Chromosome-scale inference of hybrid speciation and admixture with convolutional neural networks

Applications of machine learning in phylogenetics

Machine learning has increasingly been applied to a wide range of questions in phylogenetic inference. Supervised machine learning approaches that rely on simulated training data have been used to infer tree topologies and branch lengths, to select substitution models, and to perform downstream inferences of introgression and diversification. Here, we review how researchers have used several promising machine learning approaches to make phylogenetic inferences. Despite the promise of these methods, several barriers prevent supervised machine learning from reaching its full potential in phylogenetics. We discuss these barriers and potential paths forward. In the future, we expect that the application of careful network designs and data encodings will allow supervised machine learning to accommodate the complex processes that continue to confound traditional phylogenetic methods.

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.

Genomic and machine learning-based screening of aquaculture-associated introgression into at-risk wild North American Atlantic salmon (Salmo salar) populations

The negative genetic impacts of gene flow from domestic to wild populations can be dependent on the degree of domestication and exacerbated by the magnitude of pre-existing genetic differences between wild populations and the domestication source. Recent evidence of European ancestry within North American aquaculture Atlantic salmon (Salmo salar) has elevated the potential impact of escaped farmed salmon on often at-risk wild North American salmon populations. Here, we compare the ability of single nucleotide polymorphism (SNP) and microsatellite (SSR) marker panels of different sizes (7-SSR, 100-SSR and 220K-SNP) to detect introgression of European genetic information into North American wild and aquaculture populations. Linear regression comparing admixture predictions for a set of individuals common to the three datasets showed that the 100-SSR panel and 7-SSR panels replicated the full 220K-SNP-based admixture estimates with low accuracy (r² of .64 and .49, respectively). Additional tests explored the effects of individual sample size and marker number, which revealed that ~300 randomly selected SNPs could replicate the 220K-SNP admixture predictions with greater than 95% fidelity. We designed a custom SNP panel (301-SNP) for European admixture detection in future monitoring work and then developed and tested a python package, salmoneuadmix (https://github.com/CNuge/SalmonEuAdmix), which uses a deep neural network to make de novo estimates of individuals' European admixture proportion without the need to conduct complete admixture analysis utilizing baseline samples. The results demonstrate the mobilization of targeted SNP panels and machine learning in support of at-risk species conservation and management.

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.

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.

Reference-free discovery of nuclear SNPs permits accurate, sensitive identification of Carya (hickory) species and hybrids

PREMISE

DNA-based species identification is critical when morphological identification is restricted, but DNA-based identification pipelines typically rely on the ability to compare homologous sequence data across species. Because many clades lack robust genomic resources, we present here a bioinformatics pipeline capable of generating genome-wide single-nucleotide polymorphism (SNP) data while circumventing the need for any reference genome or annotation data.

METHODS

Using the SISRS bioinformatics pipeline, we generated de novo ortholog data for the genus Carya, isolating sites where genetic variation was restricted to a single Carya species (i.e., species-informative SNPs). We leveraged these SNPs to identify both full-species and hybrid Carya specimens, even at very low sequencing depths.

RESULTS

We identified between 46,000 and 476,000 species-identifying SNPs for each of eight diploid Carya species, and all species identifications were concordant with the species of record. For all putative F₁ hybrid specimens, both parental species were correctly identified in all cases, and more punctate patterns of introgression were detectable in more cryptic crosses.

DISCUSSION

Bioinformatics pipelines that use only short-read sequencing data provide vital new tools enabling rapid expansion of DNA identification assays for model and non-model clades alike.

Detecting adaptive introgression in human evolution using convolutional neural networks

Studies in a variety of species have shown evidence for positively selected variants introduced into a population via introgression from another, distantly related population—a process known as adaptive introgression. However, there are few explicit frameworks for jointly modelling introgression and positive selection, in order to detect these variants using genomic sequence data. Here, we develop an approach based on convolutional neural networks (CNNs). CNNs do not require the specification of an analytical model of allele frequency dynamics and have outperformed alternative methods for classification and parameter estimation tasks in various areas of population genetics. Thus, they are potentially well suited to the identification of adaptive introgression. Using simulations, we trained CNNs on genotype matrices derived from genomes sampled from the donor population, the recipient population and a related non-introgressed population, in order to distinguish regions of the genome evolving under adaptive introgression from those evolving neutrally or experiencing selective sweeps. Our CNN architecture exhibits 95% accuracy on simulated data, even when the genomes are unphased, and accuracy decreases only moderately in the presence of heterosis. As a proof of concept, we applied our trained CNNs to human genomic datasets—both phased and unphased—to detect candidates for adaptive introgression that shaped our evolutionary history.