Studying human disease with molecular network models derived from scientific literature

In my Ph.D. work, I focused on building and refining models of molecular networks, as well as on applying these models to real-world problems. Specifically, I devised methods to reliably extract knowledge about molecular interactions from the biomedical literature, I have used data integration methods to combine the literature-based information with results from high-throughput experiments, and in a novel approach I have built a probabilistic framework that combines the standard genetic linkage formalism with whole-genome molecular-interaction data to predict pathways or networks of interacting genes that contribute to common hereditary disorders. Each of those aspects of my work is grounded in the use of advanced applied machine learning and statistical modeling methods on massive amounts of data.