New AI-based method produces new diversity of AAV capsids for optimized gene therapy

Dyno Therapeutics has demonstrated the use of artificial intelligence (AI) to created an unparalleled range of adeno-associated virus (AAV) capsids for determining functional variants that can evade the immune system, a factor crucial to allow all patients to benefit from gene therapies.

A biotech company applying AI to gene therapy, Dyno recently reported this breakthrough in a publication titled “Deep diversification of an AAV capsid protein by machine learning” in the Nature Biotechnology journal.

The research was performed together with Google Research, Harvard’s Wyss Institute for Biologically Inspired Engineering, and the Harvard Medical School laboratory of George M. Church, Ph.D., a scientific co-founder of Dyno.

It is predicted that nearly 50%–70% of the human population have pre-occurring immunity to natural forms of the AAV vectors used at present to deliver gene therapies. This immunity makes a huge portion of patients ineligible to receive gene therapies that are dependent on these capsids as the vector for delivery. Solving the issue of pre-occurring immunity to AAV vectors is thus a crucial goal for the gene therapy field.

The approach described in the Nature Biotechnology paper opens a radically new frontier in capsid design. Our study clearly demonstrates the potential of machine learning to guide the design of diverse and functional sequence variants, far beyond what exists in nature.”

Eric Kelsic, PhD, CEO and Co-Founder, Dyno Therapeutics

We continue to expand and apply the power of artificial intelligence to design vectors that can not only overcome the problem of pre-existing immunity but also address the need for more effective and selective tissue targeting,” Dr Kelsic added.

At Dyno, we are making rapid progress to design novel AAV vectors that overcome the limitations of current vectors, improving treatments for more patients and expanding the number of diseases treatable with gene therapies.”

Eric Kelsic, PhD, CEO and Co-Founder, Dyno Therapeutics

In the Nature Biotechnology paper, the fast production of a large library of unique AAV capsid variants developed using machine learning models has been described. Almost 60% of the variants synthesized were found to be viable, which is a major increase over the usual yield of <1% with random mutagenesis, which is a standard technique to produce diversity.

The more we change the AAV vector from how it looks naturally, the more likely we are to overcome the problem of pre-existing immunity,” noted Sam Sinai, Ph.D., Dyno co-founder, and Machine Learning Team Lead. “Key to solving this problem, however, is also ensuring that capsid variants remain viable for packaging the DNA payload.”

With conventional methods, this diversification is time- and resource-intensive, and results in a very low yield of viable capsids. In contrast, our approach allows us to rapidly unlock the full potential diversity of AAV capsids to develop improved gene therapies for a much larger number of patients.”

Sam Sinai, Co-Founder, Dyno Therapeutics

This study is based on a previous study published in Science where a thorough landscape of single mutations around the AAV2 capsid was produced and the functional properties crucial for in vivo delivery were assessed.

Together with these studies, Dyno has forged collaborations with pioneering gene therapy companies Sarepta Therapeutics, Novartis, Spark Therapeutics, and Roche to create next-generation AAV gene therapy vectors with the aim of increasing the utility of gene therapies for muscle, ophthalmic, liver, and central nervous system (CNS) diseases.

Source:
Journal reference:

Bryant, D. H., et al. (2020) Deep diversification of an AAV capsid protein by machine learning. Nature Biotechnology. doi.org/10.1038/s41587-020-00793-4.

Comments

The opinions expressed here are the views of the writer and do not necessarily reflect the views and opinions of AZoLifeSciences.
You might also like... ×
A functional test to measure the effect of inherited gene variants in breast and ovarian cancer