Dyno Therapeutics, a biotech company applying artificial intelligence (AI) to gene therapy, today announced a publication in Nature Biotechnology that demonstrates the use of artificial intelligence to generate an unprecedented diversity of adeno-associated virus (AAV) capsids towards identifying functional variants capable of evading the immune system, a factor that is critical to enabling all patients to benefit from gene therapies.
The research was conducted in collaboration with Google Research, Harvard's Wyss Institute for Biologically Inspired Engineering and the Harvard Medical School laboratory of George M. Church, Ph.D., a Dyno scientific co-founder. The publication is entitled "Deep diversification of an AAV capsid protein by machine learning."
It is estimated that up to 50-70% of the human population have pre-existing immunity to natural forms of the AAV vectors currently being using to deliver gene therapies. This immunity renders a large portion of patients ineligible to receive gene therapies which rely upon these capsids as the vector for delivery.
Overcoming the challenge of pre-existing immunity to AAV vectors is therefore a major 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," said Eric Kelsic, Ph.D., Dyno's CEO and co-founder.
"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. 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."
The Nature Biotechnology paper describes the rapid production of a large library of distinct AAV capsid variants designed by machine learning models. Nearly 60% of the variants produced were determined to be viable, a significant increase over the typical yield of <1% using random mutagenesis, a standard method of generating 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," added 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.
This research builds upon previous work published in Science in which a complete landscape of single mutations around the AAV2 capsid was generated followed by evaluation of the functional properties important for in vivo delivery.
In parallel with these works, Dyno has established collaborations with leading gene therapy companies Novartis, Sarepta Therapeutics, Roche and Spark Therapeutics to develop next-generation AAV gene therapy vectors with a goal of expanding the utility of gene therapies for ophthalmic, muscle, central nervous system (CNS) and liver diseases.
About capsidMap™ for designing optimized AAV gene therapies
By designing capsids that confer improved functional properties to Adeno-Associated Virus (AAV) vectors, Dyno's proprietary CapsidMap™ platform overcomes the limitations of today's gene therapies on the market and in development.
Today's treatments are primarily confined to a small number of naturally occurring AAV vectors that are limited by delivery efficiency, immunity, payload size, and manufacturing challenges. CapsidMap uses artificial intelligence (AI) technology to engineer capsids, the cell-targeting protein shell of viral vectors.
The CapsidMap platform applies leading-edge DNA library synthesis and next generation DNA sequencing to measure in vivo gene delivery properties in high throughput.
At the core of CapsidMap are advanced search algorithms leveraging machine learning and Dyno's massive quantities of experimental data, that together build a comprehensive map of sequence space and thereby accelerate the design of novel capsids optimized for gene therapy.