Biology subjects

Ioannidis, A. G.

Publications and source records attributed to Ioannidis, A. G..

At least 19 recordsLinked to original sources

bioRxiv2026

Graph transformer for ancient ancestry inference

Local ancestry inference classifies segments of DNA in admixed individuals by their originating population. However, as the date of admixture becomes older, these segments become shorter and determining their ancestry becomes increasingly difficult. This limits many existing segment-based methods to relatively recent historical admixture events and more highly diverged populations. The rapidly expanding availability of ancient DNA offers a promising opportunity to use these ancient samples as references for local ancestry inference. A recent approach integrates ancient samples into the ancestral recombination graph (ARG) for local ancestry inference. Here, we introduce recent advances in deep learning for graphs into this ARG framework to create ARGMix, a graph transformer that infers local ancestry using the coalescent trees of the inferred ARG. Our approach employs ancient samples as references in the marginal trees to predict local ancestry. We train ARGMix on data reflecting the well-understood ancient European demography and demonstrate improved accuracy and robustness even under demographic misspecification. We then apply ARGMix to an ARG of ancient and present-day European samples for ancestry-specific analyses, finding evidence of continuity between Otzi the Iceman and present-day individuals from nearby regions.

genetics↗

bioRxiv2026

The diploid reference genome of a human embryonic stem cell line

Advances in DNA sequencing and assembly technologies are spurring a shift from haploid reference genomes to sample-specific diploid assemblies. Here, we generated the first telomere-to-telomere (T2T) diploid reference for the widely used human embryonic stem cell (hESC) line, H9 (WAe009-A). This haplotype-resolved assembly is highly accurate with comprehensive annotation of genes, segmental duplications, methylation, and chromatin conformation. Pangenomic and phased-locus inference point to H9s mixed ancestry with a predominant European component. H9-specific genomic features include near-perfect telomeres [~]1.65-fold longer than other T2T assemblies, consistent with telomerase activity during pluripotency; chromosome 17 inversions that can predispose offspring to neurological syndromes; and expansions of ncRNA clusters, with overall genomic stability maintained despite extensive culturing. Mapping multi-omic datasets to the genome, we demonstrate the power of this resource for allele-specific, high-precision transcriptomic, genetic, and epigenetic analyses, with far-reaching implications for human development and disease.

genomics↗

bioRxiv2026

Point cloud local ancestry inference (PCLAI): continuous coordinate-based ancestry along the genome

Local ancestry inference (LAI) predicts a discrete ancestry label for each segment of an individuals genome and has become integral to studying population history, genetic variation, and polygenic trait association. We present a new local ancestry paradigm that eschews discrete categorical labels and instead performs inference in a continuous coordinate space. We call this method "point cloud local ancestry inference" (PCLAI), since it represents an individuals genetic ancestry as a point cloud with each point corresponding to a small haplotypic segment in their genome. This formulation works in any co-ordinate space (for instance, geographic or principal components) permitting the representation of continuous genetic variation at the haplotypic-segment level without resorting to artificially constructed discrete labels. We illustrate PCLAI by training on ancient samples from multiple time periods separately, yielding chromosome paintings based on geography that are time-stratified and provide insight into how individuals genomic segments moved across space and time.

