annotate 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

<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>
    </requirements>
    <command detect_errors="exit_code">
    <![CDATA[

        #if $infile.ext == 'imzml'
            ln -s '${infile.extra_files_path}/imzml' infile.imzML &&
            ln -s '${infile.extra_files_path}/ibd' infile.ibd &&
        #elif $infile.ext == 'analyze75'
            ln -s '${infile.extra_files_path}/hdr' infile.hdr &&
            ln -s '${infile.extra_files_path}/img' infile.img &&
            ln -s '${infile.extra_files_path}/t2m' infile.t2m &&
        #else
            ln -s $infile infile.RData &&
        #end if
        cat '${MSI_segmentation}' &&
        echo ${MSI_segmentation} &&
        Rscript '${MSI_segmentation}'

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


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

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

## Read MALDI Imaging dataset

#if $infile.ext == 'imzml'
    #if str($processed_cond.processed_file) == "processed":
        msidata <- readImzML('infile', mass.accuracy=$processed_cond.accuracy, units.accuracy = "$processed_cond.units")
    #else
        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)[] 
###################################### file properties in numbers ##############

## Number of features (m/z)
maxfeatures = length(features(msidata))
## Range m/z
minmz = round(min(mz(msidata)), digits=2)
maxmz = round(max(mz(msidata)), digits=2)
## Number of spectra (pixels)
pixelcount = length(pixels(msidata))
## Range x coordinates
minimumx = min(coord(msidata)[,1])
maximumx = max(coord(msidata)[,1])
## Range y coordinates
minimumy = min(coord(msidata)[,2])
maximumy = max(coord(msidata)[,2])
## Range of intensities
minint = round(min(spectra(msidata)[],na.rm=TRUE), digits=2)
maxint = round(max(spectra(msidata)[],na.rm=TRUE), digits=2)
medint = round(median(spectra(msidata)[]), digits=2)
## Number of intensities > 0
npeaks= sum(spectra(msidata)[]>0, na.rm=TRUE)
## Spectra multiplied with m/z (potential number of peaks)
numpeaks = ncol(spectra(msidata)[])*nrow(spectra(msidata)[])
## Percentage of intensities > 0
percpeaks = round(npeaks/numpeaks*100, digits=2)
## Number of empty TICs
TICs = colSums(spectra(msidata)[], na.rm=TRUE) 
NumemptyTIC = sum(TICs == 0)



## Processing informations
processinginfo = processingData(msidata)
centroidedinfo = processinginfo@centroided # TRUE or FALSE

## if TRUE write processinginfo if FALSE write FALSE

## normalization
if (length(processinginfo@normalization) == 0) {
  normalizationinfo='FALSE'
} else {
  normalizationinfo=processinginfo@normalization
}
## smoothing
if (length(processinginfo@smoothing) == 0) {
  smoothinginfo='FALSE'
} else {
  smoothinginfo=processinginfo@smoothing
}
## baseline
if (length(processinginfo@baselineReduction) == 0) {
  baselinereductioninfo='FALSE'
} else {
  baselinereductioninfo=processinginfo@baselineReduction
}
## peak picking
if (length(processinginfo@peakPicking) == 0) {
  peakpickinginfo='FALSE'
} 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",
               "Intensities > 0",
               "Number of zero TICs",
               "Preprocessing", 
               "Normalization", 
               "Smoothing",
               "Baseline reduction",
               "Peak picking",
               "Centroided")

values = c(paste0(maxfeatures), 
           paste0(minmz, " - ", maxmz), 
           paste0(pixelcount), 
           paste0(minimumx, " - ", maximumx),  
           paste0(minimumy, " - ", maximumy), 
           paste0(minint, " - ", maxint), 
           paste0(medint),
           paste0(percpeaks, " %"), 
           paste0(NumemptyTIC), 
           paste0(" "),
           paste0(normalizationinfo),
           paste0(smoothinginfo),
           paste0(baselinereductioninfo),
           paste0(peakpickinginfo),
           paste0(centroidedinfo))

property_df = data.frame(properties, values)


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


pdf("segmentationpdf.pdf", fonts = "Times", pointsize = 12)
plot(0,type='n',axes=FALSE,ann=FALSE)

title(main=paste0("Spatial segmentation for file: \n\n", "$infile.display_name"))


############################# 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 $colours])
        colourvector = c($color_string)

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

            strip_input = TRUE
            lattice_input = FALSE

        #elif str($image_cond.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':
            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(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")

            #end if

        #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)
            save(skm, file="$segmentation_rdata")

            #end if

        #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)
            save(ssc, file="$segmentation_rdata")

            #end if

        #end if

    dev.off()

