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.

Cephalopod Sex Determination and its Ancient Evolutionary Origin Revealed by Chromosome-level Assembly of the California Two-Spot Octopus.

Sex chromosomes are critical elements of sexual reproduction in many animal and plant taxa, however they show incredible diversity and rapid turnover even within clades. Here, using a chromosome-level assembly generated with long read sequencing, we report the first evidence for genetic sex determination in cephalopods. We have uncovered a sex chromosome in California two-spot octopus (Octopus bimaculoides) in which males/females show ZZ/ZO karyotypes respectively. We show that the octopus Z chromosome is an evolutionary outlier with respect to divergence and repetitive element content as compared to other chromosomes and that it is present in all coleoid cephalopods that we have examined. Our results suggest that the cephalopod Z chromosome originated between 455 and 248 million years ago and has been conserved to the present, making it the among the oldest conserved animal sex chromosomes known.

A quantitative genetic model of background selection in humans.

Across the human genome, there are large-scale fluctuations in genetic diversity caused by the indirect effects of selection. This "linked selection signal" reflects the impact of selection according to the physical placement of functional regions and recombination rates along chromosomes. Previous work has shown that purifying selection acting against the steady influx of new deleterious mutations at functional portions of the genome shapes patterns of genomic variation. To date, statistical efforts to estimate purifying selection parameters from linked selection models have relied on classic Background Selection theory, which is only applicable when new mutations are so deleterious that they cannot fix in the population. Here, we develop a statistical method based on a quantitative genetics view of linked selection, that models how polygenic additive fitness variance distributed along the genome increases the rate of stochastic allele frequency change. By jointly predicting the equilibrium fitness variance and substitution rate due to both strong and weakly deleterious mutations, we estimate the distribution of fitness effects (DFE) and mutation rate across three geographically distinct human samples. While our model can accommodate weaker selection, we find evidence of strong selection operating similarly across all human samples. Although our quantitative genetic model of linked selection fits better than previous models, substitution rates of the most constrained sites disagree with observed divergence levels. We find that a model incorporating selective interference better predicts observed divergence in conserved regions, but overall our results suggest uncertainty remains about the processes generating fitness variation in humans.

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.

Shared evolutionary processes shape landscapes of genomic variation in the great apes.

For at least the past 5 decades, population genetics, as a field, has worked to describe the precise balance of forces that shape patterns of variation in genomes. The problem is challenging because modeling the interactions between evolutionary processes is difficult, and different processes can impact genetic variation in similar ways. In this paper, we describe how diversity and divergence between closely related species change with time, using correlations between landscapes of genetic variation as a tool to understand the interplay between evolutionary processes. We find strong correlations between landscapes of diversity and divergence in a well-sampled set of great ape genomes, and explore how various processes such as incomplete lineage sorting, mutation rate variation, GC-biased gene conversion and selection contribute to these correlations. Through highly realistic, chromosome-scale, forward-in-time simulations, we show that the landscapes of diversity and divergence in the great apes are too well correlated to be explained via strictly neutral processes alone. Our best fitting simulation includes both deleterious and beneficial mutations in functional portions of the genome, in which 9% of fixations within those regions is driven by positive selection. This study provides a framework for modeling genetic variation in closely related species, an approach which can shed light on the complex balance of forces that have shaped genetic variation.

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/.

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.

Expanding the stdpopsim species catalog, and lessons learned for realistic genome simulations.

Simulation is a key tool in population genetics for both methods development and empirical research, but producing simulations that recapitulate the main features of genomic datasets remains a major obstacle. Today, more realistic simulations are possible thanks to large increases in the quantity and quality of available genetic data, and the sophistication of inference and simulation software. However, implementing these simulations still requires substantial time and specialized knowledge. These challenges are especially pronounced for simulating genomes for species that are not well-studied, since it is not always clear what information is required to produce simulations with a level of realism sufficient to confidently answer a given question. The community-developed framework stdpopsim seeks to lower this barrier by facilitating the simulation of complex population genetic models using up-to-date information. The initial version of stdpopsim focused on establishing this framework using six well-characterized model species (Adrion et al., 2020). Here, we report on major improvements made in the new release of stdpopsim (version 0.2), which includes a significant expansion of the species catalog and substantial additions to simulation capabilities. Features added to improve the realism of the simulated genomes include non-crossover recombination and provision of species-specific genomic annotations. Through community-driven efforts, we expanded the number of species in the catalog more than threefold and broadened coverage across the tree of life. During the process of expanding the catalog, we have identified common sticking points and developed the best practices for setting up genome-scale simulations. We describe the input data required for generating a realistic simulation, suggest good practices for obtaining the relevant information from the literature, and discuss common pitfalls and major considerations. These improvements to stdpopsim aim to further promote the use of realistic whole-genome population genetic simulations, especially in non-model organisms, making them available, transparent, and accessible to everyone.

