M2ST: Dissecting spatial domains in spatial transcriptomics by a masked graph attention autoencoder

M2ST is implemented in the pytorch framework (tested on Python 3.9.19). We recommend that users run M2ST on CUDA.Tutorial: 1. Download the M2ST_F.py and gat_conv2.py.2. Tutorial for domain identification on 10x Visium human dorsolateral prefrontal cortex (DLPFC) dataset can be found: Train_151674.ipynb.3. The datasets for the Tutorial Train_151674.ipynb can be found in the data/151674 Folder.4. The domain identification results of the Tutorial Train_151674.ipynb can be found in the data/result Folder.