Instalation

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

Required Packages

library(dplyr)
library(ggplot2)
library(survival)
library(futile.logger)
library(curatedTCGAData)
library(TCGAutils)
library(MultiAssayExperiment)
#
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.

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

Build the survival data from the clinical columns.

• Merge survival times for patients, which have different columns in case they are alive or dead.
• Build two matrix objects that fit the data xdata and ydata

skcmMetastatic <- TCGAutils::TCGAsplitAssays(skcm, "06")
xdataRaw <- t(assay(skcmMetastatic[[1]]))

# Get survival information
ydataRaw <- colData(skcmMetastatic) |>
    as.data.frame() |>
    # Find max time between all days (ignoring missings)
    dplyr::rowwise() |>
    dplyr::mutate(
        time = max(days_to_last_followup,
            days_to_death,
            na.rm = TRUE
        )
    ) |>
    # Keep only survival variables and codes
    dplyr::select(patientID, status = vital_status, time) |>
    # Discard individuals with survival time less or equal to 0
    dplyr::filter(!is.na(time) & time > 0) |>
    as.data.frame()

# Get survival information
ydataRaw <- colData(skcm) |>
    as.data.frame() |>
    # Find max time between all days (ignoring missings)
    dplyr::filter(
        !is.na(days_to_last_followup) | !is.na(days_to_death)
    ) |>
    dplyr::rowwise() |>
    dplyr::mutate(
        time = max(days_to_last_followup, days_to_death, na.rm = TRUE)
    ) |>
    # Keep only survival variables and codes
    dplyr::select(patientID, status = vital_status, time) |>
    # Discard individuals with survival time less or equal to 0
    dplyr::filter(!is.na(time) & time > 0) |>
    as.data.frame()

# Set index as the patientID
rownames(ydataRaw) <- ydataRaw$patientID

# keep only features that have standard deviation > 0
xdataRaw <- xdataRaw[
    TCGAbarcode(rownames(xdataRaw)) %in% rownames(ydataRaw),
]
xdataRaw <- xdataRaw[, apply(xdataRaw, 2, sd) != 0] |>
    scale()

# Order ydata the same as assay
ydataRaw <- ydataRaw[TCGAbarcode(rownames(xdataRaw)), ]

set.seed(params$seed)
smallSubset <- c(
    "FOXL2", "KLHL5", "PCYT2", "SLC6A10P", "STRAP", "TMEM33",
    "WT1-AS", sample(colnames(xdataRaw), 100)
)

xdata <- xdataRaw[, smallSubset[smallSubset %in% colnames(xdataRaw)]]
ydata <- ydataRaw |> dplyr::select(time, status)

Fit models

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

fitted <- cv.glmHub(
    xdata,
    Surv(ydata$time, ydata$status),
    family = "cox",
    foldid = glmSparseNet:::balancedCvFolds(ydata$status)$output,
    network = "correlation",
    options = networkOptions(
        cutoff = .6,
        minDegree = .2
    )
)

Results of Cross Validation

Shows the results of 100 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()

separate2GroupsCox(as.vector(coefsCV),
    xdata[, names(coefsCV)],
    ydata,
    plotTitle = "Full dataset", legendOutside = FALSE
)

Session Info

sessionInfo()