genomics↗

bioRxiv2026

Sex Checking by Zygosity Distributions

MotivationIn genomic and clinical studies, verifying concordance between self-reported and genotype-inferred sex is a crucial quality control step, since mismatches arising from mislabeling or aneuploidies can bias downstream analyses and affect diagnostic accuracy. Existing approaches typically require substantial auxiliary data, and often require manual threshold tuning. There remains a need for a streamlined, reference-free method that generalizes across different data modalities--including whole-genome, single-sample and array--without requiring additional files or parameter tuning. ResultsWe present Zigo, a novel ML-based sex-checking method that operates solely on a standard VCF file, designed using X-chromosome genotype class distributions across sexes. Our model was trained on synthetic data incorporating standard demographic models and empirical recombination maps to ensure realistic genetic architecture and population structure. We simulate WGS, array, and single-sample files for broad applicability. Unlike traditional methods, we eliminate manual thresholding by distilling learned discriminative patterns into a single polynomial equation that determines genetic sex directly from normalized genotype counts. We validated Zigo on independent datasets, including 1000 Genomes, UK Biobank, and HGDP. Additional experiments assessed robustness under reduced variant availability through random SNP subsampling and allele-frequency filtering. Across all evaluations, the model achieved state-of-the-art accuracy, high time efficiency, and strong generalization, even with severely limited variant sets. AvailabilityWe release our sex-checking tool as an open-source command-line interface (CLI) under GitHub at https://github.com/AI-sandbox/zigo. Supplementary informationSupplementary data are available in the Supplementary Material at the end of this article.

bioinformatics↗

bioRxiv2026

Biobank-Scale Polygenic Prediction in Admixed Populations Using Local Ancestry via the Group Lasso

Polygenic risk models trained in one ancestry often fail to perform well in others, in part due to linkage disequilibrium and allele frequency differences across ancestries. In response, separate models trained for specific ancestries have been introduced. However, this single ancestry approach is untenable in admixed groups, which have ancestry from multiple sources varying across the genome and between individuals. Here we present Combine, a biobank-scale sparse regression framework that augments per-variant genotype features with local ancestry dosages and fits all effects jointly using a variant-level group lasso penalty. In 99,298 admixed participants from the All of Us Research Program, Combine substantially outper-forms state-of-the-art multi-ancestry summary-statistic approaches (e.g., 144% relative improvement over PRS-CSx for white blood cell count). Furthermore, it matches or improves upon the predictive performance of highly optimized individual-level models (iPGS/snpnet) across seven of nine evaluated phenotypes, while uniquely providing locus-level interpretability to disentangle shared allelic effects from ancestry-linked tagging. An ancestry-specific extension, Combine-S, estimates haplotypic ancestry-associated SNP effects together with local-ancestry terms, enabling systematic identification of ancestry-dependent effect magnitudes and sign differences at established and plausible loci. Finally, we show that incorporating external GWAS evidence through group-specific penalty weights improves LDL cholesterol prediction without pre-filtering variants. Together, Combine provides a scalable framework for polygenic modeling that prioritizes efficient local ancestry-aware modeling and interpretation in admixed biobanks.

genomics↗

bioRxiv2026

snputils: A High-Performance Python Library for Genetic Variation and Population Structure

The increasing size and resolution of genomic and population genetic datasets offer unprecedented opportunities to study population structure and uncover the genetic basis of complex traits and diseases. The collection of existing analytical tools, however, is characterized by format incompatibilities, limited functionality, and computational inefficiencies, forcing researchers to construct fragile pipelines that chain together fragmented command-line utilities and ad hoc scripts. These are difficult to maintain, scale, and reproduce. To address such limitations, we present snputils, a Python library that unifies high-performance I/O, transformation, and analysis of genotype, ancestry, and phenotypic information within a single framework suitable for biobank-scale research. The library provides efficient tools for essential operations, including querying, cleaning, merging, and statistical analysis. In addition, it offers classical population genetic statistics with optional ancestry-specific masking. An identity-by-descent module supports reading of multiple formats, filtering and ancestry-restricted segment trimming for relatedness and demographic inference. snputils also incorporates ancestry-masking and multi-array functionalities for dimensionality reduction methods, as well as efficient implementations of admixture simulation, admixture mapping, and advanced visualization capabilities. With support for the most commonly used file formats, snputils integrates smoothly with existing tools and clinical databases. At the same time, its modular and optimized design reduces technical overhead, facilitating reproducible workflows that accelerate discoveries in population genetics, genomic research, and precision medicine. Benchmarking demonstrates a significant reduction in genotype data loading speed compared to existing Python libraries. The open-source library is available at https://github.com/AI-sandbox/snputils, with full documentation and tutorials at snputils.org.

