Predicting geographic location from genetic variation with deep neural networks

YHP: Y-chromosome Haplogroup Predictor for predicting male lineages based on Y-STRs

Human Y chromosome reflects the evolutionary process of males. Male lineage tracing by Y chromosome is of great use in evolutionary, forensic, and anthropological studies. Identifying the male lineage based on the specific distribution of Y haplogroups narrows down the investigation scope, which has been used in forensic scenarios. However, existing software aids in familial searching using Y-STRs (Y-chromosome short tandem repeats) to predict Y-SNP (Y-chromosome single nucleotide polymorphism) haplogroups, they often lack resolution. In this study, we developed YHP (Y Haplogroup Predictor), a novel software offering high-resolution haplogroup inference without requiring extensive Y-SNP sequencing. Leveraging existing datasets (219 haplogroups, 4064 samples in total), YHP predicts haplogroups with 0.923 accuracy under the highest haplogroup resolution, employing a random forest algorithm. YHP, available on Github (https://github.com/cissy123/YHP-Y-Haplogroup-Predictor-), facilitates high-resolution haplogroup prediction, haplotype mismatch analysis, and haplotype similarity comparison. Notably, it demonstrates efficacy in East Asian populations, benefiting from training data from eight distinct East Asian ethnic populations. Moreover, it enables seamless integration of additional training sets, extending its utility to diverse populations.

Privacy-preserving model evaluation for logistic and linear regression using homomorphically encrypted genotype data

OBJECTIVE

Linear and logistic regression are widely used statistical techniques in population genetics for analyzing genetic data and uncovering patterns and associations in large genetic datasets, such as identifying genetic variations linked to specific diseases or traits. However, obtaining statistically significant results from these studies requires large amounts of sensitive genotype and phenotype information from thousands of patients, which raises privacy concerns. Although cryptographic techniques such as homomorphic encryption offers a potential solution to the privacy concerns as it allows computations on encrypted data, previous methods leveraging homomorphic encryption have not addressed the confidentiality of shared models, which can leak information about the training data.

METHODS

In this work, we present a secure model evaluation method for linear and logistic regression using homomorphic encryption for six prediction tasks, where input genotypes, output phenotypes, and model parameters are all encrypted.

RESULTS

Our method ensures no private information leakage during inference and achieves high accuracy (≥93% for all outcomes) with each inference taking less than ten seconds for ∼200 genomes.

CONCLUSION

Our study demonstrates that it is possible to perform linear and logistic regression model evaluation while protecting patient confidentiality with theoretical security guarantees. Our implementation and test data are available at https://github.com/G2Lab/privateML/.

A genome-guided strategy for climate resilience in American chestnut restoration populations

American chestnut (Castanea dentata) is a deciduous tree species of eastern North America that was decimated by the introduction of the chestnut blight fungus (Cryphonectria parasitica) in the early 20th century. Although millions of American chestnuts survive as root collar sprouts, these trees rarely reproduce. Thus, the species is considered functionally extinct. American chestnuts with improved blight resistance have been developed through interspecific hybridization followed by conspecific backcrossing, and by genetic engineering. Incorporating adaptive genomic diversity into these backcross families and transgenic lines is important for restoring the species across broad climatic gradients. To develop sampling recommendations for ex situ conservation of wild adaptive genetic variation, we coupled whole-genome resequencing of 384 stump sprouts with genotype-environment association analyses and found that the species range can be subdivided into three seed zones characterized by relatively homogeneous adaptive allele frequencies. We estimated that 21 to 29 trees per seed zone will need to be conserved to capture most extant adaptive diversity. We also resequenced the genomes of 269 backcross trees to understand the extent to which the breeding program has already captured wild adaptive diversity, and to estimate optimal reintroduction sites for specific families on the basis of their adaptive portfolio and future climate projections. Taken together, these results inform the development of an ex situ germplasm conservation and breeding plan to target blight-resistant breeding populations to specific environments and provides a blueprint for developing restoration plans for other imperiled tree species.

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 barriers to 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 .

Estimating scale-specific and localized spatial patterns in allele frequency

Characterizing spatial patterns in allele frequencies is fundamental to evolutionary biology because these patterns contain evidence of underlying processes. However, the spatial scales at which gene flow, changing selection, and drift act are often unknown. Many of these processes can operate inconsistently across space, causing nonstationary patterns. We present a wavelet approach to characterize spatial pattern in allele frequency that helps solve these problems. We show how our approach can characterize spatial patterns in relatedness at multiple spatial scales, i.e. a multilocus wavelet genetic dissimilarity. We also develop wavelet tests of spatial differentiation in allele frequency and quantitative trait loci (QTL). With simulation, we illustrate these methods under different scenarios. We also apply our approach to natural populations of Arabidopsis thaliana to characterize population structure and identify locally adapted loci across scales. We find, for example, that Arabidopsis flowering time QTL show significantly elevated genetic differentiation at 300-1,300 km scales. Wavelet transforms of allele frequencies offer a flexible way to reveal geographic patterns and underlying evolutionary processes.

