stMMR: accurate and robust spatial domain identification from spatially resolved transcriptomics with multi-modal feature representation

Abstract

Characterizing and understanding the structure of tissues from spatially resolved transcriptomics (SRT) is of great value for deciphering the functionality of spatial domains. However, the inherent heterogeneity and varying spatial resolutions among SRT multi-modal data present challenges in the joint analysis of these modalities. In this study, we introduce a multi-modal feature representation method, named stMMR, to effectively integrate gene expression, spatial location and histological imaging information for accurate identifying spatial domains from SRT data. stMMR uses self-attention module for deep embedding of features within unimodal and incorporates similarity contrastive learning for integrating features across modalities. stMMR demonstrates superior performances in multiple analyses using datasets generated by different platforms, including spatial domain identification, pseudo-spatiotemporal analysis as well as domain-specific gene discovery. Using stMMR, we systematically analyzed the evolving lineage structures of the chicken heart and conducted an in-depth examination of domain-specific genes in breast cancer and lung cancer. In conclusion, stMMR is capable of effectively integrating the multi-modal information for spatial domain identification and exhibits superior adaptability as well as stability in handling different types of SRT data.

STEP: Spatial Transcriptomics Embedding Procedure for Multi-scale Biological Heterogeneities Revelation in Multiple Samples

“…Cell clustering, aiming to differentiate cells by cell types (Chidester et al, 2023; Li et al, 2022; Miller et al, 2021; Teng et al, 2022); 2. Spatial domain identification for discovery of biologically functional regions with a certain degree of spatial continuity in tissues (Dong & Zhang, 2022; Hu et al, 2021; Hu et al, 2024; Li & Zhou, 2022; Liu et al, 2023; Long et al, 2023; Shang & Zhou, 2022; Yang et al, 2024; Yu et al, 2023; Zhang et al, 2024; Zhao et al, 2021). The significant improvements can be observed on solving these two tasks in the single section scenario for a specific data resolution.…”

“…A batch-embedding based paired transformation model (BEM), introducing an unparalleled batch-correction technique that operates independently from BBM and delineates a new direction in handling batch variations; and 3. A spatial model (SpM) leveraging the graph convolutional network (GCN) (Kipf & Welling, 2017) distinctively applied to low-dimensional embeddings as a spatial filter or smoother rather than direct gene expression data as a feature extractor (Dong & Zhang, 2022; Gao et al, 2024; Hu et al, 2021; Long et al, 2023; Yu et al, 2023; Zhang et al, 2024; Zhou et al, 2023)—a first in the field. This innovative use of GCN significantly reduces noise, effectively capturing spatial contexts and variations with enhanced biological relevance.…”