时空食管图谱和深度学习能为食管黏膜工程带来哪些见解？

What insights can spatiotemporal esophageal atlases and deep learning bring to engineering the esophageal mucosa?

作者信息

Wang Shuyan, Liu Nianping, Qu Kun

机构信息

Department of Oncology, The First Affiliated Hospital of USTC, School of Basic Medical Sciences, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei 230027, China; School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei 230027, China.

Department of Genetics, Stanford University, Palo Alto, CA 94304, USA.

出版信息

Dev Cell. 2025 May 5;60(9):1279-1280. doi: 10.1016/j.devcel.2025.04.009.

DOI:10.1016/j.devcel.2025.04.009

PMID:40328228

Abstract

In this issue of Developmental Cell, Yang et al. present an integrated experimental and computational platform that maps the spatiotemporal development of the human esophagus and predicts key signaling pathways governing epithelial differentiation. Their findings enable a xeno-free, scalable strategy for generating esophageal mucosa from human pluripotent stem cells (hPSCs), demonstrating the power of combining spatial developmental data with deep learning.

摘要

在本期《发育细胞》杂志中，杨等人展示了一个综合实验和计算平台，该平台绘制了人类食管的时空发育图谱，并预测了控制上皮分化的关键信号通路。他们的研究结果为从人类多能干细胞（hPSC）生成食管黏膜提供了一种无动物源、可扩展的策略，证明了将空间发育数据与深度学习相结合的强大力量。