Widespread horse-based mobility arose around 2200 BCE in Eurasia

Horses revolutionized human history with fast mobility1. However, the timeline between their domestication and their widespread integration as a means of transport remains contentious2-4. Here we assemble a collection of 475 ancient horse genomes to assess the period when these animals were first reshaped by human agency in Eurasia. We find that reproductive control of the modern domestic lineage emerged around 2200 BCE, through close-kin mating and shortened generation times. Reproductive control emerged following a severe domestication bottleneck starting no earlier than approximately 2700 BCE, and coincided with a sudden expansion across Eurasia that ultimately resulted in the replacement of nearly every local horse lineage. This expansion marked the rise of widespread horse-based mobility in human history, which refutes the commonly held narrative of large horse herds accompanying the massive migration of steppe peoples across Europe around 3000 BCE and earlier3,5. Finally, we detect significantly shortened generation times at Botai around 3500 BCE, a settlement from central Asia associated with corrals and a subsistence economy centred on horses6,7. This supports local horse husbandry before the rise of modern domestic bloodlines.

Deep Learning and Likelihood Approaches for Viral Phylogeography Converge on the Same Answers Whether the Inference Model Is Right or Wrong

Analysis of phylogenetic trees has become an essential tool in epidemiology. Likelihood-based methods fit models to phylogenies to draw inferences about the phylodynamics and history of viral transmission. However, these methods are often computationally expensive, which limits the complexity and realism of phylodynamic models and makes them ill-suited for informing policy decisions in real-time during rapidly developing outbreaks. Likelihood-free methods using deep learning are pushing the boundaries of inference beyond these constraints. In this paper, we extend, compare, and contrast a recently developed deep learning method for likelihood-free inference from trees. We trained multiple deep neural networks using phylogenies from simulated outbreaks that spread among 5 locations and found they achieve close to the same levels of accuracy as Bayesian inference under the true simulation model. We compared robustness to model misspecification of a trained neural network to that of a Bayesian method. We found that both models had comparable performance, converging on similar biases. We also implemented a method of uncertainty quantification called conformalized quantile regression that we demonstrate has similar patterns of sensitivity to model misspecification as Bayesian highest posterior density (HPD) and greatly overlap with HPDs, but have lower precision (more conservative). Finally, we trained and tested a neural network against phylogeographic data from a recent study of the SARS-Cov-2 pandemic in Europe and obtained similar estimates of region-specific epidemiological parameters and the location of the common ancestor in Europe. Along with being as accurate and robust as likelihood-based methods, our trained neural networks are on average over 3 orders of magnitude faster after training. Our results support the notion that neural networks can be trained with simulated data to accurately mimic the good and bad statistical properties of the likelihood functions of generative phylogenetic models.

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.

IntroUNET: Identifying introgressed alleles via semantic segmentation

A growing body of evidence suggests that gene flow between closely related species is a widespread phenomenon. Alleles that introgress from one species into a close relative are typically neutral or deleterious, but sometimes confer a significant fitness advantage. Given the potential relevance to speciation and adaptation, numerous methods have therefore been devised to identify regions of the genome that have experienced introgression. Recently, supervised machine learning approaches have been shown to be highly effective for detecting introgression. One especially promising approach is to treat population genetic inference as an image classification problem, and feed an image representation of a population genetic alignment as input to a deep neural network that distinguishes among evolutionary models (i.e. introgression or no introgression). However, if we wish to investigate the full extent and fitness effects of introgression, merely identifying genomic regions in a population genetic alignment that harbor introgressed loci is insufficient-ideally we would be able to infer precisely which individuals have introgressed material and at which positions in the genome. Here we adapt a deep learning algorithm for semantic segmentation, the task of correctly identifying the type of object to which each individual pixel in an image belongs, to the task of identifying introgressed alleles. Our trained neural network is thus able to infer, for each individual in a two-population alignment, which of those individual's alleles were introgressed from the other population. We use simulated data to show that this approach is highly accurate, and that it can be readily extended to identify alleles that are introgressed from an unsampled "ghost" population, performing comparably to a supervised learning method tailored specifically to that task. Finally, we apply this method to data from Drosophila, showing that it is able to accurately recover introgressed haplotypes from real data. This analysis reveals that introgressed alleles are typically confined to lower frequencies within genic regions, suggestive of purifying selection, but are found at much higher frequencies in a region previously shown to be affected by adaptive introgression. Our method's success in recovering introgressed haplotypes in challenging real-world scenarios underscores the utility of deep learning approaches for making richer evolutionary inferences from genomic data.

IntroUNET: identifying introgressed alleles via semantic segmentation

A growing body of evidence suggests that gene flow between closely related species is a widespread phenomenon. Alleles that introgress from one species into a close relative are typically neutral or deleterious, but sometimes confer a significant fitness advantage. Given the potential relevance to speciation and adaptation, numerous methods have therefore been devised to identify regions of the genome that have experienced introgression. Recently, supervised machine learning approaches have been shown to be highly effective for detecting introgression. One especially promising approach is to treat population genetic inference as an image classification problem, and feed an image representation of a population genetic alignment as input to a deep neural network that distinguishes among evolutionary models (i.e. introgression or no introgression). However, if we wish to investigate the full extent and fitness effects of introgression, merely identifying genomic regions in a population genetic alignment that harbor introgressed loci is insufficient-ideally we would be able to infer precisely which individuals have introgressed material and at which positions in the genome. Here we adapt a deep learning algorithm for semantic segmentation, the task of correctly identifying the type of object to which each individual pixel in an image belongs, to the task of identifying introgressed alleles. Our trained neural network is thus able to infer, for each individual in a two-population alignment, which of those individual's alleles were introgressed from the other population. We use simulated data to show that this approach is highly accurate, and that it can be readily extended to identify alleles that are introgressed from an unsampled "ghost" population, performing comparably to a supervised learning method tailored specifically to that task. Finally, we apply this method to data from Drosophila, showing that it is able to accurately recover introgressed haplotypes from real data. This analysis reveals that introgressed alleles are typically confined to lower frequencies within genic regions, suggestive of purifying selection, but are found at much higher frequencies in a region previously shown to be affected by adaptive introgression. Our method's success in recovering introgressed haplotypes in challenging real-world scenarios underscores the utility of deep learning approaches for making richer evolutionary inferences from genomic data.

