Dispersal inference from population genetic variation using a convolutional neural network

Dispersal-diversity feedbacks and their consequences for macroecological patterns

Dispersal is a key process in ecology and evolution. While the effects of dispersal on diversity are broadly acknowledged, our understanding of the influence of diversity on dispersal remains limited. This arises from the dynamic, context-dependent, nonlinear and ubiquitous nature of dispersal. Diversity outcomes, such as competition, mutualism, parasitism and trophic interactions can feed back on dispersal, thereby influencing biodiversity patterns at several spatio-temporal scales. Here, we shed light on the dispersal-diversity causal links by discussing how dispersal-diversity ecological and evolutionary feedbacks can impact macroecological patterns. We highlight the importance of dispersal-diversity feedbacks for advancing our understanding of macro-eco-evolutionary patterns and their challenges, such as establishing a unified framework for dispersal terminology and methodologies across various disciplines and scales. This article is part of the theme issue 'Diversity-dependence of dispersal: interspecific interactions determine spatial dynamics'.

Genomic Signatures of Microgeographic Adaptation in Anopheles coluzzii Along an Anthropogenic Gradient in Gabon

Species distributed across heterogeneous environments often evolve locally adapted populations, but understanding how these persist in the presence of homogenizing gene flow remains puzzling. In Gabon, Anopheles coluzzii, a major African malaria mosquito is found along an ecological gradient, including a sylvatic population, away of any human presence. This study identifies into the genomic signatures of local adaptation in populations from distinct environments including the urban area of Libreville, and two proximate sites 10km apart in the La Lopé National Park (LLP), a village and its sylvatic neighborhood. Whole genome re-sequencing of 96 mosquitoes unveiled ∼ 5.7millions high-quality single nucleotide polymorphisms. Coalescent-based demographic analyses suggest an ∼ 8,000-year-old divergence between Libreville and La Lopé populations, followed by a secondary contact ( ∼ 4,000 ybp) resulting in asymmetric effective gene flow. The urban population displayed reduced effective size, evidence of inbreeding, and strong selection pressures for adaptation to urban settings, as suggested by the hard selective sweeps associated with genes involved in detoxification and insecticide resistance. In contrast, the two geographically proximate LLP populations showed larger effective sizes, and distinctive genomic differences in selective signals, notably soft-selective sweeps on the standing genetic variation. Although neutral loci and chromosomal inversions failed to discriminate between LLP populations, our findings support that microgeographic adaptation can swiftly emerge through selection on standing genetic variation despite high gene flow. This study contributes to the growing understanding of evolution of populations in heterogeneous environments amid ongoing gene flow and how major malaria mosquitoes adapt to human.

Significance

Anopheles coluzzii , a major African malaria vector, thrives from humid rainforests to dry savannahs and coastal areas. This ecological success is linked to its close association with domestic settings, with human playing significant roles in driving the recent urban evolution of this mosquito. Our research explores the assumption that these mosquitoes are strictly dependent on human habitats, by conducting whole-genome sequencing on An. coluzzii specimens from urban, rural, and sylvatic sites in Gabon. We found that urban mosquitoes show de novo genetic signatures of human-driven vector control, while rural and sylvatic mosquitoes exhibit distinctive genetic evidence of local adaptations derived from standing genetic variation. Understanding adaptation mechanisms of this mosquito is therefore crucial to predict evolution of vector control strategies.

Population size rescaling significantly biases outcomes of forward-in-time population genetic simulations

Simulations are an essential tool in all areas of population genetic research, used in tasks such as the validation of theoretical analysis and the study of complex evolutionary models. Forward-in-time simulations are especially flexible, allowing for various types of natural selection, complex genetic architectures, and non-Wright-Fisher dynamics. However, their intense computational requirements can be prohibitive to simulating large populations and genomes. A popular method to alleviate this burden is to scale down the population size by some scaling factor while scaling up the mutation rate, selection coefficients, and recombination rate by the same factor. However, this rescaling approach may in some cases bias simulation results. To investigate the manner and degree to which rescaling impacts simulation outcomes, we carried out simulations with different demographic histories and distributions of fitness effects using several values of the rescaling factor, Q , and compared the deviation of key outcomes (fixation times, fixation probabilities, allele frequencies, and linkage disequilibrium) between the scaled and unscaled simulations. Our results indicate that scaling introduces substantial biases to each of these measured outcomes, even at small values of Q . Moreover, the nature of these effects depends on the evolutionary model and scaling factor being examined. While increasing the scaling factor tends to increase the observed biases, this relationship is not always straightforward, thus it may be difficult to know the impact of scaling on simulation outcomes a priori. However, it appears that for most models, only a small number of replicates was needed to accurately quantify the bias produced by rescaling for a given Q . In summary, while rescaling forward-in-time simulations may be necessary in many cases, researchers should be aware of the rescaling effect's impact on simulation outcomes and consider investigating its magnitude in smaller scale simulations of the desired model(s) before selecting an appropriate value of Q .

