Mercurial > repos > lecorguille > xcms_group

comparison abims_xcms_group.xml @ 14:833d2c821d9c draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/workflow4metabolomics/xcms commit 9f72e947d9c241d11221cad561f3525d27231857
author lecorguille
date Tue, 18 Sep 2018 16:11:06 -0400
parents 13558e8a4778
children 95e689b7f27f
comparison
equal deleted inserted replaced
13:13558e8a4778 14:833d2c821d9c
1 <tool id="abims_xcms_group" name="xcms.group" version="2.1.1"> 1 <tool id="abims_xcms_group" name="xcms groupChromPeaks (group)" version="@WRAPPER_VERSION@.0">
2 2
3 <description>Group peaks together across samples using overlapping m/z bins and calculation of smoothed peak distributions in chromatographic time.</description> 3 <description>Perform the correspondence, the grouping of chromatographic peaks within and between samples.</description>
4 4
5 <macros> 5 <macros>
6 <import>macros.xml</import> 6 <import>macros.xml</import>
7 <import>macros_xcms.xml</import>
7 </macros> 8 </macros>
8 9
9 <expand macro="requirements"/> 10 <expand macro="requirements"/>
10 <expand macro="stdio"/> 11 <expand macro="stdio"/>
11 12
12 <command><![CDATA[ 13 <command><![CDATA[
13 @COMMAND_XCMS_SCRIPT@ 14 @COMMAND_RSCRIPT@/xcms_group.r
14 xfunction group
15 image '$image' 15 image '$image'
16 16
17 xsetRdataOutput '$xsetRData'
18 rplotspdf '$rplotsPdf'
19
20 method $methods.method 17 method $methods.method
21 #if $methods.method == "density": 18 #if $methods.method == "PeakDensity":
22 ## minsamp $methods.minsamp
23 minfrac $methods.minfrac
24 bw $methods.bw 19 bw $methods.bw
25 mzwid $methods.mzwid 20 minFraction $methods.minFraction
26 sleep 0.001 21 minSamples $methods.minSamples
27 #if $methods.density_options.option == "show": 22 binSize $methods.binSize
28 max $methods.density_options.max 23 ## Advanced
29 #end if 24 maxFeatures $methods.PeakDensityAdv.maxFeatures
30 #elif $methods.method == "mzClust": 25 #elif $methods.method == "MzClust":
31 mzppm $methods.mzppm 26 ppm $methods.ppm
32 mzabs $methods.mzabs 27 absMz $methods.absMz
33 minfrac $methods.minfrac 28 minFraction $methods.minFraction
34 ## minsamp $methods.minsamp 29 minSamples $methods.minSamples
35 #else: 30 #else:
36 mzVsRTbalance $methods.mzVsRTbalance 31 mzVsRtBalance $methods.mzVsRtBalance
37 mzCheck $methods.mzCheck 32 absMz $methods.absMz
38 rtCheck $methods.rtCheck 33 absRt $methods.absRt
39 kNN $methods.kNN 34 kNN $methods.kNN
40 #end if 35 #end if
41 36
42 @COMMAND_PEAKLIST@ 37 @COMMAND_PEAKLIST@
43 38
39 @COMMAND_FILE_LOAD@
40
44 @COMMAND_LOG_EXIT@ 41 @COMMAND_LOG_EXIT@
45 ]]></command> 42 ]]></command>
46 43
47 <inputs> 44 <inputs>
48 <param name="image" type="data" format="rdata.xcms.raw,rdata.xcms.group,rdata.xcms.retcor,rdata" label="xset RData file" help="output file from another function xcms (xcmsSet, retcor etc.)" /> 45 <param name="image" type="data" format="rdata.xcms.findchrompeaks,rdata.xcms.group,rdata.xcms.retcor,rdata" label="@INPUT_IMAGE_LABEL@" help="@INPUT_IMAGE_HELP@ from: findChromPeaks, groupChromPeaks or adjustRtime" />
49 <conditional name="methods"> 46 <conditional name="methods">
50 <param name="method" type="select" label="Method to use for grouping" help="[method] See the help section below"> 47 <param name="method" type="select" label="Method to use for grouping" help="See the help section below">
51 <option value="density" selected="true">density</option> 48 <option value="PeakDensity" selected="true">PeakDensity - peak grouping based on time dimension peak densities</option>
52 <option value="mzClust" >mzClust</option> 49 <option value="MzClust">MzClust - high resolution peak grouping for single spectra (direct infusion) MS data</option>
53 <option value="nearest" >nearest</option> 50 <option value="NearestPeaks">NearestPeaks - chromatographic peak grouping based on their proximity in the mz-rt space</option>
54 </param> 51 </param>
55 <when value="density"> 52 <when value="PeakDensity">
