Computational Genomics: The Convergence of AI and CRISPR in Precision Medicine

Abstract

Artificial intelligence (AI) and CRISPR-based genome editing offer complementary approaches to investigating genetic variation and developing targeted interventions in precision medicine. This narrative review examines the principles underlying AI-assisted genomic analysis and programmable genome editing, with particular attention to their potential integration in disease research and therapeutic development. Machine learning and deep learning models can analyse genomic and other molecular datasets, assist in identifying disease-associated variants, and support the prioritisation of candidate therapeutic targets. In CRISPR research, computational methods can inform guide RNA selection, estimate editing efficiency and potential off-target activity, and assist in interpreting functional screening results. Combining these approaches may improve the selection of experimental targets and strengthen investigation of biological mechanisms relevant to inherited disorders, cancer and other complex conditions. The review also discusses AI-assisted clinical decision support, pharmacogenomics, and applications of genome editing in molecular research. However, the reliability of integrated approaches remains dependent on representative training data, transparent computational methods, appropriate experimental validation and safe delivery of editing components. Unintended genomic alterations, variable editing outcomes, model bias, data privacy concerns, ethical issues and regulatory requirements continue to constrain clinical translation. Further progress will require reproducible research, long-term safety assessment and interdisciplinary collaboration. Overall, AI-guided CRISPR research may contribute to the development of more individualised therapeutic strategies, but its clinical value must be established through rigorous validation and responsible implementation.