McKinsey estimates there are nearly 270 companies working on utilizing artificial intelligence in drug development. There has been a surge in venture capitalists requesting evaluations of AI drug discovery companies over the past five years. Stanford University professor, Russ Altman, said “It went from zero to a hundred” in a very short amount of time. Morgan Stanley estimates that over the next decade, the use of AI in early-stage drug development could translate into an additional 50 novel therapies worth more than $50 billion in sales.
How is AI Being Used in Drug Development?
Companies are using algorithms to explore vast amounts of data – including the structures of chemical compounds, animal studies and information from patients – to help identify what a future drug needs to target in the human body; which molecule would be best suited for this; and most enticingly, how to create new molecules altogether.
“I absolutely do believe that all drugs will be designed this way in the future, because I do believe it’s a far more efficient way to design molecules,” said Andrew Hopkins, founder of Exscientia, one of the first companies in this space in 2012.
Verge Genomics is trialing a novel therapeutic for ALS. The development of this drug skipped the typical first step of testing in animals and went right to using human data and human models in the discovery and development phase. They believe this process provides more insightful findings than animal models.
What is the Critical Ingredient?
Immense quantities of data are needed for artificial intelligence to process and design new drugs. This can include everything from data on the chemical composition of different molecules, to research papers and patient data. Without access to this data AI can’t produce results.
“The new gap for me and a vision right now is the generation of high quality data in an amount that unlocks the true potential of artificial intelligence deep learning. These techniques do require a massive amount of validated data,” said Andrea Beccari, who heads up Italian biotech Dompe’s drug discovery platform.
Dompe couldn’t compete with a large pharmaceutical company for data resources but the European Union is trying to establish a European Health Data Space (EHDS) as a central depository of data. The EHDS plans to create standards, improve interoperability and allow access to endless datasets. Jim Weatherall, AstraZeneca’s vice president of data science, AI and R&D, acknowledges that the creation of this database is “tremendous” but says that the key is doing this without “overbearing bureaucracy.”
What Does the FDA Think?
The FDA recognizes the increased use of artificial intelligence in drug development across a range of therapeutic areas. They are seeing it in increased application submissions using AI components with 100 submissions reported in 2021. Not only is it happening in drug discovery and clinical research but also post market safety surveillance and advanced pharma manufacturing.
The FDA is accelerating their efforts to create an agile regulatory ecosystem that can facilitate innovation while safeguarding public health. “They plan to develop and adopt a flexible risk-based regulatory framework that promotes innovation and protects patient safety.’’
AZ’s Weatherall went on to say, “We’ve been on a journey from ‘what is this?’ to ‘why did we ever do it any other way?’”