def export_cube():
cube = load_pickle(RegionPairTiming.cube_filename)
README = """\
d_mu:
mu(r2)-mu(r1) for every gene and region pair.
Dimensions: <n-genes> X <n-regions> X <n-regions>
combined_std:
The combined standard deviation of the two change distributions.
std = sqrt(0.5*(std1^2 + std2^2))
Dimensions: <n-genes> X <n-regions> X <n-regions>
score:
The d' for the two change distributions. Equal to d_mu ./ combined_std.
Dimensions: <n-genes> X <n-regions> X <n-regions>
genes:
Gene names for the genes represented in other arrays
regions:
Region names for the regions represented in other arrays
age_scaler:
The scaling used for ages (i.e. 'log' means x' = log(x + 38/52))
"""
mdict = dict(
README_CUBE=README,
genes=list_of_strings_to_matlab_cell_array(cube.genes),
regions=list_of_strings_to_matlab_cell_array(cube.regions),
age_scaler=scalers.unify(cube.age_scaler).cache_name(),
d_mu=cube.d_mu,
combined_std=cube.std,
scores=cube.d_mu / cube.std,
)
save_matfile(mdict, join(results_dir(), 'export', 'cube.mat'))
def export_cube():
cube = load_pickle(RegionPairTiming.cube_filename)
README = """\
d_mu:
mu(r2)-mu(r1) for every gene and region pair.
Dimensions: <n-genes> X <n-regions> X <n-regions>
combined_std:
The combined standard deviation of the two change distributions.
std = sqrt(0.5*(std1^2 + std2^2))
Dimensions: <n-genes> X <n-regions> X <n-regions>
score:
The d' for the two change distributions. Equal to d_mu ./ combined_std.
Dimensions: <n-genes> X <n-regions> X <n-regions>
genes:
Gene names for the genes represented in other arrays
regions:
Region names for the regions represented in other arrays
age_scaler:
The scaling used for ages (i.e. 'log' means x' = log(x + 38/52))
"""
mdict = dict(
README_CUBE = README,
genes = list_of_strings_to_matlab_cell_array(cube.genes),
regions = list_of_strings_to_matlab_cell_array(cube.regions),
age_scaler = scalers.unify(cube.age_scaler).cache_name(),
d_mu = cube.d_mu,
combined_std = cube.std,
scores = cube.d_mu / cube.std,
)
save_matfile(mdict, join(results_dir(), 'export', 'cube.mat'))
def scaled(self, scaler):
import scalers
scaler = scalers.unify(scaler) # handle None
return DevStage(
num=self.num,
name=self.name,
short_name=self.short_name,
from_age=scaler.scale(self.from_age),
to_age=scaler.scale(self.to_age),
)
def scaled(self, scaler):
import scalers
scaler = scalers.unify(scaler) # handle None
return DevStage(
num = self.num,
name = self.name,
short_name = self.short_name,
from_age = scaler.scale(self.from_age),
to_age = scaler.scale(self.to_age),
)
def add_age_ticks(ax, age_scaler, fontsize=None):
if fontsize is None:
fontsize = cfg.fontsize
# set the development stages as x labels
stages = [stage.scaled(age_scaler) for stage in dev_stages]
ax.set_xticks([stage.central_age for stage in stages])
ax.set_xticklabels([stage.short_name for stage in stages], fontsize=fontsize, fontstretch='condensed', rotation=90)
# mark birth time with a vertical line
ymin, ymax = ax.get_ylim()
birth_age = scalers.unify(age_scaler).scale(0)
ax.plot([birth_age, birth_age], [ymin, ymax], '--', color='0.85')
def export_timing_info_for_all_fits(data, fitter, fits):
change_dist = compute_timing_info_for_all_fits(data, fitter, fits)
README = """\
mu:
The mean age of the change distribution for given gene and region.
Dimensions: <n-genes> X <n-regions>
std:
The standard deviation of the change distribution for given gene and region.
Dimensions: <n-genes> X <n-regions>
genes:
Gene names for the genes represented in other arrays
weights:
The change distributions for each gene and region.
Dimensions: <n-genes> X <n-regions> X <n-bins>
bin_centers:
The ages for the center of each bin used in calculating the histogram in "weights".
Dimensions: <n-bins> X 1
bin_edges:
The edges of the bins used in calculating the change histogram.
