comparison segmentation.xml @ 7:5e73ae48d674 draft

"planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/cardinal commit f986c51abe33c7f622d429a3c4a79ee24b33c1f3"

6:2588e399e044

<tool id="cardinal_segmentations" name="MSI segmentation" version="@VERSION@.3">
    <description>mass spectrometry imaging spatial clustering</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements">
        <requirement type="package" version="2.3">r-gridextra</requirement>
        <requirement type="package" version="0.20_35">r-lattice</requirement>
    </expand>
    <command detect_errors="exit_code">
    <![CDATA[

        @INPUT_LINKING@
        cat '${MSI_segmentation}' &&

    ]]>
    </command>
    <configfiles>
        <configfile name="MSI_segmentation"><![CDATA[


################################# load libraries and read file #################

library(Cardinal)
library(gridExtra)
library(lattice)



@READING_MSIDATA_INRAM@


## remove duplicated coordinates
msidata <- msidata[,!duplicated(coord(msidata))]

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

        ### preparation for images and plots:
        #if str($image_type) == "standard_image":
            print("standard image")

            strip_input = FALSE
            lattice_input = FALSE

        #elif str($image_type) == "lattice_image":
            print("lattice image")

            strip_input = strip.custom(bg="lightgrey", par.strip.text=list(col="black", cex=.9))
            lattice_input = TRUE

        #end if

        ## set seed to make analysis reproducible
        set.seed($setseed)

        #if str( $segm_cond.segmentationtool ) == 'pca':

                PC_vector[[PCs]] = c(paste0("PC",PCs))}
            sd_table = cbind(PC_vector, sd_table)
            colnames(sd_table)[1] = "Principal components"
            grid.table(sd_table, rows=NULL)
            ### images in pdf file
            print(image(pca_result, main="PCA image", lattice=lattice_input, strip = strip_input, col=colourvector, ylim=c(maximumy+2, minimumy-2)))
            for (PCs in 1:$segm_cond.pca_ncomp){
                print(image(pca_result, column = c(paste0("PC",PCs)), lattice=lattice_input,strip = strip_input, superpose = FALSE, main=paste0("PC", PCs), col.regions = risk.colors(100), ylim=c(maximumy+2, minimumy-2)))}
            ### plots in pdf file
            print(plot(pca_result, main="PCA plot", lattice=lattice_input, col= colourvector, strip = strip_input))
            for (PCs in 1:$segm_cond.pca_ncomp){
                print(plot(pca_result, column = c(paste0("PC",PCs)),main=paste0("PC", PCs),strip = FALSE,superpose = FALSE))}

            ### values in tabular files
            pcaloadings = formatC(pca_result@resultData\$ncomp\$loadings, format = "e", digits = 6)### loading for each m/z value

            ## remove msidata to clean up RAM space
            rm(msidata)
            gc()

            print(image(skm, key=TRUE, main="K-means clustering", lattice=lattice_input, strip=strip_input, col= colourvector, layout=c(1,1), ylim=c(maximumy+2, minimumy-2)))
            print(plot(skm, main="K-means plot", lattice=lattice_input, col= colourvector, strip=strip_input, layout=c(1,1)))

            skm_clusters = data.frame(matrix(NA, nrow = pixelcount, ncol = 0))
            for (iteration in 1:length(skm@resultData)){
                        skm_cluster = ((skm@resultData)[[iteration]]\$cluster)
            skm_clusters = cbind(skm_clusters, skm_cluster) }

            y_coordinates = gsub(" y = ","",y_coords)
            pixel_names = paste0("xy_", x_coordinates, "_", y_coordinates)
            skm_clusters2 = data.frame(pixel_names, x_coordinates, y_coordinates, skm_clusters)
            colnames(skm_clusters2) = c("pixel names", "x", "y",names(skm@resultData))

            skm_toplabels = topLabels(skm, n=$segm_cond.kmeans_toplabels)

            write.table(skm_toplabels, file="$mzfeatures", quote = FALSE, row.names = FALSE, col.names=TRUE, sep = "\t")
            write.table(skm_clusters2, file="$pixeloutput", quote = FALSE, row.names = FALSE, col.names=TRUE, sep = "\t")

