Science Concentrates COMPUTATIONAL CHEMISTRY
Chematica could help chemists avoid patented routes “I’m not surprised” that a computer capable of evaluating millions of routes found paths humans didn’t, Grzybowski says. The researchers did not report testing these syntheses in the lab. synthesis planning with an algorithm Grzybowski says chemists could use that searches patent literature to identithe algorithm to develop a generic drug or fy particularly important bonds formed a pharmaceutical in the protected O company could routes to a target OH use it to patent molecule. The N multiple paths to algorithm looks H H N a new drug. He not only for bonds HN adds that others whose formacan copy this altion appears in Panobinostat gorithm, in theory many different combining it with patented routes, other synthesis-planning programs besides but also bonds that produce important Chematica. structural changes rather than, say, add Richard Chinn, a chemist turned patprotecting groups. Grzybowski’s team ent attorney at the firm Grüneberg and instructed Chematica to find new routes Myers, says the algorithm is intriguing but to the patented drug molecules linezolid, he’s skeptical that a computer can outsitagliptin, and panobinostat that don’t smart human experts. Chinn says patent alter those key bonds, under the theory that routes preserving these bonds will be infringement is rarely straightforward, and points out that companies employ meaningfully different from patent-proa number of techniques to protect their tected routes. That typically meant intellectual property, including patenting Chematica found starting materials that methods or techniques, not just routes. He contained those key bonds. thinks Grzybowski’s algorithm may have In each case, the software found plausiuses, but calls it “too coarse” for the subble synthetic paths predicted to have reasonable yields of the target molecule while tle world of intellectual property.—SAM avoiding steps that are already patented. LEMONICK
Algorithm identifies patented parts of synthetic routes
Downloaded via OPEN UNIV OF HONG KONG on January 24, 2019 at 10:19:33 (UTC). See https://pubs.acs.org/sharingguidelines for options on how to legitimately share published articles.
Pharmaceutical companies employ teams of lawyers and intellectual property experts to make sure synthetic routes to new molecules can be protected and don’t infringe on existing patents. Now the creators of Chematica, an artificial intelligence–driven retrosynthesis planner, have demonstrated an algorithm they say can help chemists find routes to molecules that avoid what others have already patented (Chem 2019, DOI: 10.1016/j. chempr.2018.12.004). But lawyers aren’t sure a computer can handle the subtleties of intellectual property law. Bartosz A. Grzybowski of the Polish Academy of Sciences and Ulsan National Institute of Science and Technology and colleagues developed the Chematica software, which uses machine learning to plot synthetic routes to target molecules using some 50,000 rules of chemical reactions the team taught it. Grzybowski sold Chematica to MilliporeSigma in 2017. Last year, the researchers demonstrated that the program could chart routes to target molecules that chemists could then follow successfully in the lab. In the new work, the team pairs this
PHARMACEUTICALS
C R E D I T: J . A M. CH EM . S OC.
Is this the decade of RNA? RNA should be a terrible drug target. Its long, noodle-like structure (shown) lacks the nooks and crannies that small-molecule drugs use to grab onto proteins and thereby control them. But a decades-old disregard for RNA is starting to change. In August 2018, the US Food and Drug Administration approved the first-ever RNA interference drug, which uses a double-stranded RNA molecule to prevent the production of disease-related proteins. In the past two years, several start-ups have launched to show that some RNAs can, just like proteins, be drugged with small molecules. And a group of companies recently emerged with plans to drug proteins that make modifications to RNA, part of the budding field of epitranscriptomics. In this episode of Stereo Chemistry, C&EN visits Alnylam Pharmaceuticals, Novartis, and Accent Therapeutics to discuss these three strategies and to understand how RNA-modulating therapies will compete in the wider world of drug discovery. Listen now at cenm.ag/rnapodcast.—MATT DAVENPORT JANUARY 21, 2019 | CEN.ACS.ORG | C&EN
5
