if (!require("BiocManager")) {
install.packages("BiocManager")
}
BiocManager::install("glmSparseNet")
library(dplyr)
library(ggplot2)
library(survival)
library(futile.logger)
library(curatedTCGAData)
library(MultiAssayExperiment)
library(TCGAutils)
#
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.
brca <- curatedTCGAData(
diseaseCode = "BRCA", assays = "RNASeq2GeneNorm",
version = "1.1.38", dry.run = FALSE
)
brca <- TCGAutils::TCGAsplitAssays(brca, c("01", "11"))
xdataRaw <- t(cbind(assay(brca[[1]]), assay(brca[[2]])))
# Get matches between survival and assay data
classV <- TCGAbiospec(rownames(xdataRaw))$sample_definition |> factor()
names(classV) <- rownames(xdataRaw)
# keep features with standard deviation > 0
xdataRaw <- xdataRaw[, apply(xdataRaw, 2, sd) != 0] |>
scale()
set.seed(params$seed)
smallSubset <- c(
"CD5", "CSF2RB", "HSF1", "IRGC", "LRRC37A6P", "NEUROG2",
"NLRC4", "PDE11A", "PIK3CB", "QARS", "RPGRIP1L", "SDC1",
"TMEM31", "YME1L1", "ZBTB11",
sample(colnames(xdataRaw), 100)
)
xdata <- xdataRaw[, smallSubset[smallSubset %in% colnames(xdataRaw)]]
ydata <- classV
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,
options = networkOptions(
cutoff = .6,
minDegree = .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
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 | |
---|---|---|---|
(Intercept) | (Intercept) | (Intercept) | -6.8189813 |
AMOTL1 | AMOTL1 | AMOTL1 | 0.4430643 |
ATR | ATR | ATR | 1.2498304 |
B3GALT2 | B3GALT2 | B3GALT2 | -0.0867011 |
BAG2 | BAG2 | BAG2 | -0.1841676 |
C16orf82 | C16orf82 | C16orf82 | 0.0396368 |
CD5 | CD5 | CD5 | -1.1200445 |
CIITA | CIITA | CIITA | 0.4256103 |
DCP1A | DCP1A | DCP1A | 0.2994599 |
FAM86B1 | FAM86B1 | FAM86B1 | 0.2025463 |
FNIP2 | FNIP2 | FNIP2 | 0.6101759 |
GDF11 | GDF11 | GDF11 | -0.2676642 |
GNG11 | GNG11 | GNG11 | 3.0659066 |
GREM2 | GREM2 | GREM2 | -0.2014884 |
GZMB | GZMB | GZMB | -2.7663574 |
HAX1 | HAX1 | HAX1 | -0.1516837 |
IL2 | IL2 | IL2 | 0.6327083 |
MMP28 | MMP28 | MMP28 | -0.8438024 |
MS4A4A | MS4A4A | MS4A4A | 1.1614779 |
NDRG2 | NDRG2 | NDRG2 | 1.1142519 |
NLRC4 | NLRC4 | NLRC4 | -1.4434578 |
PIK3CB | PIK3CB | PIK3CB | -0.3880002 |
ZBTB11 | ZBTB11 | ZBTB11 | -0.3325729 |
## [INFO] Misclassified (11)
## [INFO] * False primary solid tumour: 7
## [INFO] * False normal : 4
Histogram of predicted response
ROC curve
## Setting levels: control = Primary Solid Tumor, case = Solid Tissue Normal
## Setting direction: controls < cases
## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
sessionInfo()