## R version 4.6.2 (2026-10-29)
## Platform: x86_64-pc-linux-gnu
## Running under: Ubuntu 26.04.1 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-r0.3.32.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] grid      parallel  stats4    stats     graphics  grDevices utils    
##  [8] datasets  methods   base     
## 
## other attached packages:
##  [1] VennDiagram_1.8.2           reshape2_1.4.5             
##  [3] forcats_1.0.1               Matrix_1.7-6               
##  [5] glmSparseNet_1.31.0         TCGAutils_1.33.3           
##  [7] curatedTCGAData_1.35.1      MultiAssayExperiment_1.39.1
##  [9] SummarizedExperiment_1.43.0 Biobase_2.73.2             
## [11] GenomicRanges_1.65.4        Seqinfo_1.3.2              
## [13] IRanges_2.47.5              S4Vectors_0.51.10          
## [15] BiocGenerics_0.59.12        generics_0.1.4             
## [17] MatrixGenerics_1.25.0       matrixStats_1.5.0          
## [19] futile.logger_1.4.9         survival_3.8-12            
## [21] ggplot2_4.0.3               dplyr_1.2.1                
## [23] BiocStyle_2.41.0           
## 
## loaded via a namespace (and not attached):
##  [1] DBI_1.3.0                 bitops_1.1-0             
##  [3] httr2_1.3.0               formatR_1.14             
##  [5] rlang_1.3.0               magrittr_2.0.5           
##  [7] otel_0.2.0                compiler_4.6.2           
##  [9] RSQLite_3.53.3            GenomicFeatures_1.65.0   
## [11] png_0.1-9                 vctrs_0.7.3              
## [13] stringr_1.6.0             rvest_1.0.5              
## [15] pkgconfig_2.0.3           crayon_1.5.3             
## [17] fastmap_1.2.0             dbplyr_2.6.0             
## [19] XVector_0.53.0            labeling_0.4.3           
## [21] Rsamtools_2.29.0          rmarkdown_2.32           
## [23] tzdb_0.5.0                UCSC.utils_1.9.0         
## [25] purrr_1.2.2               bit_4.6.0                
## [27] xfun_0.62                 cachem_1.1.0             
## [29] cigarillo_1.3.1           GenomeInfoDb_1.49.1      
## [31] jsonlite_2.0.0            blob_1.3.0               
## [33] DelayedArray_0.39.8       BiocParallel_1.47.0      
## [35] R6_2.6.1                  stringi_1.8.9            
## [37] bslib_0.12.0              RColorBrewer_1.1-3       
## [39] rtracklayer_1.73.0        jquerylib_0.1.4          
## [41] Rcpp_1.1.2                knitr_1.52               
## [43] readr_2.2.0               BiocBaseUtils_1.15.1     
## [45] splines_4.6.2             tidyselect_1.2.1         
## [47] abind_1.4-8               yaml_2.3.12              
## [49] codetools_0.2-20          curl_8.1.0               
## [51] plyr_1.8.9                lattice_0.23-1           
## [53] tibble_3.3.1              withr_3.0.3              
## [55] KEGGREST_1.53.6           S7_0.2.2                 
## [57] evaluate_1.0.5            lambda.r_1.2.6           
## [59] BiocFileCache_3.3.1       xml2_1.6.0               
## [61] ExperimentHub_3.3.2       Biostrings_2.81.9        
## [63] pillar_1.11.1             BiocManager_1.30.27      
## [65] filelock_1.0.3            RCurl_1.98-1.20          
## [67] BiocVersion_3.24.0        hms_1.1.4                
## [69] scales_1.4.0              glue_1.8.1               
## [71] maketools_1.3.2           tools_4.6.2              
## [73] AnnotationHub_4.3.3       BiocIO_1.23.3            
## [75] sys_3.4.3                 GenomicAlignments_1.49.2 
## [77] buildtools_1.0.0          XML_3.99-0.25            
## [79] AnnotationDbi_1.75.2      restfulr_0.0.17          
## [81] cli_3.6.6                 rappdirs_0.3.4           
## [83] futile.options_1.0.1      GenomicDataCommons_1.37.0
## [85] S4Arrays_1.13.2           gtable_0.3.6             
## [87] sass_0.4.10               digest_0.6.39            
## [89] SparseArray_1.13.4        rjson_0.2.23             
## [91] farver_2.1.2              memoise_2.0.1            
## [93] htmltools_0.5.9           lifecycle_1.0.5          
## [95] httr_1.4.9                bit64_4.8.6