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 <- classV

3 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()
## Warning in .curlWorkaround(.runCache(biomaRt::useEnsembl, biomart = "genes", : There was an problem, calling the function with ssl_verifypeer to FALSE
## 
##  : The given dataset:  hsapiens_gene_ensembl , is not valid.  Correct dataset names can be obtained with the listDatasets() function.
## Warning in force(expr): restarting interrupted promise evaluation
## Warning in value[[3L]](cond): Problem when finding gene names:
##  Error in checkDataset(dataset = dataset, mart = mart): The given dataset:  hsapiens_gene_ensembl , is not valid.  Correct dataset names can be obtained with the listDatasets() function.
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              : 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.

5 Session Info

sessionInfo()
## R Under development (unstable) (2024-11-20 r87352)
## Platform: aarch64-apple-darwin20
## Running under: macOS Ventura 13.7.1
## 
## Matrix products: default
## BLAS:   /Library/Frameworks/R.framework/Versions/4.5-arm64/Resources/lib/libRblas.0.dylib 
## LAPACK: /Library/Frameworks/R.framework/Versions/4.5-arm64/Resources/lib/libRlapack.dylib;  LAPACK version 3.12.0
## 
## 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_1.25.0         TCGAutils_1.27.0           
##  [3] curatedTCGAData_1.29.2      MultiAssayExperiment_1.33.1
##  [5] SummarizedExperiment_1.37.0 Biobase_2.67.0             
##  [7] GenomicRanges_1.59.1        GenomeInfoDb_1.43.2        
##  [9] IRanges_2.41.2              S4Vectors_0.45.2           
## [11] BiocGenerics_0.53.3         generics_0.1.3             
## [13] MatrixGenerics_1.19.0       matrixStats_1.4.1          
## [15] futile.logger_1.4.3         survival_3.7-0             
## [17] ggplot2_3.5.1               dplyr_1.1.4                
## [19] BiocStyle_2.35.0           
## 
## loaded via a namespace (and not attached):
##   [1] jsonlite_1.8.9            shape_1.4.6.1            
##   [3] magrittr_2.0.3            magick_2.8.5             
##   [5] GenomicFeatures_1.59.1    farver_2.1.2             
##   [7] rmarkdown_2.29            BiocIO_1.17.1            
##   [9] zlibbioc_1.53.0           vctrs_0.6.5              
##  [11] memoise_2.0.1             Rsamtools_2.23.1         
##  [13] RCurl_1.98-1.16           tinytex_0.54             
##  [15] progress_1.2.3            htmltools_0.5.8.1        
##  [17] S4Arrays_1.7.1            BiocBaseUtils_1.9.0      
##  [19] AnnotationHub_3.15.0      lambda.r_1.2.4           
##  [21] curl_6.0.1                pROC_1.18.5              
##  [23] SparseArray_1.7.2         sass_0.4.9               
##  [25] bslib_0.8.0               plyr_1.8.9               
##  [27] httr2_1.0.7               futile.options_1.0.1     
##  [29] cachem_1.1.0              GenomicAlignments_1.43.0 
##  [31] mime_0.12                 lifecycle_1.0.4          
##  [33] iterators_1.0.14          pkgconfig_2.0.3          
##  [35] Matrix_1.7-1              R6_2.5.1                 
##  [37] fastmap_1.2.0             GenomeInfoDbData_1.2.13  
##  [39] digest_0.6.37             colorspace_2.1-1         
##  [41] AnnotationDbi_1.69.0      ps_1.8.1                 
##  [43] ExperimentHub_2.15.0      RSQLite_2.3.9            
##  [45] labeling_0.4.3            filelock_1.0.3           
##  [47] fansi_1.0.6               httr_1.4.7               
##  [49] abind_1.4-8               compiler_4.5.0           
##  [51] bit64_4.5.2               withr_3.0.2              
##  [53] backports_1.5.0           BiocParallel_1.41.0      
##  [55] DBI_1.2.3                 biomaRt_2.63.0           
##  [57] rappdirs_0.3.3            DelayedArray_0.33.3      
##  [59] rjson_0.2.23              tools_4.5.0              
##  [61] chromote_0.3.1            glue_1.8.0               
##  [63] restfulr_0.0.15           promises_1.3.2           
##  [65] grid_4.5.0                checkmate_2.3.2          
##  [67] gtable_0.3.6              tzdb_0.4.0               
##  [69] websocket_1.4.2           hms_1.1.3                
##  [71] xml2_1.3.6                utf8_1.2.4               
##  [73] XVector_0.47.0            BiocVersion_3.21.1       
##  [75] foreach_1.5.2             pillar_1.9.0             
##  [77] stringr_1.5.1             later_1.4.1              
##  [79] splines_4.5.0             BiocFileCache_2.15.0     
##  [81] lattice_0.22-6            rtracklayer_1.67.0       
##  [83] bit_4.5.0.1               tidyselect_1.2.1         
##  [85] Biostrings_2.75.1         knitr_1.49               
##  [87] bookdown_0.41             xfun_0.49                
##  [89] stringi_1.8.4             UCSC.utils_1.3.0         
##  [91] yaml_2.3.10               evaluate_1.0.1           
##  [93] codetools_0.2-20          tibble_3.2.1             
##  [95] BiocManager_1.30.25       cli_3.6.3                
##  [97] munsell_0.5.1             processx_3.8.4           
##  [99] jquerylib_0.1.4           Rcpp_1.0.13-1            
## [101] GenomicDataCommons_1.31.0 dbplyr_2.5.0             
## [103] png_0.1-8                 XML_3.99-0.17            
## [105] parallel_4.5.0            readr_2.1.5              
## [107] blob_1.2.4                prettyunits_1.2.0        
## [109] bitops_1.0-9              glmnet_4.1-8             
## [111] scales_1.3.0              purrr_1.0.2              
## [113] crayon_1.5.3              rlang_1.1.4              
## [115] KEGGREST_1.47.0           rvest_1.0.4              
## [117] formatR_1.14