deleted file mode 100644

@@ -1,6 +0,0 @@

-{

-    "source_window_id": "",

-    "Source": "Source",

-    "cursorPosition": "8,0",

-    "scrollLine": "0"

-}

\ No newline at end of file

deleted file mode 100644

@@ -1,4 +0,0 @@

-{

-    "source_window_id": "",

-    "Source": "Source"

-}

\ No newline at end of file

deleted file mode 100644

@@ -1,26 +0,0 @@

-{

-    "id": "064EA836",

-    "path": "C:/Users/kmwai/OneDrive - Kemri Wellcome Trust/H_Drive/PhD_work/projects/protGear_data/protGear/R/launch_protGear_interactive.R",

-    "project_path": "R/launch_protGear_interactive.R",

-    "type": "r_source",

-    "hash": "0",

-    "contents": "",

-    "dirty": false,

-    "created": 1647521182528.0,

-    "source_on_save": false,

-    "relative_order": 9,

-    "properties": {

-        "source_window_id": "",

-        "Source": "Source",

-        "cursorPosition": "52,0",

-        "scrollLine": "47"

-    },

-    "folds": "",

-    "lastKnownWriteTime": 1647760747,

-    "encoding": "UTF-8",

-    "collab_server": "",

-    "source_window": "",

-    "last_content_update": 1647760747,

-    "read_only": false,

-    "read_only_alternatives": []

-}

\ No newline at end of file

deleted file mode 100644

@@ -1,64 +0,0 @@

-#' launch_protGear_interactive

-#'

-#' This is Function is to launch the shiny application

-#' @return launches the shiny interactive protGear app

-#' @import rmarkdown shiny GGally pheatmap  knitr

-#' grid styler factoextra FactoMineR   remotes

-#' @importFrom flexdashboard renderValueBox valueBoxOutput valueBox

-#' @importFrom shinydashboard renderInfoBox

-#' @importFrom  dplyr group_rows between first last

-#' @importFrom  kableExtra text_spec

-#' @export

-#' @examples

-#'launch_protGear_interactive()

-launch_protGear_interactive <- function() {

-  appDir <-

-    system.file("shiny-examples",

-                "protGear_interactive",

-                "protGear_interactive.Rmd",

-                package = "protGear")

-  if (appDir == "") {

-    stop("Could not find example directory. Try re-installing `protGear`.",

-         call. = FALSE)

-  }

-

-  rmarkdown::run(file = appDir)

-}

-

-#' launch_select

-#'

-#' This is Function is to launch mutiple shiny applications for protGear

-#' @param theApp accepts one of the folders containing the shiny appplication

-#' @return launches the app defined under theApp

-#' @export

-#' @examples

-#' launch_select('protGear_interactive')

-launch_select <- function(theApp) {

-  # locate all the shiny app examples that exist

-  validExamples <-

-    list.files(system.file("shiny-examples", package = "protGear"))

-

-  validExamplesMsg <-

-    paste0("The available apps in `protGear` are: '",

-           paste(validExamples, collapse = "', '"),

-           "'")

-

-  # if an invalid folder is given, throw an error

-  if (missing(theApp) || !nzchar(theApp) ||

-      !theApp %in% validExamples) {

-    stop(

-      'Please run `launch_select()` with a valid example app as an argument.\n',

-      validExamplesMsg,

-      call. = FALSE

-    )

-  }

-

-  # find and launch the app

-  appDir <-

-    system.file("shiny-examples", theApp, package = "protGear")

-  if (grepl('protGear_interactive', theApp)) {

-    file_rmd <- 'protGear_interactive.Rmd'

-  } else

-    file_rmd <- 'index.Rmd'

-  rmarkdown::run(file = paste0(appDir, "/", file_rmd))

-}

deleted file mode 100644

@@ -1,27 +0,0 @@

-{

-    "id": "112F37F3",

-    "path": "C:/Users/kmwai/OneDrive - Kemri Wellcome Trust/H_Drive/PhD_work/projects/protGear_data/saved_functions.R",

