Drug companies spend billions developing and protecting their trademark pharmaceuticals. Could artificial intelligence be about to shake things up? In a breakthrough development, researchers have demonstrated an A.I. which can find new methods for producing existing drugs in a way that doesn’t infringe on existing patents.
Called Chematica, the software platform does something called “retrosynthesis,” similar to the kind of reverse engineering that takes place when an engineer dissects an existing product to see how it works. In the case of Chematica, this process is based on a deep knowledge of how chemical interactions take place. It has around 70,000 synthetic chemistry “rules” coded into its system, along with thousands of additional auxiliary rules prescribing when particular reactions occur and with which molecules they’re compatible. An algorithm then inspects the massive number of possible reaction sequences in order to find another way to the same finish line.
“They effectively walk on enormous trees of synthetic possibilities, so it is a graph search problem they are trying to solve,” Bartosz Grzybowski at the Ulsan National Institute of Science and Technology (UNIST) in South Korea, told Digital Trends. “Akin to chess, every synthetic move these algorithms make is evaluated by scoring functions, which we developed over the years to tell the program whether it is navigating in the right synthetic direction.’”
The analogy to playing chess isn’t a frivolous one. Over the almost two-decades (!) that this work has been ongoing, the researchers have shown that the numbers of “positions” the A.I. must evaluate is similar to the number of possibilities that chess programs have to scrutinize.
“In principle, one can always argue that a human expert would also design this or that synthetic route,” Grzybowski continued. “That is absolutely possible given adequate amount of time, but Chematica does the job on typical timescales of [just a few minutes to one hour]. It’s like trying to multiple 468,383,83 x 25,405 with paper and pencil versus using a calculator.”
As exciting as the work is, however, don’t expect this to be anything that brings down the world of big pharma — if that’s what you’re hoping for. Chematica, which was bought by pharma giant MilliporeSigma in 2017, is more likely to be used to help these companies better protect their intellectual property.
“[In our latest] paper we tackled three blockbuster drugs, very heavily guarded by patents — and yet a ‘stupid’ computer managed to find synthetic bypasses,” Grzybowski said. “Now, what if your competitors were to use such a tool? Could they bust your patents? Should you also use the tool? What if they come up with a better version? These sorts of question might point to an arms race in developing similar and competing software solutions.”
- Analog A.I.? It sounds crazy, but it might be the future
- Nvidia’s latest A.I. results prove that ARM is ready for the data center
- Can A.I. beat human engineers at designing microchips? Google thinks so
- Google’s LaMDA is a smart language A.I. for better understanding conversation
- How the USPS uses Nvidia GPUs and A.I. to track missing mail