Bayesian neural network with pretrained protein embedding enhances prediction accuracy of drug-protein interaction.

Researchers

Journal

Modalities

Models

Abstract

Characterizing drug-protein interactions is crucial to the high-throughput screening for drug discovery. The deep learning-based approaches have attracted attention because they can predict drug-protein interactions without human trial and error. However, because data labeling requires significant resources, the available protein data size is relatively small, which consequently decreases model performance. Here we propose two methods to construct a deep learning framework that exhibits superior performance with a small labeled dataset.
At first, we use transfer learning in encoding protein sequences with a pretrained model, which trains general sequence representations in an unsupervised manner. Second, we use a Bayesian neural network to make a robust model by estimating the data uncertainty. Our resulting model performs better than the previous baselines at predicting interactions between molecules and proteins. We also show that the quantified uncertainty from the Bayesian inference is related to confidence and can be used for screening DPI data points.
Supplementary data are available at Bioinformatics online.
© The Author(s) 2021. Published by Oxford University Press.