Controllable protein design with particle-based Feynman-Kac steering

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hartman, Erik, Wallin, Jonas, Malmström, Johan, Olsson, Jimmy
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914447220539392
author Hartman, Erik
Wallin, Jonas
Malmström, Johan
Olsson, Jimmy
author_facet Hartman, Erik
Wallin, Jonas
Malmström, Johan
Olsson, Jimmy
contents Proteins underpin most biological function, and the ability to design them with tailored structures and properties is central to advances in biotechnology. Diffusion-based generative models have emerged as powerful tools for protein design, but steering them toward proteins with specified properties remains challenging. The Feynman-Kac (FK) framework provides a principled way to guide diffusion models using user-defined rewards. In this paper, we enable FK-based steering of RFdiffusion through the development of guiding potentials that leverage ProteinMPNN and structural relaxation to guide the diffusion process towards desired properties. We show that steering can be used to consistently improve predicted interface energetics and increase binder designability by $89.5\%$. Together, these results establish that diffusion-based protein design can be effectively steered toward arbitrary, non-differentiable objectives, providing a model-independent framework for controllable protein generation.
format Preprint
id arxiv_https___arxiv_org_abs_2511_09216
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Controllable protein design with particle-based Feynman-Kac steering
Hartman, Erik
Wallin, Jonas
Malmström, Johan
Olsson, Jimmy
Machine Learning
Quantitative Methods
Proteins underpin most biological function, and the ability to design them with tailored structures and properties is central to advances in biotechnology. Diffusion-based generative models have emerged as powerful tools for protein design, but steering them toward proteins with specified properties remains challenging. The Feynman-Kac (FK) framework provides a principled way to guide diffusion models using user-defined rewards. In this paper, we enable FK-based steering of RFdiffusion through the development of guiding potentials that leverage ProteinMPNN and structural relaxation to guide the diffusion process towards desired properties. We show that steering can be used to consistently improve predicted interface energetics and increase binder designability by $89.5\%$. Together, these results establish that diffusion-based protein design can be effectively steered toward arbitrary, non-differentiable objectives, providing a model-independent framework for controllable protein generation.
title Controllable protein design with particle-based Feynman-Kac steering
topic Machine Learning
Quantitative Methods
url https://arxiv.org/abs/2511.09216