(centers can be calculated from the bin_edges, but it's convenient to have it pre-calculated)
Dimensions: <n-bins + 1> X 1
regions:
Region names for the regions represented in other arrays
age_scaler:
The scaling used for ages (i.e. 'log' means x' = log(x + 38/52))
"""
mdict = dict(
README_CHANGE_DISTRIBUTIONS=README,
genes=list_of_strings_to_matlab_cell_array(change_dist.genes),
regions=list_of_strings_to_matlab_cell_array(change_dist.regions),
age_scaler=scalers.unify(change_dist.age_scaler).cache_name(),
mu=change_dist.mu,
std=change_dist.std,
bin_edges=change_dist.bin_edges,
bin_centers=change_dist.bin_centers,
weights=change_dist.weights,
)
filename = join(
cache_dir(),
fit_results_relative_path(data, fitter) + '-change-dist.mat')
save_matfile(mdict, filename)
def add_age_ticks(ax, age_scaler, fontsize=None):
if fontsize is None:
fontsize = cfg.fontsize
# set the development stages as x labels
stages = [stage.scaled(age_scaler) for stage in dev_stages]
ax.set_xticks([stage.central_age for stage in stages])
ax.set_xticklabels([stage.short_name for stage in stages],
fontsize=fontsize,
fontstretch='condensed',
rotation=90)
# mark birth time with a vertical line
ymin, ymax = ax.get_ylim()
birth_age = scalers.unify(age_scaler).scale(0)
ax.plot([birth_age, birth_age], [ymin, ymax], '--', color='0.85')
def export_timing_info_for_all_fits(data, fitter, fits):
change_dist = compute_timing_info_for_all_fits(data, fitter, fits)
README = """\
mu:
The mean age of the change distribution for given gene and region.
Dimensions: <n-genes> X <n-regions>
std:
The standard deviation of the change distribution for given gene and region.
Dimensions: <n-genes> X <n-regions>
genes:
Gene names for the genes represented in other arrays
weights:
The change distributions for each gene and region.
Dimensions: <n-genes> X <n-regions> X <n-bins>
bin_centers:
The ages for the center of each bin used in calculating the histogram in "weights".
Dimensions: <n-bins> X 1
bin_edges:
The edges of the bins used in calculating the change histogram.
(centers can be calculated from the bin_edges, but it's convenient to have it pre-calculated)
Dimensions: <n-bins + 1> X 1
regions:
Region names for the regions represented in other arrays
age_scaler:
The scaling used for ages (i.e. 'log' means x' = log(x + 38/52))
"""
mdict = dict(
README_CHANGE_DISTRIBUTIONS = README,
genes = list_of_strings_to_matlab_cell_array(change_dist.genes),
regions = list_of_strings_to_matlab_cell_array(change_dist.regions),
age_scaler = scalers.unify(change_dist.age_scaler).cache_name(),
mu = change_dist.mu,
std = change_dist.std,
bin_edges = change_dist.bin_edges,
bin_centers = change_dist.bin_centers,
weights = change_dist.weights,
)
filename = join(cache_dir(), fit_results_relative_path(data,fitter) + '-change-dist.mat')
save_matfile(mdict, filename)
def save_as_mat_files(data, fitter, fits, has_change_distributions):
for dataset in data.datasets:
filename = join(cache_dir(), fit_results_relative_path(dataset,fitter) + '.mat')
dataset_fits = fits[dataset.name]
print 'Saving mat file to {}'.format(filename)
shape = fitter.shape
gene_names = dataset.gene_names
gene_idx = {g:i for i,g in enumerate(gene_names)}
n_genes = len(gene_names)
region_names = dataset.region_names
region_idx = {r:i for i,r in enumerate(region_names)}
n_regions = len(region_names)
write_theta = shape.can_export_params_to_matlab()
if write_theta:
theta = init_array(np.NaN, shape.n_params(), n_genes,n_regions)
else:
theta = np.NaN
fit_scores = init_array(np.NaN, n_genes,n_regions)
LOO_scores = init_array(np.NaN, n_genes,n_regions)
fit_predictions = init_array(np.NaN, *dataset.expression.shape)
LOO_predictions = init_array(np.NaN, *dataset.expression.shape)
high_res_predictions = init_array(np.NaN, cfg.n_curve_points_to_plot, n_genes, n_regions)
scaled_high_res_ages = np.linspace(dataset.ages.min(), dataset.ages.max(), cfg.n_curve_points_to_plot)
original_high_res_ages = scalers.unify(dataset.age_scaler).unscale(scaled_high_res_ages)
if has_change_distributions:
change_distribution_bin_centers = fits.change_distribution_params.bin_centers
