Alexey Kamelin’s research while affiliated with National Research University Higher School of Economics and other places

Background Polygenic risk score (PRS) prediction is widely used to assess the risk of diagnosis and progression of many diseases. Routinely, the weights of individual SNPs are estimated by the linear regression model that assumes independent and linear contribution of each SNP to the phenotype. However, for complex multifactorial diseases such as Alzheimer’s disease, diabetes, cardiovascular disease, cancer, and others, association between individual SNPs and disease could be non-linear due to epistatic interactions. The aim of the presented study is to explore the power of non-linear machine learning algorithms and deep learning models to predict the risk of multifactorial diseases with epistasis. Methods Simulated data with 2- and 3-loci interactions and tested three different models of epistasis: additive, multiplicative and threshold, were generated using the GAMETES. Penetrance tables were generated using PyTOXO package. For machine learning methods we used multilayer perceptron (MLP), convolutional neural network (CNN) and recurrent neural network (RNN), Lasso regression, random forest and gradient boosting models. Performance of machine learning models were assessed using accuracy, AUC-ROC, AUC-PR, recall, precision, and F1 score. Results First, we tested ensemble tree methods and deep learning neural networks against LASSO linear regression model on simulated data with different types and strength of epistasis. The results showed that with the increase of strength of epistasis effect, non-linear models significantly outperform linear. Then the higher performance of non-linear models over linear was confirmed on real genetic data for multifactorial phenotypes such as obesity, type 1 diabetes, and psoriasis. From non-linear models, gradient boosting appeared to be the best model in obesity and psoriasis while deep learning methods significantly outperform linear approaches in type 1 diabetes. Conclusion Overall, our study underscores the efficacy of non-linear models and deep learning approaches in more accurately accounting for the effects of epistasis in simulations with specific configurations and in the context of certain diseases.

Background COVID-19 disease has infected more than 772 million people, leading to 7 million deaths. Although the severe course of COVID-19 can be prevented using appropriate treatments, effective interventions require a thorough research of the genetic factors involved in its pathogenesis. Methods We conducted a genome-wide association study (GWAS) on 7,124 individuals (comprising 6,400 controls who had mild to moderate COVID-19 and 724 cases with severe COVID-19). The inclusion criteria were acute respiratory distress syndrome (ARDS), acute respiratory failure (ARF) requiring respiratory support, or CT scans indicative of severe COVID-19 infection without any competing diseases. We also developed a polygenic risk score (PRS) model to identify individuals at high risk. Results We identified two genome-wide significant loci (P-value <5 × 10⁻⁸) and one locus with approximately genome-wide significance (P-value = 5.92 × 10⁻⁸-6.15 × 10⁻⁸). The most genome-wide significant variants were located in the leucine zipper transcription factor like 1 (LZTFL1) gene, which has been highlighted in several previous GWAS studies. Our PRS model results indicated that individuals in the top 10% group of the PRS had twice the risk of severe course of the disease compared to those at median risk [odds ratio = 2.18 (1.66, 2.86), P-value = 8.9 × 10⁻⁹]. Conclusion We conducted one of the largest studies to date on the genetics of severe COVID-19 in an Eastern European cohort. Our results are consistent with previous research and will guide further epidemiologic studies on host genetics, as well as for the development of targeted treatments.

Background Polygenic risk score (PRS) prediction is widely used to assess the risk of diagnosis and progression of many diseases. Routinely, the weights of individual SNPs are estimated by the linear regression model that assumes independent and linear contribution of each SNP to the phenotype. However, for complex multifactorial diseases such as Alzheimer's disease, diabetes, cardiovascular disease, cancer, and others, association between individual SNPs and disease could be non-linear due to epistatic interactions. The aim of the presented study is to explore the power of non-linear machine learning algorithms and deep learning models to predict the risk of multifactorial diseases with epistasis. Results First, we tested ensemble tree methods and deep learning neural networks against LASSO linear regression model on simulated data with different types and strength of epistasis. The results showed that with the increase of strength of epistasis effect, non-linear models significantly outperform linear. Then the higher performance of non-linear models over linear was confirmed on real genetic data for multifactorial phenotypes such as obesity, type 1 diabetes, and psoriasis. From non-linear models, gradient boosting appeared to be the best model in obesity and psoriasis while deep learning methods significantly outperform linear approaches in type 1 diabetes. Conclusions Overall, our study underscores the efficacy of non-linear models and deep learning approaches in more accurately accounting for the effects of epistasis in simulations with specific configurations and in the context of certain diseases.