Dispersal inference from population genetic variation using a convolutional neural network.

The geographic nature of biological dispersal shapes patterns of genetic variation over landscapes, making it possible to infer properties of dispersal from genetic variation data. Here, we present an inference tool that uses geographically distributed genotype data in combination with a convolutional neural network to estimate a critical population parameter: the mean per-generation dispersal distance. Using extensive simulation, we show that our deep learning approach is competitive with or outperforms state-of-the-art methods, particularly at small sample sizes. In addition, we evaluate varying nuisance parameters during training-including population density, demographic history, habitat size, and sampling area-and show that this strategy is effective for estimating dispersal distance when other model parameters are unknown. Whereas competing methods depend on information about local population density or accurate inference of identity-by-descent tracts, our method uses only single-nucleotide-polymorphism data and the spatial scale of sampling as input. Strikingly, and unlike other methods, our method does not use the geographic coordinates of the genotyped individuals. These features make our method, which we call "disperseNN," a potentially valuable new tool for estimating dispersal distance in nonmodel systems with whole genome data or reduced representation data. We apply disperseNN to 12 different species with publicly available data, yielding reasonable estimates for most species. Importantly, our method estimated consistently larger dispersal distances than mark-recapture calculations in the same species, which may be due to the limited geographic sampling area covered by some mark-recapture studies. Thus genetic tools like ours complement direct methods for improving our understanding of dispersal.

Standing genetic variation and chromosome differences drove rapid ecotype formation in a major malaria mosquito.

Species distributed across heterogeneous environments often evolve locally adapted ecotypes, but understanding of the genetic mechanisms involved in their formation and maintenance in the face of gene flow is incomplete. In Burkina Faso, the major African malaria mosquito Anopheles funestus comprises two strictly sympatric and morphologically indistinguishable yet karyotypically differentiated forms reported to differ in ecology and behavior. However, knowledge of the genetic basis and environmental determinants of An. funestus diversification was impeded by lack of modern genomic resources. Here, we applied deep whole-genome sequencing and analysis to test the hypothesis that these two forms are ecotypes differentially adapted to breeding in natural swamps versus irrigated rice fields. We demonstrate genome-wide differentiation despite extensive microsympatry, synchronicity, and ongoing hybridization. Demographic inference supports a split only ~1,300 y ago, closely following the massive expansion of domesticated African rice cultivation ~1,850 y ago. Regions of highest divergence, concentrated in chromosomal inversions, were under selection during lineage splitting, consistent with local adaptation. The origin of nearly all variations implicated in adaptation, including chromosomal inversions, substantially predates the ecotype split, suggesting that rapid adaptation was fueled mainly by standing genetic variation. Sharp inversion frequency differences likely facilitated adaptive divergence between ecotypes by suppressing recombination between opposing chromosomal orientations of the two ecotypes, while permitting free recombination within the structurally monomorphic rice ecotype. Our results align with growing evidence from diverse taxa that rapid ecological diversification can arise from evolutionarily old structural genetic variants that modify genetic recombination.

Shared evolutionary processes shape landscapes of genomic variation in the great apes.

