Deep Learning Based Regression and Multi-class Models for Acute Oral Toxicity Prediction with Automatic Chemical Feature Extraction

TL;DR

This paper introduces deep learning models based on molecular graph encoding convolutional neural networks for predicting acute oral toxicity, achieving high accuracy and interpretability without manual feature selection.

Contribution

It develops and compares regression, multi-classification, and multi-task deep learning models for AOT prediction using raw molecular graph features, outperforming previous models.

Findings

DeepAOT-R achieved R2 of 0.864 and MAE of 0.195.

DeepAOT-C reached over 95% accuracy on external datasets.

DeepAOT-CR maintained high accuracy with R2 of 0.861.

Abstract

For quantitative structure-property relationship (QSPR) studies in chemoinformatics, it is important to get interpretable relationship between chemical properties and chemical features. However, the predictive power and interpretability of QSPR models are usually two different objectives that are difficult to achieve simultaneously. A deep learning architecture using molecular graph encoding convolutional neural networks (MGE-CNN) provided a universal strategy to construct interpretable QSPR models with high predictive power. Instead of using application-specific preset molecular descriptors or fingerprints, the models can be resolved using raw and pertinent features without manual intervention or selection. In this study, we developed acute oral toxicity (AOT) models of compounds using the MGE-CNN architecture as a case study. Three types of high-level predictive models: regression model (deepAOT-R), multi-classification model (deepAOT-C) and multi-task model (deepAOT-CR) for AOT evaluation were constructed. These models highly outperformed previously reported models. For the two external datasets containing 1673 (test set I) and 375 (test set II) compounds, the R2 and mean absolute error (MAE) of deepAOT-R on the test set I were 0.864 and 0.195, and the prediction accuracy of deepAOT-C was 95.5% and 96.3% on the test set I and II, respectively. The two external prediction accuracy of deepAOT-CR is 95.0% and 94.1%, while the R2 and MAE are 0.861 and 0.204 for test set I, respectively.