SpaMI 1.0.0

A spatial multi-omics data integration tool

To integrate spatial transcriptome data more efficiently, we introduce the SpaMI method. It is an efficient and universally applicable deep learning method designed for the integrated representation of spatial multimodal data from the same tissue section. The method is able to take into account the heterogeneity of data from different histologies, preserve the biological significance of different histologies, and organically integrate the data so that the integrated data can reveal more comprehensive biological features, providing a comprehensive and complementary perspective for understanding cell expression patterns and spatial organization.

If you want to use GPU to train the model, please download and install cuDNN from NVIDIA official website (https://developer.nvidia.com/cudnn) according to your GPU and system configuration.