In Silico Identification of Potential Thyroid Hormone System Disruptors among Chemicals in Human Serum and Chemicals with a High Exposure Index

Abstract

Data on toxic effects are at large missing the prevailing understanding of the risks of industrial chemicals. Thyroid hormone (TH) system disruption includes interferences of the life cycle of the thyroid hormones and may occur in various organs. In the current study, high-throughput screening data available for 14 putative molecular initiating events of adverse outcome pathways, related to disruption of the TH system, were used to develop 19 in silico models for identification of potential thyroid hormone system-disrupting chemicals. The conformal prediction framework with the underlying Random Forest was used as a wrapper for the models allowing for setting the desired confidence level and controlling the error rate of predictions. The trained models were then applied to two different databases: (i) an in-house database comprising xenobiotics identified in human blood and ii) currently used chemicals registered in the Swedish Product Register, which have been predicted to have a high exposure index to consumers. The application of these models showed that among currently used chemicals, fewer were overall predicted as active compared to chemicals identified in human blood. Chemicals of specific concern for TH disruption were identified from both databases based on their predicted activity.

First Insight into the Formation of In Vivo Transformation Products of 2-Ethylhexyl diphenyl phosphate in Zebrafish and Prediction of Their Potential Toxicities

“…However, a parent compound may produce numerous transformation products in vivo ; it is unrealistic to synthesize all of them for toxicity evaluation. Nowadays, in silico approaches have been successfully applied in various stages of pharmaceutical development to explore the drug action modes and related mechanisms. , These techniques, such as machine learning, are also applied to predict the toxic effects and end points of environmental pollutants. , SwissTargetPrediction is a powerful tool that was built based on 376 342 compounds and 3068 experimentally verified macromolecular targets with high levels of predictive performance for protein target prediction . Thanks to the advancement of high-throughput analytical techniques, the databases of various toxic end points are available, which offers an opportunity to predict the toxic effects of the EHDPHP metabolites using machine learning.…”

“…22,23 These techniques, such as machine learning, are also applied to predict the toxic effects and end points of environmental pollutants. 24,25 SwissTarget-Prediction is a powerful tool that was built based on 376 342 compounds and 3068 experimentally verified macromolecular targets with high levels of predictive performance for protein target prediction. 26 Thanks to the advancement of highthroughput analytical techniques, the databases of various toxic end points are available, which offers an opportunity to predict the toxic effects of the EHDPHP metabolites using machine learning.…”

Anthropogenic Organic Contaminants Analysed in Human Blood and Combined Risk

“…Complex chemical mixtures with levels relevant to humans based on the SEDB have been created and will be tested in vivo and in vitro for mixture toxicity. The OCs listed in the SEDB and the HBDB have been used in in silico predictions towards thyroid disrupting properties (Dracheva et al 2022).…”

Machine Learning Model for Screening Thyroid Stimulating Hormone Receptor Agonists Based on Updated Datasets and Improved Applicability Domain Metrics

“…As the inconclusive compounds commonly decrease the reliability of ML models, they were not included in the modeling, as was also done in previous studies. 40,41 The data were further subjected to curation. Duplicates, inorganics, metals, and mixtures were removed.…”

“…Totally, there were 2697 active, 8558 inactive, and 27,381 inconclusive compounds. As the inconclusive compounds commonly decrease the reliability of ML models, they were not included in the modeling, as was also done in previous studies. , …”