RT Journal Article
SR Electronic
T1 STAIG: Spatial Transcriptomics Analysis via Image-Aided Graph Contrastive Learning for Domain Exploration and Alignment-Free Integration
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 2023.12.18.572279
DO 10.1101/2023.12.18.572279
A1 Yang, Yitao
A1 Cui, Yang
A1 Zeng, Xin
A1 Zhang, Yubo
A1 Loza, Martin
A1 Park, Sung-Joon
A1 Nakai, Kenta
YR 2024
UL http://biorxiv.org/content/early/2024/01/02/2023.12.18.572279.abstract
AB Spatial transcriptomics is an essential application for investigating cellular structures and interactions and requires multimodal information to precisely study spatial domains. Here, we propose STAIG, a novel deep-learning model that integrates gene expression, spatial coordinates, and histological images using graph-contrastive learning coupled with high-performance feature extraction. STAIG can integrate tissue slices without prealignment and remove batch effects. Moreover, it was designed to accept data acquired from various platforms, with or without histological images. By performing extensive benchmarks, we demonstrated the capability of STAIG to recognize spatial regions with high precision and uncover new insights into tumor microenvironments, highlighting its promising potential in deciphering spatial biological intricates.Competing Interest StatementThe authors have declared no competing interest.