The global pandemic of COVID-19 has affected the lives of millions of people around the world. Health research teams must radically changed their plans and put significant portion of their capacity into research for the disease in order to find effective help as soon as possible. Researchers from Loschmidt Laboratories, the Faculty of Science and the Institute of Computer Science of Masaryk University, the RECETOX Research Center and the International Clinical Research Center of St. Anne’s University Hospital Brno (FNUSA-ICRC) came up with an interesting initiative .
Their project is using computational biochemitry, artificial intelligence and the principles of machine learning. “Using our own CaverDock software, we focused on a protein that is key in the spread of SARS-CoV-2 virus in the human body,” described prof. Mgr. Jiří Damborský, Ph.D. from PřF MUNI and head of the Protein Engineering research team of FNUSA-ICRC. It is a viral S-glycoprotein whose trimer (a molecule of three monomers) forms the protrusions of the SARS-CoV-2 coronavirus envelope and which binds to human host cells.
The researchers performed a so-called virtual screening of 4,359 approved drugs to find out their effectiveness on this particular protein. We have used in house program CaverDock for the first time to study such a large pool of molecules in this project. The sofware posessed excellent robustness and is among the most reliable tools in its category.“ commented author of Dr. Jiří Filipovič from the Institute of Computer Science. The software CaverDock was developed thanks to support from internal grant agency of MU for interdisciplinary research and is provided to a wide user community by national infrastructure ELIXIR.CZ. “We performed several simulations of changes in the molecular arrangement of this protein to see which of the known drugs could be most effective,” said Dr. Gaspar Pinto from Loschmidt Laboratories MU and FNUSA-ICRC. Because such a process generates an enormous amount of data, machine learning methods and artificial intelligence are used to analyze them. “We also submitted the grant application to Microsoft for the use of the Azure cloud,” added Dr. Pinto.
Based on these calculations, several approved drugs have been proposed that can block this protein and thus prevent the virus from binding to the human host cell. “Artificial intelligence can also offer new drug structures that bind to protein even more effectively,” said Dr. Pinto. “This is a new area of COVID-19 research, we are creating software solutions to accelerate the development of new drugs.”