An overview of self-supervised deep learning applications to molecular data
Briefings in Bioinformatics · 2026
DOI: 10.1093/bib/bbag380 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Briefings in Bioinformatics, 2026. Verfasst von Lluis Borràs Ferrís und 6 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Informatics, University of Applied Sciences Western Switzerland (HES-SO), Technopôle 3, 3960 Sierre, Valais, Switzerland. Hauptthemen laut MEDLINE: Deep Learning, Supervised Machine Learning, Computational Biology. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 71 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: HEREDITARY Project, European Union's Horizon Europe research, and innovation programme, European Union’s Horizon Europe research, and innovation programme.
Abstract (Originalsprache)
The emergence of high-throughput sequencing technologies has generated unprecedented amounts of molecular data, posing significant challenges for analysis and interpretation. In the past 15 years, deep learning (DL) has revolutionized many data analysis fields. However, a key limitation of most DL approaches is their reliance on massive amounts of data that often require labeling. Self-supervised learning (SSL) uses large-scale unlabeled data to learn meaningful representations for specific tasks, allowing training of the models without labels. While SSL has primarily been applied to fields like natural language processing and medical image analysis, SSL can also be applied to molecular data to learn meaningful representations of molecular sequences that can be used for downstream tasks. Despite the growing interest in SSL applications using molecular data over the recent years, no comprehensive review has been published on this topic, so far, making it timely to address. This paper aims to provide researchers in DL and bioinformatics with a clear view of SSL omics applications to foster future work in the domain. This review examines the principles of SSL, such as foundation models, and it discusses the application of SSL to various omics data types, summarizes information from 17 studies, and categorizes applications by data type, detailing common tasks, model architectures, and repositories. Key applications such as DNABERT and Nucleotide Transformer are highlighted, demonstrating the contributions of SSL in understanding gene regulation. Future directions for SSL in omics are outlined, emphasizing the potential for integrating multi-omics data and developing more sophisticated pretext tasks.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Institute of Informatics, University of Applied Sciences Western Switzerland (HES-SO), Technopôle 3, 3960 Sierre, Valais, Switzerland.
- Nuclear Medicine and Molecular Imaging Department, Lausanne University Hospital (CHUV), Rue du Bugnon 46, 1011 Lausanne, Vaud, Switzerland.
- Information Engineering Department, University of Padua, Via Gradenigo 6/b, 35131 Padua, Italy.
- Department of Neuroscience, University of Padua, Via Belzoni 160, 35121 Padua, Italy.
- The Sense Innovation and Research Center, Avenue de Provence 82, 1007 Lausanne / Rue de l'Industrie 17, 1950 Sion, Switzerland.
ORCID-Profile: Lluis Borràs Ferrís, Barbara Di Camillo
Förderung
- HEREDITARY Project
- European Union's Horizon Europe research, and innovation programme
- European Union’s Horizon Europe research, and innovation programme
Zitieren
APA
Borràs Ferrís, L., Fratti, R., Nucera, V., Oreiller, V., Di Camillo, B., Atzori, M., & Müller, H. (2026). An overview of self-supervised deep learning applications to molecular data. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbag380
Vancouver
Borràs Ferrís L, Fratti R, Nucera V, Oreiller V, Di Camillo B, Atzori M, et al. An overview of self-supervised deep learning applications to molecular data. Briefings in Bioinformatics. 2026. doi:10.1093/bib/bbag380
BibTeX
@article{BorrsFerrs2026,
author = {Borràs Ferrís, Lluis and Fratti, Riccardo and Nucera, Valerio and Oreiller, Valentin and Di Camillo, Barbara and Atzori, Manfredo and Müller, Henning},
title = {An overview of self-supervised deep learning applications to molecular data},
journal = {Briefings in Bioinformatics},
year = {2026},
doi = {10.1093/bib/bbag380}
}
EUVIMED