Interpreting generative adversarial networks to infer natural selection from genetic data

Understanding natural selection and other forms of non-neutrality is a major focus for the use of machine learning in population genetics. Existing methods rely on computationally intensive simulated training data. Unlike efficient neutral coalescent simulations for demographic inference, realistic simulations of selection typically require slow forward simulations. Because there are many possible modes of selection, a high dimensional parameter space must be explored, with no guarantee that the simulated models are close to the real processes. Finally, it is difficult to interpret trained neural networks, leading to a lack of understanding about what features contribute to classification. Here we develop a new approach to detect selection and other local evolutionary processes that requires relatively few selection simulations during training. We build upon a generative adversarial network trained to simulate realistic neutral data. This consists of a generator (fitted demographic model), and a discriminator (convolutional neural network) that predicts whether a genomic region is real or fake. As the generator can only generate data under neutral demographic processes, regions of real data that the discriminator recognizes as having a high probability of being "real" do not fit the neutral demographic model and are therefore candidates for targets of selection. To incentivize identification of a specific mode of selection, we fine-tune the discriminator with a small number of custom non-neutral simulations. We show that this approach has high power to detect various forms of selection in simulations, and that it finds regions under positive selection identified by state-of-the-art population genetic methods in three human populations. Finally, we show how to interpret the trained networks by clustering hidden units of the discriminator based on their correlation patterns with known summary statistics.

Estimation of spatial demographic maps from polymorphism data using a neural network

A fundamental goal in population genetics is to understand how variation is arrayed over natural landscapes. From first principles we know that common features such as heterogeneous population densities and source sink dynamics of dispersal should shape genetic variation over space, however there are few tools currently available that can deal with these ubiquitous complexities. Geographically referenced single nucleotide polymorphism (SNP) data are increasingly accessible, presenting an opportunity to study genetic variation across geographic space in myriad species. We present a new inference method that uses geo-referenced SNPs and a deep neural network to estimate spatially heterogeneous maps of population density and dispersal rate. Our neural network trains on simulated input and output pairings, where the input consists of genotypes and sampling locations generated from a continuous space population genetic simulator, and the output is a map of the true demographic parameters. We benchmark our tool against existing methods and discuss qualitative differences between the different approaches; in particular, our program is unique because it infers the magnitude of both dispersal and density as well as their variation over the landscape, and it does so using SNP data. Similar methods are constrained to estimating relative migration rates, or require identity by descent blocks as input. We applied our tool to empirical data from North American grey wolves, for which it estimated mostly reasonable demographic parameters, but was affected by incomplete spatial sampling. Genetic based methods like ours complement other, direct methods for estimating past and present demography, and we believe will serve as valuable tools for applications in conservation, ecology, and evolutionary biology. An open source software package implementing our method is available from https://github.com/kr-colab/mapNN.

Evaluating evidence for co-geography in the Anopheles-Plasmodium host-parasite system

The often tight association between parasites and their hosts means that under certain scenarios, the evolutionary histories of the two species can become closely coupled both through time and across space. Using spatial genetic inference, we identify a potential signal of common dispersal patterns in the Anopheles gambiae and Plasmodium falciparum host-parasite system as seen through a between-species correlation of the differences between geographic sampling location and geographic location predicted from the genome. This correlation may be due to coupled dispersal dynamics between host and parasite but may also reflect statistical artifacts due to uneven spatial distribution of sampling locations. Using continuous-space population genetics simulations, we investigate the degree to which uneven distribution of sampling locations leads to bias in prediction of spatial location from genetic data and implement methods to counter this effect. We demonstrate that while algorithmic bias presents a problem in inference from spatio-genetic data, the correlation structure between A. gambiae and P. falciparum predictions cannot be attributed to spatial bias alone and is thus likely a genetic signal of co-dispersal in a host-parasite system.

Harnessing deep learning for population genetic inference

In population genetics, the emergence of large-scale genomic data for various species and populations has provided new opportunities to understand the evolutionary forces that drive genetic diversity using statistical inference. However, the era of population genomics presents new challenges in analysing the massive amounts of genomes and variants. Deep learning has demonstrated state-of-the-art performance for numerous applications involving large-scale data. Recently, deep learning approaches have gained popularity in population genetics; facilitated by the advent of massive genomic data sets, powerful computational hardware and complex deep learning architectures, they have been used to identify population structure, infer demographic history and investigate natural selection. Here, we introduce common deep learning architectures and provide comprehensive guidelines for implementing deep learning models for population genetic inference. We also discuss current challenges and future directions for applying deep learning in population genetics, focusing on efficiency, robustness and interpretability.

