Artificial intelligence will be able to discover new drug candidates within the next three years, machine learning experts predicted Nov. 21 at a STAT Summit.
AI can mine an increasing amount of biological data for patterns that humans can't see, allowing the technology to identify potential drugs. Identifying drug candidates with AI would fundamentally change the way drugmakers conduct research, the experts said.
It also could give drug researchers new approaches to finding treatments for cancers or neurodegenerative diseases like Alzheimer's.
According to Aviv Regev, PhD, a computational biologist at the Cambridge, Mass.-based Broad Institute, machine learning is already dramatically changing biological research.
"Now you can handle all sorts of things that we as humans see as imperfections," Dr. Regev told STAT. "That changes what [data] we should be collecting if we want to do drug discovery. We should not just think about doing things we’ve done 100 or a thousand times before, but doing things very differently."
However, Hal Barron, MD, chief scientific officer of GlaxoSmithKline, told STAT it will take much longer for such discoveries to be turned into approved medicines. He also warned that machine learning, which sorts through massive datasets to pick out insights, may not be as useful as some think because of the sheer amount of data needed.
Read the full article here.
More articles on pharmacy:
AHA, CVS Health backed secretive anti-pharma group
EpiPen, Humira among drugs Warren wants to regulate
31 drugmakers at high risk for bankruptcy in 2020