Key Laboratory of Medicinal Chemistry for Natural Resource, Ministry of Education; Yunnan Provincial Center for Research & Development of Natural Products; School of Chemical Science and Technology, Yunnan University, Kunming, 650091, China.
Comb Chem High Throughput Screen. 2023;26(6):1214-1223. doi: 10.2174/1386207325666220630154917.
P38α, emerging as a hot spot for drug discovery, is a member of the mitogen- activated protein kinase (MAPK) family and plays a crucial role in regulating the production of inflammatory mediators. However, despite a massive number of highly potent molecules being reported and several under clinical trials, no p38α inhibitor has been approved yet. There is still demand to discover novel p38α to deal with the safety issue induced by off-target effects.
In this study, we performed a machine learning-based virtual screening to identify p38α inhibitors from a natural products library, expecting to find novel drug lead scaffolds.
Firstly, the training dataset was processed with similarity screening to fit the chemical space of the natural products library. Then, six classifiers were constructed by combing two sets of molecular features with three different machine learning algorithms. After model evaluation, the three best classifiers were used for virtual screening.
Among the 15 compounds selected for experimental validation, picrasidine S was identified as a p38α inhibitor with the IC as 34.14 μM. Molecular docking was performed to predict the interaction mode of picrasidine S and p38α, indicating a specific hydrogen bond with Met109.
This work provides a protocol and example for machine learning-assisted discovery of p38α inhibitor from natural products, as well as a novel lead scaffold represented by picrasidine S for further optimization and investigation.
p38α 作为药物发现的热点，是丝裂原活化蛋白激酶（MAPK）家族的一员，在调节炎症介质的产生中起着至关重要的作用。然而，尽管已经报道了大量高活性的分子，并且有几个处于临床试验阶段，但仍未批准任何 p38α 抑制剂。仍需要发现新型的 p38α 抑制剂来应对由脱靶效应引起的安全问题。
在这项研究中，我们进行了基于机器学习的虚拟筛选，从天然产物库中鉴定 p38α 抑制剂，期望找到新型药物先导骨架。
首先，通过相似性筛选对训练数据集进行处理，以适应天然产物库的化学空间。然后，通过结合两组分子特征和三种不同的机器学习算法构建了六个分类器。在模型评估后，使用三个最佳分类器进行虚拟筛选。
在选择用于实验验证的 15 种化合物中，发现苦木苦味素 S 是一种 p38α 抑制剂，IC 为 34.14 μM。进行分子对接以预测苦木苦味素 S 与 p38α 的相互作用模式，表明与 Met109 存在特异性氢键。
这项工作为从天然产物中发现 p38α 抑制剂提供了一种基于机器学习的方案和范例，以及以苦木苦味素 S 为代表的新型先导骨架，可进一步进行优化和研究。
