def main(args=None):
args = process_args(args)
hm = heatmapper.heatmapper()
matrix_file = args.matrixFile.name
args.matrixFile.close()
hm.read_matrix_file(matrix_file)
if hm.parameters['min threshold'] is not None or hm.parameters[
'max threshold'] is not None:
filterHeatmapValues(hm, hm.parameters['min threshold'],
hm.parameters['max threshold'])
if args.sortRegions == 'keep':
args.sortRegions = 'no' # These are the same thing
if args.kmeans is not None:
hm.matrix.hmcluster(args.kmeans,
method='kmeans',
clustering_samples=args.clusterUsingSamples)
elif args.hclust is not None:
print("Performing hierarchical clustering."
"Please note that it might be very slow for large datasets.\n")
hm.matrix.hmcluster(args.hclust,
method='hierarchical',
clustering_samples=args.clusterUsingSamples)
group_len_ratio = np.diff(hm.matrix.group_boundaries) / len(
hm.matrix.regions)
if np.any(group_len_ratio < 5.0 / 1000):
problem = np.flatnonzero(group_len_ratio < 5.0 / 1000)
sys.stderr.write(
"WARNING: Group '{}' is too small for plotting, you might want to remove it. "
"There will likely be an error message from matplotlib regarding this "
"below.\n".format(hm.matrix.group_labels[problem[0]]))
if args.regionsLabel:
hm.matrix.set_group_labels(args.regionsLabel)
if args.samplesLabel and len(args.samplesLabel):
hm.matrix.set_sample_labels(args.samplesLabel)
if args.sortRegions != 'no':
sortUsingSamples = []
if args.sortUsingSamples is not None:
for i in args.sortUsingSamples:
if (i > 0 and i <= hm.matrix.get_num_samples()):
sortUsingSamples.append(i - 1)
else:
exit(
"The value {0} for --sortSamples is not valid. Only values from 1 to {1} are allowed."
.format(args.sortUsingSamples,
hm.matrix.get_num_samples()))
print('Samples used for ordering within each group: ',
sortUsingSamples)
hm.matrix.sort_groups(sort_using=args.sortUsing,
sort_method=args.sortRegions,
sample_list=sortUsingSamples)
if args.silhouette:
if args.kmeans is not None:
hm.matrix.computeSilhouette(args.kmeans)
elif args.hclust is not None:
hm.matrix.computeSilhouette(args.args.hclust)
if args.outFileNameMatrix:
hm.save_matrix_values(args.outFileNameMatrix)
if args.outFileSortedRegions:
hm.save_BED(args.outFileSortedRegions)
colormap_dict = {
'colorMap': args.colorMap,
'colorList': args.colorList,
'colorNumber': args.colorNumber,
'missingDataColor': args.missingDataColor,
'alpha': args.alpha
}
plotMatrix(hm,
args.outFileName,
colormap_dict,
args.plotTitle,
args.xAxisLabel,
args.yAxisLabel,
args.regionsLabel,
args.zMin,
args.zMax,
args.yMin,
args.yMax,
args.averageTypeSummaryPlot,
args.refPointLabel,
args.startLabel,
args.endLabel,
args.heatmapHeight,
args.heatmapWidth,
args.perGroup,
args.whatToShow,
linesAtTickMarks=args.linesAtTickMarks,
plot_type=args.plotType,
image_format=args.plotFileFormat,
legend_location=args.legendLocation,
box_around_heatmaps=args.boxAroundHeatmaps,
label_rotation=args.label_rotation,
dpi=args.dpi,
interpolation_method=args.interpolationMethod)
def main(args=None):
args = process_args(args)
hm = heatmapper.heatmapper()
matrix_file = args.matrixFile.name
args.matrixFile.close()
hm.read_matrix_file(matrix_file)
if hm.parameters['min threshold'] is not None or hm.parameters['max threshold'] is not None:
filterHeatmapValues(hm, hm.parameters['min threshold'], hm.parameters['max threshold'])
if args.kmeans is not None:
hm.matrix.hmcluster(args.kmeans, method='kmeans')
else:
if args.hclust is not None:
print("Performing hierarchical clustering."
