Relaxed Sequence Sampling for Diverse Protein Design

2025-10-27

AI Summary

Existing protein design methods (e.g., RSO) rely on single-path gradient optimization and neglect constraints inherent in sequence space, resulting in low sequence diversity and poor structural designability. To address this, we propose RSS, a Markov Chain Monte Carlo (MCMC)-based framework that jointly incorporates AlphaFold2’s structural prediction and ESM2’s evolutionary prior within a continuous logit-space energy function. RSS synergistically integrates gradient-guided sampling with language-model-informed “jumps” to simultaneously optimize structural accuracy and biological plausibility of sequences. Compared to RSO, RSS achieves a fivefold improvement in structural designability and a two- to threefold increase in sequence diversity at comparable computational cost. This substantially expands the tractable region of the protein design space while preserving physicochemical and evolutionary realism.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Bio-inspired Learning
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Protein design using structure prediction models such as AlphaFold2 has shown remarkable success, but existing approaches like relaxed sequence optimization (RSO) rely on single-path gradient descent and ignore sequence-space constraints, limiting diversity and designability. We introduce Relaxed Sequence Sampling (RSS), a Markov chain Monte Carlo (MCMC) framework that integrates structural and evolutionary information for protein design. RSS operates in continuous logit space, combining gradient-guided exploration with protein language model-informed jumps. Its energy function couples AlphaFold2-derived structural objectives with ESM2-derived sequence priors, balancing accuracy and biological plausibility. In an in silico protein binder design task, RSS produces 5$ imes$ more designable structures and 2-3$ imes$ greater structural diversity than RSO baselines, at equal computational cost. These results highlight RSS as a principled approach for efficiently exploring the protein design landscape.

Problem

• Enhancing protein design diversity beyond single-path optimization
• Integrating structural and evolutionary constraints for biological plausibility
• Improving designability and structural diversity in protein binder creation

Innovation

• MCMC framework integrates structural and evolutionary information
• Continuous logit space combines gradient and language model jumps
• Energy function couples AlphaFold2 objectives with ESM2 priors