def build_cytoplasmic_statistics(analysis_repo, statistics_type, molecule_type,
genes, keyorder):
gene2stat, gene2median, gene2error, gene2confidence_interval = {}, {}, {}, {}
for gene in genes:
logger.info("Running {} cytoplasmic {} analysis for {}", molecule_type,
statistics_type, gene)
image_set = ImageSet(analysis_repo,
['{0}/{1}/'.format(molecule_type, gene)])
if statistics_type == 'centrality':
if molecule_type == 'mrna':
gene2stat[
gene] = image_set.compute_cytoplasmic_spots_centrality()
else:
gene2stat[
gene] = image_set.compute_cytoplasmic_intensities_centrality(
)
if statistics_type == 'spread':
if molecule_type == 'mrna':
gene2stat[gene] = image_set.compute_cytoplasmic_spots_spread()
else:
gene2stat[
gene] = image_set.compute_intensities_cytoplasmic_spread()
if statistics_type == 'centrality':
gene2median[gene] = np.mean(gene2stat[gene])
gene2error[gene] = helpers.sem(gene2stat[gene], factor=0)
lower, higher = helpers.median_confidence_interval(gene2stat[gene])
gene2confidence_interval[gene] = [lower, higher]
if statistics_type == 'spread':
max_entropy = np.max([np.max(gene2stat[k]) for k in gene2stat.keys()])
for gene in gene2stat.keys():
gene2stat[gene] = gene2stat[gene] / max_entropy
gene2median[gene] = np.median(gene2stat[gene])
gene2error[gene] = helpers.sem(gene2stat[gene], factor=0)
lower, higher = helpers.median_confidence_interval(gene2stat[gene])
gene2confidence_interval[gene] = [lower, higher]
gene2stat = collections.OrderedDict(
sorted(gene2stat.items(), key=lambda i: keyorder.index(i[0])))
gene2median = collections.OrderedDict(
sorted(gene2median.items(), key=lambda i: keyorder.index(i[0])))
gene2error = collections.OrderedDict(
sorted(gene2error.items(), key=lambda i: keyorder.index(i[0])))
gene2confidence_interval = collections.OrderedDict(
sorted(gene2confidence_interval.items(),
key=lambda i: keyorder.index(i[0])))
return gene2median, gene2stat, gene2error, gene2confidence_interval
def compute_degree_of_clustering(genes_list, analysis_repo, molecule_type):
gene2_degree_of_clustering = {}
gene2median_degree_of_clustering = {}
gene2error_degree_of_clustering = {}
gene2confidence_interval = {}
degrees_of_clustering = []
for gene in genes_list:
image_set = ImageSet(analysis_repo,
['{0}/{1}/'.format(molecule_type, gene)])
d_of_c = np.array(image_set.compute_degree_of_clustering())
degrees_of_clustering.append(d_of_c)
for gene, degree_of_clustering in zip(genes_list, degrees_of_clustering):
degree_of_clustering = np.log(degree_of_clustering)
gene2_degree_of_clustering[gene] = degree_of_clustering
gene2median_degree_of_clustering[gene] = np.median(
degree_of_clustering)
# Standard error and CI computation
gene2error_degree_of_clustering[gene] = helpers.sem(
degree_of_clustering, factor=0)
lower, higher = helpers.median_confidence_interval(
degree_of_clustering)
gene2confidence_interval[gene] = [lower, higher]
return gene2_degree_of_clustering, gene2median_degree_of_clustering, gene2error_degree_of_clustering, gene2confidence_interval
def plot_dynamic_barplot(analysis_repo):
'''
Formats the data and calls the plotting function
'''
plot_colors = constants.analysis_config['PLOT_COLORS']
# paired mRNA-protein barplots, so we go through proteins (we have less proteins than mRNA)
tp_mrna = constants.dataset_config['TIMEPOINTS_MRNA']
tp_proteins = constants.dataset_config['TIMEPOINTS_PROTEIN']
all_timepoints = np.sort(list(set(tp_mrna) | set(tp_proteins)))
