Instalation

if (!require("BiocManager")) {
    install.packages("BiocManager")
}
BiocManager::install("glmSparseNet")

Required Packages

library(dplyr)
library(ggplot2)
library(survival)
library(futile.logger)
library(curatedTCGAData)
library(MultiAssayExperiment)
library(TCGAutils)
#
library(glmSparseNet)
#
# Some general options for futile.logger the debugging package
flog.layout(layout.format("[~l] ~m"))
options(
    "glmSparseNet.show_message" = FALSE,
    "glmSparseNet.base_dir" = withr::local_tempdir()
)
# Setting ggplot2 default theme as minimal
theme_set(ggplot2::theme_minimal())

Load data

The data is loaded from an online curated dataset downloaded from TCGA using curatedTCGAData bioconductor package and processed.

To accelerate the process we use a very reduced dataset down to 107 variables only (genes), which is stored as a data object in this package. However, the procedure to obtain the data manually is described in the following chunk.

brca <- curatedTCGAData(
    diseaseCode = "BRCA", assays = "RNASeq2GeneNorm",
    version = "1.1.38", dry.run = FALSE
)

brca <- TCGAutils::TCGAsplitAssays(brca, c("01", "11"))
xdataRaw <- t(cbind(assay(brca[[1]]), assay(brca[[2]])))

# Get matches between survival and assay data
classV <- TCGAbiospec(rownames(xdataRaw))$sample_definition |> factor()
names(classV) <- rownames(xdataRaw)

# keep features with standard deviation > 0
xdataRaw <- xdataRaw[, apply(xdataRaw, 2, sd) != 0] |>
    scale()

set.seed(params$seed)
smallSubset <- c(
    "CD5", "CSF2RB", "HSF1", "IRGC", "LRRC37A6P", "NEUROG2",
    "NLRC4", "PDE11A", "PIK3CB", "QARS", "RPGRIP1L", "SDC1",
    "TMEM31", "YME1L1", "ZBTB11",
    sample(colnames(xdataRaw), 100)
)

xdata <- xdataRaw[, smallSubset[smallSubset %in% colnames(xdataRaw)]]
ydata <- classV

Fit models

Fit model model penalizing by the hubs using the cross-validation function by cv.glmHub.

fitted <- cv.glmHub(xdata, ydata,
    family = "binomial",
    network = "correlation",
    nlambda = 1000,
    options = networkOptions(
        cutoff = .6,
        minDegree = .2
    )
)

Results of Cross Validation

Shows the results of 1000 different parameters used to find the optimal value in 10-fold cross-validation. The two vertical dotted lines represent the best model and a model with less variables selected (genes), but within a standard error distance from the best.

plot(fitted)

coefsCV <- Filter(function(.x) .x != 0, coef(fitted, s = "lambda.min")[, 1])
data.frame(
    ensembl.id = names(coefsCV),
    gene.name = geneNames(names(coefsCV))$external_gene_name,
    coefficient = coefsCV,
    stringsAsFactors = FALSE
) |>
    arrange(gene.name) |>
    knitr::kable()

## [INFO] Misclassified (11)

## [INFO]   * False primary solid tumour: 7

## [INFO]   * False normal              : 4

## Setting levels: control = Primary Solid Tumor, case = Solid Tissue Normal

## Setting direction: controls < cases

## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.

Session Info

sessionInfo()

