Cargando…
Variational autoencoders learn transferrable representations of metabolomics data
Dimensionality reduction approaches are commonly used for the deconvolution of high-dimensional metabolomics datasets into underlying core metabolic processes. However, current state-of-the-art methods are widely incapable of detecting nonlinearities in metabolomics data. Variational Autoencoders (V...
Autores principales: | , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9246987/ https://www.ncbi.nlm.nih.gov/pubmed/35773471 http://dx.doi.org/10.1038/s42003-022-03579-3 |
_version_ | 1784739058795151360 |
---|---|
author | Gomari, Daniel P. Schweickart, Annalise Cerchietti, Leandro Paietta, Elisabeth Fernandez, Hugo Al-Amin, Hassen Suhre, Karsten Krumsiek, Jan |
author_facet | Gomari, Daniel P. Schweickart, Annalise Cerchietti, Leandro Paietta, Elisabeth Fernandez, Hugo Al-Amin, Hassen Suhre, Karsten Krumsiek, Jan |
author_sort | Gomari, Daniel P. |
collection | PubMed |
description | Dimensionality reduction approaches are commonly used for the deconvolution of high-dimensional metabolomics datasets into underlying core metabolic processes. However, current state-of-the-art methods are widely incapable of detecting nonlinearities in metabolomics data. Variational Autoencoders (VAEs) are a deep learning method designed to learn nonlinear latent representations which generalize to unseen data. Here, we trained a VAE on a large-scale metabolomics population cohort of human blood samples consisting of over 4500 individuals. We analyzed the pathway composition of the latent space using a global feature importance score, which demonstrated that latent dimensions represent distinct cellular processes. To demonstrate model generalizability, we generated latent representations of unseen metabolomics datasets on type 2 diabetes, acute myeloid leukemia, and schizophrenia and found significant correlations with clinical patient groups. Notably, the VAE representations showed stronger effects than latent dimensions derived by linear and non-linear principal component analysis. Taken together, we demonstrate that the VAE is a powerful method that learns biologically meaningful, nonlinear, and transferrable latent representations of metabolomics data. |
format | Online Article Text |
id | pubmed-9246987 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Nature Publishing Group UK |
record_format | MEDLINE/PubMed |
spelling | pubmed-92469872022-07-02 Variational autoencoders learn transferrable representations of metabolomics data Gomari, Daniel P. Schweickart, Annalise Cerchietti, Leandro Paietta, Elisabeth Fernandez, Hugo Al-Amin, Hassen Suhre, Karsten Krumsiek, Jan Commun Biol Article Dimensionality reduction approaches are commonly used for the deconvolution of high-dimensional metabolomics datasets into underlying core metabolic processes. However, current state-of-the-art methods are widely incapable of detecting nonlinearities in metabolomics data. Variational Autoencoders (VAEs) are a deep learning method designed to learn nonlinear latent representations which generalize to unseen data. Here, we trained a VAE on a large-scale metabolomics population cohort of human blood samples consisting of over 4500 individuals. We analyzed the pathway composition of the latent space using a global feature importance score, which demonstrated that latent dimensions represent distinct cellular processes. To demonstrate model generalizability, we generated latent representations of unseen metabolomics datasets on type 2 diabetes, acute myeloid leukemia, and schizophrenia and found significant correlations with clinical patient groups. Notably, the VAE representations showed stronger effects than latent dimensions derived by linear and non-linear principal component analysis. Taken together, we demonstrate that the VAE is a powerful method that learns biologically meaningful, nonlinear, and transferrable latent representations of metabolomics data. Nature Publishing Group UK 2022-06-30 /pmc/articles/PMC9246987/ /pubmed/35773471 http://dx.doi.org/10.1038/s42003-022-03579-3 Text en © The Author(s) 2022 https://creativecommons.org/licenses/by/4.0/Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) . |
spellingShingle | Article Gomari, Daniel P. Schweickart, Annalise Cerchietti, Leandro Paietta, Elisabeth Fernandez, Hugo Al-Amin, Hassen Suhre, Karsten Krumsiek, Jan Variational autoencoders learn transferrable representations of metabolomics data |
title | Variational autoencoders learn transferrable representations of metabolomics data |
title_full | Variational autoencoders learn transferrable representations of metabolomics data |
title_fullStr | Variational autoencoders learn transferrable representations of metabolomics data |
title_full_unstemmed | Variational autoencoders learn transferrable representations of metabolomics data |
title_short | Variational autoencoders learn transferrable representations of metabolomics data |
title_sort | variational autoencoders learn transferrable representations of metabolomics data |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9246987/ https://www.ncbi.nlm.nih.gov/pubmed/35773471 http://dx.doi.org/10.1038/s42003-022-03579-3 |
work_keys_str_mv | AT gomaridanielp variationalautoencoderslearntransferrablerepresentationsofmetabolomicsdata AT schweickartannalise variationalautoencoderslearntransferrablerepresentationsofmetabolomicsdata AT cerchiettileandro variationalautoencoderslearntransferrablerepresentationsofmetabolomicsdata AT paiettaelisabeth variationalautoencoderslearntransferrablerepresentationsofmetabolomicsdata AT fernandezhugo variationalautoencoderslearntransferrablerepresentationsofmetabolomicsdata AT alaminhassen variationalautoencoderslearntransferrablerepresentationsofmetabolomicsdata AT suhrekarsten variationalautoencoderslearntransferrablerepresentationsofmetabolomicsdata AT krumsiekjan variationalautoencoderslearntransferrablerepresentationsofmetabolomicsdata |