Artificial Intelligence-Driven Design of Antisense Oligonucleotides for Precision Medicine in Neuromuscular Disorders

Rare neuromuscular disorders impose a significant burden on patients, caregivers, and the health care system. However, effective disease-modifying therapies remain limited. Antisense oligonucleotides (ASOs) have emerged as a promising therapeutic strategy, en-abling targeted modulation of gene expression through mechanisms such as exon skip-ping, exon inclusion, and transcript degradation. Despite the clinical approval of several ASO therapies, their efficacy is often limited by challenges such as poor target tissue up-take and delivery constraints, highlighting the need for improved design strategies. Recent advances in machine learning have led to the development of ASO optimization plat-forms such as eSkipFinder and ASOptimizer, which aim to predict effective ASO se-quences and chemistries for specific RNA targets. While these tools show considerable promise, their broader applicability remains limited due to a lack of comprehensive vali-dation and the absence of integrated safety considerations. Further refinement and valida-tion are necessary to improve their translational utility. Nevertheless, these platforms rep-resent a critical advancement in accelerating ASO development. By improving design pre-cision, reducing reliance on extensive preclinical screening, and allowing researchers with minimal experience in their design to have confidence in the platform’s outputs, machine learning is likely to enhance the accessibility and efficiency of ASO therapy for rare neu-romuscular disorders.