Innovation Institute for Artificial Intelligence in Medicine of Zhejiang University, College of Pharmaceutical Sciences and Cancer Center, Zhejiang University, Hangzhou 310058, Zhejiang, China.
Innovation Institute for Artificial Intelligence in Medicine of Zhejiang University, College of Pharmaceutical Sciences and Cancer Center, Zhejiang University, Hangzhou 310058, Zhejiang, China.
Drug Discov Today. 2022 Dec;27(12):103372. doi: 10.1016/j.drudis.2022.103372. Epub 2022 Sep 24.
The acid-base dissociation constant (pK) is a fundamental property influencing many ADMET properties of small molecules. However, rapid and accurate pK prediction remains a great challenge. In this review, we outline the current advances in machine-learning-based QSAR models for pK prediction, including descriptor-based and graph-based approaches, and summarize their pros and cons. Moreover, we highlight the current challenges and future directions regarding experimental data, crucial factors influencing pK and in silico prediction tools. We hope that this review can provide a practical guidance for the follow-up studies.
酸解离常数 (pK) 是影响小分子许多 ADMET 性质的基本性质。然而，快速准确的 pK 预测仍然是一个巨大的挑战。在这篇综述中，我们概述了基于机器学习的 QSAR 模型在 pK 预测方面的最新进展，包括基于描述符和基于图的方法，并总结了它们的优缺点。此外，我们还强调了实验数据、影响 pK 的关键因素和计算预测工具方面目前的挑战和未来的发展方向。我们希望这篇综述能为后续研究提供实用的指导。
