Mercurial > repos > pieterlukasse > prims_metabolomics
annotate msclust.xml @ 35:0ff22eec3e4b
added peak_width_max for better performance
| author | pieter.lukasse@wur.nl |
|---|---|
| date | Thu, 18 Sep 2014 14:29:57 +0200 |
| parents | 42880675f824 |
| children | 9018657a9f73 |
| rev | line source |
|---|---|
|
28
b1015b9241cd
Added option for using retentionMean (micro minutes) for the time dimension
pieter.lukasse@wur.nl
parents:
21
diff
changeset
|
1 <tool name="MsClust" id="msclust2" version="2.0.4"> |
| 3 | 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 --> | |
|
35
0ff22eec3e4b
added peak_width_max for better performance
pieter.lukasse@wur.nl
parents:
33
diff
changeset
|
10 <command interpreter="java -jar "> |
| 3 | 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
b1015b9241cd
Added option for using retentionMean (micro minutes) for the time dimension
pieter.lukasse@wur.nl
parents:
21
diff
changeset
|
28 -rtDistTolUnit $potDensFuncType.rt_dist_tol_unit.type |
|
b1015b9241cd
Added option for using retentionMean (micro minutes) for the time dimension
pieter.lukasse@wur.nl
parents:
21
diff
changeset
|
29 -rtDistTol $potDensFuncType.rt_dist_tol_unit.pdf_rt_toler |
|
b1015b9241cd
Added option for using retentionMean (micro minutes) for the time dimension
pieter.lukasse@wur.nl
parents:
21
diff
changeset
|
30 -rtDistanceConfidence $potDensFuncType.pdf_scan_conf |
|
35
0ff22eec3e4b
added peak_width_max for better performance
pieter.lukasse@wur.nl
parents:
33
diff
changeset
|
31 -peakWidthMax $potDensFuncType.rt_dist_tol_unit.peak_width_max |
| 3 | 32 -centrotypesOut $centrotypesOut |
| 33 -simOut $simOut | |
| 34 -micOut $micOut | |
| 35 -mspOut $mspOut | |
| 36 -classOut $classOut | |
| 37 -outReport $htmlReportFile | |
| 38 -outReportPicturesPath $htmlReportFile.files_path | |
| 39 #if $clusteringType.type == "fuzzyCMeans" | |
| 40 -fcmMembershipWeightingExponent $clusteringType.fcmMembershipWeightingExponent | |
| 41 -fcmStopCriterion $clusteringType.fcmStopCriterion | |
| 42 -fcmCorrelationWeight $clusteringType.fcmCorrelationWeight | |
| 43 -fcmFinalAssemblyType $clusteringType.finalClusterAssembly.type | |
| 44 #if $clusteringType.finalClusterAssembly.type == "membershipBased" | |
| 45 -fcmMembershipCutoff $clusteringType.finalClusterAssembly.fcmMembershipCutoff | |
| 46 #end if | |
| 47 #end if | |
| 48 -verbose "false" | |
| 49 #if $advancedSettings.settings == True | |
| 50 -advancedSettings YES | |
| 51 -saturationLimit $advancedSettings.saturationLimit | |
| 52 -sampleSelectionSortType $advancedSettings.sampleSelectionSortType | |
| 53 -simSelectionAlgorithm $advancedSettings.simSelectionAlgorithm | |
| 54 -simMassFilter "$advancedSettings.simMassFilter" | |
| 55 -simMembershipThreshold $advancedSettings.simMembershipThreshold | |
| 56 -simSaturationThreshold $advancedSettings.simSaturationThreshold | |
| 57 -simAbsenseThreshold $advancedSettings.simAbsenseThreshold | |
| 58 -micMembershipThreshold $advancedSettings.micMembershipThreshold | |
| 59 -peakIntensityCorrectionAlgorithm $advancedSettings.peakIntensityCorrectionAlgorithm | |
| 60 #else | |
| 61 -advancedSettings YES | |
| 62 -sampleSelectionSortType SIM_INTENSITY | |
| 63 -peakIntensityCorrectionAlgorithm CORRELATION_BASED | |
| 64 #end if | |
| 65 | |
| 66 </command> | |
| 67 <inputs> | |
|
30
60b53f2aa48a
Small fixes, added microminutes support to MsClust, removed TIC or MsClust output
pieter.lukasse@wur.nl
parents:
29
diff
changeset
|
68 |
| 3 | 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> | |
| 19 | 83 <when value="metot"> |
| 84 </when> | |
| 85 <when value="none"> | |
| 86 </when> | |
| 3 | 87 </conditional> |
| 88 <conditional name="potDensFuncType"> | |
| 89 <param name="type" type="select" size="30" label="Select PD function type ====================================================="> | |
| 90 <option value="original" selected="true">Original</option> | |
| 91 </param> | |
| 92 <when value="original"> | |
| 93 <param name="pdf_neighborhoodWindowSize" type="integer" size="10" value="200" label="Effective Peaks" /> | |
|
28
b1015b9241cd
Added option for using retentionMean (micro minutes) for the time dimension
