enhancement request: streamline multiblock functions by removing scheme and init args

[evaham1]

Is your feature request related to a problem? Please describe.

In the multiblock functions you can choose the scheme and for the horst scheme you can choose the init (svd.single or svd). As discussed with Kim-Anh today users only use the horst scheme so lets hardcode this scheme into the function. init is by default svd.single but lets hardcode it as whichever runs faster.

This will streamline this function and prevent confusion as these additional arguments are not described/explained extensively in documentation.

Functions that this affects:
✅ block.pls()
✅ block.spls()
✅ block.plsda()
✅ block.splsda() == wrapper.sgccda()
✅ mint.block.pls()
✅ mint.block.spls()
✅ mint.block.plsda()
✅ mint.block.splsda()
✅ wrapper.rgcca()
✅ wrapper.sgcca()

Process:

✅ Check whether svd.single or svd runs faster for each function

• Hardcode scheme = horst and init = svd.single
• Update docs
• Update unit tests
• Propagate changes through other functions e.g. perf() and tune()
• Check if there is anything in website/book about the schemes and update there

[evaham1]

Comparing run time of svd versus svd.single

Basically shows very little difference in runtime so will stick to svd.single.
Note for block.pls and block.spls the default was svd.single and for block.plsda and block.splsda the default was svd.

library(mixOmics)
library(microbenchmark)

## block.pls
data("breast.TCGA")
data = list(mrna = breast.TCGA$data.train$mrna, mirna = breast.TCGA$data.train$mirna)
design = matrix(1, ncol = length(data), nrow = length(data),
                dimnames = list(names(data), names(data)))
diag(design) =  0
design

system.time(
  block.pls(X = data, Y = breast.TCGA$data.train$protein, 
                           ncomp = 2, design = design, init = "svd.single")
)
# user  system elapsed 
# 0.013   0.001   0.013 

system.time(block.pls(X = data, Y = breast.TCGA$data.train$protein, 
                           ncomp = 2, design = design, init = "svd")
)
# user  system elapsed 
# 0.020   0.001   0.021 

## block.plsda
data(nutrimouse)
data = list(gene = nutrimouse$gene, lipid = nutrimouse$lipid, Y = nutrimouse$diet)
design = matrix(c(0,1,1,1,0,1,1,1,0), ncol = 3, nrow = 3,
                byrow = TRUE, dimnames = list(names(data), names(data)))

system.time(
  block.plsda(X = data, indY = 3, init = "svd.single")
)
# user  system elapsed 
# 0.006   0.000   0.006 
system.time(
  block.plsda(X = data, indY = 3, init = "svd")
)
# user  system elapsed 
# 0.005   0.000   0.005 

## mint.block.pls
study <- c(rep("study1", 100), rep("study2", 50))
data <- list(mrna = breast.TCGA$data.train$mrna, mirna = breast.TCGA$data.train$mirna)
design <- matrix(1, ncol = length(data), nrow = length(data), dimnames = list(names(data), names(data)))
diag(design) <-  0

system.time(
  mint.block.pls(data, Y = breast.TCGA$data.train$protein, study = study, ncomp = 2, init = "svd.single")
)
# user  system elapsed 
# 0.014   0.001   0.015 
system.time(
  mint.block.pls(data, Y = breast.TCGA$data.train$protein, study = study, ncomp = 2, init = "svd")
)
# user  system elapsed 
# 0.022   0.001   0.022 

## mint.block.plsda
study <- c(rep("study1",150), rep("study2",70))
mrna <- rbind(breast.TCGA$data.train$mrna, breast.TCGA$data.test$mrna)
mirna <- rbind(breast.TCGA$data.train$mirna, breast.TCGA$data.test$mirna)
Y <- c(breast.TCGA$data.train$subtype, breast.TCGA$data.test$subtype)
data <- list(mrna = mrna, mirna = mirna)

system.time(
  mint.block.plsda(data, Y, study = study, ncomp = 2, init = "svd.single")
)
# user  system elapsed 
# 0.013   0.000   0.013 
system.time(
  mint.block.plsda(data, Y, study = study, ncomp = 2, init = "svd")
)
# user  system elapsed 
# 0.011   0.001   0.011 

## session info
sessionInfo()
# R version 4.4.1 (2024-06-14)
# Platform: aarch64-apple-darwin20
# Running under: macOS 15.1
# 
# Matrix products: default
# BLAS:   /System/Library/Frameworks/Accelerate.framework/Versions/A/Frameworks/vecLib.framework/Versions/A/libBLAS.dylib 
# LAPACK: /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/lib/libRlapack.dylib;  LAPACK version 3.12.0
# 
# locale:
#   [1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
# 
# time zone: Australia/Melbourne
# tzcode source: internal
# 
# attached base packages:
#   [1] stats     graphics  grDevices utils     datasets  methods   base     
# 
# other attached packages:
#   [1] mixOmics_6.29.3 ggplot2_3.5.1   lattice_0.22-6  MASS_7.3-61    
# 
# loaded via a namespace (and not attached):
#   [1] Matrix_1.7-1        gtable_0.3.6        dplyr_1.1.4         compiler_4.4.1      tidyselect_1.2.1    Rcpp_1.0.13        
# [7] ellipse_0.5.0       stringr_1.5.1       parallel_4.4.1      gridExtra_2.3       tidyr_1.3.1         rARPACK_0.11-0     
# [13] scales_1.3.0        BiocParallel_1.39.0 plyr_1.8.9          R6_2.5.1            generics_0.1.3      igraph_2.1.1       
# [19] ggrepel_0.9.6       tibble_3.2.1        munsell_0.5.1       pillar_1.9.0        RColorBrewer_1.1-3  rlang_1.1.4        
# [25] utf8_1.2.4          stringi_1.8.4       pkgload_1.4.0       cli_3.6.3           withr_3.0.2         magrittr_2.0.3     
# [31] grid_4.4.1          rstudioapi_0.17.1   lifecycle_1.0.4     vctrs_0.6.5         RSpectra_0.16-2     glue_1.8.0         
# [37] corpcor_1.6.10      codetools_0.2-20    fansi_1.0.6         colorspace_2.1-1    purrr_1.0.2         reshape2_1.4.4     
# [43] matrixStats_1.4.1   tools_4.4.1         pkgconfig_2.0.3