A mechanistic framework for integrating chemical structure and high-throughput screening results to improve toxicity predictions

Nelms, Mark; Mellor, Claire L.; Enoch, Steven J.; Judson, Richard S.; Patlewicz, Grace; Richard, Ann M.; Madden, Judith C.; Cronin, Mark T.D.; Edwards, Stephen W.

doi:10.1016/j.comtox.2018.08.003

Cited by 14 publications

(28 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many decades of research have been undertaken by various groups globally 10,[53][54][55][56][57][58][59][60] , but arguably some of the most valuable publicly available primary data is generated by governmental organizations like the EPA and European Chemical Agency. Furthermore, the EPA and others are pursuing new methods for evaluating endocrine disruption, as highlighted by the publications on mathematical modeling and prediction of endocrine disruption 16,17,24,25,41 . However, these mathematical models require expensive in vitro data from a series of ER assays to generate AUC values for bioactivity determination.…”

Section: Discussionmentioning

confidence: 99%

Machine Learning Models for Estrogen Receptor Bioactivity and Endocrine Disruption Prediction

Zorn

Foil

Lane

et al. 2020

Environ. Sci. Technol.

View full text Add to dashboard Cite

The U.S. Environmental Protection Agency (EPA) periodically releases in vitro data across a variety of targets, including the estrogen receptor (ER). In 2015, the EPA used this data to construct mathematical models of ER agonist and antagonist pathways to prioritize chemicals for endocrine disruption testing. However, mathematical models require in vitro data prior to predicting estrogenic activity, but machine learning methods are capable of prospective prediction from molecular structure alone. The current study describes the generation and evaluation of Bayesian machine learning models grouped by the EPA's ER agonist pathway model, using multiple data types with proprietary software, Assay Central™. External predictions with three test sets of in vitro and in vivo reference chemicals with agonist activity classifications were compared to previous mathematical model publications. Training datasets were subjected to additional machine learning algorithms and compared with rank normalized scores of internal fivefold cross-validation statistics. External predictions were found to be comparable or superior to previous studies published by the EPA. When assessing six additional algorithms for the training datasets, Assay Central™ performed similarly at a reduced computational cost. This study demonstrates machine learning can prioritize chemicals for future in vitro and in vivo testing of ER agonism.

show abstract

Section: Discussionmentioning

confidence: 99%

Machine Learning Models for Estrogen Receptor Bioactivity and Endocrine Disruption Prediction

Zorn

Foil

Lane

et al. 2020

Environ. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…polymers) that included a structure. This central source of 8645 substances was combined with various data by "code" identifiers from the same summary file into two central sources, one for ToxCast/Tox21 AC 50 data 32 and the work done by Nelms et al 16 , and the other for AUC data from Kleinstreuer et al 11 . The final step prior to generating models was to standardize structures for machine learning (i.e.…”

Section: Experimental Section Datasetsmentioning

confidence: 99%

“…The current study therefore describes multiple Bayesian machine learning model groups generated from the same 11 assays used in the EPA's ToxCast AR agonist and antagonist pathway models. These groups are defined by their source and data type: in vitro ToxCast/Tox21 AR bioactivity and hit-call data 32 , the area-under-the-curve (AUC) values output from the agonist and antagonist pathway models 11 , or burst-flag hit-call data incorporating cytotoxicity considerations 16 . The performance of these groups was evaluated first by internal five-fold cross-validation metrics, then by the prediction accuracy of two external test sets utilized in previous EPA publications 11,15 .…”

Section: Introductionmentioning

confidence: 99%

Comparison of Machine Learning Models for the Androgen Receptor

Zorn

Foil

Lane

et al. 2020

Environ. Sci. Technol.

View full text Add to dashboard Cite

The androgen receptor (AR) is a target of interest for endocrine disruption research, as altered signaling can affect normal reproductive and neurological development for generations. In an effort to prioritize compounds with alternative methodologies, the U.S. Environmental Protection Agency (EPA) used in vitro data from 11 assays to construct models of AR agonist and antagonist signaling pathways. While these EPA ToxCast AR models require in vitro data to assign a bioactivity score, Bayesian machine learning methods can be used for prospective prediction from molecule structure alone. This approach was applied to multiple types of data corresponding to the EPA's AR signaling pathway with proprietary software, Assay Central®. The training performance of all machine learning models, including six other algorithms, was evaluated by internal five-fold cross-validation statistics. Bayesian machine learning models were also evaluated with external predictions of reference chemicals to compare prediction accuracies to published results from the EPA. The machine learning model group selected for further studies of endocrine disruption consisted of continuous AC 50 data from the February 2019 release of ToxCast/Tox21. These efforts demonstrate how machine learning can be used to predict ARmediated bioactivity and can also be applied to other targets of endocrine disruption.

show abstract

“…Greater biological context to what is currently a statistically based approach. Even though AOPs, as presented in the AOPwiki 21 , incorporate a useful framework for comparing two or more chemicals and also a starting point for building the experiments for the biological demonstration of similarity (Nelms et al, 2018), sharing the same AOP may only demonstrate the possible biological activity but says nothing about whether this effect really occurs and does not provide an indication of the doses that may activate the effect, which is fundamental in chemical risk assessment.…”

Section: New Approach Methodologies (Nams) and Adverse Outcome Pathways (Aops)mentioning

confidence: 99%

Internationalization of read-across as a validated new approach method (NAM) for regulatory toxicology

Rovida

Barton-Maclaren

Benfenati

et al. 2020

ALTEX

View full text Add to dashboard Cite

dossier to the European Chemicals Agency (ECHA) containing an extensive list of data on the intrinsic properties of a substance, ranging from chemical characterization and physicochemical properties to toxicological and ecotoxicological data, with increasing demands depending on the tonnage band of the quantity of the substance placed on the market. In addition, registrants should collect information on use and exposure to perform a chemical safety assessment (CSA) based on the toxicity profile of the substance. The minimum data requirements are described in Annexes VI-X of the regulation. For toxicological testing, the standard require-

show abstract

A mechanistic framework for integrating chemical structure and high-throughput screening results to improve toxicity predictions

Abstract: The version presented here may differ from the published version or from the version of the record. Please see the repository URL above for details on accessing the published version and note that access may require a subscription.

Cited by 14 publications

References 55 publications

Machine Learning Models for Estrogen Receptor Bioactivity and Endocrine Disruption Prediction

Machine Learning Models for Estrogen Receptor Bioactivity and Endocrine Disruption Prediction

Comparison of Machine Learning Models for the Androgen Receptor

Internationalization of read-across as a validated new approach method (NAM) for regulatory toxicology

Contact Info

Product

Resources

About