Gene editing and gene manipulation have emerged as central strategies in gene therapy for treating a broad spectrum of genetic disorders, ranging from single-gene diseases such as cystic fibrosis, sickle cell Anaemia, and Huntington’s disease to complex, multi-gene conditions including cancer, diabetes, and neurodevelopmental disorders. Advances in genome sequencing and functional genomics have enabled precise identification of disease-causing genes and their associated protein functions. Genome-editing platforms such as CRISPR–Cas systems (Cas9, Cas13, and Cas11) and zinc-finger nucleases have significantly improved the accuracy and efficiency of targeted genetic modifications, thereby expanding the therapeutic potential of gene therapy. The integration of artificial intelligence (AI) with gene therapy has further transformed the field by enabling data-driven design, optimization, and safety assessment of genome-editing strategies. Machine learning and deep learning algorithms can analyze large-scale genomic and proteomic datasets to design optimal guide RNAs, predict off-target effects, and engineer improved Cas variants with enhanced specificity. Advances in deep learning have accelerated protein structure prediction and epigenome editing, while generative AI models allow in silico simulation and optimization of therapeutic strategies prior to experimental validation. These innovations are increasingly being translated into real-world applications, including AI-guided CAR-T cell engineering for cancer immunotherapy and precision crop engineering for agricultural resilience. This review highlights recent advances in AI-enabled gene therapy and genome editing, emphasizing their role in improving precision, safety, and personalized treatment outcomes in human health.
Haroon et al. (Sat,) studied this question.