Mercurial > repos > galaxyp > mass_spectrometry_imaging_segmentations

comparison segmentation_tool.xml @ 6:80b6b96a175c draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/msi_segmentation commit 37da74ed68228b16efbdbde776e7c38cc06eb5d5
author galaxyp
date Tue, 19 Jun 2018 18:08:36 -0400
parents cee9cf693709
children adfef12c7e31
comparison
equal deleted inserted replaced
5:cee9cf693709 6:80b6b96a175c
1 <tool id="mass_spectrometry_imaging_segmentations" name="MSI segmentation" version="1.10.0.1"> 1 <tool id="mass_spectrometry_imaging_segmentations" name="MSI segmentation" version="1.10.0.2">
2 <description>mass spectrometry imaging spatial clustering</description> 2 <description>mass spectrometry imaging spatial clustering</description>
3 <requirements> 3 <requirements>
4 <requirement type="package" version="1.10.0">bioconductor-cardinal</requirement> 4 <requirement type="package" version="1.10.0">bioconductor-cardinal</requirement>
5 <requirement type="package" version="2.2.1">r-gridextra</requirement> 5 <requirement type="package" version="2.2.1">r-gridextra</requirement>
6 <requirement type="package" version="0.20-35">r-lattice</requirement> 6 <requirement type="package" version="0.20-35">r-lattice</requirement>
35 library(lattice) 35 library(lattice)
36 36
37 ## Read MALDI Imaging dataset 37 ## Read MALDI Imaging dataset
38 38
39 #if $infile.ext == 'imzml' 39 #if $infile.ext == 'imzml'
40 msidata = readImzML('infile') 40 msidata <- readImzML('infile', mass.accuracy=$accuracy, units.accuracy = "$units")
41 #elif $infile.ext == 'analyze75' 41 #elif $infile.ext == 'analyze75'
42 msidata = readAnalyze('infile') 42 msidata = readAnalyze('infile')
43 #else 43 #else
44 load('infile.RData') 44 load('infile.RData')
45 #end if 45 #end if
46 46
47 ## create full matrix to make processed imzML files compatible with segmentation
48 iData(msidata) <- iData(msidata)[]
47 ###################################### file properties in numbers ############## 49 ###################################### file properties in numbers ##############
48 50
49 ## Number of features (m/z) 51 ## Number of features (m/z)
50 maxfeatures = length(features(msidata)) 52 maxfeatures = length(features(msidata))
51 ## Range m/z 53 ## Range m/z
103 } else { 105 } else {
104 peakpickinginfo=processinginfo@peakPicking 106 peakpickinginfo=processinginfo@peakPicking
105 } 107 }
106 108
107 properties = c("Number of m/z features", 109 properties = c("Number of m/z features",
108 "Range of m/z values [Da]", 110 "Range of m/z values",
109 "Number of pixels", 111 "Number of pixels",
110 "Range of x coordinates", 112 "Range of x coordinates",
111 "Range of y coordinates", 113 "Range of y coordinates",
112 "Range of intensities", 114 "Range of intensities",
113 "Median of intensities", 115 "Median of intensities",
155 grid.table(property_df, rows= NULL) 157 grid.table(property_df, rows= NULL)
156 158
157 if (npeaks > 0) 159 if (npeaks > 0)
158 { 160 {
159 161
160
161 ######################## II) segmentation tools ############################# 162 ######################## II) segmentation tools #############################
162 ############################################################################# 163 #############################################################################
163 #set $color_string = ','.join(['"%s"' % $color.feature_color for $color in $colours]) 164 #set $color_string = ','.join(['"%s"' % $color.feature_color for $color in $colours])
164 colourvector = c($color_string) 165 colourvector = c($color_string)
165 166
184 ##pca 185 ##pca
185 186
186 component_vector = character() 187 component_vector = character()
187 for (numberofcomponents in 1:$segm_cond.pca_ncomp) 188 for (numberofcomponents in 1:$segm_cond.pca_ncomp)
188 {component_vector[numberofcomponents]= paste0("PC", numberofcomponents)} 189 {component_vector[numberofcomponents]= paste0("PC", numberofcomponents)}
189 pca = PCA(msidata, ncomp=$segm_cond.pca_ncomp, column = component_vector, superpose = FALSE, 190 pca_result = PCA(msidata, ncomp=$segm_cond.pca_ncomp, column = component_vector, superpose = FALSE,
190 method = "$segm_cond.pca_method", scale = $segm_cond.pca_scale, layout = c(ncomp, 1)) 191 method = "$segm_cond.pca_method", scale = $segm_cond.pca_scale, layout = c(ncomp, 1))
191 192
192 print(image(pca, main="PCA image", lattice=lattice_input, strip = strip_input, col=colourvector)) 193 ### images in pdf file
