Uncertainty quantification of molecular property prediction using Bayesian neural network models
This work addresses the need for more reliable molecular applications in chemistry, but it is incremental as it applies an existing method (Bayesian neural networks) to a specific domain.
The paper tackles the problem of unreliable predictions in molecular property prediction due to data quality issues by quantifying uncertainties using Bayesian neural networks, demonstrating their usefulness as a quality checker and confidence indicator in three experiments.
In chemistry, deep neural network models have been increasingly utilized in a variety of applications such as molecular property predictions, novel molecule designs, and planning chemical reactions. Despite the rapid increase in the use of state-of-the-art models and algorithms, deep neural network models often produce poor predictions in real applications because model performance is highly dependent on the quality of training data. In the field of molecular analysis, data are mostly obtained from either complicated chemical experiments or approximate mathematical equations, and then quality of data may be questioned.In this paper, we quantify uncertainties of prediction using Bayesian neural networks in molecular property predictions. We estimate both model-driven and data-driven uncertainties, demonstrating the usefulness of uncertainty quantification as both a quality checker and a confidence indicator with the three experiments. Our results manifest that uncertainty quantification is necessary for more reliable molecular applications and Bayesian neural network models can be a practical approach.