library(magrittr)
# simulation parameters
rho = 0.90; p = 500 ;SNR = 1 ; n = 200; n0 = n1 = 100 ; nActive = p*0.10 ; cluster_distance = "tom";
Ecluster_distance = "difftom"; rhoOther = 0.6; betaMean = 2;
alphaMean = 1; betaE = 3; distanceMethod = "euclidean"; clustMethod = "hclust";
cutMethod = "dynamic"; agglomerationMethod = "average"
#in this simulation its blocks 3 and 4 that are important
#leaveOut: optional specification of modules that should be left out
#of the simulation, that is their genes will be simulated as unrelated
#("grey"). This can be useful when simulating several sets, in some which a module
#is present while in others it is absent.
d0 <- s_modules(n = n0, p = p, rho = 0, exposed = FALSE,
modProportions = c(0.15,0.15,0.15,0.15,0.15,0.25),
minCor = 0.01,
maxCor = 1,
corPower = 1,
propNegativeCor = 0.3,
backgroundNoise = 0.5,
signed = FALSE,
leaveOut = 1:4)
d1 <- s_modules(n = n1, p = p, rho = rho, exposed = TRUE,
modProportions = c(0.15,0.15,0.15,0.15,0.15,0.25),
minCor = 0.4,
maxCor = 1,
corPower = 0.3,
propNegativeCor = 0.3,
backgroundNoise = 0.5,
signed = FALSE)
truemodule1 <- d1$setLabels
X <- rbind(d0$datExpr, d1$datExpr) %>%
magrittr::set_colnames(paste0("Gene", 1:p)) %>%
magrittr::set_rownames(paste0("Subject",1:n))
betaMainEffect <- vector("double", length = p)
betaMainInteractions <- vector("double", length = p)
# the first nActive/2 in the 3rd block are active
betaMainEffect[which(truemodule1 %in% 3)[1:(nActive/2)]] <- runif(
nActive/2, betaMean - 0.1, betaMean + 0.1)
# the first nActive/2 in the 4th block are active
betaMainEffect[which(truemodule1 %in% 4)[1:(nActive/2)]] <- runif(
nActive/2, betaMean+2 - 0.1, betaMean+2 + 0.1)
betaMainInteractions[which(betaMainEffect!=0)] <- runif(nActive, alphaMean - 0.1, alphaMean + 0.1)
beta <- c(betaMainEffect, betaE, betaMainInteractions)
result <- s_generate_data(p = p, X = X,
beta = beta,
include_interaction = TRUE,
cluster_distance = cluster_distance,
n = n, n0 = n0,
eclust_distance = Ecluster_distance,
signal_to_noise_ratio = SNR,
distance_method = distanceMethod,
cluster_method = clustMethod,
cut_method = cutMethod,
agglomeration_method = agglomerationMethod,
nPC = 1)
pen_res <- s_pen_clust(x_train = result[["X_train"]],
x_test = result[["X_test"]],
y_train = result[["Y_train"]],
y_test = result[["Y_test"]],
s0 = result[["S0"]],
gene_groups = result[["clustersAddon"]],
summary = "pc",
model = "lasso",
exp_family = "gaussian",
clust_type = "ECLUST",
include_interaction = TRUE)
unlist(pen_res)
Run the code above in your browser using DataLab