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 test_compute_intensities_cytoplasmic_spread(self):
image_set = ImageSet(self.repo, path_list=['protein/arhgdia/2h/'])
result = np.sort(image_set.compute_intensities_cytoplasmic_spread())
self.assertAlmostEqual(result.sum(), 3.0812597654, places=5)
self.assertAlmostEqual(result[1], 0.611584381, places=5)
