{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T18:29:18Z","timestamp":1792002558919,"version":"4.4.0"},"reference-count":43,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2022,9,20]],"date-time":"2022-09-20T00:00:00Z","timestamp":1663632000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Toxicol."],"abstract":"<jats:p>An area of ongoing concern in toxicology and chemical risk assessment is endocrine disrupting chemicals (EDCs). However, thousands of legacy chemicals lack the toxicity testing required to assess their respective EDC potential, and this is where computational toxicology can play a crucial role. The US (United States) Environmental Protection Agency (EPA) has run two programs, the Collaborative Estrogen Receptor Activity Project (CERAPP) and the Collaborative Modeling Project for Receptor Activity (CoMPARA) which aim to predict estrogen and androgen activity, respectively. The US EPA solicited research groups from around the world to provide endocrine receptor activity Qualitative (or Quantitative) Structure Activity Relationship ([Q]SAR) models and then combined them to create consensus models for different toxicity endpoints. Random Forest (RF) models were developed to cover a broader range of substances with high predictive capabilities using large datasets from CERAPP and CoMPARA for estrogen and androgen activity, respectively. By utilizing simple descriptors from open-source software and large training datasets, RF models were created to expand the domain of applicability for predicting endocrine disrupting activity and help in the screening and prioritization of extensive chemical inventories. In addition, RFs were trained to conservatively predict the activity, meaning models are more likely to make false-positive predictions to minimize the number of False Negatives. This work presents twelve binary and multi-class RF models to predict binding, agonism, and antagonism for estrogen and androgen receptors. The RF models were found to have high predictive capabilities compared to other <jats:italic>in silico<\/jats:italic> modes, with some models reaching balanced accuracies of 93% while having coverage of 89%. These models are intended to be incorporated into evolving priority-setting workflows and integrated strategies to support the screening and selection of chemicals for further testing and assessment by identifying potential endocrine-disrupting substances.<\/jats:p>","DOI":"10.3389\/ftox.2022.981928","type":"journal-article","created":{"date-parts":[[2022,9,20]],"date-time":"2022-09-20T09:33:51Z","timestamp":1663666431000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":20,"title":["Novel machine learning models to predict endocrine disruption activity for high-throughput chemical screening"],"prefix":"10.3389","volume":"4","author":[{"given":"Sean P.","family":"Collins","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tara S.","family":"Barton-Maclaren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2022,9,20]]},"reference":[{"key":"B1","unstructured":"ACD Percepta version 20192019"},{"key":"B2","doi-asserted-by":"publisher","first-page":"112225","DOI":"10.1016\/j.envres.2021.112225","article-title":"Innovation in regulatory approaches for endocrine disrupting chemicals: The journey to risk assessment modernization in Canada","volume":"204","author":"Barton-Maclaren","year":"2022","journal-title":"Environ. Res."},{"key":"B3","article-title":"Advancing consideration of endocrine-disrupting chemicals under the Canadian environmental protection Act, 1999","year":"2018"},{"key":"B4","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1039\/C7TX00268H","article-title":"In silico identification of protein targets for chemical neurotoxins using ToxCast in vitro data and read-across within the QSAR toolbox","volume":"7","author":"Chushak","year":"2018","journal-title":"Toxicol. Res."},{"key":"B5","doi-asserted-by":"publisher","first-page":"490","DOI":"10.1038\/s41374-020-00477-2","article-title":"Predictive modeling of estrogen receptor agonism, antagonism, and binding activities using machine- and deep-learning approaches","volume":"101","author":"Ciallella","year":"2020","journal-title":"Lab. Invest."},{"key":"B6","doi-asserted-by":"publisher","first-page":"4257","DOI":"10.3390\/MOLECULES26144257","article-title":"New in vitro-in silico approach for the prediction of in vivo performance of drug combinations","volume":"26","author":"Correia","year":"2021","journal-title":"Molecules"},{"key":"B7","doi-asserted-by":"publisher","first-page":"100213","DOI":"10.1016\/j.comtox.2022.100213","article-title":"A review of in silico toxicology approaches to support the safety assessment of cosmetics-related materials","volume":"21","author":"Cronin","year":"2022","journal-title":"Comput. Toxicol."