Pharma researchers turn to AI for help in search for new drugs

While some pharma giants may be moving slowly toward the use of AI, say stakeholders, many start-ups are using artificial intelligence techniques to accelerate other aspects of drug discovery.

Jeff Rowe | Feb 13, 2019 11:02 am

Every two years, hundreds of scientists enter a global competition that, in the long run, could significantly impact the way scientists create new medicines and fight disease.

But as often happens in such competitions, there’s a new challenger in town: Artificial Intelligence.

According to a recent article in the New York Times, the most recent staging of the contest, known pithily as the “Critical Assessment of Structure Prediction,” was won by DeepMind, the artificial intelligence lab owned by Google’s parent company.

As the writer explains, “DeepMind specializes in ‘deep learning,’ a type of artificial intelligence that is rapidly changing drug discovery science. A growing number of companies are applying similar methods to other parts of the long, enormously complex process that produces new medicines. These A.I. techniques can speed up many aspects of drug discovery and, in some cases, perform tasks typically handled by scientists.”

Not surprisingly, there are a number of perspectives swirling around the introduction of AI into drug research.

For example, longtime drug discovery researcher Derek Lowe maintains that “It is not that machines are going to replace chemists. It’s that the chemists who use machines will replace those that don’t.”

Another view was voiced by Mohammed AlQuraishi, a biologist who has dedicated his career to this kind of research. In a blog post, Dr. AlQuraishi said the melancholy he felt after losing to DeepMind gave way to what he called “a more rational assessment of the value of scientific progress.”

But he strongly criticized big pharmaceutical companies like Merck and Novartis, as well as his academic community, for not keeping pace with new AI applications.

“The smartest and most ambitious researchers wanting to work on protein structure will look to DeepMind for opportunities instead of Merck or Novartis,” he wrote. “This fact should send chills down the spines of pharma executives, but it won’t, because they’re clueless, rudderless, and asleep at the helm.”

Not surprisingly, the big pharma companies see the situation differently, the article noted, pointing out that while Merck is not exploring protein folding because its researchers believe its potential impact would be years away, it is applying deep learning to other aspects of its drug discovery process.

“We have to connect so many other dots,” said Juan Alvarez, associate vice president of computational and structural chemistry at Merck.

In the end, says the writer, regardless of the particular use or angle of approach, “DeepMind’s victory showed how the future of biochemical research will increasingly be driven by machines and the people who oversee those machines. This kind of AI research benefits from enormous amounts of computing power, and DeepMind can lean on the massive computer data centers that underpin Google. The lab also employs many of the world’s top AI researchers, who know how to get the most out of this hardware.”


Resource Center VIEW MORE