def getRegion(args, ma):
chrom = region_start = region_end = idx1 = start_pos1 = chrom2 = region_start2 = region_end2 = idx2 = start_pos2 = None
chrom, region_start, region_end = translate_region(args.region)
if type(next(iter(ma.interval_trees))) in [np.bytes_, bytes]:
chrom = toBytes(chrom)
if chrom not in list(ma.interval_trees):
if type(next(iter(ma.interval_trees))) in [np.bytes_, bytes]:
chrom = toBytes(chrom)
if chrom not in list(ma.interval_trees):
exit(
"The contig/scaffold name '{}' given in --region is not part of the Hi-C matrix. "
"Check spelling".format(chrom))
args.region = [chrom, region_start, region_end]
idx1, start_pos1 = zip(
*[(idx, x[1]) for idx, x in enumerate(ma.cut_intervals)
if x[0] == chrom and x[1] >= region_start and x[2] < region_end])
idx2 = idx1
chrom2 = chrom
start_pos2 = start_pos1
return chrom, region_start, region_end, idx1, start_pos1, chrom2, region_start2, region_end2, idx2, start_pos2
def main(args=None):
args = parse_arguments().parse_args(args)
if args.title:
args.title = remove_non_ascii(args.title)
chrom = None
start_pos1 = None
chrom2 = None
start_pos2 = None
if args.perChromosome and args.region:
log.error('ERROR, choose from the option '
'--perChromosome or --region, the two '
'options at the same time are not '
'compatible.')
exit(1)
# if args.region and args.region2 and args.bigwig:
# log.error("Inter-chromosomal pca is not supported.")
# exit(1)
# is_cooler = False
# if args.matrix.endswith('.cool') or cooler.io.is_cooler(args.matrix) or'.mcool' in args.matrix:
is_cooler = check_cooler(args.matrix)
log.debug("Cooler or no cooler: {}".format(is_cooler))
open_cooler_chromosome_order = True
if args.chromosomeOrder is not None and len(args.chromosomeOrder) > 1:
open_cooler_chromosome_order = False
if is_cooler and not args.region2 and open_cooler_chromosome_order:
log.debug("Retrieve data from cooler format and use its benefits.")
regionsToRetrieve = None
if args.region:
regionsToRetrieve = []
regionsToRetrieve.append(args.region)
# if args.region2:
# chrom2, region_start2, region_end2 = translate_region(args.region2)
# regionsToRetrieve.append(args.region2)
if args.chromosomeOrder:
args.region = None
args.region2 = None
regionsToRetrieve = args.chromosomeOrder
ma = HiCMatrix.hiCMatrix(args.matrix, pChrnameList=regionsToRetrieve)
log.debug('Shape {}'.format(ma.matrix.shape))
if args.clearMaskedBins:
ma.maskBins(ma.nan_bins)
# to avoid gaps in the plot, bins flanking the masked bins
# are enlarged
new_intervals = enlarge_bins(ma.cut_intervals)
ma.setCutIntervals(new_intervals)
if args.region:
chrom, region_start, region_end, idx1, start_pos1, chrom2, region_start2, region_end2, idx2, start_pos2 = getRegion(args, ma)
matrix = np.asarray(ma.matrix.todense().astype(float))
matrix_length = len(matrix[0])
log.debug("Number of data points matrix_cool: {}".format(matrix_length))
else:
ma = HiCMatrix.hiCMatrix(args.matrix)
if args.clearMaskedBins:
ma.maskBins(ma.nan_bins)
new_intervals = enlarge_bins(ma.cut_intervals)
ma.setCutIntervals(new_intervals)
if args.chromosomeOrder:
args.region = None
args.region2 = None
valid_chromosomes = []
invalid_chromosomes = []
log.debug('args.chromosomeOrder: {}'.format(args.chromosomeOrder))
log.debug("ma.chrBinBoundaries {}".format(ma.chrBinBoundaries))
if sys.version_info[0] == 3:
args.chromosomeOrder = toBytes(args.chromosomeOrder)
for chrom in toString(args.chromosomeOrder):
if chrom in ma.chrBinBoundaries:
