Computationally efficient demographic history inference from allele frequencies with supervised machine learning

Abstract

Inferring past demographic history of natural populations from genomic data is of central concern in many studies across research fields. Previously, our group had developed dadi, a widely used demographic history inference method based on the allele frequency spectrum (AFS) and maximum likelihood optimization. However, dadi's maximum likelihood optimization procedure is computationally expensive. Here, we developed donni (demography optimization via neural network inference), a new inference method based on dadi that is more efficient while maintaining comparable inference accuracy. For each dadi-supported demographic model, donni simulates the expected AFS and trains a multilayer perceptron algorithm to infer the model parameters from input AFS. We demonstrated that for many demographic models, donni can infer some parameters, such as population size changes and inbreeding coefficients, very well (ρ≈0.9) and other parameters, such as migration rates and times of demographic events, fairly well (ρ≈0.6-0.7). Importantly, donni provides parameter inference instantaneously from input AFS, with accuracy comparable to parameters inferred by dadi's likelihood optimization while bypassing its long and computationally intensive evaluation process. Donni's performance demonstrates that supervised machine learning algorithms may be a promising avenue for developing more sustainable and computationally efficient demographic history inference methods.