Kidney stone disease affects millions of people worldwide, with both environmental and genetic factors contributing to individual susceptibility. While Genome-Wide Association Studies (GWAS) have successfully identified numerous single-nucleotide polymorphisms (SNPs) associated with kidney stone risk, translating these findings into accurate and clinically useful prediction tools remains a significant challenge. Polygenic Risk Scores (PRS) provide a framework for quantifying an individual’s genetic predisposition, but traditional PRS approaches often fail to account for complex interactions among variants and the non-linear effects present in genomic data. In this study, we investigate the potential of deep learning techniques, specifically Convolutional Neural Networks (CNNs), to improve PRS models for predicting kidney stone susceptibility. Our approach integrates careful SNP selection, genotype filtering, and CNN-based modeling to address challenges such as data imbalance, genomic noise, and high-dimensional feature spaces. We benchmark our CNN-based framework against conventional machine learning models, including logistic regression, random forests, and support vector machines, demonstrating superior performance in terms of classification accuracy and ROC-AUC. These findings underscore the promise of deep learning-enhanced PRS models to provide more accurate genetic risk predictions for kidney stones. The research highlights the potential of integrating advanced computational approaches with genomics to advance precision medicine, improve patient stratification, and guide preventive strategies for at-risk individuals.
| Published in | Machine Learning Research (Volume 10, Issue 2) |
| DOI | 10.11648/j.mlr.20251002.18 |
| Page(s) | 151-159 |
| Creative Commons |
This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited. |
| Copyright |
Copyright © The Author(s), 2025. Published by Science Publishing Group |
Convolutional Neural Networks, Genome-Wide Association Studies, Polygenic Risk Score
| [1] |
All of us research program.
https://www.researchallofus.org/ , 2025. Accessed: 2025-11-21. |
| [2] | Babak Alipanahi, Andrew Delong, Matthew T Weirauch, and Brendan J Frey. Predicting the sequence specificities of dna-and rna-binding proteins by deep learning. Nature Biotechnology, 33(8): 831-838, 2015. |
| [3] | J. Allen and K. Thompson. Polygenic risk scores: A comprehensive review. Genetic Epidemiology, 41: 169-182, 2017. |
| [4] | A. Badré et al. Improving polygenic risk prediction using deep neural networks: Applicationto breast cancer. PLoS Genetics, 17(4): e1009522, 2021. |
| [5] | E. Brown and F. Green. Genome-wide association studies on kidney stone susceptibility. Human Genetics, 137: 789-800, 2018. |
| [6] | X. Hao, Z. Shao, N. Zhang, et al. Integrative genomewide analyses identify novel loci associated with kidney stones and provide insights into its genetic architecture. Nature Communications, 14: 7498, 2023. |
| [7] | H. He and E. Garcia. Learning from imbalanced data: Techniques and challenges. IEEE Transactions on Knowledge and Data Engineering, 21: 1263-1284, 2009. |
| [8] | A. Johnson and B. Smith. Global prevalence and risk factors for kidney stones. Journal of Nephrology, 35: 102-110, 2020. |
| [9] | Diederik P Kingma and Jimmy Ba. Adam: A method for stochastic optimization. International Conference on Learning Representations, 2015. |
| [10] | Y. LeCun, Y. Bengio, and G. Hinton. Deep learning. Nature, 521:436-444, 2015. |
| [11] | Ryan et al. Poplin. A universal snp and smallindel variant caller using deep neural networks. Nature Biotechnology, 36(10): 983-987, 2018. 16 |
| [12] | C. Smith and D. Lee. Genetic insights into kidney stone formation. Nature Genetics, 47: 456-462, 2015. |
| [13] | Jian Zhou and Olga G Troyanskaya. Predicting effects of noncoding variants with deep learning-based sequence model. Nature Methods, 12(10): 931-934, 2015. |
APA Style
Salem, A., Mondal, A. (2025). A Deep Learning Approach to Polygenic Risk Prediction of Kidney Stone Formation. Machine Learning Research, 10(2), 151-159. https://doi.org/10.11648/j.mlr.20251002.18
ACS Style
Salem, A.; Mondal, A. A Deep Learning Approach to Polygenic Risk Prediction of Kidney Stone Formation. Mach. Learn. Res. 2025, 10(2), 151-159. doi: 10.11648/j.mlr.20251002.18
Share This Article
Twitter
Linked In
Facebook
Copy
Download@article{10.11648/j.mlr.20251002.18,
