Integrating Machine Learning into ASO Design

eSkip-Finder Website

Machine learning is revolutionizing the way researchers approach ASO development by providing data-driven insights and predictive models. By combining bioinformatics, computational biology, and molecular genetics, our lab is developing ML-based systems to:

• Optimize safety and efficacy: Advanced models minimize off-target interactions and predict stability, ensuring safer, more effective ASOs.

• Streamline the design process: With ML, we can rapidly evaluate large numbers of ASO candidates, reducing the time from concept to clinical testing.

Current Focus Areas

1. Therapies for Neuromuscular Diseases
   Our lab is developing ASO-based treatments for genetic disorders like DMD and SMA, aiming to restore essential protein functions and improve patient outcomes.

2. Personalized Medicine
   By integrating patient-specific genetic data into machine-learning models, we are working toward highly individualized ASO therapies for rare genetic variants.

3. Scalable and Efficient Development
   Using ML, we are creating scalable frameworks to design ASOs for both common and rare diseases, expanding the therapeutic potential of this technology.

Why Machine Learning Matters

Traditional ASO design relies heavily on trial and error, which can be time-consuming and resource-intensive. By integrating machine learning, the Yokota Lab is transforming this process into a faster, more precise, and more cost-effective system. These advancements are paving the way for a new era of genetic medicine, where therapies are tailored to the unique needs of each patient.

Collaboration and Innovation

Our research combines expertise across disciplines, including genetics, biochemistry, and data science, to push the boundaries of what is possible in genetic therapy. We collaborate with global experts and organizations to accelerate the transition from lab discoveries to real-world applications.

Join Us in Shaping the Future of Genetic Medicine

The Yokota Lab is committed to advancing the frontiers of genetic research to improve lives. By integrating machine learning into ASO therapy development, we aim to provide hope for patients with genetic disorders and their families.

Publications:

Chiba et al. Nucleic Acids Res. 2021 Jul 2;49(W1):W193-W198. eSkip-Finder: a machine learning-based web application and database to identify the optimal sequences of antisense oligonucleotides for exon skipping. doi: 10.1093/nar/gkab442. 

Last updated: 15 January, 2025