if (!require("BiocManager"))
install.packages("BiocManager")
BiocManager::install("glmSparseNet")
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())
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 around 100 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.
prad <- curatedTCGAData(diseaseCode = "PRAD", assays = "RNASeq2GeneNorm",
version = '1.1.38', dry.run = FALSE))
Build the survival data from the clinical columns.
xdata
and ydata
# keep only solid tumour (code: 01)
prad.primary.solid.tumor <- TCGAutils::splitAssays(prad, '01')
xdata.raw <- t(assay(prad.primary.solid.tumor[[1]]))
# Get survival information
ydata.raw <- colData(prad.primary.solid.tumor) %>% as.data.frame %>%
# Find max time between all days (ignoring missings)
rowwise %>%
mutate(time = max(days_to_last_followup, days_to_death, na.rm = TRUE)) %>%
# Keep only survival variables and codes
select(patientID, status = vital_status, time) %>%
# Discard individuals with survival time less or equal to 0
filter(!is.na(time) & time > 0) %>% as.data.frame
# Set index as the patientID
rownames(ydata.raw) <- ydata.raw$patientID
# keep only features that have standard deviation > 0
xdata.raw <- xdata.raw[TCGAbarcode(rownames(xdata.raw)) %in%
rownames(ydata.raw),]
xdata.raw <- xdata.raw %>%
{ (apply(., 2, sd) != 0) } %>%
{ xdata.raw[, .] } %>%
scale
# Order ydata the same as assay
ydata.raw <- ydata.raw[TCGAbarcode(rownames(xdata.raw)), ]
set.seed(params$seed)
small.subset <- c(geneNames(c('ENSG00000103091', 'ENSG00000064787',
'ENSG00000119915', 'ENSG00000120158',
'ENSG00000114491', 'ENSG00000204176',
'ENSG00000138399'))$external_gene_name,
sample(colnames(xdata.raw), 100)) %>% unique %>% sort
xdata <- xdata.raw[, small.subset[small.subset %in% colnames(xdata.raw)]]
ydata <- ydata.raw %>% select(time, status)
Fit model model penalizing by the hubs using the cross-validation function by
cv.glmHub
.
set.seed(params$seed)
fitted <- cv.glmHub(xdata, Surv(ydata$time, ydata$status),
family = 'cox',
nlambda = 1000,
network = 'correlation',
network.options = networkOptions(cutoff = .6,
min.degree = .2))
Shows the results of 100
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(.))$external_gene_name,
coefficient = .,
stringsAsFactors = FALSE)
} %>%
arrange(gene.name) %>%
knitr::kable()
ensembl.id | gene.name | coefficient | |
---|---|---|---|
AKAP9 | AKAP9 | AKAP9 | 0.2616307 |
ALPK2 | ALPK2 | ALPK2 | -0.0714527 |
ATP5G2 | ATP5G2 | ATP5G2 | -0.2575987 |
C22orf32 | C22orf32 | C22orf32 | -0.2119992 |
CSNK2A1P | CSNK2A1P | CSNK2A1P | -1.4875518 |
MYST3 | MYST3 | MYST3 | -1.6177076 |
NBPF10 | NBPF10 | NBPF10 | 0.4507147 |
PFN1 | PFN1 | PFN1 | 0.4161846 |
SCGB2A2 | SCGB2A2 | SCGB2A2 | 0.0749064 |
SLC25A1 | SLC25A1 | SLC25A1 | -0.8484827 |
STX4 | STX4 | STX4 | -0.1690185 |
SYP | SYP | SYP | 0.2425939 |
TMEM141 | TMEM141 | TMEM141 | -0.8273147 |
UMPS | UMPS | UMPS | 0.2214068 |
ZBTB26 | ZBTB26 | ZBTB26 | 0.3696515 |
geneNames(names(coefs.v)) %>% { hallmarks(.$external_gene_name)$heatmap }
separate2GroupsCox(as.vector(coefs.v),
xdata[, names(coefs.v)],
ydata,
plot.title = 'Full dataset', legend.outside = FALSE)
## $pvalue
## [1] 0.001155155
##
## $plot
##
## $km
## Call: survfit(formula = survival::Surv(time, status) ~ group, data = prognostic.index.df)
##
## n events median 0.95LCL 0.95UCL
## Low risk 249 0 NA NA NA
## High risk 248 10 3502 3467 NA