Deep Generative Models for Phylogenetic Inference with Complex Evolutionary Processes
Abstract
Inference of phylogenetic trees from sequences plays a central role in understanding evolutionary relationships, with applications ranging from tracking pathogen spread to reconstructing the history of life. Conventionally, practitioners obtain posteriors over trees using likelihood-based methods like MCMC. However, likelihoods are only available for simple evolutionary models with restrictive assumptions. For realistic evolutionary models, inference using conventional methods is prohibitively expensive, inaccurate, or even impossible. In practice, practitioners settle for using as flexible a conventional method as possible, even though they expect it is misspecified. In principle, we could use simulation-based inference: simulate tree and sequence data from an evolutionary model and train a neural network to predict the posterior over trees given sequences. However it is a mathematical challenge to represent and train complex posterior distributions over trees. Here we present a flexible family of conditional generative models over trees. Our models iteratively build trees using three natural paradigms -- top-down, middle-out, or bottom-up -- and are trained using a discrete diffusion framework. For real and synthetic datasets of up to $65$ taxa and >105 tokens, our models recover MCMC posteriors much more accurately than the previous state-of-the-art simulation-based method Phyloformer 2. Finally, we compare to IQ-Tree, a popular flexible-but-misspecified conventional method. Our models match its tree estimates on simple data, but on more realistic data, our method is reliably more accurate.
Related
- A unified framework reveals how evolutionary scale and abundance weighting shape phylogenetic community structure
- Global spread and evolutionary trajectories of HIV-1 CRF01_AE: Insights from phylogenetic analysis
- How characters recoding, characters rescoring, and matrix combination weaken phylogenetic and taxonomic inference: the case of Scythicorhinus
- Termite-Like Phylogenetic Conservation of Gut Microbiota in Passalid Beetles Suggests Evolutionary Convergence in Decaying Wood Degradation
- Bayesian phylogenetic inference accounting for recombination in whole bacterial genomes
BibTeX
@misc{baron2026deep,
title = {{Deep Generative Models for Phylogenetic Inference with Complex Evolutionary Processes}},
author = {Ethan Baron and Alan N. Amin and Andrew Gordon Wilson},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.19053},
eprint = {2610.19053},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.19053},
}
RIS
TY - UNPB
TI - Deep Generative Models for Phylogenetic Inference with Complex Evolutionary Processes
AU - Ethan Baron
AU - Alan N. Amin
AU - Andrew Gordon Wilson
PY - 2026
DA - 2026/10/13
PB - arXiv
DO - 10.48550/arxiv.2610.19053
UR - https://arxiv.org/abs/2610.19053
AB - Inference of phylogenetic trees from sequences plays a central role in understanding evolutionary relationships, with applications ranging from tracking pathogen spread to reconstructing the history of life. Conventionally, practitioners obtain posteriors over trees using likelihood-based methods like MCMC. However, likelihoods are only available for simple evolutionary models with restrictive assumptions. For realistic evolutionary models, inference using conventional methods is prohibitively expensive, inaccurate, or even impossible. In practice, practitioners settle for using as flexible a conventional method as possible, even though they expect it is misspecified. In principle, we could use simulation-based inference: simulate tree and sequence data from an evolutionary model and train a neural network to predict the posterior over trees given sequences. However it is a mathematical challenge to represent and train complex posterior distributions over trees. Here we present a flexible family of conditional generative models over trees. Our models iteratively build trees using three natural paradigms -- top-down, middle-out, or bottom-up -- and are trained using a discrete diffusion framework. For real and synthetic datasets of up to $65$ taxa and >10^5 tokens, our models recover MCMC posteriors much more accurately than the previous state-of-the-art simulation-based method Phyloformer 2. Finally, we compare to IQ-Tree, a popular flexible-but-misspecified conventional method. Our models match its tree estimates on simple data, but on more realistic data, our method is reliably more accurate.
ER -