Michael S. Bradshaw

SeeNV is a tool for rapid, reliable, and interpretable CNV curation in diagnostic settings, achieving high precision and recall with minimal user time.

This paper identifies potential gene-to-phenotype connections for undiagnosed diseases by clustering time-versioned biological ontologies and analyzing network data.

The paper evaluates how knowledge graph topology affects link prediction performance in rare disease variant prioritization, finding that a filtered knowledge graph improves model performance.

This study develops machine learning methods to detect fabrication in large-scale molecular omics data, achieving high accuracy using digit frequency features.