PPB-Affinity: Protein-Protein Binding Affinity dataset for AI-based protein drug discovery

Prediction of protein-protein binding (PPB) affinity plays an important role in large-molecular drug discovery. Deep learning (DL) has been adopted to predict the change of PPB binding affinity upon mutation, but there was a scarcity of studies predicting the PPB affinity itself. The major reason is the paucity of open-source dataset concerning PPB affinity. Therefore, the current study aimed to introduce and disclose a PPB affinity dataset (PPB-Affinity), which will definitely benefit the development of applicable DL to predict the PPB affinity. The PPB-Affinity dataset contains key information such as crystal structures of protein-protein complexes (with or without protein mutation patterns), PPB affinity, receptor protein chain, ligand protein chain, etc. To the best of our knowledge, this is the largest and publicly available PPB-Affinity dataset, which may finally help the industry in improving the screening efficiency of discovering new large-molecular drugs. Files are orginized as follows: - PPB-Affinity.xlsx - PDB/ - Affinity Benchmark/ - file1.pdb - file2.pdb - ATLAS/ - PDBbindCN/ - SAbDab/ - SKEMPIv2.0/

蛋白质-蛋白质结合（Protein-Protein Binding，PPB）亲和力预测在大分子药物研发中具有重要作用。深度学习（Deep Learning，DL）已被应用于预测突变引发的PPB结合亲和力变化，但目前针对PPB亲和力本身的预测研究仍较为匮乏，其核心原因在于当前缺乏与PPB亲和力相关的开源数据集。因此，本研究旨在介绍并公开一款PPB亲和力数据集（PPB-Affinity），以期为适用于PPB亲和力预测的深度学习方法研发提供助力。

该PPB-Affinity数据集包含多项核心信息，例如蛋白质-蛋白质复合物的晶体结构（含/不含蛋白质突变模式）、PPB亲和力、受体蛋白链、配体蛋白链等。

据我们所知，这是目前规模最大且可公开获取的PPB-Affinity数据集，有望最终助力行业提升新型大分子药物研发的筛选效率。

文件组织形式如下：
- PPB-Affinity.xlsx
- PDB/
- Affinity Benchmark/
- file1.pdb
- file2.pdb
- ATLAS/
- PDBbindCN/
- SAbDab/
- SKEMPIv2.0/

搜集汇总

背景与挑战

背景概述

PPB-Affinity是一个用于AI驱动的大分子药物发现的蛋白质-蛋白质结合亲和力数据集，包含复合物晶体结构和亲和力等关键信息，是目前最大且公开可用的此类数据集。