Genomic Tools in Biological Invasions: Current State and Future Frontiers

Human activities are accelerating rates of biological invasions and climate-driven range expansions globally, yet we understand little of how genomic processes facilitate the invasion process. Although most of the literature has focused on underlying phenotypic correlates of invasiveness, advances in genomic technologies are showing a strong link between genomic variation and invasion success. Here, we consider the ability of genomic tools and technologies to (i) inform mechanistic understanding of biological invasions and (ii) solve real-world issues in predicting and managing biological invasions. For both, we examine the current state of the field and discuss how genomics can be leveraged in the future. In addition, we make recommendations pertinent to broader research issues, such as data sovereignty, metadata standards, collaboration, and science communication best practices that will require concerted efforts from the global invasion genomics community.

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.

A Machine-Learning-Based Approach to Prediction of Biogeographic Ancestry within Europe

Data obtained with the use of massive parallel sequencing (MPS) can be valuable in population genetics studies. In particular, such data harbor the potential for distinguishing samples from different populations, especially from those coming from adjacent populations of common origin. Machine learning (ML) techniques seem to be especially well suited for analyzing large datasets obtained using MPS. The Slavic populations constitute about a third of the population of Europe and inhabit a large area of the continent, while being relatively closely related in population genetics terms. In this proof-of-concept study, various ML techniques were used to classify DNA samples from Slavic and non-Slavic individuals. The primary objective of this study was to empirically evaluate the feasibility of discerning the genetic provenance of individuals of Slavic descent who exhibit genetic similarity, with the overarching goal of categorizing DNA specimens derived from diverse Slavic population representatives. Raw sequencing data were pre-processed, to obtain a 1200 character-long binary vector. A total of three classifiers were used-Random Forest, Support Vector Machine (SVM), and XGBoost. The most-promising results were obtained using SVM with a linear kernel, with 99.9% accuracy and F1-scores of 0.9846-1.000 for all classes.

Inference of Coalescence Times and Variant Ages Using Convolutional Neural Networks

Accurate inference of the time to the most recent common ancestor (TMRCA) between pairs of individuals and of the age of genomic variants is key in several population genetic analyses. We developed a likelihood-free approach, called CoalNN, which uses a convolutional neural network to predict pairwise TMRCAs and allele ages from sequencing or SNP array data. CoalNN is trained through simulation and can be adapted to varying parameters, such as demographic history, using transfer learning. Across several simulated scenarios, CoalNN matched or outperformed the accuracy of model-based approaches for pairwise TMRCA and allele age prediction. We applied CoalNN to settings for which model-based approaches are under-developed and performed analyses to gain insights into the set of features it uses to perform TMRCA prediction. We next used CoalNN to analyze 2,504 samples from 26 populations in the 1,000 Genome Project data set, inferring the age of ∼80 million variants. We observed substantial variation across populations and for variants predicted to be pathogenic, reflecting heterogeneous demographic histories and the action of negative selection. We used CoalNN's predicted allele ages to construct genome-wide annotations capturing the signature of past negative selection. We performed LD-score regression analysis of heritability using summary association statistics from 63 independent complex traits and diseases (average N=314k), observing increased annotation-specific effects on heritability compared to a previous allele age annotation. These results highlight the effectiveness of using likelihood-free, simulation-trained models to infer properties of gene genealogies in large genomic data sets.

Neural ADMIXTURE for rapid genomic clustering

Characterizing the genetic structure of large cohorts has become increasingly important as genetic studies extend to massive, increasingly diverse biobanks. Popular methods decompose individual genomes into fractional cluster assignments with each cluster representing a vector of DNA variant frequencies. However, with rapidly increasing biobank sizes, these methods have become computationally intractable. Here we present Neural ADMIXTURE, a neural network autoencoder that follows the same modeling assumptions as the current standard algorithm, ADMIXTURE, while reducing the compute time by orders of magnitude surpassing even the fastest alternatives. One month of continuous compute using ADMIXTURE can be reduced to just hours with Neural ADMIXTURE. A multi-head approach allows Neural ADMIXTURE to offer even further acceleration by calculating multiple cluster numbers in a single run. Furthermore, the models can be stored, allowing cluster assignment to be performed on new data in linear time without needing to share the training samples.

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.

