Technological advances in spatial transcriptomics are critical for a better understanding of the structure and function of tissues in biological research. Recently, the combination of intelligent/statistical algorithms and spatial transcriptomics are emerging to pave the way for deciphering tissue architecture. In this talk, I will introduce our efforts to advance intelligent spatial transcriptomics. We first develop a graph attention auto-encoder framework STAGATE to accurately identify spatial domains by learning low-dimensional latent embeddings via integrating spatial information and gene expression profiles. We validate STAGATE on diverse spatial transcriptomics datasets generated by different platforms with different spatial resolutions. STAGATE could substantially improve the identification accuracy of spatial domains, and denoise the data while preserving spatial expression patterns. Importantly, STAGATE could be extended to multiple consecutive sections to reduce batch effects between sections and extracting three-dimensional (3D) expression domains from the reconstructed 3D tissue effectively. Based on this, we further 1) demonstrate the effectiveness of the graph attention auto-encoder for spatial clustering of spatial metabolomics, 2) develop STAMarker for identifying spatial domain-specific variable genes and 3) design STAligner for integrating spatial transcriptomics of multiple slices from diverse biological scenarios.