            ## optional output as .RData

            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")
            ## remove msidata to clean up RAM space
            rm(msidata)
            gc()
            print(image(ssc, key=TRUE, main="Spatial shrunken centroids", lattice=lattice_input, strip = TRUE, col= colourvector,layout=c(1,1), ylim=c(maximumy+2, minimumy-2)))
            print(plot(ssc, main="Spatial shrunken centroids plot", lattice=lattice_input, col= colourvector, strip = TRUE,layout=c(1,1)))
            print(plot(ssc, mode = "tstatistics",key = TRUE, lattice=lattice_input, layout = c(1,1), main="t-statistics", col=colourvector))

            plot(summary(ssc), main = "Number of segments")

            ssc_classes = data.frame(matrix(NA, nrow = pixelcount, ncol = 0))
            for (iteration in 1:length(ssc@resultData)){

            y_coordinates = gsub(" y = ","",y_coords)
            pixel_names = paste0("xy_", x_coordinates, "_", y_coordinates)
            ssc_classes2 = data.frame(pixel_names, x_coordinates, y_coordinates, ssc_classes)
            colnames(ssc_classes2) = c("pixel names", "x", "y", names(ssc@resultData))

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

            write.table(ssc_toplabels, file="$mzfeatures", quote = FALSE, row.names = FALSE, col.names=TRUE, sep = "\t")
            write.table(ssc_classes2, file="$pixeloutput", quote = FALSE, row.names = FALSE, col.names=TRUE, sep = "\t")

            ## optional output as .RData

                </param>
                <param name="centroids_toplabels" type="integer" value="500"
                       label="Number of toplabels (m/z) which should be written in tabular output"/>
                </when>
            </conditional>
            <param name="image_type" type="boolean" checked="True" truevalue="standard_image" falsevalue="lattice_image" 
            label="Standard image" help="No: lattice function is used to display image"/>
            <param name="svg_pixelimage" type="boolean" label="Export first segmentation image as svg"/>
            <repeat name="colours" title="Colours for the plots" min="1" max="50">
                <param name="feature_color" type="color" label="Colours" value="#ff00ff" help="Numbers of colours should be the same as number of components">
                  <sanitizer>
                    <valid initial="string.letters,string.digits">

    </outputs>
    <tests>
        <test>
            <expand macro="infile_imzml"/>
            <param name="segmentationtool" value="pca"/>
            <param name="image_type" value="lattice_image"/>
            <repeat name="colours">
                <param name="feature_color" value="#ff00ff"/>
            </repeat>
            <repeat name="colours">
                <param name="feature_color" value="#0000FF"/>
            </repeat>
            <output name="segmentationimages" file="pca_imzml.pdf" compare="sim_size"/>
            <output name="mzfeatures">
                <assert_contents>
                    <has_text text="300.17" />
                    <has_text text="-4.234458e-04" />
                    <has_text text="3.878545e-10" />
                    <has_n_columns n="3" />
                </assert_contents>
            </output>
            <output name="pixeloutput" file="scores_pca.tabular"/>
        </test>
        <test>
            <expand macro="infile_analyze75"/>
            <param name="segmentationtool" value="kmeans"/>
            <param name="kmeans_r" value="1:3"/>
            <param name="kmeans_k" value="2,3"/>
            <param name="kmeans_toplabels" value="20"/>
            <repeat name="colours">

                <param name="feature_color" value="#00C957"/>
            </repeat>
            <repeat name="colours">
                <param name="feature_color" value="#B0171F"/>
            </repeat>
            <repeat name="colours">
                <param name="feature_color" value="#FFD700"/>
            </repeat>
            <repeat name="colours">
                <param name="feature_color" value="#848484"/>
            </repeat>
            <output name="segmentationimages" file="centroids_rdata.pdf" compare="sim_size"/>
            <output name="mzfeatures" file="toplabels_ssc.tabular"/>
            <output name="pixeloutput" file="classes_ssc.tabular"/>
        </test>
    </tests>
    <help>
        <![CDATA[