-    "project_path": null,

-    "type": "r_source",

-    "hash": "0",

-    "contents": "",

-    "dirty": false,

-    "created": 1647626140637.0,

-    "source_on_save": false,

-    "relative_order": 15,

-    "properties": {

-        "tempName": "Untitled1",

-        "source_window_id": "",

-        "Source": "Source",

-        "cursorPosition": "62,0",

-        "scrollLine": "36"

-    },

-    "folds": "",

-    "lastKnownWriteTime": 1640081043,

-    "encoding": "UTF-8",

-    "collab_server": "",

-    "source_window": "",

-    "last_content_update": 1640081043,

-    "read_only": false,

-    "read_only_alternatives": []

-}

\ No newline at end of file

deleted file mode 100644

@@ -1,64 +0,0 @@

-

-#'

-#' @title Merge array data with the sample ID

-#' @description  merge several slide datasets

-#'

-#' @param dfs A character vector with the names of the

-#' @param filenames A vector or list of files names

-#' @param data_files A list with of data files

-#' @param totsamples The total number of samples per slide. defined in genepix vars

-#' @param blockspersample the number of samples in a block

-#' @param sampleID_path  location of the sample id files defined in the genepix vars

-#' @param bg A logical character indicating whether the background data is being merged or not

-#' @export

-#' @import purrr

-#' @return  A data frame of slide data merged together, for eith bg data or bg corrected data

-merge_datasets <- function(dfs,filenames , data_files ,totsamples, blockspersample ,

-                           sampleID_path,bg=FALSE){

-  if(bg==TRUE){

-    data1_transp <- purrr::map(.x=dfs, .f=transp_bg,

-                               totsamples=totsamples,blockspersample=blockspersample,

-                               sampleID_path=sampleID_path,data_files=data_files )

-  }else{

-    data1_transp <- purrr::map(.x=dfs, .f=transp,

-                               totsamples=totsamples,blockspersample=blockspersample,

-                               sampleID_path=sampleID_path,data_files=data_files )

-  }

-

-

-  data1_transp <- set_names(data1_transp, purrr::map(filenames, name_of_files))

-  return(data1_transp)

-}

-#'         \\\_End_function\\\         #

-#'

-#'

-

-#' Plot mean vs SD of normalised data

-#'

-#' @param exprs_normalised A normalised object of class data frame or matrix

-#'

-#' @return A ggplot of mean vs standard deviation

-#' @export

-#' @description A genereic function to plot \code{mean} vs \code{sd} after normalisation.

-#' @import ggplot2

-#' @examples

-#' matrix_antigen <- readr::read_csv(system.file("extdata", "matrix_antigen.csv", package="protGear"))

-#' normlise_vsn <- matrix_normalise(as.matrix(matrix_antigen),

-#' method = "vsn",

-#' return_plot = FALSE

-#' )

-#' plot_mean_sd(normlise_vsn)

-plot_mean_sd <- function(exprs_normalised){

-

-  ggplot(exprs_normalised ,  aes(x=rankMean, y=stdev)) +

-    geom_jitter( color="red") + theme_classic() +

-    ggtitle(paste0(toupper(unique(exprs_normalised$method)))) +

-    xlab("Mean rank normalised") +

-    ylab("SD normalised") +

-    theme_light()

-}

-

-

-

-

-

deleted file mode 100644

@@ -1,27 +0,0 @@

-{

-    "id": "1237BDCB",

-    "path": null,

-    "project_path": null,

-    "type": "r_source",

-    "hash": "0",

-    "contents": "",

-    "dirty": true,

-    "created": 1643379365839.0,

-    "source_on_save": false,

-    "relative_order": 16,

-    "properties": {

-        "tempName": "Untitled1",

-        "source_window_id": "",

-        "Source": "Source",

-        "cursorPosition": "37,0",

-        "scrollLine": "0"

-    },

-    "folds": "",

-    "lastKnownWriteTime": 8319874934561204079,

-    "encoding": "",

-    "collab_server": "",

-    "source_window": "",

-    "last_content_update": 1643379388859,

-    "read_only": false,

-    "read_only_alternatives": []

