Example for Classification Data – Breast Invasive Carcinoma
2024-11-03
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 every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
5 Session Info
sessionInfo()## R Under development (unstable) (2024-10-26 r87273 ucrt)
## Platform: x86_64-w64-mingw32/x64
## Running under: Windows Server 2022 x64 (build 20348)
##
## Matrix products: default
##
##
## locale:
## [1] LC_COLLATE=C
## [2] LC_CTYPE=English_United States.utf8
## [3] LC_MONETARY=English_United States.utf8
## [4] LC_NUMERIC=C
## [5] LC_TIME=English_United States.utf8
##
## 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_1.27.1 MultiAssayExperiment_1.33.0
## [5] SummarizedExperiment_1.37.0 Biobase_2.67.0
## [7] GenomicRanges_1.59.0 GenomeInfoDb_1.43.0
## [9] IRanges_2.41.0 S4Vectors_0.45.0
## [11] BiocGenerics_0.53.1 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_1.59.0 farver_2.1.2
## [7] rmarkdown_2.28 BiocIO_1.17.0
## [9] zlibbioc_1.53.0 vctrs_0.6.5
## [11] memoise_2.0.1 Rsamtools_2.23.0
## [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_5.2.3 pROC_1.18.5
## [23] SparseArray_1.7.0 sass_0.4.9
## [25] bslib_0.8.0 plyr_1.8.9
## [27] httr2_1.0.5 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_2.3.7
## [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 highr_0.11
## [57] biomaRt_2.63.0 rappdirs_0.3.3
## [59] DelayedArray_0.33.1 rjson_0.2.23
## [61] tools_4.5.0 chromote_0.3.1
## [63] glue_1.8.0 restfulr_0.0.15
## [65] promises_1.3.0 grid_4.5.0
## [67] checkmate_2.3.2 gtable_0.3.6
## [69] tzdb_0.4.0 websocket_1.4.2
## [71] hms_1.1.3 xml2_1.3.6
## [73] utf8_1.2.4 XVector_0.47.0
## [75] BiocVersion_3.21.1 foreach_1.5.2
## [77] pillar_1.9.0 stringr_1.5.1
## [79] later_1.3.2 splines_4.5.0
## [81] BiocFileCache_2.15.0 lattice_0.22-6
## [83] rtracklayer_1.67.0 bit_4.5.0
## [85] tidyselect_1.2.1 Biostrings_2.75.0
## [87] knitr_1.48 bookdown_0.41
## [89] xfun_0.49 stringi_1.8.4
## [91] UCSC.utils_1.3.0 yaml_2.3.10
## [93] evaluate_1.0.1 codetools_0.2-20
## [95] tibble_3.2.1 BiocManager_1.30.25
## [97] cli_3.6.3 munsell_0.5.1
## [99] processx_3.8.4 jquerylib_0.1.4
## [101] Rcpp_1.0.13-1 GenomicDataCommons_1.31.0
## [103] dbplyr_2.5.0 png_0.1-8
## [105] XML_3.99-0.17 parallel_4.5.0
## [107] readr_2.1.5 blob_1.2.4
## [109] prettyunits_1.2.0 bitops_1.0-9
## [111] glmnet_4.1-8 scales_1.3.0
## [113] purrr_1.0.2 crayon_1.5.3
## [115] rlang_1.1.4 KEGGREST_1.47.0
## [117] rvest_1.0.4 formatR_1.14