Regression Enrichment Surfaces: a Simple Analysis Technique for Virtual Drug Screening Models
This is an incremental improvement for researchers in computational drug discovery, offering a more tailored analysis technique for virtual screening models.
The paper tackles the problem of evaluating virtual drug screening models, which are typically trained as regression models but used for ranking/classification tasks, by introducing regression enrichment surfaces (RES) to better detect top-performing treatments. The method provides a Python package for implementation and interpretation.
We present a new method for understanding the performance of a model in virtual drug screening tasks. While most virtual screening problems present as a mix between ranking and classification, the models are typically trained as regression models presenting a problem requiring either a choice of a cutoff or ranking measure. Our method, regression enrichment surfaces (RES), is based on the goal of virtual screening: to detect as many of the top-performing treatments as possible. We outline history of virtual screening performance measures and the idea behind RES. We offer a python package and details on how to implement and interpret the results.