comparison segmentation_tool.xml @ 6:80b6b96a175c draft

planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/msi_segmentation commit 37da74ed68228b16efbdbde776e7c38cc06eb5d5

5:cee9cf693709

<tool id="mass_spectrometry_imaging_segmentations" name="MSI segmentation" version="1.10.0.1">
    <description>mass spectrometry imaging spatial clustering</description>
    <requirements>
        <requirement type="package" version="1.10.0">bioconductor-cardinal</requirement>
        <requirement type="package" version="2.2.1">r-gridextra</requirement>
        <requirement type="package" version="0.20-35">r-lattice</requirement>

library(lattice)

## Read MALDI Imaging dataset

#if $infile.ext == 'imzml'
    msidata = readImzML('infile')
#elif $infile.ext == 'analyze75'
    msidata = readAnalyze('infile')
#else
    load('infile.RData')
#end if

###################################### file properties in numbers ##############

## Number of features (m/z)
maxfeatures = length(features(msidata))
## Range m/z

} else {
  peakpickinginfo=processinginfo@peakPicking
}

properties = c("Number of m/z features",
               "Range of m/z values [Da]",
               "Number of pixels", 
               "Range of x coordinates", 
               "Range of y coordinates",
               "Range of intensities", 
               "Median of intensities",

grid.table(property_df, rows= NULL)

if (npeaks > 0)
{


######################## II) segmentation tools #############################
#############################################################################
        #set $color_string = ','.join(['"%s"' % $color.feature_color for $color in $colours])
        colourvector = c($color_string)

            ##pca
            
            component_vector = character()
            for (numberofcomponents in 1:$segm_cond.pca_ncomp)
            {component_vector[numberofcomponents]= paste0("PC", numberofcomponents)}
            pca = PCA(msidata, ncomp=$segm_cond.pca_ncomp, column = component_vector, superpose = FALSE, 
            method = "$segm_cond.pca_method", scale = $segm_cond.pca_scale, layout = c(ncomp, 1))

            print(image(pca, main="PCA image", lattice=lattice_input, strip = strip_input, col=colourvector))
            print(plot(pca, main="PCA plot", lattice=lattice_input, col= colourvector, strip = strip_input))

            pcaloadings = (pca@resultData\$ncomp\$loadings) ### loading for each m/z value
            pcascores = (pca@resultData\$ncomp\$scores) ### scores for each pixel

            write.table(pcaloadings, file="$mzfeatures", quote = FALSE, row.names = TRUE, col.names=NA, sep = "\t")
            write.table(pcascores, file="$pixeloutput", quote = FALSE, row.names = TRUE, col.names=NA, sep = "\t")

            ## optional output as .RData
            #if $output_rdata:

            ## save as (.RData)
            save(pca, file="$segmentation_rdata")

            #end if

            ##centroids

            ssc = spatialShrunkenCentroids(msidata, r=c($segm_cond.centroids_r), k=c($segm_cond.centroids_k), s=c($segm_cond.centroids_s), method="$segm_cond.centroids_method")
            print(image(ssc, key=TRUE, main="Spatial shrunken centroids", lattice=lattice_input, strip = strip_input, col= colourvector,layout=c(1,1)))
            print(plot(ssc, main="Spatial shrunken centroids plot", lattice=lattice_input, col= colourvector, strip = strip_input,layout=c($segm_cond.centroids_layout)))

            ssc_classes = data.frame(matrix(NA, nrow = pixelcount, ncol = 0))
            for (iteration in 1:length(ssc@resultData)){
            ssc_class = ((ssc@resultData)[[iteration]]\$classes)
            ssc_classes = cbind(ssc_classes, ssc_class) }
            colnames(ssc_classes) = names((ssc@resultData)) 

            ssc_toplabels =  topLabels(ssc, n=$segm_cond.centroids_toplabels)

            write.table(ssc_toplabels, file="$mzfeatures", quote = FALSE, row.names = TRUE, col.names=NA, sep = "\t")
            write.table(ssc_classes, file="$pixeloutput", quote = FALSE, row.names = TRUE, col.names=NA, sep = "\t")

}

    ]]></configfile>
    </configfiles>
    <inputs>
        <param name="infile" type="data" format="imzml, rdata, analyze75"
               label="Inputfile as imzML, Analyze7.5 or Cardinal MSImageSet saved as RData"
                help="Upload composite datatype imzml (ibd+imzML) or analyze75 (hdr+img+t2m) or regular upload .RData (Cardinal MSImageSet)"/>
            <conditional name="segm_cond">
                <param name="segmentationtool" type="select" label="Select the tool for spatial clustering">
                    <option value="pca" selected="True">pca</option>
                    <option value="kmeans">k-means</option>
                    <option value="centroids">spatial shrunken centroids</option>

