Example for Classification Data – Breast Invasive Carcinoma
2024-04-30
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 version 4.4.0 beta (2024-04-15 r86425)
## Platform: x86_64-pc-linux-gnu
## Running under: Ubuntu 22.04.4 LTS
##
## Matrix products: default
## BLAS: /home/biocbuild/bbs-3.19-bioc/R/lib/libRblas.so
## LAPACK: /usr/lib/x86_64-linux-gnu/lapack/liblapack.so.3.10.0
##
## locale:
## [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C
## [3] LC_TIME=en_US.UTF-8 LC_COLLATE=en_US.UTF-8
## [5] LC_MONETARY=en_US.UTF-8 LC_MESSAGES=en_US.UTF-8
## [7] LC_PAPER=en_US.UTF-8 LC_NAME=C
## [9] LC_ADDRESS=C LC_TELEPHONE=C
## [11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C
##
## time zone: America/New_York
## tzcode source: system (glibc)
##
## 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_1.3.0 futile.logger_1.4.3
## [15] survival_3.6-4 ggplot2_3.5.1
## [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 tinytex_0.50
## [15] progress_1.2.3 htmltools_0.5.8.1
## [17] S4Arrays_1.4.0 BiocBaseUtils_1.6.0
## [19] AnnotationHub_3.12.0 lambda.r_1.2.4
## [21] curl_5.2.1 pROC_1.18.5
## [23] SparseArray_1.4.0 sass_0.4.9
## [25] bslib_0.7.0 plyr_1.8.9
## [27] httr2_1.0.1 futile.options_1.0.1
## [29] cachem_1.0.8 GenomicAlignments_1.40.0
## [31] mime_0.12 lifecycle_1.0.4
## [33] iterators_1.0.14 pkgconfig_2.0.3
## [35] Matrix_1.7-0 R6_2.5.1
## [37] fastmap_1.1.1 GenomeInfoDbData_1.2.12
## [39] digest_0.6.35 colorspace_2.1-0
## [41] AnnotationDbi_1.66.0 ps_1.7.6
## [43] ExperimentHub_2.12.0 RSQLite_2.3.6
## [45] labeling_0.4.3 filelock_1.0.3
## [47] fansi_1.0.6 httr_1.4.7
## [49] abind_1.4-5 compiler_4.4.0
## [51] bit64_4.0.5 withr_3.0.0
## [53] backports_1.4.1 BiocParallel_1.38.0
## [55] DBI_1.2.2 highr_0.10
## [57] biomaRt_2.60.0 rappdirs_0.3.3
## [59] DelayedArray_0.30.0 rjson_0.2.21
## [61] tools_4.4.0 chromote_0.2.0
## [63] glue_1.7.0 restfulr_0.0.15
## [65] promises_1.3.0 grid_4.4.0
## [67] checkmate_2.3.1 generics_0.1.3
## [69] gtable_0.3.5 tzdb_0.4.0
## [71] websocket_1.4.1 hms_1.1.3
## [73] xml2_1.3.6 utf8_1.2.4
## [75] XVector_0.44.0 BiocVersion_3.19.1
## [77] foreach_1.5.2 pillar_1.9.0
## [79] stringr_1.5.1 later_1.3.2
## [81] splines_4.4.0 BiocFileCache_2.12.0
## [83] lattice_0.22-6 rtracklayer_1.64.0
## [85] bit_4.0.5 tidyselect_1.2.1
## [87] Biostrings_2.72.0 knitr_1.46
## [89] bookdown_0.39 xfun_0.43
## [91] stringi_1.8.3 UCSC.utils_1.0.0
## [93] yaml_2.3.8 evaluate_0.23
## [95] codetools_0.2-20 tibble_3.2.1
## [97] BiocManager_1.30.22 cli_3.6.2
## [99] munsell_0.5.1 processx_3.8.4
## [101] jquerylib_0.1.4 Rcpp_1.0.12
## [103] GenomicDataCommons_1.28.0 dbplyr_2.5.0
## [105] png_0.1-8 XML_3.99-0.16.1
## [107] parallel_4.4.0 readr_2.1.5
## [109] blob_1.2.4 prettyunits_1.2.0
## [111] bitops_1.0-7 glmnet_4.1-8
## [113] scales_1.3.0 purrr_1.0.2
## [115] crayon_1.5.2 rlang_1.1.3
## [117] KEGGREST_1.44.0 rvest_1.0.4
## [119] formatR_1.14