EUVIMEDEUVIMED entdecken
Open Access

Undersampling Techniques for Nonlinear Chemical Space Visualization

Akash Surendran, Krisztina Zsigmond, Ramón Alain Miranda-Quintana iD

Molecular Informatics · 2026-07 · 45 (7)

DOI: 10.1002/minf.70041 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Molecular Informatics, online erschienen am 28.07.2026. Verfasst von Akash Surendran und 2 weiteren Autor:innen. Beteiligte Einrichtung: Quantum Theory Project and Department of Chemistry, University of Florida, Gainesville, Florida, USA. Hauptthemen laut MEDLINE: Dimensionality Reduction. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIH HHS, National Institutes of Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The visualization of high‐dimensional chemical space is a critical tool for understanding molecular diversity, structure–property relationships, and for guiding compound selection. However, the performance of non‐linear dimensionality reduction (DR) techniques like t‐stochastic neighborhood embedding (t‐SNE), uniform manifold approximation and projection (UMAP), and generative topographic mapping (GTM) are often susceptible to the choice of hyperparameters, along with the high cost of their training for large datasets. In this study, we investigated the effect of undersampling methods on the choice of hyperparameter selection for these non‐linear dimensionality reduction methods. Our results demonstrate that selecting small representative subsets of chemical data not only reduces computational costs associated with hyperparameter training but also serves as an innovative means to train nonlinear DR methods, leading to projections that better preserve the local structure within the chemical space.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Dimensionality ReductionAlgorithmsNonlinear Dynamics

Autor:innen und Institutionen

  • Quantum Theory Project and Department of Chemistry, University of Florida, Gainesville, Florida, USA.

ORCID-Profile: Ramón Alain Miranda-Quintana

Förderung

  • NIH HHS
  • National Institutes of Health

Zitieren

APA

Surendran, A., Zsigmond, K., & Miranda-Quintana, R. A. (2026). Undersampling Techniques for Nonlinear Chemical Space Visualization. Molecular Informatics, 45(7). https://doi.org/10.1002/minf.70041

Vancouver

Surendran A, Zsigmond K, Miranda-Quintana RA. Undersampling Techniques for Nonlinear Chemical Space Visualization. Molecular Informatics. 2026;45(7). doi:10.1002/minf.70041

BibTeX
@article{Surendran2026,
  author = {Surendran, Akash and Zsigmond, Krisztina and Miranda-Quintana, Ramón Alain},
  title = {Undersampling Techniques for Nonlinear Chemical Space Visualization},
  journal = {Molecular Informatics},
  year = {2026},
  volume = {45},
  number = {7},
  doi = {10.1002/minf.70041}
}
Kostenlos starten →