Martin Kelemen

Performance of deep-learning based approaches to improve polygenic scores

This study evaluates deep-learning methods for improving polygenic scores, finding limited benefits due to confounding effects from linkage disequilibrium.

Deep learning for polygenic prediction: The role of heritability, interaction type and sample size

This study evaluates deep learning methods for polygenic prediction, showing that MLP benefits most from larger sample sizes and one-hot encoding improves performance across methods.

Evaluating the cost-effectiveness of polygenic risk score-stratified screening for abdominal aortic aneurysm

This study evaluates the cost-effectiveness of polygenic risk score-stratified screening for abdominal aortic aneurysm compared to current strategies.

ShaPRS: Leveraging shared genetic effects across traits or ancestries improves accuracy of polygenic scores

ShaPRS improves polygenic score accuracy by leveraging shared genetic effects across traits or ancestries, enhancing performance for complex diseases and across populations.

RapidoPGS: A rapid polygenic score calculator for summary GWAS data without a test dataset

RapidoPGS computes polygenic scores using only summary GWAS data without needing test datasets, achieving faster performance than some existing methods.

Common genetic variants contribute to risk of rare severe neurodevelopmental disorders

The paper shows that common genetic variants contribute to risk and clinical variation in severe neurodevelopmental disorders, even in individuals with known monogenic diagnoses.