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", FALSE)

brca <- TCGAutils::splitAssays(brca, c('01','11'))

## Selecting 'Primary Solid Tumor' samples

## Selecting 'Solid Tissue Normal' samples

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

3 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)

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()

## Warning: Prefixing `UQ()` with the rlang namespace is deprecated as of rlang 0.3.0.
## Please use the non-prefixed form or `!!` instead.
## 
##   # Bad:
##   rlang::expr(mean(rlang::UQ(var) * 100))
## 
##   # Ok:
##   rlang::expr(mean(UQ(var) * 100))
## 
##   # Good:
##   rlang::expr(mean(!!var * 100))
## 
## This warning is displayed once per session.

geneNames(names(coefs.v)) %>% { hallmarks(.$external_gene_name)$heatmap }

## [INFO] Misclassified (6)

## [INFO]   * False primary solid tumour: 4

## [INFO]   * False normal              : 2