Biostatistics and Medical Informatics Seminar with Assistant Professor Marinka Zitnik of Harvard University

Graph representation learning leverages knowledge, geometry, and structure to develop powerful machine learning methods. Dr. Zitnik will first introduce Shepherd, a graph neural network for personalized diagnosis of patients with rare genetic diseases. Diagnostic delay is pervasive in patients with rare genetic conditions.Second, I will describe applications of graph neural networks in drug discovery, which are available through the Therapeutics Data Commons.