Decoding cellular dynamics from single-cell genomics data is pivotal for understanding disease mechanisms and exploring potential therapeutic strategies. Nevertheless, the prohibitive cost of single-cell genomics prevents the adoption of single-cell genomics for large-scale sequencing studies. Further, the complexities of single-cell genomics and spatial transcriptomics data make it challenging to examine the interaction dynamics between different cells. To facilitate the wider utilization of single-cell sequencing and accurate inference of cell-cell interactions, computational methods such as deep generative neural networks and agent-based models play ever-increasing important roles. In this talk, we will discuss a set of computational frameworks that we developed to promote the cost-effective utilization of single-cell omics for large-scale cohort studies. We will also cover an agent-based modeling strategy to infer the interaction cellular dynamics between various cells in the sample and identify cell interaction-based therapeutics.

报告人简介：Jun Ding is an Assistant Professor in the Department of Medicine and MILA-Quebec AI Institute at McGill University since March 2021. He is also a FRQS Junior 1 scholar in AI healthcare. Previously, Jun completed his postdoctoral training at the Computational Biology Department, School of Computer Science, Carnegie Mellon University, under the guidance of Dr. Ziv Bar-Joseph. In 2016, he obtained his Ph.D. in Computer Science from the University of Central Florida.

Jun's research primarily revolves around the development of computational methods to gain insights into cellular dynamics across various biological processes using single-cell multi-omics data. Leveraging the power of single-cell and machine learning technologies, his research focuses on understanding disease progression and identifying drugs and compounds for pulmonary diseases. Jun has published over 30 papers in leading computational biology journals, including Genome Research and Cell Stem Cell, with a significant portion dedicated to machine learning approaches for decoding cellular dynamics from single-cell datasets. Many of his computational models have paved the way for significant advancements in the field of biomedicine.