Title: "Predicting protein structures using functional data"
Speaker: Guillaume Lamoureux, Associate Professor, Department of Chemistry, Rutgers University-Camden, Camden, New Jersey.
Protein-protein interactions (PPIs) are essential for biological function but remain very difficult to predict computationally. Coevolution signals between two interacting proteins are much weaker than within a single protein and can be detected reliably only if many orthologous protein pairs are available. PPIs are also heavily dependent on biological context and are sensitive to perturbations such as genetic variations or disease mutations. In this talk, Dr. Lamoureux will present his team's contributions to the development of unified “sequence-to-structure-to-function” models based on deep neural networks. These models aim at predicting how proteins assemble and interact with one another using molecular representations learned from high-throughput PPI data. His team has demonstrated the concept on a simplified version of the protein docking problem, and he will discuss their efforts at applying it to more challenging prediction tasks.