Enabling interpretable machine learning for biological data with reliability scores

Machine learning tools have proven useful across biological disciplines, allowing researchers to draw conclusions from large datasets, and opening up new opportunities for interpreting complex and heterogeneous biological data. Alongside the rapid growth of machine learning, there have also been growing pains: some models that appear to perform well have later been revealed to rely on features of the data that are artifactual or biased; this feeds into the general criticism that machine learning models are designed to optimize model performance over the creation of new biological insights. A natural question arises: how do we develop machine learning models that are inherently interpretable or explainable? In this manuscript, we describe the SWIF(r) reliability score (SRS), a method building on the SWIF(r) generative framework that reflects the trustworthiness of the classification of a specific instance. The concept of the reliability score has the potential to generalize to other machine learning methods. We demonstrate the utility of the SRS when faced with common challenges in machine learning including: 1) an unknown class present in testing data that was not present in training data, 2) systemic mismatch between training and testing data, and 3) instances of testing data that have missing values for some attributes. We explore these applications of the SRS using a range of biological datasets, from agricultural data on seed morphology, to 22 quantitative traits in the UK Biobank, and population genetic simulations and 1000 Genomes Project data. With each of these examples, we demonstrate how the SRS can allow researchers to interrogate their data and training approach thoroughly, and to pair their domain-specific knowledge with powerful machine-learning frameworks. We also compare the SRS to related tools for outlier and novelty detection, and find that it has comparable performance, with the advantage of being able to operate when some data are missing. The SRS, and the broader discussion of interpretable scientific machine learning, will aid researchers in the biological machine learning space as they seek to harness the power of machine learning without sacrificing rigor and biological insight.

Localizing Post-Admixture Adaptive Variants with Object Detection on Ancestry-Painted Chromosomes

Gene flow between previously differentiated populations during the founding of an admixed or hybrid population has the potential to introduce adaptive alleles into the new population. If the adaptive allele is common in one source population, but not the other, then as the adaptive allele rises in frequency in the admixed population, genetic ancestry from the source containing the adaptive allele will increase nearby as well. Patterns of genetic ancestry have therefore been used to identify post-admixture positive selection in humans and other animals, including examples in immunity, metabolism, and animal coloration. A common method identifies regions of the genome that have local ancestry "outliers" compared with the distribution across the rest of the genome, considering each locus independently. However, we lack theoretical models for expected distributions of ancestry under various demographic scenarios, resulting in potential false positives and false negatives. Further, ancestry patterns between distant sites are often not independent. As a result, current methods tend to infer wide genomic regions containing many genes as under selection, limiting biological interpretation. Instead, we develop a deep learning object detection method applied to images generated from local ancestry-painted genomes. This approach preserves information from the surrounding genomic context and avoids potential pitfalls of user-defined summary statistics. We find the method is robust to a variety of demographic misspecifications using simulated data. Applied to human genotype data from Cabo Verde, we localize a known adaptive locus to a single narrow region compared with multiple or long windows obtained using two other ancestry-based methods.

Estimating human mobility in Holocene Western Eurasia with large-scale ancient genomic data

The recent increase in openly available ancient human DNA samples allows for large-scale meta-analysis applications. Trans-generational past human mobility is one of the key aspects that ancient genomics can contribute to since changes in genetic ancestry-unlike cultural changes seen in the archaeological record-necessarily reflect movements of people. Here, we present an algorithm for spatiotemporal mapping of genetic profiles, which allow for direct estimates of past human mobility from large ancient genomic datasets. The key idea of the method is to derive a spatial probability surface of genetic similarity for each individual in its respective past. This is achieved by first creating an interpolated ancestry field through space and time based on multivariate statistics and Gaussian process regression and then using this field to map the ancient individuals into space according to their genetic profile. We apply this algorithm to a dataset of 3138 aDNA samples with genome-wide data from Western Eurasia in the last 10,000 y. Finally, we condense this sample-wise record with a simple summary statistic into a diachronic measure of mobility for subregions in Western, Central, and Southern Europe. For regions and periods with sufficient data coverage, our similarity surfaces and mobility estimates show general concordance with previous results and provide a meta-perspective of genetic changes and human mobility.

Deep Learning in Population Genetics

Population genetics is transitioning into a data-driven discipline thanks to the availability of large-scale genomic data and the need to study increasingly complex evolutionary scenarios. With likelihood and Bayesian approaches becoming either intractable or computationally unfeasible, machine learning, and in particular deep learning, algorithms are emerging as popular techniques for population genetic inferences. These approaches rely on algorithms that learn non-linear relationships between the input data and the model parameters being estimated through representation learning from training data sets. Deep learning algorithms currently employed in the field comprise discriminative and generative models with fully connected, convolutional, or recurrent layers. Additionally, a wide range of powerful simulators to generate training data under complex scenarios are now available. The application of deep learning to empirical data sets mostly replicates previous findings of demography reconstruction and signals of natural selection in model organisms. To showcase the feasibility of deep learning to tackle new challenges, we designed a branched architecture to detect signals of recent balancing selection from temporal haplotypic data, which exhibited good predictive performance on simulated data. Investigations on the interpretability of neural networks, their robustness to uncertain training data, and creative representation of population genetic data, will provide further opportunities for technological advancements in the field.

Image Geo-Site Estimation Using Convolutional Auto-Encoder and Multi-Label Support Vector Machine

The estimation of an image geo-site solely based on its contents is a promising task. Compelling image labelling relies heavily on contextual information, which is not as simple as recognizing a single object in an image. An Auto-Encode-based support vector machine approach is proposed in this work to estimate the image geo-site to address the issue of misclassifying the estimations. The proposed method for geo-site estimation is conducted using a dataset consisting of 125 classes of various images captured within 125 countries. The proposed work uses a convolutional Auto-Encode for training and dimensionality reduction. After that, the acquired preprocessed input dataset is further processed by a multi-label support vector machine. The performance assessment of the proposed approach has been accomplished using accuracy, sensitivity, specificity, and F1-score as evaluation parameters. Eventually, the proposed approach for image geo-site estimation presented in this article outperforms Auto-Encode-based K-Nearest Neighbor and Auto-Encode-Random Forest methods.

