Graph representation learning, generation, and application in network medicine
Visiting speaker
Yang Shen
Associate Professor, Department of Electrical and Computer Engineering, Texas A&M University
Past Talk
Hybrid talk
Friday
Mar 31, 2023
Watch video
3:30 pm
Virtual
177 Huntington Ave.
11th floor
Online
Register here
From molecules of bonded atoms to networks of interacting genes, graph-structured data is ubiquitous throughout the hierarchy of living systems. In this talk, I will introduce our recent efforts in graph machine learning (GraphML) to address major computational challenges, with motivating applications in network medicine. (1) We ask how to learn generalizable, transferrable, and robust representation of graphs, especially when their labels tend to be of limited quantity, quality, and transferability in biomedicine. Our answers are pioneering works of self-supervised graph learning methods that make use of unlabeled graphs through predictive, contrastive, and automated pre-training tasks. (2) We ask how to generate chemical graphs specifically to target disease modules of interactomes. Our answers are hierarchical embedding of disease modules and conditional generative models, with the guidance of a network medicine principle. Other ongoing works in GraphML will also be mentioned if time permits.
About the speaker
About the speaker
Dr. Yang Shen is an associate professor in the Department of Electrical and Computer Engineering at Texas A&M University (TAMU). He is also an affiliated faculty member in the Department of Computer Science and Engineering and at the Institute of Biosciences and Technologies. His research interests are optimization, uncertainty quantification, and multimodal machine learning for modeling biological molecules, systems, and data. These algorithms have been used in biomedicine applications such as prediction and design of protein interactions, de novo protein design, mechanistic prediction of protein variation effects, and resistance-overcoming drug discovery. Dr. Shen received his B.E. from the University of Science and Technology of China, his Ph.D. in Systems Engineering from Boston University, and postdoctoral training in Biological Engineering and Computer Science at the Massachusetts Institute of Technology. Prior to joining TAMU, he was a research assistant professor at the Toyota Technological Institute at Chicago. He is a recipient of the MIRA award for early-stage investigators from the National Institute of General Medical Sciences (2017) and the CAREER award from the National Science Foundation (2020).
Dr. Yang Shen is an associate professor in the Department of Electrical and Computer Engineering at Texas A&M University (TAMU). He is also an affiliated faculty member in the Department of Computer Science and Engineering and at the Institute of Biosciences and Technologies. His research interests are optimization, uncertainty quantification, and multimodal machine learning for modeling biological molecules, systems, and data. These algorithms have been used in biomedicine applications such as prediction and design of protein interactions, de novo protein design, mechanistic prediction of protein variation effects, and resistance-overcoming drug discovery. Dr. Shen received his B.E. from the University of Science and Technology of China, his Ph.D. in Systems Engineering from Boston University, and postdoctoral training in Biological Engineering and Computer Science at the Massachusetts Institute of Technology. Prior to joining TAMU, he was a research assistant professor at the Toyota Technological Institute at Chicago. He is a recipient of the MIRA award for early-stage investigators from the National Institute of General Medical Sciences (2017) and the CAREER award from the National Science Foundation (2020).