valid_chromosomes.append(chrom)
else:
invalid_chromosomes.append(chrom)
if len(invalid_chromosomes) > 0:
log.warning("WARNING: The following chromosome/scaffold names were not found. Please check"
"the correct spelling of the chromosome names. \n")
log.warning("\n".join(invalid_chromosomes))
ma.reorderChromosomes(valid_chromosomes)
log.info("min: {}, max: {}\n".format(ma.matrix.data.min(), ma.matrix.data.max()))
if args.region:
chrom, region_start, region_end, idx1, start_pos1, chrom2, region_start2, region_end2, idx2, start_pos2 = getRegion(args, ma)
matrix = np.asarray(ma.matrix[idx1, :][:, idx2].todense().astype(float))
else:
log.debug("Else branch")
matrix = np.asarray(ma.getMatrix().astype(float))
matrix_length = len(matrix[0])
log.debug("Number of data points matrix: {}".format(matrix_length))
for matrix_ in matrix:
if not matrix_length == len(matrix_):
log.error("Matrices do not have the same length: {} , {}".format(matrix_length, len(matrix_)))
cmap = cm.get_cmap(args.colorMap)
log.debug("Nan values set to black\n")
cmap.set_bad('black')
bigwig_info = None
if args.bigwig:
bigwig_info = {'args': args, 'axis': None, 'axis_colorbar': None, 'nan_bins': ma.nan_bins}
if args.perChromosome:
fig = plotPerChr(ma, cmap, args, pBigwig=bigwig_info)
else:
norm = None
if args.log or args.log1p:
mask = matrix == 0
matrix[mask] = np.nanmin(matrix[mask == False])
if np.isnan(matrix).any() or np.isinf(matrix).any():
log.debug("any nan {}".format(np.isnan(matrix).any()))
log.debug("any inf {}".format(np.isinf(matrix).any()))
mask_nan = np.isnan(matrix)
mask_inf = np.isinf(matrix)
matrix[mask_nan] = np.nanmin(matrix[mask_nan == False])
matrix[mask_inf] = np.nanmin(matrix[mask_inf == False])
log.debug("any nan after remove of nan: {}".format(np.isnan(matrix).any()))
log.debug("any inf after remove of inf: {}".format(np.isinf(matrix).any()))
if args.log1p:
matrix += 1
norm = LogNorm()
elif args.log:
norm = LogNorm()
if args.bigwig:
# increase figure height to accommodate bigwig track
fig_height = 8.5
else:
fig_height = 7
height = 4.8 / fig_height
fig_width = 8
width = 5.0 / fig_width
left_margin = (1.0 - width) * 0.5
fig = plt.figure(figsize=(fig_width, fig_height), dpi=args.dpi)
if args.bigwig:
gs = gridspec.GridSpec(2, 2, height_ratios=[0.90, 0.1], width_ratios=[0.97, 0.03])
gs.update(hspace=0.05, wspace=0.05)
ax1 = plt.subplot(gs[0, 0])
ax2 = plt.subplot(gs[1, 0])
ax3 = plt.subplot(gs[0, 1])
bigwig_info['axis'] = ax2
bigwig_info['axis_colorbar'] = ax3
else:
ax1 = None
bottom = 1.3 / fig_height
if start_pos1 is None:
start_pos1 = make_start_pos_array(ma)
position = [left_margin, bottom, width, height]
plotHeatmap(matrix, ma.get_chromosome_sizes(), fig, position,
args, cmap, xlabel=chrom, ylabel=chrom2,
start_pos=start_pos1, start_pos2=start_pos2, pNorm=norm, pAxis=ax1, pBigwig=bigwig_info)
if not args.disable_tight_layout:
if args.perChromosome or args.bigwig:
try:
plt.tight_layout()
except UserWarning:
log.info("Failed to tight layout. Using regular plot.")
except ValueError:
log.info("Failed to tight layout. Using regular plot.")
plt.savefig(args.outFileName, dpi=args.dpi)
plt.close(fig)
def main(args=None):
args = parse_arguments().parse_args(args)
chrom = None
start_pos1 = None
chrom2 = None
start_pos2 = None
if args.perChromosome and args.region:
log.error('ERROR, choose from the option '
'--perChromosome or --region, the two '
'options at the same time are not '
'compatible.')
