使用蛋白质同质学和基于基的转移学习来更准确地预测结合亲和关系
Justin Purnomo1, Caitlin Kim2, Kunyang Sun1
1Kenneth S. Pitzer Theory Center and Department of Chemistry, University of California, Berkeley, California 94720, United States.
Journal of chemical information and modeling
|February 6, 2026
概括
一个新的混合框架UCBind准确地预测了用于药物发现的蛋白质-连接体结合亲缘关系. 它将类似性转移与深度学习相结合,提高化学图书馆的效率和性能.
科学领域:
- 计算化学是一种计算化学.
- 药物发现 药物发现
- 生物信息学是一种生物信息学.
背景情况:
- 准确预测蛋白质 - 配体结合亲缘关系对于有效的药物发现至关重要.
- 从生成模型中评估大型化学库和新型分子需要快速和精确的方法.
- 现有的方法可能会面临各种数据集的可扩展性和准确性的挑战.
研究的目的:
- 开发和验证UCBbind,这是一种混合计算框架,用于高效和准确地预测蛋白质-联体结合亲和关系.
- 将基于相似性的转移学习模块与深度学习预测模块集成在一起.
- 评估UCBbind在与药物发现相关的各种基准数据集中的表现.
主要方法:
- UCBind采用混合方法,将基于相似性的转移模块与深度学习预测模块相结合.
- 当可用时,从相似的参考蛋白-联结体对中转移实验数据.
- 当没有足够相似的参考数据存在时,使用深度学习模块.
- 性能在CASF-2016,HiQBind (2020年后) 和COVID Moonshot数据库上进行了基准测试.
主要成果:
- 在多个基准数据集上,UCBind实现了最先进的预测性能.
- 该框架在测试条目中表现出卓越的准确性,这些条目与参考蛋白-连接体对具有很高的相似性.
- 性能增长对于表征良好的参考蛋白和连接体尤其显著.
结论:
- 在药物发现中,UCBind提供了一种高效和准确的解决方案,用于预测蛋白质 - 连接体结合亲缘关系.
- 混合框架通过转移学习和深度学习有效地利用现有数据.
- UCBind显示出支持下游计算任务的前景,包括绑定站点预测和分类.
相关概念视频
Ligand Binding Sites
15.1K
Proteins are dynamic macromolecules that carry out a wide variety of essential processes; however, the activities of most proteins depend on their interactions with other molecules or ions, known as ligands.
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-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...
15.1K
Ligand Binding Sites
8.8K
8.8K
Ligand Binding and Linkage
5.6K
Allosteric proteins have more than one ligand binding site; the binding of a ligand to any of these sites influences the binding of ligands to the other sites. When a protein is allosteric, its binding sites are called coupled or linked. In the case of enzymes, the site that binds to the substrate is known as the active site and the other site is known as the regulatory site. When a ligand binds to the regulatory site, this leads to conformational changes in the protein that can influence...
5.6K
Ligand Binding and Linkage
4.1K
4.1K
Homologous Recombination
63.3K
The basic reaction of homologous recombination (HR) involves two chromatids that contain DNA sequences sharing a significant stretch of identity. One of these sequences uses a strand from another as a template to synthesize DNA in an enzyme-catalyzed reaction. The final product is a novel amalgamation of the two substrates. To ensure an accurate recombination of sequences, HR is restricted to the S and G2 phases of the cell cycle. At these stages, the DNA has been replicated already and the...
63.3K
The Equilibrium Binding Constant and Binding Strength
15.1K
The equilibrium binding constant (Kb) quantifies the strength of a protein-ligand interaction. Kb can be calculated as follows when the reaction is at equilibrium:
15.1K