-}

\ No newline at end of file

deleted file mode 100644

@@ -1,37 +0,0 @@

-

-mk_test_trend <- function (x, alternative = c("two.sided", "greater", 

-                             "less"), continuity = TRUE) 

-{

-  if (!is.numeric(x)) {

-    stop("'x' must be a numeric vector")

-  }

-  n <- length(x)

-  if (n < 3) {

-    stop("'x' must have at least 3 elements")

-  }

-  na.fail(x)

-  alternative <- match.arg(alternative)

-  S <- .mkScore(x)

-  t <- table(x)

-  names(t) <- NULL

-  varS <- .varmk(t, n)

-  D <- .Dfn(t, n)

-  tau <- S/D

-  if (continuity) {

-    sg <- sign(S)

-    z <- sg * (abs(S) - 1)/sqrt(varS)

-  }

-  else {

-    z <- S/sqrt(varS)

-  }

-  pval <- switch(alternative, two.sided = 2 * min(0.5, pnorm(abs(z), 

-                                                             lower.tail = FALSE)), greater = pnorm(z, lower.tail = FALSE), 

-                 less = pnorm(z, lower.tail = TRUE))

-  DNAME <- deparse(substitute(x))

-  ans <- list(data.name = DNAME, p.value = pval, statistic = c(z = z), 

-              null.value = c(S = 0), parameter = c(n = n), estimates = c(S = S, 

-                                                                         varS = varS, tau = tau), alternative = alternative, 

-              method = "Mann-Kendall trend test", pvalg = pval)

-  class(ans) <- "htest"

-  return(ans)

-}

deleted file mode 100644

@@ -1,26 +0,0 @@

-{

-    "id": "4AE107A5",

-    "path": "C:/Users/kmwai/OneDrive - Kemri Wellcome Trust/H_Drive/PhD_work/projects/protGear_data/protGear/R/buffer_spot_functions.R",

-    "project_path": "R/buffer_spot_functions.R",

-    "type": "r_source",

-    "hash": "0",

-    "contents": "",

-    "dirty": false,

-    "created": 1644591069314.0,

-    "source_on_save": false,

-    "relative_order": 10,

-    "properties": {

-        "source_window_id": "",

-        "Source": "Source",

-        "cursorPosition": "23,9",

-        "scrollLine": "7"

-    },

-    "folds": "",

-    "lastKnownWriteTime": 1647760747,

-    "encoding": "UTF-8",

-    "collab_server": "",

-    "source_window": "",

-    "last_content_update": 1647760747,

-    "read_only": false,

-    "read_only_alternatives": []

-}

\ No newline at end of file

deleted file mode 100644

@@ -1,85 +0,0 @@

-#' Extract buffer spots of data

-#'

-#' @param Data1 An object of the class data frame

-#' @param buffer_spot A character string containing the name of the buffer

-#' spots.

-#' @import dplyr

-#' @importFrom dplyr select  filter

-#' @description A function to extract the buffer spots data. A buffer spot only

-#'  has the solution for

-#'  proprietary ingredients for stabilizing protein and minimizing evaporation.

-#' @return A data frame of the buffer control spots

-#' @export

-#'

-#' @examples

-#' bg_correct_df <- readr::read_csv(system.file("extdata", "Data1_sample.csv",

-#' package="protGear"))

-#' buffer_spots(Data1 = bg_correct_df)

-buffer_spots <- function(Data1 , buffer_spot = "buffer") {

-  Data2_buffer <- Data1 %>%

-    # within each Name count sampleID. We had grouped this earlier

-    # n() - gives number of observations in the current group

-    mutate(replicate = 1:n()) %>%

-    # Select only relevant variables

-    dplyr:::select(sampleID,

-                   antigen,

-                   replicate,

-                   FMedianBG_correct,

-                   Block,

-                   Column,

-                   Row)

-

-  if (buffer_spot == 'buffer') {

-    Data2_buffer <- Data2_buffer %>%

-      filter(grepl('^[bB][Uu][Ff][Ff][Ee][Rr]', antigen))

-  } else {

-    Data2_buffer <- Data2_buffer %>%

-      filter(grepl(paste0('^', buffer_spot), tolower(antigen)))

-  }

-

-

-  Data2_buffer <- Data2_buffer %>%

-    # combine Name and replicate

-    unite(antigen, antigen, replicate)

-  return(Data2_buffer)

-}

-

-

-#'  Plot the buffer values

-#'

-#' @param buffer_names A character string containing the name of the variable

-#' with buffer spots. Default set to 'antigen'.