exit(1)
if args.region and args.region2 and args.pca:
log.error("Inter-chromosomal pca is not supported.")
exit(1)
is_cooler = False
if args.matrix.endswith('.cool') or cooler.io.is_cooler(args.matrix):
is_cooler = True
if is_cooler and not args.region2:
log.debug("Retrieve data from cooler format and use its benefits.")
regionsToRetrieve = None
if args.region:
regionsToRetrieve = []
regionsToRetrieve.append(args.region)
if args.region2:
chrom2, region_start2, region_end2 = translate_region(
args.region2)
regionsToRetrieve.append(args.region2)
if args.chromosomeOrder:
args.region = None
args.region2 = None
regionsToRetrieve = args.chromosomeOrder
ma = HiCMatrix.hiCMatrix(args.matrix, chrnameList=regionsToRetrieve)
if args.clearMaskedBins:
ma.maskBins(ma.nan_bins)
if args.region:
chrom, region_start, region_end, idx1, start_pos1, chrom2, region_start2, region_end2, idx2, start_pos2 = getRegion(
args, ma)
matrix = np.asarray(ma.matrix.todense().astype(float))
else:
ma = HiCMatrix.hiCMatrix(args.matrix)
if args.clearMaskedBins:
ma.maskBins(ma.nan_bins)
if args.chromosomeOrder:
args.region = None
args.region2 = None
valid_chromosomes = []
invalid_chromosomes = []
log.debug('args.chromosomeOrder: {}'.format(args.chromosomeOrder))
log.debug("ma.chrBinBoundaries {}".format(ma.chrBinBoundaries))
if sys.version_info[0] == 3:
args.chromosomeOrder = toBytes(args.chromosomeOrder)
for chrom in args.chromosomeOrder:
if chrom in ma.chrBinBoundaries:
valid_chromosomes.append(chrom)
else:
invalid_chromosomes.append(chrom)
if len(invalid_chromosomes) > 0:
log.warning(
"WARNING: The following chromosome/scaffold names were not found. Please check"
"the correct spelling of the chromosome names. \n")
log.warning("\n".join(invalid_chromosomes))
ma.reorderChromosomes(valid_chromosomes)
log.info("min: {}, max: {}\n".format(ma.matrix.data.min(),
ma.matrix.data.max()))
if args.region:
chrom, region_start, region_end, idx1, start_pos1, chrom2, region_start2, region_end2, idx2, start_pos2 = getRegion(
args, ma)
matrix = np.asarray(
ma.matrix[idx1, :][:, idx2].todense().astype(float))
else:
log.debug("Else branch")
matrix = np.asarray(ma.getMatrix().astype(float))
matrix_length = len(matrix[0])
for matrix_ in matrix:
if not matrix_length == len(matrix_):
log.error("Matrices do not have the same length: {} , {}".format(
matrix_length, len(matrix_)))
cmap = cm.get_cmap(args.colorMap)
log.debug("Nan values set to black\n")
cmap.set_bad('black')
pca = None
if args.pca:
pca = {
'args': args,
'axis': None,
'axis_colorbar': None,
'nan_bins': ma.nan_bins
}
if args.perChromosome:
fig = plotPerChr(ma, cmap, args, pPca=pca)
else:
norm = None
if args.log or args.log1p:
mask = matrix == 0
matrix[mask] = np.nanmin(matrix[mask == False])
if np.isnan(matrix).any() or np.isinf(matrix).any():
log.debug("any nan {}".format(np.isnan(matrix).any()))
log.debug("any inf {}".format(np.isinf(matrix).any()))
mask_nan = np.isnan(matrix)
mask_inf = np.isinf(matrix)
matrix[mask_nan] = np.nanmin(matrix[mask_nan == False])
matrix[mask_inf] = np.nanmin(matrix[mask_inf == False])
if args.log:
matrix = np.log(matrix)
log.debug("any nan after remove of nan: {}".format(
np.isnan(matrix).any()))
