BioLiP2-Opt
收藏资源简介:
BioLiP2-Opt数据集是由加州大学伯克利分校的研究团队开发的,旨在为蛋白质-配体结合亲和力预测提供高质量的结构数据。该数据集包含约48,000个非共价蛋白质-配体复合物的结构及其结合亲和力注释。数据集的创建过程包括自动化算法对PDBBind数据集的优化和结构准备,确保数据的高质量和一致性。BioLiP2-Opt数据集主要应用于生物学和药物发现领域,旨在提高评分函数(SFs)的准确性和可靠性,从而优化计算机辅助药物设计。
The BioLiP2-Opt dataset was developed by a research team at the University of California, Berkeley, aiming to provide high-quality structural data for protein-ligand binding affinity prediction. This dataset contains approximately 48,000 structures of non-covalent protein-ligand complexes along with their binding affinity annotations. The dataset creation process involved optimizing and structuring the PDBBind dataset using automated algorithms, ensuring high data quality and consistency. The BioLiP2-Opt dataset is primarily applied in the fields of biology and drug discovery, with the goal of enhancing the accuracy and reliability of scoring functions (SFs) to optimize computer-aided drug design.




