createSimulation2: createSimulation2 update to createSimulation2() that allows...

In insilico/npdr: Nearest-neighbor Projected-Distance Regression

createSimulation2 update to createSimulation2() that allows for rs-fMRI data generation.

Description

Changes: only an additional input with conditional if/else statements wherever an igraph object is generated. Will allow for user-supplied graph object as well, this functionality requires an igraph object specifically for now.

Usage

createSimulation2(
  num.samples = 100,
  num.variables = 100,
  pct.imbalance = 0.5,
  pct.signals = 0.1,
  main.bias = 0.4,
  interaction.bias = 0.4,
  hi.cor = 0.8,
  lo.cor = 0.2,
  label = "class",
  sim.type = "mainEffect",
  pct.train = 0.5,
  pct.holdout = 0.5,
  pct.validation = 0,
  save.file = NULL,
  mix.type = NULL,
  pct.mixed = 0.5,
  verbose = FALSE,
  plot.graph = FALSE,
  use.Rcpp = FALSE,
  prob.connected = NULL,
  out.degree = NULL,
  data.type = "continuous",
  avg.maf = 0.2,
  graph.structure = NULL
)

Arguments

num.samples	number of samples
num.variables	number of variables (features)
pct.imbalance	fraction of num.samples that are cases
pct.signals	fraction of num.variables that are functional
main.bias	approximate effect size for main effect simulations
interaction.bias	approximate effect size for interaction effects
hi.cor	parameter to use for network-connected pairwise correlations
lo.cor	parameter to use for network-non-connected pairwise correlations
label	should just be "class" for binary response
sim.type	a character that determines the type of simulation: mainEffect/mainEffect_Erdos-Renyi/mainEffect_Scalefree/interactionErdos/interactionScalefree/mixed
pct.train	fraction of num.samples used for training
pct.holdout	fraction of num.samples used for holdout
pct.validation	fraction of num.samples used for validation
save.file	logical but not currently being used
mix.type	character that determines the type of mixed effects simulation: main-interactionErdos/main-interactionScalefree
pct.mixed	percent of functional variables that are main effects (1 - pct_interaction). Use with sim.type="mixed" and specify mix.type.
verbose	logical indicating whether to display time required to generate simulation
plot.graph	logical indicating whether to plot networks
use.Rcpp	if true use Rcpp to correct negative eigenvalues
prob.connected	probability of drawing an edge between two arbitrary vertices in Erdos-Renyi graph
out.degree	out-degree of vertices in Scale-free graph
data.type	character indicating if data is from a "continuous" or "discrete" distribution
avg.maf	numeric in (0,1) indicating the desired average MAF for GWAS main effect simulations
graph.structure	(igraph) graph structure generated from igraph, NULL default

Details

New Parameter:

graph.structure - (igraph) graph structure generated from igraph. If NULL, then createSimulation2() typically generates one on its own. However, this will be handled by createfMRIsimulation() and the user will not be using createSimulation2() directly. This input is used to circumvent automatic simulation of graphs by the previous iteration of createSimulation2().

Value

A list with:

train

traing data set

holdout

holdout data set

validation

validation data set

label

the class label/column name

signal.names

the variable names with simulated signals

elapsed

total elapsed time

A.mat

adjacency matrix for random network (for interaction/mixed/main plus correlation)

main.vars

indices of main effect variables (for mixed simulations)

int.vars

indices of interaction effect variables (for mixed simulations)

Examples

# main effects with correlation from Erdos-Renyi network (continuous)

num.samples <- 100
num.variables <- 10

dataset <- createSimulation2(
  num.samples = num.samples,
  num.variables = num.variables,
  pct.imbalance = 0.5,
  pct.signals = 0.2,
  main.bias = 0.4,
  interaction.bias = 1,
  hi.cor = 0.8,
  lo.cor = 0.2,
  mix.type = "main-interactionErdos",
  label = "class",
  sim.type = "mainEffect_Erdos-Renyi",
  pct.mixed = 0.5,
  pct.train = 0.5,
  pct.holdout = 0.5,
  pct.validation = 0,
  plot.graph = FALSE,
  verbose = TRUE,
  data.type = "continuous"
)

# main effects with correlation from Erdos-Renyi network

num.samples <- 100
num.variables <- 10

dataset <- createSimulation2(
  num.samples = num.samples,
  num.variables = num.variables,
  pct.imbalance = 0.5,
  pct.signals = 0.2,
  main.bias = 0.4,
  interaction.bias = 1,
  hi.cor = 0.8,
  lo.cor = 0.2,
  mix.type = "main-interactionErdos",
  label = "class",
  sim.type = "mainEffect_Erdos-Renyi",
  pct.mixed = 0.5,
  pct.train = 0.5,
  pct.holdout = 0.5,
  pct.validation = 0,
  plot.graph = FALSE,
  verbose = TRUE,
  data.type = "discrete"
)

insilico/npdr documentation built on July 6, 2023, 1:14 p.m.