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

arXiv: https://arxiv.org/abs/2105.12807 · HTML: https://mlsanity.com/paper/2105.12807/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 55 references that are in the map.
- First posted on arXiv 26 May 2021.

## Builds on (most cited first, 10 of 10)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Methods for Interpreting and Understanding Deep Neural Networks](https://mlsanity.com/paper/1706.07979/) (2017)
- [On the importance of single directions for generalization](https://mlsanity.com/paper/1803.06959/) (2018)
- [Explaining Groups of Points in Low-Dimensional Representations](https://mlsanity.com/paper/2003.01640/) (2020)
- [Integrated Multi-omics Analysis Using Variational Autoencoders: Application to Pan-cancer Classification](https://mlsanity.com/paper/1908.06278/) (2019)
- [OmiEmbed: a unified multi-task deep learning framework for multi-omics data](https://mlsanity.com/paper/2102.02669/) (2021)

## Built on by (most cited first, 13 of 13)

- [The Inadequacy of Shapley Values for Explainability](https://mlsanity.com/paper/2302.08160/) (2023)
- [MLOmics: Cancer Multi-Omics Database for Machine Learning](https://mlsanity.com/paper/2409.02143/) (2024)
- [CustOmics: A versatile deep-learning based strategy for multi-omics integration](https://mlsanity.com/paper/2209.05485/) (2022)
- [A systematic review of biologically-informed deep learning models for cancer: fundamental trends for encoding and interpreting oncology data](https://mlsanity.com/paper/2207.00812/) (2022)
- [A Refutation of Shapley Values for Explainability](https://mlsanity.com/paper/2309.03041/) (2023)
- [Automated Cancer Subtyping via Vector Quantization Mutual Information Maximization](https://mlsanity.com/paper/2206.10801/) (2022)
- [XAI meets Biology: A Comprehensive Review of Explainable AI in Bioinformatics Applications](https://mlsanity.com/paper/2312.06082/) (2023)
- [Cancer Subtyping by Improved Transcriptomic Features Using Vector Quantized Variational Autoencoder](https://mlsanity.com/paper/2207.09783/) (2022)
- [MoCLIM: Towards Accurate Cancer Subtyping via Multi-Omics Contrastive Learning with Omics-Inference Modeling](https://mlsanity.com/paper/2308.09725/) (2023)
- [GeSubNet: Gene Interaction Inference for Disease Subtype Network Generation](https://mlsanity.com/paper/2410.13178/) (2024)
- [OmiTrans: generative adversarial networks based omics-to-omics translation framework](https://mlsanity.com/paper/2111.13785/) (2021)
- [A Fair Experimental Comparison of Neural Network Architectures for Latent Representations of Multi-Omics for Drug Response Prediction](https://mlsanity.com/paper/2208.14822/) (2022)
- [Explain Variance of Prediction in Variational Time Series Models for Clinical Deterioration Prediction](https://mlsanity.com/paper/2402.06808/) (2024)

## Abstract (arXiv)

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 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.