## R version 4.4.0 alpha (2024-03-27 r86216)
## Platform: aarch64-apple-darwin20
## Running under: macOS Ventura 13.6.5
##
## Matrix products: default
## BLAS: /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/lib/libRblas.0.dylib
## LAPACK: /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/lib/libRlapack.dylib; LAPACK version 3.12.0
##
## locale:
## [1] en_US.UTF-8/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_1.22.0 TCGAutils_1.24.0
## [3] curatedTCGAData_1.25.4 MultiAssayExperiment_1.30.0
## [5] SummarizedExperiment_1.34.0 Biobase_2.64.0
## [7] GenomicRanges_1.56.0 GenomeInfoDb_1.40.0
## [9] IRanges_2.38.0 S4Vectors_0.42.0
## [11] BiocGenerics_0.50.0 MatrixGenerics_1.16.0
## [13] matrixStats_1.2.0 futile.logger_1.4.3
## [15] survival_3.5-8 ggplot2_3.5.0
## [17] dplyr_1.1.4 BiocStyle_2.32.0
##
## loaded via a namespace (and not attached):
## [1] jsonlite_1.8.8 shape_1.4.6.1
## [3] magrittr_2.0.3 magick_2.8.3
## [5] GenomicFeatures_1.56.0 farver_2.1.1
## [7] rmarkdown_2.26 BiocIO_1.14.0
## [9] zlibbioc_1.50.0 vctrs_0.6.5
## [11] memoise_2.0.1 Rsamtools_2.20.0
## [13] RCurl_1.98-1.14 progress_1.2.3
## [15] htmltools_0.5.8 S4Arrays_1.4.0
## [17] BiocBaseUtils_1.6.0 AnnotationHub_3.12.0
## [19] lambda.r_1.2.4 curl_5.2.1
## [21] pROC_1.18.5 SparseArray_1.4.0
## [23] sass_0.4.9 bslib_0.6.2
## [25] plyr_1.8.9 httr2_1.0.0
## [27] futile.options_1.0.1 cachem_1.0.8
## [29] GenomicAlignments_1.40.0 mime_0.12
## [31] lifecycle_1.0.4 iterators_1.0.14
## [33] pkgconfig_2.0.3 Matrix_1.7-0
## [35] R6_2.5.1 fastmap_1.1.1
## [37] GenomeInfoDbData_1.2.12 digest_0.6.35
## [39] colorspace_2.1-0 AnnotationDbi_1.66.0
## [41] ps_1.7.6 ExperimentHub_2.12.0
## [43] RSQLite_2.3.5 labeling_0.4.3
## [45] filelock_1.0.3 fansi_1.0.6
## [47] httr_1.4.7 abind_1.4-5
## [49] compiler_4.4.0 bit64_4.0.5
## [51] withr_3.0.0 backports_1.4.1
## [53] BiocParallel_1.38.0 DBI_1.2.2
## [55] highr_0.10 biomaRt_2.60.0
## [57] rappdirs_0.3.3 DelayedArray_0.30.0
## [59] rjson_0.2.21 tools_4.4.0
## [61] chromote_0.2.0 glue_1.7.0
## [63] restfulr_0.0.15 promises_1.2.1
## [65] grid_4.4.0 checkmate_2.3.1
## [67] generics_0.1.3 gtable_0.3.4
## [69] tzdb_0.4.0 websocket_1.4.1
## [71] hms_1.1.3 xml2_1.3.6
## [73] utf8_1.2.4 XVector_0.44.0
## [75] BiocVersion_3.19.1 foreach_1.5.2
## [77] pillar_1.9.0 stringr_1.5.1
## [79] later_1.3.2 splines_4.4.0
## [81] BiocFileCache_2.12.0 lattice_0.22-6
## [83] rtracklayer_1.64.0 bit_4.0.5
## [85] tidyselect_1.2.1 Biostrings_2.72.0
## [87] knitr_1.45 bookdown_0.38
## [89] xfun_0.43 stringi_1.8.3
## [91] UCSC.utils_1.0.0 yaml_2.3.8
## [93] evaluate_0.23 codetools_0.2-19
## [95] tibble_3.2.1 BiocManager_1.30.22
## [97] cli_3.6.2 munsell_0.5.0
## [99] processx_3.8.4 jquerylib_0.1.4
## [101] Rcpp_1.0.12 GenomicDataCommons_1.28.0
## [103] dbplyr_2.5.0 png_0.1-8
## [105] XML_3.99-0.16.1 parallel_4.4.0
## [107] readr_2.1.5 blob_1.2.4
## [109] prettyunits_1.2.0 bitops_1.0-7
## [111] glmnet_4.1-8 scales_1.3.0
## [113] purrr_1.0.2 crayon_1.5.2
## [115] rlang_1.1.3 KEGGREST_1.44.0
## [117] rvest_1.0.4 formatR_1.14