In Vitek-Lab/MSstatsSampleSize: Simulation tool for optimal design of high-dimensional MS-based proteomics experiment

library(knitr)
hook_output = knit_hooks$get('output')
knit_hooks$set(output = function(x, options) {
  # this hook is used only when the linewidth option is not NULL
  if (!is.null(n <- options$linewidth)) {
    x = knitr:::split_lines(x)
    # any lines wider than n should be wrapped
    if (any(nchar(x) > n)) x = strwrap(x, width = n)
    x = paste(x, collapse = '\n')
  }
  hook_output(x, options)
})

Result

p1 <- designSampleSizeClassificationPlots(data = params$data,
                                          protein_importance_plot = F,
                                          predictive_accuracy_plot = T,
                                          use_h2o = params$use_h2o,
                                          alg =  params$alg,
                                          save.pdf = F)

p2 <- designSampleSizeClassificationPlots(data = params$data, 
                                        protein_importance_plot = T,
                                        predictive_accuracy_plot = F,
                                        save.pdf = F, session = "")

gridExtra::grid.arrange(p1$plot, p2$plot, ncol = 1)

\newpage

Parameters used to simulate selected sample size

cat("Input Abundance File path:", params$count)
cat("Input Annotation File path:", params$annot)
cat("Data Transform type: ", params$transform)
cat("Set Seed ?", params$set_seed)
if(params$set_seed){
  cat("Seed Value:", params$seed)
}
cat("Number of Simulations:", params$n_sim)
cat("Expected Fold Change:", !params$fc)
if(!params$fc){
  cat("Basline group:", params$baseline)
  cat("List of Different Proteins:", params$list_diff_prots)
  cat("Fold Change values:", params$fc_values)
}
cat("Rank proteins by: ", params$rank)
if(params$rank %in% c("Mean", "Combined")){
  cat("Quantile cutoff for Proteins Abundance: ", params$mean_qq, "%\n")
  cat("Mean Abundance Region: ", params$mean_eq)
}
if(params$rank %in% c("Combined", "SD")){
  cat("Quantile cutoff for Standard deviation: ", params$sd_qq, "%\n")
  cat("Standard DeviationRegion: ", params$sd_eq)
}
cat("Samples per group:", gsub("Sample","",params$sample))
cat("Simulate Validation Set:", params$valid)
if(params$valid){
  cat("Validations samples per group:", params$valid_sample)
}
cat("Classifier used to estimate sample size:", params$alg)

\newpage

Code to re-run experiment

#Need to install MsstatsSampleSize library from Bioconductor if it is not 
#installed


library(MSstatsSampleSize)

sim_data <- simulateDataset(data,
                            annotation,
                            num_simulations = 10,
                            expected_FC = "data",
                            list_diff_proteins = NULL,
                            select_simulated_proteins = "proportion",
                            protein_proportion = 1,
                            protein_number = 1000,
                            samples_per_group = 50,
                            simulate_validation = FALSE,
                            valid_samples_per_group = 50)


model <- designSampleSizeClassification(simulations = sim_data,
                                        classifier = params$alg)

designSampleSizeClassificationPlots(data = model)

\newpage

Session Information

sessionInfo()

Vitek-Lab/MSstatsSampleSize documentation built on Aug. 28, 2020, 10:39 a.m.