author = {Amr Salem and Anirban Mondal},
title = {A Deep Learning Approach to Polygenic Risk Prediction of Kidney Stone Formation
},
journal = {Machine Learning Research},
volume = {10},
number = {2},
pages = {151-159},
doi = {10.11648/j.mlr.20251002.18},
url = {https://doi.org/10.11648/j.mlr.20251002.18},
eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.mlr.20251002.18},
abstract = {Kidney stone disease affects millions of people worldwide, with both environmental and genetic factors contributing to individual susceptibility. While Genome-Wide Association Studies (GWAS) have successfully identified numerous single-nucleotide polymorphisms (SNPs) associated with kidney stone risk, translating these findings into accurate and clinically useful prediction tools remains a significant challenge. Polygenic Risk Scores (PRS) provide a framework for quantifying an individual’s genetic predisposition, but traditional PRS approaches often fail to account for complex interactions among variants and the non-linear effects present in genomic data. In this study, we investigate the potential of deep learning techniques, specifically Convolutional Neural Networks (CNNs), to improve PRS models for predicting kidney stone susceptibility. Our approach integrates careful SNP selection, genotype filtering, and CNN-based modeling to address challenges such as data imbalance, genomic noise, and high-dimensional feature spaces. We benchmark our CNN-based framework against conventional machine learning models, including logistic regression, random forests, and support vector machines, demonstrating superior performance in terms of classification accuracy and ROC-AUC. These findings underscore the promise of deep learning-enhanced PRS models to provide more accurate genetic risk predictions for kidney stones. The research highlights the potential of integrating advanced computational approaches with genomics to advance precision medicine, improve patient stratification, and guide preventive strategies for at-risk individuals.
},
year = {2025}
}
TY - JOUR T1 - A Deep Learning Approach to Polygenic Risk Prediction of Kidney Stone Formation AU - Amr Salem AU - Anirban Mondal Y1 - 2025/12/19 PY - 2025 N1 - https://doi.org/10.11648/j.mlr.20251002.18 DO - 10.11648/j.mlr.20251002.18 T2 - Machine Learning Research JF - Machine Learning Research JO - Machine Learning Research SP - 151 EP - 159 PB - Science Publishing Group SN - 2637-5680 UR - https://doi.org/10.11648/j.mlr.20251002.18 AB - Kidney stone disease affects millions of people worldwide, with both environmental and genetic factors contributing to individual susceptibility. While Genome-Wide Association Studies (GWAS) have successfully identified numerous single-nucleotide polymorphisms (SNPs) associated with kidney stone risk, translating these findings into accurate and clinically useful prediction tools remains a significant challenge. Polygenic Risk Scores (PRS) provide a framework for quantifying an individual’s genetic predisposition, but traditional PRS approaches often fail to account for complex interactions among variants and the non-linear effects present in genomic data. In this study, we investigate the potential of deep learning techniques, specifically Convolutional Neural Networks (CNNs), to improve PRS models for predicting kidney stone susceptibility. Our approach integrates careful SNP selection, genotype filtering, and CNN-based modeling to address challenges such as data imbalance, genomic noise, and high-dimensional feature spaces. We benchmark our CNN-based framework against conventional machine learning models, including logistic regression, random forests, and support vector machines, demonstrating superior performance in terms of classification accuracy and ROC-AUC. These findings underscore the promise of deep learning-enhanced PRS models to provide more accurate genetic risk predictions for kidney stones. The research highlights the potential of integrating advanced computational approaches with genomics to advance precision medicine, improve patient stratification, and guide preventive strategies for at-risk individuals. VL - 10 IS - 2 ER -
Department of Mathematics, Applied Mathematics, and Statistics, Case Western Reserve University, Cleveland, USA
Department of Mathematics, Applied Mathematics, and Statistics, Case Western Reserve University, Cleveland, USA
