EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-task deep learning models for mechanism-based prediction of developmental and reproductive toxicity (DART) using ToxCast bioassays

Siyeol Ahn, Hojun Jung, Jinwon Hwang, Donghyeon Kim, Hyunjun Kim, Wooseok Kim, Yunjung Lee, Changwon Lim, Jinhee Choi

Frontiers in Toxicology · 04.02.2026 · 8

DOI: 10.3389/ftox.2026.1751644 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Toxicology, online erschienen am 04.02.2026. Verfasst von Siyeol Ahn und 8 weiteren Autor:innen. Beteiligte Einrichtung: School of Environmental Engineering, University of Seoul, Seoul, Republic of Korea. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Korea Environmental Industry and Technology Institute.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Developmental and reproductive toxicity (DART) testing has traditionally relied on animal studies, which are costly, time-consuming, and ethically constrained. To advance new approach methodologies (NAMs), we developed a mechanism-informed deep learning framework for predicting DART using in vitro bioactivity data from 23 ToxCast assays mechanistically linked to key developmental and reproductive pathways. Four state-of-the-art (SOTA) deep learning architectures (DGCL, TransFoxMol, MolPath, and MolFormer) were evaluated to address performance limitations commonly observed in traditional supervised learning approaches. Each model was fine-tuned using the curated ToxCast dataset, with the F1 score serving as the primary evaluation metric. Among these, the DGCL model consistently outperformed baseline machine learning algorithms, including random forest, XGB, GBT, decision tree, and logistic regression. Extending DGCL to a multi-task learning framework further improved model stability and performance for endpoints with limited active data. External validation with 91 reference chemicals curated and verified by the ECVAM ReProTect program demonstrated balanced predictive performance (F1 = 0.68), confirming the reliability and generalizability of the fine-tuned DGCL model. By leveraging advanced deep learning architectures, the model effectively handles mechanistically diverse and imbalanced assay data with limited active samples, resulting in improved predictive performance across DART-related effects. Overall, this study demonstrates the potential of integrating mechanistic bioassay information with deep learning to develop reliable, mechanism-based, and non-animal methods for DART prediction and potential regulatory application.

Schlagwörter

Stichwörter der Autor:innen

ToxCastdeep learningdevelopmental and reproductive toxicitynew approach methodologiestoxicity prediction

Autor:innen und Institutionen

  • School of Environmental Engineering, University of Seoul, Seoul, Republic of Korea.
  • Department of Statistics and Data Science, Chung-Ang University, Seoul, Republic of Korea.
  • Department of Smart Cities, Chung-Ang University, Seoul, Republic of Korea.

Förderung

  • Korea Environmental Industry and Technology Institute

Zitieren

APA

Ahn, S., Jung, H., Hwang, J., Kim, D., Kim, H., Kim, W., Lee, Y., Lim, C., & Choi, J. (2026). Multi-task deep learning models for mechanism-based prediction of developmental and reproductive toxicity (DART) using ToxCast bioassays. Frontiers in Toxicology, 8. https://doi.org/10.3389/ftox.2026.1751644

Vancouver

Ahn S, Jung H, Hwang J, Kim D, Kim H, Kim W, et al. Multi-task deep learning models for mechanism-based prediction of developmental and reproductive toxicity (DART) using ToxCast bioassays. Frontiers in Toxicology. 2026;8. doi:10.3389/ftox.2026.1751644

BibTeX
@article{Ahn2026,
  author = {Ahn, Siyeol and Jung, Hojun and Hwang, Jinwon and Kim, Donghyeon and Kim, Hyunjun and Kim, Wooseok and Lee, Yunjung and Lim, Changwon and Choi, Jinhee},
  title = {Multi-task deep learning models for mechanism-based prediction of developmental and reproductive toxicity (DART) using ToxCast bioassays},
  journal = {Frontiers in Toxicology},
  year = {2026},
  volume = {8},
  doi = {10.3389/ftox.2026.1751644}
}
Kostenlos starten →