Mercurial > repos > galaxyp > cardinal_preprocessing

comparison preprocessing.xml @ 3:0b6f4c09b6eb 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/cardinal commit 2c4a1a862900b4efbc30824cbcb798f835b168b2
author galaxyp
date Thu, 28 Feb 2019 09:19:20 -0500
parents f29109d0d353
children 58fb63423b0b
comparison
equal deleted inserted replaced
2:f29109d0d353 3:0b6f4c09b6eb
58 pixelcount = ncol(msidata) 58 pixelcount = ncol(msidata)
59 minmz = round(min(mz(msidata)), digits=2) 59 minmz = round(min(mz(msidata)), digits=2)
60 maxmz = round(max(mz(msidata)), digits=2) 60 maxmz = round(max(mz(msidata)), digits=2)
61 QC_numbers= data.frame(inputdata = c(minmz, maxmz,maxfeatures, pixelcount)) 61 QC_numbers= data.frame(inputdata = c(minmz, maxmz,maxfeatures, pixelcount))
62 vectorofactions = "inputdata" 62 vectorofactions = "inputdata"
63 plot(msidata, pixel = 1:pixelcount, main="Average spectrum of input file") 63 ## Choose random spectra for QC plots
64 random_spectra = sample(pixels(msidata), 4, replace=FALSE)
65 par(mfrow = c(2, 2), oma=c(0,0,2,0))
66 for (random_sample in 1:length(random_spectra)){
67 plot(msidata, pixel=random_spectra[random_sample], main=paste0("spectrum ", names(random_spectra)[random_sample]))}
68 title("Input spectra", outer=TRUE, line=0)
69
64 70
65 ############################### Preprocessing steps ########################### 71 ############################### Preprocessing steps ###########################
66 ############################################################################### 72 ###############################################################################
67 73
68 #for $method in $methods: 74 #for $method in $methods:
82 minmz = round(min(mz(msidata)), digits=2) 88 minmz = round(min(mz(msidata)), digits=2)
83 maxmz = round(max(mz(msidata)), digits=2) 89 maxmz = round(max(mz(msidata)), digits=2)
84 normalized = c(minmz, maxmz,maxfeatures, pixelcount) 90 normalized = c(minmz, maxmz,maxfeatures, pixelcount)
85 QC_numbers= cbind(QC_numbers, normalized) 91 QC_numbers= cbind(QC_numbers, normalized)
86 vectorofactions = append(vectorofactions, "normalized") 92 vectorofactions = append(vectorofactions, "normalized")
87 plot(msidata, pixel = 1:pixelcount, main="Average spectrum after normalization") 93 par(mfrow = c(2, 2), oma=c(0,0,2,0))
94 for (random_sample in 1:length(random_spectra)){
95 plot(msidata, pixel=random_spectra[random_sample], main=paste0("spectrum ", names(random_spectra)[random_sample]))}
96 title("Spectra after normalization", outer=TRUE, line=0)
88 97
89 ############################### Baseline reduction ########################### 98 ############################### Baseline reduction ###########################
90 99
91 #elif str( $method.methods_conditional.preprocessing_method ) == 'Baseline_reduction': 100 #elif str( $method.methods_conditional.preprocessing_method ) == 'Baseline_reduction':
92 print('Baseline_reduction') 101 print('Baseline_reduction')
101 minmz = round(min(mz(msidata)), digits=2) 110 minmz = round(min(mz(msidata)), digits=2)
102 maxmz = round(max(mz(msidata)), digits=2) 111 maxmz = round(max(mz(msidata)), digits=2)
103 baseline = c(minmz, maxmz,maxfeatures, pixelcount) 112 baseline = c(minmz, maxmz,maxfeatures, pixelcount)
104 QC_numbers= cbind(QC_numbers, baseline) 113 QC_numbers= cbind(QC_numbers, baseline)
105 vectorofactions = append(vectorofactions, "baseline red.") 114 vectorofactions = append(vectorofactions, "baseline red.")
