Enhancing Safe and Controllable Protein Generation via Knowledge Preference Optimization

TL;DR

This paper introduces a Knowledge-guided Preference Optimization framework that enhances the safety of protein language models by integrating prior knowledge and reinforcement learning to reduce harmful sequence generation.

Contribution

It presents a novel KPO framework that combines a Protein Safety Knowledge Graph with reinforcement learning to improve safety in protein sequence generation.

Findings

Reduces hazardous protein sequence generation

Maintains high functional quality of generated proteins

Provides a safety assurance framework for biotech applications

Abstract

Protein language models have emerged as powerful tools for sequence generation, offering substantial advantages in functional optimization and denovo design. However, these models also present significant risks of generating harmful protein sequences, such as those that enhance viral transmissibility or evade immune responses. These concerns underscore critical biosafety and ethical challenges. To address these issues, we propose a Knowledge-guided Preference Optimization (KPO) framework that integrates prior knowledge via a Protein Safety Knowledge Graph. This framework utilizes an efficient graph pruning strategy to identify preferred sequences and employs reinforcement learning to minimize the risk of generating harmful proteins. Experimental results demonstrate that KPO effectively reduces the likelihood of producing hazardous sequences while maintaining high functionality, offering a robust safety assurance framework for applying generative models in biotechnology.