56 <param name="bw" type="float" value="30" label="Bandwidth" help="[bw] bandwidth (standard deviation or half width at half maximum) of gaussian smoothing kernel to apply to the peak density chromatogram" /> 53 <param argument="bw" type="float" value="30" label="Bandwidth" help="bandwidth (standard deviation or half width at half maximum) of gaussian smoothing kernel to apply to the peak density chromatogram" />
57 <param name="minfrac" type="float" value="0.5" label="Minimum fraction of samples necessary" help="[minfrac] in at least one of the sample groups for it to be a valid group" /> 54 <param argument="minFraction" type="float" value="0.5" label="Minimum fraction of samples" help="in at least one sample group in which the peaks have to be present to be considered as a peak group (feature)" />
58 <param name="mzwid" type="float" value="0.25" label="Width of overlapping m/z slices" help="[mzwid] to use for creating peak density chromatograms and grouping peaks across samples " /> 55 <param argument="minSamples" type="integer" value="1" label="Minimum number of samples" help="in at least one sample group in which the peaks have to be detected to be considered a peak group (feature)" />
59 <!-- 56 <param argument="binSize" type="float" value="0.25" label="Width of overlapping m/z slices" help="to use for creating peak density chromatograms and grouping peaks across samples (previously mzdiff)" />
60 <param name="minsamp" type="hidden" value="1" label="minsamp" help="minimum number of samples necessary in at least one of the sample groups for it to be a valid group " /> 57
61 --> 58 <section name="PeakDensityAdv" title="Advanced Options" expanded="False">
62 <conditional name="density_options"> 59 <param argument="maxFeatures" type="integer" value="50" label="Maximum number of groups to identify in a single m/z slice" />
63 <param name="option" type="select" label="Advanced options"> 60 </section>
64 <option value="show">show</option>
65 <option value="hide" selected="true">hide</option>
66 </param>
67 <when value="show">
68 <param name="max" type="integer" value="50" label="Maximum number of groups to identify in a single m/z slice" help="[max]" />
69 </when> 61 </when>
70 <when value="hide"> 62 <when value="MzClust">
63 <param argument="ppm" type="integer" value="20" label="Relative mz error for clustering/grouping in ppm" />
64 <param argument="absMz" type="float" value="0" label="Absolute mz error for clustering/grouping" />
65 <param argument="minFraction" type="float" value="0.5" label="Minimum fraction of samples" help="in at least one sample group in which the peaks have to be present to be considered as a peak group (feature)" />
66 <param argument="minSamples" type="integer" value="1" label="Minimum number of samples" help="in at least one sample group in which the peaks have to be detected to be considered a peak group (feature)" />
67 </when>
68 <when value="NearestPeaks">
69 <param argument="mzVsRtBalance" type="integer" value="10" label="Factor by which mz values are multiplied before calculating the (euclician) distance between two peaks" />
70 <param argument="absMz" type="float" value="0.2" label="Maximum tolerated distance for mz values" />
71 <param argument="absRt" type="integer" value="15" label="Maximum tolerated distance for RT values" />
72 <param argument="kNN" type="integer" value="10" label="Number of nearest Neighbours to check" />
71 </when> 73 </when>
72 </conditional> 74 </conditional>
73 75
74 </when>
75 <when value="mzClust">
76 <param name="mzppm" type="integer" value="20 " label="Relative error used for clustering/grouping in ppm" help="[mzppm]" />
77 <param name="mzabs" type="float" value="0" label="Absolute error used for clustering/grouping" help="[mzabs]" />
78 <param name="minfrac" type="float" value="0" label="Minimum fraction of each class in one bin" help="[minfrac] minimum fraction of samples necessary in at least one of the sample groups for it to be a valid group" />
79 <!--
80 <param name="minsamp" type="hidden" value="1" label="minsamp" help="minimum number of samples necessary in at least one of the sample groups for it to be a valid group " />
81 -->
82 </when>
83 <when value="nearest">
84 <param name="mzVsRTbalance" type="integer" value="10 " label="Multiplicator for mz value before calculating the (euclidean) distance between two peaks." help="[mzVsRTbalance]" />
