Installation

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

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

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},
}

Analyse NanoString data

Load packages

library(NACHO)
## 
## Attaching package: 'NACHO'
## The following object is masked from 'package:rmarkdown':
## 
##     render
library(GEOquery, quietly = TRUE, warn.conflicts = FALSE)
## 
## Attaching package: 'generics'
## The following object is masked from 'package:NACHO':
## 
##     visualize
## The following objects are masked from 'package:base':
## 
##     as.difftime, as.factor, as.ordered, intersect, is.element, setdiff,
##     setequal, union
## 
## Attaching package: 'BiocGenerics'
## The following objects are masked from 'package:generics':
## 
##     intersect, setdiff, setequal, union
## The following object is masked from 'package:NACHO':
## 
##     normalize
## The following objects are masked from 'package:stats':
## 
##     IQR, mad, sd, var, xtabs
## The following objects are masked from 'package:base':
## 
##     Filter, Find, Map, Position, Reduce, anyDuplicated, aperm, append,
##     as.data.frame, basename, cbind, colnames, dirname, do.call,
##     duplicated, eval, evalq, get, grep, grepl, intersect, is.unsorted,
##     lapply, mapply, match, mget, order, paste, pmax, pmax.int, pmin,
##     pmin.int, rank, rbind, rownames, sapply, saveRDS, setdiff,
##     setequal, table, tapply, union, unique, unsplit, which.max,
##     which.min
## Welcome to Bioconductor
## 
##     Vignettes contain introductory material; view with
##     'browseVignettes()'. To cite Bioconductor, see
##     'citation("Biobase")', and for packages 'citation("pkgname")'.
## Warning: multiple methods tables found for 'setequal'
## Warning: replacing previous import 'BiocGenerics::setequal' by
## 'S4Vectors::setequal' when loading 'SummarizedExperiment'
## Warning: replacing previous import 'BiocGenerics::setequal' by
## 'S4Vectors::setequal' when loading 'IRanges'
## Warning: replacing previous import 'BiocGenerics::setequal' by
## 'S4Vectors::setequal' when loading 'GenomeInfoDb'
## Warning: replacing previous import 'BiocGenerics::setequal' by
## 'S4Vectors::setequal' when loading 'GenomicRanges'
## Warning: replacing previous import 'BiocGenerics::setequal' by
## 'S4Vectors::setequal' when loading 'XVector'
## Warning: replacing previous import 'BiocGenerics::setequal' by
## 'S4Vectors::setequal' when loading 'S4Arrays'
## Warning: replacing previous import 'BiocGenerics::setequal' by
## 'S4Vectors::setequal' when loading 'DelayedArray'
## Warning: replacing previous import 'BiocGenerics::setequal' by
## 'S4Vectors::setequal' when loading 'SparseArray'
## Warning: replacing previous import 'S4Arrays::read_block' by
## 'DelayedArray::read_block' when loading 'SummarizedExperiment'
## Setting options('download.file.method.GEOquery'='auto')
## Setting options('GEOquery.inmemory.gpl'=FALSE)

Download `GSE70970` from GEO (or use your own data)

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

# Download data
gse <- getGEO("GSE70970")
## Found 1 file(s)
## GSE70970_series_matrix.txt.gz
getGEOSuppFiles(GEO = "GSE70970", baseDir = tempdir())
##                                                                    size isdir
## /tmp/RtmpLnt4ul/GSE70970/GSE70970_RAW.tar                       1986560 FALSE
## /tmp/RtmpLnt4ul/GSE70970/GSE70970_characteristics_readme.txt.gz     672 FALSE
##                                                                 mode
## /tmp/RtmpLnt4ul/GSE70970/GSE70970_RAW.tar                        644
## /tmp/RtmpLnt4ul/GSE70970/GSE70970_characteristics_readme.txt.gz  644
##                                                                               mtime
## /tmp/RtmpLnt4ul/GSE70970/GSE70970_RAW.tar                       2024-11-07 04:58:48
## /tmp/RtmpLnt4ul/GSE70970/GSE70970_characteristics_readme.txt.gz 2024-11-07 04:58:48
##                                                                               ctime
## /tmp/RtmpLnt4ul/GSE70970/GSE70970_RAW.tar                       2024-11-07 04:58:48
## /tmp/RtmpLnt4ul/GSE70970/GSE70970_characteristics_readme.txt.gz 2024-11-07 04:58:48
##                                                                               atime
## /tmp/RtmpLnt4ul/GSE70970/GSE70970_RAW.tar                       2024-11-07 04:58:47
## /tmp/RtmpLnt4ul/GSE70970/GSE70970_characteristics_readme.txt.gz 2024-11-07 04:58:48
##                                                                 uid gid uname
## /tmp/RtmpLnt4ul/GSE70970/GSE70970_RAW.tar                         0   0  root
## /tmp/RtmpLnt4ul/GSE70970/GSE70970_characteristics_readme.txt.gz   0   0  root
##                                                                 grname
## /tmp/RtmpLnt4ul/GSE70970/GSE70970_RAW.tar                         root
## /tmp/RtmpLnt4ul/GSE70970/GSE70970_characteristics_readme.txt.gz   root
# Unzip data
untar(
  tarfile = file.path(tempdir(), "GSE70970", "GSE70970_RAW.tar"),
  exdir = data_directory
)
# Get phenotypes and add IDs
targets <- pData(phenoData(gse[[1]]))
targets$IDFILE <- list.files(data_directory)

Import RCC files

GSE70970 <- load_rcc(data_directory, targets, id_colname = "IDFILE")
## [NACHO] Importing RCC files.
## Error in load_rcc(data_directory, targets, id_colname = "IDFILE"): [NACHO] Multiple Nanostring file/software versions detected.
##   Please provide a set of files with the same version.
##   - FileVersion: '1.6', '1.6'
##   - SoftwareVersion: '2.1.2.3', '2.1.1.0005'

Perform the analyses using `limma`

library(limma)
## 
## Attaching package: 'limma'
## The following object is masked from 'package:BiocGenerics':
## 
##     plotMA

Get the phenotypes

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: object 'GSE70970' not found
selected_pheno <- na.exclude(selected_pheno)
## Error: object 'selected_pheno' not found

## Error: object 'selected_pheno' not found

Get the normalised counts

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: object 'GSE70970' not found

## Error: object 'expr_counts' not found

Alternatively, "Accession" number is also available.

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

Select phenotypes and counts

Make sure count matrix and phenotypes have the same samples

samples_kept <- intersect(selected_pheno[["IDFILE"]], colnames(expr_counts))
## Error in h(simpleError(msg, call)): error in evaluating the argument 'x' in selecting a method for function 'intersect': object 'selected_pheno' not found
expr_counts <- expr_counts[, samples_kept]
## Error: object 'expr_counts' not found
selected_pheno <- selected_pheno[IDFILE %in% c(samples_kept)]
## Error: object 'selected_pheno' not found

Build the numeric design matrix

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

limma

eBayes(lmFit(expr_counts, design))
## Error: object 'expr_counts' not found

Perform the analyses using `lm` (or any other model)

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: object 'GSE70970' not found

NACHO Analysis