Although a British artificial intelligence (AI) developer said Eli Lilly’s Olumiant (ingredient: baricitinib) could be effective in treating the new coronavirus (2019-nCoV), it is too early to use the drug for urgent patients, experts said.
Professor Justin Stebbing of Imperial College London and researchers at BenevolentAI, the U.K. healthcare firm, published their joint study on the Lancet on Tuesday.
The researchers said that with the advancement of DNA sequencing analysis, anti-HIV treatments such as a combo of lopinavir and ritonavir had been cited as an alternative treatment for the new coronavirus. Still, there was no authorized drug with concrete evidence to treat the new virus, the researchers said.
The researchers used AI to search for existing medicines that could block the transmission of the 2019-nCoV, and the results showed that Olumiant was the most likely one to do so.
Olumiant is a therapeutic agent for immunological diseases that selectively inhibits janus kinase 1(JAK1) and JAK2, which are intracellular signaling pathways for inflammatory cytokines. The agent is used around the world, initially approved for rheumatoid arthritis.
BenevolentAI narrowed down candidates out of the 378 AAK1 (AP2-associated kinase 1) inhibitors based on affinity and toxicity. The company chose six with the highest affinity but excluded sunitinib and erlotinib due to serious side effects.
Finally, the company picked Olumiant as the most suitable drug for the new coronavirus, as it had a sufficient therapeutic effect even at a low dose (2mg or 4mg once daily).
However, the researchers said, “Our early investigations and suggestions require further detailed work and analysis and should not be relied on as constituting any kind of medical or other advice or recommendation.”
A Korean specialist in infectious disease also said that as the new coronavirus was quickly spreading, it was unlikely that physicians could use a drug found through machine learning. “Maybe in the future, there could be a clinical trial,” he said.
Experts outside Korea paid more attention to the fact that AI could help protect the public health in an extremely urgent public health crisis than Olumiant’s efficacy on the novel coronavirus.
Mike Tarselli, scientific director of the Society for Laboratory Automation and Screening (SLAS) that consists of 16,000 U.S. and European scientists, said AI-based efforts could save time and resources of drug researchers.
“The use of AI to augment human capacity, to address a pressing public health concern using existing data without re-deploying a full team, should be a boon to researchers,” he said.
However, Timothy Cernak, a medicinal chemist at the University of Michigan, raised concerns for a scenario where a worried patient takes Olumiant without medical supervision.
He pointed out that BenevolentAI’s paper did not reveal how the researchers or their software decided to focus on AAK1.