How artificial intelligence can accelerate drug development
Artificial intelligence – the ultimate optimization engine – takes on one of its biggest challenges: unraveling the complicated, slow, and expensive work of drug development.
Why is this important: Even though computing power has become faster and cheaper, drugs remain slow and expensive to develop, in part because of the work that goes into selecting a candidate and getting them to cross the finish line.
- AI – with its ability to quickly identify data patterns in galaxies – can provide a vital shortcut.
What they say : “What you see [with AI] is a platform for a new generation of drugs, biologics, life extension, all of which are building at a rate impossible to describe, “says Eric Schmidt, former CEO of Google and co-author of the new book”Age of AI. “
The big picture: Drug development is great business, if you don’t mind repeated and costly failures.
- The process of finding and developing a new drug can take more than a decade and costs an average of $ 2.8 billion – and even so, 9 out of 10 drug molecules fail Phase II clinical trials and regulatory approval.
- There are many possible points of failure – identifying a drug candidate from the more than 10⁶⁰ atomic configurations that exist in chemical space, optimizing it for delivery and testing it on animals and humans to see if it is both safe and effective – and they all add to the total cost drugs and health care.
- “Imagine you build 10 skyscrapers and you can guarantee nine will collapse,” says Isaac Bentwich, CEO of new AI drug discovery startup Quris. “But you have no idea which ones will fall, so all you can do is build them and charge higher rent on the one that’s left standing.”
- “This is the problem that we are trying to solve.”
How it works: AI can provide a boost at almost any stage of a drug’s development cycle, evangelists say.
- Exscientia “Centaur Chemist” AI Platform sort by calculation through and compare millions of potential small molecules, looking for a handful to synthesize, test and optimize in the lab before selecting a candidate for clinical trials, which has enabled the company to help bring a drug against cancer in trials in just eight months, compared to a more standard period of four to five years.
- Quris is working to speed up the testing process by testing drugs on miniaturized organs and tissues on a chip that “represent the full genomic diversity of the potential patient population,” notes Bentwich, which in turn generates data that can help train your AI platform to predict the clinical safety and efficacy of new drugs.
- Lantern Pharma is partnering with digital healthcare company Deep Lens to use AI to match the right type of new molecule with the right patient profile for clinical trials for accelerated clinical trials.
- This AI-based approach “can save hundreds of millions of dollars in past drug development costs by ensuring that it is tested on a very specific patient platform,” said Panna Sharma, CEO of Lantern Pharma .
In numbers : The AI market for pharmaceuticals has grown from $ 200 million in 2015 to $ 700 million in 2018, and is expected to reach $ 5 billion by 2024, while job postings related to the AI in the pharmaceutical industry have tripled over the past two years.
The trap : Even as AI becomes more powerful, data sets for drug development can involve millions of compounds, which may exceed the capabilities of current machine learning tools.
- The ultimate ability of AI to change the fundamentals of such a huge, expensive and regulated industry as drug development is “yet to be proven,” Paul Nioi, senior director of research at Alnylam Pharmaceuticals, told Genetic Engineering and Biotechnology News.
The bottom line: Sharma argues that will change – over the past 20 years, technology has “shattered the costs of product development in everything except drug development,” he says.
- “And over the next 20 years, it’s going to totally change this industry.”
Go further: how AI could revolutionize biology – and vice versa