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())
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.
skcm <- curatedTCGAData(
diseaseCode = "SKCM", assays = "RNASeq2GeneNorm",
version = "1.1.38", dry.run = FALSE
)
Build the survival data from the clinical columns.
xdata
and
ydata
skcmMetastatic <- TCGAutils::TCGAsplitAssays(skcm, "06")
xdataRaw <- t(assay(skcmMetastatic[[1]]))
# Get survival information
ydataRaw <- colData(skcmMetastatic) |>
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()
# Get survival information
ydataRaw <- colData(skcm) |>
as.data.frame() |>
# Find max time between all days (ignoring missings)
dplyr::filter(
!is.na(days_to_last_followup) | !is.na(days_to_death)
) |>
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(
"FOXL2", "KLHL5", "PCYT2", "SLC6A10P", "STRAP", "TMEM33",
"WT1-AS", sample(colnames(xdataRaw), 100)
)
xdata <- xdataRaw[, smallSubset[smallSubset %in% colnames(xdataRaw)]]
ydata <- ydataRaw |> dplyr::select(time, status)
Fit model model penalizing by the hubs using the cross-validation
function by cv.glmHub
.
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.
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 | |
---|---|---|---|
AMICA1 | AMICA1 | AMICA1 | -0.2758400 |
C4orf49 | C4orf49 | C4orf49 | -0.0059089 |
PCYT2 | PCYT2 | PCYT2 | 0.0646641 |
separate2GroupsCox(as.vector(coefsCV),
xdata[, names(coefsCV)],
ydata,
plotTitle = "Full dataset", legendOutside = FALSE
)
## $pvalue
## [1] 0.0001269853
##
## $plot
##
## $km
## Call: survfit(formula = survival::Surv(time, status) ~ group, data = prognosticIndexDf)
##
## n events median 0.95LCL 0.95UCL
## Low risk - 1 180 79 4000 2927 6164
## High risk - 1 179 114 2005 1524 2829
## R version 4.4.1 (2024-06-14)
## Platform: x86_64-pc-linux-gnu
## Running under: Ubuntu 24.04.1 LTS
##
## Matrix products: default
## BLAS: /usr/lib/x86_64-linux-gnu/openblas-pthread/libblas.so.3
## LAPACK: /usr/lib/x86_64-linux-gnu/openblas-pthread/libopenblasp-r0.3.26.so; LAPACK version 3.12.0
##
## locale:
## [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C
## [3] LC_TIME=en_US.UTF-8 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: Etc/UTC
## 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_1.23.0
## [7] TCGAutils_1.25.1 curatedTCGAData_1.27.0
## [9] MultiAssayExperiment_1.31.5 SummarizedExperiment_1.35.1
## [11] Biobase_2.65.1 GenomicRanges_1.57.1
## [13] GenomeInfoDb_1.41.1 IRanges_2.39.2
## [15] S4Vectors_0.43.2 BiocGenerics_0.51.2
## [17] MatrixGenerics_1.17.0 matrixStats_1.4.1
## [19] futile.logger_1.4.3 survival_3.7-0
## [21] ggplot2_3.5.1 dplyr_1.1.4
## [23] BiocStyle_2.33.1
##
## loaded via a namespace (and not attached):
## [1] sys_3.4.2 jsonlite_1.8.9
## [3] shape_1.4.6.1 magrittr_2.0.3
## [5] GenomicFeatures_1.57.0 farver_2.1.2
## [7] rmarkdown_2.28 BiocIO_1.15.2
## [9] zlibbioc_1.51.1 vctrs_0.6.5
## [11] memoise_2.0.1 Rsamtools_2.21.2
## [13] RCurl_1.98-1.16 rstatix_0.7.2
## [15] htmltools_0.5.8.1 S4Arrays_1.5.9
## [17] BiocBaseUtils_1.7.3 progress_1.2.3
## [19] AnnotationHub_3.13.3 lambda.r_1.2.4
## [21] curl_5.2.3 broom_1.0.7
## [23] pROC_1.18.5 SparseArray_1.5.40
## [25] sass_0.4.9 bslib_0.8.0
## [27] plyr_1.8.9 httr2_1.0.5
## [29] zoo_1.8-12 futile.options_1.0.1
## [31] cachem_1.1.0 buildtools_1.0.0
## [33] GenomicAlignments_1.41.0 mime_0.12
## [35] lifecycle_1.0.4 iterators_1.0.14
## [37] pkgconfig_2.0.3 R6_2.5.1
## [39] fastmap_1.2.0 GenomeInfoDbData_1.2.12
## [41] digest_0.6.37 colorspace_2.1-1
## [43] AnnotationDbi_1.67.0 ExperimentHub_2.13.1
## [45] RSQLite_2.3.7 ggpubr_0.6.0
## [47] filelock_1.0.3 labeling_0.4.3
## [49] km.ci_0.5-6 fansi_1.0.6
## [51] httr_1.4.7 abind_1.4-8
## [53] compiler_4.4.1 bit64_4.5.2
## [55] withr_3.0.1 backports_1.5.0
## [57] BiocParallel_1.39.0 carData_3.0-5
## [59] DBI_1.2.3 highr_0.11
## [61] ggsignif_0.6.4 biomaRt_2.61.3
## [63] rappdirs_0.3.3 DelayedArray_0.31.11
## [65] rjson_0.2.23 tools_4.4.1
## [67] glue_1.7.0 restfulr_0.0.15
## [69] checkmate_2.3.2 generics_0.1.3
## [71] gtable_0.3.5 KMsurv_0.1-5
## [73] tzdb_0.4.0 tidyr_1.3.1
## [75] survminer_0.4.9 data.table_1.16.0
## [77] hms_1.1.3 car_3.1-2
## [79] xml2_1.3.6 utf8_1.2.4
## [81] XVector_0.45.0 BiocVersion_3.20.0
## [83] foreach_1.5.2 pillar_1.9.0
## [85] stringr_1.5.1 splines_4.4.1
## [87] BiocFileCache_2.13.0 lattice_0.22-6
## [89] rtracklayer_1.65.0 bit_4.5.0
## [91] tidyselect_1.2.1 maketools_1.3.0
## [93] Biostrings_2.73.2 knitr_1.48
## [95] gridExtra_2.3 xfun_0.47
## [97] stringi_1.8.4 UCSC.utils_1.1.0
## [99] yaml_2.3.10 evaluate_1.0.0
## [101] codetools_0.2-20 tibble_3.2.1
## [103] BiocManager_1.30.25 cli_3.6.3
## [105] xtable_1.8-4 munsell_0.5.1
## [107] jquerylib_0.1.4 survMisc_0.5.6
## [109] Rcpp_1.0.13 GenomicDataCommons_1.29.6
## [111] dbplyr_2.5.0 png_0.1-8
## [113] XML_3.99-0.17 readr_2.1.5
## [115] blob_1.2.4 prettyunits_1.2.0
## [117] bitops_1.0-8 scales_1.3.0
## [119] purrr_1.0.2 crayon_1.5.3
## [121] rlang_1.1.4 KEGGREST_1.45.1
## [123] rvest_1.0.4 formatR_1.14