A Likelihood-Free Inference Framework for Population Genetic Data using Exchangeable Neural Networks
This provides a scalable, general-purpose inference method for population genetics and other fields, addressing bottlenecks in handling exchangeable data and intractable likelihoods.
The authors tackled the challenge of performing likelihood-free inference on complex population genetic models by developing an exchangeable neural network that eliminates the need for hand-designed summary statistics, and demonstrated its effectiveness by outperforming the state-of-the-art on the recombination hotspot testing problem.
An explosion of high-throughput DNA sequencing in the past decade has led to a surge of interest in population-scale inference with whole-genome data. Recent work in population genetics has centered on designing inference methods for relatively simple model classes, and few scalable general-purpose inference techniques exist for more realistic, complex models. To achieve this, two inferential challenges need to be addressed: (1) population data are exchangeable, calling for methods that efficiently exploit the symmetries of the data, and (2) computing likelihoods is intractable as it requires integrating over a set of correlated, extremely high-dimensional latent variables. These challenges are traditionally tackled by likelihood-free methods that use scientific simulators to generate datasets and reduce them to hand-designed, permutation-invariant summary statistics, often leading to inaccurate inference. In this work, we develop an exchangeable neural network that performs summary statistic-free, likelihood-free inference. Our framework can be applied in a black-box fashion across a variety of simulation-based tasks, both within and outside biology. We demonstrate the power of our approach on the recombination hotspot testing problem, outperforming the state-of-the-art.