Example for Classification Data – Breast Invasive Carcinoma
2026-05-18
Contents
0.1 Instalation
if (!require("BiocManager")) {
install.packages("BiocManager")
}
BiocManager::install("glmSparseNet")1 Required Packages
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())2 Load data
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 <- classV3 Fit models
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
)
)4 Results of Cross Validation
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)
4.1 Coefficients of selected model from Cross-Validation
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 |
4.2 Accuracy
## [INFO] Misclassified (11)## [INFO] * False primary solid tumour: 7## [INFO] * False normal : 4Histogram 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 per session.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
5 Session Info
sessionInfo()## R version 4.6.0 Patched (2026-05-01 r89994)
## Platform: aarch64-apple-darwin23
## Running under: macOS Tahoe 26.3.1
##
## Matrix products: default
## BLAS: /Library/Frameworks/R.framework/Versions/4.6/Resources/lib/libRblas.0.dylib
## LAPACK: /Library/Frameworks/R.framework/Versions/4.6/Resources/lib/libRlapack.dylib; LAPACK version 3.12.1
##
## 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_1.31.0 TCGAutils_1.33.1
## [3] curatedTCGAData_1.35.0 MultiAssayExperiment_1.39.0
## [5] SummarizedExperiment_1.43.0 Biobase_2.73.1
## [7] GenomicRanges_1.65.0 Seqinfo_1.3.0
## [9] IRanges_2.47.1 S4Vectors_0.51.2
## [11] BiocGenerics_0.59.2 generics_0.1.4
## [13] MatrixGenerics_1.25.0 matrixStats_1.5.0
## [15] futile.logger_1.4.9 survival_3.8-6
## [17] ggplot2_4.0.3 dplyr_1.2.1
## [19] BiocStyle_2.41.0
##
## loaded via a namespace (and not attached):
## [1] RColorBrewer_1.1-3 jsonlite_2.0.0
## [3] shape_1.4.6.1 magrittr_2.0.5
## [5] magick_2.9.1 GenomicFeatures_1.65.0
## [7] farver_2.1.2 rmarkdown_2.31
## [9] BiocIO_1.23.3 vctrs_0.7.3
## [11] memoise_2.0.1 Rsamtools_2.29.0
## [13] RCurl_1.98-1.18 tinytex_0.59
## [15] htmltools_0.5.9 S4Arrays_1.13.0
## [17] BiocBaseUtils_1.15.1 progress_1.2.3
## [19] AnnotationHub_4.3.0 lambda.r_1.2.4
## [21] curl_7.1.0 pROC_1.19.0.1
## [23] SparseArray_1.13.2 sass_0.4.10
## [25] bslib_0.11.0 httr2_1.2.2
## [27] futile.options_1.0.1 cachem_1.1.0
## [29] GenomicAlignments_1.49.0 lifecycle_1.0.5
## [31] iterators_1.0.14 pkgconfig_2.0.3
## [33] Matrix_1.7-5 R6_2.6.1
## [35] fastmap_1.2.0 digest_0.6.39
## [37] AnnotationDbi_1.75.0 ExperimentHub_3.3.0
## [39] RSQLite_3.52.0 labeling_0.4.3
## [41] filelock_1.0.3 httr_1.4.8
## [43] abind_1.4-8 compiler_4.6.0
## [45] bit64_4.8.0 withr_3.0.2
## [47] S7_0.2.2 backports_1.5.1
## [49] BiocParallel_1.47.0 DBI_1.3.0
## [51] biomaRt_2.69.0 rappdirs_0.3.4
## [53] DelayedArray_0.39.2 rjson_0.2.23
## [55] tools_4.6.0 chromote_0.5.1
## [57] otel_0.2.0 glue_1.8.1
## [59] restfulr_0.0.16 promises_1.5.0
## [61] grid_4.6.0 checkmate_2.3.4
## [63] gtable_0.3.6 tzdb_0.5.0
## [65] websocket_1.4.4 hms_1.1.4
## [67] xml2_1.5.2 XVector_0.53.0
## [69] BiocVersion_3.24.0 foreach_1.5.2
## [71] pillar_1.11.1 stringr_1.6.0
## [73] later_1.4.8 splines_4.6.0
## [75] BiocFileCache_3.3.0 lattice_0.22-9
## [77] rtracklayer_1.73.0 bit_4.6.0
## [79] tidyselect_1.2.1 Biostrings_2.81.1
## [81] knitr_1.51 bookdown_0.46
## [83] xfun_0.57 stringi_1.8.7
## [85] UCSC.utils_1.9.0 yaml_2.3.12
## [87] evaluate_1.0.5 codetools_0.2-20
## [89] cigarillo_1.3.0 tibble_3.3.1
## [91] BiocManager_1.30.27 cli_3.6.6
## [93] processx_3.9.0 jquerylib_0.1.4
## [95] dichromat_2.0-0.1 Rcpp_1.1.1-1.1
## [97] GenomeInfoDb_1.49.0 GenomicDataCommons_1.37.0
## [99] dbplyr_2.5.2 png_0.1-9
## [101] XML_3.99-0.23 parallel_4.6.0
## [103] readr_2.2.0 blob_1.3.0
## [105] prettyunits_1.2.0 bitops_1.0-9
## [107] glmnet_5.0 scales_1.4.0
## [109] purrr_1.2.2 crayon_1.5.3
## [111] rlang_1.2.0 KEGGREST_1.53.0
## [113] rvest_1.0.5 formatR_1.14