Graph Neural Network-Based Framework for Single Cell Active Pathways and Gene Modules Analysis
BIC_LTMG
BIC_ZIMG
Construct association networks for gene-gene, cell-cell, and gene-cell...
Identify cell phenotype activated gene module
Create the create_scapGNN_env environment on miniconda
Fitting function for Left-truncated mixed Gaussian
Global_Zcut
Install the pyhton module through the reticulate R package
Integrate network data from single-cell RNA-seq and ATAC-seq
The internal functions of the scapGNN package
load pathway or gene set's gmt file
An S4 class to represent the input data for LTMG.
Left-truncated mixed Gaussian
Visualize cell cluster association network graph
Visualize gene association network graph of a gene module or pathway a...
Visualize gene association network graph for activated gene modules un...
Data preprocessing
Pure_CDF
Run Left-truncated mixed Gaussian
Function that performs a random Walk with restart (RWR) on a given gra...
Infer pathway activation score matrix at single-cell resolution
It is a single cell active pathway analysis tool based on the graph neural network (F. Scarselli (2009) <doi:10.1109/TNN.2008.2005605>; Thomas N. Kipf (2017) <arXiv:1609.02907v4>) to construct the gene-cell association network, infer pathway activity scores from different single cell modalities data, integrate multiple modality data on the same cells into one pathway activity score matrix, identify cell phenotype activated gene modules and parse association networks of gene modules under multiple cell phenotype. In addition, abundant visualization programs are provided to display the results.