pieter.lukasse@wur.nl
parents:
21
diff
changeset
|
94 <conditional name="rt_dist_tol_unit"> |
|
b1015b9241cd
Added option for using retentionMean (micro minutes) for the time dimension
pieter.lukasse@wur.nl
parents:
21
diff
changeset
|
95 <param name="type" type="select" size="30" label="Peak time unit"> |
|
b1015b9241cd
Added option for using retentionMean (micro minutes) for the time dimension
pieter.lukasse@wur.nl
parents:
21
diff
changeset
|
96 <option value="1" selected="true">scan nr</option> |
| 29 | 97 <option value="2" >(average) micro minutes</option> |
|
28
b1015b9241cd
Added option for using retentionMean (micro minutes) for the time dimension
pieter.lukasse@wur.nl
parents:
21
diff
changeset
|
98 </param> |
| 29 | 99 <when value="1"> |
|
28
b1015b9241cd
Added option for using retentionMean (micro minutes) for the time dimension
pieter.lukasse@wur.nl
parents:
21
diff
changeset
|
100 <param name="pdf_rt_toler" type="float" size="10" value="10" label="Peak Width, in scans" /> |
|
35
0ff22eec3e4b
added peak_width_max for better performance
pieter.lukasse@wur.nl
parents:
33
diff
changeset
|
101 <param name="peak_width_max" type="float" size="10" value="30" label="MAX Peak Width, in scans" help="This parameter is to avoid calculations of correlation |
|
0ff22eec3e4b
added peak_width_max for better performance
pieter.lukasse@wur.nl
parents:
33
diff
changeset
|
102 between peaks that are too far apart anyway" /> |
|
28
b1015b9241cd
Added option for using retentionMean (micro minutes) for the time dimension
pieter.lukasse@wur.nl
parents:
21
diff
changeset
|
103 </when> |
| 29 | 104 <when value="2"> |
|
28
b1015b9241cd
Added option for using retentionMean (micro minutes) for the time dimension
pieter.lukasse@wur.nl
parents:
21
diff
changeset
|
105 <param name="pdf_rt_toler" type="float" size="10" value="100000" label="Peak Width, in micro minutes" help="e.g. 100,000=6 seconds" /> |
|
35
0ff22eec3e4b
added peak_width_max for better performance
pieter.lukasse@wur.nl
parents:
33
diff
changeset
|
106 <param name="peak_width_max" type="float" size="10" value="300000" label="MAX Peak Width, in micro minutes" help="This parameter is to avoid calculations of correlation |
|
0ff22eec3e4b
added peak_width_max for better performance
pieter.lukasse@wur.nl
parents:
33
diff
changeset
|
107 between peaks that are too far apart anyway" /> |
|
28
b1015b9241cd
Added option for using retentionMean (micro minutes) for the time dimension
pieter.lukasse@wur.nl
parents:
21
diff
changeset
|
108 </when> |
|
b1015b9241cd
Added option for using retentionMean (micro minutes) for the time dimension
pieter.lukasse@wur.nl
parents:
21
diff
changeset
|
109 </conditional> |
| 3 | 110 <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])" /> |
| 111 <param name="pdf_pears_treshold" type="float" size="10" value="0.8" label="Correlation threshold (0.0 - 1.0)" /> | |
| 112 <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])" /> | |
| 113 </when> | |
| 114 </conditional> | |
| 115 <conditional name="centerSelectionType"> | |
| 116 <param name="type" type="select" label="Initial Centers selection type ==================================================" > | |
| 117 <option value="original" selected="true">Original - Subtractive potential reductions with stop criterion and REUSE tolerances (from PD function)</option> | |
| 118 </param> | |
| 119 <when value="original"> | |
| 120 <param name="cs_pears_pd_reductionTreshold" type="float" size="10" value="0.8" label="Potential Density reduction (0.0 - 1.0)" /> | |
| 121 <param name="cs_pears_pd_reductionSlope" type="float" size="10" value="0.01" label="Potential Density reduction softness " /> | |
| 122 <param name="cs_stop_criterion" type="float" size="10" value="2" label="Stop Criterion " /> | |
| 123 </when> | |
| 124 </conditional> | |
| 125 <conditional name="clusteringType"> | |
| 126 <param name="type" type="select" label="Classify using ==========================================================="> | |
| 127 <option value="original" selected="true">Original - Fuzzy clustering, keep original centers and REUSE (scan distance) tolerances</option> | |
