scglue.models.scglue.IndSCGLUEModel

class scglue.models.scglue.IndSCGLUEModel(adatas, vertices, latent_dim=50, h_depth=2, h_dim=256, dropout=0.2, shared_batches=False, random_seed=0)[source]

Bases: scglue.models.scglue.SCGLUEModel

Independent GLUE model as a negative control where data reconstruction is independent from feature embeddings

Parameters

  • adatas (Mapping[str, AnnData]) – Datasets (indexed by domain name)

  • vertices (List[str]) – Prior graph vertices (must cover feature names in all domains)

  • latent_dim (int) – Latent dimensionality

  • h_depth (int) – Hidden layer depth for encoder and discriminator

  • h_dim (int) – Hidden layer dimensionality for encoder and discriminator

  • dropout (float) – Dropout rate

  • shared_batches (bool) – Whether the same batches are shared across domains

  • random_seed (int) – Random seed

Note

Do NOT use!

Methods

Attributes

logger