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 per session.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.

Session Info

sessionInfo()

## R version 4.6.0 (2026-04-24)
## Platform: x86_64-pc-linux-gnu
## Running under: Ubuntu 24.04.4 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=en_US.UTF-8    
##  [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_1.31.0         TCGAutils_1.33.2           
##  [3] curatedTCGAData_1.35.0      MultiAssayExperiment_1.39.0
##  [5] SummarizedExperiment_1.43.0 Biobase_2.73.1             
##  [7] GenomicRanges_1.65.0        Seqinfo_1.3.0              
##  [9] IRanges_2.47.2              S4Vectors_0.51.3           
## [11] BiocGenerics_0.59.7         generics_0.1.4             
## [13] MatrixGenerics_1.25.0       matrixStats_1.5.0          
## [15] futile.logger_1.4.9         survival_3.8-6             
## [17] ggplot2_4.0.3               dplyr_1.2.1                
## [19] BiocStyle_2.41.0           
## 
## loaded via a namespace (and not attached):
##   [1] DBI_1.3.0                 bitops_1.0-9             
##   [3] pROC_1.19.0.1             httr2_1.2.2              
##   [5] formatR_1.14              biomaRt_2.69.0           
##   [7] rlang_1.2.0               magrittr_2.0.5           
##   [9] otel_0.2.0                compiler_4.6.0           
##  [11] RSQLite_3.53.2            GenomicFeatures_1.65.0   
##  [13] png_0.1-9                 vctrs_0.7.3              
##  [15] stringr_1.6.0             rvest_1.0.5              
##  [17] shape_1.4.6.1             pkgconfig_2.0.3          
##  [19] crayon_1.5.3              fastmap_1.2.0            
##  [21] backports_1.5.1           dbplyr_2.6.0             
##  [23] XVector_0.53.0            labeling_0.4.3           
##  [25] Rsamtools_2.29.0          rmarkdown_2.31           
##  [27] tzdb_0.5.0                UCSC.utils_1.9.0         
##  [29] purrr_1.2.2               bit_4.6.0                
##  [31] glmnet_5.0                xfun_0.59                
##  [33] cachem_1.1.0              cigarillo_1.3.0          
##  [35] GenomeInfoDb_1.49.1       jsonlite_2.0.0           
##  [37] progress_1.2.3            blob_1.3.0               
##  [39] DelayedArray_0.39.3       BiocParallel_1.47.0      
##  [41] prettyunits_1.2.0         parallel_4.6.0           
##  [43] R6_2.6.1                  stringi_1.8.7            
##  [45] bslib_0.11.0              RColorBrewer_1.1-3       
##  [47] rtracklayer_1.73.0        jquerylib_0.1.4          
##  [49] Rcpp_1.1.1-1.1            iterators_1.0.14         
##  [51] knitr_1.51                readr_2.2.0              
##  [53] BiocBaseUtils_1.15.1      Matrix_1.7-5             
##  [55] splines_4.6.0             tidyselect_1.2.1         
##  [57] abind_1.4-8               yaml_2.3.12              
##  [59] codetools_0.2-20          curl_7.1.0               
##  [61] lattice_0.22-9            tibble_3.3.1             
##  [63] withr_3.0.3               KEGGREST_1.53.4          
##  [65] S7_0.2.2                  evaluate_1.0.5           
##  [67] lambda.r_1.2.4            BiocFileCache_3.3.0      
##  [69] xml2_1.6.0                ExperimentHub_3.3.1      
##  [71] Biostrings_2.81.3         pillar_1.11.1            
##  [73] BiocManager_1.30.27       filelock_1.0.3           
##  [75] foreach_1.5.2             checkmate_2.3.4          
##  [77] RCurl_1.98-1.19           BiocVersion_3.24.0       
##  [79] hms_1.1.4                 scales_1.4.0             
##  [81] glue_1.8.1                maketools_1.3.2          
##  [83] tools_4.6.0               AnnotationHub_4.3.1      
##  [85] BiocIO_1.23.3             sys_3.4.3                
##  [87] GenomicAlignments_1.49.0  buildtools_1.0.0         
##  [89] XML_3.99-0.23             grid_4.6.0               
##  [91] AnnotationDbi_1.75.0      restfulr_0.0.17          
##  [93] cli_3.6.6                 rappdirs_0.3.4           
##  [95] futile.options_1.0.1      GenomicDataCommons_1.37.0
##  [97] S4Arrays_1.13.0           gtable_0.3.6             
##  [99] sass_0.4.10               digest_0.6.39            
## [101] SparseArray_1.13.2        rjson_0.2.23             
## [103] farver_2.1.2              memoise_2.0.1            
## [105] htmltools_0.5.9           lifecycle_1.0.5          
## [107] httr_1.4.8                bit64_4.8.2