|
3
|
1 <tool name="MsClust" id="msclust2" version="2.0.2">
|
|
|
2 <description>Extracts fragmentation spectra from aligned data</description>
|
|
|
3 <!--
|
|
|
4 For remote debugging start you listener on port 8000 and use the following as command interpreter:
|
|
|
5 java -jar -Xdebug -Xrunjdwp:transport=dt_socket,address=D0100564.wurnet.nl:8000
|
|
|
6 //////////////////////////
|
|
|
7
|
|
|
8 TODO in command below: add conditionals according to options of using or NOT the tolerances/thresholds from previous steps
|
|
|
9 -->
|
|
|
10 <command interpreter="java -jar ">
|
|
|
11 MsClust.jar
|
|
|
12 -peaksFileName $inputPeaks
|
|
|
13 -dataType $dataType
|
|
|
14 -imputationMethod $imputationMethod.type
|
|
|
15 #if $imputationMethod.type == "valueRange"
|
|
|
16 -rangeUpperLimit $imputationMethod.rangeUpperLimit
|
|
|
17 #end if
|
|
|
18 -plInputFormat "metalign"
|
|
|
19 -potDensFuncType $potDensFuncType.type
|
|
|
20 -centerSelectionType $centerSelectionType.type
|
|
|
21 -clusteringType $clusteringType.type
|
|
|
22 -neighborhoodWindowSize $potDensFuncType.pdf_neighborhoodWindowSize
|
|
|
23 -clusterSearchStopCriterium $centerSelectionType.cs_stop_criterion
|
|
|
24 -pearsonDistTreshold $potDensFuncType.pdf_pears_treshold
|
|
|
25 -pearsonTresholdConfidence $potDensFuncType.pdf_pears_conf
|
|
|
26 -pearsonPDReductionThreshold $centerSelectionType.cs_pears_pd_reductionTreshold
|
|
|
27 -pearsonPDReductionSlope $centerSelectionType.cs_pears_pd_reductionSlope
|
|
|
28 -scanDistTol $potDensFuncType.pdf_scan_toler
|
|
|
29 -scanDistanceConfidence $potDensFuncType.pdf_scan_conf
|
|
|
30 -centrotypesOut $centrotypesOut
|
|
|
31 -simOut $simOut
|
|
|
32 -micOut $micOut
|
|
|
33 -mspOut $mspOut
|
|
|
34 -classOut $classOut
|
|
|
35 -outReport $htmlReportFile
|
|
|
36 -outReportPicturesPath $htmlReportFile.files_path
|
|
|
37 #if $clusteringType.type == "fuzzyCMeans"
|
|
|
38 -fcmMembershipWeightingExponent $clusteringType.fcmMembershipWeightingExponent
|
|
|
39 -fcmStopCriterion $clusteringType.fcmStopCriterion
|
|
|
40 -fcmCorrelationWeight $clusteringType.fcmCorrelationWeight
|
|
|
41 -fcmFinalAssemblyType $clusteringType.finalClusterAssembly.type
|
|
|
42 #if $clusteringType.finalClusterAssembly.type == "membershipBased"
|
|
|
43 -fcmMembershipCutoff $clusteringType.finalClusterAssembly.fcmMembershipCutoff
|
|
|
44 #end if
|
|
|
45 #end if
|
|
|
46 -verbose "false"
|
|
|
47 #if $advancedSettings.settings == True
|
|
|
48 -advancedSettings YES
|
|
|
49 -saturationLimit $advancedSettings.saturationLimit
|
|
|
50 -sampleSelectionSortType $advancedSettings.sampleSelectionSortType
|
|
|
51 -simSelectionAlgorithm $advancedSettings.simSelectionAlgorithm
|
|
|
52 -simMassFilter "$advancedSettings.simMassFilter"
|
|
|
53 -simMembershipThreshold $advancedSettings.simMembershipThreshold
|
|
|
54 -simSaturationThreshold $advancedSettings.simSaturationThreshold
|
|
|
55 -simAbsenseThreshold $advancedSettings.simAbsenseThreshold
|
|
|
56 -micMembershipThreshold $advancedSettings.micMembershipThreshold
|
|
|
57 -peakIntensityCorrectionAlgorithm $advancedSettings.peakIntensityCorrectionAlgorithm
|
|
|
58 #else
|
|
|
59 -advancedSettings YES
|
|
|
60 -sampleSelectionSortType SIM_INTENSITY
|
|
|
61 -peakIntensityCorrectionAlgorithm CORRELATION_BASED
|
|
|
62 #end if
|
|
|
63
|
|
|
64 </command>
|
|
|
65 <inputs>
|
|
|
66 <!-- <param name="rankingWeightConfig" type="text" area="true" size="11x70" label="NB - TEST VERSION"
|
|
|
67 value="VERSION BEING TESTED AT THIS MOMENT...NOT READY FOR USE..."/>
|
|
|
68 -->
|
|
|
69 <param name="inputPeaks" type="data" format="txt" label="Ion-wise aligned data (e.g. MetAlign output data)" />
|
|
|
70 <param name="dataType" type="select" size="30" label="Data type">
|
|
|
71 <option value="gcms" selected="true">GC-MS</option>
|
|
|
72 <option value="lcms">LC-MS</option>
|
|
|
73 </param>
|
|
|