bioinformatics↗

bioRxiv2026

ARGformer: learning on ancestral recombination graphs with transformers

Recent advances in inference of the ancestral recombination graph (ARG), which describes how segments of chromosomes trace back through recombination and shared lineages, have made it possible to reconstruct genome-wide genealogies for large cohorts, but it remains difficult to summarize and use this information for population genetic analyses. We present ARGformer, an encoder-only transformer that learns context-dependent embeddings with a self-supervised masked objective finetuned with contrastive learning for downstream retrieval tasks. We train ARGformer on genealogies from coalescent simulations and on genealogies inferred from ancient and present-day Homo sapiens genomes. Using only these learned embeddings, without access to genotype matrices, ARGformer captures patterns of global population structure and supports ancestry inference through clustering and nearest-neighbor retrieval. On genealogies that include archaic hominins, ARGformer can highlight Denisovan-derived segments in Oceanian genomes and reveals Oceanian-like ancestry in South American Indigenous populations. ARGformer is available at https://github.com/AI-sandbox/ARGformer.

genomics↗

bioRxiv2026

ADAMIXTURE: Adaptive First-Order Optimization for Biobank-Scale Genetic Clustering

MotivationEstimating genetic clusters from sequencing data is a fundamental task in population and medical genetics, enabling demographic inference and adjustment for population structure in association studies. ADMIXTURE, a widely used model-based clustering method, employs an accelerated Expectation-Maximization (EM) algorithm to infer population parameters; however, its computational demands scale poorly, limiting its usefulness for modern biobank-sized datasets. While recent EM acceleration strategies employing second-order quasi-Newton schemes preserve accuracy, they remain computationally intensive. Conversely, EM-free approaches that prioritize speed often compromise solution quality. ResultsWe introduce ADAMIXTURE, a novel optimization framework that integrates the EM algorithm with Adaptive Moment Estimation (Adam). Unlike traditional acceleration methods, ADAMIXTURE utilizes first-order gradients with adaptive learning rates derived from raw and squared moments to approximate curvature information, bypassing the computational overhead of Hessian approximations. This approach surpasses the convergence efficiency of second-order methods while maintaining the low computational complexity of first-order updates. Across simulated and large-scale empirical datasets, ADAMIXTURE demonstrates substantial reductions in wall-clock runtime and enhanced scalability compared to state-of-the-art methods, while maintaining comparable or improved inference accuracy. Its GPU implementation runs in under 2 hours on half a million samples and variants, a two order of magnitude speedup over current state-of-the-art. Availability and implementationSource code is available at: https://github.com/AI-sandbox/ADAMIXTURE. Contactioannidis@stanford.edu

bioinformatics↗

bioRxiv2025

Pan-African metapopulation model explains Homo sapiens genetic and morphological evolution

A growing body of evidence has challenged the traditional assumption of a single-region origin for Homo sapiens, suggesting instead that our species originated from multiple geographically distinct populations in Africa, which intermittently exchanged genes and culture. However, our understanding of how this Pan-African metapopulation would have evolved through time is still limited. Furthermore, the drivers of such changes are uncertain, and quantitative models of the respective contributions of different African regions are lacking. Here we provide a complete reconstruction of the meta-population dynamics over the last 200,000 years by quantitatively integrating an ecological niche model, informed by archaeological sites, within a spatially explicit population genetic framework. The inferred metapopulation dynamics account for the divergence among all available contemporary and ancient genomes of African hunter-gatherers used to calibrate the model. In addition, it also accurately predicts the patterns of craniometric diversification across the continent from the Late Middle Pleistocene to the present. Finally, we show how the climate-driven changes in population sizes and connectivity are congruent with major patterns of archaeological and phenotypic diversification over the last 200,000 years across the African continent.