| 128 <option value="fuzzyCMeans">(experimental) Fuzzy C-Means - Fuzzy clustering, optimize centers</option> | |
| 129 </param> | |
| 130 <when value="original"> | |
| 131 <!-- nothing --> | |
| 132 </when> | |
| 19 | 133 <!-- one idea would be to have clustering specific tolerance values, not reusing the centrotype selection ones |
| 3 | 134 <when value="originalNewTol"> |
| 135 <param name="clust_scan_toler" type="float" size="10" value="10" label="Peak Width, in scans" /> | |
| 136 <param name="clust_scan_slope" type="float" size="10" value="2" label="Peak Width margin softness" /> | |
| 137 </when> | |
| 19 | 138 --> |
| 3 | 139 <when value="fuzzyCMeans"> |
| 140 <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)" /> | |
| 141 <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)" /> | |
| 142 <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)" /> | |
| 143 <conditional name="finalClusterAssembly"> | |
| 144 <param name="type" type="select" label="Final cluster assembly" > | |
| 145 <option value="original" selected="true">Original - distance based</option> | |
| 146 <option value="membershipBased">Membership based</option> | |
| 147 </param> | |
| 148 <when value="membershipBased"> | |
| 149 <param name="fcmMembershipCutoff" type="select" label="Maximum allowed peak overlap" > | |
| 150 <option value="0.05" >~7 clusters</option> | |
| 151 <option value="0.10" >~5 clusters</option> | |
| 152 <option value="0.20" >~3 clusters</option> | |
| 153 </param> | |
| 154 </when> | |
| 155 <when value="original"> | |
| 156 <!-- nothing --> | |
| 157 </when> | |
| 158 </conditional> | |
| 159 </when> | |
| 160 </conditional> | |
| 161 | |
| 162 <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)"/> | |
| 163 | |
| 164 <conditional name="advancedSettings"> | |
| 165 <param name="settings" type="boolean" truevalue="Yes" falsevalue="No" checked="false" label="Advanced settings ========================================================"/> | |
| 166 <when value="Yes"> | |
| 167 <param name="saturationLimit" optional="true" type="integer" size="10" label="Saturation limit (optional)" help="fill in if you have saturation problems in your data" /> | |
| 168 <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." > | |
| 169 <option value="None">None</option> | |
| 170 <!-- in order of best FORWARD scoring when tested on /test/data/report_test_sets/(P2) Relative peak heights in spectra/Input (Test set 1) --> | |
| 171 <option value="SIM_INTENSITY" selected="true">SIM intensities</option> | |
| 172 <option value="MAX_INTENSITY">Maximum intensities</option> | |
| 173 <option value="CENTROTYPE_INTENSITY">Centrotype peak intensities</option> | |
| 174 <option value="MIC_INTENSITY">MIC intensities</option> | |
| 175 </param> | |
| 176 <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" > | |
| 177 <option value="MEMBERSHIP_BASED">Membership based (msclust 1.0 mode)</option> | |
| 178 <option value="CORRELATION_BASED" selected="true">Correlation based</option> | |
| 179 </param> | |
| 180 <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"> | |
| 181 <option value="" selected="true"></option> | |
| 182 <option value="uniqueSIM">Unique SIM peak</option> | |
| 183 <option value="sharedSIM">Shared SIM peak</option> | |
| 184 </param> | |
| 185 <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,...' " /> | |
| 186 <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 " /> | |
| 187 <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" /> | |
| 188 <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" /> | |
| 189 | |
| 190 <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 " /> | |
| 191 | |
| 192 </when> | |
| 19 | 193 <when value="No"> |
| 194 </when> | |
| 3 | 195 </conditional> |
| 196 | |
| 197 | |
| 198 </inputs> | |
| 199 <outputs> | |
| 200 <data name="centrotypesOut" format="msclust.csv" label="${tool.name} on ${on_string} - centrotypes file"/> | |
| 201 <data name="simOut" format="msclust.csv" label="${tool.name} on ${on_string} - SIM file"/> | |
| 202 <data name="micOut" format="msclust.csv" label="${tool.name} on ${on_string} - MIC file"/> | |
