Advanced Cross-Graph Cycle Attention Model for Dissecting Complex Structures in Mass Spectrometry Imaging

• Published in: Journal of computer science and technology Vol. 40; no. 3; pp. 766 - 779
• Main Authors: Cui, Jiang-Nan, Gao, Yang, Wang, Qiu, Li, Xuan, Xu, Ke-Ren, Huang, Zhen-Yu, Zhang, Jing-Song, Zuo, Chun-Man
• Format: Journal Article
• Language: English
• Published: Singapore Springer Nature Singapore 01.05.2025; Springer Nature B.V
• Subjects: Artificial Intelligence; Computer Science; Data Structures and Information Theory; Graph neural networks; Heterogeneity; Histology; Information Systems Applications (incl.Internet); Mass spectrometry; Noise levels; Regular Paper; Scientific imaging; Software Engineering; Spatial data; Theory of Computation; graph attention autoencoder; mass spectrometry imaging; multimodal data integration; cross-graph cycle attention
• DOI: 10.1007/s11390-025-4342-2
• ISSN: 1000-9000

Joint analysis of multimodalities in spatial mass spectrometry imaging (SMSI) data, including histology, spatial location, and molecule data, allows us to gain novel insights into tissue structures. However, the significant differences in characteristics such as scale and heterogeneity among the multimodal data, coupled with the high noise levels and uneven quality of MSI data, severely hinder their comprehensive analysis. Here, we introduce a cross-graph cycle attention model, MSCG, to learn efficient joint embeddings for multimodalities of SMSI data by integrating graph attention autoencoders and attention-transfer. Specifically, MSCG enables leveraging one modality (e.g., histology) to fine-tune the graph neural network trained for another modality (e.g., MSI). Our study on real datasets from different platforms highlights the superior capacities of MSCG in dissecting cellular heterogeneity, as well as in denoising and aggregating MSI data. Notably, MSCG demonstrates versatile applicability across MSI data from various platforms, showcasing its potential for broad utility in this field.