},{"key":"B8","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1210\/er.2009-0002","article-title":"Endocrine-disrupting chemicals: An endocrine society scientific statement","volume":"30","author":"Diamanti-Kandarakis","year":"2009","journal-title":"Endocr. Rev."},{"key":"B9","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1080\/1062936X.2015.1136680","article-title":"QSAR Toolbox \u2013 workflow and major functionalities","volume":"27","author":"Dimitrov","year":"2016","journal-title":"Sar. QSAR Environ. Res."},{"key":"B10","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1093\/toxsci\/kfl103","article-title":"The ToxCast program for prioritizing toxicity testing of environmental chemicals","volume":"95","author":"Dix","year":"2007","journal-title":"Toxicol. Sci."},{"key":"B11","volume-title":"Follow-up report to the house of commons standing committee on environment and sustainable development on the Canadian environmental protection Act, 1999","year":"2018"},{"key":"B12","doi-asserted-by":"publisher","first-page":"1739","DOI":"10.1021\/jm0306430","article-title":"Glide: A new approach for rapid, accurate docking and scoring. 1. Method and assessment of docking accuracy","volume":"47","author":"Friesner","year":"2004","journal-title":"J. Med. Chem."},{"key":"B13","doi-asserted-by":"publisher","first-page":"1501","DOI":"10.1021\/ACS.JCIM.8B00297","article-title":"QSAR modeling of ToxCast assays relevant to the molecular initiating events of AOPs leading to hepatic steatosis","volume":"58","author":"Gadaleta","year":"2018","journal-title":"J. Chem. Inf. Model."},{"key":"B14","doi-asserted-by":"publisher","first-page":"D1100","DOI":"10.1093\/nar\/gkr777","article-title":"ChEMBL: A large-scale bioactivity database for drug discovery","volume":"40","author":"Gaulton","year":"2012","journal-title":"Nucleic Acids Res."},{"key":"B15","doi-asserted-by":"publisher","first-page":"593","DOI":"10.1210\/er.2015-1093","article-title":"Executive summary to EDC-2: The endocrine society\u2019s second scientific statement on endocrine-disrupting chemicals","volume":"36","author":"Gore","year":"2015","journal-title":"Endocr. Rev."},{"key":"B16","doi-asserted-by":"publisher","first-page":"1839","DOI":"10.1021\/acs.jcim.8b00794","article-title":"Machine learning consensus to predict the binding to the androgen receptor within the CoMPARA project","volume":"59","author":"Grisoni","year":"2019","journal-title":"J. Chem. Inf. Model."},{"key":"B17","first-page":"467","article-title":"Scoring functions for AutoDock","volume-title":"Methods in molecular biology","author":"Hill","year":"2015"},{"key":"B18","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1093\/toxsci\/kfv168","article-title":"Integrated model of chemical perturbations of a biological pathway using 18 in vitro high-throughput screening assays for the estrogen receptor","volume":"148","author":"Judson","year":"2015","journal-title":"Toxicol. Sci."},{"key":"B19","doi-asserted-by":"publisher","first-page":"1632","DOI":"10.1016\/S1734-1140(13)71524-X","article-title":"Impact of endocrine-disrupting chemicals on neural development and the onset of neurological disorders","volume":"65","author":"Kajta","year":"2013","journal-title":"Pharmacol. Rep."},{"key":"B20","doi-asserted-by":"publisher","first-page":"D1102","DOI":"10.1093\/nar\/gky1033","article-title":"PubChem 2019 update: Improved access to chemical data","volume":"47","author":"Kim","year":"2019","journal-title":"Nucleic Acids Res."},{"key":"B21","doi-asserted-by":"publisher","first-page":"946","DOI":"10.1021\/acs.chemrestox.6b00347","article-title":"Development and validation of a computational model for androgen receptor activity","volume":"30","author":"Kleinstreuer","year":"2017","journal-title":"Chem. Res. Toxicol."},{"key":"B22","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1177\/0261192920965977","article-title":"A review of in silico tools as alternatives to animal testing: Principles, resources and applications","volume":"48","author":"Madden","year":"2020","journal-title":"Altern. Lab. Anim."},{"key":"B23","doi-asserted-by":"publisher","first-page":"204","DOI":"10.1016\/J.CHEMOSPHERE.2018.12.131","article-title":"Development, validation and integration of in silico models to identify androgen active chemicals","volume":"220","author":"Manganelli","year":"2019","journal-title":"Chemosphere"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1023","DOI":"10.1289\/ehp.1510267","article-title":"Cerapp: Collaborative estrogen receptor activity prediction project","volume":"124","author":"Mansouri","year":"2016","journal-title":"Environ. Health Perspect."},{"key":"B25","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1186\/s13321-018-0263-1","article-title":"OPERA models for predicting physicochemical properties and environmental fate endpoints","volume":"10","author":"Mansouri","year":"2018","journal-title":"J. Cheminform."