def integrate_sketch(datasets_dimred,
integration_fn,
integration_fn_args={},
sampling_fn=gs,
N=2000,
n_iter=1):
sketch_idxs = [
sorted(
set(gs(X, N, replace=False)) | set(uniform(X, N, replace=False)))
for X in datasets_dimred
]
datasets_sketch = [X[idx] for X, idx in zip(datasets_dimred, sketch_idxs)]
for _ in range(n_iter):
datasets_int = integration_fn(datasets_sketch[:],
**integration_fn_args)
labels = []
curr_label = 0
for i, a in enumerate(datasets_sketch):
labels += list(np.zeros(a.shape[0]) + curr_label)
curr_label += 1
labels = np.array(labels, dtype=int)
for i, (X_dimred,
X_sketch) in enumerate(zip(datasets_dimred, datasets_sketch)):
X_int = datasets_int[i]
neigh = NearestNeighbors(n_neighbors=3).fit(X_dimred)
_, neigh_idx = neigh.kneighbors(X_sketch)
ds_idxs, ref_idxs = [], []
for ref_idx in range(neigh_idx.shape[0]):
for k_idx in range(neigh_idx.shape[1]):
ds_idxs.append(neigh_idx[ref_idx, k_idx])
ref_idxs.append(ref_idx)
bias = transform(X_dimred,
X_int,
ds_idxs,
ref_idxs,
15,
batch_size=1000)
datasets_int[i] = X_dimred + bias
return datasets_int
NAMESPACE + '_uncorrected',
[ str(ct) for ct in sorted(set(labels)) ],
perplexity=100, n_iter=500, image_suffix='.png',
viz_cluster=True
)
entropy_test(embedding, labels[idx])
datasets, genes_list, n_cells = load_names(data_names)
datasets, genes = merge_datasets(datasets, genes_list)
X = vstack(datasets)
if not os.path.isfile('data/dimred/{}_{}.txt'.format(METHOD, NAMESPACE)):
log('Dimension reduction with {}...'.format(METHOD))
X_dimred = reduce_dimensionality(
normalize(X), method=METHOD, dimred=DIMRED
)
log('Dimensionality = {}'.format(X_dimred.shape[1]))
np.savetxt('data/dimred/{}_{}.txt'.format(METHOD, NAMESPACE), X_dimred)
else:
X_dimred = np.loadtxt('data/dimred/{}_{}.txt'.format(METHOD, NAMESPACE))
from ample import gs
samp_idx = gs(X_dimred, 1000, replace=False)
save_sketch(X, samp_idx, genes, NAMESPACE + '1000')
for scale in [ 10, 25, 100 ]:
N = int(X.shape[0] / scale)
samp_idx = gs(X_dimred, N, replace=False)
save_sketch(X, samp_idx, genes, NAMESPACE + str(N))
datasets, genes = merge_datasets(datasets, genes_list)
X = vstack(datasets)
if not os.path.isfile('data/dimred/{}_{}.txt'.format(METHOD, NAMESPACE)):
log('Dimension reduction with {}...'.format(METHOD))
X_dimred = reduce_dimensionality(normalize(X),
method=METHOD,
dimred=DIMRED)
log('Dimensionality = {}'.format(X_dimred.shape[1]))
np.savetxt('data/dimred/{}_{}.txt'.format(METHOD, NAMESPACE), X_dimred)
else:
X_dimred = np.loadtxt('data/dimred/{}_{}.txt'.format(
METHOD, NAMESPACE))
from ample import gs, uniform
samp_idx = gs(X_dimred, 20000, replace=False)
#samp_idx = uniform(X_dimred, 20000, replace=False)
#from anndata import AnnData
#import scanpy.api as sc
#adata = AnnData(X=X_dimred[samp_idx, :])
#sc.pp.neighbors(adata, use_rep='X')
#sc.tl.louvain(adata, resolution=1.5, key_added='louvain')
#
#louv_labels = np.array(adata.obs['louvain'].tolist())
#le = LabelEncoder().fit(louv_labels)
#cell_labels = le.transform(louv_labels)
#
#np.savetxt('data/cell_labels/mouse_brain_louvain.txt', cell_labels)
cell_labels = (open('data/cell_labels/mouse_brain_louvain.txt').read().
cell_names += [ 'mcsf_day6' ] * a.shape[0]
else:
assert(False)
le = LabelEncoder().fit(cell_names)
cell_labels = le.transform(cell_names)
write_table(X.toarray(), genes, 'data/pseudotime/' + NAMESPACE)
with open('data/pseudotime/mono_macro_meta.txt', 'w') as of:
of.write('Label\n')
for idx in range(X.shape[0]):
of.write('mono_macro{}\t{}'.format(idx, cell_names[idx]))
from ample import gs, gs_gap, uniform
gs_idx = gs(X_dimred, 110, replace=False)
write_table(X[gs_idx, :].toarray(), genes, 'data/pseudotime/' + NAMESPACE + '_gs')
report_cluster_counts(cell_labels[gs_idx])
with open('data/pseudotime/mono_macro_meta_gs.txt', 'w') as of:
of.write('Label\n')
i = 0
for idx in range(X.shape[0]):
if idx not in gs_idx:
continue
of.write('mono_macro_gs{}\t{}\n'.format(i, cell_names[idx]))
i += 1
uni_idx = uniform(X_dimred, 110, replace=False)
write_table(X[uni_idx, :].toarray(), genes, 'data/pseudotime/' + NAMESPACE + '_uni')
report_cluster_counts(cell_labels[uni_idx])