DeepDelta: predicting ADMET improvements of molecular derivatives with deep learning

Zachary Fralish; Ashley Chen; Paul Skaluba; Daniel Reker

doi:10.1186/s13321-023-00769-x

DeepDelta: predicting ADMET improvements of molecular derivatives with deep learning

J Cheminform. 2023 Oct 27;15(1):101. doi: 10.1186/s13321-023-00769-x.

Authors

Zachary Fralish¹, Ashley Chen², Paul Skaluba¹, Daniel Reker³

Affiliations

¹ Department of Biomedical Engineering, Duke University, Durham, NC, 27708, USA.
² Department of Computer Science, Duke University, Durham, NC, 27708, USA.
³ Department of Biomedical Engineering, Duke University, Durham, NC, 27708, USA. daniel.reker@duke.edu.

Abstract

Established molecular machine learning models process individual molecules as inputs to predict their biological, chemical, or physical properties. However, such algorithms require large datasets and have not been optimized to predict property differences between molecules, limiting their ability to learn from smaller datasets and to directly compare the anticipated properties of two molecules. Many drug and material development tasks would benefit from an algorithm that can directly compare two molecules to guide molecular optimization and prioritization, especially for tasks with limited available data. Here, we develop DeepDelta, a pairwise deep learning approach that processes two molecules simultaneously and learns to predict property differences between two molecules from small datasets. On 10 ADMET benchmark tasks, our DeepDelta approach significantly outperforms two established molecular machine learning algorithms, the directed message passing neural network (D-MPNN) ChemProp and Random Forest using radial fingerprints, for 70% of benchmarks in terms of Pearson's r, 60% of benchmarks in terms of mean absolute error (MAE), and all external test sets for both Pearson's r and MAE. We further analyze our performance and find that DeepDelta is particularly outperforming established approaches at predicting large differences in molecular properties and can perform scaffold hopping. Furthermore, we derive mathematically fundamental computational tests of our models based on mathematical invariants and show that compliance to these tests correlates with overall model performance - providing an innovative, unsupervised, and easily computable measure of expected model performance and applicability. Taken together, DeepDelta provides an accurate approach to predict molecular property differences by directly training on molecular pairs and their property differences to further support fidelity and transparency in molecular optimization for drug development and the chemical sciences.

Keywords: ADMET; Drug design; Drug development; Machine learning; Molecular optimization; Neural network.