AI to Speed Cancer Drug Development
An estimated 4 out of every 10 Americans will deal with cancer sometime in their lifetimes. According to the National Cancer Institute, most people with a cancer diagnosis will die within 5 years. On average, it takes more than 10 years for a new cancer drug to reach the marketplace. Then 93% of experimental cancer drugs tested by the FDA fail in terms of effectiveness.
Insilico Medicine, a Baltimore-based biotech research company, hopes to revolutionize drug development by slashing the time necessary for research using artificial intelligence (AI).
In a study published in the medical journal Oncotarget, a team led by Insilico Medicine details their approach. Essentially, researchers built two computer networks (together known as generative adversarial networks, or GANs). One suggests new molecules that may have cancer-fighting properties; the other eliminates those suggestions based on known treatments.
As the networks begin to do their dance with each other, the team at Insilico Medicine managed to to screen 72 million chemicals from a public database. Among these compounds were 60 already recognized as cancer treatments. What this means is, the in silico ( computer tested) method is exponentially faster than the old, method of using racks of test tubes and notebooks filled with scribbles.
This new process by Insilico Medicine will save billions of dollars in cancer research as well. A study from the Journal of Health Economics estimates that the costs associated with failed drugs adds more than $1.6 billion to the cost of each successful one.