多任务生物试验预培训对蛋白质 - 配体结合亲缘关系的预测
Jiaxian Yan1, Zhaofeng Ye2, Ziyi Yang2
1Anhui Province Key Lab of Big Data Analysis and Application, University of Science and Technology of China, JinZhai Road, 230026, Anhui, China.
这项研究引入了多任务生物测试预训 (MBP),这是预测蛋白质 - 配体结合亲和力 (PLBA) 的新框架. MBP利用具有多种亲和度标签的大型数据集来改善药物发现中的模型概括性.
科学领域:
- 计算化学是一种计算化学.
- 药物发现 药物发现
- 机器学习 机器学习
背景情况:
- 预测蛋白质 - 配体结合亲和力 (PLBA) 对药物发现至关重要.
- 目前用于PLBA预测的深度学习模型受到数据稀缺和概括问题的限制.
- 像ChEMBL这样现有的大规模亲和数据集具有不一致的标签和实验条件.
研究的目的:
- 为基于结构的PLBA预测提出一个新的预培训框架,即多任务生物测试预培训 (MBP).
- 为了构建一个全面的预训练数据集,ChEMBL-Dock,包含超过300k的亲和度标签和2.8M的对接3D结构.
- 通过从多样化和杂的数据中学习强大的结构知识,提高PLBA预测模型的概括能力.
主要方法:
- 开发了多任务生物测试预培训 (MBP) 框架.
- 创建了ChEMBL-Dock数据集,整合了各种亲和标签和3D结构.
- 采用多任务学习来预测生物试验中的不同亲和标签和相对排名.
主要成果:
- MBP在基于结构的PLBA预测方面表现出显著的能力.
- 预培训方法有效地学习可转移的结构知识.
- 开发的ChEMBL-Dock数据集解决了现有的亲和数据的局限性.
结论:
- MBP是PLBA预测的第一个亲和力预训模型.
- 该框架显示了推动药物发现的巨大潜力.
- MBP为处理杂和多样化的生物试验数据提供了强大的解决方案.
更多相关视频
06:50Author Spotlight: A Computational Approach to Decipher Amino Acid Preferences in Multispecific Protein-Protein Interactions
Published on: January 26, 2024
10:29Quantitative Structure-Activity Relationship, Activity Prediction, and Molecular Dynamics of Non-nucleotide Reverse Transcriptase Inhibitors
Published on: May 9, 2025
相关概念视频
The Equilibrium Binding Constant and Binding Strength
Ligand Binding Sites
Protein-ligand interactions are quite specific; even though numerous potential ligands surround a cellular protein at any given time, only a particular ligand can bind to that protein. Moreover, a ligand binds only to a dedicated area on the surface of the protein, known as the...
Protein-protein Interfaces
Conserved Binding Sites
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...
Ligand Binding and Linkage
