Example for Survival Data – Breast Invasive Carcinoma
2023-04-25
Contents
0.1 Instalation
if (!require("BiocManager"))
install.packages("BiocManager")
BiocManager::install("glmSparseNet")1 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())2 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 107 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.
brca <- curatedTCGAData(diseaseCode = "BRCA", assays = "RNASeq2GeneNorm",
version = "1.1.38", dry.run = FALSE)# keep only solid tumour (code: 01)
brca.primary.solid.tumor <- TCGAutils::TCGAsplitAssays(brca, '01')
xdata.raw <- t(assay(brca.primary.solid.tumor[[1]]))
# Get survival information
ydata.raw <- colData(brca.primary.solid.tumor) %>% as.data.frame %>%
# Keep only data relative to survival or samples
dplyr::select(patientID, vital_status,
Days.to.date.of.Death, Days.to.Date.of.Last.Contact,
days_to_death, days_to_last_followup,
Vital.Status) %>%
# Convert days to integer
dplyr::mutate(Days.to.date.of.Death = as.integer(Days.to.date.of.Death)) %>%
dplyr::mutate(
Days.to.Last.Contact = as.integer(Days.to.Date.of.Last.Contact)
) %>%
# Find max time between all days (ignoring missings)
dplyr::rowwise() %>%
dplyr::mutate(
time = max(days_to_last_followup, Days.to.date.of.Death,
Days.to.Last.Contact, 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$patientID
# Get matches between survival and assay data
xdata.raw <- xdata.raw[TCGAbarcode(rownames(xdata.raw)) %in%
rownames(ydata.raw),]
xdata.raw <- xdata.raw %>%
{ (apply(., 2, sd) != 0) } %>%
{ xdata.raw[, .] } %>%
scale
# Order ydata the same as assay
ydata.raw <- ydata.raw[TCGAbarcode(rownames(xdata.raw)), ]
# Using only a subset of genes previously selected to keep this short example.
set.seed(params$seed)
small.subset <- c('CD5', 'CSF2RB', 'IRGC', 'NEUROG2', 'NLRC4', 'PDE11A',
'PTEN', 'TP53', 'BRAF',
'PIK3CB', 'QARS', 'RFC3', 'RPGRIP1L', 'SDC1', 'TMEM31',
'YME1L1', 'ZBTB11', sample(colnames(xdata.raw), 100)) %>%
unique
xdata <- xdata.raw[, small.subset[small.subset %in% colnames(xdata.raw)]]
ydata <- ydata.raw %>% dplyr::select(time, status)3 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',
lambda = buildLambda(1),
network = 'correlation',
network.options = networkOptions(cutoff = .6,
min.degree = .2))## Warning in regularize.values(x, y, ties, missing(ties), na.rm = na.rm):
## collapsing to unique 'x' values
## Warning in regularize.values(x, y, ties, missing(ties), na.rm = na.rm):
## collapsing to unique 'x' values
## Warning in regularize.values(x, y, ties, missing(ties), na.rm = na.rm):
## collapsing to unique 'x' values
## Warning in regularize.values(x, y, ties, missing(ties), na.rm = na.rm):
## collapsing to unique 'x' values
## Warning in regularize.values(x, y, ties, missing(ties), na.rm = na.rm):
## collapsing to unique 'x' values
## Warning in regularize.values(x, y, ties, missing(ties), na.rm = na.rm):
## collapsing to unique 'x' values
## Warning in regularize.values(x, y, ties, missing(ties), na.rm = na.rm):
## collapsing to unique 'x' values
## Warning in regularize.values(x, y, ties, missing(ties), na.rm = na.rm):
## collapsing to unique 'x' values
## Warning in regularize.values(x, y, ties, missing(ties), na.rm = na.rm):
## collapsing to unique 'x' values
## Warning in regularize.values(x, y, ties, missing(ties), na.rm = na.rm):
## collapsing to unique 'x' values4 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)
4.1 Coefficients of selected model from Cross-Validation
Taking the best model described by lambda.min
coefs.v <- coef(fitted, s = 'lambda.min')[,1] %>% { .[. != 0]}## Warning in regularize.values(x, y, ties, missing(ties), na.rm = na.rm):
## collapsing to unique 'x' valuescoefs.v %>% {
data.frame(gene.name = names(.),
coefficient = .,
stringsAsFactors = FALSE)
} %>%
arrange(gene.name) %>%
knitr::kable()| gene.name | coefficient | |
|---|---|---|
| CD5 | CD5 | -0.16632 |
