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.
skcm <- curatedTCGAData(diseaseCode = 'SKCM', assays = 'RNASeq2GeneNorm',
version = '1.1.38', dry.run = FALSE)
Build the survival data from the clinical columns.
xdata
and ydata
skcm.metastatic <- TCGAutils::TCGAsplitAssays(skcm, '06')
xdata.raw <- t(assay(skcm.metastatic[[1]]))
# Get survival information
ydata.raw <- colData(skcm.metastatic) %>% 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
ydata.raw <- colData(skcm) %>% 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('FOXL2', 'KLHL5', 'PCYT2', 'SLC6A10P', 'STRAP', 'TMEM33',
'WT1-AS', sample(colnames(xdata.raw), 100))
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
.
fitted <- cv.glmHub(
xdata,
Surv(ydata$time, ydata$status),
family = 'cox',
foldid = glmSparseNet:::balanced.cv.folds(!!ydata$status)$output,
network = 'correlation',
network.options = networkOptions(min.degree = .2,
cutoff = .6)
)
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(ensembl.id = names(.),
gene.name = geneNames(names(.))$external_gene_name,
coefficient = .,
stringsAsFactors = FALSE)
} %>%
arrange(gene.name) %>%
knitr::kable()
ensembl.id | gene.name | coefficient | |
---|---|---|---|
PCYT2 | PCYT2 | AMICA1 | 0.0646641 |
AMICA1 | AMICA1 | C4orf49 | -0.2758400 |
C4orf49 | C4orf49 | PCYT2 | -0.0059089 |
geneNames(names(coefs.v)) %>% { hallmarks(.$external_gene_name)$heatmap }
## Error in curl::curl_fetch_memory(url, handle = handle): Failed to connect to chat.lionproject.net port 443 after 116 ms: Connection refused
## Request failed [ERROR]. Retrying in 1.2 seconds...
## Error in curl::curl_fetch_memory(url, handle = handle): Failed to connect to chat.lionproject.net port 443 after 7124 ms: Connection refused
## Request failed [ERROR]. Retrying in 1.6 seconds...
## Cannot call Hallmark API, please try again later.
## NULL
separate2GroupsCox(as.vector(coefs.v),
xdata[, names(coefs.v)],
ydata,
plot.title = 'Full dataset', legend.outside = FALSE)
## $pvalue
## [1] 0.0001269853
##
## $plot
##
## $km
## Call: survfit(formula = survival::Surv(time, status) ~ group, data = prognostic.index.df)
##
## n events median 0.95LCL 0.95UCL
## Low risk 180 79 4000 2927 6164
## High risk 179 114 2005 1524 2829
sessionInfo()
## R version 4.3.0 RC (2023-04-13 r84266)
## Platform: aarch64-apple-darwin20 (64-bit)
## Running under: macOS Monterey 12.6.1
##
## Matrix products: default
## BLAS: /Library/Frameworks/R.framework/Versions/4.3-arm64/Resources/lib/libRblas.0.dylib
## LAPACK: /Library/Frameworks/R.framework/Versions/4.3-arm64/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_1.18.0
## [5] glmnet_4.1-7 Matrix_1.5-4
## [7] TCGAutils_1.20.0 curatedTCGAData_1.21.2
## [9] MultiAssayExperiment_1.26.0 SummarizedExperiment_1.30.1
## [11] Biobase_2.60.0 GenomicRanges_1.52.0
## [13] GenomeInfoDb_1.36.0 IRanges_2.34.0
## [15] S4Vectors_0.38.1 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_1.1.1
## [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_0.6.1
## [11] memoise_2.0.1 Rsamtools_2.16.0
## [13] RCurl_1.98-1.12 rstatix_0.7.2
## [15] htmltools_0.5.5 S4Arrays_1.0.1
## [17] progress_1.2.2 AnnotationHub_3.8.0
## [19] lambda.r_1.2.4 curl_5.0.0
## [21] broom_1.0.4 pROC_1.18.0
## [23] sass_0.4.5 bslib_0.4.2
## [25] plyr_1.8.8 zoo_1.8-12
## [27] futile.options_1.0.1 cachem_1.0.7
## [29] GenomicAlignments_1.36.0 mime_0.12
## [31] lifecycle_1.0.3 iterators_1.0.14
## [33] pkgconfig_2.0.3 R6_2.5.1
## [35] fastmap_1.1.1 GenomeInfoDbData_1.2.10
## [37] shiny_1.7.4 digest_0.6.31
## [39] colorspace_2.1-0 AnnotationDbi_1.62.1
## [41] ExperimentHub_2.8.0 RSQLite_2.3.1
## [43] ggpubr_0.6.0 filelock_1.0.2
## [45] labeling_0.4.2 km.ci_0.5-6
## [47] fansi_1.0.4 abind_1.4-5
## [49] httr_1.4.5 compiler_4.3.0
## [51] bit64_4.0.5 withr_2.5.0
## [53] backports_1.4.1 BiocParallel_1.34.1
## [55] carData_3.0-5 DBI_1.1.3
## [57] highr_0.10 ggsignif_0.6.4
## [59] biomaRt_2.56.0 rappdirs_0.3.3
## [61] DelayedArray_0.26.2 rjson_0.2.21
## [63] tools_4.3.0 interactiveDisplayBase_1.38.0
## [65] httpuv_1.6.9 glue_1.6.2
## [67] restfulr_0.0.15 promises_1.2.0.1
## [69] generics_0.1.3 gtable_0.3.3
## [71] KMsurv_0.1-5 tzdb_0.3.0
## [73] tidyr_1.3.0 survminer_0.4.9
## [75] data.table_1.14.8 hms_1.1.3
## [77] car_3.1-2 xml2_1.3.3
## [79] utf8_1.2.3 XVector_0.40.0
## [81] BiocVersion_3.17.1 foreach_1.5.2
## [83] pillar_1.9.0 stringr_1.5.0
## [85] later_1.3.0 splines_4.3.0
## [87] BiocFileCache_2.8.0 lattice_0.21-8
## [89] rtracklayer_1.60.0 bit_4.0.5
## [91] tidyselect_1.2.0 Biostrings_2.68.0
## [93] knitr_1.42 gridExtra_2.3
## [95] bookdown_0.33 xfun_0.38
## [97] stringi_1.7.12 yaml_2.3.7
## [99] evaluate_0.20 codetools_0.2-19
## [101] tibble_3.2.1 BiocManager_1.30.20
## [103] cli_3.6.1 xtable_1.8-4
## [105] munsell_0.5.0 jquerylib_0.1.4
## [107] survMisc_0.5.6 Rcpp_1.0.10
## [109] GenomicDataCommons_1.24.0 dbplyr_2.3.2
## [111] png_0.1-8 XML_3.99-0.14
## [113] ellipsis_0.3.2 readr_2.1.4
## [115] blob_1.2.4 prettyunits_1.1.1
## [117] bitops_1.0-7 scales_1.2.1
## [119] purrr_1.0.1 crayon_1.5.2
## [121] rlang_1.1.0 KEGGREST_1.40.0
## [123] rvest_1.0.3 formatR_1.14