School of Chemistry, Chemistry Engineering and Biotechnology, Nanyang Technological University, 21 Nanyang Link, Singapore 637371, Singapore.
J Chem Inf Model. 2023 Aug 28;63(16):5035-5044. doi: 10.1021/acs.jcim.3c00554. Epub 2023 Aug 15.
Oral bioavailability is a pharmacokinetic property that plays an important role in drug discovery. Recently developed computational models involve the use of molecular descriptors, fingerprints, and conventional machine-learning models. However, determining the type of molecular descriptors requires domain expert knowledge and time for feature selection. With the emergence of the graph neural network (GNN), models can be trained to automatically extract features that they deem important. In this article, we exploited the automatic feature selection of GNN to predict oral bioavailability. To enhance the prediction performance of GNN, we utilized transfer learning by pre-training a model to predict solubility and obtained a final average accuracy of 0.797, an F1 score of 0.840, and an AUC-ROC of 0.867, which outperformed previous studies on predicting oral bioavailability with the same test data set.
口服生物利用度是药物发现中一个重要的药代动力学性质。最近开发的计算模型涉及使用分子描述符、指纹和传统机器学习模型。然而，确定分子描述符的类型需要领域专家知识和特征选择的时间。随着图神经网络（GNN）的出现，模型可以被训练来自动提取它们认为重要的特征。在本文中，我们利用 GNN 的自动特征选择来预测口服生物利用度。为了提高 GNN 的预测性能，我们通过预训练一个模型来预测溶解度来利用迁移学习，最终平均准确率为 0.797，F1 得分为 0.840，AUC-ROC 为 0.867，优于使用相同测试数据集预测口服生物利用度的先前研究。