"Please note that it might be very slow for large datasets.\n")
hm.matrix.hmcluster(args.hclust, method='hierarchical')
group_len_ratio = np.diff(hm.matrix.group_boundaries) / float(len(hm.matrix.regions))
if np.any(group_len_ratio < 5.0 / 1000):
problem = np.flatnonzero(group_len_ratio < 5.0 / 1000)
sys.stderr.write("WARNING: Group '{}' is too small for plotting, you might want to remove it. \n".format(hm.matrix.group_labels[problem[0]]))
if args.regionsLabel:
hm.matrix.set_group_labels(args.regionsLabel)
if args.samplesLabel and len(args.samplesLabel):
hm.matrix.set_sample_labels(args.samplesLabel)
if args.outFileNameData:
hm.save_tabulated_values(args.outFileNameData, reference_point_label=args.refPointLabel,
start_label=args.startLabel,
end_label=args.endLabel,
averagetype=args.averageType)
if args.outFileSortedRegions:
hm.save_BED(args.outFileSortedRegions)
prof = Profile(hm, args.outFileName,
plot_title=args.plotTitle,
y_axis_label=args.yAxisLabel,
y_min=args.yMin, y_max=args.yMax,
averagetype=args.averageType,
reference_point_label=args.refPointLabel,
start_label=args.startLabel,
end_label=args.endLabel,
plot_height=args.plotHeight,
plot_width=args.plotWidth,
per_group=args.perGroup,
plot_type=args.plotType,
image_format=args.plotFileFormat,
color_list=args.colors,
legend_location=args.legendLocation,
plots_per_row=args.numPlotsPerRow,
label_rotation=args.label_rotation,
dpi=args.dpi)
if args.plotType == 'heatmap':
prof.plot_heatmap()
elif args.plotType == 'overlapped_lines':
prof.plot_hexbin()
else:
prof.plot_profile()
def main(args=None):
args = process_args(args)
hm = heatmapper.heatmapper()
matrix_file = args.matrixFile.name
args.matrixFile.close()
hm.read_matrix_file(matrix_file)
if hm.parameters['min threshold'] is not None or hm.parameters[
'max threshold'] is not None:
filterHeatmapValues(hm, hm.parameters['min threshold'],
hm.parameters['max threshold'])
if args.kmeans is not None:
hm.matrix.hmcluster(args.kmeans, method='kmeans')
else:
if args.hclust is not None:
print(
"Performing hierarchical clustering."
"Please note that it might be very slow for large datasets.\n")
hm.matrix.hmcluster(args.hclust, method='hierarchical')
group_len_ratio = np.diff(hm.matrix.group_boundaries) / float(
len(hm.matrix.regions))
if np.any(group_len_ratio < 5.0 / 1000):
problem = np.flatnonzero(group_len_ratio < 5.0 / 1000)
sys.stderr.write(
"WARNING: Group '{}' is too small for plotting, you might want to remove it. \n"
.format(hm.matrix.group_labels[problem[0]]))
if args.regionsLabel:
hm.matrix.set_group_labels(args.regionsLabel)
if args.samplesLabel and len(args.samplesLabel):
hm.matrix.set_sample_labels(args.samplesLabel)
if args.outFileNameData:
hm.save_tabulated_values(args.outFileNameData,
reference_point_label=args.refPointLabel,
start_label=args.startLabel,
end_label=args.endLabel,
averagetype=args.averageType)
if args.outFileSortedRegions:
hm.save_BED(args.outFileSortedRegions)
prof = Profile(hm,
args.outFileName,
plot_title=args.plotTitle,
y_axis_label=args.yAxisLabel,
y_min=args.yMin,
y_max=args.yMax,
averagetype=args.averageType,
reference_point_label=args.refPointLabel,
