A benchmark study on reliable molecular supervised learning via Bayesian learning
This work addresses the need for reliable predictive probabilities in virtual screening for drug discovery, but it is incremental as it benchmarks existing methods.
The study evaluated Bayesian learning algorithms for graph neural networks in molecular property prediction, finding they enable well-calibrated predictions across architectures and tasks, potentially improving virtual screening success rates.
Virtual screening aims to find desirable compounds from chemical library by using computational methods. For this purpose with machine learning, model outputs that can be interpreted as predictive probability will be beneficial, in that a high prediction score corresponds to high probability of correctness. In this work, we present a study on the prediction performance and reliability of graph neural networks trained with the recently proposed Bayesian learning algorithms. Our work shows that Bayesian learning algorithms allow well-calibrated predictions for various GNN architectures and classification tasks. Also, we show the implications of reliable predictions on virtual screening, where Bayesian learning may lead to higher success in finding hit compounds.