106 plot(msidata, pixel = 1:pixelcount, main="Average spectrum after baseline reduction") 115 for (random_sample in 1:length(random_spectra)){
116 plot(msidata, pixel=random_spectra[random_sample], main=paste0("spectrum ", names(random_spectra)[random_sample]))}
117 title("Spectra after baseline reduction", outer=TRUE, line=0)
107 118
108 ############################### Smoothing ########################### 119 ############################### Smoothing ###########################
109 120
110 #elif str( $method.methods_conditional.preprocessing_method ) == 'Smoothing': 121 #elif str( $method.methods_conditional.preprocessing_method ) == 'Smoothing':
111 print('Smoothing') 122 print('Smoothing')
134 minmz = round(min(mz(msidata)), digits=2) 145 minmz = round(min(mz(msidata)), digits=2)
135 maxmz = round(max(mz(msidata)), digits=2) 146 maxmz = round(max(mz(msidata)), digits=2)
136 smoothed = c(minmz, maxmz,maxfeatures, pixelcount) 147 smoothed = c(minmz, maxmz,maxfeatures, pixelcount)
137 QC_numbers= cbind(QC_numbers, smoothed) 148 QC_numbers= cbind(QC_numbers, smoothed)
138 vectorofactions = append(vectorofactions, "smoothed") 149 vectorofactions = append(vectorofactions, "smoothed")
139 plot(msidata, pixel = 1:pixelcount, main="Average spectrum after smoothing") 150 for (random_sample in 1:length(random_spectra)){
151 plot(msidata, pixel=random_spectra[random_sample], main=paste0("spectrum ", names(random_spectra)[random_sample]))}
152 title("Spectra after smoothing", outer=TRUE, line=0)
140 153
141 ############################### Peak picking ########################### 154 ############################### Peak picking ###########################
142 155
143 #elif str( $method.methods_conditional.preprocessing_method) == 'Peak_picking': 156 #elif str( $method.methods_conditional.preprocessing_method) == 'Peak_picking':
144 print('Peak_picking') 157 print('Peak_picking')
168 minmz = round(min(mz(msidata)), digits=2) 181 minmz = round(min(mz(msidata)), digits=2)
169 maxmz = round(max(mz(msidata)), digits=2) 182 maxmz = round(max(mz(msidata)), digits=2)
170 picked = c(minmz, maxmz,maxfeatures, pixelcount) 183 picked = c(minmz, maxmz,maxfeatures, pixelcount)
171 QC_numbers= cbind(QC_numbers, picked) 184 QC_numbers= cbind(QC_numbers, picked)
172 vectorofactions = append(vectorofactions, "picked") 185 vectorofactions = append(vectorofactions, "picked")
173 plot(msidata, pixel = 1:pixelcount, main="Average spectrum after peak picking") 186 for (random_sample in 1:length(random_spectra)){
187 plot(msidata, pixel=random_spectra[random_sample], main=paste0("spectrum ", names(random_spectra)[random_sample]))}
188 title("Spectra after peak picking", outer=TRUE, line=0)
174 189
175 ############################### Peak alignment ########################### 190 ############################### Peak alignment ###########################
176 191
177 #elif str( $method.methods_conditional.preprocessing_method ) == 'Peak_alignment': 192 #elif str( $method.methods_conditional.preprocessing_method ) == 'Peak_alignment':
178 print('Peak_alignment') 193 print('Peak_alignment')
182 197
183 align_peak_reference = msidata 198 align_peak_reference = msidata
184 199
185 #elif str( $method.methods_conditional.align_ref_type.align_reference_datatype) == 'align_table': 200 #elif str( $method.methods_conditional.align_ref_type.align_reference_datatype) == 'align_table':
186 201
187 align_reference_table = read.delim("$method.methods_conditional.align_ref_type.mz_tabular", header = $method.methods_conditional.align_ref_type.align_mass_header, stringsAsFactors = FALSE) 202 align_reference_table = read.delim("$method.methods_conditional.align_ref_type.mz_tabular", header = $method.methods_conditional.align_ref_type.feature_header, stringsAsFactors = FALSE)
188 align_reference_column = align_reference_table[,$method.methods_conditional.align_ref_type.align_mass_column] 203 align_reference_column = align_reference_table[,$method.methods_conditional.align_ref_type.feature_column]
189 align_peak_reference = align_reference_column[align_reference_column>=min(mz(msidata)) & align_reference_column<=max(mz(msidata))] 204 align_peak_reference = align_reference_column[align_reference_column>=min(mz(msidata)) & align_reference_column<=max(mz(msidata))]
190 if (length(align_peak_reference) == 0) 205 if (length(align_peak_reference) == 0)
