scPathway: Infer pathway activation score matrix at single-cell...

In scapGNN: Graph Neural Network-Based Framework for Single Cell Active Pathways and Gene Modules Analysis

Infer pathway activation score matrix at single-cell resolution

Description

Calculate pathway activity score of single-cell by random walk with restart (RWR).

Usage

scPathway(
  network.data,
  gmt.path = NULL,
  pathway.min = 10,
  pathway.max = 500,
  nperm = 50,
  parallel.cores = 2,
  rwr.gamma = 0.7,
  normal_dist = TRUE,
  seed = 1217,
  verbose = TRUE
)

Arguments

network.data	The input network data is the result from the ConNetGNN function.
gmt.path	Pathway database in GMT format.
pathway.min	Minimum size (in genes) for pathway to be considered. Default: 10.
pathway.max	Maximum size (in genes) for database gene sets to be considered. Default: 500.
nperm	Number of random permutations. Default: 50. We recommend the setting of 100.
parallel.cores	Number of processors to use when doing the calculations in parallel (default: 2). If parallel.cores=0, then it will use all available core processors unless we set this argument with a smaller number.
rwr.gamma	Restart parameter. Default: 0.7.
normal_dist	Whether to use pnorm to calculate P values. Default: TRUE.Note that if normal_dist is FALSE, we need to increase nperm (we recommend 100).
seed	Random number generator seed.
verbose	Gives information about each step. Default: TRUE.

Details

scPathway

The scPathway function integrates the results of ConNetGNN into a gene-cell association network. The genes included in each pathway are used as a restart set in the gene-cell association network to calculate the strength of its association with each cell through RWR. Perturbation analysis was performed to remove noise effects in the network and to obtain the final single-cell pathway activity score matrix.

Value

A matrix of single-cell pathway activity score.

Examples

require(parallel)
require(utils)
# Load the result of the ConNetGNN function.
data(ConNetGNN_data)
kegg.path<-system.file("extdata", "KEGG_human.gmt", package = "scapGNN")
# We recommend the use of a compiler.
# The compiler package can be used to speed up the operation.
# library(compiler)
# scPathway<- cmpfun(scPathway)
scPathway_data<-scPathway(ConNetGNN_data,gmt.path=kegg.path,
                          pathway.min=25,nperm=2,parallel.cores=1)

scapGNN documentation built on Aug. 8, 2023, 9:06 a.m.