Do we need different machine learning algorithms for QSAR modeling? A comprehensive assessment of 16 machine learning algorithms on 14 QSAR data sets

• Published in: Briefings in bioinformatics Vol. 22; no. 4
• Main Authors: Wu, Zhenxing, Zhu, Minfeng, Kang, Yu, Leung, Elaine Lai-Han, Lei, Tailong, Shen, Chao, Jiang, Dejun, Wang, Zhe, Cao, Dongsheng, Hou, Tingjun
• Format: Journal Article
• Language: English
• Published: England Oxford University Press 01.07.2021; Oxford Publishing Limited (England)
• Subjects: Algorithms; Artificial neural networks; Computer applications; Datasets; Gaussian process; Learning algorithms; Learning theory; Least squares method; Linear functions; Machine learning; Neural networks; Physicochemical properties; Predictions; Principal components analysis; Radial basis function; Regression analysis; Spline functions; Structure-activity relationships; Support vector machines; Toxicity; ensemble learning; support vector machine; machine learning; QSAR; XGBoost

Abstract 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 M...