TarDis: Achieving robust and structured disentanglement of multiple covariates
Cell Systems · 2026-05 · 17 (5) · 101573
DOI: 10.1016/j.cels.2026.101573 ↗Kurz gefasst
Fachartikel in der Zeitschrift Cell Systems, 2026-05. Verfasst von Kemal Inecik und 4 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Computational Biology, Helmholtz Center Munich, Neuherberg 85764, Germany; School of Life Sciences, Technical University of Munich, Frei…. Hauptthemen laut MEDLINE: Genomics. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 101 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Deutsches Forschungszentrum für Gesundheit und Umwelt, Helmholtz Zentrum München.
Abstract (Originalsprache)
Addressing challenges in domain invariance within single-cell genomics necessitates innovative strategies for managing the heterogeneity of multi-source datasets while maintaining the integrity of biological signals. We introduce targeted disentanglement (TarDis), an end-to-end deep generative model designed to disentangle intricate covariate structures across diverse biological datasets, distinguishing technical artifacts from true biological variations. By employing tailored covariate-specific loss components and a self-supervised approach, TarDis effectively generates multiple latent-space representations that capture each continuous and categorical target covariate separately, along with unexplained variation. Our extensive evaluations demonstrate that TarDis outperforms existing methods in data integration, covariate disentanglement, and robust out-of-distribution predictions. The model's capacity to produce interpretable and structured latent spaces, including its introduction of ordered latent representations for continuous covariates, markedly enhances its utility in hypothesis-driven research. Consequently, TarDis offers a promising analytical platform for advancing scientific discovery, providing insights into cellular dynamics, and enabling targeted therapeutic interventions.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Institute of Computational Biology, Helmholtz Center Munich, Neuherberg 85764, Germany; School of Life Sciences, Technical University of Munich, Freising 85354, Germany. Electronic address: kemal.inecik@helmholtz-munich…
- Institute of Computational Biology, Helmholtz Center Munich, Neuherberg 85764, Germany; Department of Computer Science, Technical University of Munich, Garching 85748, Germany.
- Wellcome Sanger Institute, Wellcome Genome Campus, Hinxton, Cambridge CB10 1SA, UK; Biosciences Institute, Newcastle University, Newcastle upon Tyne NE2 4HH, UK.
- Wellcome Sanger Institute, Wellcome Genome Campus, Hinxton, Cambridge CB10 1SA, UK; Biosciences Institute, Newcastle University, Newcastle upon Tyne NE2 4HH, UK; Department of Dermatology, Newcastle Hospitals NHS Founda…
- Institute of Computational Biology, Helmholtz Center Munich, Neuherberg 85764, Germany; Department of Mathematics, Technical University of Munich, Garching 85748, Germany. Electronic address: fabian.theis@helmholtz-muni…
Förderung
- Deutsches Forschungszentrum für Gesundheit und Umwelt, Helmholtz Zentrum München
Zitieren
APA
Inecik, K., Kara, A., Rose, A., Haniffa, M., & Theis, F. J. (2026). TarDis: Achieving robust and structured disentanglement of multiple covariates. Cell Systems, 17(5), 101573. https://doi.org/10.1016/j.cels.2026.101573
Vancouver
Inecik K, Kara A, Rose A, Haniffa M, Theis FJ. TarDis: Achieving robust and structured disentanglement of multiple covariates. Cell Systems. 2026;17(5):101573. doi:10.1016/j.cels.2026.101573
BibTeX
@article{Inecik2026,
author = {Inecik, Kemal and Kara, Aleyna and Rose, Antony and Haniffa, Muzlifah and Theis, Fabian J},
title = {TarDis: Achieving robust and structured disentanglement of multiple covariates},
journal = {Cell Systems},
year = {2026},
volume = {17},
number = {5},
pages = {101573},
doi = {10.1016/j.cels.2026.101573}
}
EUVIMED