Sign In

Communications of the ACM

ACM TechNews

Artificial Intelligence Helps Identify Effective Cancer Drug Combinations

Artist's represention of an anti-cancer therapy derived by artificial intelligence.

Artificial intelligence can help scientists predict which combinations of existing drugs may work on different types of cancer.

Credit: Innovation Toronto

Researchers at Cornell University have found artificial intelligence (AI) can help scientists predict what combinations of existing drugs could combat different types of cancer.

In two studies, the researchers found AI techniques were able to suggest effective anti-cancer drug combinations, and the most effective combinations were later confirmed experimentally.

In the first study, the researchers used AI techniques to build models that predict synergistic drug combinations. They trained the models to recognize the tested combinations and applied them to assess a larger set of combinations to determine which ones might be effective. The researchers used an algorithm-based approach to predict what drugs might work well together.

In the second study, the researchers used AI to build a detailed model of the B cell receptor antigen pathway, and found how different genes on the pathway work together to encourage cancer growth.

From Cornell University
View Full Article


Abstracts Copyright © 2017 Information Inc., Bethesda, Maryland, USA


No entries found