Geographical classification of malaria parasites through applying machine learning to whole genome sequence data

Malaria, caused by Plasmodium parasites, is a major global health challenge. Whole genome sequencing (WGS) of Plasmodium falciparum and Plasmodium vivax genomes is providing insights into parasite genetic diversity, transmission patterns, and can inform decision making for clinical and surveillance purposes. Advances in sequencing technologies are helping to generate timely and big genomic datasets, with the prospect of applying Artificial Intelligence analytical techniques (e.g., machine learning) to support programmatic malaria control and elimination. Here, we assess the potential of applying deep learning convolutional neural network approaches to predict the geographic origin of infections (continents, countries, GPS locations) using WGS data of P. falciparum (n = 5957; 27 countries) and P. vivax (n = 659; 13 countries) isolates. Using identified high-quality genome-wide single nucleotide polymorphisms (SNPs) (P. falciparum: 750 k, P. vivax: 588 k), an analysis of population structure and ancestry revealed clustering at the country-level. When predicting locations for both species, classification (compared to regression) methods had the lowest distance errors, and > 90% accuracy at a country level. Our work demonstrates the utility of machine learning approaches for geo-classification of malaria parasites. With timelier WGS data generation across more malaria-affected regions, the performance of machine learning approaches for geo-classification will improve, thereby supporting disease control activities.

dnadna: a deep learning framework for population genetics inference

MOTIVATION

We present dnadna, a flexible python-based software for deep learning inference in population genetics. It is task-agnostic and aims at facilitating the development, reproducibility, dissemination and re-usability of neural networks designed for population genetic data.

RESULTS

dnadna defines multiple user-friendly workflows. First, users can implement new architectures and tasks, while benefiting from dnadna utility functions, training procedure and test environment, which saves time and decreases the likelihood of bugs. Second, the implemented networks can be re-optimized based on user-specified training sets and/or tasks. Newly implemented architectures and pre-trained networks are easily shareable with the community for further benchmarking or other applications. Finally, users can apply pre-trained networks in order to predict evolutionary history from alternative real or simulated genetic datasets, without requiring extensive knowledge in deep learning or coding in general. dnadna comes with a peer-reviewed, exchangeable neural network, allowing demographic inference from SNP data, that can be used directly or retrained to solve other tasks. Toy networks are also available to ease the exploration of the software, and we expect that the range of available architectures will keep expanding thanks to community contributions.

AVAILABILITY AND IMPLEMENTATION

dnadna is a Python (≥3.7) package, its repository is available at gitlab.com/mlgenetics/dnadna and its associated documentation at mlgenetics.gitlab.io/dnadna/.

The Anglo-Saxon migration and the formation of the early English gene pool

The history of the British Isles and Ireland is characterized by multiple periods of major cultural change, including the influential transformation after the end of Roman rule, which precipitated shifts in language, settlement patterns and material culture1. The extent to which migration from continental Europe mediated these transitions is a matter of long-standing debate2-4. Here we study genome-wide ancient DNA from 460 medieval northwestern Europeans-including 278 individuals from England-alongside archaeological data, to infer contemporary population dynamics. We identify a substantial increase of continental northern European ancestry in early medieval England, which is closely related to the early medieval and present-day inhabitants of Germany and Denmark, implying large-scale substantial migration across the North Sea into Britain during the Early Middle Ages. As a result, the individuals who we analysed from eastern England derived up to 76% of their ancestry from the continental North Sea zone, albeit with substantial regional variation and heterogeneity within sites. We show that women with immigrant ancestry were more often furnished with grave goods than women with local ancestry, whereas men with weapons were as likely not to be of immigrant ancestry. A comparison with present-day Britain indicates that subsequent demographic events reduced the fraction of continental northern European ancestry while introducing further ancestry components into the English gene pool, including substantial southwestern European ancestry most closely related to that seen in Iron Age France5,6.

Prospects for genomic surveillance for selection in schistosome parasites

Schistosomiasis is a neglected tropical disease caused by multiple parasitic Schistosoma species, and which impacts over 200 million people globally, mainly in low- and middle-income countries. Genomic surveillance to detect evidence for natural selection in schistosome populations represents an emerging and promising approach to identify and interpret schistosome responses to ongoing control efforts or other environmental factors. Here we review how genomic variation is used to detect selection, how these approaches have been applied to schistosomes, and how future studies to detect selection may be improved. We discuss the theory of genomic analyses to detect selection, identify experimental designs for such analyses, and review studies that have applied these approaches to schistosomes. We then consider the biological characteristics of schistosomes that are expected to respond to selection, particularly those that may be impacted by control programs. Examples include drug resistance, host specificity, and life history traits, and we review our current understanding of specific genes that underlie them in schistosomes. We also discuss how inherent features of schistosome reproduction and demography pose substantial challenges for effective identification of these traits and their genomic bases. We conclude by discussing how genomic surveillance for selection should be designed to improve understanding of schistosome biology, and how the parasite changes in response to selection.

