EUVIMEDEUVIMED entdecken
Crossref

Distance-Aware Molecular Property Prediction in Nonlinear Structure–Property Space

Jae Young Kim, Dionisios G Vlachos iD

Journal of Chemical Information and Modeling · 2025

DOI: 10.1021/acs.jcim.5c01037 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, 2025. Verfasst von Jae Young Kim und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Chemical and Biomolecular Engineering, University of Delaware, Newark, Delaware 19716, United States. Hauptthemen laut MEDLINE: Nonlinear Dynamics. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 64 Literaturangaben. Gefördert von: Delaware Biotechnology Institute.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Molecular property prediction with limited data in novel chemical domains remains challenging. We introduce an approach based on the hypothesis that prediction difficulty increases systematically with distance from well-characterized regions in an appropriately defined structure-property space. Our framework combines nonlinear structure-property space embedding with distance-aware domain classification and uncertainty quantification. We create a structure-property embedding connecting molecular similarity with prediction difficulty, implement distance-aware classification balancing precision and true positive rate, and provide distance-based uncertainty estimates scaled by molecular similarity. Across four ecotoxicity data sets, our local models reduced root mean squared error by 28-48% for truly in-domain molecules compared to global models, with strong correlations (r = 0.40-0.62) between distance and prediction error. In a biolubricant base oil property application, our approach reduced prediction error by 29% compared to a global model and outperformed transfer learning and standard machine learning approaches. This framework's focus on relevant domains and distance-calibrated uncertainty estimates for limited, heterogeneous chemical data makes it broadly applicable across applications, such as toxicity prediction, drug discovery, and materials design.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Nonlinear DynamicsMachine LearningDrug DiscoveryUncertainty

Autor:innen und Institutionen

  • Department of Chemical and Biomolecular Engineering, University of Delaware, Newark, Delaware 19716, United States.
  • Delaware Energy Institute (DEI), University of Delaware, 221 Academy St., Newark, Delaware 19716, United States.

ORCID-Profile: Dionisios G Vlachos

Förderung

  • Delaware Biotechnology Institute

Zitieren

APA

Kim, J. Y., & Vlachos, D. G. (2025). Distance-Aware Molecular Property Prediction in Nonlinear Structure–Property Space. Journal of Chemical Information and Modeling. https://doi.org/10.1021/acs.jcim.5c01037

Vancouver

Kim JY, Vlachos DG. Distance-Aware Molecular Property Prediction in Nonlinear Structure–Property Space. Journal of Chemical Information and Modeling. 2025. doi:10.1021/acs.jcim.5c01037

BibTeX
@article{Kim2025,
  author = {Kim, Jae Young and Vlachos, Dionisios G},
  title = {Distance-Aware Molecular Property Prediction in Nonlinear Structure–Property Space},
  journal = {Journal of Chemical Information and Modeling},
  year = {2025},
  doi = {10.1021/acs.jcim.5c01037}
}
Kostenlos starten →