comparison segmentation.xml @ 2:4ba8fcfef86f draft

planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/cardinal commit f127be2141cf22e269c85282d226eb16fe14a9c1

1:bb63d8ef0379

<tool id="cardinal_segmentations" name="MSI segmentation" version="@VERSION@.1">
    <description>mass spectrometry imaging spatial clustering</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements">

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

@READING_MSIDATA@


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

@DATA_PROPERTIES@

######################################## PDF ###################################
################################################################################
################################################################################

############################# I) numbers ####################################
#############################################################################
grid.table(property_df, rows= NULL)

if (npeaks > 0)
{

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

            print('pca')
            ##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, 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(matrix(unlist(strsplit(rownames(pcaloadings), " = ")), ncol=2, byrow=TRUE)[,2], pcaloadings)
            colnames(pcaloadings2) = c("mz", colnames(pcaloadings))
            pcascores = (pca_result@resultData\$ncomp\$scores) ### scores for each pixel

            ## pixel names and coordinates
            ## to remove potential sample names and z dimension, split at comma and take only x and y 
            x_coords = unlist(lapply(strsplit(rownames(pcascores), ","), `[[`, 1))
            y_coords = unlist(lapply(strsplit(rownames(pcascores), ","), `[[`, 2))

        #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(1,1)))

            skm_clusters = data.frame(matrix(NA, nrow = pixelcount, ncol = 0))

        #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(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")

                </param>
                <when value="standard_image"/>
                <when value="lattice_image"/>
            </conditional>
            <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 columns should be the same as number of components">
                  <sanitizer>
                    <valid initial="string.letters,string.digits">
                      <add value="#" />
                    </valid>
                  </sanitizer>

            </repeat>
        <param name="output_rdata" type="boolean" 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 = "${tool.name} on ${on_string}"/>
        <data format="tabular" name="mzfeatures" label="${tool.name} on ${on_string}: features"/>
        <data format="tabular" name="pixeloutput" label="${tool.name} on ${on_string}: pixels"/>
        <data format="rdata" name="segmentation_rdata" label="${tool.name} on ${on_string}: results.RData">
            <filter>output_rdata</filter>
        </data>

            </repeat>
            <repeat name="colours">
                <param name="feature_color" value="#0000FF"/>
            </repeat>
            <output name="segmentationimages" file="pca_imzml.pdf" compare="sim_size"/>
            <output name="mzfeatures" file="loadings_pca.tabular"/>
            <output name="pixeloutput" file="scores_pca.tabular"/>
        </test>
        <test>
            <expand macro="infile_analyze75"/>
            <param name="segmentationtool" value="kmeans"/>

2:4ba8fcfef86f

<tool id="cardinal_segmentations" name="MSI segmentation" version="@VERSION@.2">
    <description>mass spectrometry imaging spatial clustering</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements">

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



@READING_MSIDATA_INRAM@

## to make sure that processed files work as well: 
iData(msidata) = iData(msidata)[]

## count and print number of NAs, all methods are not compatible with NAs
print(paste0("Number of NA in dataset: ", sum(is.na(spectra(msidata)[])), " - segmentation does not work with NA values"))

@DATA_PROPERTIES_INRAM@


######################################## PDF ###################################
################################################################################
################################################################################

############################# I) numbers ####################################
#############################################################################
grid.table(property_df, rows= NULL)

if (npeaks > 0 && sum(is.na(spectra(msidata)[]))==0)
{

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

            print('pca')
            ##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))

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

            ### table in pdf file
            plot(0,type='n',axes=FALSE,ann=FALSE)
            sd_table = as.data.frame(round(pca_result@resultData\$ncomp\$sdev, digits=2))
            colnames(sd_table) = "Standard deviation"
            PC_vector = character()
            for (PCs in 1:$segm_cond.pca_ncomp){
                PC_vector[[PCs]] = c(paste0("PC",PCs))}
            sd_table = cbind(PC_vector, sd_table)
            colnames(sd_table)[1] = "Principal components"
            grid.table(sd_table, rows=NULL)
            ### images in pdf file
            print(image(pca_result, main="PCA image", lattice=lattice_input, strip = strip_input, col=colourvector, ylim=c(maximumy+2, minimumy-2)))
            for (PCs in 1:$segm_cond.pca_ncomp){
                print(image(pca_result, column = c(paste0("PC",PCs)), lattice=lattice_input, 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 = formatC(pca_result@resultData\$ncomp\$loadings, format = "e", digits = 6)### loading for each m/z value
            pcaloadings2 = cbind(matrix(unlist(strsplit(rownames(pcaloadings), " = ")), ncol=2, byrow=TRUE)[,2], pcaloadings)
            colnames(pcaloadings2) = c("mz", colnames(pcaloadings))
            pcascores = round(pca_result@resultData\$ncomp\$scores, digits=6) ### scores for each pixel

            ## pixel names and coordinates
            ## to remove potential sample names and z dimension, split at comma and take only x and y 
            x_coords = unlist(lapply(strsplit(rownames(pcascores), ","), `[[`, 1))
            y_coords = unlist(lapply(strsplit(rownames(pcascores), ","), `[[`, 2))

        #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")

            ## 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))

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

                </param>
                <when value="standard_image"/>
                <when value="lattice_image"/>
            </conditional>
            <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">
                      <add value="#" />
                    </valid>
                  </sanitizer>

            </repeat>
        <param name="output_rdata" type="boolean" 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 = "${tool.name} on ${on_string}: results"/>
        <data format="tabular" name="mzfeatures" label="${tool.name} on ${on_string}: features"/>
        <data format="tabular" name="pixeloutput" label="${tool.name} on ${on_string}: pixels"/>
        <data format="rdata" name="segmentation_rdata" label="${tool.name} on ${on_string}: results.RData">
            <filter>output_rdata</filter>
        </data>

            </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"/>