Example for Survival Data – Prostate Adenocarcinoma
2026-05-18
Contents
1 Instalation
if (!require("BiocManager")) {
install.packages("BiocManager")
}
BiocManager::install("glmSparseNet")2 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())3 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 around 100 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.
prad <- curatedTCGAData(
diseaseCode = "PRAD", assays = "RNASeq2GeneNorm",
version = "1.1.38", dry.run = FALSE
)Build the survival data from the clinical columns.
- Selects only primary solid tumour samples
- Merge survival times for patients, which have different columns in case they are alive or dead.
- Build two matrix objects that fit the data
xdataandydata
# keep only solid tumour (code: 01)
pradPrimarySolidTumor <- TCGAutils::TCGAsplitAssays(prad, "01")
xdataRaw <- t(assay(pradPrimarySolidTumor[[1]]))
# Get survival information
ydataRaw <- colData(pradPrimarySolidTumor) |>
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()
# 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(
geneNames(c(
"ENSG00000103091", "ENSG00000064787",
"ENSG00000119915", "ENSG00000120158",
"ENSG00000114491", "ENSG00000204176",
"ENSG00000138399"
))$external_gene_name,
sample(colnames(xdataRaw), 100)
) |>
unique() |>
sort()
xdata <- xdataRaw[, smallSubset[smallSubset %in% colnames(xdataRaw)]]
ydata <- ydataRaw |> dplyr::select(time, status)4 Fit models
Fit model model penalizing by the hubs using the cross-validation function by
cv.glmHub.
set.seed(params$seed)
fitted <- cv.glmHub(xdata, Surv(ydata$time, ydata$status),
family = "cox",
nlambda = 1000,
network = "correlation",
options = networkOptions(
cutoff = .6,
minDegree = .2
)
