scglue.models.scglue.SCGLUEModel.get_losses

SCGLUEModel.get_losses(adatas, graph, edge_weight='weight', edge_sign='sign', neg_samples=10, data_batch_size=128, graph_batch_size=- 1)[source]

Compute loss function values

Parameters

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

  • graph (Graph) – Prior graph

  • edge_weight (str) – Key of edge attribute for edge weight

  • edge_sign (str) – Key of edge attribute for edge sign

  • neg_samples (int) – Number of negative samples for each edge

  • data_batch_size (int) – Number of cells in each data minibatch

  • graph_batch_size (int) – Number of edges in each graph minibatch

Return type

Mapping[str, ndarray]

Returns

losses – Loss function values