changeset 5:7f432d87c82c draft

"planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/maxquant commit dad20a951ffa71a4b98fd851e496b50cd423e0a3"
author galaxyp
date Wed, 15 Apr 2020 11:17:42 -0400
parents dcd39bcc7481
children 2133b0be850a
files macros.xml maxquant.xml
diffstat 2 files changed, 68 insertions(+), 46 deletions(-) [+]
line wrap: on
line diff
--- a/macros.xml	Sat Apr 11 11:49:19 2020 -0400
+++ b/macros.xml	Wed Apr 15 11:17:42 2020 -0400
@@ -133,7 +133,7 @@
 
     <xml name="ptxqc-opts">
         <conditional name="qc">
-            <param name="do_it" label="Generate PTXQC (proteomics quality control pipeline) report? (at own risk)"
+            <param name="do_it" label="Generate PTXQC (proteomics quality control pipeline) report? (experimental setting)"
                    type="boolean" checked="false"/>
             <when value="true">
                 <param name="parameters" type="boolean" checked="true"
--- a/maxquant.xml	Sat Apr 11 11:49:19 2020 -0400
+++ b/maxquant.xml	Wed Apr 15 11:17:42 2020 -0400
@@ -227,7 +227,7 @@
             </param>
             <param name="description_parse_rule" type="text"
                    label="description parse rule" value="^&gt;.*\|.*\|[^ ]+ (.*) OS.*$"
-                   help="Modify parse rules if needed">
+                   help="Modify parse rules if needed.">
                 <sanitizer>
                     <valid initial="string.printable">
                         <remove value="&apos;"/>
@@ -241,37 +241,44 @@
                    label="Specify an experimental design template (if needed). For detailed
                           instructions see the help text." />
             <param type="integer" name="min_peptide_len"
-	           label="minimum peptide length" value="7"/>
+	           label="minimum peptide length" value="7"
+                help="Peptides shorter than this value will not be reported nor be considered during protein identification and quantification 
+short peptides are usually not unique in the protein database and therefore not statistically informative."/>
             <param type="integer" name="max_peptide_mass"
-	           label="maximum peptide mass" value="4600"/>
+	           label="maximum peptide mass [Da]" value="4600"
+        help="Peptides that are heavier than this mass will be discarded in the Andromeda search."/>
             <param type="integer" name="min_unique_pep"
-	           label="minimum unique peptides" value="0" />
+	           label="minimum unique peptides" value="0" 
+        help="The minimum number of unique peptides a protein group should have to be considered as identified and reported in the final table." />
             <param name="calc_peak_properties" type="boolean" checked="false"
-	           label="Calculate peak properties?"
-	           truevalue="True" falsevalue="False" />
+	           label="Calculate peak properties"
+	           truevalue="True" falsevalue="False" 
+        help="If checked, several quantities characterizing peaks and isotopes patterns are calculated. This may lead to a substantial increase in computation time."/>
             <param name="match_between_runs" type="boolean" checked="false"
-	           label="Match between runs?"
-	           truevalue="True" falsevalue="False" />
+	           label="Match between runs"
+	           truevalue="True" falsevalue="False" 
+        help="Identifications are transferred to non-sequenced or non-identified MS features in other LC-MS runs."/>
         </section>
         
         <repeat name="paramGroups" title="Parameter Group" min="1" default="1">
             <param type="data" format="thermo.raw,mzXML,mzML" name="files" label="Infiles" multiple="true"
                    help="Only select infiles matching the filetype specified in the input options."/>
             <param type="integer" name="maxMissedCleavages"
-	           label="missed cleavages" value="2"/>
+	           label="missed cleavages" value="2"
+         help="The number of missed cleavages that are maximally tolerated in the in-silico digestion of the protien sequences."/>
             <param name="fixedModifications" type="select" label="fixed modifications"
-	           multiple="true" help="select zero or more fixed modifications">
+	           multiple="true" help="Select zero or more fixed modifications. They will always be attached to any occurence of the respective amino acid.">
 	        <expand macro="modification"/>
                 <expand macro="default_mod_option" value="Carbamidomethyl (C)"/>
             </param>
             <param name="variableModifications" type="select" label="variable modifications"
-	           multiple="true" help="select zero or more variable modifications">
+	           multiple="true" help="Select zero or more variable modifications. Do not specify label modifications here, neither ms1 level labels, like SILAC, nor isobaric labels.">
                 <expand macro="default_mod_option" value="Oxidation (M)"/>
                 <expand macro="default_mod_option" value="Acetyl (Protein N-term)"/>
 	        <expand macro="modification"/>
             </param>
-            <param name="enzymes" type="select" label="proteases"
-	           multiple="true" help="select zero or more proteases">
+            <param name="enzymes" type="select" label="enzyme"
+	           multiple="true" help="Select zero or more enzymes. The enzymes used for generating the in silico peptides for the Andromeda search.">
                 <expand macro="default_mod_option" value="Trypsin/P"/>
 	        <expand macro="proteases"/>
             </param>
@@ -280,34 +287,38 @@
                        help="Select a method if needed.">
                     <option value="">None</option>
                     <option value="lfq">label free quantification</option>
-                    <option value="silac">label based quantification (SILAC)</option>
+                    <option value="silac">label based quantification</option>
                     <option value="reporter_ion_ms2">reporter ion MS2</option>
                 </param>
                 <when value=""/>
                 <when value="silac">
 	            <param name="light_labels" type="select" label="light labels"
-		           multiple="true" help="select zero or more light modifications">
+		           multiple="true" help="Select zero or more light modifications.">
 	                <expand macro="label"/>
 	            </param>
 	            <param name="medium_labels" type="select" label="medium labels"
-		           multiple="true" help="select zero or more medium modifications">
+		           multiple="true" help="Select zero modifications if you have two labels. Select a medium modification if you have three labels.">
 	                <expand macro="label"/>
 	            </param>
 	            <param name="heavy_labels" type="select" label="heavy labels"
-		           multiple="true" help="select zero or more heavy modifications">
+		           multiple="true" help="Select zero or more heavy modifications.">
 	                <expand macro="label"/>
 	            </param>
                 </when>
                 <when value="lfq">
 		    <param type="integer" name="lfqMinRatioCount"
-		           label="LFQ minimum ratio count" value="2"/>
+		           label="LFQ minimum ratio count" value="2"
+                   help="Minimum number of peptides that has to be available in pair-wise comparisons between two samples for a protein."/>
 		    <param type="integer" name="lfqMinEdgesPerNode"
-			   label="LFQ minimum number of neighbours" value="3"/>
+			   label="LFQ minimum number of neighbours" value="3"
+               help="Defines the network to normalize the samples in the fast LFQ mode."/>
 		    <param type="integer" name="lfqAvEdgesPerNode"
-			   label="LFQ average number of neighbours" value="6"/>
+			   label="LFQ average number of neighbours" value="6"
+               help="Defines the network to normalize the samples in the fast LFQ mode."/>
 		    <param type="boolean" name="lfqSkipNorm" checked="true"
-			   label="Skip normalization?"
-			   truevalue="True" falsevalue="False" />
+			   label="Skip normalization"
+			   truevalue="True" falsevalue="False" 
+               help="If checked the high-speed version of MaxLFQ is used. This is recommended for large numbers of samples (Experiments). For less than 10 samples the original MaxLFQ normalization algorithm is used."/>
                 </when>
                 <when value="reporter_ion_ms2">
                     <conditional name="iso_labels">
@@ -333,10 +344,10 @@
                         <when value="iodotmt6plex"></when>
                         <when value="custom">
                             <repeat name="iso_label" title="Isobaric Label" min="1" default="1">
-                                <param name="internallabel" type="select" label="internal label">
+                                <param name="internallabel" type="select" label="internal label" help="contains Lys">
 	                            <expand macro="iso_labels"/>
 	                        </param>
-                                <param name="terminallabel" type="select" label="terminal label">
+                                <param name="terminallabel" type="select" label="terminal label" help="contains Nter">
                                     <option value="">None</option>
 	                            <expand macro="iso_labels"/>
 	                        </param>
@@ -356,29 +367,32 @@
 
         <section title="LFQ Options" name="lfq_opts" expanded="false">
 	    <param name="separateLfq" type="boolean" checked="false"
-		   label="Separate LFQ in parameter Groups?"
-		   truevalue="True" falsevalue="False" />
+		   label="Separate LFQ in parameter Groups"
+		   truevalue="True" falsevalue="False" 
+           help="The MaxLFQ algorithm will be applied independently to samples in different parameter groups."/>
 	    <param name="lfqStabilizeLargeRatios" type="boolean" checked="true"
-		   label="Stabilize large LFQ ratios?"
-		   truevalue="True" falsevalue="False" />
+		   label="Stabilize large LFQ ratios"
+		   truevalue="True" falsevalue="False" 
+           help="Large protein ratios will get an admixture of the total protein intensity ratio as described in the MaxLFQ paper"/>
 	    <param name="lfqRequireMsms" type="boolean" checked="true"
-		   label="Require MS/MS for LFQ comparisons?"
-		   truevalue="True" falsevalue="False" />
+		   label="Require MS/MS for LFQ comparisons"
+		   truevalue="True" falsevalue="False" 
+           help="Requires for each pari-wise peptide intensity comparison that at least one of two peptides has been identified by MS/MS"/>
 	    <conditional name="do_ibaq">
-                <param name="ibaq" type="select" label="iBAQ?">
+                <param name="ibaq" type="select" label="iBAQ (calculates absolute protein abundances by normalizing to copy number and not protein mass)">
                     <option value="False">No</option>
                     <option value="True">Yes</option>
 		</param>
                 <when value="True">
                     <param name="ibaqLogFit" type="boolean" checked="true"
-                           label="Logarithmic fit?"
+                           label="Logarithmic fit"
                            truevalue="True" falsevalue="False" />
                 </when>
                 <when value="False">
                 </when>
 	    </conditional>
 	    <param name="advancedSiteIntensities" type="boolean" checked="true"
-		   label="Advanced site intensities?"
+		   label="Advanced site intensities"
 		   truevalue="True" falsevalue="False" />
         </section>
 
@@ -539,15 +553,18 @@
     <help><![CDATA[
 MaxQuant is a quantitative proteomics software package designed for analyzing large mass-spectrometric data sets. 
 
-This tool is a wrapper for MaxQuant v@VERSION@. The current version of the wrapper only supports a very reduced set of search parameters, but another version of the tool that gets its parameters directly from a mqpar.xml file is available, too. If possible, this tool should be preferred. 
+This tool is a wrapper for MaxQuant v@VERSION@. The current version of the wrapper only supports a reduced set of parameters, but another version of the tool that gets its parameters directly from a mqpar.xml file is available, too.
 
 **Input files**
 
-- Thermo raw files or mzXML files (in parameter group section):
-    - The datatype of all files has to be either 'thermo.raw' or 'mzXML'. Make sure to specify the correct datatype either during upload to Galaxy or afterwards (edit attributes --> datatypes)
-- Fasta files: specify parse rules accordingly, default rules are compatible with uniprot
+- Thermo raw, mzML, mzXMLfiles (in parameter group section)
+
+    - The datatype of all files has to be either 'thermo.raw', 'mzML' or 'mzXML'. Make sure to specify the correct datatype either during upload to Galaxy or afterwards (edit attributes --> datatypes)
+- Fasta file: specify parse rules accordingly, default rules are compatible with uniprot
 - Optional files:
+
     - Tabular file with experimental design template:
+
         - Currently four columns are needed: Name, Fraction, Experiment and PTM. The headers must have this exact naming. Name and Experiment are abitrary strings, Fraction is an integer or emtpy, PTM is either 'True', 'False' or empty. Consider you uploaded files named File1.mzxml, ..., File5.mzxml. This is a (syntactically) correct experimental design template:
 
                 ::
@@ -557,7 +574,7 @@
                     File2        2          E1       False
                     ghost       234        none
                     File3        3          E1       False
-                    File4                   E2       true
+                    File4                   E2       True
                     File5                   E1
 
         - This is the counter-example with one error per line:
@@ -569,19 +586,24 @@
                     File2.mzxml 1           E2            (filename with extension)
                     File3       f3          E1            (fraction not an integer)
                     File4       1                         (missing experiment)
-                                                          (File5 misssing)
+                                                          (File5 missing)
 
 **Parameter Options**
 
-- Quantification options
-    - label based: 
-        - for two channels: choose options from light and heavy sections, for three channels choose options from light, medium and heavy sections
-    - label-free
-    - reporter ion ms2: either use the pre-defined labelings with correction factors set to 0 or specify a custom labeling
+- Quantitation methods (in section parameter groups)
+
+    - label free (LFQ): Protein intensity will be reported as 'LFQ intensity' columns in the proteinGroups table
+    - label based: quantifies MS1 labelled samples ('SILAC', 'Dimethyl', 'ICAT', 'ICPL', 'mTRAQ', '18 O')
+
+        - for two channels: choose options from light and heavy sections
+        - for three channels: choose options from light, medium and heavy sections
+    - reporter ion ms2: quantifies conventional isobaric labelling samples. Either use the pre-defined labellings with correction factors set to 0 or specify a custom labelling
+- PTXQC quality control: quality control software creates an automatic quality control pdf report 
+
 
 **Output files**
 
-Different output file options are available, most of them are part of the MaxQuant txt directory. If ptxqc report ist selected, a quality control report will be created.
+Different output file options are available, most of them are part of the MaxQuant txt directory. 
     ]]></help>
     <expand macro="citations"/>
 </tool>