![[2602.22239] VAE-MS: An Asymmetric Variational Autoencoder for Mutational Signature Extraction](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.22239] VAE-MS: An Asymmetric Variational Autoencoder for Mutational Signature Extraction
Summary
The paper introduces VAE-MS, an Asymmetric Variational Autoencoder designed to enhance mutational signature extraction in cancer research, outperforming traditional methods in real data scenarios.
Why It Matters
This research addresses the limitations of existing mutational signature extraction methods, which are crucial for understanding cancer biology. By leveraging a novel neural network architecture, VAE-MS aims to improve accuracy and reliability, potentially impacting clinical applications and cancer research methodologies.
Key Takeaways
- VAE-MS combines an asymmetric architecture with probabilistic methods for improved mutational signature extraction.
- The model outperformed traditional methods like NMF and other autoencoders in real cancer data scenarios.
- Probabilistic components significantly enhance the model's ability to generalize to unseen data.
- No single model showed a clear advantage in signature extraction consistency, indicating the need for further research.
- Software for VAE-MS is publicly available, promoting accessibility for researchers.
Statistics > Applications arXiv:2602.22239 (stat) [Submitted on 24 Feb 2026] Title:VAE-MS: An Asymmetric Variational Autoencoder for Mutational Signature Extraction Authors:Ida Egendal, Rasmus Froberg Brøndum, Dan J Woodcock, Christopher Yau, Martin Bøgsted View a PDF of the paper titled VAE-MS: An Asymmetric Variational Autoencoder for Mutational Signature Extraction, by Ida Egendal and 4 other authors View PDF HTML (experimental) Abstract:Mutational signature analysis has emerged as a powerful method for uncovering the underlying biological processes driving cancer development. However, the signature extraction process, typically performed using non-negative matrix factorization (NMF), often lacks reliability and clinical applicability. To address these limitations, several solutions have been introduced, including the use of neural networks to achieve more accurate estimates and probabilistic methods to better capture natural variation in the data. In this work, we introduce a Variational Autoencoder for Mutational Signatures (VAE-MS), a novel model that leverages both an asymmetric architecture and probabilistic methods for the extraction of mutational signatures. VAE-MS is compared to with three state-of-the-art models for mutational signature extraction: SigProfilerExtractor, the NMF-based gold standard; MUSE-XAE, an autoencoder that employs an asymmetric design without probabilistic components; and SigneR, a Bayesian NMF model, to illustrate the strength in combinin...
