Interpretable high-resolution dimension reduction of spatial transcriptomics data by DeepFuseNMF
Year: 2024
Type: article
Abstract: Description DeepFuseNMF is a tool designed to generate interpretable high-resolution representations of spatial transcriptomics data by integrating high-resolution histology images. This project provides: Raw and processed data, including spatial transcriptomics data, high-resolution histology images, and normalized expression profiles with pre-determined genes. The associated analysis code. Dataset This project analyzes data from four major studies: Simulation Studies: Includes two synthetic datasets. Mouse Brain Study: Includes data from five slices. Patient-Derived Orthotopic Xenograft Mice Study: Includes data from four slices. Human Colorectal Cancer Study: Includes data from three patients. A detailed description of each dataset is available in the “Data Description.xlsx” file. The prepared data for downstream analysis can be found in each study's “usedata” sub-folder. Analysis Code The analysis code for each study is implemented in Python and R and can be found in the “code” sub-folder. Document and tutorial for running the analysis code is available at https://deepfusenmf.readthedocs.io. Contact Information Junjie Tang: [email protected] Ruibin Xi: [email protected]
Authors: Tang, Junjie, Chen, Zihao
Language: English
Subfield: Molecular Biology
Domain: Life Sciences
Open Access status: green
OpenAlex ID: W6911863479