stMMR

stMMR is a multi-modal feature representation approach based on similarity contrastive learning, specifically designed for spatial transcriptomics. stMMR can effectively integrates gene expression, spatial location, and histological imaging information. stMMR uses self-attention module for deep embedding of features within unimodal and incorporates similarity contrastive learning for integrating features across modalities. It demonstrates superior performances in multiple analyses using datasets generated by different platforms, including domain identification, developmental trajectory inference as well as enhancement of gene expression.