Deciphering signatures of natural selection via deep learning

Identifying genomic regions influenced by natural selection provides fundamental insights into the genetic basis of local adaptation. However, it remains challenging to detect loci under complex spatially varying selection. We propose a deep learning-based framework, DeepGenomeScan, which can detect signatures of spatially varying selection. We demonstrate that DeepGenomeScan outperformed principal component analysis- and redundancy analysis-based genome scans in identifying loci underlying quantitative traits subject to complex spatial patterns of selection. Noticeably, DeepGenomeScan increases statistical power by up to 47.25% under nonlinear environmental selection patterns. We applied DeepGenomeScan to a European human genetic dataset and identified some well-known genes under selection and a substantial number of clinically important genes that were not identified by SPA, iHS, Fst and Bayenv when applied to the same dataset.

Origins of high latitude introductions of Aedes aegypti to Nebraska and Utah during 2019

Aedes aegypti (L.), the yellow fever mosquito, is also an important vector of dengue and Zika viruses, and an invasive species in North America. Aedes aegypti inhabits tropical and sub-tropical areas of the world and in North America is primarily distributed throughout the southern US states and Mexico. The northern range of Ae. aegypti is limited by cold winter months and establishment in these areas has been mostly unsuccessful. However, frequent introductions of Ae. aegypti to temperate, non-endemic areas during the warmer months can lead to seasonal activity and disease outbreaks. Two Ae. aegypti incursions were reported in the late summer of 2019 into York, Nebraska and Moab, Utah. These states had no history of established populations of this mosquito and no evidence of previous seasonal activity. We genotyped a subset of individuals from each location at 12 microsatellite loci and ~ 14,000 single nucleotide polymorphic markers to determine their genetic affinities to other populations worldwide and investigate their potential source of introduction. Our results support a single origin for each of the introductions from different sources. Aedes aegypti from Utah likely derived from Tucson, Arizona, or a nearby location. Nebraska specimen results were not as conclusive, but point to an origin from southcentral or southeastern US. In addition to an effective, efficient, and sustainable control of invasive mosquitoes, such as Ae. aegypti, identifying the potential routes of introduction will be key to prevent future incursions and assess their potential health threat based on the ability of the source population to transmit a particular virus and its insecticide resistance profile, which may complicate vector control.

KLFDAPC: a supervised machine learning approach for spatial genetic structure analysis

Geographic patterns of human genetic variation provide important insights into human evolution and disease. A commonly used tool to detect and describe them is principal component analysis (PCA) or the supervised linear discriminant analysis of principal components (DAPC). However, genetic features produced from both approaches could fail to correctly characterize population structure for complex scenarios involving admixture. In this study, we introduce Kernel Local Fisher Discriminant Analysis of Principal Components (KLFDAPC), a supervised non-linear approach for inferring individual geographic genetic structure that could rectify the limitations of these approaches by preserving the multimodal space of samples. We tested the power of KLFDAPC to infer population structure and to predict individual geographic origin using neural networks. Simulation results showed that KLFDAPC has higher discriminatory power than PCA and DAPC. The application of our method to empirical European and East Asian genome-wide genetic datasets indicated that the first two reduced features of KLFDAPC correctly recapitulated the geography of individuals and significantly improved the accuracy of predicting individual geographic origin when compared to PCA and DAPC. Therefore, KLFDAPC can be useful for geographic ancestry inference, design of genome scans and correction for spatial stratification in GWAS that link genes to adaptation or disease susceptibility.

Wild sunflower goes viral: citizen science and comparative genomics allow tracking the origin and establishment of invasive sunflower in the Levant

Globalization and intensified volume of trade and transport around the world are accelerating the rate of biological invasions. It is therefore increasingly important to understand the processes through which invasive species colonize new habitats, often to the detriment of native flora. The initial steps of an invasion are particularly critical, as the introduced species relies on limited genetic diversity to adapt to a new environment. However, our understanding of this critical stage of the invasion is currently limited. We used a citizen science approach and social media to survey the distribution of invasive sunflower in Israel. We then sampled and sequenced a representative collection and compared it with available genomic data sets of North American wild sunflower, landraces and cultivars. We show that invasive wild sunflower is rapidly establishing throughout Israel, probably from a single, recent introduction from Texas, while maintaining high genetic diversity through ongoing gene flow. Since its introduction, invasive sunflower has spread quickly to most regions, and differentiation was detected despite extensive gene flow between clusters. Our findings suggest that rapid spread followed by continuous gene flow between diverging populations can serve as an efficient mechanism for maintaining sufficient genetic diversity at the early stages of invasion, promoting rapid adaptation and establishment in the new territory.

