R. Michael Sivley

VUStruct analyzes genetic variants of unknown significance by integrating 3D protein structure data and machine learning to improve clinical and research interpretation of rare genetic disorders.

This paper develops an integrated risk tool combining polygenic risk scores with clinical risk factors to improve coronary artery disease prediction, showing better performance than existing tools.

The paper assesses how well existing human protein 3D structures represent genetic and functional diversity across the 1000 Genomes Project, finding significant underrepresentation of African ancestry sequences.

The paper analyzes the spatial distribution of missense variants in human protein structures to classify variants of unknown significance, finding disease-causing variants cluster more than benign ones.