Ordinal Confidence\nLevel Assignments for Regression\nModel Predictions
We present a simple method for assigning accurate confidence\nlevels\nto molecular property predictions from regression models. These confidence\nlevels are easy to interpret and useful for making decisions in drug\ndiscovery programs. We demonstrate their performance using time-split\nvalidation with assay data from the Relay Therapeutics internal database.
Publication Details
- Journal
- Figshare
- Published
- 2024-12-09
- DOI
- https://doi.org/10.1021/acs.jcim.4c01755.s001
- Primary Topic
- Computational Drug Discovery Methods
- Type
- article
- Field-Weighted Citation Impact
- 0.00