Skip to Main Content

It often takes years and hundreds of millions of dollars to discover a novel drug candidate. It requires the identification of promising molecules that can grab on to the right protein, synthesizing a compound, and then testing it. The process is so complicated that it has defied most computational methods to shorten it.

But a paper published Monday in Nature Biotechnology describes a new method using artificial intelligence that, within 46 days, generated compounds capable of hitting a specific disease target.

Unlock this article by subscribing to STAT+ and enjoy your first 30 days free!