Example for Survival Data – Prostate Adenocarcinoma
2021-10-26
Contents
1 Instalation
if (!require("BiocManager"))
install.packages("BiocManager")
BiocManager::install("glmSparseNet")2 Required Packages
library(dplyr)
library(ggplot2)
library(survival)
library(loose.rock)
library(futile.logger)
library(curatedTCGAData)
library(TCGAutils)
#
library(glmSparseNet)
#
# Some general options for futile.logger the debugging package
.Last.value <- flog.layout(layout.format('[~l] ~m'))
.Last.value <- loose.rock::show.message(FALSE)
# 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)
prad.primary.solid.tumor <- TCGAutils::TCGAsplitAssays(prad, '01')
xdata.raw <- t(assay(prad.primary.solid.tumor[[1]]))
# Get survival information
ydata.raw <- colData(prad.primary.solid.tumor) %>% 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(ydata.raw) <- ydata.raw$patientID
# keep only features that have standard deviation > 0
xdata.raw <- xdata.raw[TCGAbarcode(rownames(xdata.raw)) %in%
rownames(ydata.raw),]
xdata.raw <- xdata.raw %>%
{ (apply(., 2, sd) != 0) } %>%
{ xdata.raw[, .] } %>%
scale
# Order ydata the same as assay
ydata.raw <- ydata.raw[TCGAbarcode(rownames(xdata.raw)), ]
set.seed(params$seed)
small.subset <- c(geneNames(c('ENSG00000103091', 'ENSG00000064787',
'ENSG00000119915', 'ENSG00000120158',
'ENSG00000114491', 'ENSG00000204176',
'ENSG00000138399'))$external_gene_name,
sample(colnames(xdata.raw), 100)) %>% unique %>% sort
xdata <- xdata.raw[, small.subset[small.subset %in% colnames(xdata.raw)]]
ydata <- ydata.raw %>% dplyr::select(time, status)4 Fit models
Fit model model penalizing by the hubs using the cross-validation function by
cv.glmHub.
set.seed(params$seed)
fitted <- cv.glmHub(xdata, Surv(ydata$time, ydata$status),
family = 'cox',
nlambda = 1000,
network = 'correlation',
network.options = networkOptions(cutoff = .6,
min.degree = .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
coefs.v <- coef(fitted, s = 'lambda.min')[,1] %>% { .[. != 0]}
coefs.v %>% {
data.frame(ensembl.id = names(.),
gene.name = geneNames(names(.))$external_gene_name,
coefficient = .,
stringsAsFactors = FALSE)
} %>%
arrange(gene.name) %>%
knitr::kable()| ensembl.id | gene.name | coefficient | |
|---|---|---|---|
| AKAP9 | AKAP9 | AKAP9 | 0.2616307 |
| ALPK2 | ALPK2 | ALPK2 | -0.0714527 |
| ATP5G2 | ATP5G2 | ATP5G2 | -0.2575987 |
| C22orf32 | C22orf32 | C22orf32 | -0.2119992 |
| CSNK2A1P | CSNK2A1P | CSNK2A1P | -1.4875518 |
| MYST3 | MYST3 | MYST3 | -1.6177076 |
| NBPF10 | NBPF10 | NBPF10 | 0.4507147 |
| PFN1 | PFN1 | PFN1 | 0.4161846 |
| SCGB2A2 | SCGB2A2 | SCGB2A2 | 0.0749064 |
| SLC25A1 | SLC25A1 | SLC25A1 | -0.8484827 |
| STX4 | STX4 | STX4 | -0.1690185 |
| SYP | SYP | SYP | 0.2425939 |
| TMEM141 | TMEM141 | TMEM141 | -0.8273147 |
| UMPS | UMPS | UMPS | 0.2214068 |
| ZBTB26 | ZBTB26 | ZBTB26 | 0.3696515 |
5.2 Hallmarks of Cancer
geneNames(names(coefs.v)) %>% { hallmarks(.$external_gene_name)$heatmap }
5.3 Survival curves and Log rank test
separate2GroupsCox(as.vector(coefs.v),
xdata[, names(coefs.v)],
ydata,
plot.title = 'Full dataset', legend.outside = FALSE)## $pvalue
## [1] 0.001155155
##
## $plot
##
## $km
## Call: survfit(formula = survival::Surv(time, status) ~ group, data = prognostic.index.df)
##
## n events median 0.95LCL 0.95UCL
## Low risk 249 0 NA NA NA
## High risk 248 10 3502 3467 NA6 Session Info
sessionInfo()## R version 4.1.1 (2021-08-10)
