lambda2_calculator {SparseMDC}

Lambda 2 Calculator

Description

Calculates the lambda 2 values for use in the main SparseMDC algorithm, the lambda 2 value controls the number of genes that show condition-dependent expression within each cell type. That is it controls the number of different mean values across the conditions for each cluster. It is calculated by estimating the value of lambda 2 that would result in no difference in mean values across conditions when there are no meaningful differences across between the conditions. For further details please see the original manuscript.

Usage

lambda2_calculator(dat_l, dim, nclust, nboot = 1000, alpha2 = 0.5,
  delta = 1e-07, lambda1)

Arguments

dat_l

list with D entries, each entry contains data d, p * n matrix. This data should be centered and log-transformed.

dim

Total number of conditions, D.

nclust

Total number of clusters.

nboot

The number of bootstrap repetitions for estimating lambda 2, the default value is 1000.

alpha2

The quantile of the bootstrapped lambda 2 values to use, range is (0,1). The default value is 0.5, the median of the calculated lambda 2 values.

delta

Small term to ensure existance of solution, default is 0.0000001.

lambda1

Calcualted penalty parameter for mean size.

Value

The estimated value of lambda2

Examples

set.seed(10)
# Select small dataset for example
data_test <- data_biase[1:100,]
# Split data into condition A and B
data_A <- data_test[ , which(condition_biase == "A")]
data_B <- data_test[ , which(condition_biase == "B")]
data_C <- data_test[ , which(condition_biase == "C")]
# Store data as list
dat_l <- list(data_A, data_B, data_C)
# Pre-process the data
pdat <- pre_proc_data(dat_l, dim=3, norm = FALSE, log = TRUE,
center = TRUE)
lambda1 <- lambda1_calculator(pdat, dim = 3, nclust = 3)
lambda2 <- lambda2_calculator(pdat, dim = 3, nclust = 3, lambda1 = lambda1)