AI that describes how yeast works will help scientists model biology better
A machine-learning algorithm fully describes how the cells function, and could help us improve how we simulate medical research.
Background: Virtually all AI systems are black boxes—algorithms that are impossible for us to examine. That’s fine for, say, tech firms doing image recognition, but biologists would like to understand what algorithms are doing in order to trust them.
The news: IEEE Spectrum reports that researchers mapped all of the functions of brewer’s yeast—a well-studied, single-cell organism—to a neural network. That lets them understand how the AI describes biological behaviour, making it a reliable research tool.
Why it matters: The algorithm has already given researchers new insight into the cell biology of yeast. And, applied to human cells, it could spur advances, by allowing researchers to simulate things like personalized treatments and discover new cancer drugs.
But: Going from yeast to human cells will be tough. And the same problem that bugs computer scientists—a need for data—will frustrate medical researchers trying to hone complex human models.