)## Warning: Starting in glmnet 5.1, the default Cox tie-handling method will
## change from 'breslow' to 'efron' (matching survival::coxph). To silence this
## message and lock in the v5.0 default, pass cox.ties = 'breslow' explicitly. To
## preview the v5.1 behavior, pass cox.ties = 'efron'.
## Warning: Starting in glmnet 5.1, the default Cox tie-handling method will
## change from 'breslow' to 'efron' (matching survival::coxph). To silence this
## message and lock in the v5.0 default, pass cox.ties = 'breslow' explicitly. To
## preview the v5.1 behavior, pass cox.ties = 'efron'.
## Warning: Starting in glmnet 5.1, the default Cox tie-handling method will
## change from 'breslow' to 'efron' (matching survival::coxph). To silence this
## message and lock in the v5.0 default, pass cox.ties = 'breslow' explicitly. To
## preview the v5.1 behavior, pass cox.ties = 'efron'.
## Warning: Starting in glmnet 5.1, the default Cox tie-handling method will
## change from 'breslow' to 'efron' (matching survival::coxph). To silence this
## message and lock in the v5.0 default, pass cox.ties = 'breslow' explicitly. To
## preview the v5.1 behavior, pass cox.ties = 'efron'.
## Warning: Starting in glmnet 5.1, the default Cox tie-handling method will
## change from 'breslow' to 'efron' (matching survival::coxph). To silence this
## message and lock in the v5.0 default, pass cox.ties = 'breslow' explicitly. To
## preview the v5.1 behavior, pass cox.ties = 'efron'.
## Warning: Starting in glmnet 5.1, the default Cox tie-handling method will
## change from 'breslow' to 'efron' (matching survival::coxph). To silence this
## message and lock in the v5.0 default, pass cox.ties = 'breslow' explicitly. To
## preview the v5.1 behavior, pass cox.ties = 'efron'.
## Warning: Starting in glmnet 5.1, the default Cox tie-handling method will
## change from 'breslow' to 'efron' (matching survival::coxph). To silence this
## message and lock in the v5.0 default, pass cox.ties = 'breslow' explicitly. To
## preview the v5.1 behavior, pass cox.ties = 'efron'.
## Warning: Starting in glmnet 5.1, the default Cox tie-handling method will
## change from 'breslow' to 'efron' (matching survival::coxph). To silence this
## message and lock in the v5.0 default, pass cox.ties = 'breslow' explicitly. To
## preview the v5.1 behavior, pass cox.ties = 'efron'.
## Warning: Starting in glmnet 5.1, the default Cox tie-handling method will
## change from 'breslow' to 'efron' (matching survival::coxph). To silence this
## message and lock in the v5.0 default, pass cox.ties = 'breslow' explicitly. To
## preview the v5.1 behavior, pass cox.ties = 'efron'.
## Warning: Starting in glmnet 5.1, the default Cox tie-handling method will
## change from 'breslow' to 'efron' (matching survival::coxph). To silence this
## message and lock in the v5.0 default, pass cox.ties = 'breslow' explicitly. To
## preview the v5.1 behavior, pass cox.ties = 'efron'.
## Warning: Starting in glmnet 5.1, the default Cox tie-handling method will
## change from 'breslow' to 'efron' (matching survival::coxph). To silence this
## message and lock in the v5.0 default, pass cox.ties = 'breslow' explicitly. To
## preview the v5.1 behavior, pass cox.ties = 'efron'.5 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)
5.1 Coefficients of selected model from Cross-Validation
Taking the best model described by lambda.min
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()| ensembl.id | gene.name | coefficient | |
|---|---|---|---|
| AKAP9 | AKAP9 | AKAP9 | 0.2629182 |
| ALPK2 | ALPK2 | ALPK2 | -0.0736154 |
| ATP5G2 | ATP5G2 | ATP5G2 | -0.2579907 |
| C22orf32 | C22orf32 | C22orf32 | -0.2135232 |
| CSNK2A1P | CSNK2A1P | CSNK2A1P | -1.4901438 |
| MYST3 | MYST3 | MYST3 | -1.6201982 |
| NBPF10 | NBPF10 | NBPF10 | 0.4516203 |
| PFN1 | PFN1 | PFN1 | 0.4190713 |
| SCGB2A2 | SCGB2A2 | SCGB2A2 | 0.0745027 |
| SLC25A1 | SLC25A1 | SLC25A1 | -0.8520986 |
| STX4 | STX4 | STX4 | -0.1700270 |
