Integrating Machine Learning-Based Approaches into the Design of ASO Therapies

Rare diseases impose a significant burden on affected individuals, caregivers, and healthcare systems worldwide. Developing effective therapeutics for these small patient populations presents substantial challenges. Antisense oligonucleotides (ASOs) have emerged as a promising therapeutic approach that targets the underlying genetic cause of disease at the RNA level. Several ASOs have gained FDA approval for the treatment of genetic conditions, including use in personalized N-of-1 trials. However, despite their potential, ASOs often exhibit limited clinical efficacy, and optimizing their design is a complex process influenced by numerous factors. Machine learning-based platforms, including eSkip-Finder and ASOp-timizer, have been developed to address these challenges by predicting optimal ASO sequences and chemical modifications to enhance efficacy. eSkip-Finder focuses on exon-skipping applications, while ASOptimizer aims to optimize ASOs for RNA degradation. Preliminary in vitro results have demon-strated the promising predictive power of these platforms. However, limitations remain, including their generalizability to alternative targets and gaps in their consideration of all factors influencing ASO efficacy and safety. Continued advancements in machine learning models, alongside efforts to incorporate ad-ditional features affecting ASO efficacy and safety, hold significant promise for the field. These platforms have the potential to streamline ASO development, reduce associated costs, and improve clinical out-comes, positioning machine learning as a key tool in the future of ASO therapeutics.