面向酶动力学参数的多模态蛋白质语言模型：从底物识别到构象适配
Multimodal Protein Language Models for Enzyme Kinetic Parameters: From Substrate Recognition to Conformational Adaptation
把「先识别底物、再适配构象」的两阶段条件注入做成可插拔适配器（MRCA + 几何感知 MoE），并用 RKHS 上的分布对齐约束微调不破坏预训练先验——这套「冻结主干 + 分阶段跨模态注入 + 分布正则」的范式可直接迁移到视觉-语言或图像-结构条件生成任务中。
原文依据 Geometry-aware Mixture-of-Experts (G-MoE) then integrates active-site structure and routes samples to pocket-specialized experts to reflect induced fit.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论预测酶动力学参数可量化酶在特定生化条件下催化特定底物的效率。转换数（k_cat）、米氏常数（K_m）和抑制常数（K_i）等经典参数共同取决于酶序列、底物化学性质以及结合过程中活性位点的构象适配。许多学习流程将该过程简化为酶与底物之间的静态相容性问题，通过浅层操作融合二者表征并回归单一数值。此类建模忽略了催化的分阶段特性，即同时涉及底物识别与构象适配。为此，我们将动力学预测重新表述为分阶段的多模态条件建模问题，并提出酶-反应桥接适配器（ERBA），在保留蛋白质语言模型（PLM）生化先验的同时，通过微调向其注入跨模态信息。ERBA 分两个阶段施加条件：分子识别交叉注意力（MRCA）首先将底物信息注入酶表征以刻画特异性；几何感知混合专家（G-MoE）随后整合活性位点结构，并将样本路由至口袋专用专家以反映诱导契合。为保持语义保真度，酶-底物分布对齐（ESDA）在再生核希尔伯特空间中强制 PLM 流形内的分布一致性。在三个动力学终点和多个 PLM 主干上的实验表明，与仅序列和浅层融合基线相比，ERBA 取得了一致增益和更强的分布外性能，为可扩展的动力学预测提供了具有生物学依据的路径，并为引入辅因子、突变和时间分辨结构线索奠定了基础。
英文原文摘要 1905 字符
Predicting enzyme kinetic parameters quantifies how efficiently an enzyme catalyzes a specific substrate under defined biochemical conditions. Canonical parameters such as the turnover number (k_\text cat ), Michaelis constant (K_\text m ), and inhibition constant (K_\text i ) depend jointly on the enzyme sequence, the substrate chemistry, and the conformational adaptation of the active site during binding. Many learning pipelines simplify this process to a static compatibility problem between the enzyme and substrate, fusing their representations through shallow operations and regressing a single value. Such formulations overlook the staged nature of catalysis, which involves both substrate recognition and conformational adaptation. In this regard, we reformulate kinetic prediction as a staged multimodal conditional modeling problem and introduce the Enzyme-Reaction Bridging Adapter (ERBA), which injects cross-modal information via fine-tuning into Protein Language Models (PLMs) while preserving their biochemical priors. ERBA performs conditioning in two stages: Molecular Recognition Cross-Attention (MRCA) first injects substrate information into the enzyme representation to capture specificity; Geometry-aware Mixture-of-Experts (G-MoE) then integrates active-site structure and routes samples to pocket-specialized experts to reflect induced fit. To maintain semantic fidelity, Enzyme-Substrate Distribution Alignment (ESDA) enforces distributional consistency within the PLM manifold in a reproducing kernel Hilbert space. Experiments across three kinetic endpoints and multiple PLM backbones, ERBA delivers consistent gains and stronger out-of-distribution performance compared with sequence-only and shallow-fusion baselines, offering a biologically grounded route to scalable kinetic prediction and a foundation for adding cofactors, mutations, and time-resolved structural cues.