if (!require("BiocManager"))
install.packages("BiocManager")
BiocManager::install("glmSparseNet")
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())
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)
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))
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)
Taking the best model described by lambda.min
coefs.v <- coef(fitted, s = 'lambda.min')[,1] %>% { .[. != 0]}
coefs.v %>% {
data.frame(gene.name = names(.),
coefficient = .,
stringsAsFactors = FALSE)
} %>%
arrange(gene.name) %>%
knitr::kable()
separate2GroupsCox(as.vector(coefs.v),
xdata[, names(coefs.v)],
ydata,
plot.title = 'Full dataset', legend.outside = FALSE)
sessionInfo()
## R version 4.3.2 Patched (2023-11-01 r85457)
## Platform: x86_64-apple-darwin20 (64-bit)
## Running under: macOS Monterey 12.7.1
##
## Matrix products: default
## BLAS: /Library/Frameworks/R.framework/Versions/4.3-x86_64/Resources/lib/libRblas.0.dylib
## LAPACK: /Library/Frameworks/R.framework/Versions/4.3-x86_64/Resources/lib/libRlapack.dylib; LAPACK version 3.11.0
##
## locale:
## [1] C/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
##
## time zone: America/New_York
## tzcode source: internal
##
## 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_1.20.1
## [5] glmnet_4.1-8 Matrix_1.6-5
## [7] TCGAutils_1.22.2 curatedTCGAData_1.24.0
## [9] MultiAssayExperiment_1.28.0 SummarizedExperiment_1.32.0
## [11] Biobase_2.62.0 GenomicRanges_1.54.1
## [13] GenomeInfoDb_1.38.5 IRanges_2.36.0
## [15] S4Vectors_0.40.2 BiocGenerics_0.48.1
## [17] MatrixGenerics_1.14.0 matrixStats_1.2.0
## [19] futile.logger_1.4.3 survival_3.5-7
## [21] ggplot2_3.4.4 dplyr_1.1.4
## [23] BiocStyle_2.30.0
##
## loaded via a namespace (and not attached):
## [1] jsonlite_1.8.8 shape_1.4.6
## [3] magrittr_2.0.3 magick_2.8.2
## [5] GenomicFeatures_1.54.3 farver_2.1.1
## [7] rmarkdown_2.25 BiocIO_1.12.0
## [9] zlibbioc_1.48.0 vctrs_0.6.5
## [11] memoise_2.0.1 Rsamtools_2.18.0
## [13] RCurl_1.98-1.14 htmltools_0.5.7
## [15] S4Arrays_1.2.0 progress_1.2.3
## [17] AnnotationHub_3.10.0 lambda.r_1.2.4
## [19] curl_5.2.0 SparseArray_1.2.3
## [21] sass_0.4.8 bslib_0.6.1
## [23] plyr_1.8.9 futile.options_1.0.1
## [25] cachem_1.0.8 GenomicAlignments_1.38.2
## [27] mime_0.12 lifecycle_1.0.4
## [29] iterators_1.0.14 pkgconfig_2.0.3
## [31] R6_2.5.1 fastmap_1.1.1
## [33] GenomeInfoDbData_1.2.11 shiny_1.8.0
## [35] digest_0.6.34 colorspace_2.1-0
## [37] AnnotationDbi_1.64.1 ExperimentHub_2.10.0
## [39] RSQLite_2.3.5 filelock_1.0.3
## [41] labeling_0.4.3 fansi_1.0.6
## [43] httr_1.4.7 abind_1.4-5
## [45] compiler_4.3.2 bit64_4.0.5
## [47] withr_3.0.0 BiocParallel_1.36.0
## [49] DBI_1.2.1 highr_0.10
## [51] biomaRt_2.58.2 rappdirs_0.3.3
## [53] DelayedArray_0.28.0 rjson_0.2.21
## [55] tools_4.3.2 interactiveDisplayBase_1.40.0
## [57] httpuv_1.6.14 glue_1.7.0
## [59] restfulr_0.0.15 promises_1.2.1
## [61] generics_0.1.3 gtable_0.3.4
## [63] tzdb_0.4.0 hms_1.1.3
## [65] xml2_1.3.6 utf8_1.2.4
## [67] XVector_0.42.0 BiocVersion_3.18.1
## [69] foreach_1.5.2 pillar_1.9.0
## [71] stringr_1.5.1 later_1.3.2
## [73] splines_4.3.2 BiocFileCache_2.10.1
## [75] lattice_0.22-5 rtracklayer_1.62.0
## [77] bit_4.0.5 tidyselect_1.2.0
## [79] Biostrings_2.70.2 knitr_1.45
## [81] bookdown_0.37 xfun_0.41
## [83] stringi_1.8.3 yaml_2.3.8
## [85] evaluate_0.23 codetools_0.2-19
## [87] tibble_3.2.1 BiocManager_1.30.22
## [89] cli_3.6.2 xtable_1.8-4
## [91] munsell_0.5.0 jquerylib_0.1.4
## [93] Rcpp_1.0.12 GenomicDataCommons_1.26.0
## [95] dbplyr_2.4.0 png_0.1-8
## [97] XML_3.99-0.16.1 ellipsis_0.3.2
## [99] readr_2.1.5 blob_1.2.4
## [101] prettyunits_1.2.0 bitops_1.0-7
## [103] scales_1.3.0 purrr_1.0.2
## [105] crayon_1.5.2 rlang_1.1.3
## [107] KEGGREST_1.42.0 rvest_1.0.3
## [109] formatR_1.14