CustOmics: A versatile deep-learning based strategy for multi-omics integration
PLOS Computational Biology · 06.03.2023 · 19 (3) · e1010921
DOI: 10.1371/journal.pcbi.1010921 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS Computational Biology, online erschienen am 06.03.2023. Verfasst von Hakim Benkirane und 3 weiteren Autor:innen. Beteiligte Einrichtung: Université Paris-Saclay, CentraleSupélec, Lab of Mathematics and Informatics (MICS), Gif-sur-Yvette, France. Hauptthemen laut MEDLINE: Breast Neoplasms, Deep Learning. Die Arbeit wurde bisher 111-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Agence Nationale de la Recherche, Public Health graduate school of Paris-Saclay University.
Abstract (Originalsprache)
The availability of patient cohorts with several types of omics data opens new perspectives for exploring the disease’s underlying biological processes and developing predictive models. It also comes with new challenges in computational biology in terms of integrating high-dimensional and heterogeneous data in a fashion that captures the interrelationships between multiple genes and their functions. Deep learning methods offer promising perspectives for integrating multi-omics data. In this paper, we review the existing integration strategies based on autoencoders and propose a new customizable one whose principle relies on a two-phase approach. In the first phase, we adapt the training to each data source independently before learning cross-modality interactions in the second phase. By taking into account each source’s singularity, we show that this approach succeeds at taking advantage of all the sources more efficiently than other strategies. Moreover, by adapting our architecture to the computation of Shapley additive explanations, our model can provide interpretable results in a multi-source setting. Using multiple omics sources from different TCGA cohorts, we demonstrate the performance of the proposed method for cancer on test cases for several tasks, such as the classification of tumor types and breast cancer subtypes, as well as survival outcome prediction. We show through our experiments the great performances of our architecture on seven different datasets with various sizes and provide some interpretations of the results obtained. Our code is available on ( https://github.com/HakimBenkirane/CustOmics ).
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Université Paris-Saclay, CentraleSupélec, Lab of Mathematics and Informatics (MICS), Gif-sur-Yvette, France.
- Oncostat U1018, Inserm, Université Paris-Saclay, Équipe Labellisée Ligue Contre le Cancer, CESP, Villejuif, France.
- Bureau de Biostatistique et d'Épidémiologie, Gustave Roussy, Université Paris-Saclay, Villejuif, France.
ORCID-Profile: Hakim Benkirane
Förderung
- the Agence Nationale de la Recherche
- Public Health graduate school of Paris-Saclay University
Zitieren
APA
Benkirane, H., Pradat, Y., Michiels, S., & Cournède, P. H. (2023). CustOmics: A versatile deep-learning based strategy for multi-omics integration. PLOS Computational Biology, 19(3), e1010921. https://doi.org/10.1371/journal.pcbi.1010921
Vancouver
Benkirane H, Pradat Y, Michiels S, Cournède PH. CustOmics: A versatile deep-learning based strategy for multi-omics integration. PLOS Computational Biology. 2023;19(3):e1010921. doi:10.1371/journal.pcbi.1010921
BibTeX
@article{Benkirane2023,
author = {Benkirane, Hakim and Pradat, Yoann and Michiels, Stefan and Cournède, Paul-Henry},
title = {CustOmics: A versatile deep-learning based strategy for multi-omics integration},
journal = {PLOS Computational Biology},
year = {2023},
volume = {19},
number = {3},
pages = {e1010921},
doi = {10.1371/journal.pcbi.1010921}
}
EUVIMED