85 <param name="mzCheck" type="float" value="0.2" label="Maximum tolerated distance for mz" help="[mzCheck]" />
86 <param name="rtCheck" type="integer" value="15" label="Maximum tolerated distance for RT" help="[rtCheck]" />
87 <param name="kNN" type="integer" value="10" label="Number of nearest Neighbours to check" help="[kNN]" />
88 </when>
89 </conditional>
90 <!--
91 <param name="sleepy" type="float" value="0.001" label="sleep" help="seconds to pause between plotting successive steps of the peak grouping algorithm. peaks are plotted as points showing relative intensity. identified groups are flanked by dotted vertical lines">
92 <validator type="in_range" message="Must be more than 0" min="0.001" max="inf"/>
93 </param>
94 -->
95
96 <expand macro="input_peaklist"/> 76 <expand macro="input_peaklist"/>
77
78 <expand macro="input_file_load"/>
97 </inputs> 79 </inputs>
98 80
99 <outputs> 81 <outputs>
100 <data name="xsetRData" format="rdata.xcms.group" label="${image.name[:-6]}.group.RData"/> 82 <data name="xsetRData" format="rdata.xcms.group" label="${image.name[:-6]}.groupChromPeaks.RData" from_work_dir="group.RData"/>
101 <data name="rplotsPdf" format="pdf" label="${image.name[:-6]}.group.Rplots.pdf"/> 83 <data name="plotChromPeakDensity" format="pdf" label="${image.name[:-6]}.groupChromPeaks.plotChromPeakDensity.pdf" from_work_dir="plotChromPeakDensity.pdf"/>
102 <expand macro="output_peaklist" function="group"/> 84 <expand macro="output_peaklist" function="group"/>
103 <data name="log" format="txt" label="xset.log.txt" hidden="true" />
104 </outputs> 85 </outputs>
105 86
106 <tests> 87 <tests>
107 <!--<test> 88 <!-- from xcmsSet
108 <param name="image" value="xset.RData"/> 89 <test>
109 <param name="methods|method" value="density"/> 90 <param name="image" value="faahKO-single-class.xset.merged.RData" ftype="rdata"/>
110 <param name="methods|bw" value="5"/> 91 <conditional name="methods">
111 <param name="methods|minfrac" value="0.3"/> 92 <param name="method" value="PeakDensity"/>
112 <param name="methods|mzwid" value="0.01"/> 93 <param name="bw" value="5"/>
113 <param name="methods|density_options|option" value="show"/> 94 <param name="minFraction" value="0.3"/>
114 <param name="methods|density_options|max" value="50"/> 95 <param name="binSize" value="0.01"/>
115 <output name="log"> 96 <section name="PeakDensityAdv">
116 <assert_contents> 97 <param name="maxFeatures" value="50"/>
117 <has_text text="object with 4 samples" /> 98 </section>
118 <has_text text="Time range: 0.7-1139.7 seconds (0-19 minutes)" /> 99 </conditional>
119 <has_text text="Mass range: 50.0021-999.9863 m/z" /> 100 <conditional name="peaklist">
120 <has_text text="Peaks: 59359 (about 14840 per sample)" /> 101 <param name="peaklistBool" value="true" />
121 <has_text text="Peak Groups: 48998" /> 102 <param name="convertRTMinute" value="false" />
122 <has_text text="Sample classes: bio, blank" /> 103 <param name="numDigitsMZ" value="4" />
123 </assert_contents> 104 <param name="numDigitsRT" value="1" />
124 </output> 105 <param name="naTOzero" value="false" />
106 </conditional>
107 <expand macro="test_file_load_single"/>
108 <assert_stdout>
109 <has_text text="bw: 5" />
110 <has_text text="minFraction: 0.3" />
111 <has_text text="maxFeatures: 50" />
112 <has_text text="object with 4 samples" />
113 <has_text text="Time range: 2506.1-4477.9 seconds (41.8-74.6 minutes)" />
114 <has_text text="Mass range: 200.1-600 m/z" />
115 <has_text text="Peaks: 9251 (about 2313 per sample)" />
116 <has_text text="Peak Groups: 8372" />
117 <has_text text="Sample classes: KO, WT" />
118 </assert_stdout>
119 <output name="variableMetadata" file="faahKO.xset.group.variableMetadata.tsv" />
120 <output name="dataMatrix" file="faahKO.xset.group.dataMatrix.tsv" />
125 </test>--> 121 </test>-->
126 <test> 122 <!-- DISABLE FOR TRAVIS
127 <param name="image" value="faahKO.xset.RData"/> 123 <test>
128 <param name="methods|method" value="density"/> 124 <param name="image" value="faahKO-single.xset.merged.RData" ftype="rdata"/>
