Department of Chemistry, Indian Institute of Technology, Hauz Khas, New Delhi, 110016, India.
Supercomputing Facility for Bioinformatics and Computational Biology, Indian Institute of Technology, Hauz Khas, New Delhi, 110016, India.
J Comput Aided Mol Des. 2020 Aug;34(8):817-830. doi: 10.1007/s10822-020-00305-1. Epub 2020 Mar 17.
Scoring functions are routinely deployed in structure-based drug design to quantify the potential for protein-ligand (PL) complex formation. Here, we present a new scoring function Bappl+ that is designed to predict the binding affinities of non-metallo and metallo PL complexes. Bappl+ outperforms other state-of-the-art scoring functions, achieving a high Pearson correlation coefficient of up to ~ 0.76 with low standard deviations. The biggest contributors to the increased performance are the use of a machine-learning model and the enlarged training dataset. We have also evaluated the performance of Bappl+ on target-specific proteins, which highlighted the limitations of our function and provides a way for further improvements. We believe that Bappl+ methodology could prove valuable in ranking candidate molecules against a target metallo or non-metallo protein by reliably predicting their binding affinities, thus helping in the drug discovery process.
打分函数在基于结构的药物设计中被常规用于量化蛋白质-配体（PL）复合物形成的潜力。在这里，我们提出了一种新的打分函数 Bappl+，旨在预测非金属和金属 PL 复合物的结合亲和力。Bappl+ 优于其他最先进的打分函数，实现了高达约 0.76 的高 Pearson 相关系数和低标准偏差。性能提高的最大贡献是使用机器学习模型和扩大的训练数据集。我们还评估了 Bappl+在特定于靶标的蛋白质上的性能，这突出了我们功能的局限性，并为进一步改进提供了途径。我们相信，Bappl+ 方法可以通过可靠地预测候选分子与靶标金属或非金属蛋白的结合亲和力，从而有助于药物发现过程，从而在对靶标金属或非金属蛋白的候选分子进行排序方面具有重要价值。
