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(TCGAutils)
library(MultiAssayExperiment)
#
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
)
# keep only solid tumour (code: 01)
brcaPrimarySolidTumor <- TCGAutils::TCGAsplitAssays(brca, "01")
xdataRaw <- t(assay(brcaPrimarySolidTumor[[1]]))

# Get survival information
ydataRaw <- colData(brcaPrimarySolidTumor) |>
    as.data.frame() |>
    # Keep only data relative to survival or samples
    dplyr::select(
        patientID, vital_status,
        Days.to.date.of.Death, Days.to.Date.of.Last.Contact,
        days_to_death, days_to_last_followup,
        Vital.Status
    ) |>
    # Convert days to integer
    dplyr::mutate(Days.to.date.of.Death = as.integer(Days.to.date.of.Death)) |>
    dplyr::mutate(
        Days.to.Last.Contact = as.integer(Days.to.Date.of.Last.Contact)
    ) |>
    # Find max time between all days (ignoring missings)
    dplyr::rowwise() |>
    dplyr::mutate(
        time = max(days_to_last_followup, Days.to.date.of.Death,
            Days.to.Last.Contact, 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(ydataRaw) <- ydataRaw$patientID

# Get matches between survival and assay data
xdataRaw <- xdataRaw[
    TCGAbarcode(rownames(xdataRaw)) %in% rownames(ydataRaw),
]
xdataRaw <- xdataRaw[, apply(xdataRaw, 2, sd) != 0] |>
    scale()

# Order ydata the same as assay
ydataRaw <- ydataRaw[TCGAbarcode(rownames(xdataRaw)), ]

# Using only a subset of genes previously selected to keep this short example.
set.seed(params$seed)
smallSubset <- c(
    "CD5", "CSF2RB", "IRGC", "NEUROG2", "NLRC4", "PDE11A",
    "PTEN", "TP53", "BRAF",
    "PIK3CB", "QARS", "RFC3", "RPGRIP1L", "SDC1", "TMEM31",
    "YME1L1", "ZBTB11", sample(colnames(xdataRaw), 100)
) |>
    unique()

xdata <- xdataRaw[, smallSubset[smallSubset %in% colnames(xdataRaw)]]
ydata <- ydataRaw |> dplyr::select(time, status)

3 Fit models

Fit model model penalizing by the hubs using the cross-validation function by cv.glmHub.

set.seed(params$seed)
fitted <- cv.glmHub(xdata, Surv(ydata$time, ydata$status),
    family = "cox",
    lambda = buildLambda(1),
    network = "correlation",
    options = networkOptions(
        cutoff = .6,
        minDegree = .2
    )
)
## Warning in regularize.values(x, y, ties, missing(ties), na.rm = na.rm):
## collapsing to unique 'x' values
## Warning in regularize.values(x, y, ties, missing(ties), na.rm = na.rm):
## collapsing to unique 'x' values
## Warning in regularize.values(x, y, ties, missing(ties), na.rm = na.rm):
## collapsing to unique 'x' values
## Warning in regularize.values(x, y, ties, missing(ties), na.rm = na.rm):
## collapsing to unique 'x' values
## Warning in regularize.values(x, y, ties, missing(ties), na.rm = na.rm):
## collapsing to unique 'x' values
## Warning in regularize.values(x, y, ties, missing(ties), na.rm = na.rm):
## collapsing to unique 'x' values
## Warning in regularize.values(x, y, ties, missing(ties), na.rm = na.rm):
## collapsing to unique 'x' values
## Warning in regularize.values(x, y, ties, missing(ties), na.rm = na.rm):
## collapsing to unique 'x' values
## Warning in regularize.values(x, y, ties, missing(ties), na.rm = na.rm):
## collapsing to unique 'x' values
## Warning in regularize.values(x, y, ties, missing(ties), na.rm = na.rm):
## collapsing to unique 'x' values

4 Results of Cross Validation

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)

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])
## Warning in regularize.values(x, y, ties, missing(ties), na.rm = na.rm):
## collapsing to unique 'x' values
data.frame(
    gene.name = names(coefsCV),
    coefficient = coefsCV,
    stringsAsFactors = FALSE
) |>
    arrange(gene.name) |>
    knitr::kable()
gene.name coefficient
CD5 CD5 -0.16632

4.2 Survival curves and Log rank test

separate2GroupsCox(as.vector(coefsCV),
    xdata[, names(coefsCV)],
    ydata,
    plotTitle = "Full dataset", legendOutside = FALSE
)
## $pvalue
## [1] 0.001237802
## 
## $plot

## 
## $km
## Call: survfit(formula = survival::Surv(time, status) ~ group, data = prognosticIndexDf)
## 
##                 n events median 0.95LCL 0.95UCL
## Low risk - 1  540     58   3959    3492      NA
## High risk - 1 540     94   3738    3262    4456

