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.

skcm <- curatedTCGAData(diseaseCode = 'SKCM', assays = 'RNASeq2GeneNorm', FALSE, cache = tempdir())

Build the survival data from the clinical columns.

skcm.metastatic <- TCGAutils::splitAssays(skcm, '06')
xdata.raw <- t(assay(skcm.metastatic[[1]]))

# Get survival information
ydata.raw <- colData(skcm.metastatic) %>% 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

# Get survival information
ydata.raw <- colData(skcm) %>% 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('FOXL2', 'KLHL5', 'PCYT2', 'SLC6A10P', 'STRAP', 'TMEM33',
                  'WT1-AS', sample(colnames(xdata.raw), 100))

xdata <- xdata.raw[, small.subset[small.subset %in% colnames(xdata.raw)]]
ydata <- ydata.raw %>% select(time, status)

3 Fit models

Fit model model penalizing by the hubs using the cross-validation function by cv.glmHub.

fitted <- cv.glmHub(xdata, 
                    Surv(ydata$time, ydata$status), 
                    family  = 'cox', 
                    foldid  = balanced.cv.folds(!!ydata$status)$output,
                    network = 'correlation', 
                    network.options = networkOptions(min.degree = .2, 
                                                     cutoff = .6))

4 Results of Cross Validation

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)

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 site unresponsive, trying asia mirror
ensembl.id gene.name coefficient
PCYT2 PCYT2 AMICA1 0.0646641
AMICA1 AMICA1 C4orf49 -0.2758400
C4orf49 C4orf49 PCYT2 -0.0059089

4.2 Hallmarks of Cancer

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

4.3 Survival curves and Log rank test

separate2GroupsCox(as.vector(coefs.v), 
                   xdata[, names(coefs.v)], 
                   ydata, 
                   plot.title = 'Full dataset', legend.outside = FALSE)
## $pvalue
## [1] 0.0001269853
## 
## $plot

## 
## $km
## Call: survfit(formula = survival::Surv(time, status) ~ group, data = prognostic.index.df)
## 
##             n events median 0.95LCL 0.95UCL
## Low risk  180     79   4000    2927    6164
## High risk 179    114   2005    1524    2829