Example for Classification Data – Breast Invasive Carcinoma
2021-10-26
Contents
0.1 Instalation
if (!require("BiocManager"))
install.packages("BiocManager")
BiocManager::install("glmSparseNet")1 Required Packages
library(dplyr)
library(ggplot2)
library(survival)
library(loose.rock)
library(futile.logger)
library(curatedTCGAData)
library(TCGAutils)
#
library(glmSparseNet)
#
# Some general options for futile.logger the debugging package
.Last.value <- flog.layout(layout.format('[~l] ~m'))
.Last.value <- loose.rock::show.message(FALSE)
# 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 <- curatedTCGAData(diseaseCode = "BRCA", assays = "RNASeq2GeneNorm",
version = "1.1.38", dry.run = FALSE)brca <- TCGAutils::TCGAsplitAssays(brca, c('01','11'))
xdata.raw <- t(cbind(assay(brca[[1]]), assay(brca[[2]])))
# Get matches between survival and assay data
class.v <- TCGAbiospec(rownames(xdata.raw))$sample_definition %>% factor
names(class.v) <- rownames(xdata.raw)
# keep features with standard deviation > 0
xdata.raw <- xdata.raw %>%
{ (apply(., 2, sd) != 0) } %>%
{ xdata.raw[, .] } %>%
scale
set.seed(params$seed)
small.subset <- c('CD5', 'CSF2RB', 'HSF1', 'IRGC', 'LRRC37A6P', 'NEUROG2',
'NLRC4', 'PDE11A', 'PIK3CB', 'QARS', 'RPGRIP1L', 'SDC1',
'TMEM31', 'YME1L1', 'ZBTB11',
sample(colnames(xdata.raw), 100))
xdata <- xdata.raw[, small.subset[small.subset %in% colnames(xdata.raw)]]
ydata <- class.v3 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,
network.options = networkOptions(cutoff = .6,
min.degree = .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
coefs.v <- coef(fitted, s = 'lambda.min')[,1] %>% { .[. != 0]}
coefs.v %>% {
data.frame(ensembl.id = names(.),
gene.name = geneNames(names(.))$external_gene_name,
coefficient = .,
stringsAsFactors = FALSE)
} %>%
arrange(gene.name) %>%
knitr::kable()| ensembl.id | gene.name | coefficient | |
|---|---|---|---|
| (Intercept) | (Intercept) | (Intercept) | -6.8189811 |
| CD5 | CD5 | AMOTL1 | -1.1200445 |
| NLRC4 | NLRC4 | ATR | -1.4434577 |
| PIK3CB | PIK3CB | B3GALT2 | -0.3880002 |
| ZBTB11 | ZBTB11 | BAG2 | -0.3325728 |
| ATR | ATR | C16orf82 | 1.2498303 |
| IL2 | IL2 | CD5 | 0.6327083 |
| GDF11 | GDF11 | CIITA | -0.2676642 |
| DCP1A | DCP1A | DCP1A | 0.2994599 |
| AMOTL1 | AMOTL1 | FAM86B1 | 0.4430643 |
| BAG2 | BAG2 | FNIP2 | -0.1841676 |
| C16orf82 | C16orf82 | GDF11 | 0.0396368 |
| FAM86B1 | FAM86B1 | GNG11 | 0.2025462 |
| FNIP2 | FNIP2 | GREM2 | 0.6101758 |
| MS4A4A | MS4A4A | GZMB | 1.1614778 |
| B3GALT2 | B3GALT2 | HAX1 | -0.0867011 |
| GNG11 | GNG11 | IL2 | 3.0659065 |
| NDRG2 | NDRG2 | MMP28 | 1.1142519 |
| HAX1 | HAX1 | MS4A4A | -0.1516836 |
| GREM2 | GREM2 | NDRG2 | -0.2014884 |
| CIITA | CIITA | NLRC4 | 0.4256103 |
| GZMB | GZMB | PIK3CB | -2.7663573 |
| MMP28 | MMP28 | ZBTB11 | -0.8438023 |
4.2 Hallmarks of Cancer
geneNames(names(coefs.v)) %>% { hallmarks(.$external_gene_name)$heatmap }
4.3 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
5 Session Info
sessionInfo()## R version 4.1.1 (2021-08-10)
