AI discovers potential new cancer treatment in just 30 days

Researchers from the Univ. of Toronto and Insilico Medicine used an AI-powered database to create a drug that could potentially treat liver cancer.
AI discovers potential new cancer treatment in just 30 days
Posted at 7:23 PM, Mar 21, 2023

You've probably heard about artificial intelligence capable of writing school essays and even passing the bar exam, but it may also be able to detect and treat certain types of cancer.

In just 30 days, researchers from the University of Toronto and Insilico Medicine made a major breakthrough by using an AI-powered database called AlphaFold to create a drug that could potentially treat hepatocellular carcinoma (HCC), or liver cancer.

In the study — published in the journal Chemical Science — researchers applied AlphaFold to their AI-powered drug discovery engines.

It successfully identified a previously undiscovered pathway to treat HCC and developed a "novel hit molecule" that could bind to the target.

In a second round of AI-powered compound generation, the research team discovered an even more potent hit molecule.

However, they said any potential drug would still need to undergo clinical trials before it can be used to treat cancer.

“AlphaFold broke new scientific ground in predicting the structure of all proteins in the human body,” Feng Ren, the study's co-author, said in a statement. “At Insilico Medicine, we saw that as an incredible opportunity to take these structures and apply them to our end-to-end AI platform in order to generate novel therapeutics to tackle diseases with high unmet need. This paper is an important first step in that direction.”

SEE MORE: OpenAI unveils GPT-4, its most advanced AI language model

In a different study published in the journal JAMA Network Open, researchers at the University of British Columbia and BC Cancer showed how AI was more than 80% accurate in predicting cancer patient survivor rates. 

The model was able to analyze doctors' notes on more than 47,000 patients to accurately predict six-month, three-year, and five-year survival rates.

“The AI essentially reads the consultation document similar to how a human would read it,” lead author Dr. John-Jose Nunez said in a statement. “These documents have many details like the age of the patient, the type of cancer, underlying health conditions, past substance use, and family histories. The AI brings all of this together to paint a more complete picture of patient outcomes.”

Researchers are still in the early steps of understanding how AI can be used to help identify and treat diseases, but both studies offer encouraging signs of how it could impact the future of cancer care.

"Our hope is that a tool like this could be used to personalize and optimize the care a patient receives right away, giving them the best outcome possible," Nunez said.

Trending stories at