evolutionary biology↗

bioRxiv2023

Machine Learning Strategies for Improved Phenotype Prediction in Underrepresented Populations

Precision medicine models often perform better for populations of European ancestry due to the over-representation of this group in the genomic datasets and large-scale biobanks from which the models are constructed. As a result, prediction models may misrepresent or provide less accurate treatment recommendations for underrepresented populations, contributing to health disparities. This study introduces an adaptable machine learning toolkit that integrates multiple existing methodologies and novel techniques to enhance the prediction accuracy for underrepresented populations in genomic datasets. By leveraging machine learning techniques, including gradient boosting and automated methods, coupled with novel population-conditional re-sampling techniques, our method significantly improves the phenotypic prediction from single nucleotide polymorphism (SNP) data for diverse populations. We evaluate our approach using the UK Biobank, which is composed primarily of British individuals with European ancestry, and a minority representation of groups with Asian and African ancestry. Performance metrics demonstrate substantial improvements in phenotype prediction for underrepresented groups, achieving prediction accuracy comparable to that of the majority group. This approach represents a significant step towards improving prediction accuracy amidst current dataset diversity challenges. By integrating a tailored pipeline, our approach fosters more equitable validity and utility of statistical genetics methods, paving the way for more inclusive models and outcomes.

bioinformatics↗

bioRxiv2023

PopGenAdapt: Semi-Supervised Domain Adaptation for Genotype-to-Phenotype Prediction in Underrepresented Populations

The lack of diversity in genomic datasets, currently skewed towards individuals of European ancestry, presents a challenge in developing inclusive biomedical models. The scarcity of such data is particularly evident in labeled datasets that include genomic data linked to electronic health records. To address this gap, this paper presents PopGenAdapt, a genotype-to-phenotype prediction model which adopts semi-supervised domain adaptation (SSDA) techniques originally proposed for computer vision. PopGenAdapt is designed to leverage the substantial labeled data available from individuals of European ancestry, as well as the limited labeled and the larger amount of unlabeled data from currently underrepresented populations. The method is evaluated in underrepresented populations from Nigeria, Sri Lanka, and Hawaii for the prediction of several disease outcomes. The results suggest a significant improvement in the performance of genotype-to-phenotype models for these populations over state-of-the-art supervised learning methods, setting SSDA as a promising strategy for creating more inclusive machine learning models in biomedical research. Our code is available at https://github.com/AI-sandbox/PopGenAdapt.

bioinformatics↗

bioRxiv2023

Deep Variational Autoencoders for Population Genetics

MotivationModern biobanks provide numerous high-resolution genomic sequences of diverse populations. These datasets enable a better understanding of genotype-phenotype interactions with genome-wide association studies (GWAS) and power a new personalized precision medicine with polygenic risk scores (PRS). In order to account for diverse and admixed populations, new algorithmic tools are needed in order to properly capture the genetic composition of populations. Here we explore deep learning techniques, namely variational autoencoders (VAEs), to process genomic data from a population perspective. We hope this work will encourage the adoption of deep neural networks in the population genetics community. ResultsIn this paper, we show the power of VAEs for a variety of tasks relating to the interpretation, classification, simulation, and compression of genomic data with several worldwide whole genome datasets from both humans and canids and evaluate the performance of the proposed applications with and without ancestry conditioning. The unsupervised setting of autoencoders allows for the detection and learning of granular population structure and inferring of informative latent factors. The learned latent spaces of VAEs are able to capture and represent differentiated Gaussian-like clusters of samples with similar genetic composition on a fine-scale from single nucleotide polymorphisms (SNPs), enabling applications in dimensionality reduction, data simulation, and imputation. These individual genotype sequences can then be decomposed into latent representations and reconstruction errors (residuals) which provide a sparse representation useful for lossless compression. We show that different population groups have differentiated compression ratios and classification accuracies. Additionally, we analyze the entropy of the SNP data, its effect on compression across populations, its relation to historical migrations, and we show how to introduce autoencoders into existing compression pipelines.

