Scientists are aiming to fuse artificial intelligence and virtual reality in the search for a COVID-19 cure.
Many potential therapeutics aimed at containing the spread of the virus have targeted the ‘spike’ protein, a surface protein that plays a vital role in viral entry into host cells.
However, a new study involving AI and VR technologies, suggests that two-thirds of the SARS-CoV-2 genome comprises non-structural proteins, such as the viral protease (the protein necessary for viral replication).
These, researchers say, should not be overlooked as potential therapeutic targets.
Nanome, a US-based VR startup, has co-authored a paper describing 10 potential small molecule inhibitors targeting the SARS-CoV-2 main protease that were generated by AI.
The study was conducted in collaboration with Insilico Medicine, an artificial intelligence company based in Hong Kong.
It is hoped that it could reveal as yet-undiscovered methods for attacking the virus that have eluded scientists working with existing drug candidates.
“The SARS-CoV-2 main protease is a much more druggable protein than the spike protein,” said Alex Zhavoronkov, CEO of Insilico Medicine and lead author on the paper. “It contains a pocket perfect for small molecule inhibitors.”
But since the beginning of the COVID-19 outbreak, only a few studies on novel SARS-CoV-2 protease inhibitors have been published.
“One reason for this is the daunting number of chemical structures that can be generated from scratch,” said Zhavoronkov. “Consequently, conventional computational drug design approaches tend to include a limited number of fragments and/or employ sophisticated search strategies to sample hit compounds from a predefined area of the chemical space.”
Scientists have developed a new type of computational method for drug discovery using recent advances in deep learning and AI. Zhavoronkov calls it “AI imagination”.
Insilico’s proprietary AI imagination platform has already been successfully applied to design small molecule drugs for a wide range of human diseases, such as cancer, fibrosis, and immunological diseases.
In the study, the authors used a protein structure published to the Protein Data Bank (PDB) website by Purdue University to generate a number of novel, non-covalent drug candidates.
The generation was followed by the selection of 10 representative examples and medicinal chemistry analysis in VR, provided by Nanome.
The authors hope their compounds will be synthesized and tested in vitro and in vivo in the future.