comparison quality_report.xml @ 12:ecaebe7c7b54 draft

"planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/cardinal commit 0c667acd7cc0d0ef6c4e979ca29372b8c0d92c23"

11:f396c176f366

<tool id="cardinal_quality_report" name="MSI Qualitycontrol" version="@VERSION@.0">
    <description>
        mass spectrometry imaging QC
    </description>
    <macros>
        <import>macros.xml</import>

#end if

###################### calculation of data properties ################################
@DATA_PROPERTIES_INRAM@


## Median intensities
medint = round(median(int_matrix), digits=2)
## Spectra multiplied with m/z (potential number of peaks)
numpeaks = as.numeric(ncol(msidata)*nrow(msidata))
## Percentage of intensities > 0

medTIC = round(median(TICs), digits=1)
sdTIC = round(sd(TICs), digits=0)
## Median and sd # peaks per spectrum
medpeaks = round(median(colSums(spectra(msidata)>0, na.rm=TRUE), na.rm=TRUE), digits=0)
sdpeaks = round(sd(colSums(spectra(msidata)>0, na.rm=TRUE), na.rm=TRUE), digits=0)
## Processing informations
centroidedinfo = centroided(msidata)

############## Read and filter tabular file with m/z ###########################

properties2 = c("Median of intensities",
               "Intensities > 0",
               "Number of empty spectra",
               "Median TIC ± sd", 
               "Median # peaks per spectrum ± sd",
               "Centroided", 
               paste0("input m/z (#valid/#input) in \n", "$calibrant_file.display_name"))

values2 = c(paste0(medint),
           paste0(percpeaks, " %"), 
           paste0(NumemptyTIC), 
           paste0(medTIC, " ± ", sdTIC),
           paste0(medpeaks, " ± ",sdpeaks),
           paste0(centroidedinfo), 
           paste0(number_calibrants_valid, " / ", number_calibrants_in))

property_df2 = data.frame(properties2, values2)
colnames(property_df2) = c("properties", "values")

    pixelnumber = 1:pixelcount
    pixelxyarray=data.frame(coord(msidata)\$x, coord(msidata)\$y,pixelnumber)
    colnames(pixelxyarray) = c("x", "y", "pixelnumber")
    gg_title = "Pixel order"
    
    print(ggplot(pixelxyarray, aes(x=x, y=y, fill=pixelnumber))+
     geom_tile() + coord_fixed()+
     ggtitle(gg_title) + theme_bw()+
     theme(plot.title = element_text(hjust = 0.5))+
     theme(text=element_text(family="ArialMT", face="bold", size=12))+

    differencevector = numeric()
    differencevector2 = vector()

    if (length(inputcalibrantmasses) != 0){

    ### calculate plusminus values in m/z for each calibrant, this is used for all following plots
    plusminusvalues = rep($plusminus_ppm/1000000, length(inputcalibrantmasses)) * inputcalibrantmasses

        for (mass in 1:length(inputcalibrantmasses)){

            maxmasspixel1 = features(msidata_no_NA, mz=inputcalibrantmasses[mass]+1.5)
            minmasspixel2 = features(msidata_no_NA, mz=inputcalibrantmasses[mass]-0.25)
            maxmasspixel2 = features(msidata_no_NA, mz=inputcalibrantmasses[mass]+0.5)
            minmasspixel3 = features(msidata_no_NA, mz=inputcalibrantmasses[mass]-1.5)
            maxmasspixel3 = features(msidata_no_NA, mz=inputcalibrantmasses[mass]+3)

            ### find m/z with the highest mean intensity in m/z range (red line in plot 16) and calculate ppm difference for plot 17
            filtered_data = msidata_no_NA[mz(msidata_no_NA) >= inputcalibrantmasses[mass]-plusminusvalues[mass] & mz(msidata_no_NA) <= inputcalibrantmasses[mass]+plusminusvalues[mass],]

            if (nrow(filtered_data) > 0 & sum(spectra(filtered_data)) > 0){

        par(mfrow = c(1,1))
        ### plot the ppm difference calculated above: theor. m/z value to highest m/z value: 

        calibrant_names = as.character(inputcalibrants[,2])
        diff_df = data.frame(differencevector, calibrant_names)

        if (sum(is.na(diff_df[,1])) == nrow(diff_df)){
                plot(0,type='n',axes=FALSE,ann=FALSE)
                title(main=paste("plot 17: no peaks in the chosen region, repeat with higher ppm range"))
        }else{

12:ecaebe7c7b54

<tool id="cardinal_quality_report" name="MSI Qualitycontrol" version="@VERSION@.1">
    <description>
        mass spectrometry imaging QC
    </description>
    <macros>
        <import>macros.xml</import>

#end if

###################### calculation of data properties ################################
@DATA_PROPERTIES_INRAM@