## R version 4.5.2 (2025-10-31)
## Platform: x86_64-pc-linux-gnu
## Running under: Ubuntu 24.04.3 LTS
## 
## Matrix products: default
## BLAS:   /usr/lib/x86_64-linux-gnu/openblas-pthread/libblas.so.3 
## LAPACK: /usr/lib/x86_64-linux-gnu/openblas-pthread/libopenblasp-r0.3.26.so;  LAPACK version 3.12.0
## 
## locale:
##  [1] LC_CTYPE=en_US.UTF-8       LC_NUMERIC=C              
##  [3] LC_TIME=en_US.UTF-8        LC_COLLATE=C              
##  [5] LC_MONETARY=en_US.UTF-8    LC_MESSAGES=en_US.UTF-8   
##  [7] LC_PAPER=en_US.UTF-8       LC_NAME=C                 
##  [9] LC_ADDRESS=C               LC_TELEPHONE=C            
## [11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C       
## 
## time zone: Etc/UTC
## tzcode source: system (glibc)
## 
## attached base packages:
## [1] stats4    stats     graphics  grDevices utils     datasets  methods  
## [8] base     
## 
## other attached packages:
##  [1] glmSparseNet_1.28.0         TCGAutils_1.31.3           
##  [3] curatedTCGAData_1.32.0      MultiAssayExperiment_1.36.0
##  [5] SummarizedExperiment_1.40.0 Biobase_2.70.0             
##  [7] GenomicRanges_1.62.0        Seqinfo_1.0.0              
##  [9] IRanges_2.44.0              S4Vectors_0.48.0           
## [11] BiocGenerics_0.56.0         generics_0.1.4             
## [13] MatrixGenerics_1.22.0       matrixStats_1.5.0          
## [15] futile.logger_1.4.3         survival_3.8-3             
## [17] ggplot2_4.0.1               dplyr_1.1.4                
## [19] BiocStyle_2.38.0           
## 
## loaded via a namespace (and not attached):
##   [1] DBI_1.2.3                 bitops_1.0-9             
##   [3] pROC_1.19.0.1             httr2_1.2.1              
##   [5] formatR_1.14              biomaRt_2.66.0           
##   [7] rlang_1.1.6               magrittr_2.0.4           
##   [9] compiler_4.5.2            RSQLite_2.4.4            
##  [11] GenomicFeatures_1.62.0    png_0.1-8                
##  [13] vctrs_0.6.5               stringr_1.6.0            
##  [15] rvest_1.0.5               shape_1.4.6.1            
##  [17] pkgconfig_2.0.3           crayon_1.5.3             
##  [19] fastmap_1.2.0             backports_1.5.0          
##  [21] dbplyr_2.5.1              XVector_0.50.0           
##  [23] labeling_0.4.3            Rsamtools_2.26.0         
##  [25] rmarkdown_2.30            tzdb_0.5.0               
##  [27] UCSC.utils_1.6.0          purrr_1.2.0              
##  [29] bit_4.6.0                 glmnet_4.1-10            
##  [31] xfun_0.54                 cachem_1.1.0             
##  [33] cigarillo_1.0.0           GenomeInfoDb_1.46.0      
##  [35] jsonlite_2.0.0            progress_1.2.3           
##  [37] blob_1.2.4                DelayedArray_0.36.0      
##  [39] BiocParallel_1.44.0       prettyunits_1.2.0        
##  [41] parallel_4.5.2            R6_2.6.1                 
##  [43] stringi_1.8.7             bslib_0.9.0              
##  [45] RColorBrewer_1.1-3        rtracklayer_1.70.0       
##  [47] jquerylib_0.1.4           Rcpp_1.1.0               
##  [49] iterators_1.0.14          knitr_1.50               
##  [51] readr_2.1.6               BiocBaseUtils_1.12.0     
##  [53] Matrix_1.7-4              splines_4.5.2            
##  [55] tidyselect_1.2.1          abind_1.4-8              
##  [57] yaml_2.3.10               codetools_0.2-20         
##  [59] curl_7.0.0                lattice_0.22-7           
##  [61] tibble_3.3.0              withr_3.0.2              
##  [63] KEGGREST_1.50.0           S7_0.2.1                 
##  [65] evaluate_1.0.5            lambda.r_1.2.4           
##  [67] BiocFileCache_3.0.0       xml2_1.4.1               
##  [69] ExperimentHub_3.0.0       Biostrings_2.78.0        
##  [71] pillar_1.11.1             BiocManager_1.30.27      
##  [73] filelock_1.0.3            foreach_1.5.2            
##  [75] checkmate_2.3.3           RCurl_1.98-1.17          
##  [77] BiocVersion_3.23.1        hms_1.1.4                
##  [79] scales_1.4.0              glue_1.8.0               
##  [81] maketools_1.3.2           tools_4.5.2              
##  [83] AnnotationHub_4.0.0       BiocIO_1.20.0            
##  [85] sys_3.4.3                 GenomicAlignments_1.46.0 
##  [87] buildtools_1.0.0          XML_3.99-0.20            
##  [89] grid_4.5.2                AnnotationDbi_1.72.0     
##  [91] restfulr_0.0.16           cli_3.6.5                
##  [93] rappdirs_0.3.3            futile.options_1.0.1     
##  [95] GenomicDataCommons_1.34.1 S4Arrays_1.10.0          
##  [97] gtable_0.3.6              sass_0.4.10              
##  [99] digest_0.6.38             SparseArray_1.10.1       
## [101] rjson_0.2.23              farver_2.1.2             
## [103] memoise_2.0.1             htmltools_0.5.8.1        
## [105] lifecycle_1.0.4           httr_1.4.7               
## [107] bit64_4.6.0-1