For at least the past five decades population genetics, as a field, has worked to describe the precise balance of forces that shape patterns of variation in genomes. The problem is challenging because modelling the interactions between evolutionary processes is difficult, and different processes can impact genetic variation in similar ways. In this paper, we describe how diversity and divergence between closely related species change with time, using correlations between landscapes of genetic variation as a tool to understand the interplay between evolutionary processes. We find strong correlations between landscapes of diversity and divergence in a well sampled set of great ape genomes, and explore how various processes such as incomplete lineage sorting, mutation rate variation, GC-biased gene conversion and selection contribute to these correlations. Through highly realistic, chromosome-scale, forward-in-time simulations we show that the landscapes of diversity and divergence in the great apes are too well correlated to be explained via strictly neutral processes alone. Our best fitting simulation includes both deleterious and beneficial mutations in functional portions of the genome, in which 9% of fixations within those regions is driven by positive selection. This study provides a framework for modelling genetic variation in closely related species, an approach which can shed light on the complex balance of forces that have shaped genetic variation.

Biomechanical guidance can improve accuracy of reduction for intra-articular tibia plafond fractures and reduce joint contact stress.

Articular fracture malreduction increases posttraumatic osteoarthritis (PTOA) risk by elevating joint contact stress. A new biomechanical guidance system (BGS) that provides intraoperative assessment of articular fracture reduction and joint contact stress based solely on a preoperative computed tomography (CT) and intraoperative fluoroscopy may facilitate better fracture reduction. The objective of this proof-of-concept cadaveric study was to test this premise while characterizing BGS performance. Articular tibia plafond fractures were created in five cadaveric ankles. CT scans were obtained to provide digital models. Indirect reduction was performed in a simulated operating room once with and once without BGS guidance. CT scans after fixation provided models of the reduced ankles for assessing reduction accuracy, joint contact stresses, and BGS accuracy. BGS was utilized 4.8 ± 1.3 (mean ± SD) times per procedure, increasing operative time by 10 min (39%), and the number of fluoroscopy images by 31 (17%). Errors in BGS reduction assessment compared to CT-derived models were 0.45 ± 0.57 mm in translation and 2.0 ± 2.5° in rotation. For the four ankles that were successfully reduced and fixed, associated absolute errors in computed mean and maximum contact stress were 0.40 ± 0.40 and 0.96 ± 1.12 MPa, respectively. BGS reduced mean and maximum contact stress by 1.1 and 2.6 MPa, respectively. BGS thus improved the accuracy of articular fracture reduction and significantly reduced contact stress. Statement of Clinical Significance: Malreduction of articular fractures is known to lead to PTOA. The BGS described in this work has potential to improve quality of articular fracture reduction and clinical outcomes for patients with a tibia plafond fracture.

Cell types and molecular architecture of the Octopus bimaculoides visual system.

Cephalopods have a remarkable visual system, with a camera-type eye and high acuity vision that they use for a wide range of sophisticated visually driven behaviors. However, the cephalopod brain is organized dramatically differently from that of vertebrates and invertebrates, and beyond neuroanatomical descriptions, little is known regarding the cell types and molecular determinants of their visual system organization. Here, we present a comprehensive single-cell molecular atlas of the octopus optic lobe, which is the primary visual processing structure in the cephalopod brain. We combined single-cell RNA sequencing with RNA fluorescence in situ hybridization to both identify putative molecular cell types and determine their anatomical and spatial organization within the optic lobe. Our results reveal six major neuronal cell classes identified by neurotransmitter/neuropeptide usage, in addition to non-neuronal and immature neuronal populations. We find that additional markers divide these neuronal classes into subtypes with distinct anatomical localizations, revealing further diversity and a detailed laminar organization within the optic lobe. We also delineate the immature neurons within this continuously growing tissue into subtypes defined by evolutionarily conserved developmental genes as well as novel cephalopod- and octopus-specific genes. Together, these findings outline the organizational logic of the octopus visual system, based on functional determinants, laminar identity, and developmental markers/pathways. The resulting atlas presented here details the "parts list" for neural circuits used for vision in octopus, providing a platform for investigations into the development and function of the octopus visual system as well as the evolution of visual processing.

The Effect of Progressive Lateral Column Lengthening in a Novel Stage II-B Flatfoot Cadaveric Model Evaluated Using Software-Guided Radiographic Measurements of Foot Alignment.