129 <param name="methods|bw" value="5"/> 125 <conditional name="methods">
130 <param name="methods|minfrac" value="0.3"/> 126 <param name="method" value="PeakDensity"/>
131 <param name="methods|mzwid" value="0.01"/> 127 <param name="bw" value="5"/>
132 <param name="methods|density_options|option" value="show"/> 128 <param name="minFraction" value="0.3"/>
133 <param name="methods|density_options|max" value="50"/> 129 <param name="binSize" value="0.01"/>
130 <conditional name="density_options">
131 <param name="option" value="show"/>
132 <param name="maxFeatures" value="50"/>
133 </conditional>
134 </conditional>
135 <expand macro="test_file_load_single"/>
136 <assert_stdout>
137 <has_text text="object with 4 samples" />
138 <has_text text="Time range: 2506.1-4477.9 seconds (41.8-74.6 minutes)" />
139 <has_text text="Mass range: 200.1-600 m/z" />
140 <has_text text="Peaks: 9251 (about 2313 per sample)" />
141 <has_text text="Peak Groups: 611" />
142 <has_text text="Sample classes: ." />
143 </assert_stdout>
144 </test>
145 -->
146 <!-- DISABLE FOR TRAVIS Zip from xcmsSet
147 <test>
148 <param name="image" value="faahKO.xset.RData" ftype="rdata"/>
149 <conditional name="methods">
150 <param name="method" value="PeakDensity"/>
151 <param name="bw" value="5"/>
152 <param name="minFraction" value="0.3"/>
153 <param name="binSize" value="0.01"/>
154 <conditional name="density_options">
155 <param name="option" value="show"/>
156 <param name="maxFeatures" value="50"/>
157 </conditional>
158 </conditional>
134 <conditional name="peaklist"> 159 <conditional name="peaklist">
135 <param name="convertRTMinute" value="false" /> 160 <param name="convertRTMinute" value="false" />
136 <param name="peaklistBool" value="true" /> 161 <param name="peaklistBool" value="true" />
137 <param name="numDigitsMZ" value="4" /> 162 <param name="numDigitsMZ" value="4" />
138 <param name="numDigitsRT" value="1" /> 163 <param name="numDigitsRT" value="1" />
139 </conditional> 164 <param name="naTOzero" value="false" />
140 <output name="log"> 165 </conditional>
141 <assert_contents> 166 <expand macro="test_file_load_zip"/>
142 <has_text text="object with 4 samples" /> 167 <assert_stdout>
143 <has_text text="Time range: 2506.1-4477.9 seconds (41.8-74.6 minutes)" /> 168 <has_text text="object with 4 samples" />
144 <has_text text="Mass range: 200.1-600 m/z" /> 169 <has_text text="Time range: 2506.1-4477.9 seconds (41.8-74.6 minutes)" />
145 <has_text text="Peaks: 9251 (about 2313 per sample)" /> 170 <has_text text="Mass range: 200.1-600 m/z" />
146 <has_text text="Peak Groups: 8275" /> 171 <has_text text="Peaks: 9251 (about 2313 per sample)" />
147 <has_text text="Sample classes: KO, WT" /> 172 <has_text text="Peak Groups: 8372" />
148 </assert_contents> 173 <has_text text="Sample classes: KO, WT" />
149 </output> 174 </assert_stdout>
150 <output name="variableMetadata" file="faahKO.xset.group.variableMetadata.tsv" /> 175 <output name="variableMetadata" file="faahKO.xset.group.variableMetadata.tsv" />
151 <output name="dataMatrix" file="faahKO.xset.group.dataMatrix.tsv" /> 176 <output name="dataMatrix" file="faahKO.xset.group.dataMatrix.tsv" />
152 </test> 177 </test>
153 <test> 178 -->
154 <param name="image" value="faahKO-single-class.xset.merged.RData"/> 179
155 <param name="methods|method" value="density"/> 180 <!-- DISABLE FOR TRAVIS Zip from retcor
156 <param name="methods|bw" value="5"/> 181 <test>
157 <param name="methods|minfrac" value="0.3"/> 182 <param name="image" value="faahKO.xset.group.retcor.RData" ftype="rdata"/>
158 <param name="methods|mzwid" value="0.01"/> 183 <conditional name="methods">
159 <param name="methods|density_options|option" value="show"/> 184 <param name="method" value="PeakDensity"/>
160 <param name="methods|density_options|max" value="50"/> 185 <param name="bw" value="5"/>
161 <conditional name="peaklist"> 186 <param name="minFraction" value="0.3"/>
162 <param name="convertRTMinute" value="false" /> 187 <param name="binSize" value="0.01"/>
163 <param name="peaklistBool" value="true" /> 188 <conditional name="density_options">
