Cargando…
XOmiVAE: an interpretable deep learning model for cancer classification using high-dimensional omics data
The lack of explainability is one of the most prominent disadvantages of deep learning applications in omics. This ‘black box’ problem can undermine the credibility and limit the practical implementation of biomedical deep learning models. Here we present XOmiVAE, a variational autoencoder (VAE)-bas...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Oxford University Press
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8575033/ https://www.ncbi.nlm.nih.gov/pubmed/34402865 http://dx.doi.org/10.1093/bib/bbab315 |
_version_ | 1784595605228617728 |
---|---|
author | Withnell, Eloise Zhang, Xiaoyu Sun, Kai Guo, Yike |
author_facet | Withnell, Eloise Zhang, Xiaoyu Sun, Kai Guo, Yike |
author_sort | Withnell, Eloise |
collection | PubMed |
description | The lack of explainability is one of the most prominent disadvantages of deep learning applications in omics. This ‘black box’ problem can undermine the credibility and limit the practical implementation of biomedical deep learning models. Here we present XOmiVAE, a variational autoencoder (VAE)-based interpretable deep learning model for cancer classification using high-dimensional omics data. XOmiVAE is capable of revealing the contribution of each gene and latent dimension for each classification prediction and the correlation between each gene and each latent dimension. It is also demonstrated that XOmiVAE can explain not only the supervised classification but also the unsupervised clustering results from the deep learning network. To the best of our knowledge, XOmiVAE is one of the first activation level-based interpretable deep learning models explaining novel clusters generated by VAE. The explainable results generated by XOmiVAE were validated by both the performance of downstream tasks and the biomedical knowledge. In our experiments, XOmiVAE explanations of deep learning-based cancer classification and clustering aligned with current domain knowledge including biological annotation and academic literature, which shows great potential for novel biomedical knowledge discovery from deep learning models. |
format | Online Article Text |
id | pubmed-8575033 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | Oxford University Press |
record_format | MEDLINE/PubMed |
spelling | pubmed-85750332021-11-09 XOmiVAE: an interpretable deep learning model for cancer classification using high-dimensional omics data Withnell, Eloise Zhang, Xiaoyu Sun, Kai Guo, Yike Brief Bioinform Problem Solving Protocol The lack of explainability is one of the most prominent disadvantages of deep learning applications in omics. This ‘black box’ problem can undermine the credibility and limit the practical implementation of biomedical deep learning models. Here we present XOmiVAE, a variational autoencoder (VAE)-based interpretable deep learning model for cancer classification using high-dimensional omics data. XOmiVAE is capable of revealing the contribution of each gene and latent dimension for each classification prediction and the correlation between each gene and each latent dimension. It is also demonstrated that XOmiVAE can explain not only the supervised classification but also the unsupervised clustering results from the deep learning network. To the best of our knowledge, XOmiVAE is one of the first activation level-based interpretable deep learning models explaining novel clusters generated by VAE. The explainable results generated by XOmiVAE were validated by both the performance of downstream tasks and the biomedical knowledge. In our experiments, XOmiVAE explanations of deep learning-based cancer classification and clustering aligned with current domain knowledge including biological annotation and academic literature, which shows great potential for novel biomedical knowledge discovery from deep learning models. Oxford University Press 2021-08-17 /pmc/articles/PMC8575033/ /pubmed/34402865 http://dx.doi.org/10.1093/bib/bbab315 Text en © The Author(s) 2021. Published by Oxford University Press. 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 reuse, distribution, and reproduction in any medium, provided the original work is properly cited. |
spellingShingle | Problem Solving Protocol Withnell, Eloise Zhang, Xiaoyu Sun, Kai Guo, Yike XOmiVAE: an interpretable deep learning model for cancer classification using high-dimensional omics data |
title | XOmiVAE: an interpretable deep learning model for cancer classification using high-dimensional omics data |
title_full | XOmiVAE: an interpretable deep learning model for cancer classification using high-dimensional omics data |
title_fullStr | XOmiVAE: an interpretable deep learning model for cancer classification using high-dimensional omics data |
title_full_unstemmed | XOmiVAE: an interpretable deep learning model for cancer classification using high-dimensional omics data |
title_short | XOmiVAE: an interpretable deep learning model for cancer classification using high-dimensional omics data |
title_sort | xomivae: an interpretable deep learning model for cancer classification using high-dimensional omics data |
topic | Problem Solving Protocol |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8575033/ https://www.ncbi.nlm.nih.gov/pubmed/34402865 http://dx.doi.org/10.1093/bib/bbab315 |
work_keys_str_mv | AT withnelleloise xomivaeaninterpretabledeeplearningmodelforcancerclassificationusinghighdimensionalomicsdata AT zhangxiaoyu xomivaeaninterpretabledeeplearningmodelforcancerclassificationusinghighdimensionalomicsdata AT sunkai xomivaeaninterpretabledeeplearningmodelforcancerclassificationusinghighdimensionalomicsdata AT guoyike xomivaeaninterpretabledeeplearningmodelforcancerclassificationusinghighdimensionalomicsdata |