The dual-enhanced graph learning framework DePass allows paired data integration in single-cell and spatial multiomics V.1 v1

DePass is a dual-enhanced graph learning framework designed for integrated analysis of both single-cell and spatial paired multi-omics data. It flexibly supports diverse modality combinations. This protocol provides a minimal reproducible pipeline using Visium-MALDI mouse brain RNA-metabolite paired spatial data (demo dataset link: https://drive.google.com/drive/folders/1OoChH4cbJgPsgIcl5jx66iHb0of3XykM?usp=drive_link or https://doi.org/10.5281/zenodo.21736075). We cover full environment setup, data preprocessing, model training, spatial domain clustering and quantitative evaluation. Comprehensive interactive Jupyter notebooks for all benchmark datasets are hosted on GitHub: https://github.com/zhanglabNKU/DePass