Mercurial > repos > galaxyp > msi_filtering

comparison msi_filtering.xml @ 5:3d5ac78fb2b0 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_filtering commit 8087490eb4dcaf4ead0f03eae4126780d21e5503
author galaxyp
date Fri, 06 Jul 2018 14:13:22 -0400
parents bf61fc662615
children bab12ded74a5
comparison
equal deleted inserted replaced
4:bf61fc662615 5:3d5ac78fb2b0
1 <tool id="mass_spectrometry_imaging_filtering" name="MSI filtering" version="1.10.0.2"> 1 <tool id="mass_spectrometry_imaging_filtering" name="MSI filtering" version="1.10.0.3">
2 <description>tool for filtering mass spectrometry imaging data</description> 2 <description>tool for filtering mass spectrometry imaging data</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 </requirements> 6 </requirements>
31 31
32 32
33 library(Cardinal) 33 library(Cardinal)
34 library(gridExtra) 34 library(gridExtra)
35 35
36
36 #if $infile.ext == 'imzml' 37 #if $infile.ext == 'imzml'
37 msidata <- readImzML('infile', mass.accuracy=$accuracy, units.accuracy = "$units") 38 #if str($processed_cond.processed_file) == "processed":
39 msidata <- readImzML('infile', mass.accuracy=$processed_cond.accuracy, units.accuracy = "$processed_cond.units")
40 #else
41 msidata <- readImzML('infile')
42 #end if
38 #elif $infile.ext == 'analyze75' 43 #elif $infile.ext == 'analyze75'
39 msidata = readAnalyze('infile') 44 msidata = readAnalyze('infile')
40 #else 45 #else
41 load('infile.RData') 46 load('infile.RData')
42 #end if 47 #end if
43 48
49
44 ########################### optional QC numbers ######################## 50 ########################### optional QC numbers ########################
45 51
46 #if $outputs.outputs_select == "quality_control": 52 if (sum(spectra(msidata)[]>0, na.rm=TRUE) > 0)
47 53 {
48 ## Number of features (m/z) 54 #if $outputs.outputs_select == "quality_control":
49 maxfeatures = length(features(msidata)) 55
50 ## Range m/z 56 ## Number of features (m/z)
51 minmz = round(min(mz(msidata)), digits=2) 57 maxfeatures = length(features(msidata))
52 maxmz = round(max(mz(msidata)), digits=2) 58 ## Range m/z
53 ## Number of spectra (pixels) 59 minmz = round(min(mz(msidata)), digits=2)
54 pixelcount = length(pixels(msidata)) 60 maxmz = round(max(mz(msidata)), digits=2)
55 ## Range x coordinates 61 ## Number of spectra (pixels)
56 minimumx = min(coord(msidata)[,1]) 62 pixelcount = length(pixels(msidata))
57 maximumx = max(coord(msidata)[,1]) 63 ## Range x coordinates
58 ## Range y coordinates 64 minimumx = min(coord(msidata)[,1])
59 minimumy = min(coord(msidata)[,2]) 65 maximumx = max(coord(msidata)[,1])
60 maximumy = max(coord(msidata)[,2]) 66 ## Range y coordinates
61 ## Number of intensities > 0 67 minimumy = min(coord(msidata)[,2])
62 npeaks= sum(spectra(msidata)[]>0) 68 maximumy = max(coord(msidata)[,2])
63 ## Spectra multiplied with m/z (potential number of peaks) 69 ## Number of intensities > 0
64 numpeaks = ncol(spectra(msidata)[])*nrow(spectra(msidata)[]) 70 npeaks= sum(spectra(msidata)[]>0, na.rm=TRUE)
65 ## Percentage of intensities > 0 71 ## Spectra multiplied with m/z (potential number of peaks)
66 percpeaks = round(npeaks/numpeaks*100, digits=2) 72 numpeaks = ncol(spectra(msidata)[])*nrow(spectra(msidata)[])
67 ## Number of empty TICs 73 ## Percentage of intensities > 0
68 TICs = colSums(spectra(msidata)[]) 74 percpeaks = round(npeaks/numpeaks*100, digits=2)
69 NumemptyTIC = sum(TICs == 0) 75 ## Number of empty TICs
70 ## median TIC 76 TICs = colSums(spectra(msidata)[], na.rm=TRUE)
71 medint = round(median(TICs), digits=2) 77 NumemptyTIC = sum(TICs == 0)
72 ## Store features for QC plot 78 ## median TIC
73 featuresinfile = mz(msidata) 79 medint = round(median(TICs), digits=2)
74 80 ## Store features for QC plot