}else{
    print("Inputfile has no intensities > 0")
    dev.off()
}

    ]]></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="processed_cond">
            <param name="processed_file" type="select" label="Is the input file a processed imzML file ">
                <option value="no_processed" selected="True">not a processed imzML</option>
                <option value="processed">processed imzML</option>
            </param>
            <when value="no_processed"/>
            <when value="processed">
                <param name="accuracy" type="float" value="50" label="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="Unit of the mass accuracy" help="either m/z or ppm">
                    <option value="mz" >mz</option>
                    <option value="ppm" selected="True" >ppm</option>
                </param>
            </when>
        </conditional>
            <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>
                </param>
                <when value="pca">
                    <param name="pca_ncomp" type="integer" value="2"
                           label="The number of principal components to calculate"/>
                    <param name="pca_method" type="select" 
                           label="The function used to calculate the singular value decomposition">
                        <option value="irlba" selected="True">irlba</option>
                        <option value="svd">svd</option>
                    </param>
                    <param name="pca_scale" type="select" display="radio" optional="False"
                           label="Scaling of data before analysis">
                        <option value="TRUE">yes</option>
                        <option value="FALSE" selected="True">no</option>
                </param>
                </when>

                <when value="kmeans">
                    <param name="kmeans_r" type="text" value="2"
                           label="The spatial neighborhood radius of nearby pixels to consider (r)" help="Multiple values are allowed (e.g. 1,2,3 or 2:5)"/>
                    <param name="kmeans_k" type="text" value="3"
                           label="The number of clusters (k)" help="Multiple values are allowed (e.g. 1,2,3 or 2:5)"/>
                    <param name="kmeans_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) clustering, and 'adaptive' refers to spatially-aware structurally-adaptive (SASA) clustering">
                        <option value="gaussian">gaussian</option>
                        <option value="adaptive" selected="True">adaptive</option>
                </param>
                <param name="kmeans_toplabels" type="integer" value="500"
                       label="Number of toplabels (m/z) which should be written in tabular output"/>
                <param name="kmeans_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"/>
                 </when>

                <when value="centroids">
                    <param name="centroids_r" type="text" value="2"
                           label="The spatial neighborhood radius of nearby pixels to consider (r)" help="Multiple values are allowed (e.g. 1,2,3 or 2:5)"/>
                    <param name="centroids_k" type="text" value="5"
                           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"/>
                </when>
            </conditional>
            <conditional name="image_cond">
                <param name="image_type" type="select" label="Select the image type">
                    <option value="standard_image" selected="True">standard</option>
                    <option value="lattice_image">lattice</option>
                </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>
                </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="$infile.display_name pixels"/>
        <data format="rdata" name="segmentation_rdata" label="$infile.display_name segmentation">
            <filter>output_rdata</filter>
        </data>
    </outputs>
    <tests>
        <test>
            <param name="infile" value="" ftype="imzml">
                <composite_data value="Example_Continuous.imzML"/>
                <composite_data value="Example_Continuous.ibd"/>
            </param>
            <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" delta="20000"/>
            <output name="mzfeatures" file="loadings_pca.tabular" compare="sim_size"/>
            <output name="pixeloutput" file="scores_pca.tabular" compare="sim_size"/>
        </test>
        <test>
            <param name="infile" value="" ftype="analyze75">
                <composite_data value="Analyze75.hdr" />
                <composite_data value="Analyze75.img" />
                <composite_data value="Analyze75.t2m" />
            </param>
            <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="#ff00ff"/>
            </repeat>
            <repeat name="colours">
                <param name="feature_color" value="#0000FF"/>
            </repeat>
            <repeat name="colours">
                <param name="feature_color" value="#00C957"/>
            </repeat>
            <param name="output_rdata" value="True"/>
            <output name="segmentationimages" file="kmeans_analyze.pdf" compare="sim_size" delta="20000"/>
            <output name="mzfeatures" file="toplabels_skm.tabular" compare="sim_size"/>
            <output name="pixeloutput" file="cluster_skm.tabular" compare="sim_size"/>
            <output name="pixeloutput" file="cluster_skm.tabular" compare="sim_size"/>
            <output name="segmentation_rdata" file="cluster_skm.RData" compare="sim_size"/>
        </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">
                <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" delta="20000"/>
            <output name="mzfeatures" file="toplabels_ssc.tabular" compare="sim_size"/>
            <output name="pixeloutput" file="classes_ssc.tabular" compare="sim_size"/>
        </test>
    </tests>
    <help>
        <![CDATA[

Cardinal is an R package that implements statistical & computational tools for analyzing mass spectrometry imaging datasets. `More information on Cardinal <http://cardinalmsi.org//>`_

This tool provides three different Cardinal functions for unsupervised clustering/spatial segmentation of mass spectrometry imaging data.

Input data: 3 types of input data can be used:

- imzml file (upload imzml and ibd file via the "composite" function) `Introduction to the imzml format <https://ms-imaging.org/wp/imzml/>`_
- Analyze7.5 (upload hdr, img and t2m file via the "composite" function)
- 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
- Tabular file with information on m/z and pixels: loadings/scores (PCA), toplabels/clusters (k-means), toplabels/classes (spatial shrunken centroids)
- Optional .RData file which contains the segmentation results and can be used for further exploration in R

        ]]>
    </help>
    <citations>
        <citation type="doi">10.1093/bioinformatics/btv146</citation>
    </citations>
</tool>