-#' @param buffer_mfi A character string containing the name of the variable with

-#' MFI value.Assuming background correction is done already.

-#' Default to 'FMedianBG_correct'

-#' @param slide_id  A character string containing the name of the slide/array

-#' identifier variable.

-#' @param df A data frame to be used to plot

-#' @import dplyr ggplot2

-#' @importFrom dplyr select  filter

-#' @importFrom gtools mixedsort

-#' @importFrom ggplot2 ggplot

-#' @return plot of buffer spots

-#' @export

-#'

-#' @examples

-#'buffers <- readr::read_csv(system.file("extdata", "buffers_sample2.csv",

-#'package="protGear"))

-#' plot_buffer(df=buffers,buffer_names = "sampleID")

-plot_buffer <- function(df = buffers,

-                        buffer_names = "antigen",

-                        buffer_mfi = "FMedianBG_correct",

-                        slide_id = ".id") {

-  x <- buffer_names

-  y <- buffer_mfi

-  df[[buffer_names]] <- factor(df[[buffer_names]] ,

-                               levels = mixedsort(unique(as.character(df[[buffer_names]]))))

-

-

-  p <- ggplot(data = df, aes_string(x = x, y = y)) +

-    geom_jitter(aes_string(x = x, y = y, color = slide_id)) +

-    geom_boxplot(aes_string(x = x, y = y), alpha = 0.2) +

-    theme_light() +

-    theme(axis.text.x = element_text(angle = 45, hjust = 1))

-  return(p)

-}

deleted file mode 100644

@@ -1,24 +0,0 @@

-{

-    "id": "4D556D40",

-    "path": "C:/Users/kmwai/OneDrive - Kemri Wellcome Trust/H_Drive/PhD_work/projects/protGear_data/runthis.R",

-    "project_path": null,

-    "type": "r_source",

-    "hash": "3771495863",

-    "contents": "",

-    "dirty": false,

-    "created": 1647626114720.0,

-    "source_on_save": false,

-    "relative_order": 13,

-    "properties": {

-        "source_window_id": "",

-        "Source": "Source"

-    },

-    "folds": "",

-    "lastKnownWriteTime": 1598965142,

-    "encoding": "UTF-8",

-    "collab_server": "",

-    "source_window": "",

-    "last_content_update": 1598965142,

-    "read_only": false,

-    "read_only_alternatives": []

-}

\ No newline at end of file

deleted file mode 100644

@@ -1 +0,0 @@

-devtools::document()

deleted file mode 100644

@@ -1,26 +0,0 @@

-{

-    "id": "5344A29F",

-    "path": "C:/Users/kmwai/OneDrive - Kemri Wellcome Trust/H_Drive/PhD_work/projects/protGear_data/protGear/NEWS.md",

-    "project_path": "NEWS.md",

-    "type": "markdown",

-    "hash": "0",

-    "contents": "",

-    "dirty": false,

-    "created": 1647521025022.0,

-    "source_on_save": false,

-    "relative_order": 8,

-    "properties": {

-        "source_window_id": "",

-        "Source": "Source",

-        "cursorPosition": "7,38",

-        "scrollLine": "0"

-    },

-    "folds": "",

-    "lastKnownWriteTime": 1647521040,

-    "encoding": "UTF-8",

-    "collab_server": "",

-    "source_window": "",

-    "last_content_update": 1647521040512,

-    "read_only": false,

-    "read_only_alternatives": []

-}

\ No newline at end of file

deleted file mode 100644

@@ -1,13 +0,0 @@

-# Changes in version 0.99.1 (2021-12-15)

-

-+ Submitted to Bioconductor

-

-# Changes in version 0.99.543 (2022-02-14)

