Cargando…
CustOmics: A versatile deep-learning based strategy for multi-omics integration
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 heterogene...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10019780/ https://www.ncbi.nlm.nih.gov/pubmed/36877736 http://dx.doi.org/10.1371/journal.pcbi.1010921 |
_version_ | 1784908100426268672 |
---|---|
author | Benkirane, Hakim Pradat, Yoann Michiels, Stefan Cournède, Paul-Henry |
author_facet | Benkirane, Hakim Pradat, Yoann Michiels, Stefan Cournède, Paul-Henry |
author_sort | Benkirane, Hakim |
collection | PubMed |
description | 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). |
format | Online Article Text |
id | pubmed-10019780 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | Public Library of Science |
record_format | MEDLINE/PubMed |
spelling | pubmed-100197802023-03-17 CustOmics: A versatile deep-learning based strategy for multi-omics integration Benkirane, Hakim Pradat, Yoann Michiels, Stefan Cournède, Paul-Henry PLoS Comput Biol Research Article 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). Public Library of Science 2023-03-06 /pmc/articles/PMC10019780/ /pubmed/36877736 http://dx.doi.org/10.1371/journal.pcbi.1010921 Text en © 2023 Benkirane et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. |
spellingShingle | Research Article Benkirane, Hakim Pradat, Yoann Michiels, Stefan Cournède, Paul-Henry CustOmics: A versatile deep-learning based strategy for multi-omics integration |
title | CustOmics: A versatile deep-learning based strategy for multi-omics integration |
title_full | CustOmics: A versatile deep-learning based strategy for multi-omics integration |
title_fullStr | CustOmics: A versatile deep-learning based strategy for multi-omics integration |
title_full_unstemmed | CustOmics: A versatile deep-learning based strategy for multi-omics integration |
title_short | CustOmics: A versatile deep-learning based strategy for multi-omics integration |
title_sort | customics: a versatile deep-learning based strategy for multi-omics integration |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10019780/ https://www.ncbi.nlm.nih.gov/pubmed/36877736 http://dx.doi.org/10.1371/journal.pcbi.1010921 |
work_keys_str_mv | AT benkiranehakim customicsaversatiledeeplearningbasedstrategyformultiomicsintegration AT pradatyoann customicsaversatiledeeplearningbasedstrategyformultiomicsintegration AT michielsstefan customicsaversatiledeeplearningbasedstrategyformultiomicsintegration AT cournedepaulhenry customicsaversatiledeeplearningbasedstrategyformultiomicsintegration |