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.

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

# keep only solid tumour (code: 01)
brcaPrimarySolidTumor <- TCGAutils::TCGAsplitAssays(brca, "01")
xdataRaw <- t(assay(brcaPrimarySolidTumor[[1]]))

# Get survival information
ydataRaw <- colData(brcaPrimarySolidTumor) |>
    as.data.frame() |>
    # Keep only data relative to survival or samples
    dplyr::select(
        patientID, vital_status,
        Days.to.date.of.Death, Days.to.Date.of.Last.Contact,
        days_to_death, days_to_last_followup,
        Vital.Status
    ) |>
    # Convert days to integer
    dplyr::mutate(Days.to.date.of.Death = as.integer(Days.to.date.of.Death)) |>
    dplyr::mutate(
        Days.to.Last.Contact = as.integer(Days.to.Date.of.Last.Contact)
    ) |>
    # Find max time between all days (ignoring missings)
    dplyr::rowwise() |>
    dplyr::mutate(
        time = max(days_to_last_followup, Days.to.date.of.Death,
            Days.to.Last.Contact, 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

# Get matches between survival and assay data
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)), ]

# Using only a subset of genes previously selected to keep this short example.
set.seed(params$seed)
smallSubset <- c(
    "CD5", "CSF2RB", "IRGC", "NEUROG2", "NLRC4", "PDE11A",
    "PTEN", "TP53", "BRAF",
    "PIK3CB", "QARS", "RFC3", "RPGRIP1L", "SDC1", "TMEM31",
    "YME1L1", "ZBTB11", sample(colnames(xdataRaw), 100)
) |>
    unique()

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.

set.seed(params$seed)
fitted <- cv.glmHub(xdata, Surv(ydata$time, ydata$status),
    family = "cox",
    lambda = buildLambda(1),
    network = "correlation",
    options = networkOptions(
        cutoff = .6,
        minDegree = .2
    )
)

## Warning in regularize.values(x, y, ties, missing(ties), na.rm = na.rm):
## collapsing to unique 'x' values
## Warning in regularize.values(x, y, ties, missing(ties), na.rm = na.rm):
## collapsing to unique 'x' values
## Warning in regularize.values(x, y, ties, missing(ties), na.rm = na.rm):
## collapsing to unique 'x' values
## Warning in regularize.values(x, y, ties, missing(ties), na.rm = na.rm):
## collapsing to unique 'x' values
## Warning in regularize.values(x, y, ties, missing(ties), na.rm = na.rm):
## collapsing to unique 'x' values
## Warning in regularize.values(x, y, ties, missing(ties), na.rm = na.rm):
## collapsing to unique 'x' values
## Warning in regularize.values(x, y, ties, missing(ties), na.rm = na.rm):
## collapsing to unique 'x' values
## Warning in regularize.values(x, y, ties, missing(ties), na.rm = na.rm):
## collapsing to unique 'x' values
## Warning in regularize.values(x, y, ties, missing(ties), na.rm = na.rm):
## collapsing to unique 'x' values
## Warning in regularize.values(x, y, ties, missing(ties), na.rm = na.rm):
## collapsing to unique 'x' values

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])

## Warning in regularize.values(x, y, ties, missing(ties), na.rm = na.rm):
## collapsing to unique 'x' values

data.frame(
    gene.name = names(coefsCV),
    coefficient = coefsCV,
    stringsAsFactors = FALSE
) |>
    arrange(gene.name) |>
    knitr::kable()

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

## $pvalue
## [1] 0.001237802
## 
## $plot

## 
## $km
## Call: survfit(formula = survival::Surv(time, status) ~ group, data = prognosticIndexDf)
## 
##                 n events median 0.95LCL 0.95UCL
## Low risk - 1  540     58   3959    3492      NA
## High risk - 1 540     94   3738    3262    4456

Session Info

sessionInfo()