-+ Submitted to Bioconductor for review

-

-# Changes in version 0.99.544 (2022-03-17)

-+ Removed unnecessary files

-+ Added Suggests in Description

-+ Updated R requirement to 4.2

-+ Added the data documentation

-

deleted file mode 100644

@@ -1,26 +0,0 @@

-{

-    "id": "5B090C88",

-    "path": "C:/Users/kmwai/OneDrive - Kemri Wellcome Trust/H_Drive/PhD_work/projects/protGear_data/protGear/inst/shiny-examples/protGear_interactive/app.R",

-    "project_path": "inst/shiny-examples/protGear_interactive/app.R",

-    "type": "r_source",

-    "hash": "0",

-    "contents": "",

-    "dirty": false,

-    "created": 1644833056795.0,

-    "source_on_save": false,

-    "relative_order": 15,

-    "properties": {

-        "source_window_id": "",

-        "Source": "Source",

-        "cursorPosition": "6,4",

-        "scrollLine": "0"

-    },

-    "folds": "",

-    "lastKnownWriteTime": 1619183120,

-    "encoding": "UTF-8",

-    "collab_server": "",

-    "source_window": "",

-    "last_content_update": 1619183120,

-    "read_only": false,

-    "read_only_alternatives": []

-}

\ No newline at end of file

deleted file mode 100644

@@ -1,54 +0,0 @@

-library(shiny)

-library(shinyFiles)

-

-# Define UI for application that draws a histogram

-ui <- fluidPage(

-

-  # Application title

-  titlePanel("Example - Shiny Files Buttons Use"),

-

-  # Sidebar with a slider input for number of bins

-  sidebarLayout(

-    sidebarPanel(

-      p("First press this ShinyDir Button to locate an existing folder and set

-        it to be your new working directory"),

-      shinyDirButton("folderChoose","Choose Folder","Choose working directory"),

-

-      p("In this second step, press the ShinyFiles Button that should point to the

-        volumes (Just as the previous button does). In my R version, this is where it

-        renders a white interface (see attached picture"),

-      shinyFilesButton("filesChoose1","Files Chooser 1","Choose your files",

-                       multiple=TRUE),

-

-      p("In this third button, pI owuld like to link the ShinyFiles interface with

-        the selected folder in button 1. This part I have not been able to solve"),

-      shinyFilesButton("filesChoose2","Files Chooser 2","Choose your files",

-                       multiple=TRUE)

-

-      ),

-

-    # Show a plot of the generated distribution

-    mainPanel(

-      verbatimTextOutput("path")

-    )

-      )

-    )

-

-# Define server logic required to draw a histogram

-server <- function(input, output, session) {

-

-  volumes <-  getVolumes()

-  shinyDirChoose(input, "folderChoose", roots = volumes, session = session)

-  sel_path <- reactive({return(print(parseDirPath(volumes, input$folderChoose)))})

-  shinyFileChoose(input, "filesChoose1", roots = volumes, session = session)

-

-

-  setWorkingDir<-eventReactive(input$folderChoose,{

-    setwd(sel_path())

-  })

-

-  output$path<-renderText(sel_path())

-}

-

-# Run the application

-shinyApp(ui = ui, server = server)

deleted file mode 100644

@@ -1,27 +0,0 @@

-{

-    "id": "68D04000",

-    "path": "C:/Users/kmwai/OneDrive - Kemri Wellcome Trust/H_Drive/PhD_work/projects/protGear_data/protGear/vignettes/vignette.Rmd",

-    "project_path": "vignettes/vignette.Rmd",

-    "type": "r_markdown",

-    "hash": "0",

-    "contents": "",

-    "dirty": true,

-    "created": 1647516170123.0,

-    "source_on_save": false,

-    "relative_order": 7,

-    "properties": {

-        "source_window_id": "",

-        "Source": "Source",

-        "cursorPosition": "258,0",

-        "scrollLine": "0",

-        "last_setup_crc32": ""

