Abstract
Detecting signals of selection from genomic data is a central problem in population genetics. Coupling the rich information in the ancestral recombination graph (ARG) with a powerful and scalable deep-learning framework, we developed a novel method to detect and quantify positive selection: Selection Inference using the Ancestral recombination graph (SIA). Built on a Long Short-Term Memory (LSTM) architecture, a particular type of a Recurrent Neural Network (RNN), SIA can be trained to explicitly infer a full range of selection coefficients, as well as the allele frequency trajectory and time of selection onset. We benchmarked SIA extensively on simulations under a European human demographic model, and found that it performs as well or better as some of the best available methods, including state-of-the-art machine-learning and ARG-based methods. In addition, we used SIA to estimate selection coefficients at several loci associated with human phenotypes of interest. SIA detected novel signals of selection particular to the European (CEU) population at the MC1R and ABCC11 loci. In addition, it recapitulated signals of selection at the LCT locus and several pigmentation-related genes. Finally, we reanalyzed polymorphism data of a collection of recently radiated southern capuchino seedeater taxa in the genus Sporophila to quantify the strength of selection and improved the power of our previous methods to detect partial soft sweeps. Overall, SIA uses deep learning to leverage the ARG and thereby provides new insight into how selective sweeps shape genomic diversity.
Highlights
The ability to accurately detect and quantify the influence of selection from genomic sequence data enables a wide variety of insights, ranging from understanding historical evolutionary events to characterizing the functional and disease relevance of observed or potential genetic variants
An ancestral recombination graph (ARG)-guided deep-learning model could potentially provide new insight into how natural selection impacts the human genome, human diseases and other phenotypes, and human evolution. With these goals in mind, we developed a new method, called SIA (Selection Inference using the Ancestral recombination graph), that uses a Recurrent Neural Network (RNN) (Hochreiter and Schmidhuber 1997; Maas et al 2011) to infer the selection coefficient and allele frequency (AF) trajectory of a variant that maps to a gene tree embedded in an ARG
ARG-level statistics are extracted at the site under selection as features to be used as input to the deep-learning model
Summary
The ability to accurately detect and quantify the influence of selection from genomic sequence data enables a wide variety of insights, ranging from understanding historical evolutionary events to characterizing the functional and disease relevance of observed or potential genetic variants. Previous approaches to detecting selective sweeps (such as traditional summary statistics [Tajima 1989], approximate likelihood and Approximate Bayesian Computation [ABC] methods [Peter et al 2012], or supervised machine-learning [ML] methods [Schrider and Kern 2016; Kern and Schrider 2018]) exploit the effect of genetic hitchhiking on the spatial haplotype structure and site frequency spectrum (SFS). Summary statistics have the advantage of being fast and easy to compute, but may confound the effects of selection on genetic diversity with the effects of complex demographic histories including bottlenecks, population expansions, and structured populations. They cannot be used to estimate the value of the selection coefficient.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
