Challenges and opportunities of machine-guided capsid engineering for gene therapyPublished: May 20, 2019
Vector Characterization & Validation
Eric D Kelsic & George M Church
Advances in DNA delivery will be crucial to the enablement of new gene therapies. Pioneering efforts in developing recombinant Adeno-Associated Virus (AAV) technology for gene delivery have led to a recent wave of treatments for genetic diseases with great unmet need. Most current therapies use the capsids of AAV isolated from Adenovirus stocks and primary human and primate tissues, that were then discovered to have favorable tropism, immunogenicity and manufacturability properties. However, despite much work invested in the engineering of new capsids for enhanced delivery, many delivery targets remain out of reach. In our view, high-throughput capsid engineering could be done more effectively by combining three advanced technologies in a closed-loop manner: i. next-gen library synthesis, ii. next-gen sequencing, and iii. machine learning. This approach enables a machine-guided data-driven workflow in which the search for improved capsids is dramatically accelerated relative to traditional open-loop methods. In this report, we review the technological advances that are pushing the field of AAV capsid engineering toward machine-guided methods, describe and explore the promise of this new approach, and discuss anticipated challenges. In the near future, machine-guided approaches will revolutionize our ability to design safe, targeted, delivery tools for the treatment of genetic conditions.DOI: 10.18609/cgti.2019.058
Submitted for review: February 26, 2019
Citation: Cell & Gene Therapy Insights 2019; 5(4), 523-536.