                           label="The initial number of clusters (k)" help="Multiple values are allowed (e.g. 1,2,3 or 2:5)"/>
                    <param name="centroids_s" type="text" value="2"
                           label="The sparsity thresholding parameter by which to shrink the t-statistics (s)"
                           help="As s increases, fewer m/z features (m/z values) will be used in the spatial segmentation, and only the informative m/z features will be retained. Multiple values are allowed (e.g. 1,2,3 or 2:5)"/>
                    <param name="centroids_method" type="select" display="radio" label = "The method to use to calculate the spatial smoothing kernels for the embedding. The 'gaussian' method refers to spatially-aware (SA) weights, and 'adaptive' refers to spatially-aware structurally-adaptive (SASA) weights">
                        <option value="gaussian" selected="True">gaussian</option>
                        <option value="adaptive">adaptive</option>
                </param>
                <param name="centroids_toplabels" type="integer" value="500"
                       label="Number of toplabels (m/z) which should be written in tabular output"/>
                <param name="centroids_layout" type="text" value="1,1"
                       label="Number of rows and columns to plot pictures in pdf output" help="e.g. 1,1 means 1 plot per page; 2,3 means 2 rows with 3 plots each = 6 plots per page"/>

        </test>
        <test>
            <param name="infile" value="preprocessed.RData" ftype="rdata"/>
            <param name="segmentationtool" value="centroids"/>
            <param name="centroids_r" value="1,2"/>
            <param name="centroids_k" value="5"/>
            <param name="centroids_toplabels" value="50"/>
            <repeat name="colours">
                <param name="feature_color" value="#0000FF"/>
            </repeat>
            <repeat name="colours">

- Cardinal "MSImageSet" data (with variable name "msidata", saved as .RData)

Options: 

- PCA: principal component analysis
- k-means: patially-aware k-means clustering
- spatial shrunken centroids: Allows the number of segments to decrease according to the data. This allows automatic selection of the number of clusters

Output: 

- Pdf with the heatmaps and plots for the segmentation

6:80b6b96a175c

<tool id="mass_spectrometry_imaging_segmentations" name="MSI segmentation" version="1.10.0.2">
    <description>mass spectrometry imaging spatial clustering</description>
    <requirements>
        <requirement type="package" version="1.10.0">bioconductor-cardinal</requirement>
        <requirement type="package" version="2.2.1">r-gridextra</requirement>
        <requirement type="package" version="0.20-35">r-lattice</requirement>

library(lattice)

## Read MALDI Imaging dataset

#if $infile.ext == 'imzml'
    msidata <- readImzML('infile', mass.accuracy=$accuracy, units.accuracy = "$units")
#elif $infile.ext == 'analyze75'
    msidata = readAnalyze('infile')
#else
    load('infile.RData')
#end if

## create full matrix to make processed imzML files compatible with segmentation
iData(msidata) <- iData(msidata)[] 
###################################### file properties in numbers ##############

## Number of features (m/z)
maxfeatures = length(features(msidata))
## Range m/z

} else {
  peakpickinginfo=processinginfo@peakPicking
}

properties = c("Number of m/z features",
               "Range of m/z values",
               "Number of pixels", 
               "Range of x coordinates", 
               "Range of y coordinates",
               "Range of intensities", 
               "Median of intensities",

grid.table(property_df, rows= NULL)

if (npeaks > 0)
{

######################## II) segmentation tools #############################
#############################################################################
        #set $color_string = ','.join(['"%s"' % $color.feature_color for $color in $colours])
        colourvector = c($color_string)

            ##pca
            
            component_vector = character()
            for (numberofcomponents in 1:$segm_cond.pca_ncomp)
            {component_vector[numberofcomponents]= paste0("PC", numberofcomponents)}
            pca_result = PCA(msidata, ncomp=$segm_cond.pca_ncomp, column = component_vector, superpose = FALSE, 
            method = "$segm_cond.pca_method", scale = $segm_cond.pca_scale, layout = c(ncomp, 1))

            ### images in pdf file
            print(image(pca_result, main="PCA image", lattice=lattice_input, strip = strip_input, col=colourvector))
            for (PCs in 1:$segm_cond.pca_ncomp){
                print(image(pca_result, column = c(paste0("PC",PCs)), superpose = FALSE, col.regions = risk.colors(100)))}
            ### plots in pdf file
            print(plot(pca_result, main="PCA plot", lattice=lattice_input, col= colourvector, strip = strip_input))
            for (PCs in 1:$segm_cond.pca_ncomp){
            print(plot(pca_result, column = c(paste0("PC",PCs)), superpose = FALSE))}

            
            ### values in tabular files
            pcaloadings = (pca_result@resultData\$ncomp\$loadings) ### loading for each m/z value
            pcascores = (pca_result@resultData\$ncomp\$scores) ### scores for each pixel

            write.table(pcaloadings, file="$mzfeatures", quote = FALSE, row.names = TRUE, col.names=NA, sep = "\t")
            write.table(pcascores, file="$pixeloutput", quote = FALSE, row.names = TRUE, col.names=NA, sep = "\t")

