用机器学习加速抗体设计，10个月变几天。
ImmunoAI: Accelerated Antibody Discovery Using Gradient-Boosted Machine Learning with Thermodynamic-Hydrodynamic Descriptors and 3D Geometric Interface Topology
- 结合热力学、流体力学和三维结构拓扑特征，用梯度提升模型预测抗体亲和力。
- 候选抗体数量减少89%，对新冠病毒抗体预测误差降至0.92（原1.70）。
- 可快速筛选针对新病毒突变株的高亲和力抗体，适合疫情应急研发。
人副流感病毒（hMPV）对儿童、老年人及免疫缺陷人群构成严重威胁。传统抗体发现流程需10-12个月，难以应对突发疫情。本研究提出ImmunoAI，一种基于梯度提升的机器学习框架，利用热力学、流体力学和3D几何界面拓扑描述符预测高亲和力抗体。研究构建了包含213个抗体-抗原复合物的数据集，提取几何与理化特征，并训练LightGBM回归器实现高精度亲和力预测。模型将候选抗体搜索空间缩减89%；在117个SARS-CoV-2结合对上微调后，均方根误差（RMSE）从1.70降至0.92。针对hMPV A2.2变异株缺乏实验结构的问题，使用AlphaFold2预测其三维结构。该优化模型识别出两个靶向关键突变位点（G42V和E96K）的候选抗体，预测亲和力达皮摩尔级，具备优异的实验验证潜力。综上，ImmunoAI显著缩短设计周期，支持结构驱动的病毒暴发快速响应。
原文摘要 · Abstract (English)
Human metapneumovirus (hMPV) poses serious risks to pediatric, elderly, and immunocompromised populations. Traditional antibody discovery pipelines require 10-12 months, limiting their applicability for rapid outbreak response. This project introduces ImmunoAI, a machine learning framework that accelerates antibody discovery by predicting high-affinity candidates using gradient-boosted models trained on thermodynamic, hydrodynamic, and 3D topological interface descriptors. A dataset of 213 antibody-antigen complexes was curated to extract geometric and physicochemical features, and a LightGBM regressor was trained to predict binding affinity with high precision. The model reduced the antibody candidate search space by 89%, and fine-tuning on 117 SARS-CoV-2 binding pairs further reduced Root Mean Square Error (RMSE) from 1.70 to 0.92. In the absence of an experimental structure for the hMPV A2.2 variant, AlphaFold2 was used to predict its 3D structure. The fine-tuned model identified two optimal antibodies with predicted picomolar affinities targeting key mutation sites (G42V and E96K), making them excellent candidates for experimental testing. In summary, ImmunoAI shortens design cycles and enables faster, structure-informed responses to viral outbreaks.
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。