts[sec]]) / len(cmprts[sec])
except ZeroDivisionError:
meanh = 1.
for cmprt in cmprts[sec]:
try:
cmprt['dens'] /= meanh
except ZeroDivisionError:
cmprt['dens'] = 1.
gammas = {}
for gamma in range(101):
gammas[gamma] = _find_ab_compartments(float(gamma) / 100,
matrix,
breaks,
cmprts[sec],
save=False)
# print gamma, gammas[gamma]
gamma = min(gammas.keys(), key=lambda k: gammas[k][0])
_ = _find_ab_compartments(float(gamma) / 100,
matrix,
breaks,
cmprts[sec],
save=True)
if savefig or show:
vmin = kwargs.get('vmin', -1)
vmax = kwargs.get('vmax', 1)
if vmin == 'auto' == vmax:
vmax = max([abs(npmin(matrix)), abs(npmax(matrix))])
vmin = -vmax
plot_compartments(sec,
first,
cmprts,
matrix,
show,
savefig + '/chr' + sec + '.pdf',
vmin=vmin,
vmax=vmax)
plot_compartments_summary(sec, cmprts, show,
savefig + '/chr' + sec + '_summ.pdf')
self.compartments = cmprts
if savedata:
self.write_compartments(savedata)
