StructEvo：面向蛋白质定向进化的结构感知强化学习框架
Structure-aware Reinforcement Learning for Protein Directed Evolution
AI 导读
arXiv 论文提出 StructEvo，一种结构感知的强化学习框架，用于蛋白质定向进化。该框架采用 delta-structure fusion 编码器近似突变体结构特征，并通过结构对齐的分层动作网络分解巨大突变空间，几何约束稳定学习。在两个优化基准上分别超过此前 SOTA 方法 9.2% 和 16.3%，还在 GFP 中识别出经实验验证的上位性模式。
正文 · 原文
Abstract:Protein optimization remains a longstanding goal in life sciences. Existing machine learning-assisted directed evolution (MLDE) methods primarily rely on sequence-only features, overlooking the critical spatial constraints and co-evolutionary interactions encoded in protein structures. However, directly integrating structural information remains challenging due to the scarcity of reliable mutant structures. To address these issues, we propose StructEvo, a novel structure-aware reinforcement learning framework for protein directed evolution. StructEvo employs a delta-structure fusion encoder to approximate mutant structure features via feature differences, enabling dynamic incorporation of spatial knowledge. The vast mutation space is then decomposed into manageable subspaces through a structure-aligned hierarchical action network, while a geometric constraint further stabilizes delta feature learning. Our approach outperforms prior state-of-the-art methods by 9.2% and 16.3% on two challenging optimization benchmarks, and further identifies an experimentally validated epistasis pattern in GFP, highlighting the importance of structural guidance for effective protein directed evolution.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2609.39048 [cs.LG] |
| (or arXiv:2609.39048v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2609.39048 arXiv-issued DOI via DataCite |
Submission history
From: Zikun Nie [view email]
[v1]
Wed, 30 Sep 2026 05:56:18 UTC (5,045 KB)
[v2]
Thu, 5 Nov 2026 03:02:15 UTC (5,051 KB)
来源：arXiv cs.AI · arxiv.org