Example for Survival Data – Prostate Adenocarcinoma
2022-05-15
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(glmSparseNet)
#
# Some general options for futile.logger the debugging package
.Last.value <- flog.layout(layout.format('[~l] ~m'))
.Last.value <- glmSparseNet:::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 }## Error in curl::curl_fetch_memory(url, handle = handle): OpenSSL SSL_connect: SSL_ERROR_SYSCALL in connection to chat.lionproject.net:443
## Request failed [ERROR]. Retrying in 2 seconds...
## Error in curl::curl_fetch_memory(url, handle = handle): OpenSSL SSL_connect: SSL_ERROR_SYSCALL in connection to chat.lionproject.net:443
## Request failed [ERROR]. Retrying in 2 seconds...## Cannot call Hallmark API, please try again later.## NULL5.3 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 4.2.0 (2022-04-22)
## Platform: x86_64-pc-linux-gnu (64-bit)
## Running under: Ubuntu 20.04.4 LTS
##
## Matrix products: default
## BLAS: /home/biocbuild/bbs-3.15-bioc/R/lib/libRblas.so
## LAPACK: /home/biocbuild/bbs-3.15-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_1.7.3 reshape2_1.4.4
## [3] forcats_0.5.1 glmSparseNet_1.14.1
## [5] glmnet_4.1-4 Matrix_1.4-1
## [7] TCGAutils_1.16.0 curatedTCGAData_1.18.0
## [9] MultiAssayExperiment_1.22.0 SummarizedExperiment_1.26.1
## [11] Biobase_2.56.0 GenomicRanges_1.48.0
## [13] GenomeInfoDb_1.32.2 IRanges_2.30.0
## [15] S4Vectors_0.34.0 BiocGenerics_0.42.0
## [17] MatrixGenerics_1.8.0 matrixStats_0.62.0
## [19] futile.logger_1.4.3 survival_3.3-1
## [21] ggplot2_3.3.6 dplyr_1.0.9
## [23] BiocStyle_2.24.0
##
## loaded via a namespace (and not attached):
## [1] backports_1.4.1 AnnotationHub_3.4.0
## [3] BiocFileCache_2.4.0 plyr_1.8.7
## [5] splines_4.2.0 BiocParallel_1.30.2
## [7] digest_0.6.29 foreach_1.5.2
## [9] htmltools_0.5.2 magick_2.7.3
## [11] fansi_1.0.3 magrittr_2.0.3
## [13] memoise_2.0.1 tzdb_0.3.0
## [15] Biostrings_2.64.0 readr_2.1.2
## [17] prettyunits_1.1.1 colorspace_2.0-3
## [19] blob_1.2.3 rvest_1.0.2
## [21] rappdirs_0.3.3 xfun_0.31
## [23] crayon_1.5.1 RCurl_1.98-1.6
## [25] jsonlite_1.8.0 zoo_1.8-10
## [27] iterators_1.0.14 glue_1.6.2
## [29] survminer_0.4.9 GenomicDataCommons_1.20.1
## [31] gtable_0.3.0 zlibbioc_1.42.0
## [33] XVector_0.36.0 DelayedArray_0.22.0
## [35] car_3.0-13 shape_1.4.6
## [37] abind_1.4-5 scales_1.2.0
## [39] futile.options_1.0.1 DBI_1.1.2
## [41] rstatix_0.7.0 Rcpp_1.0.8.3
## [43] xtable_1.8-4 progress_1.2.2
## [45] bit_4.0.4 km.ci_0.5-6
## [47] httr_1.4.3 ellipsis_0.3.2
## [49] pkgconfig_2.0.3 XML_3.99-0.9
## [51] farver_2.1.0 sass_0.4.1
## [53] dbplyr_2.1.1 utf8_1.2.2
## [55] tidyselect_1.1.2 labeling_0.4.2
## [57] rlang_1.0.2 later_1.3.0
## [59] AnnotationDbi_1.58.0 munsell_0.5.0
## [61] BiocVersion_3.15.2 tools_4.2.0
## [63] cachem_1.0.6 cli_3.3.0
## [65] generics_0.1.2 RSQLite_2.2.14
## [67] ExperimentHub_2.4.0 broom_0.8.0
## [69] evaluate_0.15 stringr_1.4.0
## [71] fastmap_1.1.0 yaml_2.3.5
## [73] knitr_1.39 bit64_4.0.5
## [75] survMisc_0.5.6 purrr_0.3.4
## [77] KEGGREST_1.36.0 mime_0.12
## [79] formatR_1.12 xml2_1.3.3
## [81] biomaRt_2.52.0 compiler_4.2.0
## [83] filelock_1.0.2 curl_4.3.2
## [85] png_0.1-7 interactiveDisplayBase_1.34.0
## [87] ggsignif_0.6.3 tibble_3.1.7
## [89] bslib_0.3.1 stringi_1.7.6
## [91] highr_0.9 GenomicFeatures_1.48.1
## [93] lattice_0.20-45 KMsurv_0.1-5
## [95] vctrs_0.4.1 pillar_1.7.0
## [97] lifecycle_1.0.1 BiocManager_1.30.17
## [99] jquerylib_0.1.4 data.table_1.14.2
## [101] bitops_1.0-7 httpuv_1.6.5
## [103] rtracklayer_1.56.0 R6_2.5.1
## [105] BiocIO_1.6.0 bookdown_0.26
## [107] promises_1.2.0.1 gridExtra_2.3
## [109] codetools_0.2-18 lambda.r_1.2.4
## [111] assertthat_0.2.1 rjson_0.2.21
## [113] withr_2.5.0 GenomicAlignments_1.32.0
## [115] Rsamtools_2.12.0 GenomeInfoDbData_1.2.8
## [117] hms_1.1.1 tidyr_1.2.0
## [119] rmarkdown_2.14 carData_3.0-5
## [121] ggpubr_0.4.0 pROC_1.18.0
## [123] shiny_1.7.1 restfulr_0.0.13