EvoVGM: a Deep Variational Generative Model for Evolutionary Parameter Estimation

TL;DR

EvoVGM is a deep variational Bayesian model that estimates evolutionary parameters and generates sequence alignments, explicitly considering evolutionary dynamics within a probabilistic framework, applicable to various substitution models.

Contribution

It introduces a novel deep variational model that jointly estimates evolutionary parameters and generates sequences, explicitly modeling evolutionary dynamics unlike prior models.

Findings

EvoVGM accurately estimates parameters on synthetic data.

The model is robust across different evolutionary scenarios.

It effectively generates biologically plausible sequence alignments.

Abstract

Most evolutionary-oriented deep generative models do not explicitly consider the underlying evolutionary dynamics of biological sequences as it is performed within the Bayesian phylogenetic inference framework. In this study, we propose a method for a deep variational Bayesian generative model (EvoVGM) that jointly approximates the true posterior of local evolutionary parameters and generates sequence alignments. Moreover, it is instantiated and tuned for continuous-time Markov chain substitution models such as JC69, K80 and GTR. We train the model via a low-variance stochastic estimator and a gradient ascent algorithm. Here, we analyze the consistency and effectiveness of EvoVGM on synthetic sequence alignments simulated with several evolutionary scenarios and different sizes. Finally, we highlight the robustness of a fine-tuned EvoVGM model using a sequence alignment of gene S of coronaviruses.