Hilmar Lapp CV

My research interests broadly fall into biological and biomedical data science, in particular enabling data and knowledge to be more findable, accessible, interoperable, and reusable ("FAIR"). My research program for >15 years has focused on allowing the vast body of observational data expressed in natural language descriptions to be fully computable, through the use of knowledge representation and discovery technologies, in particular ontologies and machine reasoning. I have been funded for this work by the National Science Foundation (NSF) through a series of collaborative grants, as part of which I design and build eScience infrastructure, including data standards, ontologies, data integration systems, and reusable programming interfaces and tools.

Specifically, I am one of the PIs of Phenoscape, a >10 year collaborative project aiming to make evolutionary phenotype descriptions amenable to large-scale computation and reuse, by allowing machines to understand their semantics. Within the recently created HDR Imageomics Institute, where I am part of the leadership team, my research work centers around fully reproducible and automated machine learning (ML) workflows, and making  structured knowledge available to ML algorithms. I was also a PI of the Phyloreferencing project, a collaborative effort to enable machines to understand phylogenetic clade definitions and to use them for reproducible computational data integration of taxon-linked data.