74 <conditional name="imputationMethod">
|
|
|
75 <param name="type" type="select" size="30" label="Select the approach used for imputing missing values (optional)" help="select how you generated the values to fill in the data gaps">
|
|
|
76 <option value="none" >none</option>
|
|
|
77 <option value="metot" selected="true">MeTot</option>
|
|
|
78 <option value="valueRange">Values range</option>
|
|
|
79 </param>
|
|
|
80 <when value="valueRange">
|
|
|
81 <param name="rangeUpperLimit" type="integer" size="10" value="0" label="Range upper limit" help="values up to this limit will be considered 'generated' values" />
|
|
|
82 </when>
|
|
|
83 </conditional>
|
|
|
84 <conditional name="potDensFuncType">
|
|
|
85 <param name="type" type="select" size="30" label="Select PD function type =====================================================">
|
|
|
86 <option value="original" selected="true">Original</option>
|
|
|
87 </param>
|
|
|
88 <when value="original">
|
|
|
89 <param name="pdf_neighborhoodWindowSize" type="integer" size="10" value="200" label="Effective Peaks" />
|
|
|
90 <param name="pdf_scan_toler" type="float" size="10" value="10" label="Peak Width, in scans" />
|
|
|
91 <param name="pdf_scan_conf" type="float" size="10" value="80" label="Peak Width confidence (0.0 to 99.99)" help="example: 0[no confidence]...50[good guess]...99.9[quite certain])" />
|
|
|
92 <param name="pdf_pears_treshold" type="float" size="10" value="0.8" label="Correlation threshold (0.0 - 1.0)" />
|
|
|
93 <param name="pdf_pears_conf" type="float" size="10" value="98.0" label="Correlation threshold confidence (0.0 to 99.99)" help="example: 0[no confidence]...50[good guess]...99.9[quite certain])" />
|
|
|
94 </when>
|
|
|
95 </conditional>
|
|
|
96 <conditional name="centerSelectionType">
|
|
|
97 <param name="type" type="select" label="Initial Centers selection type ==================================================" >
|
|
|
98 <option value="original" selected="true">Original - Subtractive potential reductions with stop criterion and REUSE tolerances (from PD function)</option>
|
|
|
99 </param>
|
|
|
100 <when value="original">
|
|
|
101 <param name="cs_pears_pd_reductionTreshold" type="float" size="10" value="0.8" label="Potential Density reduction (0.0 - 1.0)" />
|
|
|
102 <param name="cs_pears_pd_reductionSlope" type="float" size="10" value="0.01" label="Potential Density reduction softness " />
|
|
|
103 <param name="cs_stop_criterion" type="float" size="10" value="2" label="Stop Criterion " />
|
|
|
104 </when>
|
|
|
105 </conditional>
|
|
|
106 <conditional name="clusteringType">
|
|
|
107 <param name="type" type="select" label="Classify using ===========================================================">
|
|
|
108 <option value="original" selected="true">Original - Fuzzy clustering, keep original centers and REUSE (scan distance) tolerances</option>
|
|
|
109 <option value="fuzzyCMeans">(experimental) Fuzzy C-Means - Fuzzy clustering, optimize centers</option>
|
|
|
110 </param>
|
|
|
111 <when value="original">
|
|
|
112 <!-- nothing -->
|
|
|
113 </when>
|
|
|
114 <when value="originalNewTol">
|
|
|
115 <param name="clust_scan_toler" type="float" size="10" value="10" label="Peak Width, in scans" />
|
|
|
116 <param name="clust_scan_slope" type="float" size="10" value="2" label="Peak Width margin softness" />
|
|
|
117 </when>
|
|
|
118 <when value="fuzzyCMeans">
|
|
|
119 <param name="fcmMembershipWeightingExponent" type="float" size="10" value="2.0" label="Membership Weighting Exponent" help="Influences cluster center repositioning in the iterations 1.1 (exploratory) to around 3.0 (conservative)" />
|
|
|
120 <param name="fcmStopCriterion" type="float" size="10" value="0.05" label="Stop Criterion" help="When convergence is 'reached' (e.g. 0.05 means memberships only changed with 5% in last iteration)" />
|
|
|
