Example for Survival Data – Prostate Adenocarcinoma
2024-05-01
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 4.4.0 beta (2024-04-15 r86425)
## Platform: x86_64-pc-linux-gnu
## Running under: Ubuntu 22.04.4 LTS
##
## Matrix products: default
## BLAS: /home/biocbuild/bbs-3.19-bioc/R/lib/libRblas.so
## LAPACK: /usr/lib/x86_64-linux-gnu/lapack/liblapack.so.3.10.0
##
## 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: 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_1.7-0 glmSparseNet_1.22.0
## [7] TCGAutils_1.24.0 curatedTCGAData_1.25.4
## [9] MultiAssayExperiment_1.30.0 SummarizedExperiment_1.34.0
## [11] Biobase_2.64.0 GenomicRanges_1.56.0
## [13] GenomeInfoDb_1.40.0 IRanges_2.38.0
## [15] S4Vectors_0.42.0 BiocGenerics_0.50.0
## [17] MatrixGenerics_1.16.0 matrixStats_1.3.0
## [19] futile.logger_1.4.3 survival_3.6-4
## [21] ggplot2_3.5.1 dplyr_1.1.4
## [23] BiocStyle_2.32.0
##
## loaded via a namespace (and not attached):
## [1] jsonlite_1.8.8 shape_1.4.6.1
## [3] magrittr_2.0.3 magick_2.8.3
## [5] GenomicFeatures_1.56.0 farver_2.1.1
## [7] rmarkdown_2.26 BiocIO_1.14.0
## [9] zlibbioc_1.50.0 vctrs_0.6.5
## [11] memoise_2.0.1 Rsamtools_2.20.0
## [13] RCurl_1.98-1.14 rstatix_0.7.2
## [15] tinytex_0.50 progress_1.2.3
## [17] htmltools_0.5.8.1 S4Arrays_1.4.0
## [19] BiocBaseUtils_1.6.0 AnnotationHub_3.12.0
## [21] lambda.r_1.2.4 curl_5.2.1
## [23] broom_1.0.5 pROC_1.18.5
## [25] SparseArray_1.4.0 sass_0.4.9
## [27] bslib_0.7.0 plyr_1.8.9
## [29] httr2_1.0.1 zoo_1.8-12
## [31] futile.options_1.0.1 cachem_1.0.8
## [33] GenomicAlignments_1.40.0 mime_0.12
## [35] lifecycle_1.0.4 iterators_1.0.14
## [37] pkgconfig_2.0.3 R6_2.5.1
## [39] fastmap_1.1.1 GenomeInfoDbData_1.2.12
## [41] digest_0.6.35 colorspace_2.1-0
## [43] AnnotationDbi_1.66.0 ps_1.7.6
## [45] ExperimentHub_2.12.0 RSQLite_2.3.6
## [47] ggpubr_0.6.0 labeling_0.4.3
## [49] filelock_1.0.3 km.ci_0.5-6
## [51] fansi_1.0.6 httr_1.4.7
## [53] abind_1.4-5 compiler_4.4.0
## [55] bit64_4.0.5 withr_3.0.0
## [57] backports_1.4.1 BiocParallel_1.38.0
## [59] carData_3.0-5 DBI_1.2.2
## [61] highr_0.10 ggsignif_0.6.4
## [63] biomaRt_2.60.0 rappdirs_0.3.3
## [65] DelayedArray_0.30.0 rjson_0.2.21
## [67] tools_4.4.0 chromote_0.2.0
## [69] glue_1.7.0 restfulr_0.0.15
## [71] promises_1.3.0 checkmate_2.3.1
## [73] generics_0.1.3 gtable_0.3.5
## [75] KMsurv_0.1-5 tzdb_0.4.0
## [77] tidyr_1.3.1 survminer_0.4.9
## [79] websocket_1.4.1 data.table_1.15.4
## [81] hms_1.1.3 car_3.1-2
## [83] xml2_1.3.6 utf8_1.2.4
## [85] XVector_0.44.0 BiocVersion_3.19.1
## [87] foreach_1.5.2 pillar_1.9.0
## [89] stringr_1.5.1 later_1.3.2
## [91] splines_4.4.0 BiocFileCache_2.12.0
## [93] lattice_0.22-6 rtracklayer_1.64.0
## [95] bit_4.0.5 tidyselect_1.2.1
## [97] Biostrings_2.72.0 knitr_1.46
## [99] gridExtra_2.3 bookdown_0.39
## [101] xfun_0.43 stringi_1.8.3
## [103] UCSC.utils_1.0.0 yaml_2.3.8
## [105] evaluate_0.23 codetools_0.2-20
## [107] tibble_3.2.1 BiocManager_1.30.22
## [109] cli_3.6.2 xtable_1.8-4
## [111] munsell_0.5.1 processx_3.8.4
## [113] jquerylib_0.1.4 survMisc_0.5.6
## [115] Rcpp_1.0.12 GenomicDataCommons_1.28.0
## [117] dbplyr_2.5.0 png_0.1-8
## [119] XML_3.99-0.16.1 readr_2.1.5
## [121] blob_1.2.4 prettyunits_1.2.0
## [123] bitops_1.0-7 scales_1.3.0
## [125] purrr_1.0.2 crayon_1.5.2
## [127] rlang_1.1.3 KEGGREST_1.44.0
## [129] rvest_1.0.4 formatR_1.14