164 <param name="numDigitsMZ" value="4" /> 189 <param name="option" value="show"/>
165 <param name="numDigitsRT" value="1" /> 190 <param name="maxFeatures" value="50"/>
166 </conditional> 191 </conditional>
167 <output name="log"> 192 </conditional>
168 <assert_contents> 193 <expand macro="test_file_load_zip"/>
169 <has_text text="object with 4 samples" /> 194 <assert_stdout>
170 <has_text text="Time range: 2506.1-4477.9 seconds (41.8-74.6 minutes)" /> 195 <has_text text="object with 4 samples" />
171 <has_text text="Mass range: 200.1-600 m/z" /> 196 <has_text text="Time range: 2509.2-4480.3 seconds (41.8-74.7 minutes)" />
172 <has_text text="Peaks: 9251 (about 2313 per sample)" /> 197 <has_text text="Mass range: 200.1-600 m/z" />
173 <has_text text="Peak Groups: 8275" /> 198 <has_text text="Peaks: 9251 (about 2313 per sample)" />
174 <has_text text="Sample classes: KO, WT" /> 199 <has_text text="Peak Groups: 8209" />
175 </assert_contents> 200 <has_text text="Sample classes: KO, WT" />
176 </output> 201 </assert_stdout>
177 <output name="variableMetadata" file="faahKO.xset.group.variableMetadata.tsv" /> 202 </test>
178 <output name="dataMatrix" file="faahKO.xset.group.dataMatrix.tsv" /> 203 -->
179 </test> 204 <!-- from retcor -->
180 <test> 205 <test>
181 <param name="image" value="faahKO-single.xset.merged.RData"/> 206 <param name="image" value="faahKO-single.xset.merged.group.retcor.RData" ftype="rdata"/>
182 <param name="methods|method" value="density"/> 207 <conditional name="methods">
183 <param name="methods|bw" value="5"/> 208 <param name="method" value="PeakDensity"/>
184 <param name="methods|minfrac" value="0.3"/> 209 <param name="bw" value="5"/>
185 <param name="methods|mzwid" value="0.01"/> 210 <param name="minFraction" value="0.3"/>
186 <param name="methods|density_options|option" value="show"/> 211 <param name="binSize" value="0.01"/>
187 <param name="methods|density_options|max" value="50"/> 212 <section name="PeakDensityAdv">
188 <output name="log"> 213 <param name="maxFeatures" value="50"/>
189 <assert_contents> 214 </section>
190 <has_text text="object with 4 samples" /> 215 </conditional>
191 <has_text text="Time range: 2506.1-4477.9 seconds (41.8-74.6 minutes)" /> 216 <expand macro="test_file_load_single"/>
192 <has_text text="Mass range: 200.1-600 m/z" /> 217 <assert_stdout>
193 <has_text text="Peaks: 9251 (about 2313 per sample)" /> 218 <has_text text="bw: 5" />
194 <has_text text="Peak Groups: 664" /> 219 <has_text text="minFraction: 0.3" />
195 <has_text text="Sample classes: ." /> 220 <has_text text="binSize: 0.01"/>
196 </assert_contents> 221 <has_text text="maxFeatures: 50" />
197 </output> 222 <has_text text="object with 4 samples" />
198 </test> 223 <has_text text="Time range: 2509.2-4480.3 seconds (41.8-74.7 minutes)" />
199 <test> 224 <has_text text="Mass range: 200.1-600 m/z" />
200 <param name="image" value="MM-single.xset.merged.RData"/> 225 <has_text text="Peaks: 9251 (about 2313 per sample)" />
201 <param name="methods|method" value="density"/> 226 <has_text text="Peak Groups: 8209" />
202 <param name="methods|bw" value="5"/> 227 <has_text text="Sample classes: KO, WT" />
203 <param name="methods|minfrac" value="0.3"/> 228 </assert_stdout>
204 <param name="methods|mzwid" value="0.01"/> 229 </test>
205 <param name="methods|density_options|option" value="show"/> 230 <!-- DISABLE FOR TRAVIS
206 <param name="methods|density_options|max" value="50"/> 231 Test to test the different methods parameters
207 <output name="log"> 232 <test expect_failure="True">
208 <assert_contents> 233 <param name="image" value="faahKO-single.xset.merged.group.retcor.RData" ftype="rdata"/>
209 <has_text text="object with 2 samples" /> 234 <conditional name="methods">
210 <has_text text="Time range: 19.7-307.3 seconds (0.3-5.1 minutes)" /> 235 <param name="method" value="MzClust"/>
211 <has_text text="Mass range: 117.0357-936.7059 m/z" /> 236 <param name="ppm" value="21"/>
212 <has_text text="Peaks: 236 (about 118 per sample)" /> 237 <param name="absMz" value="0.1"/>
213 <has_text text="Peak Groups: 236" /> 238 </conditional>
