期刊
BRIEFINGS IN BIOINFORMATICS
卷 22, 期 4, 页码 -出版社
OXFORD UNIV PRESS
DOI: 10.1093/bib/bbaa321
关键词
QSAR; machine learning; XGBoost; support vector machine; ensemble learning
资金
- Key R&D Program of Zhejiang Province [2020C03010]
- National Natural Science Foundation of China [21575128, 81773632]
- Leading Talent of 'Ten Thousand Plan'-National High-Level Talents Special Support Plan
- Zhejiang Provincial Natural Science Foundation of China [LZ19H300001]
A study on learning QSAR models using various ML algorithms for 14 public datasets showed that rbf-SVM, rbf-GPR, XGBoost, and DNN generally perform better than other algorithms. SVM and XGBoost are recommended for regression learning on small datasets, while XGBoost is an excellent choice for large datasets. Ensemble models integrating multiple algorithms can improve prediction accuracy.
Although a wide variety of machine learning (ML) algorithms have been utilized to learn quantitative structure-activity relationships (QSARs), there is no agreed single best algorithm for QSAR learning. Therefore, a comprehensive understanding of the performance characteristics of popular ML algorithms used in QSAR learning is highly desirable. In this study, five linear algorithms [linear function Gaussian process regression (linear-GPR), linear function support vector machine (linear-SVM), partial least squares regression (PLSR), multiple linear regression (MLR) and principal component regression (PCR)], three analogizers [radial basis function support vector machine (rbf-SVM), K-nearest neighbor (KNN) and radial basis function Gaussian process regression (rbf-GPR)], six symbolists [extreme gradient boosting (XGBoost), Cubist, random forest (RF), multiple adaptive regression splines (MARS), gradient boosting machine (GBM), and classification and regression tree (CART)] and two connectionists [principal component analysis artificial neural network (pca-ANN) and deep neural network (DNN)] were employed to learn the regression-based QSAR models for 14 public data sets comprising nine physicochemical properties and five toxicity endpoints. The results show that rbf-SVM, rbf-GPR, XGBoost and DNN generally illustrate better performances than the other algorithms. The overall performances of different algorithms can be ranked from the best to the worst as follows: rbf-SVM>XGBoost > rbf-GPR>Cubist > GBM>DNN>RF>pca-ANN>MARS > linear-GPR approximate to KNN>linear-SVM approximate to PLSR > CART approximate to PCR approximate to MLR. In terms of prediction accuracy and computational efficiency, SVM and XGBoost are recommended to the regression learning for small data sets, and XGBoost is an excellent choice for large data sets. We then investigated the performances of the ensemble models by integrating the predictions of multiple ML algorithms. The results illustrate that the ensembles of two or three algorithms in different categories can indeed improve the predictions of the best individual ML algorithms. [GRAPHICS]
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据