Identification of Species by Combining Molecular and Morphological Data Using Convolutional Neural Networks

Integrative taxonomy is central to modern taxonomy and systematic biology, including behaviour, niche preference, distribution, morphological analysis and DNA barcoding. However, decades of use demonstrate that these methods can face challenges when used in isolation, for instance, potential misidentifications due to phenotypic plasticity for morphological methods, and incorrect identifications because of introgression, incomplete lineage sorting and horizontal gene transfer for DNA barcoding. Although researchers have advocated the use of integrative taxonomy, few detailed algorithms have been proposed. Here, we develop a convolutional neural network method (morphology-molecule network (MMNet)) that integrates morphological and molecular data for species identification. The newly proposed method (MMNet) worked better than four currently-available alternative methods when tested with 10 independent datasets representing varying genetic diversity from different taxa. High accuracies were achieved for all groups, including beetles (98.1% of 123 species), butterflies (98.8% of 24 species), fishes (96.3% of 214 species) and moths (96.4% of 150 total species). Further, MMNet demonstrated a high degree of accuracy (>98%) in four datasets including closely related species from the same genus. The average accuracy of two modest sub-genomic (single nucleotide polymorphism) datasets, comprising eight putative subspecies respectively, is 90%. Additional tests show that the success rate of species identification under this method most strongly depends on the amount of training data, and is robust to sequence length and image size. Analyses on the contribution of different data types (image versus gene) indicate that both morphological and genetic data are important to the model, and that genetic data contribute slightly more. The approaches developed here serve as a foundation for the future integration of multi-modal information for integrative taxonomy, such as image, audio, video, 3D scanning and biosensor data, to characterize organisms more comprehensively as a basis for improved investigation, monitoring and conservation of biodiversity.

LINADMIX: Evaluating the effect of ancient admixture events on modern populations

MOTIVATION

The rise in the number of genotyped ancient individuals provides an opportunity to estimate population admixture models for many populations. However, in models describing modern populations as mixtures of ancient ones, it is typically difficult to estimate the model mixing coefficients and to evaluate its fit to the data.

RESULTS

We present LINADMIX, designed to tackle this problem by solving a constrained linear model when both the ancient and the modern genotypes are represented in a low-dimensional space. LINADMIX estimates the mixing coefficients and their standard errors, and computes a p-value for testing the model fit to the data. We quantified the performance of LINADMIX using an extensive set of simulated studies. We show that LINADMIX can accurately estimate admixture coefficients, and is robust to factors such as population size, genetic drift, proportion of missing data, and various types of model misspecification.

AVAILABILITY

LINADMIX is available as a python code at https://github.com/swidler/linadmix.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Introgression shapes fruit color convergence in invasive Galápagos tomato

Invasive species represent one of the foremost risks to global biodiversity. Here, we use population genomics to evaluate the history and consequences of an invasion of wild tomato-Solanum pimpinellifolium-onto the Galápagos Islands from continental South America. Using >300 archipelago and mainland collections, we infer this invasion was recent and largely the result of a single event from central Ecuador. Patterns of ancestry within the genomes of invasive plants also reveal post-colonization hybridization and introgression between S. pimpinellifolium and the closely related Galápagos endemic Solanum cheesmaniae. Of admixed invasive individuals, those that carry endemic alleles at one of two different carotenoid biosynthesis loci also have orange fruits-characteristic of the endemic species-instead of typical red S. pimpinellifolium fruits. We infer that introgression of two independent fruit color loci explains this observed trait convergence, suggesting that selection has favored repeated transitions of red to orange fruits on the Galápagos.

Spatial population genetics in heavily managed species: Separating patterns of historical translocation from contemporary gene flow in white-tailed deer

Approximately 100 years ago, unregulated harvest nearly eliminated white-tailed deer (Odocoileus virginianus) from eastern North America, which subsequently served to catalyze wildlife management as a national priority. An extensive stock-replenishment effort soon followed, with deer broadly translocated among states as a means of re-establishment. However, an unintended consequence was that natural patterns of gene flow became obscured and pretranslocation signatures of population structure were replaced. We applied cutting-edge molecular and biogeographic tools to disentangle genetic signatures of historical management from those reflecting spatially heterogeneous dispersal by evaluating 35,099 single nucleotide polymorphisms (SNPs) derived via reduced-representation genomic sequencing from 1143 deer sampled statewide in Arkansas. We then employed Simpson's diversity index to summarize ancestry assignments and visualize spatial genetic transitions. Using sub-sampled transects across these transitions, we tested clinal patterns across loci against theoretical expectations of their response under scenarios of re-colonization and restricted dispersal. Two salient results emerged: (A) Genetic signatures from historic translocations are demonstrably apparent; and (B) Geographic filters (major rivers; urban centers; highways) now act as inflection points for the distribution of this contemporary ancestry. These results yielded a statewide assessment of contemporary population structure in deer as driven by historic translocations as well as ongoing processes. In addition, the analytical framework employed herein to effectively decipher extant/historic drivers of deer distribution in Arkansas is also applicable for other biodiversity elements with similarly complex demographic histories.

Predicting future from past: The genomic basis of recurrent and rapid stickleback evolution

Similar forms often evolve repeatedly in nature, raising long-standing questions about the underlying mechanisms. Here, we use repeated evolution in stickleback to identify a large set of genomic loci that change recurrently during colonization of freshwater habitats by marine fish. The same loci used repeatedly in extant populations also show rapid allele frequency changes when new freshwater populations are experimentally established from marine ancestors. Marked genotypic and phenotypic changes arise within 5 years, facilitated by standing genetic variation and linkage between adaptive regions. Both the speed and location of changes can be predicted using empirical observations of recurrence in natural populations or fundamental genomic features like allelic age, recombination rates, density of divergent loci, and overlap with mapped traits. A composite model trained on these stickleback features can also predict the location of key evolutionary loci in Darwin's finches, suggesting that similar features are important for evolution across diverse taxa.