bioinformatics↗

bioRxiv2022

Adversarial Attacks on Genotype Sequences

Adversarial attacks can drastically change the output of a method by performing a small change on its input. While they can be a useful framework to analyze worst-case robustness, they can also be used by malicious agents to perform damage in machine learning-based applications. The proliferation of platforms that allow users to share their DNA sequences and phenotype information to enable association studies has led to an increase in large databases. Such open platforms are, however, vulnerable to malicious users uploading corrupted genetic sequence files that could damage downstream studies. Such studies commonly include steps involving the analysis of the genomic sequences structure using dimensionality reduction techniques and ancestry inference methods. In this paper we show how white-box gradient-based adversarial attacks can be used to corrupt the output of genomic analyses, and we explore different machine learning techniques to detect such manipulations.

bioinformatics↗

bioRxiv2022

Nationwide genomic biobank in Mexico unravels demographic history and complex trait architecture from 6,057 individuals

Latin America continues to be severely underrepresented in genomics research, and fine-scale genetic histories as well as complex trait architectures remain hidden due to the lack of Big Data. To fill this gap, the Mexican Biobank project genotyped 1.8 million markers in 6,057 individuals from 32 states and 898 sampling localities across Mexico with linked complex trait and disease information creating a valuable nationwide genotype-phenotype database. Through a suite of state-of-the-art methods for ancestry deconvolution and inference of identity-by-descent (IBD) segments, we inferred detailed ancestral histories for the last 200 generations in different Mesoamerican regions, unraveling native and colonial/post-colonial demographic dynamics. We observed large variations in runs of homozygosity (ROH) among genomic regions with different ancestral origins reflecting their demographic histories, which also affect the distribution of rare deleterious variants across Mexico. We analyzed a range of biomedical complex traits and identified significant genetic and environmental factors explaining their variation, such as ROH found to be significant predictors for trait variation in BMI and triglycerides.

genomics↗

bioRxiv2022

Predicting Dog Phenotypes from Genotypes

We analyze dog genotypes (i.e., positions of dog DNA sequences that often vary between different dogs) in order to predict the corresponding phenotypes (i.e., unique observed characteristics). More specifically, given chromosome data from a dog, we aim to predict the breed, height, and weight. We explore a variety of linear and non-linear classification and regression techniques to accomplish these three tasks. We also investigate the use of a neural network (both in linear and non-linear modes) for breed classification and compare the performance to traditional statistical methods. We show that linear methods generally outperform or match the performance of non-linear methods for breed classification. However, we show that the reverse is true for height and weight regression. Finally, we evaluate the results of all of these methods based on the number of input features used in the analysis. We conduct experiments using different fractions of the full genomic sequences, resulting in input sequences ranging from 20 SNPs to [~]200k SNPs. In doing so, we explore the impact of using a very limited number of SNPs for prediction. Our experiments demonstrate that these phenotypes in dogs can be predicted with as few as 0.5% of randomly selected SNPs (i.e., 992 SNPs) and that dog breeds can be classified with 50% balanced accuracy with as few as 0.02% SNPs (i.e., 40 SNPs).

genomics↗

bioRxiv2022

Generative Moment Matching Networks for Genotype Simulation

The generation of synthetic genomic sequences using neural networks has potential to ameliorate privacy and data sharing concerns and to mitigate potential bias within datasets due to under-representation of some population groups. However, there is not a consensus on which architectures, training procedures, and evaluation metrics should be used when simulating single nucleotide polymorphism (SNP) sequences with neural networks. In this paper, we explore the use of Generative Moment Matching Networks (GMMNs) for SNP simulation, we present some architectural and procedural changes to properly train the networks, and we introduce an evaluation scheme to qualitatively and quantitatively assess the quality of the simulated sequences.

