Example of a Workflow

The example workflow XML file below can be used to run the provided example data set of spiked urine samples at different concentration levels with the mzMine homogenous data processing workflow.

<?xml version="1.0" encoding="UTF-8"?>
<WorkFlow baseOutputDir="/home/bhoekman/my_workflow"> 
<!--“baseOutputDir” attribute defines the directory in which the output files of the modules will be placed -->

<!--“Files” element provides the list of initial input files for the workflow. -->
	<!-- Set of files which are analyzed together to provide one matched feature matrix-->
	<FileSet name="choose name">
		<File class="0" input="/home/bhoekman/data/0810P055.mzXML"/>
		<File class="0" input="/home/bhoekman/data/0810P175.mzXML"/>
		<File class="0" input="/home/bhoekman/data/0810P155.mzXML"/>
		<File class="0" input="/home/bhoekman/data/0810P191.mzXML"/>
		<File class="0" input="/home/bhoekman/data/0810P213.mzXML"/>

		<File class="1" input="/home/bhoekman/data/0810P086.mzXML"/>
		<File class="1" input="/home/bhoekman/data/0810P019.mzXML"/>
		<File class="1" input="/home/bhoekman/data/0810P132.mzXML"/>
		<File class="1" input="/home/bhoekman/data/0810P073.mzXML"/>
		<File class="1" input="/home/bhoekman/data/0810P034.mzXML"/>
<!-- LC-MS chromatograms of samples from different class should be numbered from 0 to n-1, where n is the number of classes. This field can be omitted if there is just one class-->
<!-- the input files should compatible with the input format of the first module, which are mzXML or a mzXML.gz (gzipped) files in case of feature quantification -->
	<!-- Additional FileSets can be added without any limitation, however up to 4 FileSets are run in parallel. -->

<!-- Modules with data and parameters defined in this section will be executed in sequential order. -->

<Program program="MZmine" method="MZmine_peakPicking" format="normal">
<!--This part lists the parameters to run the feature quantification module of MZmine -->
		<FileRef initialFiles="true" program="" method=""/>
<!--When “initialFiles” attribute is true the workflow will use file sets defined under “Files” element. When “initialFiles” attribute  is false then the module is using the output from a previous module with the same “program” and “method” attribute value provided in the “Program” element of a previous modules. -->
		<Attribute attributeName="smoothing"
		<Attribute attributeName="smoothing_mzTolerance" value="0.1"/>
		<Attribute attributeName="smoothing_oneSidedWindowLength" value="5"/>
		<Attribute attributeName="intTolerance" value="0.50"/>
		<Attribute attributeName="mzTolerance" value="1"/>
		<Attribute attributeName="maximumMZPeakWidth" value="5"/>
		<Attribute attributeName="noiseLevel" value="3"/>
		<Attribute attributeName="minimumPeakDuration" value="10"/>
		<Attribute attributeName="minimumPeakHeight" value="100"/>
		<Attribute attributeName="peakPickerAlgorithm"
		<Attribute attributeName="binSize" value="0.1"/>
		<Attribute attributeName="chromatographicThresholdLevel" value="0"/>
		<Attribute attributeName="minimumMZPeakWidth" value="0.1"/>

	<!--“Pramaters” elements contains the parameters settings for the MZmine feature quantification module. The names of the parameters reflect those defined in the MZmine GUI. -->

		<Attribute attributeName="transformationFileLocation" 

<!-- The file specified here contains the set of rules, which convert the output of MZmine feature quantification modules to make it compatible with the feature matching modules of the other modules (see for more details Interconnecting data processing modules in the Material and Method) -->

<Program program="filterPeakList" method="filterPeakList" format="normal" >
		<FileRef initialFiles="false" program="MZmine" 
<!-- this part instruct the framework to use the output of the previous module -->
		<Attribute attributeName="filterListLocation" 
		<!-- Parameter file specifying the filtering rules of the feature list, which are used for feature matching modules (see Figure 1. in the article) -->

<Program program="mzMine" method="MZmine_consensusMap" format="normal">
<!--This part lists the parameters to run the feature matching module of MZmine -->
		<FileRef initialFiles="false" program="filterPeakList" 
		<Attribute attributeName="alignmentAlgorithm" value="JoinAligner"/>
		<Attribute attributeName="alignMZvsRTBalance" value="0.5"/>
		<Attribute attributeName="alignMZTolerance" value="0.1"/>		
		<Attribute attributeName="alignRTToleranceUseAbs" value="0.20"/>
		<Attribute attributeName="alignRTToleranceAbs" value="1"/>		
		<Attribute attributeName="alignRTTolerancePercent" value="0.1"/>

<Program program="exportPeakMatrix" method="exportPeakMatrixToTab" format="normal">
<!--This part instruct mzCompare to export the matched feature matrix in tab deliminated format -->
		<FileRef initialFiles="false" program="mzMine"
		<Attribute attributeName="tabExportSettingsFile"
<!-- File containing a set of rules describing, how to export matched feature matrix as a tab-delimited file. The exported tab delimited file can be used for statistical analysis. -->

<Program program="makeROC" method="makeROC" format="normal" runThis="true">
<!--Module executing the quality score function on the matched feature matrix (see equation 1 in Supplementary material). -->

		<FileRef initialFiles="false" program="mzMine"
		<Attribute attributeName="mzSpike1" value="506.65"/> 
		<Attribute attributeName="rtSpike1" value="1890"/>       

		<Attribute attributeName="mzSpike2" value="344.94"/> 
		<Attribute attributeName="rtSpike2" value="2070"/>       

		<Attribute attributeName="mzSpike3" value="338.46"/> 
		<Attribute attributeName="rtSpike3" value="2070"/>       

<!-- m/z, retention time values of feature corresponding to the spiked peptides. -->

		<Attribute attributeName="rtWindow" value="90"/>
		<Attribute attributeName="mzWindow" value="1"/>

	<!--“mzWindow” and “rtWindow” attributes defining the search range to identify feature of standard peaks used for spiking in the matched feature matrix. -->
		<Attribute attributeName="lookForIsotopes" value="true"/>
		<Attribute attributeName="rtWindowIsotope" value="6"/>
		<Attribute attributeName="mzWindowIsotope" value="0.1"/>
<!-- "lookForIsotopes" attributes determines if all isotopes (false) or only the feature having the monoisotopic mass (true) should be considered in the quality scoring function. "rtWindowIsotope" and "mzWindowIsotope" attribute determines the retention time and m/z ranges to identify features, which are the isotopes of the same compound with given charge state. -->

		<Attribute attributeName="mzName" value="mz"/>
		<Attribute attributeName="rtName" value="rt"/>
		<Attribute attributeName="statisticalTestName" value="area"/>
<!--Attributes "mzName", "rtName" and "statisticalTestName" are used to match the filed name in the matched feature matrix to identify the retention time, mz value and the type of quantification (peak height, area or volume) as this is the input of the quality score function. -->

		<Attribute attributeName="rtMin" value="1800"/>
		<Attribute attributeName="rtMax" value="4800"/>
		<Attribute attributeName="mzMin" value="285"/>
<!-- Retention time and m/z region, where matched features are considered to be used by the quality score function. -->

		<Attribute attributeName="tabExportSettingsFile"
<!-- File containing a set of rules describing, how to export matched feature matrix as a tab-delimited file. -->

Last modified 9 years ago Last modified on Jun 9, 2010, 3:09:40 PM