191 {align_peak_reference = 0} 206 {align_peak_reference = 0}
192 207
193 #elif str( $method.methods_conditional.align_ref_type.align_reference_datatype) == 'align_msidata_ref': 208 #elif str( $method.methods_conditional.align_ref_type.align_reference_datatype) == 'align_msidata_ref':
215 minmz = round(min(mz(msidata)), digits=2) 230 minmz = round(min(mz(msidata)), digits=2)
216 maxmz = round(max(mz(msidata)), digits=2) 231 maxmz = round(max(mz(msidata)), digits=2)
217 aligned = c(minmz, maxmz,maxfeatures, pixelcount) 232 aligned = c(minmz, maxmz,maxfeatures, pixelcount)
218 QC_numbers= cbind(QC_numbers, aligned) 233 QC_numbers= cbind(QC_numbers, aligned)
219 vectorofactions = append(vectorofactions, "aligned") 234 vectorofactions = append(vectorofactions, "aligned")
220 plot(msidata, pixel = 1:pixelcount, main="Average spectrum after alignment") 235 for (random_sample in 1:length(random_spectra)){
236 plot(msidata, pixel=random_spectra[random_sample], main=paste0("spectrum ", names(random_spectra)[random_sample]))}
237 title("Spectra after alignment", outer=TRUE, line=0)
221 238
222 ############################### Peak filtering ########################### 239 ############################### Peak filtering ###########################
223 240
224 #elif str( $method.methods_conditional.preprocessing_method) == 'Peak_filtering': 241 #elif str( $method.methods_conditional.preprocessing_method) == 'Peak_filtering':
225 print('Peak_filtering') 242 print('Peak_filtering')
233 minmz = round(min(mz(msidata)), digits=2) 250 minmz = round(min(mz(msidata)), digits=2)
234 maxmz = round(max(mz(msidata)), digits=2) 251 maxmz = round(max(mz(msidata)), digits=2)
235 filtered = c(minmz, maxmz,maxfeatures, pixelcount) 252 filtered = c(minmz, maxmz,maxfeatures, pixelcount)
236 QC_numbers= cbind(QC_numbers, filtered) 253 QC_numbers= cbind(QC_numbers, filtered)
237 vectorofactions = append(vectorofactions, "filtered") 254 vectorofactions = append(vectorofactions, "filtered")
238 plot(msidata, pixel = 1:pixelcount, main="Average spectrum after filtering") 255 for (random_sample in 1:length(random_spectra)){
256 plot(msidata, pixel=random_spectra[random_sample], main=paste0("spectrum ", names(random_spectra)[random_sample]))}
257 title("Spectra after filtering", outer=TRUE, line=0)
239 258
240 ############################### Data reduction ########################### 259 ############################### Data reduction ###########################
241 260
242 #elif str( $method.methods_conditional.preprocessing_method) == 'Data_reduction': 261 #elif str( $method.methods_conditional.preprocessing_method) == 'Data_reduction':
243 print('Data_reduction') 262 print('Data_reduction')
264 #elif str( $method.methods_conditional.methods_for_reduction.reduction_method) == 'peaks': 283 #elif str( $method.methods_conditional.methods_for_reduction.reduction_method) == 'peaks':
265 print('peaks reduction') 284 print('peaks reduction')
266 285
267 #if str( $method.methods_conditional.methods_for_reduction.ref_type.reference_datatype) == 'table': 286 #if str( $method.methods_conditional.methods_for_reduction.ref_type.reference_datatype) == 'table':
268 287
269 reference_table = read.delim("$method.methods_conditional.methods_for_reduction.ref_type.mz_tabular", header = $method.methods_conditional.methods_for_reduction.ref_type.mass_header, stringsAsFactors = FALSE) 288 reference_table = read.delim("$method.methods_conditional.methods_for_reduction.ref_type.mz_tabular", header = $method.methods_conditional.methods_for_reduction.ref_type.feature_header, stringsAsFactors = FALSE)
270 reference_column = reference_table[,$method.methods_conditional.methods_for_reduction.ref_type.mass_column] 289 reference_column = reference_table[,$method.methods_conditional.methods_for_reduction.ref_type.feature_column]
271 peak_reference = reference_column[reference_column>min(mz(msidata)) & reference_column<max(mz(msidata))] 290 peak_reference = reference_column[reference_column>min(mz(msidata)) & reference_column<max(mz(msidata))]
272 291
273 #elif str( $method.methods_conditional.methods_for_reduction.ref_type.reference_datatype) == 'msidata_ref': 292 #elif str( $method.methods_conditional.methods_for_reduction.ref_type.reference_datatype) == 'msidata_ref':
274 293