n_bins = len(change_distribution_bin_centers)
change_distribution_weights = init_array(np.NaN, n_bins, n_genes, n_regions)
else:
change_distribution_bin_centers = []
change_distribution_weights = []
for (g,r),fit in dataset_fits.iteritems():
series = dataset.get_one_series(g,r)
ig = gene_idx[g]
ir = region_idx[r]
fit_scores[ig,ir] = fit.fit_score
LOO_scores[ig,ir] = fit.LOO_score
if write_theta and fit.theta is not None:
theta[:,ig,ir] = fit.theta
if fit.fit_predictions is not None:
fit_predictions[series.original_inds,ig,ir] = fit.fit_predictions
if fit.LOO_predictions is not None:
LOO_predictions[series.original_inds,ig,ir] = fit.LOO_predictions
if fit.theta is not None:
high_res_predictions[:,ig,ir] = shape.f(fit.theta, scaled_high_res_ages)
change_weights = getattr(fit,'change_distribution_weights',None)
if change_weights is not None:
change_distribution_weights[:,ig,ir] = change_weights
mdict = dict(
gene_names = list_of_strings_to_matlab_cell_array(gene_names),
region_names = list_of_strings_to_matlab_cell_array(region_names),
theta = theta,
fit_scores = fit_scores,
LOO_scores = LOO_scores,
fit_predictions = fit_predictions,
LOO_predictions = LOO_predictions,
high_res_predictions = high_res_predictions,
high_res_ages = original_high_res_ages,
change_distribution_bin_centers = change_distribution_bin_centers,
change_distribution_weights = change_distribution_weights,
)
savemat(filename, mdict, oned_as='column')
def save_as_mat_files(data, fitter, fits, has_change_distributions):
for dataset in data.datasets:
filename = join(cache_dir(),
fit_results_relative_path(dataset, fitter) + '.mat')
dataset_fits = fits[dataset.name]
print 'Saving mat file to {}'.format(filename)
shape = fitter.shape
gene_names = dataset.gene_names
gene_idx = {g: i for i, g in enumerate(gene_names)}
n_genes = len(gene_names)
region_names = dataset.region_names
region_idx = {r: i for i, r in enumerate(region_names)}
n_regions = len(region_names)
write_theta = shape.can_export_params_to_matlab()
if write_theta:
theta = init_array(np.NaN, shape.n_params(), n_genes, n_regions)
else:
theta = np.NaN
fit_scores = init_array(np.NaN, n_genes, n_regions)
LOO_scores = init_array(np.NaN, n_genes, n_regions)
fit_predictions = init_array(np.NaN, *dataset.expression.shape)
LOO_predictions = init_array(np.NaN, *dataset.expression.shape)
high_res_predictions = init_array(np.NaN, cfg.n_curve_points_to_plot,
n_genes, n_regions)
scaled_high_res_ages = np.linspace(dataset.ages.min(),
dataset.ages.max(),
cfg.n_curve_points_to_plot)
original_high_res_ages = scalers.unify(
dataset.age_scaler).unscale(scaled_high_res_ages)
if has_change_distributions:
change_distribution_bin_centers = fits.change_distribution_params.bin_centers
n_bins = len(change_distribution_bin_centers)
change_distribution_weights = init_array(np.NaN, n_bins, n_genes,
n_regions)
else:
change_distribution_bin_centers = []
change_distribution_weights = []
for (g, r), fit in dataset_fits.iteritems():
series = dataset.get_one_series(g, r)
ig = gene_idx[g]
ir = region_idx[r]
fit_scores[ig, ir] = fit.fit_score
LOO_scores[ig, ir] = fit.LOO_score
if write_theta and fit.theta is not None:
theta[:, ig, ir] = fit.theta
if fit.fit_predictions is not None:
fit_predictions[series.original_inds, ig,
ir] = fit.fit_predictions
if fit.LOO_predictions is not None:
LOO_predictions[series.original_inds, ig,
ir] = fit.LOO_predictions
if fit.theta is not None:
high_res_predictions[:, ig,
ir] = shape.f(fit.theta,
scaled_high_res_ages)
change_weights = getattr(fit, 'change_distribution_weights', None)
if change_weights is not None:
change_distribution_weights[:, ig, ir] = change_weights
mdict = dict(
gene_names=list_of_strings_to_matlab_cell_array(gene_names),
region_names=list_of_strings_to_matlab_cell_array(region_names),
theta=theta,
fit_scores=fit_scores,
LOO_scores=LOO_scores,
fit_predictions=fit_predictions,
LOO_predictions=LOO_predictions,
high_res_predictions=high_res_predictions,
high_res_ages=original_high_res_ages,
change_distribution_bin_centers=change_distribution_bin_centers,
change_distribution_weights=change_distribution_weights,
)
savemat(filename, mdict, oned_as='column')
