In Silico Prediction of Chemical Toxicity for Drug Design Using Machine Learning Methods and Structural Alerts

  title={In Silico Prediction of Chemical Toxicity for Drug Design Using Machine Learning Methods and Structural Alerts},
  author={Hongbin Yang and Lixia Sun and Weihua Li and Guixia Liu and Yun Tang},
  journal={Frontiers in Chemistry},
During drug development, safety is always the most important issue, including a variety of toxicities and adverse drug effects, which should be evaluated in preclinical and clinical trial phases. This review article at first simply introduced the computational methods used in prediction of chemical toxicity for drug design, including machine learning methods and structural alerts. Machine learning methods have been widely applied in qualitative classification and quantitative regression studies… 

Figures and Tables from this paper

Computational approaches to identify structural alerts and their applications in environmental toxicology and drug discovery.

The recent progress of computational methods for identification of structural alerts and their applications in toxicology were described and two major computational approaches, namely frequency analysis and interpretable machine learning models, were reviewed.

Predicting the Toxicity of Chemicals and Drugs using Machine Learning Models

This work has used the ensemble learning algorithm voting based classifier [logistic regression, decision tree, support vector machines] to predict the toxicity of theTox21 dataset.

Chemical toxicity prediction based on semi-supervised learning and graph convolutional neural network

This study demonstrates that SSL can increase the prediction power of models by learning from unannotated data, and the same technique is expected to be beneficial to other chemical property prediction tasks by utilizing existing large chemical databases.

An Explainable Supervised Machine Learning Model for Predicting Respiratory Toxicity of Chemicals Using Optimal Molecular Descriptors

The proposed SVM model predictions are explained using the SHapley Additive exPlanations approach, which prioritizes the relevance of key modeling descriptors influencing the prediction of respiratory toxicity.

SApredictor: An Expert System for Screening Chemicals Against Structural Alerts

The rapid and accurate evaluation of chemical toxicity is of great significance for estimation of chemical safety. In the past decades, a great number of excellent computational models have been

Machine Learning Based Toxicity Prediction: From Chemical Structural Description to Transcriptome Analysis

The input parameter to the machine learning algorithm, especially its shift from chemical structural description only to that combined with human transcriptome data analysis, which can greatly enhance prediction accuracy, is discussed.

A Review of Feature Reduction Methods for QSAR-Based Toxicity Prediction

Different methods of eliminating redundant and irrelevant features to enhance prediction performance, increase interpretability, and reduce computational complexity are discussed.

Drug Safety Data Curation and Modeling in ChEMBL: Boxed Warnings and Withdrawn Drugs.

Safety-related information for approved drugs has been curated to include the assignment of toxicity class(es) based on their withdrawn status and/or black box warning information described on medicinal product labels.

Machine learning models for classification tasks related to drug safety

Although one can already find classification models with great performances to hERG-mediated cardiotoxicity and the isoenzymes of the cytochrome P450 enzyme family, these targets are still central to ADMET-related research efforts.



ADMET Evaluation in Drug Discovery. Part 17: Development of Quantitative and Qualitative Prediction Models for Chemical-Induced Respiratory Toxicity.

The SVM regression model and the XGBoost classification model can be employed as accurate prediction tools for respiratory toxicity.

ADMET evaluation in drug discovery: 15. Accurate prediction of rat oral acute toxicity using relevance vector machine and consensus modeling

It is believed that the best consensus model with high prediction accuracy can be used as a reliable virtual screening tool to filter out compounds with high rat oral acute toxicity.

Addressing toxicity risk when designing and selecting compounds in early drug discovery.

Computational Models for Human and Animal Hepatotoxicity with a Global Application Scope.

There is an urgent need for better computational models to allow for the identification of safe drug candidates and to support experimental design, and a large data set comprising 3712 compounds with liver related toxicity findings in humans and animals was collected from various sources.

In silico Prediction of Drug Induced Liver Toxicity Using Substructure Pattern Recognition Method

High accuracy classification models were built using five machine learning methods based on MACCS and FP4 fingerprints after evaluating by substructure pattern recognition method, and some key substructure patterns correlated with drug‐induced liver toxicity were also identified as structural alerts.

Adverse Drug Events: Database Construction and in Silico Prediction

A comprehensive database of adverse drug events is reported, which included more than 520,000 drug-ADE associations among 3059 unique compounds and 13,200 ADE items by data integration and text mining and a computational method was developed for prediction of potential ADEs based on the database.

In Silico Prediction of Compounds Binding to Human Plasma Proteins by QSAR Models

The QSAR models showed excellent performance for the entire test set, with mean absolute error ranging from 0.126 to 0.178, demonstrating that the models could be used by a chemist when drawing a molecular structure from scratch, and can serve as guidance for the structural modification of chemicals.

In Silico Prediction of Chemical Acute Oral Toxicity Using Multi-Classification Methods

Some representative substructures responsible for acute oral toxicity were identified using information gain and substructure frequency analysis methods, which might be very helpful for further study to avoid the toxicity.

Modelling the Tox21 10 K chemical profiles for in vivo toxicity prediction and mechanism characterization

The first comprehensive analysis of the Tox21 effort, a large-scale in vitro toxicity screening of chemicals, suggests that in vitro activity profiles can be applied as signatures of compound mechanism of toxicity and used in prioritization for more in-depth toxicological testing.

In silico prediction of chemical genotoxicity using machine learning methods and structural alerts.

Ten structural fragments which can be used to assess the genotoxicity potential of a chemical were identified by using information gain and structural fragment frequency analysis and might be helpful for the initial screening of potential genotoxic compounds.