scxpand.autoencoders.run_ae_train

scxpand.autoencoders.run_ae_train#

Functions

run_ae_training(data_path, base_save_dir, prm)

Run autoencoder training and evaluation.
scxpand.autoencoders.run_ae_train.run_ae_training(data_path, base_save_dir, prm, device=None, dev_ratio=0.2, trial=None, score_metric='harmonic_avg/AUROC', resume=False, num_workers=0)#

Run autoencoder training and evaluation.

Parameters:

  • data_path (str | Path) – Path to data file (optional if adata provided)

  • base_save_dir (str | Path) – Directory to save model and results

  • prm (AutoEncoderParams) – Autoencoder parameters

  • device (str | None (default: None)) – Device to use for training (CPU/GPU)

  • dev_ratio (float (default: 0.2)) – Ratio of data to use for validation

  • trial (Trial | None (default: None)) – Optuna trial object for hyperparameter optimization

  • score_metric (str (default: 'harmonic_avg/AUROC')) – Metric to use for scoring

  • resume (bool (default: False)) – Whether to resume from existing checkpoint

  • adata – AnnData object (optional if data_path provided)

  • num_workers (int (default: 0)) – Number of workers for data loading

Return type:

dict[str, dict[str, float]]

Returns:

Dictionary containing evaluation results

Contents