Multimodal CustOmics: A unified and interpretable multi-task deep learning framework for multimodal integrative data analysis in oncology.
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 adva...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-06-01
|
| Series: | PLoS Computational Biology |
| Online Access: | https://doi.org/10.1371/journal.pcbi.1013012 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849686724002709504 |
|---|---|
| author | Hakim Benkirane Maria Vakalopoulou David Planchard Julien Adam Ken Olaussen Stefan Michiels Paul-Henry Cournède |
| author_facet | Hakim Benkirane Maria Vakalopoulou David Planchard Julien Adam Ken Olaussen Stefan Michiels Paul-Henry Cournède |
| author_sort | Hakim Benkirane |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-39ecf9ca93cc424b8498b36fe99b6bda |
| institution | DOAJ |
| issn | 1553-734X 1553-7358 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS Computational Biology |
| spelling | doaj-art-39ecf9ca93cc424b8498b36fe99b6bda2025-08-20T03:22:35ZengPublic Library of Science (PLoS)PLoS Computational Biology1553-734X1553-73582025-06-01216e101301210.1371/journal.pcbi.1013012Multimodal CustOmics: A unified and interpretable multi-task deep learning framework for multimodal integrative data analysis in oncology.Hakim BenkiraneMaria VakalopoulouDavid PlanchardJulien AdamKen OlaussenStefan MichielsPaul-Henry CournèdeCharacterizing 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.https://doi.org/10.1371/journal.pcbi.1013012 |
| spellingShingle | Hakim Benkirane Maria Vakalopoulou David Planchard Julien Adam Ken Olaussen Stefan Michiels Paul-Henry Cournède Multimodal CustOmics: A unified and interpretable multi-task deep learning framework for multimodal integrative data analysis in oncology. PLoS Computational Biology |
| title | Multimodal CustOmics: A unified and interpretable multi-task deep learning framework for multimodal integrative data analysis in oncology. |
| title_full | Multimodal CustOmics: A unified and interpretable multi-task deep learning framework for multimodal integrative data analysis in oncology. |
| title_fullStr | Multimodal CustOmics: A unified and interpretable multi-task deep learning framework for multimodal integrative data analysis in oncology. |
| title_full_unstemmed | Multimodal CustOmics: A unified and interpretable multi-task deep learning framework for multimodal integrative data analysis in oncology. |
| title_short | Multimodal CustOmics: A unified and interpretable multi-task deep learning framework for multimodal integrative data analysis in oncology. |
| title_sort | multimodal customics a unified and interpretable multi task deep learning framework for multimodal integrative data analysis in oncology |
| url | https://doi.org/10.1371/journal.pcbi.1013012 |
| work_keys_str_mv | AT hakimbenkirane multimodalcustomicsaunifiedandinterpretablemultitaskdeeplearningframeworkformultimodalintegrativedataanalysisinoncology AT mariavakalopoulou multimodalcustomicsaunifiedandinterpretablemultitaskdeeplearningframeworkformultimodalintegrativedataanalysisinoncology AT davidplanchard multimodalcustomicsaunifiedandinterpretablemultitaskdeeplearningframeworkformultimodalintegrativedataanalysisinoncology AT julienadam multimodalcustomicsaunifiedandinterpretablemultitaskdeeplearningframeworkformultimodalintegrativedataanalysisinoncology AT kenolaussen multimodalcustomicsaunifiedandinterpretablemultitaskdeeplearningframeworkformultimodalintegrativedataanalysisinoncology AT stefanmichiels multimodalcustomicsaunifiedandinterpretablemultitaskdeeplearningframeworkformultimodalintegrativedataanalysisinoncology AT paulhenrycournede multimodalcustomicsaunifiedandinterpretablemultitaskdeeplearningframeworkformultimodalintegrativedataanalysisinoncology |