Genome & Epigenome
Multi-Omic Analyses
Holistic analysis of multi-layer biological data from genes to proteins.
Health is not limited solely to your DNA sequences. Understanding how genes function and how your cells behave is critical for predicting complex disease risk.
Multi-Omic analysis lets us holistically examine different biological data layers from genetics to proteins.
Biological Data Layers
- Genomics (WGS/SNP Array): Hereditary changes and variants; foundation for PRS.
- Epigenomics (Methylation Microarray): Methylation changes; used for gene regulation insights and epigenetic age.
- Clinical & Lifestyle Data: Biomarkers (lipids, glucose, CRP), demographics, lifestyle factors modeled with genetic risk.
Integration Architecture
- Data Harmonization & Feature Engineering: Consistency across datasets; multiple imputation (MICE KNN); proper encoding/normalization.
- Integration with Machine Learning: All omic and clinical data feed AI models to predict 10–20 year disease risk at the individual level.
References
- Steinfeldt, J. et al. (2022). Neural network-based integration of polygenic and clinical information... The Lancet Digital Health, 4(2), e84-e94.