75 #end if 81 featuresinfile = mz(msidata)
76 82
77 ###################################### Filtering of pixels ##################### 83 #end if
78 ################################################################################ 84
79 85 ###################################### Filtering of pixels #####################
80 #################### Pixels in the one column format "x=,y=" ##################### 86 ################################################################################
81 87
82 #if str($pixels_cond.pixel_filtering) == "single_column": 88 #################### Pixels in the one column format "x=,y=" #####################
83 print("single column") 89
84 90 #if str($pixels_cond.pixel_filtering) == "single_column":
85 input_list = read.delim("$pixels_cond.single_pixels", header = FALSE, stringsAsFactors = FALSE) 91 print("single column")
86 numberpixels = length(input_list[,$pixels_cond.pixel_column]) 92
87 valid_entries = input_list[,$pixels_cond.pixel_column] %in% names(pixels(msidata)) 93 input_list = read.delim("$pixels_cond.single_pixels", header = FALSE, stringsAsFactors = FALSE)
88 validpixels = sum(valid_entries) 94 numberpixels = length(input_list[,$pixels_cond.pixel_column])
89 95 valid_entries = input_list[,$pixels_cond.pixel_column] %in% names(pixels(msidata))
90 if (validpixels != 0){ 96 validpixels = sum(valid_entries)
91 pixelsofinterest = pixels(msidata)[names(pixels(msidata)) %in% input_list[valid_entries,$pixels_cond.pixel_column]] 97
92 msidata = msidata[,pixelsofinterest] 98 if (validpixels != 0){
93 }else{ 99 pixelsofinterest = pixels(msidata)[names(pixels(msidata)) %in% input_list[valid_entries,$pixels_cond.pixel_column]]
94 msidata = msidata[,0] 100 msidata = msidata[,pixelsofinterest]
95 validpixels=0} 101 }else{
96 102 msidata = msidata[,0]
97 ############ Pixels in two columns format: x and y in different columns ############# 103 validpixels=0}
98 104
99 #elif str($pixels_cond.pixel_filtering) == "two_columns": 105 ############ Pixels in two columns format: x and y in different columns #############
100 print("two columns") 106
101 107 #elif str($pixels_cond.pixel_filtering) == "two_columns":
102 input_list = read.delim("$pixels_cond.two_columns_pixel", header = FALSE, 108 print("two columns")
103 stringsAsFactors = FALSE) 109
104 numberpixels = length(input_list[,$pixels_cond.pixel_column_x]) 110 input_list = read.delim("$pixels_cond.two_columns_pixel", header = FALSE,
105 111 stringsAsFactors = FALSE)
106 inputpixel_x = input_list[,$pixels_cond.pixel_column_x] 112 numberpixels = length(input_list[,$pixels_cond.pixel_column_x])
107 inputpixel_y = input_list[,$pixels_cond.pixel_column_y] 113
108 inputpixels = cbind(inputpixel_x, inputpixel_y) 114 inputpixel_x = input_list[,$pixels_cond.pixel_column_x]
109 colnames(inputpixels) = c("x", "y") 115 inputpixel_y = input_list[,$pixels_cond.pixel_column_y]
110 valid_rows = merge(inputpixels, coord(msidata)[,1:2]) 116 inputpixels = cbind(inputpixel_x, inputpixel_y)
111 validpixels = nrow(valid_rows) 117 colnames(inputpixels) = c("x", "y")
112 118 valid_rows = merge(inputpixels, coord(msidata)[,1:2])
113 if (validpixels != 0){ 119 validpixels = nrow(valid_rows)
114 pixelvector = character() 120
115 for (pixel in 1:nrow(valid_rows)){ 121 if (validpixels != 0){
116 pixelvector[pixel] = paste0("x = ", valid_rows[pixel,1],", ", "y = ", valid_rows[pixel,2])} 122 pixelvector = character()
117 pixelsofinterest= pixels(msidata)[names(pixels(msidata)) %in% pixelvector] 123 for (pixel in 1:nrow(valid_rows)){
118 msidata = msidata[,pixelsofinterest] 124 pixelvector[pixel] = paste0("x = ", valid_rows[pixel,1],", ", "y = ", valid_rows[pixel,2])}
119 }else{ 125 pixelsofinterest= pixels(msidata)[names(pixels(msidata)) %in% pixelvector]
