# if args.reference in adata.obs:
# cluster_report(adata.obs[args.reference].cat.codes, adata.obs[args.cluster_method].astype(int))
sc.settings.figdir = outdir
sc.set_figure_params(dpi=80, figsize=(6, 6), fontsize=10)
if args.embed == 'UMAP':
sc.tl.umap(adata, min_dist=0.1)
color = [
c for c in ['celltype', args.cluster_method] if c in adata.obs
]
sc.pl.umap(adata, color=color, save='.pdf', wspace=0.4, ncols=4)
elif args.embed == 'tSNE':
sc.tl.tsne(adata, use_rep='latent')
color = [
c for c in ['celltype', args.cluster_method] if c in adata.obs
]
sc.pl.tsne(adata, color=color, save='.pdf', wspace=0.4, ncols=4)
if args.impute:
adata.obsm['impute'] = model.encodeBatch(testloader,
device=device,
out='x')
if args.binary:
adata.obsm['impute'] = model.encodeBatch(testloader,
device=device,
out='x')
adata.obsm['binary'] = binarization(adata.obsm['impute'], adata.X)
adata.write(outdir + 'adata.h5ad', compression='gzip')
pred = model.predict(testloader, device)
pd.Series(pred, index=dataset.barcode).to_csv(os.path.join(
outdir, 'cluster_assignments.txt'),
sep='\t',
header=False)
# 3. imputed data
if args.impute or args.binary:
recon_x = model.encodeBatch(testloader,
device,
out='x',
transforms=[normalizer.inverse_transform])
if args.binary:
import scipy
print("Saving binary imputed data")
recon_x = binarization(recon_x, dataset.data).T
imputed_dir = outdir + '/binary_imputed/'
os.makedirs(imputed_dir, exist_ok=True)
scipy.io.mmwrite(imputed_dir + 'count.mtx', recon_x)
pd.Series(dataset.peaks).to_csv(imputed_dir + 'peak.txt',
sep='\t',
index=False,
header=None)
pd.Series(dataset.barcode).to_csv(imputed_dir + 'barcode.txt',
sep='\t',
index=False,
header=None)
elif args.impute:
print("Saving imputed data")
recon_x = pd.DataFrame(recon_x.T,
index=dataset.peaks,