Representation learning for multi-modal spatially resolved transcriptomics data
Bioinformatics · 2026
DOI: 10.1093/bioinformatics/btag316 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, 2026. Verfasst von Kalin Nonchev und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, ETH Zurich, Universitätstrasse 6, Zurich 8092, Switzerland. Hauptthemen laut MEDLINE: Deep Learning, Gene Expression Profiling, Transcriptome. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Tumor Profiler Initiative and the Tumor Profiler Center, Hoffmann-La Roche Ltd., ETH Zurich.
Abstract (Originalsprache)
Motivation Spatial transcriptomics enables in-depth molecular characterization of samples on a morphology and RNA level while preserving spatial location. Integrating the resulting multi-modal data is an unsolved problem, and developing new solutions in precision medicine depends on improved methodologies. Results We introduce AESTETIK, a convolutional deep learning model that jointly integrates spatial, transcriptomics, and morphology information to learn accurate spot representations. AESTETIK yielded substantially improved cluster assignments on widely adopted technology platforms (e.g. 10x Genomics™, NanoString™) across multiple datasets. We achieved performance enhancement on structured tissues (e.g. brain) with a 21% increase in median ARI over previous state-of-the-art methods. Notably, AESTETIK also demonstrated superior performance on cancer tissues with heterogeneous cell populations, showing a 2-fold increase in breast cancer, 79% in melanoma, and 21% in liver cancer. We expect that these advances will enable a multi-modal understanding of key biological processes. Availability and implementation AESTETIK is implemented in Python 3 and is available as open source software at http://www.github.com/ratschlab/aestetik. The Snakemake pipeline for reproducing the results is available at http://www.github.com/ratschlab/st-rep.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Computer Science, ETH Zurich, Universitätstrasse 6, Zurich 8092, Switzerland.
- Swiss Institute of Bioinformatics, Amphipôle, Quartier UNIL-Sorge, Zurich 1015, Switzerland.
- Computational and Translational Pathology Group, Department of Pathology and Molecular Pathology, University Hospital Zurich, University of Zürich, Schmelzbergstrasse 12, Zurich 8091, Switzerland.
- Department of Oncology, University of Oxford, Roosevelt Drive, Oxford OX3 7DQ, United Kingdom.
- Institute of Medical Genetics and Pathology, University Hospital Basel, Schönbeinstrasse 40, Basel 4031, Switzerland.
- AI Center, ETH Zurich, Andreasstrasse 5, Zurich 8092, Switzerland.
ORCID-Profile: Kalin Nonchev, Gunnar Rätsch
Förderung
- Tumor Profiler Initiative and the Tumor Profiler Center
- Hoffmann-La Roche Ltd.
- ETH Zurich
- University of Zurich
- University Hospital Zurich
- University Hospital Basel
- Swiss Federal Institutes of Technology strategic focus
- Swiss National Science Foundation
Zitieren
APA
Nonchev, K., Andani, S., Ficek-Pascual, J., Nowak, M., Sobottka, B., Tumor Profiler Consortium, Koelzer, V. H., & Rätsch, G. (2026). Representation learning for multi-modal spatially resolved transcriptomics data. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag316
Vancouver
Nonchev K, Andani S, Ficek-Pascual J, Nowak M, Sobottka B, Tumor Profiler Consortium, et al. Representation learning for multi-modal spatially resolved transcriptomics data. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag316
BibTeX
@article{Nonchev2026,
author = {Nonchev, Kalin and Andani, Sonali and Ficek-Pascual, Joanna and Nowak, Marta and Sobottka, Bettina and Tumor Profiler Consortium, Tumor Profiler Consortium and Koelzer, Viktor H and Rätsch, Gunnar},
title = {Representation learning for multi-modal spatially resolved transcriptomics data},
journal = {Bioinformatics},
year = {2026},
doi = {10.1093/bioinformatics/btag316}
}
EUVIMED