-    },

-    "folds": "",

-    "lastKnownWriteTime": 1647443184,

-    "encoding": "UTF-8",

-    "collab_server": "",

-    "source_window": "",

-    "last_content_update": 1647516586911,

-    "read_only": false,

-    "read_only_alternatives": []

-}

\ No newline at end of file

deleted file mode 100644

@@ -1,629 +0,0 @@

-title: protGear vignette

-  processing suite

-author: "Kennedy Mwai"

-header-includes:

-   - \usepackage[T1]{fontenc}

-date: '`r format(Sys.time(), "%d %B, %Y")`'

-package: protGear

-vignette: >

-  %\VignetteIndexEntry{protGear}

-  %\VignetteEncoding{UTF-8}

-  %\VignetteEngine{knitr::rmarkdown}

-link-citations: true

-output:

-  html_document:

-    df_print: paged

-    toc: true

-    toc_float:

-      collapsed: false

-    number_sections: false

-    theme: spacelab

-    highlight: tango

-  pdf_document: default

-

-

-

-```{r setup, message=FALSE, warning=FALSE}

-library(ggpubr)

-library(gtools)

-library(purrr)

-library(scales)

-library(pheatmap)

-library(data.table)

-library(kableExtra)

-library(gridExtra)

-library(png)

-library(knitr)

-library(grid)

-library(styler)

-library(FactoMineR)

-library(factoextra)

-library(magick)

-library(rlang)

-library(GGally)

-library(ggplotify)

-library(remotes)

-library(dplyr)

-library(tidyr)

-knitr::opts_chunk$set(echo = TRUE, message=FALSE,warning = FALSE,

-                      fig.align = 'center',

-                      dev = "png", 

-                       tidy='styler', tidy.opts=list(strict=TRUE))

-

-

-```

-

-

-```{css ,echo=FALSE}

-.custom-inline {

-  color: red;

-  font-weight: 700

-}

-```

-

-## Introduction 

-

-### General information

-protGear is a package for protein micro data processing just before the main analysis. The package loads the '`gpr`' or '`txt`' file format extracted by the quantification software and merges this with the specific sample identifiers. The package processes multiple files extracted batch by batch with their corresponding sample identifier file. The sample identifier file has 2 variables '`v1`' and '`v2`' which indicate the mini-array or block number and sample identifier respectively. The '`gpr`' file and the corresponding sample identifier file have the same file name.  protGear also provides a web based $Shiny^{(R)}$ platform for real time visualization of the data processing. 

-

-In this vignette the general work-flow of protGear will be outlined by processing a sample dataset from a multicentre study __Plasmodium falciparum__ Merozoite Protein Microarray. The multicentre study design motivated the development of the protGear suite. 

-

-The details of the methodologies are published here https://doi.org/10.1016/j.csbj.2021.04.044

-

-### Analysis setup

-Create 2 folders that hold the '`.gpr`' files and the corresponding sample identifier files.

-

-![Folder structure of array and sample ID files](folder_structure.png){width=70%}

-

-

-

-## Sample identifier file

-

-![sample ID file structure](image_slide.png)

-

-### Installation 

-

-To install `protGear` from BioConductor the following commands in R

-

-```{r install_package, eval=FALSE}

-## install from BioConductor

-if (!require("BiocManager", quietly = TRUE))

-    install.packages("BiocManager")

-BiocManager::install('protGear')

-```

-

-

-## Importing data

-

-```{r call_protGear}

-## load the package 

-library(protGear)

-```

-

-The first part is to specify the parameters of the micro-array experiment to assist in processing the data.  The parameters specified are 

-

-  - channel - The scanner fluorescence output used to record the data. It can be  green,red,blue among others with a specified number. 

-  - chip_path - the folder where the sub folders of 'gpr' or 'txt' files are stored. This path contains sub folders with the array data, for example the sub folders for the different batches. 

-  - totsamples - the number of samples in a slide or array.  

-  - blockspersample - The number of blocks a sample it takes. In this example each sample occupies 2 blocks each with 384 spots. 

-  - sampleID_path - the folder where the sample identifiers files are stored

-  - machine - The indicator for which machine was used to hybridize the samples if the experiment had more than one machine. 