BACKGROUND: This work used software-guided radiographic measurement to assess the effects of progressive lateral column lengthening (LCL) on restoring alignment in a novel cadaveric model of stage II-B flatfoot deformity. METHODS: A stage II-B flatfoot was created in 8 cadaveric specimens by transecting the spring ligament complex, anterior deltoid, and interosseous talocalcaneal and cervical ligaments. Weightbearing computed tomographic (WBCT) scans were performed with specimens under 450 N of compressive load in the intact, flat, and 6-, 8-, and 10-mm lateral column-lengthening conditions. Custom software-guided radiographic measurements of the lateral talo-first metatarsal (Meary) angle, anteroposterior talo-first metatarsal angle, naviculocuneiform overlap, and 2 new measures (plantar fascia [PF] distance and angle) were recorded on digitally reconstructed radiographs. Four anonymized analysts performed measurements twice. Intra- and interobserver agreement was assessed using intraclass correlation coefficients (ICCs). RESULTS: Six-millimeter LCL restored alignment closest to the intact foot in this new cadaveric model, whereas 10-mm lengthening tended toward overcorrection. The PF line displaced laterally in the flatfoot condition, and LCL restored the PF line to a location beneath the talonavicular joint. Interobserver agreement was excellent for PF distance (ICC = 0.99) and naviculocuboid overlap (ICC = 0.91), good for Meary angle (ICC = 0.81) and PF angle (ICC = 0.69), and acceptable for the talonavicular coverage angle (ICC = 0.65). CONCLUSION: In this stage II-B cadaveric flatfoot model, cervical ligament transection was essential to create deformity after the medial hindfoot ligaments were transected. Software-guided radiographic measurement proved reliable; standardized implementation should improve comparability between studies of flatfoot deformity. The novel PF distance performed most consistently (ICC = 0.99) and warrants further study. With this model, we found that a 6-mm LCL restored alignment closest to the intact foot, whereas 10-mm lengthening tended toward overcorrection. CLINICAL RELEVANCE: Future joint-sparing flatfoot corrections may consider using a relatively small LCL combined with other bony and/or anatomic ligament/tendon reconstructions.

Longitudinal Relationship Between Tibiofemoral Contact Stress at Baseline and Worsening of Knee Pain Over 84 Months in the Multicenter Osteoarthritis Study.

OBJECTIVE: The aim of the study was to determine whether tibiofemoral contact stress predicts risk for worsening knee pain over 84 ms in adults aged 50-79 yrs with or at elevated risk for knee osteoarthritis. DESIGN: Baseline tibiofemoral contact stress was estimated using discrete element analysis. Other baseline measures included weight, height, hip-knee-ankle alignment, Kellgren-Lawrence grade, and Western Ontario and McMaster Universities Osteoarthritis Index pain subscale. Logistic regression models assessed the association between baseline contact stress and 84-mo worsening of Western Ontario and McMaster Universities Osteoarthritis Index pain subscale. RESULTS: Data from the dominant knee (72.6% Kellgren-Lawrence grade 0/1 and 27.4% Kellgren-Lawrence grade ≥ 2) of 208 participants (64.4% female, mean ± SD body mass index = 29.6 ± 5.1 kg/m 2 ) were analyzed. Baseline mean and peak contact stress were 3.3 ± 0.9 and 9.4 ± 4.3 MPa, respectively. Forty-seven knees met the criterion for worsening pain. The highest tertiles in comparison with the lowest tertiles of mean (odds ratio [95% confidence interval] = 2.47 [1.03-5.95], P = 0.04) and peak (2.49 [1.03-5.98], P = 0.04) contact stress were associated with worsening pain at 84 mos, after adjustment for age, sex, race, clinic site, and baseline pain. Post hoc sensitivity analyses including adjustment for body mass index and hip-knee-ankle alignment attenuated the effect. CONCLUSIONS: These findings suggest that elevated tibiofemoral contact stress can predict the development of worsening of knee pain.

Efficient ancestry and mutation simulation with msprime 1.0.

Stochastic simulation is a key tool in population genetics, since the models involved are often analytically intractable and simulation is usually the only way of obtaining ground-truth data to evaluate inferences. Because of this, a large number of specialized simulation programs have been developed, each filling a particular niche, but with largely overlapping functionality and a substantial duplication of effort. Here, we introduce msprime version 1.0, which efficiently implements ancestry and mutation simulations based on the succinct tree sequence data structure and the tskit library. We summarize msprime's many features, and show that its performance is excellent, often many times faster and more memory efficient than specialized alternatives. These high-performance features have been thoroughly tested and validated, and built using a collaborative, open source development model, which reduces duplication of effort and promotes software quality via community engagement.

