XOmiVAE: an interpretable deep learning model for cancer classification using high-dimensional omics data

@article{Withnell2021XOmiVAEAI,
  title={XOmiVAE: an interpretable deep learning model for cancer classification using high-dimensional omics data},
  author={Eloise Withnell and Xiaoyu Zhang and Kai Sun and Yike Guo},
  journal={Briefings in bioinformatics},
  year={2021}
}
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… Expand
OmiEmbed: A Unified Multi-Task Deep Learning Framework for Multi-Omics Data
TLDR
OmiEmbed is a powerful and unified framework that can be widely adapted to various applications of high-dimensional omics data and has great potential to facilitate more accurate and personalised clinical decision making. Expand

References

SHOWING 1-10 OF 60 REFERENCES
Integrated Multi-omics Analysis Using Variational Autoencoders: Application to Pan-cancer Classification
TLDR
The integrated model learned from multi-omics datasets outperformed those using only one type of omics data, which indicates that the complementary information from different omics datatypes provides useful insights for biomedical tasks like cancer classification. Expand
Biological interpretation of deep neural network for phenotype prediction based on gene expression
TLDR
An original approach for biological interpretation of deep learning models for phenotype prediction from gene expression data is proposed, which produces interpretations more coherent with biology than the state-of-the-art based approaches. Expand
OmiEmbed: A Unified Multi-Task Deep Learning Framework for Multi-Omics Data
TLDR
OmiEmbed is a powerful and unified framework that can be widely adapted to various applications of high-dimensional omics data and has great potential to facilitate more accurate and personalised clinical decision making. Expand
DeePathology: Deep Multi-Task Learning for Inferring Molecular Pathology from Cancer Transcriptome
TLDR
A novel architecture of Deep Neural Networks that is capable of simultaneous inference of various properties of biological samples, through multi-task and transfer learning is introduced, which significantly outperforms prior works and classical machine learning approaches in predicting tissue-of-origin, normal or disease state and cancer type of each sample. Expand
PathME: pathway based multi-modal sparse autoencoders for clustering of patient-level multi-omics data
TLDR
A suggested multi-modal sparse denoising autoencoder framework coupled with sparse non-negative matrix factorization approach allows for an effective and interpretable integration of multi-omics data on pathway level while addressing the high dimensional character of omics data. Expand
Extracting a biologically relevant latent space from cancer transcriptomes with variational autoencoders
TLDR
The extent to which a Variational autoencoders can be trained to model cancer gene expression, and whether or not such a VAE would capture biologically-relevant features are determined. Expand
Unsupervised generative and graph representation learning for modelling cell differentiation
TLDR
Unsupervised generative neural methods, based on the variational autoencoder, are explored that can model cell differentiation by building meaningful representations from the high dimensional and complex gene expression data. Expand
Opening the Black Box: Interpretable Machine Learning for Geneticists.
TLDR
The importance of interpretable ML, different strategies for interpreting ML models, and examples of how these strategies have been applied are discussed, and challenges and promising future directions for interpretableML in genetics and genomics are identified. Expand
A Unified Approach to Interpreting Model Predictions
TLDR
A unified framework for interpreting predictions, SHAP (SHapley Additive exPlanations), which unifies six existing methods and presents new methods that show improved computational performance and/or better consistency with human intuition than previous approaches. Expand
TCGAbiolinks: an R/Bioconductor package for integrative analysis of TCGA data
TLDR
An R/Bioconductor package called TCGAbiolinks is developed to address bioinformatics challenges of the Cancer Genome Atlas data by using a guided workflow to allow users to query, download and perform integrative analyses of TCGA data. Expand
...
1
2
3
4
5
...