Novel multi-omics deconfounding variational autoencoders can obtain meaningful disease subtyping
Briefings in Bioinformatics · 2024
DOI: 10.1093/bib/bbae512 ↗Kurz gefasst
Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2024. Verfasst von Zuqi Li und 7 weiteren Autor:innen. Beteiligte Einrichtung: BIO3 - Laboratory for Systems Medicine, Department of Human Genetics, KU Leuven, Herestraat 49, 3000 Leuven, Belgium. Hauptthemen laut MEDLINE: Algorithms. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIA NIH HHS, The Netherlands Organisation for Health Research and Development, Personalized Medicine in Infections: from Systems Biomedicine and Immunometabolism to Precision Diagnosis and Stratification Permitting Individualized Therapies.
Abstract (Originalsprache)
Unsupervised learning, particularly clustering, plays a pivotal role in disease subtyping and patient stratification, especially with the abundance of large-scale multi-omics data. Deep learning models, such as variational autoencoders (VAEs), can enhance clustering algorithms by leveraging inter-individual heterogeneity. However, the impact of confounders—external factors unrelated to the condition, e.g. batch effect or age—on clustering is often overlooked, introducing bias and spurious biological conclusions. In this work, we introduce four novel VAE-based deconfounding frameworks tailored for clustering multi-omics data. These frameworks effectively mitigate confounding effects while preserving genuine biological patterns. The deconfounding strategies employed include (i) removal of latent features correlated with confounders, (ii) a conditional VAE, (iii) adversarial training, and (iv) adding a regularization term to the loss function. Using real-life multi-omics data from The Cancer Genome Atlas, we simulated various confounding effects (linear, nonlinear, categorical, mixed) and assessed model performance across 50 repetitions based on reconstruction error, clustering stability, and deconfounding efficacy. Our results demonstrate that our novel models, particularly the conditional multi-omics VAE (cXVAE), successfully handle simulated confounding effects and recover biologically driven clustering structures. cXVAE accurately identifies patient labels and unveils meaningful pathological associations among cancer types, validating deconfounded representations. Furthermore, our study suggests that some of the proposed strategies, such as adversarial training, prove insufficient in confounder removal. In summary, our study contributes by proposing innovative frameworks for simultaneous multi-omics data integration, dimensionality reduction, and deconfounding in clustering. Benchmarking on open-access data offers guidance to end-users, facilitating meaningful patient stratification for optimized precision medicine.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- BIO3 - Laboratory for Systems Medicine, Department of Human Genetics, KU Leuven, Herestraat 49, 3000 Leuven, Belgium.
- Medical Imaging Research Center, University Hospitals Leuven, Herestraat 49, 3000 Leuven, Belgium.
- BIO3 - Laboratory for Systems Genetics, GIGA Molecular & Computational Biology, University of Liège, Avenue de l'Hôpital 11, 4000 Liège, Belgium.
- Department of Radiology and Nuclear Medicine, Erasmus MC, Dr. Molewaterplein 40, 3015 GD Rotterdam, Netherlands.
- Laboratory of Systems and Synthetic Biology, Wageningen University & Research, PO Box 8033, 6700 EJ Wageningen, Netherlands.
- LifeGlimmer GmbH, Markelstraße 38, 12163 Berlin, Germany.
Förderung
- NIA NIH HHS
- The Netherlands Organisation for Health Research and Development
- Personalized Medicine in Infections: from Systems Biomedicine and Immunometabolism to Precision Diagnosis and Stratification Permitting Individualized Therapies
- PerMed Joint Transnational call JTC 2018
- Marie Sklodowska-Curie
Zitieren
APA
Li, Z., Katz, S., Saccenti, E., Fardo, D. W., Claes, P., Martins Dos Santos, V. A. P., Van Steen, K., & Roshchupkin, G. V. (2024). Novel multi-omics deconfounding variational autoencoders can obtain meaningful disease subtyping. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbae512
Vancouver
Li Z, Katz S, Saccenti E, Fardo DW, Claes P, Martins Dos Santos VAP, et al. Novel multi-omics deconfounding variational autoencoders can obtain meaningful disease subtyping. Briefings in Bioinformatics. 2024. doi:10.1093/bib/bbae512
BibTeX
@article{Li2024,
author = {Li, Zuqi and Katz, Sonja and Saccenti, Edoardo and Fardo, David W and Claes, Peter and Martins Dos Santos, Vitor A P and Van Steen, Kristel and Roshchupkin, Gennady V},
title = {Novel multi-omics deconfounding variational autoencoders can obtain meaningful disease subtyping},
journal = {Briefings in Bioinformatics},
year = {2024},
doi = {10.1093/bib/bbae512}
}
EUVIMED