Whole genome sequencing (WGS) has transformed biomedical research by providing comprehensive genomic information for disease prediction. Traditional genotyping arrays measure only a limited number of variants and therefore provide incomplete genetic risk profiles. Recent advances in artificial intelligence (AI) enable improved modeling of complex relationships among genetic variants. In this study we develop an AI-driven framework for polygenic risk prediction using whole genome sequencing data. Machine learning models including Random Forest and Gradient Boosting are compared with traditional likelihood ratio based genomic risk models. Results demonstrate that AI-based approaches significantly improve predictive performance for complex diseases by capturing nonlinear genetic interactions. The proposed framework highlights the potential of integrating artificial intelligence and genomic sequencing to advance precision medicine