## R version 4.5.2 (2025-10-31)
## 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=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] grid      parallel  stats4    stats     graphics  grDevices utils    
##  [8] datasets  methods   base     
## 
## other attached packages:
##  [1] glmnet_4.1-10               VennDiagram_1.8.2          
##  [3] reshape2_1.4.5              forcats_1.0.1              
##  [5] Matrix_1.7-4                glmSparseNet_1.29.0        
##  [7] TCGAutils_1.31.4            curatedTCGAData_1.33.1     
##  [9] MultiAssayExperiment_1.37.2 SummarizedExperiment_1.41.1
## [11] Biobase_2.71.0              GenomicRanges_1.63.1       
## [13] Seqinfo_1.1.0               IRanges_2.45.0             
## [15] S4Vectors_0.49.0            BiocGenerics_0.57.0        
## [17] generics_0.1.4              MatrixGenerics_1.23.0      
## [19] matrixStats_1.5.0           futile.logger_1.4.9        
## [21] survival_3.8-6              ggplot2_4.0.2              
## [23] dplyr_1.2.0                 BiocStyle_2.39.0           
## 
## loaded via a namespace (and not attached):
##   [1] RColorBrewer_1.1-3        sys_3.4.3                
##   [3] jsonlite_2.0.0            shape_1.4.6.1            
##   [5] magrittr_2.0.4            GenomicFeatures_1.63.1   
##   [7] farver_2.1.2              rmarkdown_2.30           
##   [9] BiocIO_1.21.0             vctrs_0.7.1              
##  [11] memoise_2.0.1             Rsamtools_2.27.1         
##  [13] RCurl_1.98-1.17           rstatix_0.7.3            
##  [15] htmltools_0.5.9           S4Arrays_1.11.1          
##  [17] BiocBaseUtils_1.13.0      progress_1.2.3           
##  [19] AnnotationHub_4.1.0       lambda.r_1.2.4           
##  [21] curl_7.0.0                broom_1.0.12             
##  [23] Formula_1.2-5             SparseArray_1.11.11      
##  [25] pROC_1.19.0.1             sass_0.4.10              
##  [27] bslib_0.10.0              plyr_1.8.9               
##  [29] httr2_1.2.2               futile.options_1.0.1     
##  [31] cachem_1.1.0              buildtools_1.0.0         
##  [33] GenomicAlignments_1.47.0  lifecycle_1.0.5          
##  [35] iterators_1.0.14          pkgconfig_2.0.3          
##  [37] R6_2.6.1                  fastmap_1.2.0            
##  [39] digest_0.6.39             AnnotationDbi_1.73.0     
##  [41] ExperimentHub_3.1.0       RSQLite_2.4.6            
##  [43] ggpubr_0.6.3              filelock_1.0.3           
##  [45] labeling_0.4.3            httr_1.4.8               
##  [47] abind_1.4-8               compiler_4.5.2           
##  [49] bit64_4.6.0-1             withr_3.0.2              
##  [51] S7_0.2.1                  backports_1.5.0          
##  [53] BiocParallel_1.45.0       carData_3.0-6            
##  [55] DBI_1.3.0                 ggsignif_0.6.4           
##  [57] biomaRt_2.67.6            rappdirs_0.3.4           
##  [59] DelayedArray_0.37.0       rjson_0.2.23             
##  [61] tools_4.5.2               glue_1.8.0               
##  [63] restfulr_0.0.16           checkmate_2.3.4          
##  [65] gtable_0.3.6              tzdb_0.5.0               
##  [67] tidyr_1.3.2               survminer_0.5.2          
##  [69] hms_1.1.4                 car_3.1-5                
##  [71] xml2_1.5.2                XVector_0.51.0           
##  [73] BiocVersion_3.23.1        foreach_1.5.2            
##  [75] pillar_1.11.1             stringr_1.6.0            
##  [77] splines_4.5.2             BiocFileCache_3.1.0      
##  [79] lattice_0.22-9            rtracklayer_1.71.3       
##  [81] bit_4.6.0                 tidyselect_1.2.1         
##  [83] maketools_1.3.2           Biostrings_2.79.5        
##  [85] knitr_1.51                gridExtra_2.3            
##  [87] xfun_0.56                 stringi_1.8.7            
##  [89] UCSC.utils_1.7.1          yaml_2.3.12              
##  [91] evaluate_1.0.5            codetools_0.2-20         
##  [93] cigarillo_1.1.0           tibble_3.3.1             
##  [95] BiocManager_1.30.27       cli_3.6.5                
##  [97] jquerylib_0.1.4           Rcpp_1.1.1               
##  [99] GenomeInfoDb_1.47.2       GenomicDataCommons_1.35.1
## [101] dbplyr_2.5.2              png_0.1-9                
## [103] XML_3.99-0.22             readr_2.2.0              
## [105] blob_1.3.0                prettyunits_1.2.0        
## [107] bitops_1.0-9              scales_1.4.0             
## [109] purrr_1.2.1               crayon_1.5.3             
## [111] rlang_1.1.7               KEGGREST_1.51.1          
## [113] rvest_1.0.5               formatR_1.14