-  - date_process -the date of sample processing 

-  

-The parameters "`chip_path`", "`channel`" , "`totsamples`" and "`sampleID_path`" are mandatory. 

-

-```{r array_params}

-## specify the the parameters to process the data

-genepix_vars <- array_vars(channel="635" ,

-                           chip_path = system.file("extdata/array_data/", package="protGear"),

-                           totsamples = 21,

-                           blockspersample = 2,

-                           sampleID_path = system.file("extdata/array_sampleID/", package="protGear"),

-                           mig_prefix = "_first",

-                           machine =1,

-                           ## optional 

-                           date_process = "0520")

-```

-

-

-The exact channel used should be checked in the header of the file from the quantification software under `Wavelengths`. 

-

-```{r gpr_header}

-header_gpr <- readLines(system.file("extdata/array_data/machine1/KK2-06.txt", package="protGear"),

-                        n=40)

-header_gpr <- gsub("\"", "", header_gpr[1:32])

-header_gpr[1:32]

-```

-

-

-The function  `r text_spec("check_sampleID_files()",color="red")` helps to check whether each micro array file has a corresponding sample identifier file. The sample identifier files are generated from the lab plate maps to match the corresponding samples on a specific slide.If the sample identifier file is missing, protGear automatically generates the id's. 

-

-### Spatial structure of slide

-

-protGear offers a functionality to inspect the slide visually for any strong spatial biases when the scan image is not available. However, we recommend using the scanned image to visualize the spatial artefacts that might not be recorded in the `.gpr` file. We include the functions `r text_spec("visualize_slide()",color="red")` and `r text_spec("visualize_slide_2d()",color="red")`  to check the spatial structure. The functions are build on `r text_spec("structure_plot()",color="red")`  which shows the block and mini-array structure of a slide. 

-

-

-

-#### Visualize the foreground MFI 

-

-Here we visualize the foreground MFI using the `r text_spec("visualize_slide",color="red")` function

-

-```{r slide_struct, fig.align='left'}

-visualize_slide(infile=system.file("extdata/array_data/machine1/KK2-06.txt", package="protGear"),

-                MFI_var ='F635 Median' )

-

-```

-

-#### Visualize the background MFI  

-

-Here we visualize  the background MFI using the `visualize_slide_2d` function

-

-```{r slide_struct_2d, fig.align='left'}

-visualize_slide_2d(infile =system.file("extdata/array_data/machine1/KK2-06.txt", package="protGear"), 

-                   MFI_var ='B635 Median' )

-```

-

-

-### Import .gpr/txt data

-

-Microarray data is imported using the `r text_spec("read_array_files()",color="red")` function. The function accepts the following mandatory arguments; 

-

- - `filename` - the name of the file which the data are to be read from. In this example a list of multiple files from a folder is used and passed to `r text_spec("read_array_files()","red")` using `r text_spec("purrr",color="red")`. 

- - `data_path` - The path where the file with the data  is located 

- - `genepix_vars` -  A list of specific definitions of the experiment design. See  `r text_spec("array_vars()",color="red")`  

-

-For this example I use the sub-folder 1 specified using `genepix_vars$paths[[1]]` which is this path under vignette folder `r genepix_vars$paths[[1]]`. 

- 

-```{r array_files}

-#### read in all the datasets

-### list all the file names under data folder

-filenames <- list.files(file.path(genepix_vars$paths[[1]]), 

-                        pattern="*.txt$|*.gpr$", full.names=FALSE)

-#' @___________________read_in_the_files_with_the_text_data_from_the_chip_____________________________

-### read all the data files and save them in a list 

-data_path <- paste0(genepix_vars$paths[[1]],"/") 

-data_files <- purrr::map(.x = filenames, 

-                         .f = read_array_files,

-                         data_path=data_path ,

-                         genepix_vars=genepix_vars)

-data_files <- set_names(data_files, purrr::map(filenames, name_of_files))

-```

-

-

-## Background Correction

-

-Background noise is caused by non-specific fluorescence such as auto-fluorescence of the glass slide or non-specific binding of parameters and reference substances. To cut down the effect of background noise we have included different approaches for background correction. First, we extract the background values, visualize and select the best background approach. We have implemented five different approaches;

