mass_spectrometry_imaging_segmentations: segmentation

comparison segmentation_tool.xml @ 4:aec189b0c64d draft

planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/msi_segmentation commit 1c808d60243bb1eeda0cd26cb4b0a17ab05de2c0

author	galaxyp
date	Mon, 28 May 2018 12:39:28 -0400
parents	830c6df59603
children	cee9cf693709

comparison

equal deleted inserted replaced

-:830c6df59603
+:aec189b0c64d
-<tool id="mass_spectrometry_imaging_segmentations" name="MSI segmentation" version="1.7.0.3">
+<tool id="mass_spectrometry_imaging_segmentations" name="MSI segmentation" version="1.10.0.0">
 <description>tool for spatial clustering</description>
 <requirements>
-<requirement type="package" version="1.7.0">bioconductor-cardinal</requirement>
+<requirement type="package" version="1.10.0">bioconductor-cardinal</requirement>
 <requirement type="package" version="2.2.1">r-gridextra</requirement>
-<requirement type="package" version="2.23-15">r-kernsmooth</requirement>
 <requirement type="package" version="0.20-35">r-lattice</requirement>
 </requirements>
 <command detect_errors="exit_code">
 <![CDATA[
 #if $infile.ext == 'imzml'
-cp '${infile.extra_files_path}/imzml' infile.imzML &&
+ln -s '${infile.extra_files_path}/imzml' infile.imzML &&
-cp '${infile.extra_files_path}/ibd' infile.ibd &&
+ln -s '${infile.extra_files_path}/ibd' infile.ibd &&
 #elif $infile.ext == 'analyze75'
-cp '${infile.extra_files_path}/hdr' infile.hdr &&
+ln -s '${infile.extra_files_path}/hdr' infile.hdr &&
-cp '${infile.extra_files_path}/img' infile.img &&
+ln -s '${infile.extra_files_path}/img' infile.img &&
-cp '${infile.extra_files_path}/t2m' infile.t2m &&
+ln -s '${infile.extra_files_path}/t2m' infile.t2m &&
 #else
 ln -s $infile infile.RData &&
 #end if
 cat '${MSI_segmentation}' &&
 echo ${MSI_segmentation} &&
 ################################# load libraries and read file #########################
 library(Cardinal)
 library(gridExtra)
-library(KernSmooth)
 library(lattice)
 ## Read MALDI Imaging dataset
 #if $infile.ext == 'imzml'
-msidata = readMSIData('infile.imzML')
+msidata = readImzML('infile')
 #elif $infile.ext == 'analyze75'
-msidata = readMSIData('infile.hdr')
+msidata = readAnalyze('infile')
 #else
 load('infile.RData')
 #end if
-###################################### file properties in numbers ######################
+###################################### file properties in numbers ##############
 ## Number of features (mz)
 maxfeatures = length(features(msidata))
 ## Range mz
 minmz = round(min(mz(msidata)), digits=2)
 paste0(centroidedinfo))
 property_df = data.frame(properties, values)
-######################################## PDF #############################################
+######################################## PDF ###################################
-##########################################################################################
+################################################################################
-##########################################################################################
+################################################################################
 pdf("segmentationpdf.pdf", fonts = "Times", pointsize = 12)
 plot(0,type='n',axes=FALSE,ann=FALSE)
 for (numberofcomponents in 1:$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=TRUE, strip = strip.custom(bg="lightgrey", par.strip.text=list(col="black", cex=.9)), col=colourvector, ylim=c(maximumy+2, 0)))
+print(image(pca, main="PCA image", lattice=TRUE, strip = strip.custom(bg="lightgrey", par.strip.text=list(col="black", cex=.9)), col=colourvector))
 print(plot(pca, main="PCA plot", lattice=TRUE, col= colourvector, strip = strip.custom(bg="lightgrey", par.strip.text=list(col="black", cex=.9))))
 pcaloadings = (pca@resultData\$ncomp\$loadings) ### loading for each mz value
 pcascores = (pca@resultData\$ncomp\$scores) ### scores for each pixel
 #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=TRUE, strip = strip.custom(bg="lightgrey", par.strip.text=list(col="black", cex=.9)), col= colourvector, ylim=c(maximumy+2, 0), layout=c(1,1)))
+print(image(skm, key=TRUE, main="K-means clustering", lattice=TRUE, strip = strip.custom(bg="lightgrey", par.strip.text=list(col="black", cex=.9)), col= colourvector, layout=c(1,1)))
 print(plot(skm, main="K-means plot", lattice=TRUE, col= colourvector, strip = strip.custom(bg="lightgrey", par.strip.text=list(col="black", cex=.9)), layout=c($segm_cond.kmeans_layout)))
