Amortized Phylodynamic Inference with Neural Bayes Estimators and Recursive Neural Networks

TL;DR

This paper introduces a neural Bayes estimator using recursive neural networks to efficiently estimate key epidemic parameters from phylogenetic trees, providing accurate, fast, and less biased results compared to traditional methods.

Contribution

The paper presents a novel neural Bayes estimator with recursive neural networks for phylodynamic inference, enabling direct posterior estimation from reconstructed trees.

Findings

Achieves good predictive performance in simulations

Provides less biased estimates than BEAST2 in test settings

Remains reasonable under sampling model misspecification

Abstract

Phylodynamics is used to estimate epidemic dynamics from phylogenetic trees or genomic sequences of pathogens, but the likelihood calculations needed can be challenging for complex models. We present a neural Bayes estimator (NBE) for key epidemic quantities: the reproduction number, prevalence, and cumulative infections through time. By performing quantile regression over tree space, the NBE allows us to estimate posterior medians and credible intervals directly from a reconstructed tree. Our approach uses a recursive neural network as a tree embedding network with a prediction network conditioned on time and quantile level to generate the estimates. In simulation studies, the NBE achieves good predictive performance, with conservative uncertainty estimates. Compared with a BEAST2 fixed-tree analysis, the NBE gives less biased estimates of time-varying reproduction numbers in our test setting. Under a misspecified sampling model, the NBE performance degrades (as expected) but remains reasonable, and fine-tuning a pre-trained model yields estimates comparable to those from a model trained from scratch, at substantially lower computational cost.