Integrating somatic and germline variation for the prediction of chronic kidney disease

This research project aims to develop a comprehensive prediction model for Chronic Kidney Disease (CKD), addressing the limitations of current models that struggle to fully capture individual risk. CKD affects roughly 10% of adults and can progress unpredictably, making early identification and personalized management a critical challenge in nephrology.

Our approach integrates inherited (germline) and acquired (somatic) genetic information with established clinical, demographic, and pharmacological risk factors to create a unified, predictive framework. Leveraging the innovative blended genome-exome (BGE) technology, we analyze DNA samples from participants in the Swiss HIV Cohort Study (SHCS) alongside large-scale data from the UK Biobank. This combination allows for the development of a statistically robust and generalizable model that can quantify individual CKD risk and forecast disease progression more accurately than existing methods. 

The project’s significance lies in its potential to transform CKD management. By providing precise, personalized risk assessments, the model could guide early interventions, improve patient outcomes, and support more targeted treatment strategies. Beyond nephrology, the methods and insights generated may serve as a blueprint for similar predictive models in other complex diseases, demonstrating the power of integrating genetic and clinical data.