SpaHDmap: deep fusion of spatial transcriptomics and histology images for interpretable high-definition embedding mapping
SpaHDmap is based on a multi-modal neural network that takes advantage of the high-dimensionality of transcriptomics data and the high-definition of image data to achieve interpretable high-definition dimension reduction. The high-dimensional expression data enable refined functional annotations and the high-definition image data help to enhance the spatial resolution.
Based on the high-definition embedding and the reconstruction of gene expressions, SpaHDmap can then perform high-definition downstream analyses, such as spatial domain detection, gene expression recovery, and identification of embedding-associated genes as well as high-definition cluster-associated genes.
For more details, please refer to our manuscript.
Please install SpaHDmap from pypi with:
pip install SpaHDmapOr clone this repository and use
pip install -e .in the root of this repository.
Please refer to the documentation for more details.