scvi.module.MRDeconv

class scvi.module.MRDeconv(n_spots, n_labels, n_batch, n_hidden, n_layers, n_latent, n_genes, decoder_state_dict, px_decoder_state_dict, px_r, per_ct_bias, dropout_decoder, dropout_amortization=0.03, augmentation=True, n_samples_augmentation=2, n_states_per_label=3, eps_v=0.002, mean_vprior=None, var_vprior=None, mp_vprior=None, amortization='both', prior_mode='mog', add_celltypes=1, n_latent_amortization=None, extra_encoder_kwargs=None, extra_decoder_kwargs=None)

Bases: EmbeddingModuleMixin, BaseModuleClass

Model for multi-resolution deconvolution of spatial transriptomics.

Parameters:

• n_spots (int) – Number of input spots

• n_labels (int) – Number of cell types

• n_hidden (int) – Number of neurons in the hidden layers

• n_layers (int) – Number of layers used in the encoder networks

• n_latent (int) – Number of dimensions used in the latent variables

• n_genes (int) – Number of genes used in the decoder

• px_r (tensor) – parameters for the px_r tensor in the CondSCVI model

• per_ct_bias (tensor) – estimates of per cell-type expression bias in the CondSCVI model

• decoder_state_dict (OrderedDict) – state_dict from the decoder of the CondSCVI model

• px_decoder_state_dict (OrderedDict) – state_dict from the px_decoder of the CondSCVI model

• dropout_decoder (float) – Dropout rate for the decoder neural network (same dropout as in CondSCVI decoder)

• dropout_amortization (float (default: 0.03)) – Dropout rate for the amortization neural network

• n_samples_augmentation (int (default: 2)) – Number of samples used in the augmentation

• n_states_per_label (int (default: 3)) – Number of states per cell-type in each spot

• eps_v (float (default: 0.002)) – Epsilon value for each cell-type proportion used during training.

• n_states_per_augmented_label – Number of states per cell-type in each spot during augmentation

• mean_vprior (ndarray (default: None)) – Mean parameter for each component in the empirical prior over the latent space

• var_vprior (ndarray (default: None)) – Diagonal variance parameter for each component in the empirical prior over the latent space

• mp_vprior (ndarray (default: None)) – Mixture proportion in cell type sub-clustering of each component in the empirical prior amortization

• prior_mode (Literal['mog', 'normal'] (default: 'mog')) – Mode of the prior distribution for the latent space. Either “mog” for mixture of gaussians or “normal” for normal distribution.

• add_celltypes (int (default: 1)) – Number of additional cell types compared to single cell data to add to the model

• n_latent_amortization (int | None (default: None)) – Number of dimensions used in the latent variables for the amortization encoder neural network

• extra_encoder_kwargs (dict | None (default: None)) – Extra keyword arguments passed into FCLayers.

• extra_decoder_kwargs (dict | None (default: None)) – Extra keyword arguments passed into FCLayers.

Attributes table

training

Methods table

generative(z, ind_x, library, batch_index)	Build the deconvolution model for every cell in the minibatch.
inference(x_augmented, batch_index[, ...])	Runs the inference (encoder) model.
loss(tensors, inference_outputs, ...[, ...])	Compute the loss.
sample(tensors[, n_samples, library_size])	Sample from the posterior.

Attributes

MRDeconv.training: bool

Methods

MRDeconv.generative(z, ind_x, library, batch_index)

Build the deconvolution model for every cell in the minibatch.

MRDeconv.inference(x_augmented, batch_index, n_samples=1, prior_sampled=None, ratios_ct_augmentation=None, ratio_augmentation=None)

Runs the inference (encoder) model.

MRDeconv.loss(tensors, inference_outputs, generative_outputs, kl_weight=1.0, ct_sparsity_weight=2.0, weighting_augmentation=100.0, weighting_smoothing=100.0, eta_reg=1.0, beta_reg=1.0, weighting_kl_latent=0.001, reconst_weight=3.0)

Compute the loss.

MRDeconv.sample(tensors, n_samples=1, library_size=1)

Sample from the posterior.