Evaluating evidence for co-geography in the Anopheles-Plasmodium host-parasite system

The often tight association between parasites and their hosts means that under certain scenarios, the evolutionary histories of the two species can become closely coupled both through time and across space. Using spatial genetic inference, we identify a potential signal of common dispersal patterns in the Anopheles gambiae and Plasmodium falciparum host-parasite system as seen through a between-species correlation of the differences between geographic sampling location and geographic location predicted from the genome. This correlation may be due to coupled dispersal dynamics between host and parasite, but may also reflect statistical artifacts due to uneven spatial distribution of sampling locations. Using continuous-space population genetics simulations, we investigate the degree to which uneven distribution of sampling locations leads to bias in prediction of spatial location from genetic data and implement methods to counter this effect. We demonstrate that while algorithmic bias presents a problem in inference from spatio-genetic data, the correlation structure between A. gambiae and P. falciparum predictions cannot be attributed to spatial bias alone, and is thus likely a genetic signal of co-dispersal in a host-parasite system.

disperseNN2: a neural network for estimating dispersal distance from georeferenced polymorphism data

Spatial genetic variation is shaped in part by an organism's dispersal ability. We present a deep learning tool, disperseNN2, for estimating the mean per-generation dispersal distance from georeferenced polymorphism data. Our neural network performs feature extraction on pairs of genotypes, and uses the geographic information that comes with each sample. These attributes led disperseNN2 to outperform a state-of-the-art deep learning method that does not use explicit spatial information: the mean relative absolute error was reduced by 33% and 48% using sample sizes of 10 and 100 individuals, respectively. disperseNN2 is particularly useful for non-model organisms or systems with sparse genomic resources, as it uses unphased, single nucleotide polymorphisms as its input. The software is open source and available from https://github.com/kr-colab/disperseNN2 , with documentation located at https://dispersenn2.readthedocs.io/en/latest/ .

disperseNN2: a neural network for estimating dispersal distance from georeferenced polymorphism data

Spatial genetic variation is shaped in part by an organism's dispersal ability. We present a deep learning tool, disperseNN2, for estimating the mean per-generation dispersal distance from georeferenced polymorphism data. Our neural network performs feature extraction on pairs of genotypes, and uses the geographic information that comes with each sample. These attributes led disperseNN2 to outperform a state-of-the-art deep learning method that does not use explicit spatial information: the mean relative absolute error was reduced by 33% and 48% using sample sizes of 10 and 100 individuals, respectively. disperseNN2 is particularly useful for non-model organisms or systems with sparse genomic resources, as it uses unphased, single nucleotide polymorphisms as its input. The software is open source and available from https://github.com/kr-colab/disperseNN2, with documentation located at https://dispersenn2.readthedocs.io/en/latest/.

This population does not exist: learning the distribution of evolutionary histories with generative adversarial networks

Numerous studies over the last decade have demonstrated the utility of machine learning methods when applied to population genetic tasks. More recent studies show the potential of deep-learning methods in particular, which allow researchers to approach problems without making prior assumptions about how the data should be summarized or manipulated, instead learning their own internal representation of the data in an attempt to maximize inferential accuracy. One type of deep neural network, called Generative Adversarial Networks (GANs), can even be used to generate new data, and this approach has been used to create individual artificial human genomes free from privacy concerns. In this study, we further explore the application of GANs in population genetics by designing and training a network to learn the statistical distribution of population genetic alignments (i.e. data sets consisting of sequences from an entire population sample) under several diverse evolutionary histories-the first GAN capable of performing this task. After testing multiple different neural network architectures, we report the results of a fully differentiable Deep-Convolutional Wasserstein GAN with gradient penalty that is capable of generating artificial examples of population genetic alignments that successfully mimic key aspects of the training data, including the site-frequency spectrum, differentiation between populations, and patterns of linkage disequilibrium. We demonstrate consistent training success across various evolutionary models, including models of panmictic and subdivided populations, populations at equilibrium and experiencing changes in size, and populations experiencing either no selection or positive selection of various strengths, all without the need for extensive hyperparameter tuning. Overall, our findings highlight the ability of GANs to learn and mimic population genetic data and suggest future areas where this work can be applied in population genetics research that we discuss herein.