121 <param name="fcmCorrelationWeight" type="float" size="10" value="2" label="Correlation weight factor" help="Increase this if you think the correlation is reliable (e.g. you have a high number of samples)" />
|
|
|
122 <conditional name="finalClusterAssembly">
|
|
|
123 <param name="type" type="select" label="Final cluster assembly" >
|
|
|
124 <option value="original" selected="true">Original - distance based</option>
|
|
|
125 <option value="membershipBased">Membership based</option>
|
|
|
126 </param>
|
|
|
127 <when value="membershipBased">
|
|
|
128 <param name="fcmMembershipCutoff" type="select" label="Maximum allowed peak overlap" >
|
|
|
129 <option value="0.05" >~7 clusters</option>
|
|
|
130 <option value="0.10" >~5 clusters</option>
|
|
|
131 <option value="0.20" >~3 clusters</option>
|
|
|
132 </param>
|
|
|
133 </when>
|
|
|
134 <when value="original">
|
|
|
135 <!-- nothing -->
|
|
|
136 </when>
|
|
|
137 </conditional>
|
|
|
138 </when>
|
|
|
139 </conditional>
|
|
|
140
|
|
|
141 <param name="summaryReport" type="boolean" checked="true" label="Generate summary report" help="NB: this will increase the processing time (in some cases up to a few extra minutes)"/>
|
|
|
142
|
|
|
143 <conditional name="advancedSettings">
|
|
|
144 <param name="settings" type="boolean" truevalue="Yes" falsevalue="No" checked="false" label="Advanced settings ========================================================"/>
|
|
|
145 <when value="Yes">
|
|
|
146 <param name="saturationLimit" optional="true" type="integer" size="10" label="Saturation limit (optional)" help="fill in if you have saturation problems in your data" />
|
|
|
147 <param name="sampleSelectionSortType" type="select" label="Sample selection scheme for spectrum peak intensity correction algorithm (optional/experimental)" help="The intensity values to use to select the samples for each cluster/metabolite in which it is most intense/abundant. These samples are used in the peak intensity correction (see parameter below). Use this option to try to avoid samples that have insufficient signal or saturation." >
|
|
|
148 <option value="None">None</option>
|
|
|
149 <!-- in order of best FORWARD scoring when tested on /test/data/report_test_sets/(P2) Relative peak heights in spectra/Input (Test set 1) -->
|
|
|
150 <option value="SIM_INTENSITY" selected="true">SIM intensities</option>
|
|
|
151 <option value="MAX_INTENSITY">Maximum intensities</option>
|
|
|
152 <option value="CENTROTYPE_INTENSITY">Centrotype peak intensities</option>
|
|
|
153 <option value="MIC_INTENSITY">MIC intensities</option>
|
|
|
154 </param>
|
|
|
155 <param name="peakIntensityCorrectionAlgorithm" type="select" label="Spectrum peak intensity correction algorithm (optional/experimental)" help="Whether spectrum peak heights should be adjusted according to their membership to the cluster or to their correlation to the cluster's centrotype ion" >
|
|
|
156 <option value="MEMBERSHIP_BASED">Membership based (msclust 1.0 mode)</option>
|
|
|
157 <option value="CORRELATION_BASED" selected="true">Correlation based</option>
|
|
|
158 </param>
|
|
|
159 <param name="simSelectionAlgorithm" type="select" label="SIM selection algorithm (experimental)" help="Set this if you want to deviate from the standard which is: allow shared SIM peaks for GC-MS data, and force unique SIM peaks for LC-MS data">
|
|
|
160 <option value="" selected="true"></option>
|
|
|
161 <option value="uniqueSIM">Unique SIM peak</option>
|
|
|
162 <option value="sharedSIM">Shared SIM peak</option>
|
|
|
163 </param>
|
|
|
164 <param name="simMassFilter" type="text" optional="true" size="30" label="SIM mass exclusion list" help="Comma-separated list of masses NOT to use as SIM peaks. E.g. '73,147,...' " />
|
|
|
165 <param name="simMembershipThreshold" optional="true" type="float" size="10" label="SIM membership threshold" help="Minimum membership a peak should have to qualify as a SIM candidate. E.g. 0.8 " />