## Median intensities
medint = round(median(int_matrix), digits=2)
## Spectra multiplied with m/z (potential number of peaks)
numpeaks = as.numeric(ncol(msidata)*nrow(msidata))
## Percentage of intensities > 0

medTIC = round(median(TICs), digits=1)
sdTIC = round(sd(TICs), digits=0)
## Median and sd # peaks per spectrum
medpeaks = round(median(colSums(spectra(msidata)>0, na.rm=TRUE), na.rm=TRUE), digits=0)
sdpeaks = round(sd(colSums(spectra(msidata)>0, na.rm=TRUE), na.rm=TRUE), digits=0)
##max window size 
max_window = round(mz(msidata)[nrow(msidata)]-mz(msidata)[nrow(msidata)-1], digits=2)
## Processing informations
centroidedinfo = centroided(msidata)

############## Read and filter tabular file with m/z ###########################

properties2 = c("Median of intensities",
               "Intensities > 0",
               "Number of empty spectra",
               "Median TIC ± sd", 
               "Median # peaks per spectrum ± sd",
               "maximum m/z window size",
               "Centroided", 
               paste0("input m/z (#valid/#input) in \n", "$calibrant_file.display_name"))

values2 = c(paste0(medint),
           paste0(percpeaks, " %"), 
           paste0(NumemptyTIC), 
           paste0(medTIC, " ± ", sdTIC),
           paste0(medpeaks, " ± ",sdpeaks),
           paste0(max_window),
           paste0(centroidedinfo), 
           paste0(number_calibrants_valid, " / ", number_calibrants_in))

property_df2 = data.frame(properties2, values2)
colnames(property_df2) = c("properties", "values")

    pixelnumber = 1:pixelcount
    pixelxyarray=data.frame(coord(msidata)\$x, coord(msidata)\$y,pixelnumber)
    colnames(pixelxyarray) = c("x", "y", "pixelnumber")
    gg_title = "Pixel order"

    print(ggplot(pixelxyarray, aes(x=x, y=y, fill=pixelnumber))+
     geom_tile() + coord_fixed()+
     ggtitle(gg_title) + theme_bw()+
     theme(plot.title = element_text(hjust = 0.5))+
     theme(text=element_text(family="ArialMT", face="bold", size=12))+

    differencevector = numeric()
    differencevector2 = vector()

    if (length(inputcalibrantmasses) != 0){


    ### calculate plusminus values in m/z for each calibrant, this is used for all following plots
    plusminusvalues = rep($plusminus_ppm/1000000, length(inputcalibrantmasses)) * inputcalibrantmasses

        for (mass in 1:length(inputcalibrantmasses)){

            maxmasspixel1 = features(msidata_no_NA, mz=inputcalibrantmasses[mass]+1.5)
            minmasspixel2 = features(msidata_no_NA, mz=inputcalibrantmasses[mass]-0.25)
            maxmasspixel2 = features(msidata_no_NA, mz=inputcalibrantmasses[mass]+0.5)
            minmasspixel3 = features(msidata_no_NA, mz=inputcalibrantmasses[mass]-1.5)
            maxmasspixel3 = features(msidata_no_NA, mz=inputcalibrantmasses[mass]+3)
            
            ## test if some values are lower than min(mz)
            minmasspixel1 = ifelse(length(minmasspixel1)>0, minmasspixel1, 1)
            minmasspixel2 = ifelse(length(minmasspixel2)>0, minmasspixel2, 1)
            minmasspixel3 = ifelse(length(minmasspixel3)>0, minmasspixel3, 1)
            
            ## test if min and max are same (more likely for centroided data):
            maxmasspixel1 = ifelse(minmasspixel1 != maxmasspixel1, maxmasspixel1, maxmasspixel1 + 1)
            maxmasspixel2 = ifelse(minmasspixel2 != maxmasspixel2, maxmasspixel2, maxmasspixel1 + 1)
            maxmasspixel3 = ifelse(minmasspixel3 != maxmasspixel3, maxmasspixel3, maxmasspixel1 + 1)
            

            ### find m/z with the highest mean intensity in m/z range (red line in plot 16) and calculate ppm difference for plot 17
            filtered_data = msidata_no_NA[mz(msidata_no_NA) >= inputcalibrantmasses[mass]-plusminusvalues[mass] & mz(msidata_no_NA) <= inputcalibrantmasses[mass]+plusminusvalues[mass],]

            if (nrow(filtered_data) > 0 & sum(spectra(filtered_data)) > 0){

        par(mfrow = c(1,1))
        ### plot the ppm difference calculated above: theor. m/z value to highest m/z value: 

        calibrant_names = as.character(inputcalibrants[,2])

        diff_df = data.frame(differencevector, calibrant_names)


        if (sum(is.na(diff_df[,1])) == nrow(diff_df)){
                plot(0,type='n',axes=FALSE,ann=FALSE)
                title(main=paste("plot 17: no peaks in the chosen region, repeat with higher ppm range"))
        }else{