scparadise.sceve.predict

Contents

scparadise.sceve.predict#

scparadise.sceve.predict(adata, path_model, used_mod_name='auto', imputed_mod_name='auto', layer=None, batch_size=256, device='auto', return_mdata=False, verbose=True)[source]#

Predict (impute) the second modality in cells using the pretrained scEve model.

Parameters:

  • adata (AnnData) – Annotated data matrix.

  • path_model (str, path object) – Path to the folder containing the trained scEve model.

  • used_mod_name (str (default: 'auto')) – Used for imputation modality name. If the value is “auto”, then the name is selected from the model.

  • imputed_mod_name (str (default: 'auto')) – Imputed modality name. If the value is “auto”, then the name is selected from the model

  • layer (str (default: None)) – If specified, use adata.layers[layer] for expression values instead of adata.X.

  • batch_size (int, (default: 256)) – Number of examples per batch. Used only by version 2 scEve models.

  • device (str (default: 'auto')) – Type of device to use in training model (‘cpu’, ‘cuda’). Set ‘auto’ for automatic selection.

  • return_mdata (bool (default: True)) – If set ‘True’ return MuData object. If set ‘False’ return AnnData object with predicted (imputed) modality.

  • verbose (bool (default: True)) – Show progress bar for each batch during prediction.

Returns:

MuData or AnnData with imputed modality.

Contents