Insights into invasive species from whole-genome resequencing

Studies of invasive species can simultaneously inform management strategies and quantify rapid evolution in the wild. The role of genomics in invasion science is increasingly recognised, and the growing availability of reference genomes for invasive species is paving the way for whole-genome resequencing studies in a wide range of systems. Here, we survey the literature to assess the application of whole-genome resequencing data in invasion biology. For some applications, such as the reconstruction of invasion routes in time and space, sequencing the whole genome of many individuals can increase the accuracy of existing methods. In other cases, population genomic approaches such as haplotype analysis can permit entirely new questions to be addressed and new technologies applied. To date whole-genome resequencing has only been used in a handful of invasive systems, but these studies have confirmed the importance of processes such as balancing selection and hybridization in allowing invasive species to reuse existing adaptations and rapidly overcome the challenges of a foreign ecosystem. The use of genomic data does not constitute a paradigm shift per se, but by leveraging new theory, tools, and technologies, population genomics can provide unprecedented insight into basic and applied aspects of invasion science.

Discovery of Ongoing Selective Sweeps within Anopheles Mosquito Populations Using Deep Learning

Identification of partial sweeps, which include both hard and soft sweeps that have not currently reached fixation, provides crucial information about ongoing evolutionary responses. To this end, we introduce partialS/HIC, a deep learning method to discover selective sweeps from population genomic data. partialS/HIC uses a convolutional neural network for image processing, which is trained with a large suite of summary statistics derived from coalescent simulations incorporating population-specific history, to distinguish between completed versus partial sweeps, hard versus soft sweeps, and regions directly affected by selection versus those merely linked to nearby selective sweeps. We perform several simulation experiments under various demographic scenarios to demonstrate partialS/HIC's performance, which exhibits excellent resolution for detecting partial sweeps. We also apply our classifier to whole genomes from eight mosquito populations sampled across sub-Saharan Africa by the Anopheles gambiae 1000 Genomes Consortium, elucidating both continent-wide patterns as well as sweeps unique to specific geographic regions. These populations have experienced intense insecticide exposure over the past two decades, and we observe a strong overrepresentation of sweeps at insecticide resistance loci. Our analysis thus provides a list of candidate adaptive loci that may be relevant to mosquito control efforts. More broadly, our supervised machine learning approach introduces a method to distinguish between completed and partial sweeps, as well as between hard and soft sweeps, under a variety of demographic scenarios. As whole-genome data rapidly accumulate for a greater diversity of organisms, partialS/HIC addresses an increasing demand for useful selection scan tools that can track in-progress evolutionary dynamics.

Spatial population genomics of a recent mosquito invasion

Population genomic approaches can characterize dispersal across a single generation through to many generations in the past, bridging the gap between individual movement and intergenerational gene flow. These approaches are particularly useful when investigating dispersal in recently altered systems, where they provide a way of inferring long-distance dispersal between newly established populations and their interactions with existing populations. Human-mediated biological invasions represent such altered systems which can be investigated with appropriate study designs and analyses. Here we apply temporally restricted sampling and a range of population genomic approaches to investigate dispersal in a 2004 invasion of Aedes albopictus (the Asian tiger mosquito) in the Torres Strait Islands (TSI) of Australia. We sampled mosquitoes from 13 TSI villages simultaneously and genotyped 373 mosquitoes at genome-wide single nucleotide polymorphisms (SNPs): 331 from the TSI, 36 from Papua New Guinea (PNG) and four incursive mosquitoes detected in uninvaded regions. Within villages, spatial genetic structure varied substantially but overall displayed isolation by distance and a neighbourhood size of 232-577. Close kin dyads revealed recent movement between islands 31-203 km apart, and deep learning inferences showed incursive Ae. albopictus had travelled to uninvaded regions from both adjacent and nonadjacent islands. Private alleles and a co-ancestry matrix indicated direct gene flow from PNG into nearby islands. Outlier analyses also detected four linked alleles introgressed from PNG, with the alleles surrounding 12 resistance-associated cytochrome P450 genes. By treating dispersal as both an intergenerational process and a set of discrete events, we describe a highly interconnected invasive system.

The origins and spread of domestic horses from the Western Eurasian steppes

Domestication of horses fundamentally transformed long-range mobility and warfare¹. However, modern domesticated breeds do not descend from the earliest domestic horse lineage associated with archaeological evidence of bridling, milking and corralling^2-4 at Botai, Central Asia around 3500 BC³. Other longstanding candidate regions for horse domestication, such as Iberia⁵ and Anatolia⁶, have also recently been challenged. Thus, the genetic, geographic and temporal origins of modern domestic horses have remained unknown. Here we pinpoint the Western Eurasian steppes, especially the lower Volga-Don region, as the homeland of modern domestic horses. Furthermore, we map the population changes accompanying domestication from 273 ancient horse genomes. This reveals that modern domestic horses ultimately replaced almost all other local populations as they expanded rapidly across Eurasia from about 2000 BC, synchronously with equestrian material culture, including Sintashta spoke-wheeled chariots. We find that equestrianism involved strong selection for critical locomotor and behavioural adaptations at the GSDMC and ZFPM1 genes. Our results reject the commonly held association⁷ between horseback riding and the massive expansion of Yamnaya steppe pastoralists into Europe around 3000 BC^8,9 driving the spread of Indo-European languages¹⁰. This contrasts with the scenario in Asia where Indo-Iranian languages, chariots and horses spread together, following the early second millennium BC Sintashta culture^11,12.