Identifying prognosis-associated spatial patterns by integrating bulk RNA-seq and spatial transcriptomic data

View at publisher Summarise with VIRAT
Authors: Yuxin Miao, Yanhong Wu, Xinqi Li, Wenbo Guo, Cheng Chen, Jin Gu
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The latest spatial transcriptomics (ST) technology can characterize spatial-resolved intra-tumor heterogeneities, and while large-scale traditional bulk transcriptomic datasets possess valuable clinical phenotype information. To link spatial features with survival information, we present stSurvTrans, a deep transfer learning framework for prognosis-associated spatial patterns identification. stSurvTrans harmonizes bulk RNA sequencing (RNA-seq) and ST data based on conditional variational autoencoder (CVAE), and utilizes a Weibull module to transfer clinical survival information from bulk samples to ST data. We benchmarked stSurvTrans on three simulated datasets, demonstrating its accuracy and superiority. Furthermore, in ST data from hepatocellular carcinoma (HCC), stSurvTrans identified the bile duct tumor thrombus, a spatial structure associated with worse prognosis.

Fields of Study & Subjects

Single-cell and spatial transcriptomics Gene expression and cancer classification Cancer-related molecular mechanisms research

Publication details

Journal / source
IEEE Transactions on Computational Biology and Bioinformatics
Volume
PP
Pages
1–10
Publication date
26 March 2026
Language
EN