Controllable Protein Sequence Generation with LLM Preference Optimization
Xiangyu Liu, Yi Liu, Silei Chen, Wei Hu
TL;DR
This paper tackles controllable protein sequence generation with specific attributes using protein LLMs, aiming to produce sequences that are both functional and structurally stable. It introduces CtrlProt, which couples prefix-tuning with a novel multi-listwise preference optimization that jointly considers structural stability and functionality. Stability is measured by Rosetta energy, and functionality by structure-based encoder similarity, and a multi-attribute extension enables simultaneous handling of several attributes. Empirical results across six GO-derived attributes show state-of-the-art performance on single- and multi-attribute generation, with improvements in pLDDT, TM-score, RMSD, and sequence diversity.
Abstract
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.