120 validpixels=0} 126 msidata = msidata[,pixelsofinterest]
121 127 }else{
122 ########### Pixels wihin x and y minima and maxima are kept ################### 128 validpixels=0}
123 129
124 #elif str($pixels_cond.pixel_filtering) == "pixel_range": 130 ########### Pixels wihin x and y minima and maxima are kept ###################
125 print("pixel range") 131
126 132 #elif str($pixels_cond.pixel_filtering) == "pixel_range":
127 numberpixels = "range" 133 print("pixel range")
128 validpixels = "range" 134
129 135 numberpixels = "range"
130 ## only filter pixels if at least one pixel will be left 136 validpixels = "range"
131 137
132 if (sum(coord(msidata)\$x <= $pixels_cond.max_x_range & coord(msidata)\$x >= $pixels_cond.min_x_range) > 0 & sum(coord(msidata)\$y <= $pixels_cond.max_y_range & coord(msidata)\$y >= $pixels_cond.min_y_range) > 0){ 138 ## only filter pixels if at least one pixel will be left
133 msidata = msidata[, coord(msidata)\$x <= $pixels_cond.max_x_range & coord(msidata)\$x >= $pixels_cond.min_x_range] 139
134 msidata = msidata[, coord(msidata)\$y <= $pixels_cond.max_y_range & coord(msidata)\$y >= $pixels_cond.min_y_range] 140 if (sum(coord(msidata)\$x <= $pixels_cond.max_x_range & coord(msidata)\$x >= $pixels_cond.min_x_range) > 0 & sum(coord(msidata)\$y <= $pixels_cond.max_y_range & coord(msidata)\$y >= $pixels_cond.min_y_range) > 0){
135 }else{ 141
136 msidata = msidata[,0] 142 msidata = msidata[, coord(msidata)\$x <= $pixels_cond.max_x_range & coord(msidata)\$x >= $pixels_cond.min_x_range]
137 print("no valid pixel found")} 143 msidata = msidata[, coord(msidata)\$y <= $pixels_cond.max_y_range & coord(msidata)\$y >= $pixels_cond.min_y_range]
138 144 }else{
139 #elif str($pixels_cond.pixel_filtering) == "none": 145 msidata = msidata[,0]
140 print("no pixel filtering") 146 print("no valid pixel found")}
141 147
142 numberpixels = 0 148 #elif str($pixels_cond.pixel_filtering) == "none":
143 validpixels = 0 149 print("no pixel filtering")
144 150
145 #end if 151 numberpixels = 0
146 152 validpixels = 0
153
154 #end if
155
156
157 }else{
158 print("Inputfile has no intensities > 0")
159
160 }
147 161
148 ###################################### filtering of features ###################### 162 ###################################### filtering of features ######################
149 ################################################################################## 163 ##################################################################################
150 164
151 ######################## Keep m/z from tabular file ######################### 165 ######################## Keep m/z from tabular file #########################
152 166
153 #if str($features_cond.features_filtering) == "features_list": 167 if (sum(spectra(msidata)[], na.rm=TRUE) > 0){
154 print("feature list") 168
155 169 #if str($features_cond.features_filtering) == "features_list":
156 input_features = read.delim("$inputfeatures", header = FALSE, stringsAsFactors = FALSE) 170 print("feature list")
157 startingrow = $features_cond.feature_header+1 171
158 extracted_features = input_features[startingrow:nrow(input_features),$features_cond.feature_column] 172 input_features = read.delim("$inputfeatures", header = FALSE, stringsAsFactors = FALSE)
159 numberfeatures = length(extracted_features) 173 startingrow = $features_cond.feature_header+1
160 174 extracted_features = input_features[startingrow:nrow(input_features),$features_cond.feature_column]
161 if (grepl("m/z = ", input_features[startingrow,$features_cond.feature_column])==FALSE){ 175 numberfeatures = length(extracted_features)
162 176
163 ### if input is in numeric format 177 if (grepl("m/z = ", input_features[startingrow,$features_cond.feature_column])==FALSE){