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] grid      parallel  stats4    stats     graphics  grDevices utils    
##  [8] datasets  methods   base     
## 
## other attached packages:
##  [1] glmnet_4.1-8                VennDiagram_1.7.3          
##  [3] reshape2_1.4.4              forcats_1.0.0              
##  [5] Matrix_1.7-1                glmSparseNet_1.25.0        
##  [7] TCGAutils_1.27.0            curatedTCGAData_1.29.2     
##  [9] MultiAssayExperiment_1.33.1 SummarizedExperiment_1.37.0
## [11] Biobase_2.67.0              GenomicRanges_1.59.1       
## [13] GenomeInfoDb_1.43.2         IRanges_2.41.2             
## [15] S4Vectors_0.45.2            BiocGenerics_0.53.3        
## [17] generics_0.1.3              MatrixGenerics_1.19.0      
## [19] matrixStats_1.4.1           futile.logger_1.4.3        
## [21] survival_3.7-0              ggplot2_3.5.1              
## [23] dplyr_1.1.4                 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           rstatix_0.7.2            
##  [15] tinytex_0.54              progress_1.2.3           
##  [17] htmltools_0.5.8.1         S4Arrays_1.7.1           
##  [19] BiocBaseUtils_1.9.0       AnnotationHub_3.15.0     
##  [21] lambda.r_1.2.4            curl_6.0.1               
##  [23] broom_1.0.7               Formula_1.2-5            
##  [25] pROC_1.18.5               SparseArray_1.7.2        
##  [27] sass_0.4.9                bslib_0.8.0              
##  [29] plyr_1.8.9                httr2_1.0.7              
##  [31] zoo_1.8-12                futile.options_1.0.1     
##  [33] cachem_1.1.0              GenomicAlignments_1.43.0 
##  [35] mime_0.12                 lifecycle_1.0.4          
##  [37] iterators_1.0.14          pkgconfig_2.0.3          
##  [39] R6_2.5.1                  fastmap_1.2.0            
##  [41] GenomeInfoDbData_1.2.13   digest_0.6.37            
##  [43] colorspace_2.1-1          AnnotationDbi_1.69.0     
##  [45] ps_1.8.1                  ExperimentHub_2.15.0     
##  [47] RSQLite_2.3.9             ggpubr_0.6.0             
##  [49] labeling_0.4.3            filelock_1.0.3           
##  [51] km.ci_0.5-6               fansi_1.0.6              
##  [53] httr_1.4.7                abind_1.4-8              
##  [55] compiler_4.5.0            bit64_4.5.2              
##  [57] withr_3.0.2               backports_1.5.0          
##  [59] BiocParallel_1.41.0       carData_3.0-5            
##  [61] DBI_1.2.3                 ggsignif_0.6.4           
##  [63] biomaRt_2.63.0            rappdirs_0.3.3           
##  [65] DelayedArray_0.33.3       rjson_0.2.23             
##  [67] tools_4.5.0               chromote_0.3.1           
##  [69] glue_1.8.0                restfulr_0.0.15          
##  [71] promises_1.3.2            checkmate_2.3.2          
##  [73] gtable_0.3.6              KMsurv_0.1-5             
##  [75] tzdb_0.4.0                tidyr_1.3.1              
##  [77] survminer_0.5.0           websocket_1.4.2          
##  [79] data.table_1.16.2         hms_1.1.3                
##  [81] car_3.1-3                 xml2_1.3.6               
##  [83] utf8_1.2.4                XVector_0.47.0           
##  [85] BiocVersion_3.21.1        foreach_1.5.2            
##  [87] pillar_1.9.0              stringr_1.5.1            
##  [89] later_1.4.1               splines_4.5.0            
##  [91] BiocFileCache_2.15.0      lattice_0.22-6           
##  [93] rtracklayer_1.67.0        bit_4.5.0.1              
##  [95] tidyselect_1.2.1          Biostrings_2.75.1        
##  [97] knitr_1.49                gridExtra_2.3            
##  [99] bookdown_0.41             xfun_0.49                
## [101] stringi_1.8.4             UCSC.utils_1.3.0         
## [103] yaml_2.3.10               evaluate_1.0.1           
## [105] codetools_0.2-20          tibble_3.2.1             
## [107] BiocManager_1.30.25       cli_3.6.3                
## [109] xtable_1.8-4              munsell_0.5.1            
## [111] processx_3.8.4            jquerylib_0.1.4          
## [113] survMisc_0.5.6            Rcpp_1.0.13-1            
## [115] GenomicDataCommons_1.31.0 dbplyr_2.5.0             
## [117] png_0.1-8                 XML_3.99-0.17            
## [119] readr_2.1.5               blob_1.2.4               
## [121] prettyunits_1.2.0         bitops_1.0-9             
## [123] scales_1.3.0              purrr_1.0.2              
## [125] crayon_1.5.3              rlang_1.1.4              
## [127] KEGGREST_1.47.0           rvest_1.0.4              
## [129] formatR_1.14