Prediction of the Blood–Brain Barrier (BBB) Permeability of Chemicals Based on Machine-Learning and Ensemble Methods,Chemical Research in Toxicology

当前位置： X-MOL 学术 › Chem. Res. Toxicol. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Prediction of the Blood–Brain Barrier (BBB) Permeability of Chemicals Based on Machine-Learning and Ensemble Methods
Chemical Research in Toxicology ( IF 3.7 ) Pub Date : 2021-05-28 , DOI: 10.1021/acs.chemrestox.0c00343
Lili Liu ₁ , Li Zhang _{1,

2,

3} , Huawei Feng ₁ , Shimeng Li ₁ , Miao Liu ₁ , Jian Zhao ₁ , Hongsheng Liu _{2,

3,

4}

Affiliation

The ability of chemicals to enter the blood–brain barrier (BBB) is a key factor for central nervous system (CNS) drug development. Although many models for BBB permeability prediction have been developed, they have insufficient accuracy (ACC) and sensitivity (SEN). To improve performance, ensemble models were built to predict the BBB permeability of compounds. In this study, in silico ensemble-learning models were developed using 3 machine-learning algorithms and 9 molecular fingerprints from 1757 chemicals (integrated from 2 published data sets) to predict BBB permeability. The best prediction performance of the base classifier models was achieved by a prediction model based on an random forest (RF) and a MACCS molecular fingerprint with an ACC of 0.910, an area under the receiver-operating characteristic (ROC) curve (AUC) of 0.957, a SEN of 0.927, and a specificity of 0.867 in 5-fold cross-validation. The prediction performance of the ensemble models is better than that of most of the base classifiers. The final ensemble model has also demonstrated good accuracy for an external validation and can be used for the early screening of CNS drugs.

中文翻译：

基于机器学习和集成方法的化学物质血脑屏障 (BBB) 渗透性预测

化学物质进入血脑屏障 (BBB) 的能力是中枢神经系统 (CNS) 药物开发的关键因素。尽管已经开发了许多用于 BBB 渗透率预测的模型，但它们的准确性 (ACC) 和灵敏度 (SEN) 不足。为了提高性能，建立了集成模型来预测化合物的 BBB 渗透性。在这项研究中，使用 3 种机器学习算法和来自 1757 种化学物质（从 2 个已发布的数据集整合）的 9 个分子指纹开发了计算机集成学习模型，以预测 BBB 渗透性。基分类器模型的最佳预测性能是通过基于随机森林 (RF) 和 MACCS 分子指纹的预测模型实现的，ACC 为 0.910，受试者工作特征 (ROC) 曲线下面积 (AUC) 为0.957，SEN 为 0。927，在 5 折交叉验证中的特异性为 0.867。集成模型的预测性能优于大多数基分类器。最终的集成模型也证明了外部验证的良好准确性，可用于 CNS 药物的早期筛选。

更新日期：2021-06-21

点击分享查看原文

点击收藏

阅读更多本刊最新论文本刊介绍/投稿指南11