214 <has_text text="Sample classes: ." /> 239 <expand macro="test_file_load_single"/>
215 </assert_contents> 240 <assert_stdout>
216 </output> 241 <has_text text="ppm: 21" />
217 </test> 242 <has_text text="absMz: 0.1" />
218 <!--<test> 243 </assert_stdout>
219 <param name="image" value="xset.group.retcor.RData"/> 244 </test>
220 <param name="methods|method" value="density"/> 245 <test>
221 <param name="methods|bw" value="5"/> 246 <param name="image" value="faahKO-single.xset.merged.group.retcor.RData" ftype="rdata"/>
222 <param name="methods|minfrac" value="0.3"/> 247 <conditional name="methods">
223 <param name="methods|mzwid" value="0.01"/> 248 <param name="method" value="NearestPeaks"/>
224 <param name="methods|density_options|option" value="show"/> 249 <param name="mzVsRtBalance" value="11"/>
225 <param name="methods|density_options|max" value="50"/> 250 <param name="absMz" value="0.1"/>
226 <output name="log"> 251 </conditional>
227 <assert_contents> 252 <expand macro="test_file_load_single"/>
228 <has_text text="object with 4 samples" /> 253 <assert_stdout>
229 <has_text text="Time range: 0.2-1140.1 seconds (0-19 minutes)" /> 254 <has_text text="mzVsRtBalance: 11" />
230 <has_text text="Mass range: 50.0021-999.9863 m/z" /> 255 <has_text text="absMz: 0.1" />
231 <has_text text="Peaks: 59359 (about 14840 per sample)" /> 256 </assert_stdout>
232 <has_text text="Peak Groups: 48958" /> 257 </test>
233 <has_text text="Sample classes: bio, blank" /> 258 -->
234 </assert_contents>
235 </output>
236 </test>-->
237 <test>
238 <param name="image" value="faahKO.xset.group.retcor.RData"/>
239 <param name="methods|method" value="density"/>
240 <param name="methods|bw" value="5"/>
241 <param name="methods|minfrac" value="0.3"/>
242 <param name="methods|mzwid" value="0.01"/>
243 <param name="methods|density_options|option" value="show"/>
244 <param name="methods|density_options|max" value="50"/>
245 <output name="log">
246 <assert_contents>
247 <has_text text="object with 4 samples" />
248 <has_text text="Time range: 2507.7-4481.7 seconds (41.8-74.7 minutes)" />
249 <has_text text="Mass range: 200.1-600 m/z" />
250 <has_text text="Peaks: 9251 (about 2313 per sample)" />
251 <has_text text="Peak Groups: 8157" />
252 <has_text text="Sample classes: KO, WT" />
253 </assert_contents>
254 </output>
255 </test>
256 <test>
257 <param name="image" value="faahKO-single.xset.merged.group.retcor.RData"/>
258 <param name="methods|method" value="density"/>
259 <param name="methods|bw" value="5"/>
260 <param name="methods|minfrac" value="0.3"/>
261 <param name="methods|mzwid" value="0.01"/>
262 <param name="methods|density_options|option" value="show"/>
263 <param name="methods|density_options|max" value="50"/>
264 <output name="log">
265 <assert_contents>
266 <has_text text="object with 4 samples" />
267 <has_text text="Time range: 2507.7-4481.7 seconds (41.8-74.7 minutes)" />
268 <has_text text="Mass range: 200.1-600 m/z" />
269 <has_text text="Peaks: 9251 (about 2313 per sample)" />
270 <has_text text="Peak Groups: 8157" />
271 <has_text text="Sample classes: KO, WT" />
272 </assert_contents>
273 </output>
274 </test>
275 </tests> 259 </tests>
276 260
277 <help><![CDATA[ 261 <help><![CDATA[
278 262
279 @HELP_AUTHORS@ 263 @HELP_AUTHORS@
280 264
281 ========== 265 ====================
282 Xcms.Group 266 xcms groupChromPeaks
283 ========== 267 ====================
284 268
285 ----------- 269 -----------
286 Description 270 Description
287 ----------- 271 -----------
288 272
289 After peak identification with xcmsSet, this tool groups the peaks which represent the same analyte across samples using overlapping m/z bins and calculation of smoothed peak distributions in chromatographic time. Allows rejection of features, which are only partially detected within the replicates of a sample class. 273 After peak identification with xcmsSet, this tool groups the peaks which represent the same analyte across samples using overlapping m/z bins and calculation of smoothed peak distributions in chromatographic time. Allows rejection of features, which are only partially detected within the replicates of a sample class.