| SYP | SYP | SYP | 0.2520132 |
| TMEM141 | TMEM141 | TMEM141 | -0.8293076 |
| UMPS | UMPS | UMPS | 0.2250850 |
| ZBTB26 | ZBTB26 | ZBTB26 | 0.3698158 |
5.2 Survival curves and Log rank test
separate2GroupsCox(as.vector(coefsCV),
xdata[, names(coefsCV)],
ydata,
plotTitle = "Full dataset", legendOutside = FALSE
)## $pvalue
## [1] 0.001155155
##
## $plot
##
## $km
## Call: survfit(formula = survival::Surv(time, status) ~ group, data = prognosticIndexDf)
##
## n events median 0.95LCL 0.95UCL
## Low risk - 1 249 0 NA NA NA
## High risk - 1 248 10 3502 3467 NA6 Session Info
sessionInfo()## R version 4.6.0 Patched (2026-05-01 r89994)
## Platform: aarch64-apple-darwin23
## Running under: macOS Tahoe 26.3.1
##
## Matrix products: default
## BLAS: /Library/Frameworks/R.framework/Versions/4.6/Resources/lib/libRblas.0.dylib
## LAPACK: /Library/Frameworks/R.framework/Versions/4.6/Resources/lib/libRlapack.dylib; LAPACK version 3.12.1
##
## locale:
## [1] C/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
##
## time zone: America/New_York
## tzcode source: internal
##
## attached base packages:
## [1] grid parallel stats4 stats graphics grDevices utils
## [8] datasets methods base
##
## other attached packages:
## [1] glmnet_5.0 VennDiagram_1.8.2
## [3] reshape2_1.4.5 forcats_1.0.1
## [5] Matrix_1.7-5 glmSparseNet_1.31.0
## [7] TCGAutils_1.33.1 curatedTCGAData_1.35.0
## [9] MultiAssayExperiment_1.39.0 SummarizedExperiment_1.43.0
## [11] Biobase_2.73.1 GenomicRanges_1.65.0
## [13] Seqinfo_1.3.0 IRanges_2.47.1
## [15] S4Vectors_0.51.2 BiocGenerics_0.59.2
## [17] generics_0.1.4 MatrixGenerics_1.25.0
## [19] matrixStats_1.5.0 futile.logger_1.4.9
## [21] survival_3.8-6 ggplot2_4.0.3
## [23] dplyr_1.2.1 BiocStyle_2.41.0
##
## loaded via a namespace (and not attached):
## [1] RColorBrewer_1.1-3 jsonlite_2.0.0
## [3] shape_1.4.6.1 magrittr_2.0.5
## [5] magick_2.9.1 GenomicFeatures_1.65.0
## [7] farver_2.1.2 rmarkdown_2.31
## [9] BiocIO_1.23.3 vctrs_0.7.3
## [11] memoise_2.0.1 Rsamtools_2.29.0
## [13] RCurl_1.98-1.18 rstatix_0.7.3
## [15] tinytex_0.59 htmltools_0.5.9
## [17] S4Arrays_1.13.0 BiocBaseUtils_1.15.1
## [19] progress_1.2.3 AnnotationHub_4.3.0
## [21] lambda.r_1.2.4 curl_7.1.0
## [23] broom_1.0.13 Formula_1.2-5
## [25] pROC_1.19.0.1 SparseArray_1.13.2
## [27] sass_0.4.10 bslib_0.11.0
## [29] plyr_1.8.9 httr2_1.2.2
## [31] futile.options_1.0.1 cachem_1.1.0
## [33] GenomicAlignments_1.49.0 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_1.75.0
## [41] ExperimentHub_3.3.0 RSQLite_3.52.0
## [43] ggpubr_0.6.3 labeling_0.4.3
## [45] filelock_1.0.3 httr_1.4.8
## [47] abind_1.4-8 compiler_4.6.0
## [49] bit64_4.8.0 withr_3.0.2
## [51] S7_0.2.2 backports_1.5.1
## [53] BiocParallel_1.47.0 carData_3.0-6
## [55] DBI_1.3.0 ggsignif_0.6.4
## [57] biomaRt_2.69.0 rappdirs_0.3.4
## [59] DelayedArray_0.39.2 rjson_0.2.23
## [61] tools_4.6.0 chromote_0.5.1
## [63] otel_0.2.0 glue_1.8.1
## [65] restfulr_0.0.16 promises_1.5.0
## [67] checkmate_2.3.4 gtable_0.3.6
## [69] tzdb_0.5.0 tidyr_1.3.2
## [71] survminer_0.5.2 websocket_1.4.4
## [73] hms_1.1.4 car_3.1-5
## [75] xml2_1.5.2 XVector_0.53.0
## [77] BiocVersion_3.24.0 foreach_1.5.2
## [79] pillar_1.11.1 stringr_1.6.0
## [81] later_1.4.8 splines_4.6.0
## [83] BiocFileCache_3.3.0 lattice_0.22-9
## [85] rtracklayer_1.73.0 bit_4.6.0
## [87] tidyselect_1.2.1 Biostrings_2.81.1
## [89] knitr_1.51 gridExtra_2.3
## [91] bookdown_0.46 xfun_0.57
## [93] stringi_1.8.7 UCSC.utils_1.9.0
## [95] yaml_2.3.12 evaluate_1.0.5
## [97] codetools_0.2-20 cigarillo_1.3.0
## [99] tibble_3.3.1 BiocManager_1.30.27
## [101] cli_3.6.6 processx_3.9.0
## [103] jquerylib_0.1.4 dichromat_2.0-0.1
## [105] Rcpp_1.1.1-1.1 GenomeInfoDb_1.49.0
## [107] GenomicDataCommons_1.37.0 dbplyr_2.5.2
## [109] png_0.1-9 XML_3.99-0.23
## [111] readr_2.2.0 blob_1.3.0
## [113] prettyunits_1.2.0 bitops_1.0-9
## [115] scales_1.4.0 purrr_1.2.2
## [117] crayon_1.5.3 rlang_1.2.0
## [119] KEGGREST_1.53.0 rvest_1.0.5
## [121] formatR_1.14