Software outsmarts drug research

Clever software programming combined with deep knowledge of chemistry is set to change the way intellectual property on pharmaceutical breakthroughs is protected or challenged. It’s called Chematica, a computer programme, that can plan chemical syntheses. It promises to make patent protection on new drugs more complex than it already is.

Patents are the lifeblood of the pharma industry, and much money and time is expended on protecting new molecules, some of which turn into blockbuster drugs. Patent attorneys are hired at huge costs to look at production processes to ensure that new drugs —or the processes to make them —are well protected. They also have to make sure that no existing patents are infringed upon. Finding a way through these patent thickets can involve months of labour and expense. To break a drug patent, researchers have to find a different synthesis route and or a different compound, a skill that the Indian generic drug industry is adept at. That, too, takes a while.

All this is set to change with Chematica, an algorithm developed by Polish and South Korean researchers, after 15 years of work. It is difficult to imagine how a computer programme could trump pharma research but Bartosz Grzybowski of the Polish Academy of Sciences and professor of chemistry at the Ulsan National Institute of Science and Technology, South Korea, and his team have demonstrated that the organic synthesis software Chematica can find viable synthetic alternatives to even the most heavily patent-protected drugs. Chematica found the loopholes in the system and new retrosynthetic pathways that circumvented the patents in a jiffy. To put it simply, the computer pinpoints the molecule’s most important bonds that are most commonly formed in patented routes, along with those that produce significant structural changes, and comes up with the alternative syntheses based on this data. As Grzybowski explains, it first identifies the key disconnections on which the existing patents rely and then forces the machine to find alternative routes.

Karol Molga, Piotr Dittwald and Grzybowski created a database and then searched for new and unpatented pathways that connected starting compounds to the desired compound. They demonstrated the efficacy of Chematica by creating non-patented pathways to synthesise linezolid, a last-resort antibiotic, sitagliptin, a drug for diabetes, and panobinostat, a medicine to treat multiple myeloma. The programme found alternatives in a few minutes running on a 64-core machine!

What does this portend for the pharma industry, specially for India’s generic drug makers? If the innovator drug companies use Chematica’s power to preemptively patent large numbers of viable synthetic routes, it could mean the end of the road for generics companies. It is also bad news for patients worldwide that look to India to provide them with cheaper alternatives to the high-cost drugs developed by multinationals.

As yet, there has been no reaction to Chematica by the pharmacy industry. But then, it was only in mid-January that Grzybowski’s findings were published online. The researchers are upgrading the programme to tackle the syntheses of very complex molecules and even more impressively, the environmental and safety issues. Will it turn into a nightmare for patients in poor countries?

(This article was first published in Down To Earth's February 16-28, 2019 print edition)

Subscribe to Daily Newsletter :

SUPPORT US

We are a voice to you; you have been a support to us. Together we build journalism that is independent, credible and fearless. You can further help us by making a donation. This will mean a lot for our ability to bring you news, perspectives and analysis from the ground so that we can make change together.