193 print(plot(pca, main="PCA plot", lattice=lattice_input, col= colourvector, strip = strip_input)) 194 print(image(pca_result, main="PCA image", lattice=lattice_input, strip = strip_input, col=colourvector))
194 195 for (PCs in 1:$segm_cond.pca_ncomp){
195 pcaloadings = (pca@resultData\$ncomp\$loadings) ### loading for each m/z value 196 print(image(pca_result, column = c(paste0("PC",PCs)), superpose = FALSE, col.regions = risk.colors(100)))}
196 pcascores = (pca@resultData\$ncomp\$scores) ### scores for each pixel 197 ### plots in pdf file
198 print(plot(pca_result, main="PCA plot", lattice=lattice_input, col= colourvector, strip = strip_input))
199 for (PCs in 1:$segm_cond.pca_ncomp){
200 print(plot(pca_result, column = c(paste0("PC",PCs)), superpose = FALSE))}
201
202
203 ### values in tabular files
204 pcaloadings = (pca_result@resultData\$ncomp\$loadings) ### loading for each m/z value
205 pcascores = (pca_result@resultData\$ncomp\$scores) ### scores for each pixel
197 206
198 write.table(pcaloadings, file="$mzfeatures", quote = FALSE, row.names = TRUE, col.names=NA, sep = "\t") 207 write.table(pcaloadings, file="$mzfeatures", quote = FALSE, row.names = TRUE, col.names=NA, sep = "\t")
199 write.table(pcascores, file="$pixeloutput", quote = FALSE, row.names = TRUE, col.names=NA, sep = "\t") 208 write.table(pcascores, file="$pixeloutput", quote = FALSE, row.names = TRUE, col.names=NA, sep = "\t")
200 209
201 ## optional output as .RData 210 ## optional output as .RData
202 #if $output_rdata: 211 #if $output_rdata:
203
204 ## save as (.RData) 212 ## save as (.RData)
205 save(pca, file="$segmentation_rdata") 213 save(pca, file="$segmentation_rdata")
206 214
207 #end if 215 #end if
208 216
239 ##centroids 247 ##centroids
240 248
241 ssc = spatialShrunkenCentroids(msidata, r=c($segm_cond.centroids_r), k=c($segm_cond.centroids_k), s=c($segm_cond.centroids_s), method="$segm_cond.centroids_method") 249 ssc = spatialShrunkenCentroids(msidata, r=c($segm_cond.centroids_r), k=c($segm_cond.centroids_k), s=c($segm_cond.centroids_s), method="$segm_cond.centroids_method")
242 print(image(ssc, key=TRUE, main="Spatial shrunken centroids", lattice=lattice_input, strip = strip_input, col= colourvector,layout=c(1,1))) 250 print(image(ssc, key=TRUE, main="Spatial shrunken centroids", lattice=lattice_input, strip = strip_input, col= colourvector,layout=c(1,1)))
243 print(plot(ssc, main="Spatial shrunken centroids plot", lattice=lattice_input, col= colourvector, strip = strip_input,layout=c($segm_cond.centroids_layout))) 251 print(plot(ssc, main="Spatial shrunken centroids plot", lattice=lattice_input, col= colourvector, strip = strip_input,layout=c($segm_cond.centroids_layout)))
252 print(plot(ssc, mode = "tstatistics",key = TRUE, lattice=lattice_input, layout = c($segm_cond.centroids_layout), main="t-statistics", col=colourvector))
253 print(plot(summary(ssc), main = "Number of segments",lattice=lattice_input))
244 254
245 ssc_classes = data.frame(matrix(NA, nrow = pixelcount, ncol = 0)) 255 ssc_classes = data.frame(matrix(NA, nrow = pixelcount, ncol = 0))
246 for (iteration in 1:length(ssc@resultData)){ 256 for (iteration in 1:length(ssc@resultData)){
247 ssc_class = ((ssc@resultData)[[iteration]]\$classes) 257 ssc_class = ((ssc@resultData)[[iteration]]\$classes)
248 ssc_classes = cbind(ssc_classes, ssc_class) } 258 ssc_classes = cbind(ssc_classes, ssc_class) }
249 colnames(ssc_classes) = names((ssc@resultData)) 259 colnames(ssc_classes) = names((ssc@resultData))
250 260
251 ssc_toplabels = topLabels(ssc, n=$segm_cond.centroids_toplabels) 261 ssc_toplabels = topLabels(ssc, n=$segm_cond.centroids_toplabels)
252 262
253 write.table(ssc_toplabels, file="$mzfeatures", quote = FALSE, row.names = TRUE, col.names=NA, sep = "\t") 263 write.table(ssc_toplabels, file="$mzfeatures", quote = FALSE, row.names = TRUE, col.names=NA, sep = "\t")
254 write.table(ssc_classes, file="$pixeloutput", quote = FALSE, row.names = TRUE, col.names=NA, sep = "\t") 264 write.table(ssc_classes, file="$pixeloutput", quote = FALSE, row.names = TRUE, col.names=NA, sep = "\t")
271 } 281 }
272 282
273 ]]></configfile> 283 ]]></configfile>
274 </configfiles> 284 </configfiles>
275 <inputs> 285 <inputs>
276 <param name="infile" type="data" format="imzml, rdata, analyze75" 286 <param name="infile" type="data" format="imzml,rdata,analyze75"
277 label="Inputfile as imzML, Analyze7.5 or Cardinal MSImageSet saved as RData" 287 label="Inputfile as imzML, Analyze7.5 or Cardinal MSImageSet saved as RData"
