1 Installation

# Install NACHO from CRAN:
install.packages("NACHO")

# Or the the development version from GitHub:
# install.packages("remotes")
remotes::install_github("mcanouil/NACHO")

2 Overview

NACHO (NAnostring quality Control dasHbOard) is developed for NanoString nCounter data.
NanoString nCounter data is a messenger-RNA/micro-RNA (mRNA/miRNA) expression assay and works with fluorescent barcodes.
Each barcode is assigned a mRNA/miRNA, which can be counted after bonding with its target.
As a result each count of a specific barcode represents the presence of its target mRNA/miRNA.

NACHO is able to load, visualise and normalise the exported NanoString nCounter data and facilitates the user in performing a quality control.
NACHO does this by visualising quality control metrics, expression of control genes, principal components and sample specific size factors in an interactive web application.

With the use of two functions, RCC files are summarised and visualised, namely: load_rcc() and visualise().

• The load_rcc() function is used to preprocess the data.
• The visualise() function initiates a Shiny-based dashboard that visualises all relevant QC plots.

NACHO also includes a function normalise(), which (re)calculates sample specific size factors and normalises the data.

• The normalise() function creates a list in which your settings, the raw counts and normalised counts are stored.

In addition (since v0.6.0) NACHO includes two (three) additional functions:

• The render() function renders a full quality-control report (HTML) based on the results of a call to load_rcc() or normalise() (using print() in a Rmarkdown chunk).
• The autoplot() function draws any quality-control metrics from visualise() and render().

For more vignette("NACHO") and vignette("NACHO-analysis").

Canouil M, Bouland GA, Bonnefond A, Froguel P, Hart L, Slieker R (2019). “NACHO: an R package for quality control of NanoString nCounter data.” Bioinformatics. ISSN 1367-4803, doi:10.1093/bioinformatics/btz647.

@Article{,
  title = {{NACHO}: an {R} package for quality control of {NanoString} {nCounter} data},
  author = {Mickaël Canouil and Gerard A. Bouland and Amélie Bonnefond and Philippe Froguel and Leen Hart and Roderick Slieker},
  journal = {Bioinformatics},
  address = {Oxford, England},
  year = {2019},
  month = {aug},
  issn = {1367-4803},
  doi = {10.1093/bioinformatics/btz647},
}

3 Analyse NanoString data

library(NACHO)
library(GEOquery, quietly = TRUE, warn.conflicts = FALSE)
## Error in library(GEOquery, quietly = TRUE, warn.conflicts = FALSE): there is no package called 'GEOquery'

data_directory <- file.path(tempdir(), "GSE70970", "Data")

# Download data
gse <- getGEO("GSE70970")
## Error in getGEO("GSE70970"): could not find function "getGEO"
getGEOSuppFiles(GEO = "GSE70970", baseDir = tempdir())
## Error in getGEOSuppFiles(GEO = "GSE70970", baseDir = tempdir()): could not find function "getGEOSuppFiles"
# Unzip data
untar(
  tarfile = file.path(tempdir(), "GSE70970", "GSE70970_RAW.tar"),
  exdir = data_directory
)
## Warning in untar(tarfile = file.path(tempdir(), "GSE70970",
## "GSE70970_RAW.tar"), : '/usr/bin/tar -xf
## '/var/folders/gn/mxv05rj52wd1yg1hb018s4s40000gn/T//RtmpQG4XyK/GSE70970/GSE70970_RAW.tar'
## -C
## '/var/folders/gn/mxv05rj52wd1yg1hb018s4s40000gn/T//RtmpQG4XyK/GSE70970/Data''
## returned error code 1
# Get phenotypes and add IDs
targets <- pData(phenoData(gse[[1]]))
## Error in pData(phenoData(gse[[1]])): could not find function "pData"
targets$IDFILE <- list.files(data_directory)
## Error: object 'targets' not found

GSE70970 <- load_rcc(data_directory, targets, id_colname = "IDFILE")
## Error in eval(expr, envir, enclos): object 'targets' not found

library(limma)
## Error in library(limma): there is no package called 'limma'

selected_pheno <- GSE70970[["nacho"]][
  j = lapply(unique(.SD), function(x) ifelse(x == "NA", NA, x)),
  .SDcols = c("IDFILE", "age:ch1", "gender:ch1", "chemo:ch1", "disease.event:ch1")
]
## Error in eval(expr, envir, enclos): object 'GSE70970' not found
selected_pheno <- na.exclude(selected_pheno)
## Error in eval(expr, envir, enclos): object 'selected_pheno' not found

## Error in eval(expr, envir, enclos): object 'selected_pheno' not found

expr_counts <- GSE70970[["nacho"]][
  i = grepl("Endogenous", CodeClass),
  j = as.matrix(
    dcast(.SD, Name ~ IDFILE, value.var = "Count_Norm"),
    "Name"
  ),
  .SDcols = c("IDFILE", "Name", "Count_Norm")
]
## Error in eval(expr, envir, enclos): object 'GSE70970' not found

## Error in eval(expr, envir, enclos): object 'expr_counts' not found

GSE70970[["nacho"]][
  i = grepl("Endogenous", CodeClass),
  j = as.matrix(
    dcast(.SD, Accession ~ IDFILE, value.var = "Count_Norm"),
    "Accession"
  ),
  .SDcols = c("IDFILE", "Accession", "Count_Norm")
]

samples_kept <- intersect(selected_pheno[["IDFILE"]], colnames(expr_counts))
## Error in eval(expr, envir, enclos): object 'selected_pheno' not found
expr_counts <- expr_counts[, samples_kept]
## Error in eval(expr, envir, enclos): object 'expr_counts' not found
selected_pheno <- selected_pheno[IDFILE %in% c(samples_kept)]
## Error in eval(expr, envir, enclos): object 'selected_pheno' not found

design <- model.matrix(~ `disease.event:ch1`, selected_pheno)
## Error in eval(expr, envir, enclos): object 'selected_pheno' not found

eBayes(lmFit(expr_counts, design))
## Error in eBayes(lmFit(expr_counts, design)): could not find function "eBayes"

GSE70970[["nacho"]][
  i = grepl("Endogenous", CodeClass),
  j = lapply(unique(.SD), function(x) ifelse(x == "NA", NA, x)),
  .SDcols = c(
    "IDFILE", "Name", "Accession", "Count", "Count_Norm",
    "age:ch1", "gender:ch1", "chemo:ch1", "disease.event:ch1"
  )
][
  Name %in% head(unique(Name), 10)
][
  j = as.data.table(
    coef(summary(lm(
      formula = Count_Norm ~ `disease.event:ch1`,
      data = na.exclude(.SD)
    ))),
    "term"
  ),
  by = c("Name", "Accession")
]
## Error in eval(expr, envir, enclos): object 'GSE70970' not found