Computational Approaches for Predicting<scp>hERG</scp>Activity

Alves, Vinícius M.; Braga, Rodolpho C.; Andrade, Carolina Horta

doi:10.1002/9781119282594.ch3

Cited by 4 publications

(4 citation statements)

References 117 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The previous versions of Pred-hERG contained only binary and multiclass models, − with the latest published in 2015 reporting balanced accuracy of 0.80 and 0.74 for binary and multiclass, respectively. The new models reported herein showed a slight increase of ≅ 0.07 for binary classification and a more significant increase of ≅ 0.11 for multiclass classification.…”

Section: Resultsmentioning

confidence: 99%

“…A critical examination of recent models reveals that most exhibit the same failures as those reported in previous studies. 21 , 52 These significant drawbacks jeopardize the practical application of these models for the reliable assessment of drug-induced QT syndrome. A few enhancements are worth mentioning.…”

Section: Resultsmentioning

confidence: 99%

“…Our group previously developed the Pred-hERG tool, − an application that helps researchers identify potential hERG blockers and nonblockers of untested compounds using classificatory (blocker and nonblocker) and multiclassificatory (strong blocker, moderate/weak blocker and nonblocker) QSAR models over the years. The latest version (Pred-hERG 4.2) was released in 2016 and the models were built using data available in ChEMBL v21 with 16,932 chemical records in raw data.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Enhancing hERG Risk Assessment with Interpretable Classificatory and Regression Models

Sanches,

Braga,

Alves

et al. 2024

Chem. Res. Toxicol.

Self Cite

View full text Add to dashboard Cite

The human Ether-à-go-go-Related Gene (hERG) is a transmembrane protein that regulates cardiac action potential, and its inhibition can induce a potentially deadly cardiac syndrome. In vitro tests help identify hERG blockers at early stages; however, the high cost motivates searching for alternative, cost-effective methods. The primary goal of this study was to enhance the Pred-hERG tool for predicting hERG blockage. To achieve this, we developed new QSAR models that incorporated additional data, updated existing classificatory and multiclassificatory models, and introduced new regression models. Notably, we integrated SHAP (SHapley Additive exPlanations) values to offer a visual interpretation of these models. Utilizing the latest data from ChEMBL v30, encompassing over 14,364 compounds with hERG data, our binary and multiclassification models outperformed both the previous iteration of Pred-hERG and all publicly available models. Notably, the new version of our tool introduces a regression model for predicting hERG activity (pIC50). The optimal model demonstrated an R 2 of 0.61 and an RMSE of 0.48, surpassing the only available regression model in the literature. Pred-hERG 5.0 now offers users a swift, reliable, and user-friendly platform for the early assessment of chemically induced cardiotoxicity through hERG blockage. The tool provides versatile outcomes, including (i) classificatory predictions of hERG blockage with prediction reliability, (ii) multiclassificatory predictions of hERG blockage with reliability, (iii) regression predictions with estimated pIC50 values, and (iv) probability maps illustrating the contribution of chemical fragments for each prediction. Furthermore, we implemented explainable AI analysis (XAI) to visualize SHAP values, providing insights into the contribution of each feature to binary classification predictions. A consensus prediction calculated based on the predictions of the three developed models is also present to assist the user’s decision-making process. Pred-hERG 5.0 has been designed to be user-friendly, making it accessible to users without computational or programming expertise. The tool is freely available at .

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Enhancing hERG Risk Assessment with Interpretable Classificatory and Regression Models

Sanches,

Braga,

Alves

et al. 2024

Chem. Res. Toxicol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Due to the complexity of the underlying mechanism and the prediction difficulty of hERG blockers, most hERG prediction models were developed based on machine learning algorithms. Several public prediction Web sites, such as Pred-hERG, have been developed and used in cardiotoxicity assessment. , More details can be found in the published reviews. − …”

Section: Cardiotoxicitymentioning

confidence: 99%

Application of Negative Design To Design a More Desirable Virtual Screening Library

Yang

Lü

et al. 2020

J. Med. Chem.

View full text Add to dashboard Cite

Negative design is a group of virtual screening methods that aims at weeding out compounds with undesired properties during the early stages of drug development. These methods are mainly designed to predict three important types of pharmacological properties: drug-likeness, frequent hitters, and toxicity. In order to achieve high screening efficiency, most negative design methods are physicochemical property-based and/or substructure-based rules or filters. Such methods have advantages of simplicity and good interpretability, but they also suffer from some defects such as inflexibility, discontinuity, and hard decisionmaking. In this review, the advances in negative design for the evaluations of druglikeness, frequent hitters, and toxicity are outlined. In addition, the related Web servers and software packages developed recently for negative design are summarized. Finally, future research directions in this field are discussed.

show abstract

Deep Learning Framework for Cancer

Pratishtha¹

2022

Deep Learning for Targeted Treatments

View full text Add to dashboard Cite

Computational Approaches for PredictinghERGActivity

Cited by 4 publications

References 117 publications

Enhancing hERG Risk Assessment with Interpretable Classificatory and Regression Models

Enhancing hERG Risk Assessment with Interpretable Classificatory and Regression Models

Application of Negative Design To Design a More Desirable Virtual Screening Library

Deep Learning Framework for Cancer

Contact Info

Product

Resources

About