bioinformatics↗

bioRxiv2022

Hyperbolic Geometry-Based Deep Learning Methods to Produce Population Trees from Genotype Data

The production of population-level trees using the genomic data of individuals is a fundamental task in the field of population genetics. Typically, these trees are produced using methods like hierarchical clustering, neighbor joining, or maximum likelihood. However, such methods are non-parametric: they require all data to be present at the time of tree formation, and the addition of new data points necessitates the regeneration of the entire tree, a potentially expensive process. They also do not easily integrate with larger workflows. In this study, we aim to address these problems by introducing parametric deep learning methods for tree formation from genotype data. Our models specifically create continuous representations of population trees in hyperbolic space, which has previously proven highly effective in embedding hierarchically structured data. We present two different architectures - a multi-layer perceptron (MLP) and a variational autoencoder (VAE) - and we analyze their performance using a variety of metrics along with comparisons to established tree-building methods. Both models tested produce embedding spaces that reflect human evolutionary history. In addition, we demonstrate the generalizability of these models by verifying that addition of new samples to an existing tree occurs in a semantically meaningful manner. Finally, we use Dasguptas Cost to compare the quality of trees generated by our models to those produced by established methods. Despite the fact that the benchmark methods are directly fit on the evaluation data, our models are able to outperform some of these and achieve highly comparable performance overall. Author summaryTree production is a vital task in population genetics, but current approaches fall prey to several common shortfalls. Most notably, they lack the ability to add new data points after tree generation, and they are often difficult to use in larger pipelines. By leveraging cutting-edge advances pairing deep learning with hyperbolic geometry, we develop multiple models designed to rectify these issues. Through experiments on a dataset of humans from globally widespread ancestries, we demonstrate the generalizability of our models to new data, and we also show strong empirical performance with respect to currently used methods. In addition, we show that the data representations produced by our models are semantically meaningful and reflect known facts about human evolutionary history. Finally, we discuss the additional benefits our models could provide, including improved visualization, greater privacy preservation, and improved integration with downstream machine learning tasks. In conclusion, we present models that are accurate, flexible, and generalizable, with the potential to facilitate a variety of further applications.

evolutionary biology↗

bioRxiv2021

Archetypal Analysis for Population Genetics

The estimation of genetic clusters using genomic data has application from genome-wide association studies (GWAS) to demographic history to polygenic risk scores (PRS) and is expected to play an important role in the analyses of increasingly diverse, large-scale cohorts. However, existing methods are computationally-intensive, prohibitively so in the case of nationwide biobanks. Here we explore Archetypal Analysis as an efficient, unsupervised approach for identifying genetic clusters and for associating individuals with them. Such unsupervised approaches help avoid conflating socially constructed ethnic labels with genetic clusters by eliminating the need for exogenous training labels. We show that Archetypal Analysis yields similar cluster structure to existing unsupervised methods such as ADMIXTURE and provides interpretative advantages. More importantly, we show that since Archetypal Analysis can be used with lower-dimensional representations of genetic data, significant reductions in computational time and memory requirements are possible. When Archetypal Analysis is run in this fashion, it takes several orders of magnitude less compute time than the current standard, ADMIXTURE. Finally, we demonstrate uses ranging across datasets from humans to canids. Author summaryThis work introduces a method that combines the singular value decomposition (SVD) with Archetypal Analysis to perform fast and accurate genetic clustering by first reducing the dimensionality of the space of genomic sequences. Each sequence is described as a convex combination (admixture) of archetypes (cluster representatives) in the reduced dimensional space. We compare this interpretable approach to the widely used genetic clustering algorithm, ADMIXTURE, and show that, without significant degradation in performance, Archetypal Analysis outperforms, offering shorter run times and representational advantages. We include theoretical, qualitative, and quantitative comparisons between both methods.

bioinformatics↗