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 <- tryCatch({
curatedTCGAData(
diseaseCode = "BRCA",
assays = "RNASeq2GeneNorm",
version = "1.1.38",
dry.run = FALSE
)
}, error = function(err) {
NULL
})
brca <- curatedTCGAData(diseaseCode = "BRCA", assays = "RNASeq2GeneNorm",
version = "1.1.38", dry.run = FALSE)
brca <- TCGAutils::TCGAsplitAssays(brca, c('01','11'))
xdata.raw <- t(cbind(assay(brca[[1]]), assay(brca[[2]])))
# Get matches between survival and assay data
class.v <- TCGAbiospec(rownames(xdata.raw))$sample_definition %>% factor
names(class.v) <- rownames(xdata.raw)
# keep features with standard deviation > 0
xdata.raw <- xdata.raw %>%
{ (apply(., 2, sd) != 0) } %>%
{ xdata.raw[, .] } %>%
scale()
set.seed(params$seed)
small.subset <- c('CD5', 'CSF2RB', 'HSF1', 'IRGC', 'LRRC37A6P', 'NEUROG2',
'NLRC4', 'PDE11A', 'PIK3CB', 'QARS', 'RPGRIP1L', 'SDC1',
'TMEM31', 'YME1L1', 'ZBTB11',
sample(colnames(xdata.raw), 100))
xdata <- xdata.raw[, small.subset[small.subset %in% colnames(xdata.raw)]]
ydata <- class.v
Fit model model penalizing by the hubs using the cross-validation function by
cv.glmHub
.
fitted <- cv.glmHub(xdata, ydata,
family = 'binomial',
network = 'correlation',
nlambda = 1000,
network.options = networkOptions(cutoff = .6,
min.degree = .2))
Shows the results of 1000
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(.))$external_gene_name,
coefficient = .,
stringsAsFactors = FALSE)
} %>%
arrange(gene.name) %>%
knitr::kable()
geneNames(names(coefs.v)) %>% { hallmarks(.$external_gene_name)$heatmap }
Histogram of predicted response
ROC curve
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] stats4 stats graphics grDevices utils datasets methods
## [8] base
##
## other attached packages:
## [1] glmSparseNet_1.20.1 glmnet_4.1-8
## [3] Matrix_1.6-5 TCGAutils_1.22.2
## [5] curatedTCGAData_1.24.0 MultiAssayExperiment_1.28.0
## [7] SummarizedExperiment_1.32.0 Biobase_2.62.0
## [9] GenomicRanges_1.54.1 GenomeInfoDb_1.38.5
## [11] IRanges_2.36.0 S4Vectors_0.40.2
## [13] BiocGenerics_0.48.1 MatrixGenerics_1.14.0
## [15] matrixStats_1.2.0 futile.logger_1.4.3
## [17] survival_3.5-7 ggplot2_3.4.4
## [19] dplyr_1.1.4 BiocStyle_2.30.0
##
## loaded via a namespace (and not attached):
## [1] DBI_1.2.1 bitops_1.0-7
## [3] formatR_1.14 biomaRt_2.58.2
## [5] rlang_1.1.3 magrittr_2.0.3
## [7] compiler_4.3.2 RSQLite_2.3.5
## [9] GenomicFeatures_1.54.3 png_0.1-8
## [11] vctrs_0.6.5 rvest_1.0.3
## [13] stringr_1.5.1 shape_1.4.6
## [15] pkgconfig_2.0.3 crayon_1.5.2
## [17] fastmap_1.1.1 dbplyr_2.4.0
## [19] XVector_0.42.0 ellipsis_0.3.2
## [21] utf8_1.2.4 Rsamtools_2.18.0
## [23] promises_1.2.1 rmarkdown_2.25
## [25] tzdb_0.4.0 purrr_1.0.2
## [27] bit_4.0.5 xfun_0.41
## [29] zlibbioc_1.48.0 cachem_1.0.8
## [31] jsonlite_1.8.8 progress_1.2.3
## [33] blob_1.2.4 later_1.3.2
## [35] DelayedArray_0.28.0 BiocParallel_1.36.0
## [37] interactiveDisplayBase_1.40.0 parallel_4.3.2
## [39] prettyunits_1.2.0 R6_2.5.1
## [41] stringi_1.8.3 bslib_0.6.1
## [43] rtracklayer_1.62.0 jquerylib_0.1.4
## [45] iterators_1.0.14 Rcpp_1.0.12
## [47] bookdown_0.37 knitr_1.45
## [49] readr_2.1.5 httpuv_1.6.14
## [51] splines_4.3.2 tidyselect_1.2.0
## [53] abind_1.4-5 yaml_2.3.8
## [55] codetools_0.2-19 curl_5.2.0
## [57] lattice_0.22-5 tibble_3.2.1
## [59] shiny_1.8.0 withr_3.0.0
## [61] KEGGREST_1.42.0 evaluate_0.23
## [63] lambda.r_1.2.4 BiocFileCache_2.10.1
## [65] xml2_1.3.6 ExperimentHub_2.10.0
## [67] Biostrings_2.70.2 pillar_1.9.0
## [69] BiocManager_1.30.22 filelock_1.0.3
## [71] foreach_1.5.2 generics_0.1.3
## [73] RCurl_1.98-1.14 BiocVersion_3.18.1
## [75] hms_1.1.3 munsell_0.5.0
## [77] scales_1.3.0 xtable_1.8-4
## [79] glue_1.7.0 tools_4.3.2
## [81] BiocIO_1.12.0 AnnotationHub_3.10.0
## [83] GenomicAlignments_1.38.2 forcats_1.0.0
## [85] XML_3.99-0.16.1 grid_4.3.2
## [87] AnnotationDbi_1.64.1 colorspace_2.1-0
## [89] GenomeInfoDbData_1.2.11 restfulr_0.0.15
## [91] cli_3.6.2 rappdirs_0.3.3
## [93] futile.options_1.0.1 fansi_1.0.6
## [95] GenomicDataCommons_1.26.0 S4Arrays_1.2.0
## [97] gtable_0.3.4 sass_0.4.8
## [99] digest_0.6.34 SparseArray_1.2.3
## [101] rjson_0.2.21 memoise_2.0.1
## [103] htmltools_0.5.7 lifecycle_1.0.4
## [105] httr_1.4.7 mime_0.12
## [107] bit64_4.0.5