@CARDINAL_DESCRIPTION@

7:5e73ae48d674

<tool id="cardinal_segmentations" name="MSI segmentation" version="@VERSION@.0">
    <description>mass spectrometry imaging spatial clustering</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements">
        <requirement type="package" version="2.3">r-gridextra</requirement>
      </expand>
    <command detect_errors="exit_code">
    <![CDATA[

        @INPUT_LINKING@
        cat '${MSI_segmentation}' &&

    ]]>
    </command>
    <configfiles>
        <configfile name="MSI_segmentation"><![CDATA[

################################# load libraries and read file #################

library(Cardinal)
library(gridExtra)

@READING_MSIDATA@

       msidata = as(msidata, "MSImageSet") ##coercion to MSImageSet

## remove duplicated coordinates
msidata <- msidata[,!duplicated(coord(msidata))]

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

        ## set seed to make analysis reproducible
        set.seed($setseed)

        #if str( $segm_cond.segmentationtool ) == 'pca':

                PC_vector[[PCs]] = c(paste0("PC",PCs))}
            sd_table = cbind(PC_vector, sd_table)
            colnames(sd_table)[1] = "Principal components"
            grid.table(sd_table, rows=NULL)
            ### images in pdf file
            print(image(pca_result, main="PCA image", strip = FALSE, col=colourvector, ylim=c(maximumy+2, minimumy-2)))
            for (PCs in 1:$segm_cond.pca_ncomp){
                print(image(pca_result, column = c(paste0("PC",PCs)),strip = FALSE, superpose = FALSE, main=paste0("PC", PCs), col.regions = risk.colors(100), ylim=c(maximumy+2, minimumy-2)))}
            ### plots in pdf file
            print(plot(pca_result, main="PCA plot", col= colourvector, strip = FALSE))
            for (PCs in 1:$segm_cond.pca_ncomp){
                print(plot(pca_result, column = c(paste0("PC",PCs)),main=paste0("PC", PCs),strip = FALSE,superpose = FALSE))}

            ### values in tabular files
            pcaloadings = formatC(pca_result@resultData\$ncomp\$loadings, format = "e", digits = 6)### loading for each m/z value

            ## remove msidata to clean up RAM space
            rm(msidata)
            gc()

            print(image(skm, key=TRUE, main="K-means clustering", strip=FALSE, col= colourvector, layout=c(1,1), ylim=c(maximumy+2, minimumy-2)))
            print(plot(skm, main="K-means plot", col= colourvector, strip=FALSE, layout=c(1,1)))

            skm_clusters = data.frame(matrix(NA, nrow = pixelcount, ncol = 0))
            for (iteration in 1:length(skm@resultData)){
                        skm_cluster = ((skm@resultData)[[iteration]]\$cluster)
            skm_clusters = cbind(skm_clusters, skm_cluster) }

            y_coordinates = gsub(" y = ","",y_coords)
            pixel_names = paste0("xy_", x_coordinates, "_", y_coordinates)
            skm_clusters2 = data.frame(pixel_names, x_coordinates, y_coordinates, skm_clusters)
            colnames(skm_clusters2) = c("pixel names", "x", "y",names(skm@resultData))

            skm_toplabels = topFeatures(skm, n=$segm_cond.kmeans_toplabels)

            write.table(skm_toplabels, file="$mzfeatures", quote = FALSE, row.names = FALSE, col.names=TRUE, sep = "\t")
            write.table(skm_clusters2, file="$pixeloutput", quote = FALSE, row.names = FALSE, col.names=TRUE, sep = "\t")

            ## optional output as .RData

            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")
            ## remove msidata to clean up RAM space
            rm(msidata)
            gc()
            print(image(ssc, key=TRUE, main="Spatial shrunken centroids", strip = TRUE, col= colourvector,layout=c(1,1), ylim=c(maximumy+2, minimumy-2)))
            print(plot(ssc, main="Spatial shrunken centroids plot", col= colourvector, strip = TRUE,layout=c(1,1)))
            print(plot(ssc, mode = "tstatistics",key = TRUE, layout = c(1,1), main="t-statistics", col=colourvector))

            plot(summary(ssc), main = "Number of segments")

            ssc_classes = data.frame(matrix(NA, nrow = pixelcount, ncol = 0))
            for (iteration in 1:length(ssc@resultData)){

            y_coordinates = gsub(" y = ","",y_coords)
            pixel_names = paste0("xy_", x_coordinates, "_", y_coordinates)
            ssc_classes2 = data.frame(pixel_names, x_coordinates, y_coordinates, ssc_classes)
            colnames(ssc_classes2) = c("pixel names", "x", "y", names(ssc@resultData))

