As more bioactivity and protein structure data become available, scoring functions (SFs) using machine learning (ML) to leverage these data sets continue to gain further accuracy and broader applicability. Advances in our understanding of the optimal ways to train and evaluate these ML-based SFs have introduced further improvements. One of these advances is how to select the most suitable decoys (molecules assumed inactive) to train or test an ML-based SF on a given target. We also review the latest applications of ML-based SFs for prospective structure-based virtual screening (SBVS), with a focus on the observed improvement over those using classical SFs. Finally, we provide recommendations for future prospective SBVS studies based on the findings of recent methodological studies.

随着越来越多的生物活性和蛋白质结构数据变得可用，使用机器学习 (ML) 来利用这些数据集的评分函数 (SF) 继续获得进一步的准确性和更广泛的适用性。我们对训练和评估这些基于 ML 的 SF 的最佳方法的理解取得了进展，这带来了进一步的改进。其中一项进步是如何选择最合适的诱饵（假定分子不活跃）来训练或测试给定目标上基于 ML 的 SF。我们还回顾了基于 ML 的 SF 在前瞻性基于结构的虚拟筛选 (SBVS) 中的最新应用，重点是观察到的对使用经典 SF 的改进。最后，我们根据最近的方法学研究结果为未来的前瞻性 SBVS 研究提供建议。