Multimodal CustOmics: A unified and interpretable multi-task deep learning framework for multimodal integrative data analysis in oncology
PLOS Computational Biology · 17.06.2025 · 21 (6) · e1013012
DOI: 10.1371/journal.pcbi.1013012 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS Computational Biology, online erschienen am 17.06.2025. Verfasst von Hakim Benkirane und 6 weiteren Autor:innen. Beteiligte Einrichtung: Université Paris-Saclay, CentraleSupélec, Laboratory of Mathematics and Computer Science (MICS), Gif-sur-Yvette, France. Hauptthemen laut MEDLINE: Deep Learning, Neoplasms, Medical Oncology. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Agence Nationale de la Recherche, Paris-Saclay University (HB), ANR.
Abstract (Originalsprache)
Characterizing cancer presents a delicate challenge as it involves deciphering complex biological interactions within the tumor’s microenvironment. Clinical trials often provide histology images and molecular profiling of tumors, which can help understand these interactions. Despite recent advances in representing multimodal data for weakly supervised tasks in the medical domain, achieving a coherent and interpretable fusion of whole slide images and multi-omics data is still a challenge. Each modality operates at distinct biological levels, introducing substantial correlations between and within data sources. In response to these challenges, we propose a novel deep-learning-based approach designed to represent multi-omics & histopathology data for precision medicine in a readily interpretable manner. While our approach demonstrates superior performance compared to state-of-the-art methods across multiple test cases, it also deals with incomplete and missing data in a robust manner. It extracts various scores characterizing the activity of each modality and their interactions at the pathway and gene levels. The strength of our method lies in its capacity to unravel pathway activation through multimodal relationships and to extend enrichment analysis to spatial data for supervised tasks. We showcase its predictive capacity and interpretation scores by extensively exploring multiple TCGA datasets and validation cohorts. The method opens new perspectives in understanding the complex relationships between multimodal pathological genomic data in different cancer types and is publicly available on Github .
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Université Paris-Saclay, CentraleSupélec, Laboratory of Mathematics and Computer Science (MICS), Gif-sur-Yvette, France.
- IHU PRISM, National PRecISion Medicine Center in Oncology, Gustave Roussy, Villejuif, France.
- Inserm U1018 Oncostat, Équipe Labellisée Ligue Contre le Cancer, Université Paris-Saclay, Villejuif, France.
- Université Paris-Saclay, Faculty of Medicine, Le Kremlin Bicêtre, France.
- Department of Medical Oncology, Thoracic Group and International Center for Thoracic Cancers (CICT), Gustave Roussy, Université Paris-Saclay, Villejuif, France.
- Inserm U1186, Gustave Roussy, Université Paris-Saclay, Villejuif, France.
ORCID-Profile: Hakim Benkirane, Paul-Henry Cournède
Förderung
- Agence Nationale de la Recherche
- Paris-Saclay University (HB)
- ANR
- Ecoles doctorales, Université Paris-Saclay
Zitieren
APA
Benkirane, H., Vakalopoulou, M., Planchard, D., Adam, J., Olaussen, K., Michiels, S., & Cournède, P. H. (2025). Multimodal CustOmics: A unified and interpretable multi-task deep learning framework for multimodal integrative data analysis in oncology. PLOS Computational Biology, 21(6), e1013012. https://doi.org/10.1371/journal.pcbi.1013012
Vancouver
Benkirane H, Vakalopoulou M, Planchard D, Adam J, Olaussen K, Michiels S, et al. Multimodal CustOmics: A unified and interpretable multi-task deep learning framework for multimodal integrative data analysis in oncology. PLOS Computational Biology. 2025;21(6):e1013012. doi:10.1371/journal.pcbi.1013012
BibTeX
@article{Benkirane2025,
author = {Benkirane, Hakim and Vakalopoulou, Maria and Planchard, David and Adam, Julien and Olaussen, Ken and Michiels, Stefan and Cournède, Paul-Henry},
title = {Multimodal CustOmics: A unified and interpretable multi-task deep learning framework for multimodal integrative data analysis in oncology},
journal = {PLOS Computational Biology},
year = {2025},
volume = {21},
number = {6},
pages = {e1013012},
doi = {10.1371/journal.pcbi.1013012}
}
EUVIMED