太阳集团见好就收9728定量生物学中心

学术报告 

题    目: Machine learning cell dynamics

报告人: Ming HAN, Ph.D.

Kadanoff-Rice Postdoctoral Fellow

James Franck Institute and Pritzker School of Molecular Engineering

The University of Chicago

时    间: 3月29日（周二）上午9:30-10:30

地    点: ZOOM线上报告

Meeting ID: 746 492 6744

Password：654321

主持人: 林杰 研究员

摘 要:

The dynamics of a multicellular tissue is the consequence of collective motions across multiple length and time scales. At the single-cell level, collections of macromolecules self-organize into sub-cellular machines to drive the morphogenesis, migration, and division of the cell. At the tissue level, those cellular behaviors are coordinated by mechanical stresses and chemical signaling between the cells. A fundamental challenge of cell dynamics is to build predictive models that map the high dimensional information about intracellular molecules and intercellular interactions onto low dimensional physical descriptions of biological matter. In this talk, I will present a multiscale machine-learning pipeline for the study of cell dynamics. In particular, I will show how to identify key molecular inputs for cellular dynamics of interest as well as how to forecast multicellular dynamics from geometric information of the cells that is easily accessible in experiment.

报告人简介：

Ming Han obtained his B.S. in Physics & Applied Mathematics from Shanghai Jiao Tong University，and Ph.D. in Applied Physics from Northwestern University. In 2018, he joined Prof. Vincenzo Vitelli’ lab at the James Franck Institute at the University of Chicago. His previous works are solving forward problems guided by statistical mechanics. Now he is leaning more towards the use of machine learning (ML) to understand biological.