scparadise.sceve.available_models

scparadise.sceve.available_models#

scparadise.sceve.available_models(species=None, tissue=None, suspension=None, query=None, max_rmse=None, max_mae=None, min_n_proteins=None, sort_by=None, ascending=True, compact=True, refresh=False)[source]#

Get a table of available pretrained scEve models with optional filtering.

Parameters:

  • species (str (default: None)) – Filter models by species, using the Species column. (for example: ‘human’, ‘mouse’).

  • tissue (str (default: None)) – Filter models by tissue or organ, using the Tissue/Organ column. (for example: ‘blood’, ‘heart’, ‘spleen’).

  • suspension (str (default: None)) – Filter models by assay input type from the Suspension column. (for example: ‘cells’).

  • query (str (default: None)) – Search substring across Model name, Description, Tissue/Organ, and Species.

  • max_rmse (float (default: None)) – Keep only models with RMSE less than or equal to this value.

  • max_mae (float (default: None)) – Keep only models with MAE less than or equal to this value.

  • min_n_proteins (int (default: None)) – Keep only models with Number of Proteins greater than or equal to this value.

  • sort_by (str (default: None)) – Column name used for sorting.

  • ascending (bool (default: True)) – Sort order. For error metrics such as RMSE and MAE, ascending=True is usually preferable because lower values are better.

  • compact (bool (default: True)) – If True, return a compact subset of the most useful columns. If False, return the full table.

  • refresh (bool (default: False)) – If True, clear the cache and reload the table from the remote source.

Returns:

DataFrame with available pretrained scEve models after applying all requested filters.

Return type:

pandas.DataFrame

Notes

The table is loaded from the official scParadise repository and contains metadata columns including Model name, Tissue/Organ, Species, Description, Suspension, RMSE, MAE, and Number of Proteins.

Examples

>>> available_models()
>>> available_models(species='human')
>>> available_models(tissue='blood', suspension='cells')
>>> available_models(query='pbmc', max_rmse=0.35)
>>> available_models(max_mae=0.25, min_n_proteins=100)