if (!require("BiocManager"))
install.packages("BiocManager")
BiocManager::install("glmSparseNet")
library(dplyr)
library(ggplot2)
library(survival)
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 <- glmSparseNet:::show.message(FALSE)
# Setting ggplot2 default theme as minimal
theme_set(ggplot2::theme_minimal())
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.v
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))
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)
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(.))$external_gene_name,
coefficient = .,
stringsAsFactors = FALSE)
} %>%
arrange(gene.name) %>%
knitr::kable()
ensembl.id | gene.name | coefficient | |
---|---|---|---|
(Intercept) | (Intercept) | (Intercept) | -6.8189813 |
CD5 | CD5 | AMOTL1 | -1.1200445 |
NLRC4 | NLRC4 | ATR | -1.4434578 |
PIK3CB | PIK3CB | B3GALT2 | -0.3880002 |
ZBTB11 | ZBTB11 | BAG2 | -0.3325729 |
ATR | ATR | C16orf82 | 1.2498304 |
IL2 | IL2 | CD5 | 0.6327083 |
GDF11 | GDF11 | CIITA | -0.2676642 |
DCP1A | DCP1A | DCP1A | 0.2994599 |
AMOTL1 | AMOTL1 | FAM86B1 | 0.4430643 |
BAG2 | BAG2 | FNIP2 | -0.1841676 |
C16orf82 | C16orf82 | GDF11 | 0.0396368 |
FAM86B1 | FAM86B1 | GNG11 | 0.2025463 |
FNIP2 | FNIP2 | GREM2 | 0.6101759 |
MS4A4A | MS4A4A | GZMB | 1.1614779 |
B3GALT2 | B3GALT2 | HAX1 | -0.0867011 |
GNG11 | GNG11 | IL2 | 3.0659066 |
NDRG2 | NDRG2 | MMP28 | 1.1142519 |
HAX1 | HAX1 | MS4A4A | -0.1516837 |
GREM2 | GREM2 | NDRG2 | -0.2014884 |
CIITA | CIITA | NLRC4 | 0.4256103 |
GZMB | GZMB | PIK3CB | -2.7663574 |
MMP28 | MMP28 | ZBTB11 | -0.8438024 |
geneNames(names(coefs.v)) %>% { hallmarks(.$external_gene_name)$heatmap }
## Error in curl::curl_fetch_memory(url, handle = handle): Timeout was reached: [chat.lionproject.net] Operation timed out after 10001 milliseconds with 0 out of 0 bytes received
## Request failed [ERROR]. Retrying in 1.1 seconds...
## Error in curl::curl_fetch_memory(url, handle = handle): OpenSSL SSL_connect: SSL_ERROR_SYSCALL in connection to chat.lionproject.net:443
## Request failed [ERROR]. Retrying in 1.1 seconds...
## Cannot call Hallmark API, please try again later.
## NULL
## [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
sessionInfo()
## R version 4.2.0 (2022-04-22)
## Platform: x86_64-pc-linux-gnu (64-bit)
## Running under: Ubuntu 20.04.4 LTS
##
## Matrix products: default
## BLAS: /home/biocbuild/bbs-3.15-bioc/R/lib/libRblas.so
## LAPACK: /home/biocbuild/bbs-3.15-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_1.14.1 glmnet_4.1-4
## [3] Matrix_1.4-1 TCGAutils_1.16.0
## [5] curatedTCGAData_1.18.0 MultiAssayExperiment_1.22.0
## [7] SummarizedExperiment_1.26.1 Biobase_2.56.0
## [9] GenomicRanges_1.48.0 GenomeInfoDb_1.32.2
## [11] IRanges_2.30.0 S4Vectors_0.34.0
## [13] BiocGenerics_0.42.0 MatrixGenerics_1.8.0
## [15] matrixStats_0.62.0 futile.logger_1.4.3
## [17] survival_3.3-1 ggplot2_3.3.6
## [19] dplyr_1.0.9 BiocStyle_2.24.0
##
## loaded via a namespace (and not attached):
## [1] colorspace_2.0-3 rjson_0.2.21
## [3] ellipsis_0.3.2 XVector_0.36.0
## [5] farver_2.1.0 bit64_4.0.5
## [7] interactiveDisplayBase_1.34.0 AnnotationDbi_1.58.0
## [9] fansi_1.0.3 xml2_1.3.3
## [11] codetools_0.2-18 splines_4.2.0
## [13] cachem_1.0.6 knitr_1.39
## [15] jsonlite_1.8.0 pROC_1.18.0
## [17] Rsamtools_2.12.0 dbplyr_2.1.1
## [19] png_0.1-7 shiny_1.7.1
## [21] BiocManager_1.30.17 readr_2.1.2
## [23] compiler_4.2.0 httr_1.4.3
## [25] assertthat_0.2.1 fastmap_1.1.0
## [27] cli_3.3.0 later_1.3.0
## [29] formatR_1.12 htmltools_0.5.2
## [31] prettyunits_1.1.1 tools_4.2.0
## [33] gtable_0.3.0 glue_1.6.2
## [35] GenomeInfoDbData_1.2.8 rappdirs_0.3.3
## [37] Rcpp_1.0.8.3 jquerylib_0.1.4
## [39] vctrs_0.4.1 Biostrings_2.64.0
## [41] ExperimentHub_2.4.0 rtracklayer_1.56.0
## [43] iterators_1.0.14 xfun_0.31
## [45] stringr_1.4.0 rvest_1.0.2
## [47] mime_0.12 lifecycle_1.0.1
## [49] restfulr_0.0.13 XML_3.99-0.9
## [51] AnnotationHub_3.4.0 zlibbioc_1.42.0
## [53] scales_1.2.0 hms_1.1.1
## [55] promises_1.2.0.1 parallel_4.2.0
## [57] lambda.r_1.2.4 yaml_2.3.5
## [59] curl_4.3.2 memoise_2.0.1
## [61] sass_0.4.1 biomaRt_2.52.0
## [63] stringi_1.7.6 RSQLite_2.2.14
## [65] highr_0.9 BiocVersion_3.15.2
## [67] BiocIO_1.6.0 GenomicDataCommons_1.20.1
## [69] foreach_1.5.2 GenomicFeatures_1.48.1
## [71] filelock_1.0.2 BiocParallel_1.30.2
## [73] shape_1.4.6 rlang_1.0.2
## [75] pkgconfig_2.0.3 bitops_1.0-7
## [77] evaluate_0.15 lattice_0.20-45
## [79] purrr_0.3.4 labeling_0.4.2
## [81] GenomicAlignments_1.32.0 bit_4.0.4
## [83] tidyselect_1.1.2 plyr_1.8.7
## [85] magrittr_2.0.3 bookdown_0.26
## [87] R6_2.5.1 magick_2.7.3
## [89] generics_0.1.2 DelayedArray_0.22.0
## [91] DBI_1.1.2 pillar_1.7.0
## [93] withr_2.5.0 KEGGREST_1.36.0
## [95] RCurl_1.98-1.6 tibble_3.1.7
## [97] crayon_1.5.1 futile.options_1.0.1
## [99] utf8_1.2.2 BiocFileCache_2.4.0
## [101] tzdb_0.3.0 rmarkdown_2.14
## [103] progress_1.2.2 grid_4.2.0
## [105] blob_1.2.3 forcats_0.5.1
## [107] digest_0.6.29 xtable_1.8-4
## [109] httpuv_1.6.5 munsell_0.5.0
## [111] bslib_0.3.1