# Project to higher dimension.
Z = np.absolute(np.random.randn(2, 100))
datasets = [np.dot(s, Z) for s in samples]
# Add batch effect "noise."
datasets = [ds + np.random.randn(1, 100) for ds in datasets]
# Normalize datasets.
datasets = [normalize(ds, axis=1) for ds in datasets]
tsne = TSNE(n_iter=400, perplexity=100, verbose=2, random_state=69)
tsne.fit(np.concatenate(datasets[1:]))
plot_clusters(tsne.embedding_, np.concatenate(clusters[1:]), s=500)
plt.title('Uncorrected data')
plt.savefig('simulation_uncorrected.svg')
# Assemble datasets.
assembled = assemble(datasets[1:], verbose=1, sigma=1, knn=10, approx=True)
tsne.fit(datasets[1])
plot_clusters(tsne.embedding_, clusters[1], s=500)
plt.title('Dataset 1')
plt.xlabel('t-SNE 1')
plt.ylabel('t-SNE 2')
plt.savefig('simulation_ds1.svg')
tsne.fit(datasets[2])
plot_clusters(tsne.embedding_, clusters[2], s=500)
plt.title('Dataset 2')
plt.xlabel('t-SNE 1')
#datasets_dimred, genes = process_data(datasets, genes, hvg=hvg)
datasets, genes = correct(datasets, genes_list)
X = vstack(datasets).toarray()
X[X < 0] = 0
cell_labels = (
open('data/cell_labels/pancreas_cluster.txt').read().rstrip().split())
er_idx = [i for i, cl in enumerate(cell_labels) if cl == 'beta_er']
beta_idx = [i for i, cl in enumerate(cell_labels) if cl == 'beta']
gadd_idx = list(genes).index('GADD45A')
herp_idx = list(genes).index('HERPUD1')
plt.figure()
plt.boxplot([X[er_idx, gadd_idx], X[beta_idx, gadd_idx]], showmeans=True)
plt.title('GADD45A (p = {})'.format(
ttest_ind(X[er_idx, gadd_idx], X[beta_idx, gadd_idx],
equal_var=False)[1]))
plt.xticks([1, 2], ['beta_er', 'beta'])
plt.ylabel('Scaled gene expression')
plt.savefig('er_stress_GADD45A.svg')
plt.figure()
plt.boxplot([X[er_idx, herp_idx], X[beta_idx, herp_idx]], showmeans=True)
plt.title('HERPUD1 (p = {})'.format(
ttest_ind(X[er_idx, herp_idx], X[beta_idx, herp_idx],
equal_var=False)[1]))
plt.xticks([1, 2], ['beta_er', 'beta'])
plt.ylabel('Scaled gene expression')
plt.savefig('er_stress_HERPUD1.svg')
)
# Scanorama.
X = np.loadtxt('data/panorama_embedding.txt')
idx = np.random.choice(X.shape[0], size=20000, replace=False)
sil_pan = sil(X[idx, :], labels[idx])
print(np.median(sil_pan))
# scran MNN.
X = np.loadtxt('data/mnn_embedding.txt')
idx = np.random.choice(X.shape[0], size=20000, replace=False)
sil_mnn = sil(X[idx, :], labels[idx])
print(np.median(sil_mnn))