|
|
|
166 <param name="simSaturationThreshold" optional="true" type="float" size="10" label="SIM saturation threshold (%)" help="Maximum % of samples in which a SIM candidate peak may be saturated. If the candidate peak exceeds this threshold, then another peak is chosen. If no peak can be found this criteria, mass 0 is reported" />
|
|
|
167 <param name="simAbsenseThreshold" optional="true" type="float" size="10" label="SIM absence threshold (%)" help="Maximum % of samples in which a SIM candidate peak may be absent. If the candidate peak exceeds this threshold, then another peak is chosen. If no peak can be found meeting this criteria, mass 0 is reported" />
|
|
|
168
|
|
|
169 <param name="micMembershipThreshold" optional="true" type="float" size="10" label="MIC membership threshold" help="Minimum membership a peak should have to be counted in the MIC sum. E.g. 0.8 " />
|
|
|
170
|
|
|
171 </when>
|
|
|
172 </conditional>
|
|
|
173
|
|
|
174
|
|
|
175 </inputs>
|
|
|
176 <outputs>
|
|
|
177 <data name="centrotypesOut" format="msclust.csv" label="${tool.name} on ${on_string} - centrotypes file"/>
|
|
|
178 <data name="simOut" format="msclust.csv" label="${tool.name} on ${on_string} - SIM file"/>
|
|
|
179 <data name="micOut" format="msclust.csv" label="${tool.name} on ${on_string} - MIC file"/>
|
|
|
180 <data name="mspOut" format="msp" label="${tool.name} on ${on_string} - SPECTRA file"/>
|
|
|
181 <data name="classOut" format="msclust.csv" label="${tool.name} on ${on_string} - Classification file"/>
|
|
|
182 <data name="htmlReportFile" format="html" label="${tool.name} on ${on_string} - HTML report">
|
|
|
183 <!-- If the expression is false, the file is not created -->
|
|
|
184 <filter>( summaryReport == True )</filter>
|
|
|
185 </data>
|
|
|
186 </outputs>
|
|
|
187 <tests>
|
|
|
188 <!-- find out how to use -->
|
|
|
189 </tests>
|
|
|
190 <help>
|
|
|
191
|
|
|
192 <!-- see also http://docutils.sourceforge.net/docs/ref/rst/restructuredtext.html#hyperlink-targets -->
|
|
|
193
|
|
|
194 .. class:: infomark
|
|
|
195
|
|
|
196 This tool extracts spectra from ion-wise aligned MS(/MS) results. It uses expression profiles and
|
|
|
197 retention times of the putative ions to cluster them. Each cluster is then used to generate
|
|
|
198 one spectrum containing the clustered ions (peaks).
|
|
|
199
|
|
4
|
200 .. image:: msclust_summary.png
|
|
3
|
201
|
|
|
202
|
|
|
203 -----
|
|
|
204
|
|
|
205 **Output**
|
|
|
206
|
|
|
207 This tools returns a number of ouptut files and a small report.
|
|
|
208
|
|
|
209 **Parameters index**
|
|
|
210
|
|
|
211
|
|
|
212 *Select the approach used for imputing missing values:* only select this if you have used a specific method to
|
|
|
213 fill in the data gaps in the input file. One example is replacing zero values by some randomly generated low value.
|
|
|
214 If MeTot is chosen, then a value is considered generated if: the value contains a dot '.' and some number
|
|
|
215 other than 0 (zero) after the dot.
|
|
|
216
|
|
|
217 *Effective Peaks:* Neighborhood window size to consider when calculating density. Smaller values increase
|
|
|
218 performance but are less reliable.
|
|
|
219
|
|
|
220 *Peak Width, in scans:* Scan window width of scans to consider 'close'. One can see this as the
|
|
|
221 'tolerated variation in scans' for the apex positions of the fragment peaks composing a cluster.
|
|
|
222 Note: if MetAlign was used, this is the variation *after* pre-processing by MetAlign.
|
|
|
223
|
|
|
224 *Peak Width confidence:* The higher the confidence, the stricter the threshold.
|
|
|
225
|
|
|
226 *Correlation threshold (0.0 - 1.0):* Tolerance center for pearson distance calculation. The higher this value,
|
|
|
227 the higher the correlation between 2 items has to be for them to be considered 'close'.