start_label=args.startLabel,
end_label=args.endLabel,
plot_height=args.plotHeight,
plot_width=args.plotWidth,
per_group=args.perGroup,
plot_type=args.plotType,
image_format=args.plotFileFormat,
color_list=args.colors,
legend_location=args.legendLocation,
plots_per_row=args.numPlotsPerRow,
label_rotation=args.label_rotation,
dpi=args.dpi)
if args.plotType == 'heatmap':
prof.plot_heatmap()
elif args.plotType == 'overlapped_lines':
prof.plot_hexbin()
else:
prof.plot_profile()
def main(args=None):
args = process_args(args)
hm = heatmapper.heatmapper()
matrix_file = args.matrixFile.name
args.matrixFile.close()
hm.read_matrix_file(matrix_file)
if hm.parameters['min threshold'] is not None or hm.parameters['max threshold'] is not None:
filterHeatmapValues(hm, hm.parameters['min threshold'], hm.parameters['max threshold'])
if args.sortRegions == 'keep':
args.sortRegions = 'no' # These are the same thing
if args.kmeans is not None:
hm.matrix.hmcluster(args.kmeans, method='kmeans')
else:
if args.hclust is not None:
print("Performing hierarchical clustering."
"Please note that it might be very slow for large datasets.\n")
hm.matrix.hmcluster(args.hclust, method='hierarchical')
group_len_ratio = np.diff(hm.matrix.group_boundaries) / len(hm.matrix.regions)
if np.any(group_len_ratio < 5.0 / 1000):
problem = np.flatnonzero(group_len_ratio < 5.0 / 1000)
sys.stderr.write("WARNING: Group '{}' is too small for plotting, you might want to remove it. "
"There will likely be an error message from matplotlib regarding this "
"below.\n".format(hm.matrix.group_labels[problem[0]]))
if args.regionsLabel:
hm.matrix.set_group_labels(args.regionsLabel)
if args.samplesLabel and len(args.samplesLabel):
hm.matrix.set_sample_labels(args.samplesLabel)
if args.sortRegions != 'no':
sortUsingSamples = []
if args.sortUsingSamples is not None:
for i in args.sortUsingSamples:
if (i > 0 and i <= hm.matrix.get_num_samples()):
sortUsingSamples.append(i - 1)
else:
exit("The value {0} for --sortSamples is not valid. Only values from 1 to {1} are allowed.".format(args.sortUsingSamples, hm.matrix.get_num_samples()))
print('Samples used for ordering within each group: ', sortUsingSamples)
hm.matrix.sort_groups(sort_using=args.sortUsing,
sort_method=args.sortRegions,
sample_list=sortUsingSamples)
if args.outFileNameMatrix:
hm.save_matrix_values(args.outFileNameMatrix)
if args.outFileSortedRegions:
hm.save_BED(args.outFileSortedRegions)
colormap_dict = {'colorMap': args.colorMap,
'colorList': args.colorList,
'colorNumber': args.colorNumber,
'missingDataColor': args.missingDataColor,
'alpha': args.alpha}
plotMatrix(hm,
args.outFileName,
colormap_dict, args.plotTitle,
args.xAxisLabel, args.yAxisLabel, args.regionsLabel,
args.zMin, args.zMax,
args.yMin, args.yMax,
args.averageTypeSummaryPlot,
args.refPointLabel,
args.startLabel,
args.endLabel,
args.heatmapHeight,
args.heatmapWidth,
args.perGroup,
args.whatToShow,
plot_type=args.plotType,
image_format=args.plotFileFormat,
legend_location=args.legendLocation,
box_around_heatmaps=args.boxAroundHeatmaps,
label_rotation=args.label_rotation,
dpi=args.dpi,
interpolation_method=args.interpolationMethod)