Evaluating human autosomal loci for sexually antagonistic viability selection in two large biobanks.

Sex and sexual differentiation are pervasive across the tree of life. Because females and males often have substantially different functional requirements, we expect selection to differ between the sexes. Recent studies in diverse species, including humans, suggest that sexually antagonistic viability selection creates allele frequency differences between the sexes at many different loci. However, theory and population-level simulations indicate that sex-specific differences in viability would need to be very large to produce and maintain reported levels of between-sex allelic differentiation. We address this contradiction between theoretical predictions and empirical observations by evaluating evidence for sexually antagonistic viability selection on autosomal loci in humans using the largest cohort to date (UK Biobank, n = 487,999) along with a second large, independent cohort (BioVU, n = 93,864). We performed association tests between genetically ascertained sex and autosomal loci. Although we found dozens of genome-wide significant associations, none replicated across cohorts. Moreover, closer inspection revealed that all associations are likely due to cross-hybridization with sex chromosome regions during genotyping. We report loci with potential for mis-hybridization found on commonly used genotyping platforms that should be carefully considered in future genetic studies of sex-specific differences. Despite being well powered to detect allele frequency differences of up to 0.8% between the sexes, we do not detect clear evidence for this signature of sexually antagonistic viability selection on autosomal variation. These findings suggest a lack of strong ongoing sexually antagonistic viability selection acting on single locus autosomal variation in humans.

Association between foot thermal responses and shear forces during turning gait in young adults.

BACKGROUND: The human foot typically changes temperature between pre and post-locomotion activities. However, the mechanisms responsible for temperature changes within the foot are currently unclear. Prior studies indicate that shear forces may increase foot temperature during locomotion. Here, we examined the shear-temperature relationship using turning gait with varying radii to manipulate magnitudes of shear onto the foot. METHODS: Healthy adult participants (N = 18) walked barefoot on their toes for 5 minutes at a speed of 1.0 m s-1 at three different radii (1.0, 1.5, and 2.0 m). Toe-walking was utilized so that a standard force plate could measure shear localized to the forefoot. A thermal imaging camera was used to quantify the temperature changes from pre to post toe-walking (ΔT), including the entire foot and forefoot regions on the external limb (limb farther from the center of the curved path) and internal limb. RESULTS: We found that shear impulse was positively associated with ΔT within the entire foot (P < 0.001) and forefoot (P < 0.001): specifically, for every unit increase in shear, the temperature of the entire foot and forefoot increased by 0.11 and 0.17 °C, respectively. While ΔT, on average, decreased following the toe-walking trials (i.e., became colder), a significant change in ΔT was observed between radii conditions and between external versus internal limbs. In particular, ΔT was greater (i.e., less negative) when walking at smaller radii (P < 0.01) and was greater on the external limb (P < 0.01) in both the entire foot and forefoot regions, which were likely explained by greater shear forces with smaller radii (P < 0.0001) and on the external limb (P < 0.0001). Altogether, our results support the relationship between shear and foot temperature responses. These findings may motivate studying turning gait in the future to quantify the relationship between shear and foot temperature in individuals who are susceptible to abnormal thermoregulation.

Visualizing population structure with variational autoencoders.

Dimensionality reduction is a common tool for visualization and inference of population structure from genotypes, but popular methods either return too many dimensions for easy plotting (PCA) or fail to preserve global geometry (t-SNE and UMAP). Here we explore the utility of variational autoencoders (VAEs)-generative machine learning models in which a pair of neural networks seek to first compress and then recreate the input data-for visualizing population genetic variation. VAEs incorporate nonlinear relationships, allow users to define the dimensionality of the latent space, and in our tests preserve global geometry better than t-SNE and UMAP. Our implementation, which we call popvae, is available as a command-line python program at github.com/kr-colab/popvae. The approach yields latent embeddings that capture subtle aspects of population structure in humans and Anopheles mosquitoes, and can generate artificial genotypes characteristic of a given sample or population.