Prediction Models for Agonists and Antagonists of Molecular Initiation Events for Toxicity Pathways Using an Improved Deep-Learning-Based Quantitative Structure-Activity Relationship System.

Yasunari Matsuzaka,Yoshihiro Uesawa,Kentaro Handa,Tetsuyoshi Shiota,Shin Totoki,Kota Kurosaki

doi:10.3390/ijms221910821

Abstract

In silico approaches have been studied intensively to assess the toxicological risk of various chemical compounds as alternatives to traditional in vivo animal tests. Among these approaches, quantitative structure–activity relationship (QSAR) analysis has the advantages that it is able to construct models to predict the biological properties of chemicals based on structural information. Previously, we reported a deep learning (DL) algorithm-based QSAR approach called DeepSnap-DL for high-performance prediction modeling of the agonist and antagonist activity of key molecules in molecular initiating events in toxicological pathways using optimized hyperparameters. In the present study, to achieve high throughput in the DeepSnap-DL system–which consists of the preparation of three-dimensional molecular structures of chemical compounds, the generation of snapshot images from the three-dimensional chemical structures, DL, and statistical calculations—we propose an improved DeepSnap-DL approach. Using this improved system, we constructed 59 prediction models for the agonist and antagonist activity of key molecules in the Tox21 10K library. The results indicate that modeling of the agonist and antagonist activity with high prediction performance and high throughput can be achieved by optimizing suitable parameters in the improved DeepSnap-DL system.

Highlights

Methods for predicting toxicity risk have focused on deep learning (DL)-based models, due to their high accuracy and the use of large datasets, as alternatives to animal testing
These methods follow the principle of the 3Rs for the discovery of molecular initiating events (MIEs) in the adverse outcome pathway (AOP), where MIEs are the first point of chemical–biological interaction within the human body [1,2,3]
We reported 35 prediction models for agonists and antagonists of nuclear receptors as MIEs for chemical compounds derived from the Tox21 10K library using an approach called DeepSnap-DL

Summary

Introduction

Methods for predicting toxicity risk have focused on deep learning (DL)-based models, due to their high accuracy and the use of large datasets, as alternatives to animal testing. These methods follow the principle of the 3Rs (replacement, reduction, and refinement) for the discovery of molecular initiating events (MIEs) in the adverse outcome pathway (AOP), where MIEs are the first point of chemical–biological interaction within the human body [1,2,3]. The mean values of ROC_AUC, BAC, PR_AUC, F, Acc, loss, and MCC on the validation and test datasets for the nine colors with 11 angles were 0.919 ± 0.014 (ROC_AUC_valid), 0.895 ± 0.013 (ROC_AUC_test), 0.861 ± 0.023

Methods

Results

Discussion

Conclusion