Ricardo Scheufen Tieghi, Marielle Rath, José Teófilo Moreira-Filho, James Wellnitz, Holli-Joi Martin, Kathleen Gates, Helena T Hogberg, Nicole Kleinstreuer, Alexander Tropsha, Eugene N Muratov
{"title":"DeTox: an <i>In-Silico</i> Alternative to Animal Testing for Predicting Developmental Toxicity Potential.","authors":"Ricardo Scheufen Tieghi, Marielle Rath, José Teófilo Moreira-Filho, James Wellnitz, Holli-Joi Martin, Kathleen Gates, Helena T Hogberg, Nicole Kleinstreuer, Alexander Tropsha, Eugene N Muratov","doi":"10.1289/EHP15307","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Medication use among pregnant women is common, yet the safety of these medications for the developing fetus/baby is widely understudied. Quantitative Structure-Activity Relationship (QSAR) models can be used to predict the overall and trimester-specific developmental toxicity potential of chemicals, supporting the development of safer medications for pregnant women and regulatory assessment aligned with the 3Rs (<u>r</u>efining, <u>r</u>educing, and <u>r</u>eplacing) of animal testing.</p><p><strong>Objectives: </strong>This study aimed to collect and curate a database of compounds classified according to their developmental toxicity potential, use this database to develop and validate QSAR models for predicting prenatal developmental toxicity, and implement models via a user-friendly online platform to support regulatory assessments of drug candidates.</p><p><strong>Methods: </strong>We compiled and curated data from the FDA and Teratogen Information System (TERIS) databases and validated annotations with rigorous literature searches. The database was leveraged to create QSAR models using machine learning algorithms (RF, SVM, LightGBM) with Bayesian hyperparameter optimization. These models were implemented into a web tool.</p><p><strong>Results: </strong>We built a binary classification QSAR model for overall pregnancy risk, and separate QSAR models for trimester-specific risk, exhibiting correct classification rates of and 76% (overall), 80% (1<sup>st</sup> trimester), 95% (2<sup>nd</sup> trimester), and 95% (3<sup>rd</sup> trimester). Models showed a sensitivity between 53% and 90%, specificity between 46% and 100%, and coverage of 76% assessed using a five-fold external validation protocol. We established a publicly accessible web portal (https://detox.mml.unc.edu/) for developmental toxicity prediction of both overall and trimester-specific toxicity predictions.</p><p><strong>Conclusions: </strong>DeTox can be employed to support regulatory assessment of pharmaceutical and cosmetic products aligned with the 3Rs of animal testing and to guide the development of safer drugs for pregnant populations. The curated dataset of developmental toxicants is publicly available, and all models are implemented in a public, user-friendly web tool, DeTox (<u>De</u>velopmental <u>Tox</u>icity), at https://detox.mml.unc.edu/. https://doi.org/10.1289/EHP15307.</p>","PeriodicalId":11862,"journal":{"name":"Environmental Health Perspectives","volume":" ","pages":""},"PeriodicalIF":10.1000,"publicationDate":"2025-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Environmental Health Perspectives","FirstCategoryId":"93","ListUrlMain":"https://doi.org/10.1289/EHP15307","RegionNum":1,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENVIRONMENTAL SCIENCES","Score":null,"Total":0}
引用次数: 0
Abstract
Background: Medication use among pregnant women is common, yet the safety of these medications for the developing fetus/baby is widely understudied. Quantitative Structure-Activity Relationship (QSAR) models can be used to predict the overall and trimester-specific developmental toxicity potential of chemicals, supporting the development of safer medications for pregnant women and regulatory assessment aligned with the 3Rs (refining, reducing, and replacing) of animal testing.
Objectives: This study aimed to collect and curate a database of compounds classified according to their developmental toxicity potential, use this database to develop and validate QSAR models for predicting prenatal developmental toxicity, and implement models via a user-friendly online platform to support regulatory assessments of drug candidates.
Methods: We compiled and curated data from the FDA and Teratogen Information System (TERIS) databases and validated annotations with rigorous literature searches. The database was leveraged to create QSAR models using machine learning algorithms (RF, SVM, LightGBM) with Bayesian hyperparameter optimization. These models were implemented into a web tool.
Results: We built a binary classification QSAR model for overall pregnancy risk, and separate QSAR models for trimester-specific risk, exhibiting correct classification rates of and 76% (overall), 80% (1st trimester), 95% (2nd trimester), and 95% (3rd trimester). Models showed a sensitivity between 53% and 90%, specificity between 46% and 100%, and coverage of 76% assessed using a five-fold external validation protocol. We established a publicly accessible web portal (https://detox.mml.unc.edu/) for developmental toxicity prediction of both overall and trimester-specific toxicity predictions.
Conclusions: DeTox can be employed to support regulatory assessment of pharmaceutical and cosmetic products aligned with the 3Rs of animal testing and to guide the development of safer drugs for pregnant populations. The curated dataset of developmental toxicants is publicly available, and all models are implemented in a public, user-friendly web tool, DeTox (Developmental Toxicity), at https://detox.mml.unc.edu/. https://doi.org/10.1289/EHP15307.
期刊介绍:
Environmental Health Perspectives (EHP) is a monthly peer-reviewed journal supported by the National Institute of Environmental Health Sciences, part of the National Institutes of Health under the U.S. Department of Health and Human Services. Its mission is to facilitate discussions on the connections between the environment and human health by publishing top-notch research and news. EHP ranks third in Public, Environmental, and Occupational Health, fourth in Toxicology, and fifth in Environmental Sciences.