| 203 <data name="mspOut" format="msp" label="${tool.name} on ${on_string} - SPECTRA file"/> | |
| 204 <data name="classOut" format="msclust.csv" label="${tool.name} on ${on_string} - Classification file"/> | |
| 205 <data name="htmlReportFile" format="html" label="${tool.name} on ${on_string} - HTML report"> | |
| 206 <!-- If the expression is false, the file is not created --> | |
| 207 <filter>( summaryReport == True )</filter> | |
| 208 </data> | |
| 209 </outputs> | |
| 210 <tests> | |
| 211 <!-- find out how to use --> | |
| 212 </tests> | |
| 213 <help> | |
| 214 | |
| 215 <!-- see also http://docutils.sourceforge.net/docs/ref/rst/restructuredtext.html#hyperlink-targets --> | |
| 216 | |
| 217 .. class:: infomark | |
| 218 | |
| 219 This tool extracts spectra from ion-wise aligned MS(/MS) results. It uses expression profiles and | |
| 220 retention times of the putative ions to cluster them. Each cluster is then used to generate | |
| 221 one spectrum containing the clustered ions (peaks). | |
| 222 | |
| 4 | 223 .. image:: msclust_summary.png |
| 3 | 224 |
| 225 | |
| 226 ----- | |
| 227 | |
|
30
60b53f2aa48a
Small fixes, added microminutes support to MsClust, removed TIC or MsClust output
pieter.lukasse@wur.nl
parents:
29
diff
changeset
|
228 **Input** |
|
60b53f2aa48a
Small fixes, added microminutes support to MsClust, removed TIC or MsClust output
pieter.lukasse@wur.nl
parents:
29
diff
changeset
|
229 |
|
60b53f2aa48a
Small fixes, added microminutes support to MsClust, removed TIC or MsClust output
pieter.lukasse@wur.nl
parents:
29
diff
changeset
|
230 The input file should contain the following columns (in this order), followed by the sample intensity columns (one column with the |
|
60b53f2aa48a
Small fixes, added microminutes support to MsClust, removed TIC or MsClust output
pieter.lukasse@wur.nl
parents:
29
diff
changeset
|
231 intensity value for each sample): |
|
60b53f2aa48a
Small fixes, added microminutes support to MsClust, removed TIC or MsClust output
pieter.lukasse@wur.nl
parents:
29
diff
changeset
|
232 |
| 31 | 233 *ScanNR* |
| 234 | |
| 235 *Ret(umin)* | |
| 236 | |
| 237 *Mass(uD)* | |
| 238 | |
| 239 *(Optional)retentionMean* | |
| 240 | |
| 241 *(only required if retentionMean is present)retentionSD* | |
| 242 | |
| 243 *N sample intensity columns...* | |
| 244 | |
|
30
60b53f2aa48a
Small fixes, added microminutes support to MsClust, removed TIC or MsClust output
pieter.lukasse@wur.nl
parents:
29
diff
changeset
|
245 |
|
60b53f2aa48a
Small fixes, added microminutes support to MsClust, removed TIC or MsClust output
pieter.lukasse@wur.nl
parents:
29
diff
changeset
|
246 ----- |
|
60b53f2aa48a
Small fixes, added microminutes support to MsClust, removed TIC or MsClust output
pieter.lukasse@wur.nl
parents:
29
diff
changeset
|
247 |
| 3 | 248 **Output** |
| 249 | |
| 250 This tools returns a number of ouptut files and a small report. | |
| 251 | |
| 252 **Parameters index** | |
| 253 | |
| 254 | |
| 255 *Select the approach used for imputing missing values:* only select this if you have used a specific method to | |
| 256 fill in the data gaps in the input file. One example is replacing zero values by some randomly generated low value. | |
| 257 If MeTot is chosen, then a value is considered generated if: the value contains a dot '.' and some number | |
| 258 other than 0 (zero) after the dot. | |
| 259 | |
| 260 *Effective Peaks:* Neighborhood window size to consider when calculating density. Smaller values increase | |
| 261 performance but are less reliable. | |
| 262 | |
| 263 *Peak Width, in scans:* Scan window width of scans to consider 'close'. One can see this as the | |
| 264 'tolerated variation in scans' for the apex positions of the fragment peaks composing a cluster. | |
| 265 Note: if MetAlign was used, this is the variation *after* pre-processing by MetAlign. | |
| 266 | |
| 267 *Peak Width confidence:* The higher the confidence, the stricter the threshold. | |
| 268 | |
| 269 *Correlation threshold (0.0 - 1.0):* Tolerance center for pearson distance calculation. The higher this value, | |
| 270 the higher the correlation between 2 items has to be for them to be considered 'close'. | |
