抗体的适应性景观2:基准测试揭示了蛋白质人工智能模型尚未能够一致预测可开发性质
Michael Chungyoun1, Jeffrey Gray1,2
1Department of Chemical and Biomolecular Engineering, Johns Hopkins University, Baltimore, MD, 21287, USA.
bioRxiv : the preprint server for biology
|January 7, 2026
概括
抗体健康格局 (FLAb2) 基准显示,当前的人工智能模型难以预测治疗性抗体开发能力. 数据组成和内在特性显著影响模型性能,突出显示了在抗体设计中AI改进的领域.
科学领域:
- 生物技术是生物技术.
- 人工智能的人工智能
- 免疫学 免疫学 免疫学
背景情况:
- 准确预测治疗性抗体开发能力对于成功开发药物至关重要.
- 现有的蛋白质功能基准排除了抗体特异性数据,限制了AI模型的评估.
- 了解序列-结构-功能关系 (健身景观) 是抗体设计的关键.
研究的目的:
- 介绍针对抗体2 (FLAb2) 的健康格局,这是治疗性抗体设计的最大公共基准.
- 评估30个人工智能和生物物理模型在预测抗体开发性质方面的表现.
- 确定影响人工智能模型性能在抗体可开发性预测中的关键因素.
主要方法:
- 编制了FLAb2数据集,包含32项研究中的400多万个可开发性测试结果.
- 评估了七种抗体特性:热稳定性,表达,聚合,结合亲和力,药理动力学,多活性性和免疫性.
- 使用零射击和微调方法对30个AI和生物物理模型进行了基准测试.
主要成果:
- 人工智能模型在可开发数据集之间显示了有限的统计学显著相关性 (20%).
- 没有一个单一的模型能够准确地预测所有属性或跨多个相似数据集.
- 微调提高了性能,但数据量 (10^3点) 使得更简单的模型可以匹配复杂的模型.
- 进化信号对蛋白质语言模型预测有显著的贡献 (40%的生殖系编辑距离).
结论:
- 目前的AI模型需要显著改进,以可靠地预测治疗性抗体的可开发性.
- 训练数据的组成和内在的生物物理特性比模型架构更为关键.
- 在抗体设计中,FLAb2为基准测试和推进AI提供了宝贵的资源.
相关概念视频
01:13Physiological Pharmacokinetic Models: Assumption with Protein Binding
208
Physiological models with protein binding in pharmacokinetics offer a sophisticated approach to understanding drug disposition. These models consider drug-protein interactions, enabling them to effectively predict drug concentrations in different organs and tissues. This precision aids in accurate drug dosing, providing a significant advantage over conventional models. A key process within these models is equilibration, which ensures that drug concentrations achieve a steady state within the...
208
02:26Conservation of Protein Domains Over Different Proteins
14.0K
Protein domains are small structurally independent units that are part of a single amino acid chain. Although these domains are often structurally independent, they may rely on synergistic effects to perform their functions as part of a larger protein. Protein domains may be conserved within the same organism, as well as across different organisms.
A limited set of protein domains often duplicate and recombine during evolution. These domains can be organized in different combinations to...
A limited set of protein domains often duplicate and recombine during evolution. These domains can be organized in different combinations to...
14.0K
02:04Protein-protein Interfaces
14.4K
Many proteins form complexes to carry out their functions, making protein-protein interactions (PPIs) essential for an organism's survival. Most PPIs are stabilized by numerous weak noncovalent chemical forces. The physical shape of the interfaces determines the way two proteins interact. Many globular proteins have closely-matching shapes on their surfaces, which form a large number of weak bonds. Additionally, many PPIs occur between two helices or between a surface cleft and a...
14.4K
01:49Conserved Binding Sites
5.0K
Many proteins’ biological role depends on their interactions with their ligands, small molecules that bind to specific locations on the protein known as ligand-binding sites. Ligand-binding sites are often conserved among homologous proteins as these sites are critical for protein function.
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally...
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally...
5.0K