- Title：SAIR-T-030:Graph Neural Network Frameworks for Single Cell and Spatial Transcriptomics Data Analysis and Biological Discoveries
- Date：9:00pm US East time, 12/23/2023
- Date：10:00am Beijing time, 12/24/2023
- Zoom ID：933 1613 9423
- Zoom PWD：416262
- Zoom:https://uwmadison.zoom.us/meeting/register/tJcudu-prTIuGNda1MsF8PKyRQlnGn06TP2E
MAIB: Manifold learning, Artificial Intelligence, Biology Forum (MAIB)
Presentation Record(Previous Presentation will be showed here if the video is not released for this talk)
*Dr. Juexin Wang is an assistant professor at the Department of BioHealth Informatics at Luddy School of Informatics, Computation, and Engineering at Indiana University Purdue University Indianapolis since August 2022. He obtained a Master’s and Ph.D. in computer science from Jilin University in China and finished bioinformatics training at the University of Missouri. Dr. Wang’s research interest is machine learning and deep learning modeling single-cell multi-omics and spatial omics, and their applications in cancer, Alzheimer’s disease, and kidney disease. Some of his presentative works are published in Nature Communications and Bioinformatics, and highlighted as featured articles in Nature Communications’ Biotechnology and Methods Focus session. Wang’s research is currently supported by NIH.
Background
Emerging single cell and spatial omics technologies provide unprecedented opportunities and challenges for biologists. In this talk, I will talk about some of my recent works using machine learning to address some of the fundamental challenges in spatial omics, including (1) scGNN, one of the first graph neural networks modeling scRNA-seq data, (2) RESEPT, visualizing spatial transcriptomics data using graph representation learning; (3) BSP, a granularity-based data-driven approach to identify spatial variable genes in 2D and 3D spatial transcriptomics data; and some other machine learning works.
