2019/05/31 by Matthew C. Robinson, Robert C. Glen, Alpha A. Lee
Biochemistry, Genetics and Molecular Biology · Computer Science · Materials Science · #Computational Drug Discovery Methods #Machine Learning in Materials Science #Protein Structure and Dynamics
paper · pdf · doi:10.1007/s10822-019-00274-0
openalex publication_date 2020/01/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/01
Machine learning methods may have the potential to significantly accelerate drug discovery. However, the increasing rate of new methodological approaches being published in the literature raises the fundamental question of how models should be benchmarked and validated. We reanalyze the data generated by a recently published large-scale comparison of machine learning models for bioactivity prediction and arrive at a somewhat different conclusion. We show that the performance of support vector machines is competitive with that of deep learning methods. Additionally, using a series of numerical experiments, we question the relevance of area under the receiver operating characteristic curve as a metric in virtual screening. We further suggest that area under the precision-recall curve should be used in conjunction with the receiver operating characteristic curve. Our numerical experiments also highlight challenges in estimating the uncertainty in model performance via scaffold-split nested cross validation.