164 if (class(extracted_features) == "numeric"){ 178
165 ### max digits given in the input file will be used to match m/z 179 ### if input is in numeric format
166 max_digits = max(nchar(matrix(unlist(strsplit(as.character(extracted_features), "\\.")), ncol=2, byrow=TRUE)[,2])) 180 if (class(extracted_features) == "numeric"){
167 validfeatures = extracted_features %in% round(mz(msidata),max_digits) 181 ### max digits given in the input file will be used to match m/z
168 featuresofinterest = features(msidata)[round(mz(msidata), digits = max_digits) %in% extracted_features[validfeatures]] 182 max_digits = max(nchar(matrix(unlist(strsplit(as.character(extracted_features), "\\.")), ncol=2, byrow=TRUE)[,2]))
169 validmz = length(unique(featuresofinterest)) 183 validfeatures = extracted_features %in% round(mz(msidata),max_digits)
184 featuresofinterest = features(msidata)[round(mz(msidata), digits = max_digits) %in% extracted_features[validfeatures]]
185 validmz = length(unique(featuresofinterest))
186 }else{
187 validmz = 0
188 featuresofinterest = 0}
189
190 ### if input is already in character format (m/z = 800.01)
191
170 }else{ 192 }else{
171 validmz = 0 193 validfeatures = extracted_features %in% names(features(msidata))
172 featuresofinterest = 0} 194 featuresofinterest = features(msidata)[names(features(msidata)) %in% extracted_features[validfeatures]]
173 195 validmz = sum(validfeatures)}
174 ### if input is already in character format (m/z = 800.01) 196
175 197 ### filter msidata for valid features
176 }else{ 198
177 validfeatures = extracted_features %in% names(features(msidata)) 199 msidata = msidata[featuresofinterest,]
178 featuresofinterest = features(msidata)[names(features(msidata)) %in% extracted_features[validfeatures]] 200
179 validmz = sum(validfeatures)} 201 ############### features within a given range are kept #########################
180 202
181 ### filter msidata for valid features 203 #elif str($features_cond.features_filtering) == "features_range":
182 204 print("feature range")
183 msidata = msidata[featuresofinterest,] 205
184 206 numberfeatures = "range"
185 ############### features within a given range are kept ######################### 207 validmz = "range"
186 208
187 #elif str($features_cond.features_filtering) == "features_range": 209 if (sum(mz(msidata) >= $features_cond.min_mz & mz(msidata) <= $features_cond.max_mz)> 0){
188 print("feature range") 210 msidata = msidata[mz(msidata) >= $features_cond.min_mz & mz(msidata) <= $features_cond.max_mz,]
189 211 }else{
190 numberfeatures = "range" 212 msidata = msidata[0,]
191 validmz = "range" 213 print("no valid mz range")}
192 214
193 if (sum(mz(msidata) >= $features_cond.min_mz & mz(msidata) <= $features_cond.max_mz)> 0){ 215 ############### Remove m/z from tabular file #########################
194 msidata = msidata[mz(msidata) >= $features_cond.min_mz & mz(msidata) <= $features_cond.max_mz,] 216
195 }else{ 217 #elif str($features_cond.features_filtering) == "remove_features":
196 msidata = msidata[0,] 218 print("remove features")
197 print("no valid mz range")} 219
198 220 ### Tabular file contains mz either as numbers or in the format mz = 800.01
199 ############### Remove m/z from tabular file ######################### 221
200 222 input_features = read.delim("$inputfeatures_removal", header = FALSE, stringsAsFactors = FALSE)
201 #elif str($features_cond.features_filtering) == "remove_features": 223 startingrow = $features_cond.removal_header+1
202 print("remove features") 224 extracted_features = input_features[startingrow:nrow(input_features),$features_cond.removal_column]
203 225 numberfeatures = length(extracted_features)