290 274
291
292
293 ----------------- 275 -----------------
294 Workflow position 276 Workflow position
295 ----------------- 277 -----------------
296 278
297 **Upstream tools** 279 **Upstream tools**
298 280
299 ========================= ================= =================== ========== 281 ==================================== ======================== ==============================
300 Name output file format parameter 282 Name Output file Format
301 ========================= ================= =================== ========== 283 ==================================== ======================== ==============================
302 xcms.xcmsSet xset.RData rdata.xcms.raw RData file 284 xcms.findChromPeaks Merger (single) xset.merged.RData rdata.xcms.findchrompeaks
303 ------------------------- ----------------- ------------------- ---------- 285 ------------------------------------ ------------------------ ------------------------------
304 xcms.xcmsSet Merger xset.RData rdata.xcms.raw RData file 286 xcms.findChromPeaks (zip) ``*``.raw.xset.RData rdata.xcms.findchrompeaks
305 ------------------------- ----------------- ------------------- ---------- 287 ------------------------------------ ------------------------ ------------------------------
306 xcms.retcor xset.RData rdata.xcms.retcor RData file 288 xcms.adjustRtime ``*``.adjustRtime.RData rdata.xcms.retcor
307 ========================= ================= =================== ========== 289 ==================================== ======================== ==============================
308 290
309 291
310 **Downstream tools** 292 **Downstream tools**
311 293
312 +---------------------------+--------------------------------------+ 294 =========================== =========================== ====================
313 | Name | Output file | Format | 295 Name Output file Format
314 +===========================+=================+====================+ 296 =========================== =========================== ====================
315 |xcms.retcor | xset.RData | rdata.xcms.group | 297 xcms.adjustRtime ``*``.groupChromPeaks.RData rdata.xcms.group
316 +---------------------------+--------------------------------------+ 298 --------------------------- --------------------------- --------------------
317 |xcms.fillPeaks | xset.RData | rdata.xcms.group | 299 xcms.fillChromPeaks ``*``.groupChromPeaks.RData rdata.xcms.group
318 +---------------------------+--------------------------------------+ 300 =========================== =========================== ====================
319
320 The output file is an xcmsSet.RData file. You can continue your analysis using it in **xcms.retcor** tool as an next step and then **xcms.fillPeaks**.
321 301
322 **General schema of the metabolomic workflow** 302 **General schema of the metabolomic workflow**
323 303
324 .. image:: xcms_group_workflow.png 304 .. image:: xcms_group_workflow.png
325 305
326 306 ---------------------------------------------------
327 -----------
328 Input files
329 -----------
330
331 +---------------------------+-----------------------+
332 | Parameter : num + label | Format |
333 +===========================+=======================+
334 | Or : RData file | rdata.xcms.raw |
335 +---------------------------+-----------------------+
336 | Or : RData file | rdata.xcms.retcor |
337 +---------------------------+-----------------------+
338
339 307
340 ---------- 308 ----------
341 Parameters 309 Parameters
342 ---------- 310 ----------
343 311
344 Method to use for grouping 312 Method to use for grouping
345 -------------------------- 313 --------------------------
346 314
347 **mzClust** 315 **MzClust**
348 316
349 | Runs high resolution alignment on single spectra samples stored in the RData file generated by the **xcmsSet tool**. 317 | This method performs high resolution correspondence for single spectra samples.
350 318 | See the MzClust_manual_
351 **density** 319
352 320 **PeakDensity**
353 | Groups peaks together across samples using overlapping m/z bins and calculation of smoothed peak distributions in chromatographic time. 321
354 322 | This method performs performs correspondence (chromatographic peak grouping) based on the density (distribution) of identified peaks along the retention time axis within slices of overlapping mz ranges. All peaks (from the same or from different samples) being close on the retention time axis are grouped into a feature (peak group).
355 **nearest** 323 | See the PeakDensity_manual_
356 324
357 | Groups peaks together across samples by creating a master peak list and assigning corresponding peaks from all samples. It is inspired by the alignment algorithm of mzMine. 325 **NearestPeaks**
358 326
327 | This method is inspired by the grouping algorithm of mzMine [Katajamaa 2006] and performs correspondence based on proximity of peaks in the space spanned by retention time and mz values. The method creates first a master peak list consisting of all chromatographic peaks from the sample in which most peaks were identified, and starting from that, calculates distances to peaks from the sample with the next most number of peaks. If peaks are closer than the defined threshold they are grouped together.
