Abstract:
Neurofibromatosis (NF) is a genetic disorder characterized by mutations in the NF1 and NF2 genes, leading to tumor formation, nerve damage, and significant patient morbidity. Despite advances in targeted therapies, treatment responses remain highly variable, and there is a lack of predictive tools to determine which patients will benefit from specific interventions. This study presents a novel AI-powered precision medicine framework that integrates machine learning for NF1/NF2 mutation classification and deep-learning-optimized CRISPR guide RNA selection for gene therapy. Genomic data was sourced from ClinVar, HGMD, and the Leiden Open Variation Database (LOVD), with additional pathogenicity scores obtained from REVEL and PolyPhen-2. The machine learning model achieved 93% accuracy in classifying NF1/NF2 mutations and 92% precision in predicting disease severity. The AI-driven CRISPR guide RNA optimization framework demonstrated a 98% target specificity rate and a 72% reduction in off-target effects. A web-based deployment system was created using Streamlit, allowing real-time genomic analysis, mutation classification, and automated CRISPR guide RNA recommendations. These findings underscore the potential for AI-driven approaches to advance precision medicine and provide a scalable solution for neurofibromatosis treatment.