204 ### Tabular file contains mz either as numbers or in the format mz = 800.01 226
205 227 if (grepl("m/z = ", input_features[startingrow,$features_cond.removal_column])==TRUE){
206 input_features = read.delim("$inputfeatures_removal", header = FALSE, stringsAsFactors = FALSE) 228
207 startingrow = $features_cond.removal_header+1 229 ### if input is mz = 800 character format
208 extracted_features = input_features[startingrow:nrow(input_features),$features_cond.removal_column] 230 print("input is in format mz = 400")
209 numberfeatures = length(extracted_features) 231 validfeatures = extracted_features %in% names(features(msidata))
210 232 validmz = sum(validfeatures)
211 if (grepl("m/z = ", input_features[startingrow,$features_cond.removal_column])==TRUE){ 233 filtered_features = features(msidata)[names(features(msidata)) %in% extracted_features[validfeatures]]
212 234 featuresofinterest = mz(msidata)[filtered_features]
213 ### if input is mz = 800 character format 235
214 print("input is in format mz = 400") 236 ### if input is numeric:
215 validfeatures = extracted_features %in% names(features(msidata)) 237 }else{
216 validmz = sum(validfeatures) 238 if (class(extracted_features) == "numeric"){
217 filtered_features = features(msidata)[names(features(msidata)) %in% extracted_features[validfeatures]] 239 print("input is numeric")
218 featuresofinterest = mz(msidata)[filtered_features] 240 featuresofinterest = extracted_features
219 241 validmz = sum(featuresofinterest <= max(mz(msidata))& featuresofinterest >= min(mz(msidata)))
220 ### if input is numeric: 242 }else{featuresofinterest = 0
221 }else{ 243 validmz = 0}
222 if (class(extracted_features) == "numeric"){ 244 }
223 print("input is numeric") 245
224 featuresofinterest = extracted_features 246 ### Here starts removal of features:
225 validmz = sum(featuresofinterest <= max(mz(msidata))& featuresofinterest >= min(mz(msidata))) 247
226 }else{featuresofinterest = 0 248 plusminus = $features_cond.removal_plusminus
227 validmz = 0} 249
228 } 250 mass_to_remove = numeric()
229 251 if (sum(featuresofinterest) > 0){
230 ### Here starts removal of features: 252 for (masses in featuresofinterest){
231 253 #if str($features_cond.units_removal) == "ppm":
232 plusminus = $features_cond.removal_plusminus 254 plusminus = masses * $features_cond.removal_plusminus/1000000
233 255 #end if
234 mass_to_remove = numeric() 256 current_mass = which(c(mz(msidata) <= masses + plusminus & mz(msidata) >= masses - plusminus))
235 if (sum(featuresofinterest) > 0){ 257 mass_to_remove = append(mass_to_remove, current_mass)}
236 for (masses in featuresofinterest){ 258 msidata= msidata[-mass_to_remove, ]
237 #if str($features_cond.units_removal) == "ppm": 259 }else{print("No features were removed as they were not fitting to m/z values and/or range")}
238 plusminus = masses * $features_cond.removal_plusminus/1000000 260
239 #end if 261
240 current_mass = which(c(mz(msidata) <= masses + plusminus & mz(msidata) >= masses - plusminus)) 262 #elif str($features_cond.features_filtering) == "none":
241 mass_to_remove = append(mass_to_remove, current_mass)} 263
242 msidata= msidata[-mass_to_remove, ] 264 print("no feature filtering")
243 }else{print("No features were removed as they were not fitting to m/z values and/or range")} 265 validmz = 0
244 266 numberfeatures = 0
245 267
246 #elif str($features_cond.features_filtering) == "none": 268 #end if
247 269
248 print("no feature filtering") 270 ## save msidata as Rfile
249 validmz = 0 271 save(msidata, file="$msidata_filtered")
250 numberfeatures = 0 272
251 273 #################### optional QC numbers #######################
252 #end if 274
253 275 #if $outputs.outputs_select == "quality_control":
