AI-Driven Nutrigenomic Modeling of Gene–Diet Interactions in Obesity and Insulin Resistance Through Skeletal Muscle Splicing Signatures
Keywords:
nutrigenomics, alternative splicing, artificial intelligence, skeletal muscle, obesity, insulin resistance, gene–diet interactions, system architecture, fairness, governanceAbstract
The rising prevalence of obesity and insulin resistance represents a global health crisis that demands integrative approaches capable of reconciling genetic predisposition with dietary intervention. Recent advances in transcriptomics have revealed that alternative splicing events in skeletal muscle tissue constitute a critical but underexplored layer of gene regulation that mediates metabolic responses to nutritional stimuli. This paper presents a system-level analysis of artificial intelligence-driven nutrigenomic modeling that leverages skeletal muscle splicing signatures to decode gene–diet interactions underlying obesity and insulin resistance. We argue that traditional linear models fail to capture the combinatorial complexity of splicing regulatory networks and the non-linear feedback loops between macronutrient composition, post-transcriptional modification, and metabolic phenotype. Artificial intelligence architectures, particularly deep learning and graph neural networks, offer the capacity to integrate multi-omic data with high-dimensional splicing profiles, while also enabling causal inference through counterfactual reasoning. However, the deployment of such models raises significant structural trade-offs involving robustness, generalizability, interpretability, and computational sustainability. The infrastructure required for federated learning across clinical cohorts introduces governance challenges regarding data sovereignty, algorithmic fairness, and equitable access to precision nutrition. We examine these dimensions through the lens of socio-technical infrastructure, drawing parallels with large-scale genomic data sharing initiatives. A synthesis of recent experimental evidence highlights that exercise and dietary weight loss interventions alter splicing patterns in a manner that is both gene-specific and polymorphism-dependent, further complicating predictive modeling. We conclude by outlining a framework for responsible AI deployment in nutrigenomics that prioritizes transparency, reproducibility, and policy alignment with population health objectives.
References
1. Corella, D., & Ordovas, J. M. (2014). Nutrigenomics in cardiovascular medicine. Circulation: Cardiovascular Genetics, 7(2), 175–185.
2. Nutter, C. A., & Bregman, A. (2018). Alternative splicing of the insulin receptor: Implications for metabolic disease. Trends in Endocrinology & Metabolism, 29(6), 397–408.
3. Zhang, L., & Kwan, T. (2020). Genetic regulation of alternative splicing in human tissues. Nature Reviews Genetics, 21(2), 122–139.
4. Angermueller, C., Pärnamaa, T., Parts, L., & Stegle, O. (2016). Deep learning for computational biology. Molecular Systems Biology, 12(7), 878.
5. Yarkoni, T., & Westfall, J. (2017). Choosing prediction over explanation in psychology: Lessons from machine learning. Perspectives on Psychological Science, 12(6), 1100–1122.
6. Eraslan, G., Avsec, Ž., Gagneur, J., & Theis, F. J. (2019). Deep learning: new computational modelling techniques for genomics. Nature Reviews Genetics, 20(7), 389–403.
7. Keller, M., & Häring, H. U. (2021). Skeletal muscle splicing in response to dietary interventions. Diabetes, 70(Suppl 1), A198.
8. Rampášek, L., & Goldenberg, A. (2020). Variational autoencoders for sparse genomic data. Proceedings of the 2020 ACM Conference on Bioinformatics, Computational Biology, and Health Informatics, 23–32.
9. Wang, W., Liew, W. L., Huang, S., Chan, E., Tan, A. L. M., Tian, C., ... & Liu, B. (2025). Impact of polymorphisms on gene expression and splicing in response to exercise and diet-induced weight loss in human skeletal muscle tissues. Cell Genomics, 5(9).
10. Domínguez-Villanueva, D., & Loza, E. (2022). Robustness vs. generalization in genomic deep learning: A survey. Briefings in Bioinformatics, 23(4), bbac261.
11. Calderón, A. A., & Zaitlen, N. (2018). Hierarchical Bayesian models for precision medicine. Annual Review of Statistics and Its Application, 5, 179–200.
12. Li, T., Sahu, A. K., Talwalkar, A., & Smith, V. (2020). Federated learning: Challenges, methods, and future directions. IEEE Signal Processing Magazine, 37(3), 50–60.
13. Strubell, E., Ganesh, A., & McCallum, A. (2019). Energy and policy considerations for deep learning in NLP. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 3645–3650.
14. Berger, B., & Cho, H. (2020). Survey of data privacy in genomics. Nature Biotechnology, 38(7), 790–799.
15. Martin, A. R., Kanai, M., Kamatani, Y., Okada, Y., Neale, B. M., & Daly, M. J. (2019). Clinical use of current polygenic risk scores may exacerbate health disparities. Nature Genetics, 51(4), 584–591.
16. Vayena, E., & Blasimme, A. (2017). Biomedical big data: New models of control over access, use and governance. Journal of Bioethical Inquiry, 14(4), 543–554.
17. Regev, A., Teichmann, S. A., Lander, E. S., Amit, I., Benoist, C., Birney, E., ... & Yosef, N. (2017). The Human Cell Atlas. eLife, 6, e27041.
18. Pearl, J. (2019). The seven tools of causal inference, with reflections on machine learning. Communications of the ACM, 62(3), 54–60.
19. Bouchard, C., & Ordovas, J. M. (2022). Standardized reporting of exposures and molecular signatures in nutrigenomics. Nutrients, 14(11), 2298.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Computer Science and Engineering Transactions
This work is licensed under a Creative Commons Attribution 4.0 International License.
This article is published under the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
