EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY-NC 4.0

A survey of contrastive learning methods in molecular representation

Ali Forooghi iD, Shaghayegh Sadeghi iD, Luis Rueda iD, Alioune Ngom

Briefings in Bioinformatics · 2026

DOI: 10.1093/bib/bbaf731 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Briefings in Bioinformatics, 2026. Verfasst von Ali Forooghi und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, University of Windsor, 401 Sunset Avenue, N9B 3P4 Ontario, Canada. Hauptthemen laut MEDLINE: Deep Learning, Cheminformatics. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 94 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Molecular representation is fundamental to the field of cheminformatics, facilitating accurate prediction and exploration of molecular properties. Since the nineteenth century, methods for representing molecules have evolved significantly, with recent advances in deep learning offering state-of-the-art performance across various tasks. Among these, contrastive learning (CL) has emerged as one of the most powerful techniques for training deep learning models. CL aims to optimize the representation of similar molecules by reducing the distance between their vector embeddings, while simultaneously increasing the distance between dissimilar ones. Driven by the growing success of CL in enhancing representation learning, this paper presents the first comprehensive review dedicated to CL methods for molecular representation. We begin by surveying existing literature in the field, providing context for the evolution of molecular representation. Next, we introduce the core principles of the CL framework and examine its application to molecular representation learning tasks. Finally, we highlight the key challenges faced by CL-based approaches and discuss potential future directions for advancing molecular representation with these methods.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningCheminformaticsRepresentation Machine LearningAlgorithms

Stichwörter der Autor:innen

contrastive learningmolecular data augmentationmolecular representationself-supervised learning

Autor:innen und Institutionen

  • School of Computer Science, University of Windsor, 401 Sunset Avenue, N9B 3P4 Ontario, Canada.

ORCID-Profile: Ali Forooghi, Shaghayegh Sadeghi, Luis Rueda

Zitieren

APA

Forooghi, A., Sadeghi, S., Rueda, L., & Ngom, A. (2026). A survey of contrastive learning methods in molecular representation. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbaf731

Vancouver

Forooghi A, Sadeghi S, Rueda L, Ngom A. A survey of contrastive learning methods in molecular representation. Briefings in Bioinformatics. 2026. doi:10.1093/bib/bbaf731

BibTeX
@article{Forooghi2026,
  author = {Forooghi, Ali and Sadeghi, Shaghayegh and Rueda, Luis and Ngom, Alioune},
  title = {A survey of contrastive learning methods in molecular representation},
  journal = {Briefings in Bioinformatics},
  year = {2026},
  doi = {10.1093/bib/bbaf731}
}
Kostenlos starten →