254 ## save msidata as Rfile 276
255 save(msidata, file="$msidata_filtered") 277 ## Number of features (m/z)
256 278 maxfeatures2 = length(features(msidata))
257 #################### optional QC numbers ####################### 279 ## Range m/z
258 280 minmz2 = round(min(mz(msidata)), digits=2)
259 #if $outputs.outputs_select == "quality_control": 281 maxmz2 = round(max(mz(msidata)), digits=2)
260 282 ## Number of spectra (pixels)
261 ## Number of features (m/z) 283 pixelcount2 = length(pixels(msidata))
262 maxfeatures2 = length(features(msidata)) 284 ## Range x coordinates
263 ## Range m/z 285 minimumx2 = min(coord(msidata)[,1])
264 minmz2 = round(min(mz(msidata)), digits=2) 286 maximumx2 = max(coord(msidata)[,1])
265 maxmz2 = round(max(mz(msidata)), digits=2) 287 ## Range y coordinates
266 ## Number of spectra (pixels) 288 minimumy2 = min(coord(msidata)[,2])
267 pixelcount2 = length(pixels(msidata)) 289 maximumy2 = max(coord(msidata)[,2])
268 ## Range x coordinates 290 ## Number of intensities > 0
269 minimumx2 = min(coord(msidata)[,1]) 291 npeaks2= sum(spectra(msidata)[]>0, na.rm=TRUE)
270 maximumx2 = max(coord(msidata)[,1]) 292 ## Spectra multiplied with m/z (potential number of peaks)
271 ## Range y coordinates 293 numpeaks2 = ncol(spectra(msidata)[])*nrow(spectra(msidata)[])
272 minimumy2 = min(coord(msidata)[,2]) 294 ## Percentage of intensities > 0
273 maximumy2 = max(coord(msidata)[,2]) 295 percpeaks2 = round(npeaks2/numpeaks2*100, digits=2)
274 ## Number of intensities > 0 296 ## Number of empty TICs
275 npeaks2= sum(spectra(msidata)[]>0) 297 TICs2 = colSums(spectra(msidata)[], na.rm=TRUE)
276 ## Spectra multiplied with m/z (potential number of peaks) 298 NumemptyTIC2 = sum(TICs2 == 0)
277 numpeaks2 = ncol(spectra(msidata)[])*nrow(spectra(msidata)[]) 299 ## median TIC
278 ## Percentage of intensities > 0 300 medint2 = round(median(TICs2), digits=2)
279 percpeaks2 = round(npeaks2/numpeaks2*100, digits=2) 301
280 ## Number of empty TICs 302 properties = c("Number of m/z features",
281 TICs2 = colSums(spectra(msidata)[]) 303 "Range of m/z values",
282 NumemptyTIC2 = sum(TICs2 == 0) 304 "Number of pixels",
283 ## median TIC 305 "Range of x coordinates",
284 medint2 = round(median(TICs2), digits=2) 306 "Range of y coordinates",
285 307 "Intensities > 0",
286 properties = c("Number of m/z features", 308 "Median TIC per pixel",
287 "Range of m/z values", 309 "Number of zero TICs",
288 "Number of pixels", 310 "pixel overview",
289 "Range of x coordinates", 311 "feature overview")
290 "Range of y coordinates", 312
291 "Intensities > 0", 313 before = c(paste0(maxfeatures),
292 "Median TIC per pixel", 314 paste0(minmz, " - ", maxmz),
293 "Number of zero TICs", 315 paste0(pixelcount),
294 "pixel overview", 316 paste0(minimumx, " - ", maximumx),
295 "feature overview") 317 paste0(minimumy, " - ", maximumy),
296 318 paste0(percpeaks, " %"),
297 before = c(paste0(maxfeatures), 319 paste0(medint),
298 paste0(minmz, " - ", maxmz), 320 paste0(NumemptyTIC),
299 paste0(pixelcount), 321 paste0("input pixels: ", numberpixels),
300 paste0(minimumx, " - ", maximumx), 322 paste0("input mz: ", numberfeatures))
301 paste0(minimumy, " - ", maximumy), 323
302 paste0(percpeaks, " %"), 324 filtered = c(paste0(maxfeatures2),
303 paste0(medint), 325 paste0(minmz2, " - ", maxmz2),
304 paste0(NumemptyTIC), 326 paste0(pixelcount2),
305 paste0("input pixels: ", numberpixels), 327 paste0(minimumx2, " - ", maximumx2),
306 paste0("input mz: ", numberfeatures)) 328 paste0(minimumy2, " - ", maximumy2),
307 329 paste0(percpeaks2, " %"),
308 filtered = c(paste0(maxfeatures2), 330 paste0(medint2),
309 paste0(minmz2, " - ", maxmz2), 331 paste0(NumemptyTIC2),
310 paste0(pixelcount2), 332 paste0("valid pixels: ", validpixels),
