用三维几何深度学习预测药物-蛋白结合，更准更可信。
EquiCPI: SE(3)-Equivariant Geometric Deep Learning for Structure-Aware Prediction of Compound-Protein Interactions
- 基于原子点云的旋转平移反射等变神经网络，保留三维结构对称性。
- 在BindingDB和DUD-E数据集上表现达顶尖水平，超越现有方法。
- 适合做新药研发、分子对接和结构生物学研究的科研人员。
准确预测化合物-蛋白相互作用（CPI）仍是计算药物发现的核心挑战。现有基于序列的方法依赖分子指纹或图表示，却忽视了结合亲和力的关键三维（3D）结构因素。为弥补这一空白，我们提出EquiCPI，一种端到端的几何深度学习框架，融合第一性原理结构建模与SE(3)-等变神经网络。该流程通过ESMFold生成蛋白质的3D原子坐标，用DiffDock-L生成配体结构，再经物理引导的构象重排序与等变特征学习。核心采用在原子点云上的SE(3)-等变消息传递机制，保持旋转、平移和反射下的对称性，并通过球谐函数的张量积层次编码局部相互作用模式。模型在BindingDB（亲和力预测）和DUD-E（虚拟筛选）上评估，性能达到或超过当前最先进深度学习方法。
原文摘要 · Abstract (English)
Accurate prediction of compound-protein interactions (CPI) remains a cornerstone challenge in computational drug discovery. While existing sequence-based approaches leverage molecular fingerprints or graph representations, they critically overlook three-dimensional (3D) structural determinants of binding affinity. To bridge this gap, we present EquiCPI, an end-to-end geometric deep learning framework that synergizes first-principles structural modeling with SE(3)-equivariant neural networks. Our pipeline transforms raw sequences into 3D atomic coordinates via ESMFold for proteins and DiffDock-L for ligands, followed by physics-guided conformer re-ranking and equivariant feature learning. At its core, EquiCPI employs SE(3)-equivariant message passing over atomic point clouds, preserving symmetry under rotations, translations, and reflections, while hierarchically encoding local interaction patterns through tensor products of spherical harmonics. The proposed model is evaluated on BindingDB (affinity prediction) and DUD-E (virtual screening), EquiCPI achieves performance on par with or exceeding the state-of-the-art deep learning competitors.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。