EUVIMEDEUVIMED entdecken
Crossref

Reliability-Aware Deep Learning Framework for Chemical Genotoxicity Prediction with Uncertainty Quantification

Seul Lee, Taehyeon Kim, Jaeoh Kim, Keunhong Jeong iD

Journal of Chemical Information and Modeling · 08.06.2026 · 66 (11) · 6350-6360

DOI: 10.1021/acs.jcim.6c00885 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, online erschienen am 20.05.2026. Verfasst von Seul Lee und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Statistics, Seoul National University, Seoul08826, South Korea. Hauptthemen laut MEDLINE: Deep Learning, Mutagens. Die Arbeit nennt 29 Literaturangaben. Gefördert von: National Research Foundation of Korea.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Genotoxicity assessment is crucial for drug development and chemical safety evaluation. However, traditional experimental approaches are time-consuming, resource-intensive, and raise ethical concerns related to animal testing. Although computational models offer efficient alternatives, most existing approaches treat all data points equally, disregarding the heterogeneous quality of public database records and rarely addressing predictive uncertainty. We present a reliability-aware framework for genotoxicity prediction using a curated data set of 8,389 compounds annotated with experimental reliability tiers reflecting protocol quality, reproducibility, and review status. A two-step hierarchical learning strategy is employed. First, a message-passing neural network trained on high- and medium-reliability data is used to evaluate low-reliability samples and assign adaptive weights. These weights are then incorporated into conventional machine learning models, including random forest, support vector machine (SVM), and logistic regression, using molecular fingerprints. To address predictive uncertainty, we integrate conformal prediction, which provides distribution-free, finite-sample coverage guarantees for individual predictions. Random forest and RBF-kernel SVM achieved AUC values of 0.8613 and 0.8582, respectively, with Brier scores of 0.1523 and 0.1530. Conformal prediction attained 90.7% empirical coverage at α = 0.1 and identified 35.8% of test compounds as ambiguous. By incorporating data reliability and uncertainty quantification, the proposed framework provides a more transparent and uncertainty-aware approach.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningMutagensReproducibility of ResultsUncertaintySupport Vector MachineMutagenicity TestsRandom ForestPrediction AlgorithmsPredictive Learning Models

Substanzen

Mutagens

Autor:innen und Institutionen

  • Department of Statistics, Seoul National University, Seoul08826, South Korea.
  • Department of Chemistry, Sogang University, Seoul04107, South Korea.
  • Department of Data Science, Inha University, Incheon22212, South Korea.

ORCID-Profile: Keunhong Jeong

Förderung

  • National Research Foundation of Korea

Zitieren

APA

Lee, S., Kim, T., Kim, J., & Jeong, K. (2026). Reliability-Aware Deep Learning Framework for Chemical Genotoxicity Prediction with Uncertainty Quantification. Journal of Chemical Information and Modeling, 66(11), 6350-6360. https://doi.org/10.1021/acs.jcim.6c00885

Vancouver

Lee S, Kim T, Kim J, Jeong K. Reliability-Aware Deep Learning Framework for Chemical Genotoxicity Prediction with Uncertainty Quantification. Journal of Chemical Information and Modeling. 2026;66(11):6350-6360. doi:10.1021/acs.jcim.6c00885

BibTeX
@article{Lee2026,
  author = {Lee, Seul and Kim, Taehyeon and Kim, Jaeoh and Jeong, Keunhong},
  title = {Reliability-Aware Deep Learning Framework for Chemical Genotoxicity Prediction with Uncertainty Quantification},
  journal = {Journal of Chemical Information and Modeling},
  year = {2026},
  volume = {66},
  number = {11},
  pages = {6350--6360},
  doi = {10.1021/acs.jcim.6c00885}
}
Kostenlos starten →