Seek and You Shall Fold

TL;DR

This paper introduces a novel framework that enables the integration of non-differentiable experimental data into protein generative models, improving structure prediction by coupling diffusion models with genetic algorithms across multiple data modalities.

Contribution

It presents a general method for guiding protein generative models with non-differentiable experimental data using a genetic algorithm, expanding capabilities to include chemical shifts.

Findings

Effective guidance using pairwise distance constraints

Successful incorporation of nuclear Overhauser effect restraints

First demonstration of chemical shift guided structure generation

Abstract

Accurate protein structures are essential for understanding biological function, yet incorporating experimental data into protein generative models remains a major challenge. Most predictors of experimental observables are non-differentiable, making them incompatible with gradient-based conditional sampling. This is especially limiting in nuclear magnetic resonance, where rich data such as chemical shifts are hard to directly integrate into generative modeling. We introduce a framework for non-differentiable guidance of protein generative models, coupling a continuous diffusion-based generator with any black-box objective via a tailored genetic algorithm. We demonstrate its effectiveness across three modalities: pairwise distance constraints, nuclear Overhauser effect restraints, and for the first time chemical shifts. These results establish chemical shift guided structure generation as feasible, expose key weaknesses in current predictors, and showcase a general strategy for incorporating diverse experimental signals. Our work points toward automated, data-conditioned protein modeling beyond the limits of differentiability.