run_SNF: Run similarity network fusion

In ProfessionalFarmer/loonR: Common function in bioinformatics analysis

Run similarity network fusion

Description

Run similarity network fusion

Usage

run_SNF(
  dataL = NULL,
  alpha = 0.5,
  K = 20,
  Iterations = 20,
  dist.method = "Euclidean",
  survival = NA,
  max.cluster = 5,
  std.normalize = TRUE,
  cnv.index = 0
)

Arguments

dataL	list( t(mRNA.snf.df), t(methylation.snf.df), t(cnv.snf.df) )
alpha	Default 0.5. hyperparameter, usually (0.3~0.8) Variance for local model
K	Default 20. Number of neighbors, must be greater than 1. usually (10~30) 20
Iterations	T.Default 20. Number of Iterations, usually (10~50)
dist.method	Default Euclidean. pearson, spearman, kendall
survival	Must a data frame. colnames OS.time, OS.event, RFS.time, RFS.event. Rownames must be sample name. Two columns or four columns.
std.normalize	Default TRUE
cnv.index	Default 0. If CNV data index is specified, Euclidean will be used to calculate distance

Examples

run_SNF( list( t(mRNA.snf.df), t(methylation.snf.df), t(cnv.snf.df) ),  alpha = 0.5, K = 20, Iterations = 20    )
https://cran.r-project.org/web/packages/SNFtool/SNFtool.pdf
Distance reference: https://www.rdocumentation.org/packages/bioDist/versions/1.44.0

ProfessionalFarmer/loonR documentation built on Oct. 9, 2024, 9:56 p.m.