Biology subjects

Yelmen, B.

Publications and source records attributed to Yelmen, B..

8 recordsLinked to original sources

bioRxiv2026

Detecting CYP2C19 deletions from genotyping array signals using neural networks

Since copy number variations (CNVs) in pharmacogenes can cause significant alterations in drug metabolism, their reliable detection is of high importance both for large-scale studies and personalized medicine. Whole-genome sequencing, and specifically long-read sequencing, is the gold standard for CNV detection. Despite increasing availability of these technologies, genotyping arrays are still widely used as cost-effective alternatives in biobank and clinical settings, yet calling CNVs based on array intensity signals is challenging due to low base pair resolution. In this work, we developed a neural network model, nnCNV, to predict deletions in the CYP2C19 pharmacogene region from array intensity signals. We compared our method to the most widely used algorithm, PennCNV, and demonstrated better performance reaching 100% accuracy in the test dataset. Furthermore, we predicted probe-by-probe CYP2C19 deletion coordinates for all Estonian Biobank samples using nnCNV and PennCNV, and validated these predictions using an identity-by-descent (IBD) sharing method, which also demonstrated superior nnCNV performance. For the deletion samples with conflicting PennCNV and nnCNV predictions, we performed PCR analysis for validation, which showed 97% precision for nnCNV compared to 23% for PennCNV. Finally, we assessed the gradient-based feature importance maps and showed that nnCNV utilizes signal intensity information not only from deletion probes, but also from probes in flanking regions. Our results demonstrate that long-range information, which cannot be utilized by hidden Markov models, can improve CNV calling.

bioinformatics↗

bioRxiv2026

Covariate-aware genomic prediction of blood metabolite profiles using multi-task neural networks

Predictive models of quantitative traits can combine genetic and covariate information, but overall predictive performance alone does not reveal whether differences between models arise from covariate, genetic or joint covariate-genetic effects. Circulating metabolites provide a high-dimensional set of clinically relevant quantitative traits in which these effects can be examined systematically. Although their genetic determinants are well characterised through genome-wide association studies, marginal associations do not establish how accurately metabolomic profiles can be predicted or whether nonlinear models can improve prediction by capturing complex and potentially interactive structure. Here, we developed a multi-task neural network (NN) for simultaneously predicting metabolomic profiles with a three-stage architecture separating covariate, genetic and joint contributions. In comparative analyses, the multi-task NN demonstrated the strongest mean performance across metabolites (R2=0.219), followed by the single-task NN (R2=0.211), elastic net (R2=0.207), and an activation-free multi-task model (R2=0.191). Decomposition analyses indicated that gains were mainly driven by nonlinear covariate modelling, consistent with improved prediction after incorporating nonlinear age effects into a linear model. Together, these analyses provide a framework for identifying sources of predictive differences between different models, which may be applicable to other collections of quantitative traits.

genomics↗

bioRxiv2025

Bias in genome-wide association test statistics due to omitted interactions

Over the past two decades, genome-wide association studies (GWAS) enabled the discovery of thousands of variants associated with many complex human traits. However, conventional GWAS are still widely performed with linear models with the assumption that the genetic effects are predominantly additive. In this work, we investigate the test statistic behavior when linear models are used to obtain significant genotype-phenotype associations without accounting for epistasis. We first algebraically derive mean and variance shift in the null statistic due to the omitted interaction term, and define the boundary between conservative (i.e., deflated statistic tail) and anti-conservative (i.e., inflated statistic tail) regimes for the common GWAS significance threshold. We then perform phenotype simulation analyses using the Estonian Biobank genotypes and validate the mathematical model. We demonstrate that the anti-conservative regime is plausible under realistic parameter settings and models omitting interaction terms can produce spurious significance. Our findings suggest caution when interpreting statistically significant signals reported in the literature based on linear models, especially for large-scale GWAS.

bioinformatics↗

bioRxiv2024

Diffusion-based artificial genomes and their usefulness for local ancestry inference

The creation of synthetic data through generative modeling has emerged as a significant area of research in genomics, offering versatile applications from tailoring functional sequences with specific attributes to generating high-quality, privacy-preserving in silico genomes. Notwithstanding these advancements, a key challenge remains: while some methods exist to evaluate artificially generated genomic data, comprehensive tools to assess its usefulness are still limited. To tackle this issue and present a promising use case, we test artificial genomes within the framework of population genetics and local ancestry inference (LAI). Building on previous work in deep generative modeling for genomics, we introduce a novel, frugal diffusion model and show that it produces high-quality genomic data. We then assess the performance of a downstream machine learning LAI model trained on composite datasets comprising both real and/or synthetic data. Our findings reveal that the LAI model achieves comparable performance when trained exclusively on real data versus high-quality synthetic data. Moreover, we highlight how data augmentation using high-quality artificial genomes significantly benefits the LAI model, particularly when real data is limited. Finally, we compare the conventional use of a single synthetic dataset to a robust ensemble approach, wherein multiple LAI models are trained on diverse synthetic datasets, and their predictions are aggregated. Our study highlights the potential of frugal diffusion-based generative models and synthetic data integration in genomics. This approach could improve fair representation across populations by overcoming data accessibility challenges, while ensuring the reliability of genomic analyses conducted on artificial data.