| 271 | |
| 272 *Correlation threshold confidence:* The higher the confidence, the stricter the threshold. `More...`__ | |
| 273 | |
| 274 *Potential Density reduction (0.0 - 1.0):* Reduction tolerance center for pearson distance calculation. | |
| 275 The higher this value, the less the low correlated items get reduced, getting a chance to form a cluster of their own. | |
| 276 | |
| 277 *Potential Density reduction softness:* Reduction curve slope for pearson distance tolerance. Lower | |
| 278 values = stricter separation at the value determined in 'Potential Density reduction' above | |
| 279 (TODO review this comment). | |
| 280 | |
| 281 *Stop Criterion:* When to stop reducing and looking for new clusters. Lower values = more iterations | |
| 282 | |
| 13 | 283 .. __: javascript:window.open('.. image:: confidence_and_slope_params_explain.png'.replace('.. image:: ', ''),'popUpWindow','height=700,width=800,left=10,top=10,resizable=yes,scrollbars=yes,toolbar=yes,menubar=no,location=no,directories=no,status=yes') |
| 3 | 284 |
| 285 | |
| 286 ----- | |
| 287 | |
| 288 **Output files described below** | |
| 289 | |
| 290 ----- | |
| 291 | |
| 292 *SPECTRA:* this file can be submitted to NIST for identification of the spectra. | |
| 293 | |
| 294 `Click here for more details on the Sample selection and Spectrum peak intensity correction algorithm parameters related to SPECTRA generation`_ | |
| 295 | |
| 14 | 296 .. _Click here for more details on the Sample selection and Spectrum peak intensity correction algorithm parameters related to SPECTRA generation: javascript:window.open('.. image:: sample_sel_and_peak_height_correction.png'.replace('.. image:: ', ''),'popUpWindow','height=700,width=800,left=10,top=10,resizable=yes,scrollbars=yes,toolbar=yes,menubar=no,location=no,directories=no,status=yes') |
| 3 | 297 |
| 298 ----- | |
| 299 | |
| 300 *MIC:* stands for Measured Ions Count -> it contains, for each cluster, the sum of the ion count | |
| 301 values (corrected by their membership) for all MEASURED cluster ions in the given sample. | |
| 302 | |
| 303 The MIC for a **cluster i** in **sample s**, where **cluster i** has **n** members is thus: | |
| 304 | |
| 305 sum ( [intensity of member n in **sample s**] x [membership value of member n in **cluster i** ] ) | |
| 306 | |
| 307 ----- | |
| 308 | |
| 309 *SIM:* stands for Selective Ion Mode -> it contains, for each cluster, the intensity values of the | |
| 310 most representative member ion peak of this cluster. The most representative member peak is the one with the | |
| 311 highest membership*average_intensity. This definition leads to conflicts as a peak can have a | |
| 312 membership in two or more clusters. The assignment of a SIM peak to a cluster depends on | |
| 313 the configured data type (LC or GC-MS). NB: this can be overruled in the "advanced settings": | |
| 314 | |
| 315 (1) LC-MS SIM: select SIM peak only once and for the centrotype in which this specific mass has its | |
| 316 highest membership; for neighboring centrotypes use its "second best SIM", etcetera. In other words, | |
| 317 if the SIM peak has been identified as the SIM in more than 1 cluster, assign as SIM to the cluster | |
| 318 with highest membership. Continue searching for other SIM peaks to assign to the other clusters until | |
| 319 all ambiguities are solved. | |
| 320 | |
| 321 (2) GC-MS SIM: the SIM peak can be "shared" by multiple clusters. However, the intensity values are corrected | |
| 322 by the membership value of the peak in the cluster in case the SIM peak is "shared". If the SIM peak is not | |
| 323 "shared" then the "raw" intensity values of the SIM peak are recorded in the SIM file. | |
| 324 | |
| 325 `Click here for more details on the SIM output file`_ | |
| 326 | |
| 15 | 327 .. _Click here for more details on the SIM output file: javascript:window.open('.. image:: sample_SIM.png'.replace('.. image:: ', ''),'popUpWindow','height=700,width=800,left=10,top=10,resizable=yes,scrollbars=yes,toolbar=yes,menubar=no,location=no,directories=no,status=yes') |
| 3 | 328 |
| 329 | |
| 330 | |
| 331 </help> | |
| 332 </tool> |