def SCANVI_acc(gene_dataset:GeneExpressionDataset, plotname: str,pred1,pred2,coral1,coral2, rep='0'):
fname = '../%s/scanvi_acc.txt'%(plotname)
methods = ['scanvi','scanvi1','scanvi2']
f = open(fname, "w+")
f.write('method\t' + "%s\t" * len(gene_dataset.cell_types) % tuple(gene_dataset.cell_types) + "\n")
for i,method in enumerate(methods):
vae_posterior = trainVAE(gene_dataset,plotname,rep)
scanvi = SCANVI(gene_dataset.nb_genes, gene_dataset.n_batches, gene_dataset.n_labels, n_layers=2)
scanvi.load_state_dict(vae_posterior.model.state_dict(), strict=False)
if method=='scanvi1':
trainer_scanvi = AlternateSemiSupervisedTrainer(scanvi, gene_dataset, classification_ratio=10,
n_epochs_classifier=50, lr_classification=5 * 1e-3)
trainer_scanvi.labelled_set = trainer_scanvi.create_posterior(indices=(gene_dataset.batch_indices == 0))
trainer_scanvi.unlabelled_set = trainer_scanvi.create_posterior(indices=(gene_dataset.batch_indices == 1))
elif method=='scanvi2':
trainer_scanvi = AlternateSemiSupervisedTrainer(scanvi, gene_dataset, classification_ratio=10,
n_epochs_classifier=50, lr_classification=5 * 1e-3)
trainer_scanvi.labelled_set = trainer_scanvi.create_posterior(indices=(gene_dataset.batch_indices == 1))
trainer_scanvi.unlabelled_set = trainer_scanvi.create_posterior(indices=(gene_dataset.batch_indices == 0))
else:
trainer_scanvi = SemiSupervisedTrainer(scanvi, gene_dataset, classification_ratio=50,
n_epochs_classifier=1, lr_classification=5 * 1e-3)
trainer_scanvi.train(n_epochs=5)
labelled_idx = trainer_scanvi.labelled_set.indices
unlabelled_idx = trainer_scanvi.unlabelled_set.indices
full = trainer_scanvi.create_posterior(trainer_scanvi.model, gene_dataset, indices=np.arange(len(gene_dataset)))
labels, labels_pred = full.sequential().compute_predictions()
shared = set(labels[labelled_idx]).intersection(set(labels[unlabelled_idx]))
acc = [np.mean(labels_pred[unlabelled_idx][labels[unlabelled_idx] == i] == i) for i in np.unique(labels)]
for x in np.unique(labels):
if x not in [*shared] and method!='scanvi':
acc[x]=-1
f.write(method + "\t" + "%.4f\t" * len(acc) % tuple(acc) + "\n")
labels = gene_dataset.labels.ravel()
batch = gene_dataset.batch_indices.ravel()
acc = [np.mean(pred1[labels[batch == 1] == i] == i) for i in np.unique(labels)]
f.write('scmap1' + "\t" + "%.4f\t" * len(acc) % tuple(acc) + "\n")
acc = [np.mean(pred2[labels[batch == 0] == i] == i) for i in np.unique(labels)]
f.write('scmap2' + "\t" + "%.4f\t" * len(acc) % tuple(acc) + "\n")
acc = [np.mean(coral1[labels[batch == 1] == i] == i) for i in np.unique(labels)]
f.write('coral1' + "\t" + "%.4f\t" * len(acc) % tuple(acc) + "\n")
acc = [np.mean(coral2[labels[batch == 0] == i] == i) for i in np.unique(labels)]
f.write('coral2' + "\t" + "%.4f\t" * len(acc) % tuple(acc) + "\n")
f.close()
def runScanvi(adata, batch, labels):
# Use non-normalized (count) data for scanvi!
# Check for counts data layer
if 'counts' not in adata.layers:
raise TypeError(
'Adata does not contain a `counts` layer in `adata.layers[`counts`]`'
)
from scvi.models import VAE, SCANVI
from scvi.inference import UnsupervisedTrainer, SemiSupervisedTrainer
from sklearn.preprocessing import LabelEncoder
from scvi.dataset import AnnDatasetFromAnnData
import numpy as np
# STEP 1: prepare the data
net_adata = adata.copy()
net_adata.X = adata.layers['counts']
del net_adata.layers['counts']
# Ensure that the raw counts are not accidentally used
del net_adata.raw # Note that this only works from anndata 0.7
# Define batch indices
le = LabelEncoder()
net_adata.obs['batch_indices'] = le.fit_transform(
net_adata.obs[batch].values)
net_adata.obs['labels'] = le.fit_transform(net_adata.obs[labels].values)
net_adata = AnnDatasetFromAnnData(net_adata)
print("scANVI dataset object with {} batches and {} cell types".format(
net_adata.n_batches, net_adata.n_labels))
#if hvg is True:
# # this also corrects for different batches by default
# net_adata.subsample_genes(2000, mode="seurat_v3")
# # Defaults from SCVI github tutorials scanpy_pbmc3k and harmonization
n_epochs_scVI = np.min([round((20000 / adata.n_obs) * 400), 400]) #400
n_epochs_scANVI = int(np.min([10, np.max([2, round(n_epochs_scVI / 3.)])]))
n_latent = 30
n_hidden = 128
n_layers = 2
# STEP 2: RUN scVI to initialize scANVI
vae = VAE(
net_adata.nb_genes,
reconstruction_loss='nb',
n_batch=net_adata.n_batches,
n_latent=n_latent,
n_hidden=n_hidden,
n_layers=n_layers,
)
trainer = UnsupervisedTrainer(
vae,
net_adata,
train_size=1.0,
use_cuda=False,
)
trainer.train(n_epochs=n_epochs_scVI, lr=1e-3)
# STEP 3: RUN scANVI
scanvi = SCANVI(net_adata.nb_genes,
net_adata.n_batches,
net_adata.n_labels,
n_hidden=n_hidden,
n_latent=n_latent,
n_layers=n_layers,
dispersion='gene',
reconstruction_loss='nb')
scanvi.load_state_dict(trainer.model.state_dict(), strict=False)
# use default parameter from semi-supervised trainer class
trainer_scanvi = SemiSupervisedTrainer(scanvi, net_adata)
# use all cells as labelled set
trainer_scanvi.labelled_set = trainer_scanvi.create_posterior(
trainer_scanvi.model, net_adata, indices=np.arange(len(net_adata)))
# put one cell in the unlabelled set
trainer_scanvi.unlabelled_set = trainer_scanvi.create_posterior(
indices=[0])
trainer_scanvi.train(n_epochs=n_epochs_scANVI)
# extract info from posterior
scanvi_full = trainer_scanvi.create_posterior(trainer_scanvi.model,
net_adata,
indices=np.arange(
len(net_adata)))
latent, _, _ = scanvi_full.sequential().get_latent()
adata.obsm['X_emb'] = latent
return adata