bioinformatics↗

bioRxiv2024

Latent generative modeling of long genetic sequences with GANs

Synthetic data generation via generative modeling has recently become a prominent research field in genomics, with applications ranging from functional sequence design to high-quality, privacy-preserving artificial in silico genomes. Following a body of work on Artificial Genomes (AGs) created via various generative models trained with raw genomic input, we propose a conceptually different approach to address the issues of scalability and complexity of genomic data generation in very high dimensions. Our method combines dimensionality reduction, achieved by Principal Component Analysis (PCA), and a Generative Adversarial Network (GAN) learning in this reduced space. Using this framework, we generated genomic proxy datasets for very diverse human populations around the world. We compared the quality of AGs generated by our approach with AGs generated by the established models and report improvements in capturing population structure, linkage disequilibrium, and metrics related to privacy leakage. Furthermore, we developed a frugal model with orders of magnitude fewer parameters and comparable performance to larger models. For quality assessment, we also implemented a new evaluation metric based on information theory to measure local haplotypic diversity, showing that generative models yield higher diversity than real genomes. In addition, we addressed the shrinkage issue associated with PCA and generative modeling, examined its relation to the nearest neighbor resemblance metric, and proposed a resolution. Finally, we evaluated the effect of different binarization methods on the quality of the output AGs.

genomics↗

bioRxiv2023

Deep convolutional and conditional neural networks for large-scale genomic data generation

Applications of generative models for genomic data have gained significant momentum in the past few years, with scopes ranging from data characterization to generation of genomic segments and functional sequences. In our previous study, we demonstrated that generative adversarial networks (GANs) and restricted Boltzmann machines (RBMs) can be used to create novel high-quality artificial genomes (AGs) which can preserve the complex characteristics of real genomes such as population structure, linkage disequilibrium and selection signals. However, a major drawback of these models is scalability, since the large feature space of genome-wide data increases computational complexity vastly. To address this issue, we implemented a novel convolutional Wasserstein GAN (WGAN) model along with a novel conditional RBM (CRBM) framework for generating AGs with high SNP number. These networks implicitly learn the varying landscape of haplotypic structure in order to capture complex correlation patterns along the genome and generate a wide diversity of plausible haplotypes. We performed comparative analyses to assess both the quality of these generated haplotypes and the amount of possible privacy leakage from the training data. As the importance of genetic privacy becomes more prevalent, the need for effective privacy protection measures for genomic data increases. We used generative neural networks to create large artificial genome segments which possess many characteristics of real genomes without substantial privacy leakage from the training dataset. In the near future with further improvements in haplotype quality and privacy preservation, large-scale artificial genome databases can be assembled to provide easily accessible surrogates of real databases, allowing researchers to conduct studies with diverse genomic data within a safe ethical framework in terms of donor privacy. Author summaryGenerative modelling has recently become a prominent research field in genomics, with applications ranging from functional sequence design to characterization of population structure. We previously used generative neural networks to create artificial genome segments which possess many characteristics of real genomes but these segments were short in size due to computational requirements. In this work, we present novel generative models for generating artificial genomes with larger sequence size. We test the generated artificial genomes with multiple summary statistics to assess the haplotype quality, overfitting and privacy leakage from the training dataset. Our findings suggest that although there is still room for improvement both in terms of genome quality and privacy preservation, convolutional architectures and conditional generation can be utilised for generating good quality, large-scale genomic data. In the near future with additional improvements, large-scale artificial genomes can be used for assembling surrogate biobanks as alternatives to real biobanks with access restrictions, increasing data accessibility to researchers around the globe.

genomics↗

bioRxiv2020

Revisiting the Out of Africa event with a novel Deep Learning approach

Anatomically modern humans evolved around 300 thousand years ago in Africa1. Modern humans started to appear in the fossil record outside of Africa about 100 thousand years ago though other hominins existed throughout Eurasia much earlier2-4. Recently, several researchers argued in favour of a single out of Africa event for modern humans based on whole-genome sequences analyses5-7. However, the single out of Africa model is in contrast with some of the findings from fossil records, which supports two out of Africa8,9, and uniparental data, which proposes back to Africa movement10,11. Here, we used a novel deep learning approach coupled with Approximate Bayesian Computation and Sequential Monte Carlo to revisit these hypotheses from the whole genome sequence perspective. Our results support the back to Africa model over other alternatives. We estimated that there are two successive splits between Africa and out of African populations happening around 60-80 thousand years ago and separated by 12-13 thousand years. One of the populations resulting from the more recent split has to a large extent replaced the older West African population while the other one has founded the out of Africa populations.

genetics↗

bioRxiv2019

Creating Artificial Human Genomes Using Generative Models

Generative models have shown breakthroughs in a wide spectrum of domains due to recent advancements in machine learning algorithms and increased computational power. Despite these impressive achievements, the ability of generative models to create realistic synthetic data is still under-exploited in genetics and absent from population genetics.\n\nYet a known limitation of this field is the reduced access to many genetic databases due to concerns about violations of individual privacy, although they would provide a rich resource for data mining and integration towards advancing genetic studies. In this study, we demonstrated that deep generative adversarial networks (GANs) and restricted Boltzmann machines (RBMs) can be trained to learn the high dimensional distributions of real genomic datasets and create high quality artificial genomes (AGs) with none to little privacy loss. To illustrate the promising outcomes of our method, we showed that (i) imputation quality for low frequency alleles can be improved by augmenting reference panels with AGs, (ii) scores obtained from selection tests on AGs and real genomes are highly correlated and (iii) AGs can inherit genotype-phenotype associations. AGs have the potential to become valuable assets in genetic studies by providing high quality anonymous substitutes for private databases.

bioinformatics↗