BIMSA >
Seminar on Bioinformatics
Introduction to cell representation learning via contrastive learning
Introduction to cell representation learning via contrastive learning
Organizer
Speaker
(Tsinghua) Tao Zhou
Time
Thursday, January 4, 2024 9:00 PM - 9:30 PM
Venue
Online
Abstract
ScRNA-seq methods generate a wealth of high-dimensional data characterizing the heterogeneity of cell populations. Representation learning methods are routinely used to analyze these complex, high-dimensional data by projecting them into lower dimensional embeddings. This facilitates the interpretation and interrogation of the structures, dynamics, and regulation of cell heterogeneity. This week, we will focus on contrastive learning methods and introduce some of the latest work in this field. By understanding the latest methods, it helps us to further explore the possibility of applying the natural vector method in single-cell data representation in the future.