for i, gene in enumerate(constants.analysis_config['PROTEINS']):
df = pd.DataFrame(
columns=["Molecule", "Timepoint", "d_of_c", "error", "CI"])
for molecule, timepoints in zip(["mrna", "protein"],
[tp_mrna, tp_proteins]):
for j, tp in enumerate(all_timepoints):
if tp not in timepoints:
df = df.append(
{
"Molecule": molecule,
"Timepoint": tp,
"error": 0,
"CI": [0, 0],
"d_of_c": 0
},
ignore_index=True)
continue
image_set = ImageSet(
analysis_repo, ["{0}/{1}/{2}/".format(molecule, gene, tp)])
degree_of_clustering = np.log(
image_set.compute_degree_of_clustering(
)) # * factor[gene][molecule][j]
err = helpers.sem(degree_of_clustering, factor=6)
lower, higher = helpers.median_confidence_interval(
degree_of_clustering)
df = df.append(
{
"Molecule": molecule,
"Timepoint": tp,
"error": err,
"CI": [lower, higher],
"d_of_c": degree_of_clustering
},
ignore_index=True)
df = df.sort_values('Timepoint')
df = df.groupby('Molecule').apply(mean_column)
my_pal = {
"mrna": str(plot_colors[i]),
"protein": str(color_variant(plot_colors[i], +80))
}
tgt_image_name = constants.analysis_config[
'DYNAMIC_FIGURE_NAME_FORMAT'].format(gene=gene)
tgt_fp = pathlib.Path(
constants.analysis_config['FIGURE_OUTPUT_PATH'].format(
root_dir=global_root_dir), tgt_image_name)
plot.bar_profile_median_timepoints(df,
palette=my_pal,
figname=tgt_fp,
fixed_yscale=15)
def mrna_cytoplasmic_total_count(analysis_repo, keyorder):
gene2image_set = {}
gene2cyto_count = {}
gene2median_cyto_count = {}
gene2error = {}
gene2confidence_interval = {}
for gene in constants.analysis_config['MRNA_GENES']:
logger.info("Running mrna cytoplasmic total count analysis for {}", gene)
gene2image_set[gene] = ImageSet(analysis_repo, ['mrna/%s/' % gene])
gene2cyto_count[gene] = gene2image_set[gene].compute_cytoplasmic_spots_counts()
gene2median_cyto_count[gene] = np.median(gene2cyto_count[gene])
gene2error[gene] = helpers.sem(gene2cyto_count[gene], factor=0)
lower, higher = helpers.median_confidence_interval(gene2cyto_count[gene])
gene2confidence_interval[gene] = [lower, higher]
# generate bar plot image
gene2median_cyto_count = collections.OrderedDict(sorted(gene2median_cyto_count.items(), key=lambda i: keyorder.index(i[0])))
gene2error = collections.OrderedDict(sorted(gene2error.items(), key=lambda i: keyorder.index(i[0])))
gene2confidence_interval = collections.OrderedDict(sorted(gene2confidence_interval.items(), key=lambda i: keyorder.index(i[0])))
xlabels = constants.analysis_config['MRNA_GENES_LABEL']
tgt_image_name = constants.analysis_config['FIGURE_NAME_FORMAT'].format(molecule_type="mrna")
tgt_fp = pathlib.Path(constants.analysis_config['FIGURE_OUTPUT_PATH'].format(root_dir=global_root_dir),
tgt_image_name)
plot.bar_profile_median(gene2median_cyto_count,
gene2error.values(),
'mrna',
xlabels,
tgt_fp,
gene2confidence_interval,
annot=False,
data_to_annot=gene2cyto_count
)
# generate violin plot image
tgt_image_name = constants.analysis_config['FIGURE_NAME_VIOLIN_FORMAT'].format(molecule_type="mrna")
tgt_fp = pathlib.Path(constants.analysis_config['FIGURE_OUTPUT_PATH'].format(root_dir=global_root_dir),
tgt_image_name)
plot.violin_profile(gene2cyto_count, tgt_fp, xlabels, rotation=0, annot=False)
def test_median_confidence_interval(self):
a = np.array([24, 38, 61, 22, 16, 57, 31, 29, 35])
l, h = helpers.median_confidence_interval(a, cutoff=0.8)
self.assertEqual(l, 29)
self.assertEqual(h, 57)