4.2 Hallmarks of Cancer
names(coefs.v) %>% { hallmarks(.)$heatmap }## Error in curl::curl_fetch_memory(url, handle = handle): error:0A000126:SSL routines::unexpected eof while reading
## Request failed [ERROR]. Retrying in 1.6 seconds...## Error in curl::curl_fetch_memory(url, handle = handle): error:0A000126:SSL routines::unexpected eof while reading
## Request failed [ERROR]. Retrying in 3 seconds...## Cannot call Hallmark API, please try again later.## NULL4.3 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] 0.001237802
##
## $plot
##
## $km
## Call: survfit(formula = survival::Surv(time, status) ~ group, data = prognostic.index.df)
##
## n events median 0.95LCL 0.95UCL
## Low risk 540 58 3959 3492 NA
## High risk 540 94 3738 3262 44565 Session Info
sessionInfo()## R version 4.3.0 RC (2023-04-13 r84269)
## Platform: x86_64-pc-linux-gnu (64-bit)
## Running under: Ubuntu 22.04.2 LTS
##
## Matrix products: default
## BLAS: /home/biocbuild/bbs-3.17-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_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] VennDiagram_1.7.3 reshape2_1.4.4
## [3] forcats_1.0.0 glmSparseNet_1.18.0
## [5] glmnet_4.1-7 Matrix_1.5-4
## [7] TCGAutils_1.20.0 curatedTCGAData_1.21.3
## [9] MultiAssayExperiment_1.26.0 SummarizedExperiment_1.30.0
## [11] Biobase_2.60.0 GenomicRanges_1.52.0
## [13] GenomeInfoDb_1.36.0 IRanges_2.34.0
## [15] S4Vectors_0.38.0 BiocGenerics_0.46.0
## [17] MatrixGenerics_1.12.0 matrixStats_0.63.0
## [19] futile.logger_1.4.3 survival_3.5-5
## [21] ggplot2_3.4.2 dplyr_1.1.2
## [23] BiocStyle_2.28.0
##
## loaded via a namespace (and not attached):
## [1] jsonlite_1.8.4 shape_1.4.6
## [3] magrittr_2.0.3 magick_2.7.4
## [5] GenomicFeatures_1.52.0 farver_2.1.1
## [7] rmarkdown_2.21 BiocIO_1.10.0
## [9] zlibbioc_1.46.0 vctrs_0.6.2
## [11] memoise_2.0.1 Rsamtools_2.16.0
## [13] RCurl_1.98-1.12 rstatix_0.7.2
## [15] htmltools_0.5.5 progress_1.2.2
## [17] AnnotationHub_3.8.0 lambda.r_1.2.4
## [19] curl_5.0.0 broom_1.0.4
## [21] pROC_1.18.0 sass_0.4.5
## [23] bslib_0.4.2 plyr_1.8.8
## [25] zoo_1.8-12 futile.options_1.0.1
## [27] cachem_1.0.7 GenomicAlignments_1.36.0
## [29] mime_0.12 lifecycle_1.0.3
## [31] iterators_1.0.14 pkgconfig_2.0.3
## [33] R6_2.5.1 fastmap_1.1.1
## [35] GenomeInfoDbData_1.2.10 shiny_1.7.4
## [37] digest_0.6.31 colorspace_2.1-0
## [39] AnnotationDbi_1.62.0 ExperimentHub_2.8.0
## [41] RSQLite_2.3.1 ggpubr_0.6.0
## [43] filelock_1.0.2 labeling_0.4.2
## [45] km.ci_0.5-6 fansi_1.0.4
## [47] abind_1.4-5 httr_1.4.5
## [49] compiler_4.3.0 bit64_4.0.5
## [51] withr_2.5.0 backports_1.4.1
## [53] BiocParallel_1.34.0 carData_3.0-5
## [55] DBI_1.1.3 highr_0.10
## [57] ggsignif_0.6.4 biomaRt_2.56.0
## [59] rappdirs_0.3.3 DelayedArray_0.26.0
## [61] rjson_0.2.21 tools_4.3.0
## [63] interactiveDisplayBase_1.38.0 httpuv_1.6.9
## [65] glue_1.6.2 restfulr_0.0.15
## [67] promises_1.2.0.1 generics_0.1.3
## [69] gtable_0.3.3 KMsurv_0.1-5
## [71] tzdb_0.3.0 tidyr_1.3.0
## [73] survminer_0.4.9 data.table_1.14.8
## [75] hms_1.1.3 car_3.1-2
## [77] xml2_1.3.3 utf8_1.2.3
## [79] XVector_0.40.0 BiocVersion_3.17.1
## [81] foreach_1.5.2 pillar_1.9.0
## [83] stringr_1.5.0 later_1.3.0
## [85] splines_4.3.0 BiocFileCache_2.8.0
## [87] lattice_0.21-8 rtracklayer_1.60.0
## [89] bit_4.0.5 tidyselect_1.2.0
## [91] Biostrings_2.68.0 knitr_1.42
## [93] gridExtra_2.3 bookdown_0.33
## [95] xfun_0.39 stringi_1.7.12
## [97] yaml_2.3.7 evaluate_0.20
## [99] codetools_0.2-19 tibble_3.2.1
## [101] BiocManager_1.30.20 cli_3.6.1
## [103] xtable_1.8-4 munsell_0.5.0
## [105] jquerylib_0.1.4 survMisc_0.5.6
## [107] Rcpp_1.0.10 GenomicDataCommons_1.24.0
## [109] dbplyr_2.3.2 png_0.1-8
## [111] XML_3.99-0.14 ellipsis_0.3.2
## [113] readr_2.1.4 blob_1.2.4
## [115] prettyunits_1.1.1 bitops_1.0-7
## [117] scales_1.2.1 purrr_1.0.1
## [119] crayon_1.5.2 rlang_1.1.0
## [121] KEGGREST_1.40.0 rvest_1.0.3
## [123] formatR_1.14