arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2412.12979q-bio.BM
收藏

通过强化学习引导生成蛋白质语言模型

Reinforcement Learning Guides Generative Protein Language Models

Centre for Genomic Regulation, the Barcelona Institute of Science and Technology(基因组调控中心,巴塞罗那科学技术研究所);Universitat Pompeu Fabra(庞培法布拉大学);Universitat de Barcelona, Facultat de Farmàcia i Ciències de l’Alimentació(巴塞罗那大学,药学与食品科学学院);Stanford University(斯坦福大学);Arc Institute(ARC研究所);Institució Catalana de Recerca i Estudis Avançats (ICREA)(加泰罗尼亚高级研究学院)

Filippo Stocco, Maria Artigues-Lleixa, Andrea Hunklinger, Michele Garibbo, Talal Widatalla, Marc Guell, Noelia Ferruz

AI总结:

通过强化学习引导生成蛋白质语言模型,实现EGFR结合物设计中结合亲和力的显著提升。

摘要:

蛋白质语言模型(pLMs)在生成功能性蛋白质方面展现了广泛序列空间中的成功,但缺乏按需设计高适应度变体的能力。在此,我们通过应用强化学习(RL)来迭代引导pLMs朝向用户定义的目标。我们证明RL能够通过长进化轨迹在几次迭代中引导pLMs朝向各种蛋白质特性,如拓扑结构或结合亲和力。我们将我们的框架应用于表皮生长因子受体(EGFR)结合物的设计,实现了在两次迭代中结合亲和力的26倍提升。

英文摘要:

Protein engineering can optimize molecules for biotechnology and therapeutics, but navigating the high-dimensional sequence landscape remains challenging. Protein language models (pLMs) have shown to to generate functional proteins far from natural sequences, yet their outputs tend to reflect prevalent properties in training data, limiting discovery of rare properties such as high catalytic activity or thermostability. Here, we introduce ProtRL, a reinforcement learning framework for pLMs that iteratively updates model parameters to maximize externally defined reward functions. Across diverse design tasks, ProtRL shifts generation toward specified objectives while maintaining sequence diversity. We demonstrate the optimization of target folds, bounded and continuous fitness predictors, and multi-objective optimization in binder design. As a proof of concept, we applied ProtRL to experimental feedback for the engineering of epidermal growth factor receptor binders. Testing fewer than 100 designed variants across the experimental campaign, ProtRL-guided optimization provided a final round in which 16 of 22 variants bound EGFR. The best variant showed a dissociation constant of 5.5 nM, representing a nine-fold improvement over wild-type EGF and higher affinity than previously reported EGF variants identified through substantially larger screening campaigns. Our code and models are publicly available at github.com/AI4PDLab/ProtRL

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。

↑