Please note: This seminar will take place in DC 1304.
Yuzhen Ye, Professor
Luddy School of Informatics, Computing, and Engineering, Indiana University Bloomington
Starting with MinPath, which we developed in 2009 to reconstruct biological pathways encoded by microbial communities, our work has focused on creating computational approaches to enable the analysis of multi-omics microbiome data and uncover the structure and function of microbial communities. More recently, we have been developing knowledge-guided AI models designed to be both interpretable and generalizable.
In this talk, I will first highlight several tools we have developed for microbiome research. I will then present two examples of our work on explainable AI models. The first focuses on MicroKPNN and MicroKPNN-MT, designed for microbiome-based host phenotype prediction. These models incorporate prior knowledge including microbial community structure directly into their neural network architectures. The second example introduces DCTdomain, a domain-based embedding approach that captures the contextual information of protein domains, the fundamental structural and functional units of proteins. We show that these domain-level embeddings enable rapid and accurate detection of protein similarity, and can be effectively leveraged for viral taxonomic assignment, a challenging task due to the high divergence of viruses.
Bio: Dr. Ye is a Professor in the Computer Science Department at the Luddy School of Informatics, Computing, and Engineering at Indiana University Bloomington, where she has served as Department Chair since 2019. She earned her Ph.D. in Computational Biology from the Chinese Academy of Sciences in 2001. Her research centers on bioinformatics and metagenomics, with a particular focus on developing algorithms and AI models to tackle complex biological problems.
Dr. Ye received the NSF CAREER Award in 2009, and her research has been continuously supported by grants from the NIH and NSF. In addition to her research, Dr. Ye teaches courses such as Introduction to Computers and Programming, Data Mining, and Data Structures. She also enjoys engaging with pre-college students through a variety of outreach activities.