发表机构
Shanghai Artificial Intelligence Laboratory; The University of Sydney; Shanghai Jiao Tong University（上海人工智能实验室; 悉尼大学; 上海交通大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究构建了酶促反应统一基准VenusRX-Bench，开发了统一序列到序列模型VenusRX，通过两阶段训练等技术弥合化学与酶反应的领域差距，在多任务上取得优异性能，揭示反应结构与催化功能的双向关系。
AI 中文摘要
现有反应模型主要学习分子转化，而酶促反应同时依赖分子结构与催化功能。我们将该问题建模为学习连接反应物、产物及酶委员会（Enzyme Commission, EC）注释的酶促反应空间。为表征该空间，我们引入VenusRX-Bench，这是一个用于正向反应预测、单步逆合成及EC编号预测的统一基准。VenusRX-Bench整合了多个生化数据库的反应，采用标准化整理、防泄漏划分及一致评估。对代表性化学与酶模型的基准测试显示，存在明显的化学到酶的领域差距，其成因包括领域数据有限、催化上下文依赖性以及大型生物分子结构建模的难度。为弥合该差距，我们开发了VenusRX，这是一个用于酶促反应的统一T5风格序列到序列模型。VenusRX联合学习正向预测、逆合成及反应重构，先在数百万个模板扩展反应上进行两阶段训练，再在真实生化反应上训练。此外，可选的EC条件注入催化上下文，而分子库约束解码则改进了复杂生物分子的生成。在基准任务及具有挑战性的泛化划分中，VenusRX在多数评估设置下相较于代表性化学与酶基线取得了最佳或具竞争力的性能。此外，EC信息持续提升反应预测效果，而学习到的反应表示支持准确的EC预测，揭示了反应结构与催化功能间的双向关系。VenusRX-Bench与VenusRX共同提供了一个用于阐明和建模酶促反应空间的统一框架。
英文摘要
Existing reaction models primarily learn molecular transformations, whereas enzy- matic reactions depend jointly on molecular structure and catalytic function. We formulate this problem as learning an enzymatic reaction space linking reactants, products, and Enzyme Commission (EC) annotations. To characterize this space, we introduce VenusRX-Bench, a unified benchmark for forward reaction prediction, single-step retrosynthesis, and EC-number prediction. VenusRX-Bench integrates reactions from multiple biochemical databases with standardized curation, leakage- controlled splits, and consistent evaluation. Benchmarking representative chemical and enzymatic models reveals a clear chemical-to-enzymatic domain gap, driven by limited domain data, catalytic-context dependency, and the difficulty of modeling large biomolecular structures. To bridge this gap, we develop VenusRX, a unified T5-style sequence-to-sequence model for enzymatic reactions. VenusRX jointly learns forward prediction, ret- rosynthesis, and reaction reconstruction, with two-stage training on millions of template-expanded reactions followed by real biochemical reactions. In addition, optional EC conditioning incorporates catalytic context, while Molecule Library- Constrained Decoding improves the generation of complex biomolecules. Across benchmark tasks and challenging generalization splits, VenusRX achieves the best or competitive performance on most evaluated settings over representative chem- ical and enzymatic baselines. Moreover, EC information consistently improves reaction prediction, while learned reaction representations support accurate EC prediction, revealing a bidirectional relationship between reaction structure and catalytic function. Together, VenusRX-Bench and VenusRX provide a unified framework for elucidating and modeling enzymatic reaction space
