In a world first, Insilico Medicine, a Hong Kong-based startup developing deep neural networks for drug discovery, has successfully synthesized and pre-clinically validate a drug candidate in just 25 days, making the drug discovery process, including the designing stage, take about 46 days.
According to Insilico’s research team and its collaborators at the University of Toronto, the method of designing new kinds of molecules by using a deep generative artificial intelligence (AI) model – called generative tensorial reinforcement learning (GENTRL) – not only set a record time compared to traditional methods but also proved to be 15 times faster than a typical pharma corporation’s efficient R&D process.
It’s worth pointing out, especially for readers unfamiliar with the big pharmaceutical industry, that it takes more than a decade and millions of dollars to discover and develop a drug candidate. What’s even more depressing about this inefficient industry that keeps passing off the illusion of innovation for real innovation, is that in the last twenty-plus years the success rate for a drug candidate entering Phase I trials have stagnated at under 10%. Meanwhile, in pre-clinical phases the failure rates for new compounds is over 99%. No other major industry operates under such a high failure rate and yet enjoy double digits profit margins.
Hopefully, innovative methods from AI-based companies like Insilico will help change this landscape of failure. Thanks to its GENTRL system, Insilico’s team was able to synthesize six molecules in just 21 days, targeting a protein involved in fibrosis. From that group, four AI-generated molecules showed activity in biochemical assays, and two were tested in cell-based assays. The most promising molecule displaying metabolic stability in several qualitative assays was then tested and demonstrated favorable pharmacokinetics in mice.
“Our AI can be used in all phases and in some cases lead to superhuman results”, said in statement Alex Zhavoronkov, CEO of Insilico Medicine who compared GENTRL to the AlphaGo, an AI-powered learning system developed by Google’s Deepmind. Zhavoronkov also emphasized the fact that the startup’s AI is “exceptionally good at finding the molecular targets in specific diseases and inventing new chemistry.”
Insilico put the cost of generating 30,000 designs for its novel DDR1 kinase inhibitor at $150,000.
Although Zhavoronkov cautions that the company still has much work ahead, he says his team’s research is a major breakthrough when it comes to demonstrating that artificial intelligence can successfully be used to identify and create a new drug candidate in a very short time. He concludes by saying that the potential of using cutting-edge techniques in AI for drug discovery removes “a lot of skepticism in big pharma.”
Well, there is no need really for the big pharma to be skeptical. As Yann LeCun beautifully said it: “Our intelligence is what makes us human, and AI is an extension of that quality.”
Insilico’s full paper can be found online in Nature Biotechnology
Disclaimer: This page contains affiliate links. If you choose to make a purchase after clicking a link, we may receive a commission at no additional cost to you. Thank you for your support!
Leave a Reply