 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="$segm_cond.centroids_method")
-print(image(ssc, key=TRUE, main="Spatial shrunken centroids", lattice=TRUE, strip = strip.custom(bg="lightgrey", par.strip.text=list(col="black", cex=.9)), col= colourvector,  ylim=c(maximumy+2, 0),layout=c(1,1)))
+print(image(ssc, key=TRUE, main="Spatial shrunken centroids", lattice=TRUE, strip = strip.custom(bg="lightgrey", par.strip.text=list(col="black", cex=.9)), col= colourvector,layout=c(1,1)))
 print(plot(ssc, main="Spatial shrunken centroids plot", lattice=TRUE, col= colourvector, strip = strip.custom(bg="lightgrey", par.strip.text=list(col="black", cex=.9)),layout=c($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)
 <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.">
+<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">shrunken centroids</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."/>
+label="The number of principal components to calculate"/>
 <param name="pca_method" type="select"
-label="The function used to calculate the singular value decomposition.">
+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="Shoud the data be scaled first?">
+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)"/>
+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)"/>
+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.">
+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 (masses) which should be written in tabular output"/>
 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)"/>
+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)"/>
+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)."
+label="The sparsity thresholding parameter by which to shrink the t-statistics (s)"
-help="As s increases, fewer mass features (m/z values) will be used in the spatial segmentation, and only the informative mass features will be retained. Multiple values are allowed (e.g. 1,2,3 or 2:5)."/>
+help="As s increases, fewer mass features (m/z values) will be used in the spatial segmentation, and only the informative mass 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.">
+<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 (masses) which should be written in tabular output"/>
 <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>
-<output name="segmentationimages" file="kmeans_imzml.pdf" compare="sim_size" delta="20000"/>
+<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"/>
 </test>
 <test>
-<param name="infile" value="preprocessing_results1.RData" ftype="rdata"/>
+<param name="infile" value="preprocessed.RData" ftype="rdata"/>
 <param name="segmentationtool" value="centroids"/>
-<param name="centroids_r" ftype="text" value="1,2"/>
+<param name="centroids_r" value="1,2"/>
-<param name="centroids_k" ftype="text" value="5"/>
+<param name="centroids_k" value="5"/>
-<param name="centroids_toplabels" ftype="integer" value="100"/>
+<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"/>
 <param name="feature_color" value="#FFD700"/>
 </repeat>
 <repeat name="colours">
 <param name="feature_color" value="#848484"/>
 </repeat>
-<output name="segmentationimages" file="centroids_imzml.pdf" compare="sim_size" delta="20000"/>
+<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[
-Spatially aware segmentation of mass-spectrometry imaging data by unsupervised clustering algorithms. Underlying structures can be identified with the following tools: pca, k-means clustering and spatial shrunken centroids. The spatialShrunkenCentroids method allows the number of segments to decrease according to the data. This allows automatic selection of the number
+Cardinal is an R package that implements statistical & computational tools for analyzing mass spectrometry imaging datasets. `More information on Cardinal <http://cardinalmsi.org//>`_
-of clusters.
+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 <http://ms-imaging.org/wp/introduction/>`_
+- 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)
-The output of this tool contains a pdf with plots from the segmentation tools.
+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
+- Tabular file with information on masses and pixels: loadings/scores (PCA), toplabels/clusters (k-means), toplabels/classes (spatial shrunken centroids)
 ]]>
 </help>
 <citations>
 <citation type="doi">10.1093/bioinformatics/btv146</citation>
 </citations>

Mercurial > repos > galaxyp > mass_spectrometry_imaging_segmentations

comparison segmentation_tool.xml @ 4:aec189b0c64d draft