理论物理所

Talks

Location: Home>Activities>Talks

Bridging Data and Dynamics in Single Cells through Machine Learning

03/08 2024 Seminar
  • Title Bridging Data and Dynamics in Single Cells through Machine Learning
  • Speaker Peijie Zhou (Peking University)
  • Date 10:30 Mar. 8, 2024
  • Venue 6620
    • Abstract
     The rapid development of single-cell sequencing technologies provides unprecedented resolutions to study the dynamical process of cell-state transitions during development and complex disease. Mathematically, the transitions can be modeled as a (stochastic) dynamical system with multi-scale structure. In this talk, we will discuss how recent developments in machine learning have allowed us to use dynamical systems techniques to analyze scRNA-seq data. We will introduce the MuTrans algorithm, which uses a low-dimensional dynamical manifold to uncover the underlying attractor basins and transition probabilities in snapshot data. We will also present the spliceJAC algorithms, which use non-equilibrium dynamical systems theory to analyze the stability of attractors within data and identify transition-driving genes in gene expression and splicing processes. Mathematical theory based on the popular splicing analysis method RNA velocity will also be demonstrated. Finally, we will discuss our recent efforts to interpolate non-stationary time-series scRNA-seq data using Wasserstein-Fisher-Rao-metric unbalanced optimal transport and its neural-network-based PDE implementations.

    Biography

    Peijie Zhou is a tenure-track Assistant Professor at the Center for Machine Learning Research at Peking University. He completed his B.S. and Ph.D. degrees in computational mathematics at Peking University in 2014 and 2019, respectively. From 2020 to 2023, he served as a Visiting Assistant Professor in the Department of Mathematics at the University of California, Irvine. His research is anchored in computational systems biology, with recent interest in exploring single-cell data-driven modeling and computation of complex biological systems, merging machine learning methodologies with multiscale dynamical system approaches. His research contributions can be found in interdisciplinary journals such as Nature Communications, Physical Review X, Molecular Systems Biology, Nature Genetics, Nature Machine Intelligence, Nucleic Acids Research, Briefings in Bioinformatics, and the Journal of Chemical Physics. In 2019, Peijie received the Best Ph.D. Thesis Award from Peking University.

    Inviter

    Wei-Kang Wang