# Seurat CCA.
X = np.loadtxt('data/cca_embedding.txt')
idx = np.random.choice(X.shape[0], size=20000, replace=False)
sil_cca = sil(X[idx, :], labels[idx])
print(np.median(sil_cca))
print(ttest_ind(sil_pan, sil_mnn))
print(ttest_ind(sil_pan, sil_cca))
plt.figure()
plt.boxplot([ sil_pan, sil_mnn, sil_cca ], showmeans=True)
plt.title('Distributions of Silhouette Coefficients')
plt.xticks([ 1, 2, 3 ], [ 'Scanorama', 'scran MNN', 'Seurat CCA' ])
plt.ylabel('Silhouette Coefficient')
plt.savefig('silhouette.svg')
def plot_stats(stat,
samp_fns=None,
fname=None,
dtype=float,
only_fns=None,
only_replace=None,
max_N=None):
if samp_fns is None:
assert (fname is not None)
samp_fns = parse_stats(fname)
colors = [
#'#377eb8', '#ff7f00', '#f781bf',
#'#4daf4a', '#ff0000', '#a65628', '#984ea3',
#'#999999', '#e41a1c', '#dede00',
#'#ffe119', '#e6194b', '#ffbea3',
#'#911eb4', '#46f0f0', '#f032e6',
#'#d2f53c', '#008080', '#e6beff',
#'#aa6e28', '#800000', '#aaffc3',
#'#808000', '#ffd8b1', '#000080',
#'#808080', '#fabebe', '#a3f4ff'
'#377eb8',
'#ff7f00',
'#4daf4a',
'#984ea3',
#'#f781bf', '#a65628', '#984ea3',
'#999999',
'#e41a1c',
'#dede00',
'#ffe119',
'#e6194b',
'#ffbea3',
'#911eb4',
'#46f0f0',
'#f032e6',
'#d2f53c',
'#008080',
'#e6beff',
'#aa6e28',
'#800000',
'#aaffc3',
'#808000',
'#ffd8b1',
'#000080',
'#808080',
'#fabebe',
'#a3f4ff'
]
plt.figure()
c_idx = 0
for s_idx, (samp_fn, replace) in enumerate(
sorted(samp_fns, key=lambda x: '{}_{}'.format(*x))):
if samp_fn.startswith('_'):
continue
if only_fns is not None and samp_fn not in only_fns:
continue
if only_replace is not None and replace != only_replace:
continue
Ns = []
means = []
sems = []
for N in samp_fns[(samp_fn, replace)]:
if max_N is not None and N > max_N:
continue
stat_vals = [
dtype(stat_dict[stat])
for stat_dict in samp_fns[(samp_fn, replace)][N]
if stat in stat_dict
]
if len(stat_vals) == 0:
continue
Ns.append(N)
means.append(np.mean(stat_vals))
sems.append(ss.sem(stat_vals))
sort_idx = np.argsort(Ns)
Ns = np.array(Ns)[sort_idx]
means = np.array(means)[sort_idx]
sems = np.array(sems)[sort_idx]
label = '{}_{}'.format(samp_fn, replace)
plt.plot(Ns, means, color=colors[c_idx], label=label)
plt.scatter(Ns, means, color=colors[c_idx])
plt.fill_between(Ns,
means - sems,
means + sems,
alpha=0.3,
color=colors[c_idx])
c_idx = (c_idx + 1) % len(colors)
namespace = samp_fns[('_namespace', None)]
title = '{}_{}'.format(namespace, stat)
if only_replace is not None:
title += '_replace{}'.format(only_replace)
plt.title(title)
plt.xlabel('Sample size')
plt.ylabel(stat)
plt.legend()
mkdir_p('target/stats_plots')
plt.savefig('target/stats_plots/{}.svg'.format(title))
open('data/cell_labels/pancreas_cluster.txt')
.read().rstrip().split()
)
er_idx = [ i for i, cl in enumerate(cell_labels)
if cl == 'beta_er' ]
beta_idx = [ i for i, cl in enumerate(cell_labels)
if cl == 'beta' ]
gadd_idx = list(genes).index('GADD45A')
herp_idx = list(genes).index('HERPUD1')
plt.figure()
plt.boxplot([ X[er_idx, gadd_idx], X[beta_idx, gadd_idx] ],
showmeans=True)
plt.title('GADD45A (p < {})'.format(ttest_ind(
X[er_idx, gadd_idx], X[beta_idx, gadd_idx]
)[1]))
plt.xticks([1, 2], ['beta_er', 'beta'])
plt.ylabel('Scaled gene expression')
plt.savefig('er_stress_GADD45A.svg')
plt.figure()
plt.boxplot([ X[er_idx, herp_idx], X[beta_idx, herp_idx] ],
showmeans=True)
plt.title('HERPUD1 (p < {})'.format(ttest_ind(
X[er_idx, herp_idx], X[beta_idx, herp_idx]
)[1]))
plt.xticks([1, 2], ['beta_er', 'beta'])
plt.ylabel('Scaled gene expression')
plt.savefig('er_stress_HERPUD1.svg')