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

            write.table(ssc_toplabels, file="$mzfeatures", quote = FALSE, row.names = FALSE, col.names=TRUE, sep = "\t")
            write.table(ssc_classes2, file="$pixeloutput", quote = FALSE, row.names = FALSE, col.names=TRUE, sep = "\t")

            ## optional output as .RData

                </param>
                <param name="centroids_toplabels" type="integer" value="500"
                       label="Number of toplabels (m/z) which should be written in tabular output"/>
                </when>
            </conditional>
            <param name="svg_pixelimage" type="boolean" label="Export first segmentation image as svg"/>
            <repeat name="colours" title="Colours for the plots" min="1" max="50">
                <param name="feature_color" type="color" label="Colours" value="#ff00ff" help="Numbers of colours should be the same as number of components">
                  <sanitizer>
                    <valid initial="string.letters,string.digits">

    </outputs>
    <tests>
        <test>
            <expand macro="infile_imzml"/>
            <param name="segmentationtool" value="pca"/>
            <repeat name="colours">
                <param name="feature_color" value="#ff00ff"/>
            </repeat>
            <repeat name="colours">
                <param name="feature_color" value="#0000FF"/>
            </repeat>
            <output name="segmentationimages" file="pca_imzml.pdf" compare="sim_size"/>
            <output name="mzfeatures">
                <assert_contents>
                    <has_text text="300.1667" />
                    <has_text text="300.25" />
                    <has_text text="-4.234458e-04" />
                    <has_text text="3.878545e-10" />
                    <has_n_columns n="3" />
                </assert_contents>
            </output>
            <output name="pixeloutput" file="scores_pca.tabular"/>
        </test>
        <test>
            <expand macro="infile_imzml"/>
            <param name="segmentationtool" value="kmeans"/>
            <param name="kmeans_r" value="1:3"/>
            <param name="kmeans_k" value="2,3"/>
            <param name="kmeans_toplabels" value="20"/>
            <repeat name="colours">

                <param name="feature_color" value="#00C957"/>
            </repeat>
            <repeat name="colours">
                <param name="feature_color" value="#B0171F"/>
            </repeat>
            <output name="segmentationimages" file="centroids_rdata.pdf" compare="sim_size"/>
            <output name="mzfeatures" file="toplabels_ssc.tabular"/>
            <output name="pixeloutput" file="classes_ssc.tabular"/>
        </test>
        <test>
            <param name="infile" value="" ftype="imzml">
                <composite_data value="preprocessing_results3.imzml"/>
                <composite_data value="preprocessing_results3.ibd"/>
            </param>
            <conditional name="processed_cond">
                <param name="processed_file" value="processed"/>
                <param name="accuracy" value="1"/>
                <param name="units" value="mz"/>
            </conditional>
            <param name="segmentationtool" value="centroids"/>
            <param name="centroids_r" value="1"/>
            <param name="centroids_k" value="2,3"/>
            <param name="centroids_s" value="0,3"/>
            <param name="centroids_toplabels" value="100"/>
            <repeat name="colours">
                <param name="feature_color" value="#0000FF"/>
            </repeat>
            <repeat name="colours">
                <param name="feature_color" value="#00C957"/>
            </repeat>
            <repeat name="colours">
                <param name="feature_color" value="#B0171F"/>
            </repeat>
            <output name="segmentationimages" file="centroids_proc.pdf" compare="sim_size"/>
            <output name="mzfeatures" file="toplabels_proc.tabular"/>
            <output name="pixeloutput" file="classes_proc.tabular"/>
        </test>
    </tests>
    <help>
        <![CDATA[

@CARDINAL_DESCRIPTION@