zoom.pls_tool.model_eval

zoom.pls_tool.model_eval(expression: pandas.DataFrame, SBP: pandas.DataFrame, best_comp: int, cv: int, repeats: int, seed: int, n_jobs: int) → Tuple[pandas.DataFrame, list][source]

Evaluate the final model performance for the PLS-R model.

Parameters:

  • expression (pd.DataFrame) – AHBA gene expression matrix.

  • SBP (pd.DataFrame) – One-dimensional data frame of spatial brain phenotype.

  • best_comp (int) – The optimal component number for current PLS-R model.

  • cv (int) – Number of folds.

  • repeats (int) – How many times should model performance evaluation be run?

  • seed (int) – Random seed to control the dataset split.

  • n_jobs (int) – Number of cores used for parallel computation.

Returns:

  • preds_rep (pd.DataFrame) – The predicted SBP values across repeats.

  • scores (list) – Model performances across repeats, as measured by Pearson’s correlation.

References

Wang, Y. et al. Spatio-molecular profiles shape the human cerebellar hierarchy along the sensorimotor-association axis. Cell Rep. 43, 113770 (2024).