Scientists at the University of Virginia’s School of Medicine developed a powerful artificial intelligence tool to determine how subtle changes in proteins affect and drive disease.

The tool is meant to accelerate the development of new drugs and treatments for complex diseases. The researchers dubbed the tool “ERIS2,” and it can predict how gene mutations affect the stability of cellular proteins. Protein shape determines how well proteins can do their jobs.

ERIS2 is meant to help scientists quickly and accurately identify which gene variants may affect protein function and cause illnesses such as inherited genetic disorders or cancers. This can drive development of new, more effective treatments. Current techniques to assess the effect of gene mutations on protein stability are expensive and labor-intensive and very challenging to apply to complex applications such as long sequences of amino acids.

ERIS2 automates that work; researchers combined detailed protein measurements with other structural details and trained their tool using a database of more than 100,000 known mutations. This helped the team overcome limitations that hampered prior computational models. The tool offered improved accuracy for predicting mutation effects.