Learning Universal Representations of Intermolecular Interactions with ATOMICA
Fang, A.; Desgagne, M.; Zhang, Z.; Zhou, A.; Loscalzo, J.; Pentelute, B. L.; Zitnik, M. · bioinformatics · 2026-09-07 · 原文
DOI：10.1101/2025.04.02.646906作者：7 位
Molecular interactions underlie nearly all biological processes, yet most representation models describe isolated entities or specialize in a single molecular setting. Here, we introduce ATOMICA, an interaction-centered geometric deep learning model designed to learn transferable representations of intermolecular interfaces across proteins, small molecules, metal ions, and nucleic acids. Self-supervised pretraining on 2,037,972 interaction complexes yields representations spanning atoms, molecular building blocks, and complete interfaces. The latent space captures molecular identity and interaction context, supporting sequence recovery and zero-shot prioritization of residues involved in non-covalent interactions. ATOMICA provides structural information complementary to sequence representations on RNA and protein-pocket ligand classification. Across protein-pocket analyses, ATOMICA distinguishes ATP- and ADP-associated pocket states and retrieves ligand-matched pockets across proteins without detectable structural alignment. The latent space also enables cross-modal comparison, with orthosteric inhibitor embeddings retrieving regions proximal to native peptide and protein interface
讲义
讲义·推断 依据「原文」自动生成的结构化摘要（推断），非原文表述；以原文为准。
1. 人话版
Molecular interactions underlie nearly all biological processes, yet most representation models describe isolated entities or specialize in a single molecular setting.
Here, we introduce ATOMICA, an interaction-centered geometric deep learning model designed to learn transferable representations of intermolecular interfaces across proteins, small molecules, metal ions, and nucleic acids.
2. 领域脉络
本文类目：bioinformatics，属于其所在研究脉络的最新进展。
3. 机制拆解
The latent space captures molecular identity and interaction context, supporting sequence recovery and zero-shot prioritization of residues involved in non-covalent interactions.
ATOMICA provides structural information complementary to sequence representations on RNA and protein-pocket ligand classification.
4. 证据与数字
Self-supervised pretraining on 2,037,972 interaction complexes yields representations spanning atoms, molecular building blocks, and complete interfaces.
5. 反例与边界
摘要未声明局限与反例——这是需要警惕的信号，精读时先问边界。
6. 跨领域连接与意外收获
思考本文机制能否迁移到你正在跟进的问题。
7. 可复用方法
把本文机制与你手头项目对照，找一个两周内能验证的最小实验。
8. 术语表
精读时把不熟的术语记入此处，作为下次回忆的锚点。