## Platform: x86_64-pc-linux-gnu (64-bit)
## Running under: Ubuntu 20.04.3 LTS
##
## Matrix products: default
## BLAS: /home/biocbuild/bbs-3.14-bioc/R/lib/libRblas.so
## LAPACK: /home/biocbuild/bbs-3.14-bioc/R/lib/libRlapack.so
##
## locale:
## [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C
## [3] LC_TIME=en_GB LC_COLLATE=C
## [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
##
## attached base packages:
## [1] stats4 stats graphics grDevices utils datasets methods
## [8] base
##
## other attached packages:
## [1] glmSparseNet_1.12.0 glmnet_4.1-2
## [3] Matrix_1.3-4 TCGAutils_1.14.0
## [5] curatedTCGAData_1.15.1 MultiAssayExperiment_1.20.0
## [7] SummarizedExperiment_1.24.0 Biobase_2.54.0
## [9] GenomicRanges_1.46.0 GenomeInfoDb_1.30.0
## [11] IRanges_2.28.0 S4Vectors_0.32.0
## [13] BiocGenerics_0.40.0 MatrixGenerics_1.6.0
## [15] matrixStats_0.61.0 futile.logger_1.4.3
## [17] loose.rock_1.2.0 survival_3.2-13
## [19] ggplot2_3.3.5 dplyr_1.0.7
## [21] BiocStyle_2.22.0
##
## loaded via a namespace (and not attached):
## [1] colorspace_2.0-2 rjson_0.2.20
## [3] ellipsis_0.3.2 XVector_0.34.0
## [5] farver_2.1.0 sparsebnUtils_0.0.8
## [7] bit64_4.0.5 interactiveDisplayBase_1.32.0
## [9] AnnotationDbi_1.56.0 fansi_0.5.0
## [11] xml2_1.3.2 codetools_0.2-18
## [13] splines_4.1.1 cachem_1.0.6
## [15] knitr_1.36 jsonlite_1.7.2
## [17] pROC_1.18.0 Rsamtools_2.10.0
## [19] ccdrAlgorithm_0.0.5 dbplyr_2.1.1
## [21] png_0.1-7 shiny_1.7.1
## [23] BiocManager_1.30.16 readr_2.0.2
## [25] compiler_4.1.1 httr_1.4.2
## [27] assertthat_0.2.1 fastmap_1.1.0
## [29] later_1.3.0 formatR_1.11
## [31] htmltools_0.5.2 prettyunits_1.1.1
## [33] tools_4.1.1 gtable_0.3.0
## [35] glue_1.4.2 GenomeInfoDbData_1.2.7
## [37] reshape2_1.4.4 rappdirs_0.3.3
## [39] Rcpp_1.0.7 jquerylib_0.1.4
## [41] vctrs_0.3.8 Biostrings_2.62.0
## [43] ExperimentHub_2.2.0 rtracklayer_1.54.0
## [45] iterators_1.0.13 xfun_0.27
## [47] stringr_1.4.0 rvest_1.0.2
## [49] mime_0.12 lifecycle_1.0.1
## [51] restfulr_0.0.13 XML_3.99-0.8
## [53] AnnotationHub_3.2.0 zlibbioc_1.40.0
## [55] scales_1.1.1 hms_1.1.1
## [57] promises_1.2.0.1 parallel_4.1.1
## [59] lambda.r_1.2.4 yaml_2.2.1
## [61] curl_4.3.2 memoise_2.0.0
## [63] sass_0.4.0 biomaRt_2.50.0
## [65] stringi_1.7.5 RSQLite_2.2.8
## [67] highr_0.9 BiocVersion_3.14.0
## [69] BiocIO_1.4.0 GenomicDataCommons_1.18.0
## [71] foreach_1.5.1 GenomicFeatures_1.46.0
## [73] filelock_1.0.2 BiocParallel_1.28.0
## [75] discretecdAlgorithm_0.0.7 shape_1.4.6
## [77] rlang_0.4.12 pkgconfig_2.0.3
## [79] bitops_1.0-7 evaluate_0.14
## [81] lattice_0.20-45 purrr_0.3.4
## [83] labeling_0.4.2 GenomicAlignments_1.30.0
## [85] bit_4.0.4 tidyselect_1.1.1
## [87] plyr_1.8.6 magrittr_2.0.1
## [89] bookdown_0.24 R6_2.5.1
## [91] magick_2.7.3 generics_0.1.1
## [93] DelayedArray_0.20.0 DBI_1.1.1
## [95] pillar_1.6.4 withr_2.4.2
## [97] KEGGREST_1.34.0 RCurl_1.98-1.5
## [99] tibble_3.1.5 crayon_1.4.1
## [101] futile.options_1.0.1 utf8_1.2.2
## [103] BiocFileCache_2.2.0 tzdb_0.1.2
## [105] rmarkdown_2.11 progress_1.2.2
## [107] grid_4.1.1 blob_1.2.2
## [109] forcats_0.5.1 digest_0.6.28
## [111] xtable_1.8-4 httpuv_1.6.3
## [113] munsell_0.5.0 sparsebn_0.1.2
## [115] bslib_0.3.1