VAE-MS: An Asymmetric Variational Autoencoder for Mutational Signature Extraction

TL;DR

VAE-MS introduces a novel asymmetric variational autoencoder model that combines probabilistic and nonlinear methods to improve mutational signature extraction, outperforming traditional approaches in data reconstruction and generalization.

Contribution

This work presents VAE-MS, a new probabilistic autoencoder model with an asymmetric architecture for more reliable mutational signature extraction.

Findings

VAE-MS outperforms non-probabilistic models in data reconstruction and generalization.

Probabilistic models like VAE-MS and SigneR excel in reconstructing real cancer data.

NMF-based models are more accurate on simulated data but less effective on real data.

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 combining a nonlinear extraction with a probabilistic model. In the ability to reconstruct input data and generalize to unseen data, models with probabilistic components (VAE-MS, SigneR) dramatically outperformed models without (SigProfilerExtractor, MUSE-XAE). The NMF-baed models (SigneR, SigProfilerExtractor) had the most accurate reconstructions in simulated data, while VAE-MS reconstructed more accurately on real cancer data. Upon evaluating the ability to extract signatures consistently, no model exhibited a clear advantage over the others. Software for VAE-MS is available at https://github.com/CLINDA-AAU/VAE-MS.