Self-focusing virtual screening with active design space pruning
David E. Graff, Matteo Aldeghi, Joseph A. Morrone, Kirk E. Jordan,, Edward O. Pyzer-Knapp, Connor W. Coley

TL;DR
This paper introduces a design space pruning method for virtual screening that reduces inference costs by eliminating poor candidates early, maintaining performance while lowering computational overhead.
Contribution
It extends model-guided optimization with an irreversible pruning technique to decrease inference costs in large-scale virtual screening tasks.
Findings
DSP significantly reduces overhead costs.
Performance remains comparable to baseline methods.
Applicable to various optimization tasks.
Abstract
High-throughput virtual screening is an indispensable technique utilized in the discovery of small molecules. In cases where the library of molecules is exceedingly large, the cost of an exhaustive virtual screen may be prohibitive. Model-guided optimization has been employed to lower these costs through dramatic increases in sample efficiency compared to random selection. However, these techniques introduce new costs to the workflow through the surrogate model training and inference steps. In this study, we propose an extension to the framework of model-guided optimization that mitigates inferences costs using a technique we refer to as design space pruning (DSP), which irreversibly removes poor-performing candidates from consideration. We study the application of DSP to a variety of optimization tasks and observe significant reductions in overhead costs while exhibiting similar…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMachine Learning in Materials Science · Machine Learning and Data Classification · Computational Drug Discovery Methods
MethodsPruning
