AI-Driven Whole-Exome Sequencing: Advancing Variant Interpretation and Precision Medicine
Faisal Aburub, Mayyas Al‐Remawi, Rami A. Abdel‐Rahem, Faisal Al‐Akayleh, Ahmed S.A. Ali Agha
Abstract
Whole-exome sequencing (WES) has revolutionized genomic medicine by enabling high-resolution analyses of the protein-coding regions responsible for numerous genetic diseases. Despite its advantages, processing and interpreting the massive datasets generated by WES remain challenging, particularly given the diversity of genetic variants and the need for clinically actionable insights. Artificial intelligence (AI), which includes machine learning (ML) and deep learning (DL), has emerged as a transformative approach, providing data-driven solutions for variant calling, functional annotation, and pathogenicity modeling. By integrating multi-omics data, clinical records, and large-scale WES outputs, AI-driven methods can pinpoint disease-associated variants, discover novel biomarkers, and guide personalized treatment strategies. This article highlights current AI applications in WES, discusses technical and ethical considerations, and outlines future directions for integrating AI into precision medicine workflows. Ultimately, AI offers the potential to enhance diagnostic accuracy, streamline variant interpretation, and improve patient care in genetic diagnostics.