发表机构
University of Birmingham（伯明翰大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出物理信息双态查询（DSQ）架构，将MWC变构模型嵌入神经网络，通过可学习正交查询解耦受体活性/非活性态，以对比排序约束预测GPCR配体生物活性，在激动剂子集上优于基线，但低同源性受体上存在局限。
AI 中文摘要
预测小分子对G蛋白偶联受体（GPCRs）的生物活性谱是药物发现中的一个挑战。尽管深度学习加速了结合亲和力的预测，但现有方法往往因忽略动态构象平衡而难以区分功能效力。此外，基于结构的方法常受限于高分辨率活性态晶体结构的稀缺以及静态表示中构象状态的不可区分性。为弥合黑箱预测与生物物理现实之间的差距，我们提出了双态查询（DSQ），一种物理信息多模态架构，将Monod-Wyman-Changeux（MWC）变构模型显式嵌入神经网络中。与依赖显式3D结构的传统模型不同，DSQ利用可学习的正交查询来提取受体活性态和非活性态的解耦表示。这些潜在表示由一种新颖的神经MWC门控模块控制，该模块从配体-状态亲和力与受体固有构象能垒之间的热力学竞争中数学推导出受体激活概率。还引入了对比排序目标以强制执行差异亲和力约束，确保物理一致性。大量实验表明，DSQ优于其他基线，特别是在激动剂子集上。额外的同源性分层、温度敏感性、扰动、聚类和效率分析表明，DSQ提供了有用的热力学归纳偏置，同时也暴露了在低同源性受体上的明显局限性。代码可在以下网址获取：此https URL。
英文摘要
Predicting the bioactivity profiles of small molecules against G protein-coupled receptors (GPCRs) is a challenge in drug discovery. Although deep learning has accelerated the prediction of binding affinities, existing approaches often struggle to distinguish between functional efficacies because they neglect dynamic conformational equilibria. Furthermore, structure-based methods are frequently limited by the scarcity of high-resolution active-state crystal structures and the indistinguishability of conformational states in static representations. To bridge the gap between black-box prediction and biophysical reality, we propose Dual-State Query (DSQ), a physics-informed multimodal architecture that explicitly embeds the Monod-Wyman-Changeux (MWC) model of allostery within a neural network. Unlike conventional models that rely on explicit 3D structures, DSQ utilizes learnable orthogonal queries to extract disentangled representations of active and inactive receptor states. These latent representations are governed by a novel neural MWC gating module, which mathematically derives the probability of receptor activation from thermodynamic competition between ligand-state affinities and the receptor's intrinsic conformational energy barrier. A contrastive ranking objective is also introduced to enforce differential affinity constraints, ensuring physical consistency. Extensive experiments demonstrate that DSQ outperforms other baselines, particularly for the agonist subset. Additional homology-stratified, temperature-sensitivity, perturbation, clustering, and efficiency analyses show that DSQ provides useful thermodynamic inductive bias, while also exposing a clear limitation on low-homology receptors. The code is available at https://github.com/jiankliu/DSQ.
CommentsAccepted by APBC2026
