CryptoBench:神秘的蛋白质 - 连接物结合站点数据集和基准
Vít Škrhák1, Marian Novotný2, Christos P Feidakis2
1Department of Software Engineering, Faculty of Mathematics and Physics, Charles University, 118 00 Prague, Czech Republic.
一个新的基准数据集,CryptoBench,可以更好地预测蛋白质中的加密结合位点 (CBS). 基于序列的方法在CBS检测的基于结构的方法上显示出更高的性能,建立了一个新的基线.
科学领域:
- 计算生物学是一种计算生物学.
- 结构生物信息学 结构生物信息学
- 药物发现 药物发现
背景情况:
- 预测蛋白质 - 配体结合部位对于研究和医学至关重要.
- 现有的方法经常使用连接体 (hol) 蛋白质结构,这对于密码结合点 (CBS) 是有问题的.
- 这种对全息状态的依赖导致对CBS检测的不切实际的性能期望.
研究的目的:
- 介绍CryptoBench,这是一个全面的基准数据集,用于培训和评估新的CBS预测方法.
- 使用CryptoBench建立现有的CBS预测方法的性能基准.
- 为了比较基于序列和基于结构的CBS检测方法的疗效.
主要方法:
- CryptoBench 是使用 Apo-holo 蛋白质对构建的,其结合部位具有显著的结构变化.
- 数据集包括 1107 个结构,具有预定义的交叉验证分割.
- 基于序列的方法使用了蛋白质语言模型嵌入,而基于结构的方法包括PocketMiner和P2Rank.
主要成果:
- 开发的基于序列的方法在预测CBS余量方面超过了PocketMiner和P2Rank.
- 关键指标如AUC,AUCPR,MCC和F1分数证明了基于序列的方法的优越性.
- 到目前为止,CryptoBench 是CBS预测最广泛的数据集.
结论:
- 基于序列的方法为未来的CBS预测研究提供了强有力的基准.
- CryptoBench 是一个基础资源,用于推进加密绑定站点检测领域.
- 数据集和代码是公开的,以促进进一步的研究和开发.
更多相关视频
10:21Author Spotlight: Streamlining Protein Target Prediction and Validation via Molecular Docking and CETSA
Published on: February 23, 2024
08:31Biosensor-based High Throughput Biopanning and Bioinformatics Analysis Strategy for the Global Validation of Drug-protein Interactions
Published on: December 1, 2020
相关概念视频
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...
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...
Protein-protein Interfaces
Ligand Binding and Linkage
The Equilibrium Binding Constant and Binding Strength
Protein Networks
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
