UVA releases free AI tool to predict mutation effects on proteins
University of Virginia researchers have developed ERIS2, a deep-learning tool that predicts how genetic mutations affect protein stability, potentially helping scientists identify mutations linked to diseases such as cancer and inherited disorders. Because laboratory methods for assessing these effects can be costly and labor-intensive, the tool could make the research faster and help guide treatment development. The team trained ERIS2 using more than 100,000 known mutations and protein-structure data; UVA says testing showed improved predictive accuracy. The tool is available to researchers online at no cost, and its creators say it may also aid the design of diagnostic and therapeutic proteins.
Claim check
What each side asserts, disputes — or leaves out entirely.
Where do you land?
Whose framing of this story rings truest to you?
