S2potAE: multimodal spatial spot autoencoder integrating image and transcriptomic features for deconvolution
Briefings in Bioinformatics · 07.01.2026 · 27 (1)
DOI: 10.1093/bib/bbag020 ↗Kurz gefasst
Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 31.01.2026. Verfasst von Tianyi Chen und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, City University of Hong Kong, Tat Chee Avenue, Kowloon Tong, Kowloon 999077, Hong Kong SAR. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted, Breast Neoplasms, Transcriptome, Gene Expression Profiling. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Scientific Research Innovation Capability Support Project for Young Faculty, National Key Research and Development Program of China, GuangDong Basic and Applied Basic Research Foundation.
Abstract (Originalsprache)
Spatial transcriptomics (ST) technologies have significantly advanced our ability to discern gene expression patterns within intact tissue structures, enabling unprecedented insights into cellular heterogeneity and tissue architecture. However, accurately determining cell-type proportions within spatially aggregated transcriptomic spots remains challenging due to inherent granularity discrepancies, batch effects, and spatial heterogeneity. To address these challenges, we introduce S$^{2}$potAE, a novel spatial spot autoencoder framework that integrates gene expression data, spatial coordinates, and morphological features from histology images for precise spot-level deconvolution. S$^{2}$potAE employs a multilevel feature aggregation strategy, systematically extracting and fusing spatially-aware features through a graph-based spatial encoder and perceptual image embeddings from histological patches. Furthermore, an auxiliary pathological classification task enhances biological relevance and model interpretability. Comprehensive benchmarking across multiple simulated and real datasets—including human breast cancer, mouse brain anterior, and human dorsolateral prefrontal cortex—demonstrates that S$^{2}$potAE consistently surpasses state-of-the-art methods in accuracy, robustness, and biological interpretability. Our approach effectively resolves complex cellular compositions, accurately identifies tumor boundaries, and captures nuanced cell-type distributions, significantly enhancing the utility of ST in biological research and clinical applications.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Computer Science, City University of Hong Kong, Tat Chee Avenue, Kowloon Tong, Kowloon 999077, Hong Kong SAR.
- School of Computer Science and Engineering, South China University of Technology, 381 Wushan Road, Tianhe District, Guangzhou 510006, Guangdong, P.R. China.
- School of Future Technology, South China University of Technology, 777 Xingye Avenue East, Panyu District, Guangzhou, 511442, Guangdong, P.R. China.
- Department of Computer Science, Shantou University, 243 Daxue Road, Jinping District, Shantou 515063, Guangdong, China.
- Department of Bioinformatics, Shantou University Medical College, 22 Xinling Road, Jinping District, Shantou 515041, China.
ORCID-Profile: Tianyi Chen, Yunfei Zhang, Si Wu
Förderung
- Scientific Research Innovation Capability Support Project for Young Faculty
- National Key Research and Development Program of China
- GuangDong Basic and Applied Basic Research Foundation
- TCL Science and Technology Innovation Fund
- Major Special Project for Innovation and R&D in Henan Province
Zitieren
APA
Chen, T., Xue, W., Zhang, Y., Luo, Y., Liu, C., Shen, W., Wu, S., & Wong, H. S. (2026). S2potAE: multimodal spatial spot autoencoder integrating image and transcriptomic features for deconvolution. Briefings in Bioinformatics, 27(1). https://doi.org/10.1093/bib/bbag020
Vancouver
Chen T, Xue W, Zhang Y, Luo Y, Liu C, Shen W, et al. S2potAE: multimodal spatial spot autoencoder integrating image and transcriptomic features for deconvolution. Briefings in Bioinformatics. 2026;27(1). doi:10.1093/bib/bbag020
BibTeX
@article{Chen2026,
author = {Chen, Tianyi and Xue, Wen and Zhang, Yunfei and Luo, Yongcan and Liu, Cheng and Shen, Wenjun and Wu, Si and Wong, Hau-San},
title = {S2potAE: multimodal spatial spot autoencoder integrating image and transcriptomic features for deconvolution},
journal = {Briefings in Bioinformatics},
year = {2026},
volume = {27},
number = {1},
doi = {10.1093/bib/bbag020}
}
EUVIMED