Benchmarking Generated Poses: How Rational is Structure-based Drug Design with Generative Models?

TL;DR

This paper introduces PoseCheck, a benchmark for evaluating the physical plausibility of generated drug poses in structure-based drug design, revealing many generated poses violate physical constraints and lack key interactions.

Contribution

The study provides the first comprehensive benchmark assessing the physical validity of generated poses in SBDD, highlighting limitations of current generative models.

Findings

Generated molecules often violate physical constraints

Redocking can alter key interactions significantly

Current models produce less physically plausible poses than baselines

Abstract

Deep generative models for structure-based drug design (SBDD), where molecule generation is conditioned on a 3D protein pocket, have received considerable interest in recent years. These methods offer the promise of higher-quality molecule generation by explicitly modelling the 3D interaction between a potential drug and a protein receptor. However, previous work has primarily focused on the quality of the generated molecules themselves, with limited evaluation of the 3D molecule \emph{poses} that these methods produce, with most work simply discarding the generated pose and only reporting a "corrected" pose after redocking with traditional methods. Little is known about whether generated molecules satisfy known physical constraints for binding and the extent to which redocking alters the generated interactions. We introduce PoseCheck, an extensive analysis of multiple state-of-the-art methods and find that generated molecules have significantly more physical violations and fewer key interactions compared to baselines, calling into question the implicit assumption that providing rich 3D structure information improves molecule complementarity. We make recommendations for future research tackling identified failure modes and hope our benchmark can serve as a springboard for future SBDD generative modelling work to have a real-world impact.