278 help="Upload composite datatype imzml (ibd+imzML) or analyze75 (hdr+img+t2m) or regular upload .RData (Cardinal MSImageSet)"/> 288 help="Upload composite datatype imzml (ibd+imzML) or analyze75 (hdr+img+t2m) or regular upload .RData (Cardinal MSImageSet)"/>
289 <param name="accuracy" type="float" value="50" label="Only for processed imzML files: enter 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"/>
290 <param name="units" display="radio" type="select" label="Only for processed imzML files: unit of the mass accuracy" help="either m/z or ppm">
291 <option value="mz" >mz</option>
292 <option value="ppm" selected="True" >ppm</option>
293 </param>
279 <conditional name="segm_cond"> 294 <conditional name="segm_cond">
280 <param name="segmentationtool" type="select" label="Select the tool for spatial clustering"> 295 <param name="segmentationtool" type="select" label="Select the tool for spatial clustering">
281 <option value="pca" selected="True">pca</option> 296 <option value="pca" selected="True">pca</option>
282 <option value="kmeans">k-means</option> 297 <option value="kmeans">k-means</option>
283 <option value="centroids">spatial shrunken centroids</option> 298 <option value="centroids">spatial shrunken centroids</option>
320 label="The initial number of clusters (k)" help="Multiple values are allowed (e.g. 1,2,3 or 2:5)"/> 335 label="The initial number of clusters (k)" help="Multiple values are allowed (e.g. 1,2,3 or 2:5)"/>
321 <param name="centroids_s" type="text" value="2" 336 <param name="centroids_s" type="text" value="2"
322 label="The sparsity thresholding parameter by which to shrink the t-statistics (s)" 337 label="The sparsity thresholding parameter by which to shrink the t-statistics (s)"
323 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)"/> 338 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)"/>
324 <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"> 339 <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">
325 <option value="gaussian" selected="True">gaussian</option> 340 <option value="gaussian">gaussian</option>
326 <option value="adaptive">adaptive</option> 341 <option value="adaptive" selected="True">adaptive</option>
327 </param> 342 </param>
328 <param name="centroids_toplabels" type="integer" value="500" 343 <param name="centroids_toplabels" type="integer" value="500"
329 label="Number of toplabels (m/z) which should be written in tabular output"/> 344 label="Number of toplabels (m/z) which should be written in tabular output"/>
330 <param name="centroids_layout" type="text" value="1,1" 345 <param name="centroids_layout" type="text" value="1,1"
331 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"/> 346 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"/>
404 </test> 419 </test>
405 <test> 420 <test>
406 <param name="infile" value="preprocessed.RData" ftype="rdata"/> 421 <param name="infile" value="preprocessed.RData" ftype="rdata"/>
407 <param name="segmentationtool" value="centroids"/> 422 <param name="segmentationtool" value="centroids"/>
408 <param name="centroids_r" value="1,2"/> 423 <param name="centroids_r" value="1,2"/>
409 <param name="centroids_k" value="5"/> 424 <param name="centroids_k" value="3"/>
410 <param name="centroids_toplabels" value="50"/> 425 <param name="centroids_toplabels" value="50"/>
411 <repeat name="colours"> 426 <repeat name="colours">
412 <param name="feature_color" value="#0000FF"/> 427 <param name="feature_color" value="#0000FF"/>
413 </repeat> 428 </repeat>
414 <repeat name="colours"> 429 <repeat name="colours">
442 - Cardinal "MSImageSet" data (with variable name "msidata", saved as .RData) 457 - Cardinal "MSImageSet" data (with variable name "msidata", saved as .RData)
443 458
444 Options: 459 Options:
445 460
446 - PCA: principal component analysis 461 - PCA: principal component analysis
447 - k-means: patially-aware k-means clustering 462 - k-means: spatially-aware k-means clustering
448 - spatial shrunken centroids: Allows the number of segments to decrease according to the data. This allows automatic selection of the number of clusters 463 - spatial shrunken centroids: Allows the number of segments to decrease according to the data. This allows automatic selection of the number of clusters
449 464
450 Output: 465 Output:
451 466
452 - Pdf with the heatmaps and plots for the segmentation 467 - Pdf with the heatmaps and plots for the segmentation