275 peak_reference = loadRData('$method.methods_conditional.methods_for_reduction.ref_type.peaks_msidata') 294 peak_reference = loadRData('$method.methods_conditional.methods_for_reduction.ref_type.peaks_msidata')
285 minmz = round(min(mz(msidata)), digits=2) 304 minmz = round(min(mz(msidata)), digits=2)
286 maxmz = round(max(mz(msidata)), digits=2) 305 maxmz = round(max(mz(msidata)), digits=2)
287 reduced = c(minmz, maxmz,maxfeatures, pixelcount) 306 reduced = c(minmz, maxmz,maxfeatures, pixelcount)
288 QC_numbers= cbind(QC_numbers, reduced) 307 QC_numbers= cbind(QC_numbers, reduced)
289 vectorofactions = append(vectorofactions, "reduced") 308 vectorofactions = append(vectorofactions, "reduced")
290 plot(msidata, pixel = 1:pixelcount, main="Average spectrum after data reduction") 309 for (random_sample in 1:length(random_spectra)){
310 plot(msidata, pixel=random_spectra[random_sample], main=paste0("spectrum ", names(random_spectra)[random_sample]))}
311 title("Spectra after data reduction", outer=TRUE, line=0)
291 312
292 ############################### Transformation ########################### 313 ############################### Transformation ###########################
293 314
294 #elif str( $method.methods_conditional.preprocessing_method) == 'Transformation': 315 #elif str( $method.methods_conditional.preprocessing_method) == 'Transformation':
295 print('Transformation') 316 print('Transformation')
326 minmz = round(min(mz(msidata)), digits=2) 347 minmz = round(min(mz(msidata)), digits=2)
327 maxmz = round(max(mz(msidata)), digits=2) 348 maxmz = round(max(mz(msidata)), digits=2)
328 transformed = c(minmz, maxmz,maxfeatures, pixelcount) 349 transformed = c(minmz, maxmz,maxfeatures, pixelcount)
329 QC_numbers= cbind(QC_numbers, transformed) 350 QC_numbers= cbind(QC_numbers, transformed)
330 vectorofactions = append(vectorofactions, "transformed") 351 vectorofactions = append(vectorofactions, "transformed")
331 plot(msidata, pixel = 1:pixelcount, main="Average spectrum after transformation") 352 for (random_sample in 1:length(random_spectra)){
353 plot(msidata, pixel=random_spectra[random_sample], main=paste0("spectrum ", names(random_spectra)[random_sample]))}
354 title("Spectra after transformation", outer=TRUE, line=0)
332 355
333 #end if 356 #end if
334 #end for 357 #end for
335 358
336 ############# Outputs: RData, imzml and QC report ############# 359 ############# Outputs: RData, imzml and QC report #############
338 361
339 ## save msidata as imzML file, will only work if there is at least 1 m/z left 362 ## save msidata as imzML file, will only work if there is at least 1 m/z left
340 363
341 #if str($imzml_output) == "imzml_format": 364 #if str($imzml_output) == "imzml_format":
342 if (nrow(msidata) > 0){ 365 if (nrow(msidata) > 0){
366 ## make sure that coordinates are integers
367 coord(msidata)\$y = as.integer(coord(msidata)\$y)
368 coord(msidata)\$x = as.integer(coord(msidata)\$x)
343 writeImzML(msidata, "out")} 369 writeImzML(msidata, "out")}
344 #elif str($imzml_output) == "rdata_format": 370 #elif str($imzml_output) == "rdata_format":
345 ## save as (.RData) 371 ## save as (.RData)
346 iData(msidata) = iData(msidata)[] 372 iData(msidata) = iData(msidata)[]
347 save(msidata, file="$outfile_rdata") 373 save(msidata, file="$outfile_rdata")
441 <when value="diff"> 467 <when value="diff">
442 <param name="value_diffalignment" type="float" value="200" 468 <param name="value_diffalignment" type="float" value="200"
443 label="diff.max" help="Peaks that differ less than this value will be aligned together"/> 469 label="diff.max" help="Peaks that differ less than this value will be aligned together"/>
444 <param name="units_diffalignment" type="select" display="radio" optional="False" label="units"> 470 <param name="units_diffalignment" type="select" display="radio" optional="False" label="units">
445 <option value="ppm" selected="True">ppm</option> 471 <option value="ppm" selected="True">ppm</option>
446 <option value="Da">m/z</option> 472 <option value="mz">m/z</option>
447 </param> 473 </param>
448 </when> 474 </when>
449 <when value="DP"> 475 <when value="DP">
450 <param name="gap_DPalignment" type="float" value="0" 476 <param name="gap_DPalignment" type="float" value="0"
451 label="Gap" help="The gap penalty for the dynamic programming sequence alignment"/> 477 label="Gap" help="The gap penalty for the dynamic programming sequence alignment"/>