-  

-  1) Local background subtraction

-  2) Global background subtraction

-  3) Moving minimum background subtraction

-  4) Normal and exponential model (normexp) 

-  5) Log-linear background correction (Edwards)

-

-In  '`.gpr`' files the Background column starts with a '`B`' followed by the wavelength or channel. In order to perform background correction, we extract the background mean fluorescent intensities (MFI's) using the function `r text_spec("extract_bg()",color="red")` . The function accepts the arguments `iden` which is the file identifier,  `data_files` a list of data objects with names utilised by `iden` and `genepix_vars` defined using  `r text_spec("array_vars()",color="red")` function. We utilise the `purr::map` function to extract the background MFI of multiple data files. 

-

-```{r bg_data}

-## utilising the map package we process a number of files  under data_files list

-dfs <- names(data_files) 

-allData_bg <- purrr::map(.x=dfs, .f=extract_bg,data_files=data_files,genepix_vars)

-allData_bg <- set_names(allData_bg, purrr::map(filenames, name_of_files))

-allData_bg <- plyr::ldply(allData_bg)

-```

-

-### Foreground vs Background

-

-Before selecting the best background correction approach the MFI signals are be inspected visually. In protGear we first utilise the function `r text_spec("plot_FB()",color="red")` that graphs the background, _BG_Median_ and foreground values, _FBG_Median_. On the protGear Shiny platform the visuals are interactive and you can identify the features or blocks with strong bias. 

-

-```{r bg_vs_fg}

-p1 <- plot_FB(allData_bg,antigen_name="antigen",

-              bg_MFI="BG_Median",FG_MFI="FBG_Median",log=FALSE)

-

-

-p1

-

-```

-

-### Background MFI by blocks

-

-```{r bg_plot}

-p2 <- plot_bg(df=allData_bg, x_axis="Block",bg_MFI="BG_Median",

-        log_mfi=TRUE) 

-p2

-```

-

-### Background correction

-

-After background visualization and selecting the best approach the array data are merged with their specific sample identifier files. 

-

-_`r text_spec("Note:",color="red")`_ Each array file must have its own corresponding sample identifier `.csv` file stored in `r text_spec("array_vars()",color="red")` function under `sampleID_path`. Check General information section.  

-

-

-The method of background subtraction selected is specified under `r text_spec("method",color="red")` below. The background correction is performed by  `r text_spec("bg_correct()",color="red")` function.

-

-

-

-```{r bg_correct}

-sample_ID_merged_dfs <- purrr::map(.x=dfs, .f=merge_sampleID ,data_files=data_files , 

-                             genepix_vars, method="subtract_local")

-sample_ID_merged_dfs <- set_names(sample_ID_merged_dfs, purrr::map(filenames, name_of_files))

-```

-

-

-## Buffer spots

-

-Buffer spots are specific to the experiment design and are not always included. Buffer spots are used to check for unexpected scanning artefacts. The buffer spots should have similar values in  different slides. Some outliers are expected for buffer spots close sample spots or landmark. However you can specify the name of your control antigens here `r text_spec('buffer_spot="buffer"',color="blue")` if you do not have buffer spots.

-

-```{r buffer_spots_data}

-buffer_transp <- purrr::map(.x=sample_ID_merged_dfs, .f=buffer_spots ,  buffer_spot="buffer")

-

-buffer_transp <- set_names(buffer_transp, purrr::map(filenames, name_of_files))

-

-buffers <- plyr::ldply(buffer_transp)

-plot_buffer(buffers,buffer_names="antigen",buffer_mfi="FMedianBG_correct",slide_id=".id")

-

-```

-

-## Coefficient of Variation (CV)

-

-To calculate the CV's we utilise the  `r text_spec("cv_estimation()",color="red")` function with a `cv_cut_off` specified , sample identifier variable and antigen specified under `sampleID_var` and `antigen` respectively. The `replicate_var` and `mfi_var` identifies the variable with the replicate rank generated and MFI's values.