def visualize_dictionary(ct, X_dimred, genes, cell_types,
namespace, cluster_method, verbose=True):
from anndata import AnnData
from scanorama import visualize
import scanpy as sc
import seaborn as sns
# KNN and UMAP.
if verbose:
tprint('Constructing KNN graph...')
adata = AnnData(X=X_dimred)
sc.pp.neighbors(adata, use_rep='X')
if verbose:
tprint('Visualizing with UMAP...')
sc.tl.umap(adata, min_dist=0.5)
embedding = np.array(adata.obsm['X_umap'])
embedding[embedding < -20] = -20
embedding[embedding > 20] = 20
# Visualize cell types.
le = LabelEncoder().fit(cell_types)
cell_types_int = le.transform(cell_types)
visualize(
None, cell_types_int,
'{}_pan_umap_{}_type'.format(namespace, cluster_method),
np.array(sorted(set(cell_types))),
embedding=embedding,
image_suffix='.png'
)
#max_intensity = ct.labels_.max()
for c_idx in range(ct.labels_.shape[1]):
intensity = ct.labels_[:, c_idx]
intensity /= intensity.max()
print('\nCluster {}'.format(c_idx))
print_cell_types(cell_types, intensity)
# Visualize cluster in UMAP coordinates.
plt.figure()
plt.title('Cluster {}'.format(c_idx))
plt.scatter(embedding[:, 0], embedding[:, 1],
c=intensity, cmap=cm.get_cmap('Blues'), s=1)
plt.savefig('{}_pan_umap_{}_cluster{}.png'
.format(namespace, cluster_method, c_idx), dpi=500)
plt.figure()
plt.title('Cluster {}'.format(c_idx))
plt.hist(intensity.flatten(), bins=100)
plt.savefig('{}_pan_umap_{}_intensehist{}.png'
.format(namespace, cluster_method, c_idx), dpi=500)
intensity = (intensity > 0.8) * 1
plt.figure()
plt.title('Cluster {}'.format(c_idx))
plt.scatter(embedding[:, 0], embedding[:, 1],
c=intensity, cmap=cm.get_cmap('Blues'), s=1)
plt.savefig('{}_pan_umap_{}_member{}.png'
.format(namespace, cluster_method, c_idx), dpi=500)
for c_idx in range(ct.labels_.shape[1]):
# Visualize covariance matrix.
corr = ct.dictionary_[:, :, c_idx]
corr[np.isnan(corr)] = 0
#print('\nCluster {}'.format(c_idx))
#print_gene_modules(corr, genes)
gene_idx = np.sum(np.abs(corr), axis=1) > 0
if np.sum(gene_idx) == 0:
continue
corr = corr[gene_idx]
corr = corr[:, gene_idx]
plt.figure()
plt.title('Cluster {}'.format(c_idx))
plt.rcParams.update({'font.size': 5})
cmap = sns.diverging_palette(220, 10, as_cmap=True)
corr_max = max(corr.max(), abs(corr.min()))
sns.clustermap(corr, xticklabels=genes[gene_idx],
yticklabels=genes[gene_idx], cmap=cmap,
vmin=-corr_max, vmax=corr_max)
plt.xticks(rotation=90)
plt.yticks(rotation=90)
plt.savefig('{}_pan_cov_{}_cluster{}.png'
.format(namespace, cluster_method, c_idx), dpi=500)
save_datasets(datasets, genes, data_names)
labels = []
names = []
curr_label = 0
for i, a in enumerate(datasets):
labels += list(np.zeros(a.shape[0]) + curr_label)
names.append(data_names[i])
curr_label += 1
labels = np.array(labels, dtype=int)
embedding = visualize(datasets_dimred,
labels,
NAMESPACE + '_ds',
names,
perplexity=600,
n_iter=400,
size=100)
cell_labels = (open(
'data/cell_labels/293t_jurkat_cluster.txt').read().rstrip().split())
le = LabelEncoder().fit(cell_labels)
labels = le.transform(cell_labels)
cell_types = le.classes_
visualize(None,
labels,
NAMESPACE + '_type',
cell_types,
perplexity=600,
labels = np.array(labels, dtype=int)
pbmc_genes = [
'CD14', 'PTPRC', 'FCGR3A', 'ITGAX', 'ITGAM', 'CD19', 'HLA-DRB1',
'FCGR2B', 'FCGR2A', 'CD3E', 'CD4', 'CD8A', 'CD8B', 'CD28', 'CD8',
'TBX21', 'IKAROS', 'IL2RA', 'CD44', 'SELL', 'CCR7', 'MS4A1', 'CD68',
'CD163', 'IL5RA', 'SIGLEC8', 'KLRD1', 'NCR1', 'CD22', 'IL3RA', 'CCR6',
'IL7R', 'CD27', 'FOXP3', 'PTCRA', 'ID3', 'PF4', 'CCR10', 'SIGLEC7',
'NKG7', 'S100A8', 'CXCR3', 'CCR5', 'CCR3', 'CCR4', 'PTGDR2', 'RORC'
]
embedding = visualize(datasets_dimred,
labels,
NAMESPACE + '_ds',
names,
gene_names=pbmc_genes,
gene_expr=np.concatenate(datasets),
genes=genes,
perplexity=500,
n_iter=400)
cell_labels = (
open('data/cell_labels/pbmc_cluster.txt').read().rstrip().split())
le = LabelEncoder().fit(cell_labels)
cell_labels = le.transform(cell_labels)
cell_types = le.classes_
visualize(datasets_dimred,
cell_labels,
NAMESPACE + '_type',
cell_types,
names = []
curr_label = 0
for i, a in enumerate(datasets):
labels += list(np.zeros(a.shape[0]) + curr_label)
names.append(data_names[i])
curr_label += 1
labels = np.array(labels, dtype=int)
hsc_genes = [
'GATA2', 'APOE', 'SPHK1', 'CTSE', 'FOS'
]
# Visualize with PCA.
visualize(None, labels, NAMESPACE + '_ds', names,
gene_names=hsc_genes, genes=genes,
gene_expr=np.concatenate(datasets),
embedding=np.concatenate(datasets_dimred),
size=4)
cell_labels = (
open('data/cell_labels/hsc_cluster.txt')
.read().rstrip().split()
)
le = LabelEncoder().fit(cell_labels)
cell_labels = le.transform(cell_labels)
cell_types = le.classes_
visualize(None, cell_labels, NAMESPACE + '_type', cell_types,
embedding=np.concatenate(datasets_dimred), size=4)
from scanorama import correct, visualize, process_data
from scanorama import dimensionality_reduce, merge_datasets
NAMESPACE = 'different'
data_names = [
'data/293t_jurkat/293t',
'data/brain/neuron_9k',
'data/hsc/hsc_mars',
'data/macrophage/uninfected',
'data/pancreas/pancreas_inDrop',
'data/pbmc/10x/68k_pbmc',
]
if __name__ == '__main__':
datasets, genes_list, n_cells = load_names(data_names)
datasets, genes = correct(datasets, genes_list)
datasets = [normalize(ds, axis=1) for ds in datasets]
datasets_dimred = dimensionality_reduce(datasets)
labels = []
names = []
curr_label = 0
for i, a in enumerate(datasets):
labels += list(np.zeros(a.shape[0]) + curr_label)
names.append(data_names[i])
curr_label += 1
labels = np.array(labels, dtype=int)
visualize(datasets_dimred, labels, NAMESPACE, data_names)