            ## optional output as .RData
            #if $output_rdata:
            ## save as (.RData)
            save(pca, file="$segmentation_rdata")

            #end if

            ##centroids

            ssc = spatialShrunkenCentroids(msidata, r=c($segm_cond.centroids_r), k=c($segm_cond.centroids_k), s=c($segm_cond.centroids_s), method="$segm_cond.centroids_method")
            print(image(ssc, key=TRUE, main="Spatial shrunken centroids", lattice=lattice_input, strip = strip_input, col= colourvector,layout=c(1,1)))
            print(plot(ssc, main="Spatial shrunken centroids plot", lattice=lattice_input, col= colourvector, strip = strip_input,layout=c($segm_cond.centroids_layout)))
            print(plot(ssc, mode = "tstatistics",key = TRUE, lattice=lattice_input, layout = c($segm_cond.centroids_layout), main="t-statistics", col=colourvector))
            print(plot(summary(ssc), main = "Number of segments",lattice=lattice_input))

            ssc_classes = data.frame(matrix(NA, nrow = pixelcount, ncol = 0))
            for (iteration in 1:length(ssc@resultData)){
            ssc_class = ((ssc@resultData)[[iteration]]\$classes)
            ssc_classes = cbind(ssc_classes, ssc_class) }
            colnames(ssc_classes) = names((ssc@resultData))

            ssc_toplabels =  topLabels(ssc, n=$segm_cond.centroids_toplabels)

            write.table(ssc_toplabels, file="$mzfeatures", quote = FALSE, row.names = TRUE, col.names=NA, sep = "\t")
            write.table(ssc_classes, file="$pixeloutput", quote = FALSE, row.names = TRUE, col.names=NA, sep = "\t")

}

    ]]></configfile>
    </configfiles>
    <inputs>
        <param name="infile" type="data" format="imzml,rdata,analyze75"
               label="Inputfile as imzML, Analyze7.5 or Cardinal MSImageSet saved as RData"
                help="Upload composite datatype imzml (ibd+imzML) or analyze75 (hdr+img+t2m) or regular upload .RData (Cardinal MSImageSet)"/>
        <param name="accuracy" type="float" value="50" label="Only for processed imzML files: enter mass accuracy to which the m/z values will be binned" help="This should be set to the native accuracy of the mass spectrometer, if known"/>
        <param name="units" display="radio" type="select" label="Only for processed imzML files: unit of the mass accuracy" help="either m/z or ppm">
            <option value="mz" >mz</option>
            <option value="ppm" selected="True" >ppm</option>
        </param>
            <conditional name="segm_cond">
                <param name="segmentationtool" type="select" label="Select the tool for spatial clustering">
                    <option value="pca" selected="True">pca</option>
                    <option value="kmeans">k-means</option>
                    <option value="centroids">spatial shrunken centroids</option>

                           label="The initial number of clusters (k)" help="Multiple values are allowed (e.g. 1,2,3 or 2:5)"/>
                    <param name="centroids_s" type="text" value="2"
                           label="The sparsity thresholding parameter by which to shrink the t-statistics (s)"
                           help="As s increases, fewer m/z features (m/z values) will be used in the spatial segmentation, and only the informative m/z features will be retained. Multiple values are allowed (e.g. 1,2,3 or 2:5)"/>
                    <param name="centroids_method" type="select" display="radio" label = "The method to use to calculate the spatial smoothing kernels for the embedding. The 'gaussian' method refers to spatially-aware (SA) weights, and 'adaptive' refers to spatially-aware structurally-adaptive (SASA) weights">
                        <option value="gaussian">gaussian</option>
                        <option value="adaptive" selected="True">adaptive</option>
                </param>
                <param name="centroids_toplabels" type="integer" value="500"
                       label="Number of toplabels (m/z) which should be written in tabular output"/>
                <param name="centroids_layout" type="text" value="1,1"
                       label="Number of rows and columns to plot pictures in pdf output" help="e.g. 1,1 means 1 plot per page; 2,3 means 2 rows with 3 plots each = 6 plots per page"/>

        </test>
        <test>
            <param name="infile" value="preprocessed.RData" ftype="rdata"/>
            <param name="segmentationtool" value="centroids"/>
            <param name="centroids_r" value="1,2"/>
            <param name="centroids_k" value="3"/>
            <param name="centroids_toplabels" value="50"/>
            <repeat name="colours">
                <param name="feature_color" value="#0000FF"/>
            </repeat>
            <repeat name="colours">

- Cardinal "MSImageSet" data (with variable name "msidata", saved as .RData)

Options: 

- PCA: principal component analysis
- k-means: spatially-aware k-means clustering
- spatial shrunken centroids: Allows the number of segments to decrease according to the data. This allows automatic selection of the number of clusters

Output: 

- Pdf with the heatmaps and plots for the segmentation