Abstract Generative models based on diffusion and flow matching have recently been applied to structure-based drug design, but their outputs often include unrealistic protein–ligand interactions that do not obey the laws of physics. We present an energy guidance framework that incorporates a molecular mechanics force field (MMFF94) directly into the sampling process. The method steers molecular generation toward more physically plausible and energetically stable conformations without retraining the underlying model. We evaluate this approach using two state-of-the-art architectures, SemlaFlow, a flow matching model and EDM, a diffusion model, on the PDBBind dataset. Across both models, energy guidance improves enthalpic interaction energy, improves strain energy by up to 75<InlineEquation ID="IEq1"> <EquationSource Format="TEX">$\%$</EquationSource> <EquationSource Format="MATHML"><math> <mo>%</mo> </math></EquationSource> </InlineEquation>, and generates over 1000 ligands with better docking scores than native ligands. These results demonstrate that lightweight, physics-based guidance can significantly enhance generative drug design while preserving chemical validity and diversity. Scientific contribution We introduce a novel, training-free force field guidance framework that steers ligand generation using empirical molecular mechanics (e.g., MMFF94) during diffusion or flow-based sampling–without modifying or retraining the base generative model (e.g., EDM or Semflaflow by [<CitationRef CitationID="CR24">24</CitationRef>]). Our method operates as a plug-in during inference time, leveraging energy feedback to generate poses with lower strain and having better predicted interactions with the protein structure. Our main contributions are as follows:<UnorderedList Mark="Bullet"> <ItemContent> Energy-based guidance without retraining: Unlike methods that require gradients from neural affinity predictors (e.g., BADGER [<CitationRef CitationID="CR26">26</CitationRef>]), our approach injects classical force field feedback (MMFF94) directly during the posterior sampling step. </ItemContent> <ItemContent> Improved docking and strain metrics: In benchmarks against unconditional EDM and Semflaflow, our guided inference yields consistently better AutoDock Vina scores and lower ligand strain energy, even after optimizing the final structures using the same force field. </ItemContent> <ItemContent> Compatibility and flexibility: Because the guidance module is external, it can be applied broadly to multiple generative backbones–without retraining or architecture modifications, and can be applied to arbitrary differentiable potential energy functions. </ItemContent> <ItemContent> Theoretical guarantee of stability. We demonstrate in Appendix <InternalRef RefID="Sec16">B</InternalRef> that the gradient correction step corresponds to a descent step on the energy under standard smoothness assumptions. While the full sampling update also includes model-driven (and, in the diffusion case, stochastic) components, this result formalizes how the guidance term locally biases the trajectory toward lower-energy regions and provides a principled justification for its stabilizing effect. </ItemContent> </UnorderedList>

Improving protein-ligand complex generation with force field guidance

期刊论文
出版模式：

开放获取
发表日期：

2026年5月2日

查看全文

Helen Lai,
Tingyu Wang,
Hassan Sirelkhatim,
Joe Eaton,
Howard Huang,
Brad Rees,
Ola Engkvist,
Jon Paul Janet,
Xiaoyun Wang,
Alessandro Tibo

摘要

Abstract

Generative models based on diffusion and flow matching have recently been applied to structure-based drug design, but their outputs often include unrealistic protein–ligand interactions that do not obey the laws of physics. We present an energy guidance framework that incorporates a molecular mechanics force field (MMFF94) directly into the sampling process. The method steers molecular generation toward more physically plausible and energetically stable conformations without retraining the underlying model. We evaluate this approach using two state-of-the-art architectures, SemlaFlow, a flow matching model and EDM, a diffusion model, on the PDBBind dataset. Across both models, energy guidance improves enthalpic interaction energy, improves strain energy by up to 75 $\%$ $%$ , and generates over 1000 ligands with better docking scores than native ligands. These results demonstrate that lightweight, physics-based guidance can significantly enhance generative drug design while preserving chemical validity and diversity.

Scientific contribution

We introduce a novel, training-free force field guidance framework that steers ligand generation using empirical molecular mechanics (e.g., MMFF94) during diffusion or flow-based sampling–without modifying or retraining the base generative model (e.g., EDM or Semflaflow by [24]). Our method operates as a plug-in during inference time, leveraging energy feedback to generate poses with lower strain and having better predicted interactions with the protein structure.

Our main contributions are as follows:

Energy-based guidance without retraining: Unlike methods that require gradients from neural affinity predictors (e.g., BADGER [26]), our approach injects classical force field feedback (MMFF94) directly during the posterior sampling step.

Improved docking and strain metrics: In benchmarks against unconditional EDM and Semflaflow, our guided inference yields consistently better AutoDock Vina scores and lower ligand strain energy, even after optimizing the final structures using the same force field.

Compatibility and flexibility: Because the guidance module is external, it can be applied broadly to multiple generative backbones–without retraining or architecture modifications, and can be applied to arbitrary differentiable potential energy functions.

Theoretical guarantee of stability. We demonstrate in Appendix B that the gradient correction step corresponds to a descent step on the energy under standard smoothness assumptions. While the full sampling update also includes model-driven (and, in the diffusion case, stochastic) components, this result formalizes how the guidance term locally biases the trajectory toward lower-energy regions and provides a principled justification for its stabilizing effect.