TEMPL Pipeline Core Dataset

This dataset contains the essential data files required to run the TEMPL (Template-based Protein-Ligand) pose prediction pipeline: pre-computed ESM-2 protein embeddings for 18,902 PDBBind structures and processed ligand molecules. The dataset enables template-based pose prediction research with standardized molecular data.本数据集包含运行TEMPL（Template-based Protein-Ligand）构象预测流程所需的核心数据文件：针对18902个PDBBind结构的预计算ESM-2蛋白质嵌入，以及经过预处理的配体分子。本数据集可为基于模板的蛋白质-配体构象预测研究提供标准化的分子数据支撑。