iIMPACT: integrating image and molecular profiles for spatial transcriptomics analysis

• Published in: Genome Biology Vol. 25; no. 1; pp. 147 - 25
• Main Authors: Jiang, Xi, Wang, Shidan, Guo, Lei, Zhu, Bencong, Wen, Zhuoyu, Jia, Liwei, Xu, Lin, Xiao, Guanghua, Li, Qiwei
• Format: Journal Article
• Language: English
• Published: England BioMed Central 06-06-2024; BMC
• Subjects: AI-reconstructed histology image; Breast cancer; Cluster Analysis; Clustering; Data analysis; Datasets; Functional morphology; Gene expression; Gene Expression Profiling - methods; Histology; Humans; Image Processing, Computer-Assisted - methods; Markov random field; Method; Morphology; Neural networks; Parameter estimation; Spatial clustering; Spatially resolved transcriptomics; Spatially variable gene; Statistical methods; Transcriptome; Transcriptomics; Spatial clustering; Markov random field; Spatially resolved transcriptomics; AI-reconstructed histology image; Spatially variable gene
• ISSN: 1474-760X; 1474-7596; 1474-760X
• DOI: 10.1186/s13059-024-03289-5

Current clustering analysis of spatial transcriptomics data primarily relies on molecular information and fails to fully exploit the morphological features present in histology images, leading to compromised accuracy and interpretability. To overcome these limitations, we have developed a multi-stage statistical method called iIMPACT. It identifies and defines histology-based spatial domains based on AI-reconstructed histology images and spatial context of gene expression measurements, and detects domain-specific differentially expressed genes. Through multiple case studies, we demonstrate iIMPACT outperforms existing methods in accuracy and interpretability and provides insights into the cellular spatial organization and landscape of functional genes within spatial transcriptomics data.