|
|
|
228
|
|
|
229 *Correlation threshold confidence:* The higher the confidence, the stricter the threshold. `More...`__
|
|
|
230
|
|
|
231 *Potential Density reduction (0.0 - 1.0):* Reduction tolerance center for pearson distance calculation.
|
|
|
232 The higher this value, the less the low correlated items get reduced, getting a chance to form a cluster of their own.
|
|
|
233
|
|
|
234 *Potential Density reduction softness:* Reduction curve slope for pearson distance tolerance. Lower
|
|
|
235 values = stricter separation at the value determined in 'Potential Density reduction' above
|
|
|
236 (TODO review this comment).
|
|
|
237
|
|
|
238 *Stop Criterion:* When to stop reducing and looking for new clusters. Lower values = more iterations
|
|
|
239
|
|
4
|
240 .. __: javascript:window.open('confidence_and_slope_params_explain.png','popUpWindow','height=700,width=800,left=10,top=10,resizable=yes,scrollbars=yes,toolbar=yes,menubar=no,location=no,directories=no,status=yes')
|
|
3
|
241
|
|
|
242
|
|
|
243 -----
|
|
|
244
|
|
|
245 **Output files described below**
|
|
|
246
|
|
|
247 -----
|
|
|
248
|
|
|
249 *SPECTRA:* this file can be submitted to NIST for identification of the spectra.
|
|
|
250
|
|
|
251 `Click here for more details on the Sample selection and Spectrum peak intensity correction algorithm parameters related to SPECTRA generation`_
|
|
|
252
|
|
4
|
253 .. _Click here for more details on the Sample selection and Spectrum peak intensity correction algorithm parameters related to SPECTRA generation: javascript:window.open('sample_sel_and_peak_height_correction.png','popUpWindow','height=700,width=800,left=10,top=10,resizable=yes,scrollbars=yes,toolbar=yes,menubar=no,location=no,directories=no,status=yes')
|
|
3
|
254
|
|
|
255 -----
|
|
|
256
|
|
|
257 *MIC:* stands for Measured Ions Count -> it contains, for each cluster, the sum of the ion count
|
|
|
258 values (corrected by their membership) for all MEASURED cluster ions in the given sample.
|
|
|
259
|
|
|
260 The MIC for a **cluster i** in **sample s**, where **cluster i** has **n** members is thus:
|
|
|
261
|
|
|
262 sum ( [intensity of member n in **sample s**] x [membership value of member n in **cluster i** ] )
|
|
|
263
|
|
|
264 -----
|
|
|
265
|
|
|
266 *SIM:* stands for Selective Ion Mode -> it contains, for each cluster, the intensity values of the
|
|
|
267 most representative member ion peak of this cluster. The most representative member peak is the one with the
|
|
|
268 highest membership*average_intensity. This definition leads to conflicts as a peak can have a
|
|
|
269 membership in two or more clusters. The assignment of a SIM peak to a cluster depends on
|
|
|
270 the configured data type (LC or GC-MS). NB: this can be overruled in the "advanced settings":
|
|
|
271
|
|
|
272 (1) LC-MS SIM: select SIM peak only once and for the centrotype in which this specific mass has its
|
|
|
273 highest membership; for neighboring centrotypes use its "second best SIM", etcetera. In other words,
|
|
|
274 if the SIM peak has been identified as the SIM in more than 1 cluster, assign as SIM to the cluster
|
|
|
275 with highest membership. Continue searching for other SIM peaks to assign to the other clusters until
|
|
|
276 all ambiguities are solved.
|
|
|
277
|
|
|
278 (2) GC-MS SIM: the SIM peak can be "shared" by multiple clusters. However, the intensity values are corrected
|
|
|
279 by the membership value of the peak in the cluster in case the SIM peak is "shared". If the SIM peak is not
|
|
|
280 "shared" then the "raw" intensity values of the SIM peak are recorded in the SIM file.
|
|
|
281
|
|
|
282 `Click here for more details on the SIM output file`_
|
|
|
283
|
|
10
|
284 .. _Click here for more details on the SIM output file: javascript:window.open(".. image:: sample_SIM.png",'popUpWindow','height=700,width=800,left=10,top=10,resizable=yes,scrollbars=yes,toolbar=yes,menubar=no,location=no,directories=no,status=yes')
|
|
3
|
285
|
|
|
286
|
|
|
287
|
|
|
288 </help>
|
|
|
289 </tool>
|
