Deep Learning for Population Genetic Inference
Open Access
- 28 March 2016
- journal article
- research article
- Published by Public Library of Science (PLoS) in PLoS Computational Biology
- Vol. 12 (3), e1004845
- https://doi.org/10.1371/journal.pcbi.1004845
Abstract
Given genomic variation data from multiple individuals, computing the likelihood of complex population genetic models is often infeasible. To circumvent this problem, we introduce a novel likelihood-free inference framework by applying deep learning, a powerful modern technique in machine learning. Deep learning makes use of multilayer neural networks to learn a feature-based function from the input (e.g., hundreds of correlated summary statistics of data) to the output (e.g., population genetic parameters of interest). We demonstrate that deep learning can be effectively employed for population genetic inference and learning informative features of data. As a concrete application, we focus on the challenging problem of jointly inferring natural selection and demography (in the form of a population size change history). Our method is able to separate the global nature of demography from the local nature of selection, without sequential steps for these two factors. Studying demography and selection jointly is motivated by Drosophila, where pervasive selection confounds demographic analysis. We apply our method to 197 African Drosophila melanogaster genomes from Zambia to infer both their overall demography, and regions of their genome under selection. We find many regions of the genome that have experienced hard sweeps, and fewer under selection on standing variation (soft sweep) or balancing selection. Interestingly, we find that soft sweeps and balancing selection occur more frequently closer to the centromere of each chromosome. In addition, our demographic inference suggests that previously estimated bottlenecks for African Drosophila melanogaster are too extreme. Deep learning is an active area of research in machine learning which has been applied to various challenging problems in computer science over the past several years, breaking long-standing records of classification accuracy. Here, we apply deep learning to develop a novel likelihood-free inference framework to estimate population genetic parameters and learn informative features of DNA sequence data. As a concrete example, we focus on the challenging problem of jointly inferring natural selection and demographic history.This publication has 74 references indexed in Scilit:
- SweeD: Likelihood-Based Detection of Selective Sweeps in Thousands of GenomesMolecular Biology and Evolution, 2013
- Inference of human population history from individual whole-genome sequencesNature, 2011
- MSMS: a coalescent simulation program including recombination, demographic structure and selection at a single locusBioinformatics, 2010
- ABCtoolbox: a versatile toolkit for approximate Bayesian computationsBMC Bioinformatics, 2010
- Pervasive Natural Selection in the Drosophila Genome?PLoS Genetics, 2009
- Inferring the Strength of Selection in Drosophila under Complex Demographic ModelsMolecular Biology and Evolution, 2008
- An Approximate Bayesian Estimator Suggests Strong, Recurrent Selective Sweeps in DrosophilaPLoS Genetics, 2008
- Genes mirror geography within EuropeNature, 2008
- A new approach to estimate parameters of speciation models with application to apesGenome Research, 2007
- Sequential Monte Carlo without likelihoodsProceedings of the National Academy of Sciences of the United States of America, 2007