期刊
ACS CENTRAL SCIENCE
卷 7, 期 8, 页码 1356-1367出版社
AMER CHEMICAL SOC
DOI: 10.1021/acscentsci.1c00546
关键词
-
资金
- NIH Molecular Biophysics Training Grant NIH/NIGMS [T32 GM008313]
- National Science Foundation Graduate Research Fellowship
This paper introduces a new approach to uncertainty quantification for neural network-based molecular structure-property prediction using evidential deep learning, which enables calibrated predictions, sample-efficient training, and improved experimental validation rates in the chemical and physical sciences.
While neural networks achieve state-of-the-art performance for many molecular modeling and structure-property prediction tasks, these models can struggle with generalization to out-of-domain examples, exhibit poor sample efficiency, and produce uncalibrated predictions. In this paper, we leverage advances in evidential deep learning to demonstrate a new approach to uncertainty quantification for neural network-based molecular structure-property prediction at no additional computational cost. We develop both evidential 2D message passing neural networks and evidential 3D atomistic neural networks and apply these networks across a range of different tasks. We demonstrate that evidential uncertainties enable (1) calibrated predictions where uncertainty correlates with error, (2) sample-efficient training through uncertainty-guided active learning, and (3) improved experimental validation rates in a retrospective virtual screening campaign. Our results suggest that evidential deep learning can provide an efficient means of uncertainty quantification useful for molecular property prediction, discovery, and design tasks in the chemical and physical sciences.
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