In Silico Prediction of Chemical-Induced Hepatocellular Hypertrophy Using Molecular Descriptors

Abstract

In silico prediction for toxicity of chemicals is required to reduce cost, time, and animal testing. However, predicting hepatocellular hypertrophy, which often affects the derivation of the No-Observed-Adverse-Effect Level in repeated dose toxicity studies, is difficult because pathological findings are diverse, mechanisms are largely unknown, and a wide variety of chemical structures exists. Therefore, a method for predicting the hepatocellular hypertrophy of diverse chemicals without complete understanding of their mechanisms is necessary. In this study, we developed predictive classification models of hepatocellular hypertrophy using machine learning-specifically, deep learning, random forest, and support vector machine. We extracted hepatocellular hypertrophy data on rats from 2 toxicological databases, our original database developed from risk assessment reports such as pesticides, and the Hazard Evaluation Support System Integrated Platform. Then, we constructed prediction models based on molecular descriptors and evaluated their performance using independent test chemicals datasets, which differed from the training chemicals datasets. Further, we defined the applicability domain (AD), which generally limits the application for chemicals, as structurally similar to the training chemicals dataset. The best model was found to be the support vector machine model using the Hazard Evaluation Support System Integrated Platform dataset, which was trained with 251 chemicals and predicted 214 test chemicals inside the applicability domain. It afforded a prediction accuracy of 0.76, sensitivity of 0.90, and area under the curve of 0.81. These in silico predictive classification models could be reliable tools for hepatocellular hypertrophy assessments and can facilitate the development of in silico models for toxicity prediction.

Molecular Image-Based Prediction Models of Nuclear Receptor Agonists and Antagonists Using the DeepSnap-Deep Learning Approach with the Tox21 10K Library

“…However, the best prediction model of AID:743122 (AhR_ago) had a BAC value of 0.8528 in the Data Challenge, whose BAC outperformed that in the DeepSnap-DL method (0.7785). Up to now, conflicting observations have been reported regarding whether DL performs better than conventional shallow machine learning (ML) methods, such as random forest, support vector machine, and gradient boosting decision tree [40,43,[49][50][51][52][53]. Although some reports suggest that DL outperforms conventional ML methods owing to various improvements, the performance of DL in terms of QSAR may be affected by many factors, such as molecular descriptors, assay targets, chemical space, hyper-parameter optimization, DL architectures, input data size, and quality [40].…”

Prediction Model of Aryl Hydrocarbon Receptor Activation by a Novel QSAR Approach, DeepSnap–Deep Learning

“…Differences in prediction performances in terms of the parameter loss (Val), Acc (Val), BAC, F, AUC, Acc (Test), and MCC were analyzed using the Mann-Whitney U test [79][80][81]. For each of the 10 angles (38,38,38), (42,42,42), (50,50,50), (55,55,55), (65,65,65), (85, 85, 85), (105, 105, 105), (176, 176, 176), (300, 300, 300), and (360, 360, 360) in the two datasets Tra/Val/Test = 1:1:1 and 2:2:2, seven evaluation indicators of loss (Val), Acc (Val), BAC, F, AUC, Acc (Test), and MCC are represented as box plots. Significant differences are calculated for each angle.…”

“…The 3D chemical models were captured automatically as snapshots with user-defined angle increments with respect to the x-, y-, and z-axes. In this study, 10 angle increments were used: (38,38,38), (42,42,42), (50,50,50), (55,55,55), (65,65,65), (85, 85, 85), (105, 105, 105), (176, 176, 176), (300, 300, 300), and (360, 360, 360). The snapshots were saved as 256 × 256 pixel resolution PNG files (RGB) and divided into three types of datasets: training (Tra), validation (Val), and test (Test).…”

“…We chose five different ML models to construct the prediction model of AhR activation: (1) DL, (2) RF, (3) XGB, (4) LightGBM, and (5) CB [55]. For the DL, all the PNG image files produced by DeepSnap were resized using NVIDIA DL GPU Training System (DIGITS) version 4.0.0 software (NVIDIA, Santa Clara, CA, USA) on four-GPU systems, Tesla-V100-PCIE (31.7GB), with a resolution of 256 × 256 pixels as input data [47][48][49].…”

Optimization of a Deep-Learning Method Based on the Classification of Images Generated by Parameterized Deep Snap a Novel Molecular-Image-Input Technique for Quantitative Structure–Activity Relationship (QSAR) Analysis

“…These days, machine learning has been applied in extensive toxicological fields, and it is highly effective for risk assessment (Ambe et al, 2018; Banerjee et al, 2018; Luechtefeld et al, 2018; Cipullo et al, 2019). More recently, deep learning (DL), a machine-learning method designed to extract and recognize discriminative information patterns and rules, has been proposed to identify features by several flexible fully-connected layers of a neural network (NN) (Li S. et al, 2017; Qiu et al, 2017; Hu et al, 2018; Li H. et al, 2018; Luechtefeld et al, 2018; Mayr et al, 2018).…”