311 paste0(minimumx2, " - ", maximumx2), 333 paste0("valid mz: ", validmz))
312 paste0(minimumy2, " - ", maximumy2), 334
313 paste0(percpeaks2, " %"), 335 property_df = data.frame(properties, before, filtered)
314 paste0(medint2), 336
315 paste0(NumemptyTIC2), 337 ############################### optional PDF QC ################################
316 paste0("valid pixels: ", validpixels), 338
317 paste0("valid mz: ", validmz)) 339 pdf("filtertool_QC.pdf", fonts = "Times", pointsize = 12)
318 340 plot(0,type='n',axes=FALSE,ann=FALSE)
319 property_df = data.frame(properties, before, filtered) 341 title(main=paste0("Qualitycontrol of filtering tool for file: \n\n", "$infile.display_name"))
320 342 grid.table(property_df, rows= NULL)
321 ############################### optional PDF QC ################################ 343
322 344 ### heatmap image as visual pixel control
323 pdf("filtertool_QC.pdf", fonts = "Times", pointsize = 12) 345 if (length(features(msidata))> 0 & length(pixels(msidata)) > 0){
324 plot(0,type='n',axes=FALSE,ann=FALSE) 346 image(msidata, mz=$outputs.inputmz, plusminus = $outputs.plusminus_dalton, contrast.enhance = "none",
325 title(main=paste0("Qualitycontrol of filtering tool for file: \n\n", "$infile.display_name")) 347 main= paste0($outputs.inputmz," ± ", $outputs.plusminus_dalton, " Da"), ylim = c(maximumy2+0.2*maximumy2,minimumy2-0.2*minimumy2))
326 grid.table(property_df, rows= NULL) 348
327 349 ### control features which are removed
328 ### heatmap image as visual pixel control 350 hist(mz(msidata), xlab="m/z", main="Kept m/z values")
329 if (length(features(msidata))> 0 & length(pixels(msidata)) > 0){ 351 #if str($features_cond.features_filtering) == "none":
330 image(msidata, mz=$outputs.inputmz, plusminus = $outputs.plusminus_dalton, contrast.enhance = "none", 352 print("no difference histogram as no m/z filtering took place")
331 main= paste0($outputs.inputmz," ± ", $outputs.plusminus_dalton, " Da"), ylim = c(maximumy2+0.2*maximumy2,minimumy2-0.2*minimumy2)) 353 #else:
332 354
333 ### control features which are removed 355 if (isTRUE(all.equal(featuresinfile, mz(msidata)))){
334 hist(mz(msidata), xlab="m/z", main="Kept m/z values") 356 print("No difference in m/z values before and after filtering, no histogram drawn")
335 #if str($features_cond.features_filtering) == "none": 357 }else{
336 print("no difference histogram as no m/z filtering took place") 358 hist(setdiff(featuresinfile, mz(msidata)), xlab="m/z", main="Removed m/z values")}
337 #else: 359 #end if
338 hist(setdiff(featuresinfile, mz(msidata)), xlab="m/z", main="Removed m/z values") 360 }else{
339 #end if 361 print("file has no features or pixels left")}
340 }else{ 362
341 print("file has no features or pixels left")} 363 dev.off()
342 364
343 dev.off() 365 #end if
344 366
345 #end if 367 ############################### optional intensity matrix ######################
346 368
347 ############################### optional intensity matrix ###################### 369 #if $output_matrix:
348 370
349 #if $output_matrix: 371 spectramatrix = spectra(msidata)[]
350 372 spectramatrix = cbind(mz(msidata),spectramatrix)
351 if (length(features(msidata))> 0 & length(pixels(msidata)) > 0){ 373 newmatrix = rbind(c("mz | spectra", names(pixels(msidata))), spectramatrix)
352 spectramatrix = spectra(msidata) 374 write.table(newmatrix, file="$matrixasoutput", quote = FALSE, row.names = FALSE, col.names=FALSE, sep = "\t")
353 rownames(spectramatrix) = mz(msidata) 375
354 newmatrix = rbind(pixels(msidata), spectramatrix) 376 #end if
355 write.table(newmatrix[2:nrow(newmatrix),], file="$matrixasoutput", quote = FALSE, row.names = TRUE, col.names=NA, sep = "\t") 377
356 }else{ 378 }else{
