Controllable protein design through Feynman-Kac steering

Diffusion-based models have recently enabled the generation of realistic and diverse protein structures, yet they remain limited in their ability to steer outcomes toward specific functional or biochemical objectives, such as binding affinity or sequence composition. Here we extend the Feynman-Kac (FK) steering framework, an inference-time control approach, to diffusion-based protein design. By coupling FK steering with structure generation, the method guides sampling toward desirable structural or energetic features while maintaining the diversity of the underlying diffusion process. To enable simultaneous generation of both sequence and structure properties, rewards are computed on models refined through ProteinMPNN and all-atom relaxation. Applied to binder design, FK steering consistently improves predicted interface energetics across diverse targets with minimal computational overhead. More broadly, this work demonstrates that inference-time FK control generalizes diffusion-based protein design to arbitrary, non-differentiable, and reward-agnostic objectives, providing a unified and model-independent framework for guided molecular generation.

• Publication year

  2025

• Venue

  arXiv.org

• Publication date

  2025-11-12

• Fields of study

  Biology, Mathematics, Computer Science

• Identifiers
  DOI 10.48550/arXiv.2511.09216arXiv 2511.09216
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• No references are available for this paper.

• AtomMOF: All-Atom Flow Matching for MOF-Adsorbate Structure Prediction

  2026cites this paper
• Riemannian MeanFlow

  2026cites this paper
• Steering diffusion models with quadratic rewards: a fine-grained analysis

  2026cites this paper
• Deep learning-guided evolutionary optimization for protein design

  2026cites this paper