log.debug("any inf after remove of inf: {}".format(
np.isinf(matrix).any()))
if args.log1p:
matrix += 1
norm = LogNorm()
fig_height = 7
height = 4.8 / fig_height
fig_width = 8
width = 5.0 / fig_width
left_margin = (1.0 - width) * 0.5
fig = plt.figure(figsize=(fig_width, fig_height), dpi=args.dpi)
if args.pca:
gs = gridspec.GridSpec(2,
2,
height_ratios=[0.85, 0.15],
width_ratios=[0.93, 0.07])
gs.update(hspace=0.1)
ax1 = plt.subplot(gs[0, 0])
ax2 = plt.subplot(gs[1, 0])
ax3 = plt.subplot(gs[0, 1])
pca['axis'] = ax2
pca['axis_colorbar'] = ax3
else:
ax1 = None
bottom = 1.3 / fig_height
position = [left_margin, bottom, width, height]
plotHeatmap(matrix,
ma.chrBinBoundaries,
fig,
position,
args,
cmap,
xlabel=chrom,
ylabel=chrom2,
start_pos=start_pos1,
start_pos2=start_pos2,
pNorm=norm,
pAxis=ax1,
pPca=pca)
if args.perChromosome or args.pca:
plt.tight_layout()
plt.savefig(args.outFileName, dpi=args.dpi)
plt.close(fig)
def getRegion(args, ma):
chrom = region_start = region_end = idx1 = start_pos1 = chrom2 = region_start2 = region_end2 = idx2 = start_pos2 = None
chrom, region_start, region_end = translate_region(args.region)
if type(next(iter(ma.interval_trees))) in [np.bytes_, bytes]:
chrom = toBytes(chrom)
if chrom not in list(ma.interval_trees):
chrom = change_chrom_names(chrom)
if type(next(iter(ma.interval_trees))) in [np.bytes_, bytes]:
chrom = toBytes(chrom)
if chrom not in list(ma.interval_trees):
exit("Chromosome name {} in --region not in matrix".format(
change_chrom_names(chrom)))
args.region = [chrom, region_start, region_end]
is_cooler = False
if args.matrix.endswith('.cool') or cooler.io.is_cooler(args.matrix):
is_cooler = True
if is_cooler:
idx1, start_pos1 = zip(
*[(idx, x[1]) for idx, x in enumerate(ma.cut_intervals)
if x[0] == chrom and
((x[1] >= region_start and x[2] < region_end) or
(x[1] < region_end and x[2] < region_end and x[2] > region_start
) or (x[1] > region_start and x[1] < region_end))])
else:
idx1, start_pos1 = zip(
*[(idx, x[1]) for idx, x in enumerate(ma.cut_intervals)
if x[0] == chrom and x[1] >= region_start and x[2] < region_end])
if args.region2:
chrom2, region_start2, region_end2 = translate_region(args.region2)
if type(next(iter(ma.interval_trees))) in [np.bytes_, bytes]:
chrom2 = toBytes(chrom)
if chrom2 not in list(ma.interval_trees):
chrom2 = change_chrom_names(chrom2)
if type(next(iter(ma.interval_trees))) in [np.bytes_, bytes]:
chrom2 = toBytes(chrom)
if chrom2 not in list(ma.interval_trees):
exit("Chromosome name {} in --region2 not in matrix".format(
change_chrom_names(chrom2)))
if is_cooler:
idx2, start_pos2 = zip(
*[(idx, x[1]) for idx, x in enumerate(ma.cut_intervals)
if x[0] == chrom2 and (
(x[1] >= region_start2 and x[2] < region_end2) or
(x[1] < region_end2 and x[2] < region_end2
and x[2] > region_start2) or
(x[1] > region_start2 and x[1] < region_end2))])
else:
idx2, start_pos2 = zip(
*[(idx, x[1]) for idx, x in enumerate(ma.cut_intervals)
if x[0] == chrom2 and x[1] >= region_start2
and x[2] < region_end2])
else:
idx2 = idx1
chrom2 = chrom
start_pos2 = start_pos1
return chrom, region_start, region_end, idx1, start_pos1, chrom2, region_start2, region_end2, idx2, start_pos2