The researcher built and trained their generative AI model on thousands of molecules to see which would bind with two COVID-19 protein targets. The four validated molecules still have to clear regulations and clinical trials before they can be turned into drugs, according to a June 28 IBM blog post.
The researchers hope that the study shows how generative AI could be used to expedite the drug discovery process during a public health crisis.
“It took time to develop and validate these methods, but now that we have a working pipeline in place, we can generate results much faster,” Payel Das, PhD, a researcher at IBM Research and study co-senior author, said in the release. “When the next virus emerges, generative AI could be pivotal in the search for new treatments.”
