The goal is to improve the yield and quality of next-generation gene therapy vectors—typically viruses—using artificial intelligence (AI) and machine learning.
Katherine Welles / Shutterstock.com
Oxford BioMedica announced it had inked a two-year research-and-development collaboration with Microsoft Research. The goal is to improve the yield and quality of next-generation gene therapy vectors—typically viruses—using artificial intelligence (AI) and machine learning.
Oxford Biomedica will focus on its expertise in vector development and large-scale manufacturing. The team in Microsoft’s Station B initiative will use AI and machine learning to increase the yield and improve the purity of Oxford Biomedica’s lentiviral vectors while cutting costs.
Station B will use the Microsoft Azure intelligent cloud platform to analyze large data sets created by Oxford Biomedical and develop in silico models and novel algorithms to advance cell and gene delivery technology.
The partnership will run two years and may be extended by either group.
“Our LentiVector gene delivery platform is recognized as a leading solution by major industry players but developing next-generation manufacturing technologies is complex and often involves uncertain outcomes,” stated Jason Slingsby, Oxford Biomedica’s chief business officer.
He went on to say, “The collaboration with Microsoft Research will harness our rich data resources to offer greater insights into the biological processes required to enhance quality and optimize yields of lentiviral vectors. It builds on our digital framework initiative, established in 2018, and the work underway in our collaboration with Synthace to rapidly and flexibly design, simulate and execute complex experimental designs to develop next generation manufacturing processes, including with stable producer cell lines for lentiviral vectors. Our goal is to enable faster, cheaper and more reliable manufacture of high-quality next-generation cell and gene therapies to allow more patients to benefit.”
Microsoft has been developing cloud and AI products for healthcare, particularly in streamlining data entry, triaging patients and targeted cancer care. For example, the Walgreens Boots Alliance retail chain is using Azure to connect physicians and pharmacists with patients’ healthcare data.
AI is increasingly becoming a common tool for drug development. Recently, the Critical Assessment of Structure Prediction (CASP) contest hosted by the Protein Structure Prediction Center, which is sponsored by the U.S. National Institute of General Medical Sciences (NIH/NIGMS), was “won” by DeepMind, the AI laboratory owned by Google/Alphabet—instead of by a team of biologists and biochemists.
CASP is a worldwide experiment that takes place every two years. Participants attempt to predict the 3-D shape of a specific human protein. DeepMind didn’t just beat out the other scientists but gave a prediction that was almost twice as accurate as experts expected.
And other pharma companies are utilizing various AIs to help with their research. Merck & Co. uses deep learning algorithms, although not generally for 3-D protein structure analysis. Recursion Pharmaceuticals, headquartered in Salt Lake City, Utah, combines AI, experimental biology and automation to discover and develop drugs at scale. San Francisco-based Atomwise is using AI based on convolutional neural networks to search for drugs. In January, it signed a strategic alliance with contract research organization (CRO) Charles River Laboratories International to support CRL’s hit discovery, hit-to-lead, and lead optimization efforts.
Of the collaboration with Oxford Biomedica, Andrew Phillips, head of Biological Computation at Microsoft, stated, “Programming biology has the potential to solve some of the world’s toughest problems in medicine, and to lay the foundations for a future bioeconomy based on sustainable technology. Oxford Biomedica is at the cutting edge of cell and gene therapy delivery and their highly sophisticated manufacturing processes generate a vast wealth of valuable data. We anticipate that by combining computational modeling, lab automation, machine learning and the power of the cloud, we can help them in their quest to make existing treatments more cost effective and in future to develop groundbreaking new treatments.”