357 print("file has no features or pixels left")} 379 print("Inputfile or file filtered for pixels has no intensities > 0")
358 380 }
359 #end if
360
361
362 ]]></configfile> 381 ]]></configfile>
363 </configfiles> 382 </configfiles>
364 <inputs> 383 <inputs>
365 <param name="infile" type="data" format="imzml,rdata,analyze75" 384 <param name="infile" type="data" format="imzml,rdata,analyze75"
366 label="Inputfile as imzML, Analyze7.5 or Cardinal MSImageSet saved as RData" 385 label="Inputfile as imzML, Analyze7.5 or Cardinal MSImageSet saved as RData"
367 help="Upload composite datatype imzML (ibd+imzML) or analyze75 (hdr+img+t2m) or regular upload .RData (Cardinal MSImageSet)"/> 386 help="Upload composite datatype imzML (ibd+imzML) or analyze75 (hdr+img+t2m) or regular upload .RData (Cardinal MSImageSet)"/>
368 <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"/> 387 <conditional name="processed_cond">
369 <param name="units" display="radio" type="select" label="Only for processed imzML files: unit of the mass accuracy" help="either m/z or ppm"> 388 <param name="processed_file" type="select" label="Is the input file a processed imzML file ">
370 <option value="mz" >mz</option> 389 <option value="no_processed" selected="True">not a processed imzML</option>
371 <option value="ppm" selected="True" >ppm</option> 390 <option value="processed">processed imzML</option>
372 </param> 391 </param>
392 <when value="no_processed"/>
393 <when value="processed">
394 <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"/>
395 <param name="units" display="radio" type="select" label="Unit of the mass accuracy" help="either m/z or ppm">
396 <option value="mz" >mz</option>
397 <option value="ppm" selected="True" >ppm</option>
398 </param>
399 </when>
400 </conditional>
373 <conditional name="pixels_cond"> 401 <conditional name="pixels_cond">
374 <param name="pixel_filtering" type="select" label="Select pixel filtering option"> 402 <param name="pixel_filtering" type="select" label="Select pixel filtering option">
375 <option value="none" selected="True">none</option> 403 <option value="none" selected="True">none</option>
376 <option value="single_column">tabular file with single column (x = 1, y = 1)</option> 404 <option value="single_column">tabular file with single column (x = 1, y = 1)</option>
377 <option value="two_columns">tabular file with separate columns for x and y values</option> 405 <option value="two_columns">tabular file with separate columns for x and y values</option>
603 631
604 Options: 632 Options:
605 633
606 - pixel filtering: can use a tabular file containing x and y coordinates or by defining a range for x and y by hand 634 - pixel filtering: can use a tabular file containing x and y coordinates or by defining a range for x and y by hand
607 - m/z feature filtering: can use a tabular file containing m/z of interest or by defining a range for the m/z values (! numeric input will be rounded to 2 digits before matching to m/z!) 635 - m/z feature filtering: can use a tabular file containing m/z of interest or by defining a range for the m/z values (! numeric input will be rounded to 2 digits before matching to m/z!)
608 - m/z feature removing: infering m/z such as matrix contaminants can be removed by specifying their m/z in a tabular file and optionally set a window (window in ppm or Da in which peaks should be removed) 636 - m/z feature removing: infering m/z such as matrix contaminants can be removed by specifying their m/z in a tabular file and optionally set a window (window in ppm or m/z in which peaks should be removed)
609 637
610 638
611 Output: 639 Output:
612 640
613 - imzML file filtered for pixels and/or m/z 641 - imzML file filtered for pixels and/or m/z