[论文解读] Learning to Dock: Geometric Deep Learning for Predicting Supramolecular Host-Guest Complexes

Zidi Wang, Tao Zhang+8 more|arXiv (Cornell University)|Jan 18, 2026

Supramolecular Chemistry and Complexes被引用 0

一句话总结

论文引入 DeepHostGuest，一种几何深度学习框架，预测宿主-客体结合构象并在跨多样超分子系统中实现准确的结合自由能计算。

ABSTRACT

Predicting non-covalent host-guest recognition remains challenging due to the complex interplay of electrostatics, dispersion, and steric effects, and the limited transferability of existing docking approaches to synthetic supramolecular systems. Here we present DeepHostGuest, a geometric deep-learning framework that learns generalizable recognition principles directly from experimentally resolved host-guest structures. Hosts are encoded as electrostatic surfaces and guests as molecular graphs, enabling transferable learning across diverse supramolecular systems. DeepHostGuest achieves high-accuracy predictions (RMSD $\leq 2$ Angstrom for 80.8% of test cases), substantially outperforming classical docking without case-specific tuning. Notably, the method generalizes beyond its training domain to crystalline sponge systems, accurately capturing the binding of large amphiphilic molecules within metal-organic cages. Beyond predicting binding conformations, the structures generated by DeepHostGuest serve as a reliable basis for accurate binding free-energy calculations. Density Functional Theory (DFT)-calculated affinities correlate well with experiment, enabling structure-property relationships across 876 host-guest complexes spanning 34 host families. Interpretable feature analysis reveals that binding strength arises from a cooperative interplay of host polarity, guest hydrophobicity, and geometric complementarity, with distinct design regimes across supramolecular classes. Together, these results establish data-driven molecular recognition as a practical route to predictive supramolecular design, enabling high-throughput virtual screening and rational optimization of functional host-guest systems.

研究动机与目标

• 促使非共价宿主–客体识别的预测性超分子设计.
• 开发可迁移的学习框架，使其在多样的超分子系统中具有泛化能力.
• 将宿主编码为静电表面、客体编码为分子图，以捕捉相互作用。

提出的方法

• 将宿主编码为静电表面以捕捉极性与电荷分布。
• 将客体编码为分子图以表示拓扑和连通性。
• 使用几何深度学习从实验解析的结构中学习识别原理。
• 训练以预测结合构象并生成适用于结合能计算的结构。
• 评估在晶体海绵系统以及金属有机笼中大两性体客体的可迁移性。

实验结果

研究问题

• RQ1 几何深度学习模型是否能够从实验结构中学习到宿主–客体识别的一般原理？
• RQ2 将宿主编码为静电表面、客体编码为图形在跨越多样超分子类别中的可迁移性在多大程度上实现？
• RQ3 生成的对接结构在多大程度上支持准确的结合自由能计算？
• RQ4 该方法能否处理晶体海绵系统以及 MOF 笼中的大两性体客体？
• RQ5 在不同宿主家族中，导致结合强度的可解释因素有哪些？

主要发现

• DeepHostGuest 在测试用例中实现了 RMSD ≤ 2 Å 的比例为 80.8%。
• 在不进行针对性案例微调的情况下，优于经典对接方法。
• 该方法对晶体海绵系统及 MOF 笼中的大两性体客体具有泛化能力。
• 在覆盖 876 个宿主–客体复合、跨 34 个宿主家族的实验中，DFT 计算的亲和力与实验结果高度相关。
• 可解释性分析表明，结合强度来自协同的宿主极性、客体疏水性以及几何互补性。