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...

Descripción completa

Detalles Bibliográficos
Autores principales: Withnell, Eloise, Zhang, Xiaoyu, Sun, Kai, Guo, Yike
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