Dataset Information

A Toxicity Prediction Tool for Potential Agonist/Antagonist Activities in Molecular Initiating Events Based on Chemical Structures.

ABSTRACT: Because the health effects of many compounds are unknown, regulatory toxicology must often rely on the development of quantitative structure-activity relationship (QSAR) models to efficiently discover molecular initiating events (MIEs) in the adverse-outcome pathway (AOP) framework. However, the QSAR models used in numerous toxicity prediction studies are publicly unavailable, and thus, they are challenging to use in practical applications. Approaches that simultaneously identify the various toxic responses induced by a compound are also scarce. The present study develops Toxicity Predictor, a web application tool that comprehensively identifies potential MIEs. Using various chemicals in the Toxicology in the 21st Century (Tox21) 10K library, we identified potential endocrine-disrupting chemicals (EDCs) using a machine-learning approach. Based on the optimized three-dimensional (3D) molecular structures and XGBoost algorithm, we established molecular descriptors for QSAR models. Their predictive performances and applicability domain were evaluated and applied to Toxicity Predictor. The prediction performance of the constructed models matched that of the top model in the Tox21 Data Challenge 2014. These advanced prediction results for MIEs are freely available on the Internet.

SUBMITTER: Kurosaki K

PROVIDER: S-EPMC7660166 | biostudies-literature | 2020 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A Toxicity Prediction Tool for Potential Agonist/Antagonist Activities in Molecular Initiating Events Based on Chemical Structures.

Kurosaki Kota K Wu Raymond R Uesawa Yoshihiro Y

International journal of molecular sciences 20201023 21

Because the health effects of many compounds are unknown, regulatory toxicology must often rely on the development of quantitative structure-activity relationship (QSAR) models to efficiently discover molecular initiating events (MIEs) in the adverse-outcome pathway (AOP) framework. However, the QSAR models used in numerous toxicity prediction studies are publicly unavailable, and thus, they are challenging to use in practical applications. Approaches that simultaneously identify the various tox ...[more]

PMID: 33113912

Similar Datasets

Project description:BackgroundThe advent of high-throughput transcriptomic screening technologies has resulted in a wealth of publicly available gene expression data associated with chemical treatments. From a regulatory perspective, data sets that cover a large chemical space and contain reference chemicals offer utility for the prediction of molecular initiating events associated with chemical exposure. Here, we integrate data from a large compendium of transcriptomic responses to chemical exposure with a comprehensive database of chemical-protein associations to train binary classifiers that predict mechanism(s) of action from transcriptomic responses. First, we linked reference chemicals present in the LINCS L1000 gene expression data collection to chemical identifiers in RefChemDB, a database of chemical-protein interactions. Next, we trained binary classifiers on MCF7 human breast cancer cell line derived gene expression profiles and chemical-protein labels using six classification algorithms to identify optimal analysis parameters. To validate classifier accuracy, we used holdout data sets, training-excluded reference chemicals, and empirical significance testing of null models derived from permuted chemical-protein associations. To identify classifiers that have variable predicting performance across training data derived from different cellular contexts, we trained a separate set of binary classifiers on the PC3 human prostate cancer cell line.ResultsWe trained classifiers using expression data associated with chemical treatments linked to 51 molecular initiating events. This analysis identified and validated 9 high-performing classifiers with empirical p-values lower than 0.05 and internal accuracies ranging from 0.73 to 0.94 and holdout accuracies of 0.68 to 0.92. High-ranking predictions for training-excluded reference chemicals demonstrating that predictive accuracy extends beyond the set of chemicals used in classifier training. To explore differences in classifier performance as a function of training data cellular context, MCF7-trained classifier accuracies were compared to classifiers trained on the PC3 gene expression data for the same molecular initiating events.ConclusionsThis methodology can offer insight in prioritizing candidate perturbagens of interest for targeted screens. This approach can also help guide the selection of relevant cellular contexts for screening classes of candidate perturbagens using cell line specific model performance.

Project description:Scorpion β-toxin 4 from Centruroides suffusus suffusus (Css4) enhances the activation of voltage-gated sodium channels through a voltage sensor trapping mechanism by binding the activated state of the voltage sensor in domain II and stabilizing it in its activated conformation. Here we describe the antagonist and partial agonist properties of a mutant derivative of this toxin. Substitution of seven different amino acid residues for Glu(15) in Css4 yielded toxin derivatives with both increased and decreased affinities for binding to neurotoxin receptor site 4 on sodium channels. Css4(E15R) is unique among this set of mutants in that it retained nearly normal binding affinity but lost its functional activity for modification of sodium channel gating in our standard electrophysiological assay for voltage sensor trapping. More detailed analysis of the functional effects of Css4(E15R) revealed weak voltage sensor trapping activity, which was very rapidly reversed upon repolarization and therefore was not observed in our standard assay of toxin effects. This partial agonist activity of Css4(E15R) is observed clearly in voltage sensor trapping assays with brief (5 ms) repolarization between the conditioning prepulse and the test pulse. The effects of Css4(E15R) are fit well by a three-step model of toxin action involving concentration-dependent toxin binding to its receptor site followed by depolarization-dependent activation of the voltage sensor and subsequent voltage sensor trapping. Because it is a partial agonist with much reduced efficacy for voltage sensor trapping, Css4(E15R) can antagonize the effects of wild-type Css4 on sodium channel activation and can prevent paralysis by Css4 when injected into mice. Our results define the first partial agonist and antagonist activities for scorpion toxins and open new avenues of research toward better understanding of the structure-function relationships for toxin action on sodium channel voltage sensors and toward potential toxin-based therapeutics to prevent lethality from scorpion envenomation.

Dataset Information

A Toxicity Prediction Tool for Potential Agonist/Antagonist Activities in Molecular Initiating Events Based on Chemical Structures.

Publications

A Toxicity Prediction Tool for Potential Agonist/Antagonist Activities in Molecular Initiating Events Based on Chemical Structures.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets