diff metams_lcms_pick_and_group.xml @ 49:f772a5caa86a

Added more options and better documentation. Added MsClust support for parsing XCMS alignment results. Improved output reports for XCMS wrappers. New tools.

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/metams_lcms_pick_and_group.xml	Wed Dec 10 22:03:27 2014 +0100
@@ -0,0 +1,296 @@
+<tool id="metams_lcms_pick_and_group" name="METAMS-LC/MS Pick, Align and Group"  version="0.0.4">
+	<description> Runs metaMS process for LC/MS feature picking, aligning and grouping</description>
+	<requirements>
+		<requirement type="package" version="3.1.1">R_bioc_metams</requirement>
+	</requirements>	
+	<command interpreter="Rscript">
+		metaMS_cmd_pick_and_group.r 
+	    $data_files
+	    $customMetaMSsettings
+	    $outputFile 
+	    $xsetOut
+	    $htmlReportFile
+	    $htmlReportFile.files_path
+	    $outputLog
+	</command>
+<inputs>
+	<param name="data_files" type="data" format="prims.fileset.zip" label="Data files (.zip file with CDF, mzML or mzXML files)" help=".zip file containing the CDF, mzML or mzXML files of the new measurements"/>
+	
+	<param name="protocolName" type="text" size="30" label="protocolName" value="e.g. Synapt.QTOF.RP" 
+		help="Choose a name to give for the specific settings in the parameters below"/><!-- TODO - let user choose this -->
+	
+	
+	<!-- ===========NB : if peak picking, alignment OR CAMERA settings have to be reused for runGC wrapper in the future, we can use Galaxy macro expansions here
+	                     to avoid defining these parameters again in the runGC wrapper ========================= -->
+	<conditional name="peakPicking">
+		<param name="method" type="select" size="30" label="PEAK PICKING method ====================================================="
+		help="matchedFilter=Feature detection in the chromatographic time domain ; centWave=Feature detection for high resolution LC/MS data">
+			<option value="matchedFilter" selected="true">matchedFilter</option>
+			<option value="centWave" >centWave</option>
+		</param>
+		<when value="matchedFilter">	
+			<param name="fwhm" type="integer" size="10" value="20" label="fwhm" 
+			help="full width at half maximum of matched filtration gaussian model peak. Only used to calculate the actual sigma" />
+			<param name="sigma_denom" type="float" size="10" value="2.3548" label="sigma_denominator" 
+			help="denominator for standard deviation (width) of matched filtration model peak (e.g. sigma = fwhm/2.3548)" />
+			<param name="max" type="integer" size="10" value="50" label="max" 
+			help="maximum number of peaks per extracted ion chromatogram" />
+			<param name="snthresh" type="integer" size="10" value="4" label="snthresh" 
+			help="signal to noise ratio cutoff" />
+			<param name="step" type="float" size="10" value="0.05" label="step" 
+			help="step size to use for profile generation"/>
+			<param name="steps" type="integer" size="10" value="2" label="steps" 
+			help="number of steps to merge prior to filtration"/>
+			<param name="mzdiff" type="float" size="10" value="0.8" label="mzdiff" 
+			help="minimum difference in m/z for peaks with overlapping retention times"/>
+		</when>
+		<when value="centWave">
+			<param name="ppm" type="integer" size="10" value="25" label="ppm" 
+			help="maxmial tolerated m/z deviation in consecutive scans, in ppm" />
+			<param name="peakwidth" type="text" size="10" value="20,50" label="peakwidth" 
+			help="Chromatographic peak width, given as range (min,max) in seconds" />
+			<param name="snthresh" type="integer" size="10" value="10" label="snthresh" 
+			help="signal to noise ratio cutoff" />			
+			<param name="prefilter" type="text" size="10" value="3,100" label="prefilter=c(k,I)" 
+				help="Prefilter step for the first phase. Mass traces are only retained if 
+				they contain at least k peaks with intensity &gt; = I" />			
+			<param name="mzCenterFun" type="select" size="30" label="mzCenterFun" 
+				help="Function to calculate the m/z center of the feature: wMean intensity weighted mean of the 
+				feature m/z values, mean mean of the feature m/z values, apex use m/z value at peak apex, 
+				wMeanApex3 intensity weighted mean of the m/z value at peak apex and the m/z value left and 
+				right of it, meanApex3 mean of the m/z value at peak apex and the m/z value left and right of it">
+				<option value="wMean" selected="true">wMean</option>
+				<option value="mean" >mean</option>
+				<option value="apex" >apex</option>
+				<option value="wMeanApex3" >wMeanApex3</option>
+				<option value="meanApex3" >meanApex3</option>
+			</param>
+			<param name="integrate" type="select" size="30" label="integrate" 
+				help="Integration method. If =1 peak limits are found through descent 
+				on the mexican hat filtered data, if =2 the descent is done on the real data. 
+				Method 2 is very accurate but prone to noise, while method 1 is more robust to noise but less exact">
+				<option value="1" selected="true">1</option>
+				<option value="2" >2</option>
+			</param>
+			<param name="mzdiff" type="float" size="10" value="-0.001" label="mzdiff" 
+				help="minimum difference in m/z for peaks with overlapping retention times, can be negative to allow overlap" />
+			<param name="fitgauss" type="integer" size="10" value="20" label="fitgauss" 
+				help="logical, if Yes: a Gaussian is fitted to each peak" >
+				<option value="TRUE" selected="true">Yes</option>
+				<option value="FALSE" >No</option>
+			</param>
+			<param name="noise" type="integer" size="10" value="0" label="noise" 
+				help="optional argument which is useful for data that was centroided without any intensity
+				 threshold, centroids with intensity &lt; noise are omitted from ROI detection" />
+		</when>
+	</conditional>
+
+	
+	<param name="min_class_fraction" type="float" size="10" value="0.3" label="ALIGNMENT min.class.fraction =====================================================" 
+		    help="Minimum fraction of samples necessary in the alignment to make it a valid alignment/group"/>
+	<param name="min_class_size" type="integer" size="10" value="3" label="min.class.size" 
+			help="Minimum number of samples necessary in the alignment to make it a valid alignment/group. The lowest criteria
+			between this and min.class.fraction will be used." />
+	<param name="mzwid" type="float" size="10" value="0.1" label="mzwid" 
+			help="width of overlapping m/z slices to use for creating peak density chromatograms and grouping peaks across samples"/>
+	<param name="bws" type="text" size="10" value="30,10" label="bws" 
+			help="bandwidth (standard deviation or half width at half maximum) of gaussian smoothing kernel 
+			to apply to the peak density chromatogram. Fill in two values separated by comma. First value is used for 
+			first grouping round, seccond value is used for last grouping/alignment round after retention time
+			correction. "/>
+	
+	<conditional name="retcor">
+		<param name="retcormethod" type="select" size="30" label="retcormethod" 
+			help="retention time correction method. 'peakgroups' is the default density based approach, 'obiwarp' is 
+			  alignment data by Ordered Bijective Interpolated Warping ">
+			<option value="peakgroups" selected="true">peakgroups</option>
+			<option value="obiwarp" >obiwarp</option>
+		</param>
+		<when value="peakgroups">
+			<param name="retcorfamily" type="select" size="30" label="retcorfamily" 
+				help="retention time correction method type/family">
+				<option value="symmetric" selected="true">symmetric</option>
+				<option value="gaussian">gaussian</option>
+			</param>
+			<param name="smooth" type="select" size="30" label="smooth" 
+				help="either 'loess' for non-linear alignment or 'linear' for linear alignment">
+				<option value="linear" selected="true">linear</option>
+				<option value="loess">loess (TODO - waiting for metaMS to add/parse this option)</option>
+			</param>
+			<param name="missingratio" type="float" size="10" value="0.2" label="missingratio" 
+				help="ratio of missing samples to allow in retention time correction groups"/>
+			<param name="extraratio" type="float" size="10" value="0.1" label="extraratio" 
+				help="ratio of extra peaks to allow in retention time correction correction groups"/>
+		</when>
+		<when value="obiwarp">
+			<param name="profStep" type="integer" size="10" value="1" label="profStep" 
+				help="step size (in m/z) to use for profile generation from the raw data files" />
+		</when>
+	</conditional>
+		
+	<param name="fillPeaks" type="select" size="30" label="fillPeaks" 
+		help="Fill missing peaks in peak groups/alignments that do not include peaks from every sample. 
+		This method produces intensity values for those missing samples by integrating raw data in peak group region.">
+		<option value="TRUE" selected="true">Yes</option>
+		<option value="FALSE">No</option>
+	</param>
+	<param name="perfwhm" type="float" size="10" value="0.6" label="CAMERA perfwhm =====================================================" 
+		help="percentage of FWHM width"/>
+	<param name="cor_eic_th" type="float" size="10" value="0.7" label="cor_eic_th" 
+		help="correlation threshold (0..1)" />
+	<param name="ppm" type="float" size="10" value="5.0" label="ppm" 
+		help="General ppm error" />
+	
+	<param name="groupCorr_graphMethod" type="select" size="30" label="(groupCorr)graphMethod" 
+		help="Method selection for grouping peaks after correlation analysis into pseudospectra.">
+		<option value="hcs" selected="true">hcs</option>
+	</param>
+		
+	<param name="groupCorr_pval" type="float" size="10" value="0.05" label="(groupCorr)pval" 
+		help="significant correlation threshold" />	
+
+	<param name="groupCorr_calcCiS" type="select" size="30" label="(groupCorr)calcCiS" 
+		help="Use correlation inside samples for peak grouping">
+		<option value="TRUE" selected="true">Yes</option>
+		<option value="FALSE">No</option>
+	</param>
+	
+	<param name="groupCorr_calcIso" type="select" size="30" label="(groupCorr)calcIso" 
+		help="Use isotopic relationship for peak grouping">
+		<option value="TRUE" >Yes</option>
+		<option value="FALSE" selected="true">No</option>
+	</param>
+	
+	<param name="groupCorr_calcCaS" type="select" size="30" label="(groupCorr)calcCaS" 
+		help="Use correlation across samples for peak grouping">
+		<option value="TRUE" >Yes</option>
+		<option value="FALSE" selected="true">No</option>
+	</param>
+	
+	
+	<param name="findIsotopes_maxcharge" type="integer" size="10" value="3" label="(findIsotopes)maxcharge" 
+			help="max. ion charge" />
+			
+	<param name="findIsotopes_maxiso" type="integer" size="10" value="4" label="(findIsotopes)maxiso" 
+			help="max. number of expected isotopes" />	
+			
+	<param name="findIsotopes_minfrac" type="float" size="10" value="0.5" label="(findIsotopes)minfrac" 
+		help="The ratio for the number of samples, which must satisfy the C12/C13 rule for isotope annotation" />					
+	
+	<param name="findAdducts_polarity" type="select" size="30" label="(findAdducts)polarity" 
+		help="Which polarity mode was used for measuring of the ms sample">
+		<option value="positive" selected="true">positive</option>
+		<option value="negative" >negative</option>
+	</param>
+
+	<param name="findAdducts_multiplier" type="integer" size="10" value="3" label="(findAdducts)multiplier" 
+			help="If no ruleset is provided, calculate ruleset with max. number n of [nM+x] clusterions" />
+
+
+	
+</inputs>
+<configfiles>
+
+<configfile name="customMetaMSsettings">## ====================================
+		## metaMS process settings
+		customMetaMSsettings &lt;- metaMSsettings(protocolName = "${protocolName}",
+                            chrom = "LC",
+                            PeakPicking = list(
+                              method = "${peakPicking.method}",
+							#if $peakPicking.method == "matchedFilter"  
+								fwhm = ${peakPicking.fwhm},
+								sigma = ${peakPicking.fwhm}/${peakPicking.sigma_denom},
+								max = ${peakPicking.max},
+								snthresh = ${peakPicking.snthresh},
+								step = ${peakPicking.step},
+								steps = ${peakPicking.steps},
+								mzdiff = ${peakPicking.mzdiff}),
+							#else 
+								ppm = ${peakPicking.ppm},
+								peakwidth = c(${peakPicking.peakwidth}),
+								snthresh = ${peakPicking.snthresh},
+								prefilter = c(${peakPicking.prefilter}),
+								mzCenterFun = "${peakPicking.mzCenterFun}",
+								integrate = ${peakPicking.integrate},
+								mzdiff = ${peakPicking.mzdiff},
+								fitgauss = ${peakPicking.fitgauss},
+								noise = ${peakPicking.noise}),
+							#end if
+                            Alignment = list(
+                              min.class.fraction = ${min_class_fraction},
+                              min.class.size = ${min_class_size},
+                              mzwid = ${mzwid},
+                              bws = c(${bws}),
+                              retcormethod = "${retcor.retcormethod}",
+							#if $retcor.retcormethod == "peakgroups"
+                           		smooth = "${retcor.smooth}",
+                            	missingratio = ${retcor.missingratio},
+                            	extraratio = ${retcor.extraratio},
+                            	retcorfamily = "${retcor.retcorfamily}",            
+							#else
+								##repeating the method as workaround/ backwards compatibility (can remove this one after fix from metaMS):
+								method = "${retcor.retcormethod}", 
+								profStep = ${retcor.profStep},
+							#end if								                             
+                              fillPeaks = ${fillPeaks}),
+                            CAMERA = list(
+                              perfwhm = ${perfwhm},
+                              cor_eic_th = ${cor_eic_th},
+                              ppm= ${ppm},
+                              graphMethod= "${groupCorr_graphMethod}",
+                              pval= ${groupCorr_pval},
+                              calcCiS= ${groupCorr_calcCiS},
+                              calcIso= ${groupCorr_calcIso},
+                              calcCaS= ${groupCorr_calcCaS},
+                              maxcharge= ${findIsotopes_maxcharge},
+                              maxiso= ${findIsotopes_maxiso},
+                              minfrac= ${findIsotopes_minfrac},
+                              polarity= "${findAdducts_polarity}",
+                              multiplier= ${findAdducts_multiplier}
+                              ))</configfile>
+
+</configfiles>
+
+<outputs>
+	<data name="outputFile" format="tabular" label="${tool.name} on ${on_string} - peaks table (TSV)"/>
+	<data name="outputLog" format="txt" label="${tool.name} on ${on_string} - LOG" hidden="True"/>
+	<data name="xsetOut" format="rdata" label="${tool.name} on ${on_string} - xcmsSet (RDATA)"/>
+	<data name="htmlReportFile" format="html" label="${tool.name} on ${on_string} - report (HTML)"/>
+</outputs>
+<tests>
+	<test>
+	</test>
+</tests>
+<help>
+
+.. class:: infomark
+  
+Runs metaMS process for LC/MS feature feature picking, aligning and grouping. 
+This part of the metaMS process makes use of the XCMS and CAMERA tools and algorithms.
+CAMERA is used for automatic deconvolution/annotation of LC/ESI-MS data.
+The figure below shows the main parts of the metaMS process. 
+
+.. image:: $PATH_TO_IMAGES/metaMS.png 
+
+
+**References**
+
+If you use this Galaxy tool in work leading to a scientific publication please
+cite the following papers:
+
+Wehrens, R.; Weingart, G.; Mattivi, F. (2014). 
+metaMS: an open-source pipeline for GC-MS-based untargeted metabolomics. 
+Journal of chromatography B: biomedical sciences and applications, 996 (1): 109-116. 
+doi: 10.1016/j.jchromb.2014.02.051 
+handle: http://hdl.handle.net/10449/24012
+
+Wrapper by Pieter Lukasse.
+
+
+  </help>
+  <citations>
+        <citation type="doi">10.1016/j.jchromb.2014.02.051</citation> <!-- example 
+        see also https://wiki.galaxyproject.org/Admin/Tools/ToolConfigSyntax#A.3Ccitations.3E_tag_set
+        -->
+   </citations>
+</tool>
\ No newline at end of file