},{"key":"B26","doi-asserted-by":"publisher","first-page":"027002","DOI":"10.1289\/EHP5580","article-title":"CoMPARA: Collaborative modeling project for androgen receptor activity","volume":"128","author":"Mansouri","year":"2020","journal-title":"Environ. Health Perspect."},{"key":"B27","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1007\/978-3-319-93025-1_4","article-title":"Genetic algorithm","volume-title":"Evolutionary algorithms and neural networks. Studies in computational intelligence","author":"Mirjalili","year":"2019"},{"key":"B28","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1186\/1758-2946-3-33","article-title":"Open Babel: An open chemical toolbox","volume":"3","author":"O\u2019Boyle","year":"2011","journal-title":"J. Cheminform."},{"key":"B29","doi-asserted-by":"publisher","first-page":"1040","DOI":"10.1016\/j.scitotenv.2013.10.068","article-title":"Metabolic biotransformation half-lives in fish: QSAR modeling and consensus analysis","volume":"470","author":"Papa","year":"2014","journal-title":"Sci. Total Environ."},{"key":"B30","doi-asserted-by":"publisher","first-page":"559","DOI":"10.1080\/14786440109462720","article-title":"LIII. On lines and planes of closest fit to systems of points in space","volume":"2","author":"Pearson","year":"1901","journal-title":"Lond. Edinb. Dublin Philosophical Mag. J. Sci."},{"key":"B31","doi-asserted-by":"publisher","first-page":"1225","DOI":"10.1021\/acs.chemrestox.6b00135","article-title":"ToxCast chemical landscape: Paving the road to 21st century toxicology","volume":"29","author":"Richard","year":"2016","journal-title":"Chem. Res. Toxicol."},{"key":"B32","doi-asserted-by":"publisher","first-page":"1302","DOI":"10.1021\/ci0000631","article-title":"LeadScope : Software for exploring large sets of screening data","volume":"40","author":"Roberts","year":"2000","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"B33","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.comtox.2017.07.006","article-title":"QSAR models for thyroperoxidase inhibition and screening of U.S. and EU chemical inventories","volume":"4","author":"Rosenberg","year":"2017","journal-title":"Comput. Toxicol."},{"key":"B34","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1186\/1758-2946-5-27","article-title":"Defining a novel k-nearest neighbours approach to assess the applicability domain of a QSAR model for reliable predictions","volume":"5","author":"Sahigara","year":"2013","journal-title":"J. Cheminform."},{"key":"B35","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1002\/minf.201200081","article-title":"Effectiveness of CASE ultra expert System in evaluating adverse effects of drugs","volume":"32","author":"Saiakhov","year":"2013","journal-title":"Mol. Inf."},{"key":"B36","doi-asserted-by":"publisher","first-page":"659","DOI":"10.1109\/TVCG.2015.2467091","article-title":"Reactive vega: A streaming dataflow architecture for declarative interactive visualization","volume":"22","author":"Satyanarayan","year":"2016","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"B37","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1093\/toxsci\/kft164","article-title":"Eadb: An estrogenic activity database for assessing potential endocrine activity","volume":"135","author":"Shen","year":"2013","journal-title":"Toxicol. Sci."},{"key":"B38","article-title":"ADMET predictor","year":"2020"},{"key":"B39","unstructured":"Milano chemometrics and QSAR research group\n            TodeschiniR.\n            ConsonniV.\n            MauriA.\n            BallabioD.\n            ManganaroA.\n          2007"},{"key":"B40","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1080\/1062936X.2011.569508","article-title":"Androgen receptor binding affinity: A QSAR evaluation","volume":"22","author":"Todorov","year":"2011","journal-title":"Sar. QSAR Environ. Res."},{"key":"B41","unstructured":"ToxCast database (invitroDB)2019"},{"key":"B42","unstructured":"Use of high throughput assays and computational tools in the endocrine disruptor screening program2021"},{"key":"B43","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1007\/BF00175354","article-title":"A genetic algorithm tutorial","volume":"4","author":"Whitley","year":"1994","journal-title":"Stat. Comput."}],"container-title":["Frontiers in Toxicology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/ftox.2022.981928\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,20]],"date-time":"2022-09-20T09:34:02Z","timestamp":1663666442000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/ftox.2022.981928\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,20]]},"references-count":43,"alternative-id":["10.3389\/ftox.2022.981928"],"URL":"https:\/\/doi.org\/10.3389\/ftox.2022.981928","relation":{},"ISSN":["2673-3080"],"issn-type":[{"value":"2673-3080","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,20]]},"article-number":"981928"}}