328 | See the NearestPeaks_manual_
329
330 .. _MzClust_manual: https://rdrr.io/bioc/xcms/man/groupChromPeaks-mzClust.html#heading-2
331 .. _PeakDensity_manual: https://rdrr.io/bioc/xcms/man/groupChromPeaks-density.html#heading-2
332 .. _NearestPeaks_manual: https://rdrr.io/bioc/xcms/man/groupChromPeaks-nearest.html#heading-2
333
334 @HELP_XCMS_MANUAL@
335
336 @HELP_PEAKLIST@
359 337
360 ------------ 338 ------------
361 Output files 339 Output files
362 ------------ 340 ------------
363 341
364 xset.group.Rplots.pdf 342 xset.groupChromPeaks.RData: rdata.xcms.group format
365 343
366 xset.group.RData: rdata.xcms.group format 344 | RData file that will be necessary in the third and fourth step of the workflow (xcms.adjustRtime and xcms.fillChromPeaks).
367 345
368 | Rdata file that will be necessary in the third and fourth step of the workflow (xcms.retcor and xcms.fillpeaks). 346 xset.groupChromPeaks.plotChromPeakDensity.pdf
369 347
370 348 | Density plot
371 ------ 349
372 350 @HELP_PEAKLIST_OUTPUT@
373 .. class:: infomark
374
375 The output file is an xset.group.RData file. You can continue your analysis using it in **xcms.retcor** tool.
376
377
378 ---------------------------------------------------
379
380
381 ---------------
382 Working example
383 ---------------
384
385 Input files
386 -----------
387
388 | RData file -> **xset.RData**
389
390 Parameters
391 ----------
392
393 | Method -> **density**
394 | bw -> **5**
395 | minfrac -> **0.3**
396 | mzwid -> **0.01**
397 | Advanced options: **show**
398 | max -> **50**
399
400
401 Output files
402 ------------
403
404 | **1) xset.RData: RData file**
405
406 | **2) Example of an xset.group.Rplots pdf file**
407
408 .. image:: xcms_group.png
409 :width: 700
410 351
411 352
412 --------------------------------------------------- 353 ---------------------------------------------------
413 354
414 Changelog/News 355 Changelog/News
415 -------------- 356 --------------
416 357
358 **Version 3.0.0.0 - 08/03/2018**
359
360 - UPGRADE: upgrade the xcms version from 1.46.0 to 3.0.0. So refactoring of a lot of underlying codes and methods. Some parameters may have been renamed.
361
362 - NEW: a bunch of new options: PeakDensity.minSamples), MzClust.minSamples)
363
364 - NEW: a new density plot
365
366 - IMPROVEMENT: the advanced options are now in sections. It will allow you to access to all the parameters and to know their default values.
367
368
417 **Version 2.1.1 - 29/11/2017** 369 **Version 2.1.1 - 29/11/2017**
418 370
419 - BUGFIX: To avoid issues with accented letter in the parentFile tag of the mzXML files, we changed a hidden mechanim to LC_ALL=C 371 - BUGFIX: To avoid issues with accented letter in the parentFile tag of the mzXML files, we changed a hidden mechanim to LC_ALL=C
420 372
373
421 **Version 2.1.0 - 07/02/2017** 374 **Version 2.1.0 - 07/02/2017**
422 375
423 - IMPROVEMENT: Add an option to export the peak list at this step without have to wait camara.annotate 376 - IMPROVEMENT: Add an option to export the peak list at this step without have to wait camara.annotate
424 377
425 - IMPROVEMENT: xcms.group can deal with merged individual data from "xcms.xcmsSet Merger" 378 - IMPROVEMENT: xcms.group can deal with merged individual data from "xcms.xcmsSet Merger"
426 379
427 - BUGFIX: the default value of "density" -> "Maximum number of groups to identify in a single m/z slice" which was of 5 have been changed to fix with the XMCS default values to 50 380 - BUGFIX: the default value of "density" -> "Maximum number of groups to identify in a single m/z slice" which was of 5 have been changed to fix with the XMCS default values to 50
428 381
382
429 **Version 2.0.6 - 06/07/2016** 383 **Version 2.0.6 - 06/07/2016**
430 384
431 - UPGRADE: upgrate the xcms version from 1.44.0 to 1.46.0 385 - UPGRADE: upgrate the xcms version from 1.44.0 to 1.46.0
432 386
387
433 **Version 2.0.5 - 04/04/2016** 388 **Version 2.0.5 - 04/04/2016**
434 389
435 - TEST: refactoring to pass planemo test using conda dependencies 390 - TEST: refactoring to pass planemo test using conda dependencies
436 391
437 392