comparison segmentation_tool.xml @ 8:4a62874c21a3 draft default tip

planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/msi_segmentation commit 5feaf3d0e0da8cef1241fecc1f4d6f81324594e6

7:adfef12c7e31

<tool id="mass_spectrometry_imaging_segmentations" name="MSI segmentation" version="1.10.0.3">
    <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>

        msidata <- readImzML('infile')
    #end if
#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)[] 

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

        #end if


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

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

        #elif str( $segm_cond.segmentationtool ) == 'kmeans':
            print('kmeans')
            ##k-means

            skm = spatialKMeans(msidata, r=c($segm_cond.kmeans_r), k=c($segm_cond.kmeans_k), method="$segm_cond.kmeans_method")
            print(image(skm, key=TRUE, main="K-means clustering", lattice=lattice_input, strip=strip_input, col= colourvector, layout=c(1,1)))

            print(plot(skm, main="K-means plot", lattice=lattice_input, col= colourvector, strip=strip_input, layout=c($segm_cond.kmeans_layout)))

            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) }
            colnames(skm_clusters) = names((skm@resultData)) 

            skm_toplabels = topLabels(skm, n=$segm_cond.kmeans_toplabels)
    
            write.table(skm_toplabels, file="$mzfeatures", quote = FALSE, row.names = TRUE, col.names=NA, sep = "\t")
            write.table(skm_clusters, file="$pixeloutput", quote = FALSE, row.names = TRUE, col.names=NA, sep = "\t")

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

            ## save as (.RData)

        #elif str( $segm_cond.segmentationtool ) == 'centroids':
            print('centroids')
            ##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))
            plot(summary(ssc), main = "Number of segments")

            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")

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

            ## save as (.RData)

                    </valid>
                  </sanitizer>
                </param>
            </repeat>
        <param name="output_rdata" type="boolean" display="radio" label="Results as .RData output"/>
    </inputs>
    <outputs>
        <data format="pdf" name="segmentationimages" from_work_dir="segmentationpdf.pdf" label = "$infile.display_name segmentation"/>
        <data format="tabular" name="mzfeatures" label="$infile.display_name m/z features"/>
        <data format="tabular" name="pixeloutput" label="$infile.display_name pixels"/>

8:4a62874c21a3

<tool id="mass_spectrometry_imaging_segmentations" name="MSI segmentation" version="1.10.0.4">
    <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>

        msidata <- readImzML('infile')
    #end if
#elif $infile.ext == 'analyze75'
    msidata = readAnalyze('infile')
#else
    loadRData <- function(fileName){
    load(fileName)
    get(ls()[ls() != "fileName"])
    }
    msidata = loadRData('infile.RData')
#end if


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

            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':
            print('pca')
            ##pca
            

            {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, ylim=c(maximumy+2, minimumy-2)))
            for (PCs in 1:$segm_cond.pca_ncomp){
                print(image(pca_result, column = c(paste0("PC",PCs)), lattice=lattice_input, superpose = FALSE, col.regions = risk.colors(100), ylim=c(maximumy+2, minimumy-2)))}
            ### plots in pdf file
            print(plot(pca_result, main="PCA plot", lattice=lattice_input, col= colourvector, strip = strip_input))
            for (PCs in 1:$segm_cond.pca_ncomp){
                print(plot(pca_result, column = c(paste0("PC",PCs)),superpose = FALSE))}

            ### values in tabular files
            pcaloadings = (pca_result@resultData\$ncomp\$loadings) ### loading for each m/z value
            pcaloadings2 = cbind(rownames(pcaloadings), pcaloadings)
            colnames(pcaloadings2) = c("mz", colnames(pcaloadings))
            pcascores = (pca_result@resultData\$ncomp\$scores) ### scores for each pixel
            pcascores2 = cbind(rownames(pcascores), pcascores)
            colnames(pcascores2) = c("pixel names", colnames(pcascores))

            write.table(pcaloadings2, file="$mzfeatures", quote = FALSE, row.names = FALSE, col.names=TRUE, sep = "\t")
            write.table(pcascores2, file="$pixeloutput", quote = FALSE, row.names = FALSE, col.names=TRUE, sep = "\t")

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

        #elif str( $segm_cond.segmentationtool ) == 'kmeans':
            print('kmeans')
            ##k-means

            skm = spatialKMeans(msidata, r=c($segm_cond.kmeans_r), k=c($segm_cond.kmeans_k), method="$segm_cond.kmeans_method")
            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($segm_cond.kmeans_layout)))

            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) }
            skm_clusters2 = cbind(rownames(skm_clusters), skm_clusters)
            colnames(skm_clusters2) = c("pixel names", 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
            #if $output_rdata:

            ## save as (.RData)

        #elif str( $segm_cond.segmentationtool ) == 'centroids':
            print('centroids')
            ##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), ylim=c(maximumy+2, minimumy-2)))
            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))
            plot(summary(ssc), main = "Number of segments")

            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) }
            ssc_classes2 = cbind(rownames(ssc_classes), ssc_classes)
            colnames(ssc_classes2) = c("pixel names", 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
            #if $output_rdata:

            ## save as (.RData)

                    </valid>
                  </sanitizer>
                </param>
            </repeat>
        <param name="output_rdata" type="boolean" display="radio" label="Results as .RData output"/>
        <param name="setseed" type="integer" value="1" label="set seed" help="use same value to reproduce previous results"/>
    </inputs>
    <outputs>
        <data format="pdf" name="segmentationimages" from_work_dir="segmentationpdf.pdf" label = "$infile.display_name segmentation"/>
        <data format="tabular" name="mzfeatures" label="$infile.display_name m/z features"/>
        <data format="tabular" name="pixeloutput" label="$infile.display_name pixels"/>