Cell-type Annotation for Single-cell Transcriptomics using Deep Learning with a Weighted Graph Neural Network
All pre-processed data are available here in the form of readily-for-analysis for researchers to develop new methods.
human_cell_atlas.7z
contains 198 csv
files involving 562,977 cells and 56 tissues from HCL
mouse_cell_atlas.7z
contains 126 csv
files involving 201,764 cells and 32 tissues from MCA
human_test_data.7z
contains 54 csv
files involving 130,885 cells and 10 tissues.mouse_test_data.7z
contains 128 csv
files involving 134,604 cells and 12 tissues.Each dataset contains two csv
files.
_data.csv
file contains single-cell gene expression data matrix, wherein the first column represents gene names and the first row represents cell id._celltype.csv
file contains cell type information for each cell, wherein the first column represents cell id and the second column represents the cell type.Release Python package of scDeepSort