Uncertainty quantification of molecular property prediction with Bayesian neural networks
arXiv:1903.08375
Abstract
Deep neural networks have outperformed existing machine learning models in various molecular applications. In practical applications, it is still difficult to make confident decisions because of the uncertainty in predictions arisen from insufficient quality and quantity of training data. Here, we show that Bayesian neural networks are useful to quantify the uncertainty of molecular property prediction with three numerical experiments. In particular, it enables us to decompose the predictive variance into the model- and data-driven uncertainties, which helps to elucidate the source of errors. In the logP predictions, we show that data noise affected the data-driven uncertainties more significantly than the model-driven ones. Based on this analysis, we were able to find unexpected errors in the Harvard Clean Energy Project dataset. Lastly, we show that the confidence of prediction is closely related to the predictive uncertainty by performing on bio-activity and toxicity classification problems.
References in corpus (10)
- Semi-Supervised Classification with Graph Convolutional Networks
- Weight Uncertainty in Neural Networks
- Junction Tree Variational Autoencoder for Molecular Graph Generation
- Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models
- MolGAN: An implicit generative model for small molecular graphs
- Learning Deep Generative Models of Graphs
- Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation
- Multiplicative Normalizing Flows for Variational Bayesian Neural Networks
- Atomic Convolutional Networks for Predicting Protein-Ligand Binding Affinity
- Deeply learning molecular structure-property relationships using attention- and gate-augmented graph convolutional network