Computer program to circumvent patents to produce synthetic drugs

Software capable of circumventing current intellectual property and designing drugs with the same function as the best drugs could help pharmaceutical companies…

Researchers in Poland and South Korea have developed a computerized method that could be used to synthetically produce essential drugs, bypassing patent protection.

In global industry, some of the best-kept secrets are those needed to manufacture life-saving drugs and other pharmaceutical products.

“When we started this project, I was somewhat skeptical that the machine would find viable synthetic alternatives – after all, these are blockbuster drugs worth millions of dollars, and I was sure that the respective companies had covered the patent space so densely that none of the gaps remained,” said the professor of chemistry at the National Institute of Science and Technology in Ulsan (South Korea) and the Polish Academy of Sciences, the Dr. Bartosz Grzybowski.

“It turns out the loopholes are there, and we can find new retrosynthesis pathways that bypass the patents entirely.”

Dr. Grzybowski is also the lead developer of Chematica organic synthesis software.

These pharmaceutical patents protect the intellectual property of the company and also ensure that competitors are prevented from using certain synthetic solutions. These are the ones that are usually developed by researchers to increase the purity of the final drug product, maximize its yield and reduce the costs associated with it. The process is usually extremely slow and time-consuming, with a team of scientists conducting experiment after experiment to arrive at the final product.

To overcome the patents in place, the research team “froze” difficult parts of each target molecule, which forced the computer to substitute unconventional but chemically plausible molecules based on mechanistic rules.

The researchers tested their computer software using major commercial drugs; linezolid, sitagliptin and panobinostat. Linezolid is an antibiotic of last resort, sitagliptin is an antidiabetic drug, and panobinostat is a drug for multiple myloma. Each of the drugs presented different challenges with respect to their chemical composition.

When the computer program was allowed to operate without constraints, it recommended business structure and synthesis. However, when researchers designated certain atoms and bonds as untouchable, the program came up with plans that avoided the patented ones.

“By algorithmically locating the key bonds on which the patents are based and propagating them in Chematica’s retrosynthetic trees, we can generate synthetic solutions from alternative but economical starting materials, achieving real practical impact,” said Professor Grzybowski.

The ability of software to “dodge” patents may cause chemists to change their approach to patent and intellectual property law.

The research team hopes its software can help pharmaceutical companies protect their intellectual property and accelerate research in organic chemistry.

“This work exemplifies the benefits of pushing chemists to think algorithmically and requiring computer scientists to grasp key chemical concepts, delivering chemical artificial intelligence results that matter beyond the confines of academia.” co-author, Dr. Piotr Dittwald, researcher with a background in mathematics and computer science.

The study was published in the journal Cell.

Alvin J. Chase