Predicting unseen antibodies’ neutralizability via adaptive graph neural networks

Jie Zhang ^1,9,10 , Yishan Du^1,10, Pengfei Zhou¹, Jinru Ding1, Shuai Xia²,Qian Wang², Feiyang Chen^1,3, Mu Zhou⁴, Xuemei Zhang⁵, Weifeng Wang⁶,Hongyan Wu ⁷ , Lu Lu ² & Shaoting Zhang ^1,8

Most natural and synthetic antibodies are ‘unseen’. That is, the demonstration of their neutralization effects with any antigen requires laborious and costly wet-lab experiments. The existing methods that learn antibody representations from known antibody–antigen interactions are unsuitable for unseen antibodies owing to the absence of interaction instances. The DeepAAI method proposed herein learns unseen antibody representations by constructing two adaptive relation graphs among antibodies and antigens and applying Laplacian smoothing between unseen and seen antibodies’ representations. Rather than using static protein descriptors, DeepAAI learns representations and relation graphs ‘dynamically’, optimized towards the downstream tasks of neutralization prediction and 50% inhibition concentration estimation. The performance of DeepAAI is demonstrated on human immunodeficiency virus, severe acute respiratory syndrome coronavirus 2, influenza and dengue. Moreover, the relation graphs have rich interpretability. The antibody relation graph implies similarity in antibody neutralization reactions, and the antigen relation graph indicates the relation among a virus’s different variants. We accordingly recommend probable broad-spectrum antibodies against new variants of these viruses.

¹SenseTime, Shanghai, China. ²Key Laboratory of Medical Molecular Virology (MOE/NHC/CAMS), School of Basic Medical Sciences, Shanghai Institute of Infectious Disease and Biosecurity, Fudan University, Shanghai, China. ³Department of Computer Science, The University of California, Los Angeles, Los Angeles, CA, USA. ⁴SenseBrain Research, San Jose, CA, USA. ⁵School of Pharmacy, Fudan University, Shanghai, China. ⁶OrigiMed, Shanghai, China. ⁷Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China. ⁸Shanghai Artificial Intelligence Laboratory, Shanghai, China. ⁹Advisory Committee for AI-enabled Health Solution, Merck, Shanghai, China. ¹⁰These authors contributed equally: Jie Zhang and Yishan Du.e-mail: stzhangjie@hotmail.com; hy.wu@siat.ac.cn; lul@fudan.edu.cn; zhangshaoting@pjlab.org.cn