[ad_1]
Pathways for making drugs and other life-saving pharmaceutical compounds are among the best-protected trade secrets of the global industry. Drawing on recent work computers to identify synthetic pathways leading to complex pharmaceutical molecules, researchers in Poland and South Korea have unveiled computerized methods to suggest only synthetic strategies that bypbad aspects of essential medicines protected by patents. Their work appears on January 17 in the newspaper Chem.
"When we started this project, I was a little skeptical that the machine could find viable synthetic alternatives – after all, these are star drugs worth billions of dollars, and I was sure the respective companies had so densely covered the patent space Bartosz Grzybowski, lead author and professor of chemistry at the National Institute of Science and Technology of Ulsan (South Korea) and the Polish Academy of Sciences , is the leading developer of Chematica's organic synthesis software. "It turns out that the flaws are there and that we can find new retrosynthesis pathways that completely bypbad patents."
These pharmaceutical patents protect the company's intellectual property while preventing competing companies from using certain key synthetic solutions – painstakingly developed through experience to optimize yield, increase purity and reduce costs – when trying to produce the desired compounds . To arrive at viable, non-patented options, researchers have "frozen" difficult parts of each target molecule, forcing the computer to substitute unconventional but chemically plausible approaches on the basis of mechanistic rules. They tested their system on three remarkable commercial drugs with different chemical barriers: linezolid, an antibiotic of last resort; sitagliptin, an antidiabetic agent; and panobinostat, a treatment for multiple myeloma.
In each case, when it is allowed to operate without constraint, the program recommends commercial syntheses. But even if some atoms and bonds were designated as untouchables, he innovated by applying the existing functions of Chematica to propose new plans carefully avoiding those already patented. "By algorithmically locating the key links on which the patents are based and propagating them along Chematica's retrosynthetic trees, we can generate synthetic solutions from alternative but economical starting materials, thus producing a real practical impact", explains Grzybowski.
The dodging capabilities of Chematica's patents could also alter the way chemists approach intellectual property and patent law. For example, machine-badisted searches could be used to restrict many different parts of a target molecule, bringing together radically different syntheses in a single sealed patent. However, according to Grzybowski, such a patent would not necessarily remain flawless, thanks to the future experimental discovery of new reactions that advance knowledge of chemicals through healthy competition.
Overall, the researchers hope their software will help pharmaceutical companies better protect their intellectual property and at the same time help accelerate research and development in organic chemistry by providing synthetic pathways that differ from conventional approaches. "This work illustrates the benefits of pushing chemists to think according to an algorithm and asking computer scientists to grasp key chemical concepts and provide chemical artificial intelligence results that cross borders." of the academic world, "adds co-author Piotr Dittwald, a researcher trained in mathematics. and computer science.
Source of the story:
Material provided by Cell press. Note: Content can be changed for style and length.
Source link
