arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2501.15007cs.AIcs.CEq-bio.QM
收藏

基于LLM偏好优化的可控蛋白质序列生成

Controllable Protein Sequence Generation with LLM Preference Optimization

State Key Laboratory for Novel Software Technology, Nanjing University(南京大学计算机软件新技术国家重点实验室);Medical School, Nanjing University(南京大学医学院);National Institute of Healthcare Data Science, Nanjing University(南京大学国家医疗数据科学研究院)

Xiangyu Liu, Yi Liu, Silei Chen, Wei Hu

AI总结:

本文提出CtrlProt方法,通过多列表偏好优化策略微调蛋白质LLM,解决了现有可控蛋白质生成在功能性和结构稳定性上的不足,在单属性和多属性生成任务上均达到SOTA。

摘要:

设计具有特定属性的蛋白质为应对生物医学挑战提供了重要解决方案。预训练蛋白质大语言模型(LLMs)在蛋白质序列生成上展现出可喜结果。然而,在控制序列生成以获得特定属性方面,现有工作仍表现出较差的功能性和结构稳定性。本文提出一种名为CtrlProt的新型可控蛋白质设计方法。我们通过新的多列表偏好优化策略微调蛋白质LLM,以提高生成质量并支持多属性可控生成。实验表明,CtrlProt能有效满足功能性和结构稳定性要求,在单属性和多属性蛋白质序列生成上均实现了SOTA性能。

英文摘要:

Designing proteins with specific attributes offers an important solution to address biomedical challenges. Pre-trained protein large language models (LLMs) have shown promising results on protein sequence generation. However, to control sequence generation for specific attributes, existing work still exhibits poor functionality and structural stability. In this paper, we propose a novel controllable protein design method called CtrlProt. We finetune a protein LLM with a new multi-listwise preference optimization strategy to improve generation quality and support multi-attribute controllable generation. Experiments demonstrate that CtrlProt can meet functionality and structural stability requirements effectively, achieving state-of-the-art performance in both single-attribute and multi-attribute protein sequence generation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