TThe search for new medicines is often more like a game of roulette than high-level science. But now the pharmaceutical industry is on the cusp of a transformation as it delves into cutting-edge technology to devise new treatments for diseases like cancer, rheumatoid arthritis and Alzheimer’s.
Artificial intelligence (AI) is meant to improve industry success rates and accelerate drug discovery, which could save you billions of dollars. recent survey from analytics firm GlobalData has found. AI topped a list of technologies that are considered to have the biggest impact on the industry this year. Nearly 100 partnerships between artificial intelligence specialists and Big Pharma have been established for drug discovery since 2015.
AI uses automated algorithms – sets of instructions that computers follow – to perform tasks previously performed by humans. You can quickly sift through large data sets (from clinical studies and scientific literature) to spot hidden patterns and complete tasks in seconds that would normally take months. A study in the Lancet found that artificial intelligence software could identify breast cancers that doctors missed on mammograms.
In a process known as machine learning, artificial intelligence systems execute millions of possibilities, improving each time, until they can function acceptably. The result of that training is an algorithm.
“Drug discovery is being transformed through the use of AI, which is reducing the time it takes to extract the vast amount of scientific data to allow a better understanding of disease mechanisms and identify potential new drug candidates,” says Karen Taylor, director of the Center for Health Solutions for the accounting and consulting group Deloitte. “Traditional drug discovery has been very piecemeal, very unpredictable,” he adds.
Taylor says the rapid progress of Covid-19 vaccines and potential treatments has been aided by the use of AI techniques. “It allows you to cross-reference a large body of published literature with other data in seconds.”
Kitty Whitney, director of thematic research at GlobalData, says the Covid-19 crisis could be a “tipping point” for widespread adoption in the pharmaceutical industry.
About 90% of large pharmaceutical companies started artificial intelligence projects last year, according to the American research firm Trinity Life Sciences. AstraZeneca and GSK, Britain’s two largest pharmaceutical companies, pledged in November to five-year partnership with the University of Cambridge to fund the Cambridge Center for AI in Medicine. The 15-person team will develop artificial intelligence and machine learning technologies to enhance clinical trials, personalized medicine and drug discovery.
GSK had previously opened a £ 10 million artificial intelligence research base at King’s Cross in central London, near Google’s DeepMind artificial intelligence lab. His global team of artificial intelligence experts has grown to 50 people, which he wants to double to 100.
Functional genomics, a new area of science that looks at why small changes in a person’s genetic makeup can increase disease risk, deals with large data sets. Each person has about 30,000 genes, which can be combined with others, explains Hal Barron, scientific director of GSK. “You start to realize that you are dealing with trillions and trillions of data points, even by experiment, and no human can interpret that, it is too complicated.”
Large pharmaceutical companies have been criticized for their slowness in embracing technological advances. Drug discovery has a woefully low success rate: out of 10 drugs in development, nine will typically fail; It takes 10 to 12 years on average, and comes at a high cost, of more than $ 2 billion, to take a drug through research and development and regulatory approval.
The discovery of conventional drugs has been compared to a “molecular casino” by Alex Zhavoronkov, an expert in the use of AI for the development of new drugs, who runs Hong Kong-based Insilico Medicine.
Barron of GSK acknowledges that the use of artificial intelligence technologies could at least double the success rate to 20%, saving billions of dollars spent on drug development. Others, like Zhavoronkov, hope the success rate can improve much more, potentially to 50%.
All the top 10 drug manufacturers in the world: Swiss firms Novartis and Roche; the US companies Pfizer, Johnson & Johnson, Merck, AbbVie and Bristol Myers Squibb; Sanofi from France; and AstraZeneca and GSK from the UK are now investing in AI, primarily through collaborations or by acquiring technologies.
Kim Branson, global director of AI and machine learning at GSK, says that AI is being used in the search for treatments for infectious diseases, as well as for diseases that are more difficult to solve, such as cancer, rheumatoid arthritis and autoimmune disorders. like Crohn’s disease. Alzheimer’s, “the most difficult of difficult targets,” is on GSK’s radar, but will be addressed at a later stage.
Zhavoronkov says the problem with Alzheimer’s and Parkinson’s disease brain disorder is that not enough data is available to study them, hence the large number of drug failures to date.
Zhavoronkov and Barron have expressed confidence that a breakthrough can be achieved in one of the most difficult diseases to investigate with AI technologies. Barron compares the potential of having a new microscope. “In the next year or two we could find a goal that can really make a difference.”
George is Digismak’s reported cum editor with 13 years of experience in Journalism