Abstract: Grand biomedical challenges require AI/ML models to generalize to entirely new scenarios not seen during training. However, standard supervised learning is incredibly limited in scenarios, such as designing novel therapeutics, modeling emerging pathogens, and treating rare diseases. In this talk, I present our efforts to overcome these obstacles by infusing structure and knowledge into AI/ML algorithms. First, I will outline general-purpose and scalable algorithms for few-shot learning on graphs. At the core is the notion of local subgraphs that transfer knowledge from one task to another, even when only a handful of labeled examples are available. This principle is theoretically justified as we show the evidence for predictions can be found in subgraphs surrounding the targets. Finally, I will conclude with applications in drug discovery and precision medicine. The algorithmic predictions were validated in human cells and led to discovering a new class of drugs.
Biography: Marinka Zitnik (https://zitniklab.hms.harvard.edu) is an Assistant Professor at Harvard University with appointments in the Department of Biomedical Informatics, Broad Institute of MIT and Harvard, and Harvard Data Science. She is an internationally recognized expert on graph analytics, studying machine learning and applications to science, medicine, and health. Dr. Zitnik has published extensively in top ML venues (e.g., NeurIPS, ICLR, ICML) and leading interdisciplinary journals (e.g., Nature Methods, Nature Communications, PNAS). She has organized numerous conferences in the nexus of AI, deep learning, drug discovery, and medical AI at leading conferences (NeurIPS, ICLR, ICML, ISMB, AAAI, WWW), where she is also in the organizing committees. She is also an ELLIS Scholar in the European Laboratory for Learning and Intelligent Systems (ELLIS) Society. Her research recently won best paper and research awards from the International Society for Computational Biology, Bayer Early Excellence in Science Award, Amazon Faculty Research Award, Rising Star Award in Electrical Engineering and Computer Science (EECS), and Next Generation Recognition in Biomedicine, being the only young scientist with such recognition in both EECS and Biomedicine.