## Platform: x86_64-pc-linux-gnu (64-bit)
## Running under: Ubuntu 20.04.3 LTS
##
## Matrix products: default
## BLAS: /home/biocbuild/bbs-3.14-bioc/R/lib/libRblas.so
## LAPACK: /home/biocbuild/bbs-3.14-bioc/R/lib/libRlapack.so
##
## 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
##
## attached base packages:
## [1] grid parallel stats4 stats graphics grDevices utils
## [8] datasets methods base
##
## other attached packages:
## [1] VennDiagram_1.6.20 reshape2_1.4.4
## [3] forcats_0.5.1 glmSparseNet_1.12.0
## [5] glmnet_4.1-2 Matrix_1.3-4
## [7] TCGAutils_1.14.0 curatedTCGAData_1.15.1
## [9] MultiAssayExperiment_1.20.0 SummarizedExperiment_1.24.0
## [11] Biobase_2.54.0 GenomicRanges_1.46.0
## [13] GenomeInfoDb_1.30.0 IRanges_2.28.0
## [15] S4Vectors_0.32.0 BiocGenerics_0.40.0
## [17] MatrixGenerics_1.6.0 matrixStats_0.61.0
## [19] futile.logger_1.4.3 loose.rock_1.2.0
## [21] survival_3.2-13 ggplot2_3.3.5
## [23] dplyr_1.0.7 BiocStyle_2.22.0
##
## loaded via a namespace (and not attached):
## [1] readxl_1.3.1 backports_1.2.1
## [3] AnnotationHub_3.2.0 BiocFileCache_2.2.0
## [5] plyr_1.8.6 splines_4.1.1
## [7] sparsebn_0.1.2 BiocParallel_1.28.0
## [9] digest_0.6.28 foreach_1.5.1
## [11] htmltools_0.5.2 magick_2.7.3
## [13] fansi_0.5.0 magrittr_2.0.1
## [15] memoise_2.0.0 openxlsx_4.2.4
## [17] tzdb_0.1.2 Biostrings_2.62.0
## [19] readr_2.0.2 prettyunits_1.1.1
## [21] colorspace_2.0-2 blob_1.2.2
## [23] rvest_1.0.2 rappdirs_0.3.3
## [25] haven_2.4.3 xfun_0.27
## [27] crayon_1.4.1 RCurl_1.98-1.5
## [29] jsonlite_1.7.2 zoo_1.8-9
## [31] iterators_1.0.13 glue_1.4.2
## [33] survminer_0.4.9 GenomicDataCommons_1.18.0
## [35] gtable_0.3.0 zlibbioc_1.40.0
## [37] XVector_0.34.0 DelayedArray_0.20.0
## [39] car_3.0-11 ccdrAlgorithm_0.0.5
## [41] shape_1.4.6 abind_1.4-5
## [43] discretecdAlgorithm_0.0.7 scales_1.1.1
## [45] futile.options_1.0.1 DBI_1.1.1
## [47] rstatix_0.7.0 Rcpp_1.0.7
## [49] xtable_1.8-4 progress_1.2.2
## [51] foreign_0.8-81 bit_4.0.4
## [53] km.ci_0.5-2 httr_1.4.2
## [55] ellipsis_0.3.2 pkgconfig_2.0.3
## [57] XML_3.99-0.8 farver_2.1.0
## [59] sass_0.4.0 dbplyr_2.1.1
## [61] utf8_1.2.2 tidyselect_1.1.1
## [63] labeling_0.4.2 rlang_0.4.12
## [65] later_1.3.0 AnnotationDbi_1.56.0
## [67] cellranger_1.1.0 munsell_0.5.0
## [69] BiocVersion_3.14.0 tools_4.1.1
## [71] cachem_1.0.6 cli_3.0.1
## [73] generics_0.1.1 RSQLite_2.2.8
## [75] ExperimentHub_2.2.0 broom_0.7.9
## [77] evaluate_0.14 stringr_1.4.0
## [79] fastmap_1.1.0 yaml_2.2.1
## [81] knitr_1.36 bit64_4.0.5
## [83] zip_2.2.0 survMisc_0.5.5
## [85] purrr_0.3.4 KEGGREST_1.34.0
## [87] mime_0.12 formatR_1.11
## [89] xml2_1.3.2 biomaRt_2.50.0
## [91] compiler_4.1.1 filelock_1.0.2
## [93] curl_4.3.2 png_0.1-7
## [95] interactiveDisplayBase_1.32.0 ggsignif_0.6.3
## [97] tibble_3.1.5 bslib_0.3.1
## [99] stringi_1.7.5 highr_0.9
## [101] sparsebnUtils_0.0.8 GenomicFeatures_1.46.0
## [103] lattice_0.20-45 KMsurv_0.1-5
## [105] vctrs_0.3.8 pillar_1.6.4
## [107] lifecycle_1.0.1 BiocManager_1.30.16
## [109] jquerylib_0.1.4 data.table_1.14.2
## [111] bitops_1.0-7 httpuv_1.6.3
## [113] rtracklayer_1.54.0 R6_2.5.1
## [115] BiocIO_1.4.0 bookdown_0.24
## [117] promises_1.2.0.1 gridExtra_2.3
## [119] rio_0.5.27 codetools_0.2-18
## [121] lambda.r_1.2.4 assertthat_0.2.1
## [123] rjson_0.2.20 withr_2.4.2
## [125] GenomicAlignments_1.30.0 Rsamtools_2.10.0
## [127] GenomeInfoDbData_1.2.7 hms_1.1.1
## [129] tidyr_1.1.4 rmarkdown_2.11
## [131] carData_3.0-4 ggpubr_0.4.0
## [133] pROC_1.18.0 shiny_1.7.1
## [135] restfulr_0.0.13