Example for Survival Data – Prostate Adenocarcinoma
2024-10-29
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
)
)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 | 0.2616307 |
| ALPK2 | ALPK2 | ALPK2 | -0.0714527 |
| ATP5G2 | ATP5G2 | ATP5G2 | -0.2575987 |
| C22orf32 | C22orf32 | C22orf32 | -0.2119992 |
| CSNK2A1P | CSNK2A1P | CSNK2A1P | -1.4875518 |
| MYST3 | MYST3 | MYST3 | -1.6177076 |
| NBPF10 | NBPF10 | NBPF10 | 0.4507147 |
| PFN1 | PFN1 | PFN1 | 0.4161846 |
| SCGB2A2 | SCGB2A2 | SCGB2A2 | 0.0749064 |
| SLC25A1 | SLC25A1 | SLC25A1 | -0.8484827 |
| STX4 | STX4 | STX4 | -0.1690185 |
| SYP | SYP | SYP | 0.2425939 |
| TMEM141 | TMEM141 | TMEM141 | -0.8273147 |
| UMPS | UMPS | UMPS | 0.2214068 |
| ZBTB26 | ZBTB26 | ZBTB26 | 0.3696515 |
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 4.4.1 (2024-06-14)
## Platform: x86_64-pc-linux-gnu
## Running under: Ubuntu 24.04.1 LTS
##
## Matrix products: default
## BLAS: /home/biocbuild/bbs-3.20-bioc/R/lib/libRblas.so
## LAPACK: /usr/lib/x86_64-linux-gnu/lapack/liblapack.so.3.12.0
##
## locale:
## [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C
## [3] LC_TIME=en_GB 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: America/New_York
## tzcode source: system (glibc)
##
## attached base packages:
## [1] grid parallel stats4 stats graphics grDevices utils
## [8] datasets methods base
##
## other attached packages:
## [1] glmnet_4.1-8 VennDiagram_1.7.3
## [3] reshape2_1.4.4 forcats_1.0.0
## [5] Matrix_1.7-1 glmSparseNet_1.24.0
## [7] TCGAutils_1.26.0 curatedTCGAData_1.27.1
## [9] MultiAssayExperiment_1.32.0 SummarizedExperiment_1.36.0
## [11] Biobase_2.66.0 GenomicRanges_1.58.0
## [13] GenomeInfoDb_1.42.0 IRanges_2.40.0
## [15] S4Vectors_0.44.0 BiocGenerics_0.52.0
## [17] MatrixGenerics_1.18.0 matrixStats_1.4.1
## [19] futile.logger_1.4.3 survival_3.7-0
## [21] ggplot2_3.5.1 dplyr_1.1.4
## [23] BiocStyle_2.34.0
##
## loaded via a namespace (and not attached):
## [1] jsonlite_1.8.9 shape_1.4.6.1
## [3] magrittr_2.0.3 magick_2.8.5
## [5] GenomicFeatures_1.58.0 farver_2.1.2
## [7] rmarkdown_2.28 BiocIO_1.16.0
## [9] zlibbioc_1.52.0 vctrs_0.6.5
## [11] memoise_2.0.1 Rsamtools_2.22.0
## [13] RCurl_1.98-1.16 rstatix_0.7.2
## [15] tinytex_0.53 progress_1.2.3
## [17] htmltools_0.5.8.1 S4Arrays_1.6.0
## [19] BiocBaseUtils_1.8.0 AnnotationHub_3.14.0
## [21] lambda.r_1.2.4 curl_5.2.3
## [23] broom_1.0.7 Formula_1.2-5
## [25] pROC_1.18.5 SparseArray_1.6.0
## [27] sass_0.4.9 bslib_0.8.0
## [29] plyr_1.8.9 httr2_1.0.5
## [31] zoo_1.8-12 futile.options_1.0.1
## [33] cachem_1.1.0 GenomicAlignments_1.42.0
## [35] mime_0.12 lifecycle_1.0.4
## [37] iterators_1.0.14 pkgconfig_2.0.3
## [39] R6_2.5.1 fastmap_1.2.0
## [41] GenomeInfoDbData_1.2.13 digest_0.6.37
## [43] colorspace_2.1-1 AnnotationDbi_1.68.0
## [45] ps_1.8.1 ExperimentHub_2.14.0
## [47] RSQLite_2.3.7 ggpubr_0.6.0
## [49] labeling_0.4.3 filelock_1.0.3
## [51] km.ci_0.5-6 fansi_1.0.6
## [53] httr_1.4.7 abind_1.4-8
## [55] compiler_4.4.1 bit64_4.5.2
## [57] withr_3.0.2 backports_1.5.0
## [59] BiocParallel_1.40.0 carData_3.0-5
## [61] DBI_1.2.3 highr_0.11
## [63] ggsignif_0.6.4 biomaRt_2.62.0
## [65] rappdirs_0.3.3 DelayedArray_0.32.0
## [67] rjson_0.2.23 tools_4.4.1
## [69] chromote_0.3.1 glue_1.8.0
## [71] restfulr_0.0.15 promises_1.3.0
## [73] checkmate_2.3.2 generics_0.1.3
## [75] gtable_0.3.6 KMsurv_0.1-5
## [77] tzdb_0.4.0 tidyr_1.3.1
## [79] survminer_0.4.9 websocket_1.4.2
## [81] data.table_1.16.2 hms_1.1.3
## [83] car_3.1-3 xml2_1.3.6
## [85] utf8_1.2.4 XVector_0.46.0
## [87] BiocVersion_3.20.0 foreach_1.5.2
## [89] pillar_1.9.0 stringr_1.5.1
## [91] later_1.3.2 splines_4.4.1
## [93] BiocFileCache_2.14.0 lattice_0.22-6
## [95] rtracklayer_1.66.0 bit_4.5.0
## [97] tidyselect_1.2.1 Biostrings_2.74.0
## [99] knitr_1.48 gridExtra_2.3
## [101] bookdown_0.41 xfun_0.48
## [103] stringi_1.8.4 UCSC.utils_1.2.0
## [105] yaml_2.3.10 evaluate_1.0.1
## [107] codetools_0.2-20 tibble_3.2.1
## [109] BiocManager_1.30.25 cli_3.6.3
## [111] xtable_1.8-4 munsell_0.5.1
## [113] processx_3.8.4 jquerylib_0.1.4
## [115] survMisc_0.5.6 Rcpp_1.0.13
## [117] GenomicDataCommons_1.30.0 dbplyr_2.5.0
## [119] png_0.1-8 XML_3.99-0.17
## [121] readr_2.1.5 blob_1.2.4
## [123] prettyunits_1.2.0 bitops_1.0-9
## [125] scales_1.3.0 purrr_1.0.2
## [127] crayon_1.5.3 rlang_1.1.4
## [129] KEGGREST_1.46.0 rvest_1.0.4
## [131] formatR_1.14