Y_pred.npy file about molpal HOT 3 CLOSED

These are the predicted means (end uncertainties, if needed) of your surrogate model, they’re used for checkpointing and retrospective analysis. The array is parallel to the molecules in your library.

from molpal.

These are the predicted means (end uncertainties, if needed) of your surrogate model, they’re used for checkpointing and retrospective analysis. The array is parallel to the molecules in your library.

Can I say that the higher the number is, the more likely the corresponding compound being having a better (more negative) docking score? Or do these 'predicted means' not necessarily correlate to the docking scores?

I ever tried to plot these numbers (at the final iteration) against the true docking scores. I did not see much correlation.

from molpal.

The question of surrogate model accuracy is related but not strictly similar to optimization performance. You can make whatever claims/analyses you want, we’re just giving you the information. In a greedy optimization, the most important model-based metric is rank correlation because new points are prioritized solely based on predicted mean

from molpal.