arXiv 2506.009252025-06-01q-bio.BMcs.CVcs.LG

ProtInvTree：基于奖励引导树搜索的审慎蛋白质逆向折叠

ProtInvTree: Deliberate Protein Inverse Folding with Reward-guided Tree Search

Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；AI Lab, Research Center for Industries of the Future, Westlake University（未来产业研究院人工智能实验室）；Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高陵人工智能学院）

Mengdi Liu, Xiaoxue Cheng, Zhangyang Gao, Hong Chang, Cheng Tan, Shiguang Shan, Xilin Chen

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

ProtInvTree 提出首个奖励引导树搜索框架，将蛋白质逆向折叠建模为逐步决策过程，通过聚焦-落地动作机制和跳跃式去噪策略，在不重新训练的情况下生成结构一致且多样化的蛋白质序列，并在多个基准上超越现有方法。

摘要：

设计能够折叠成目标三维结构的蛋白质序列（即蛋白质逆向折叠）是蛋白质工程中的一项基本挑战。尽管最近的深度学习方法通过恢复天然序列取得了令人瞩目的性能，但它们往往忽视了该问题的一对多本质：多个不同的序列可以折叠成同一结构。这促使我们需要一种能够在保持结构一致性的同时设计多样化序列的生成模型。为了解决这一权衡问题，我们提出了 ProtInvTree，这是首个用于蛋白质逆向折叠的奖励引导树搜索框架。ProtInvTree 将序列生成重新表述为一个审慎的、逐步的决策过程，通过自我评估、前瞻和回溯来探索多条设计路径并利用有前景的候选方案。我们提出了一种两阶段的聚焦与落地动作机制，将位置选择和残基生成解耦。为了高效评估中间状态，我们引入了一种跳跃式去噪策略，避免完整的 rollout。ProtInvTree 建立在预训练蛋白质语言模型之上，通过在不重新训练的情况下扩展搜索深度和广度来支持灵活的测试时扩展。实验表明，ProtInvTree 在多个基准上优于最先进的基线方法，生成了结构一致且多样化的序列，包括那些远离天然真实序列的序列。

英文摘要：

Designing protein sequences that fold into a target 3D structure, known as protein inverse folding, is a fundamental challenge in protein engineering. While recent deep learning methods have achieved impressive performance by recovering native sequences, they often overlook the one-to-many nature of the problem: multiple diverse sequences can fold into the same structure. This motivates the need for a generative model capable of designing diverse sequences while preserving structural consistency. To address this trade-off, we introduce ProtInvTree, the first reward-guided tree-search framework for protein inverse folding. ProtInvTree reformulates sequence generation as a deliberate, step-wise decision-making process, enabling the exploration of multiple design paths and exploitation of promising candidates through self-evaluation, lookahead, and backtracking. We propose a two-stage focus-and-grounding action mechanism that decouples position selection and residue generation. To efficiently evaluate intermediate states, we introduce a jumpy denoising strategy that avoids full rollouts. Built upon pretrained protein language models, ProtInvTree supports flexible test-time scaling by expanding the search depth and breadth without retraining. Empirically, ProtInvTree outperforms state-of-the-art baselines across multiple benchmarks, generating structurally consistent yet diverse sequences, including those far from the native ground truth.

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。