Mercurial > repos > lecorguille > xcms_retcor
diff abims_xcms_retcor.xml @ 30:4d6f4cd7c3ef draft
planemo upload for repository https://github.com/workflow4metabolomics/xcms commit e384d6dd5f410799ec211f73bca0b5d5d7bc651e
| author | lecorguille |
|---|---|
| date | Thu, 01 Mar 2018 04:16:45 -0500 |
| parents | c013ed353a2f |
| children | 281786a7b9a2 |
line wrap: on
line diff
--- a/abims_xcms_retcor.xml Tue Feb 13 04:44:03 2018 -0500 +++ b/abims_xcms_retcor.xml Thu Mar 01 04:16:45 2018 -0500 @@ -1,6 +1,6 @@ -<tool id="abims_xcms_retcor" name="xcms.retcor" version="2.1.1"> +<tool id="abims_xcms_retcor" name="xcms adjustRtime (retcor)" version="@WRAPPER_VERSION@.0"> - <description>Retention Time Correction using retcor function from xcms R package </description> + <description>Retention Time Correction</description> <macros> <import>macros.xml</import> @@ -10,27 +10,31 @@ <expand macro="stdio"/> <command><![CDATA[ - @COMMAND_XCMS_SCRIPT@ + @COMMAND_XCMS_SCRIPT@/xcms_retcor.r image '$image' - xfunction retcor - - xsetRdataOutput '$xsetRData' - ticspdf '$ticsCorPdf' - bicspdf '$bpcsCorPdf' - rplotspdf '$rplotsPdf' method $methods.method - #if $methods.method == "obiwarp": - profStep $methods.profStep + #if $methods.method == "PeakGroups": + minFraction $methods.minFraction + extraPeaks $methods.extraPeaks + smooth $methods.smooth_cond.smooth + ## PeakGroupsSmoothLoess Advanced + span $methods.smooth_cond.PeakGroupsSmoothLoessAdv.span + family $methods.smooth_cond.PeakGroupsSmoothLoessAdv.family #else - smooth $methods.smooth - extra $methods.extra - missing $methods.missing - #if $methods.options.option == "show": - span $methods.options.span - family $methods.options.family - plottype $methods.options.plottype + binSize $methods.binSize + ## Advanced + #if $methods.ObiwarpAdv.centerSample != "": + centerSample $methods.ObiwarpAdv.centerSample #end if + response $methods.ObiwarpAdv.response + distFun $methods.ObiwarpAdv.distFunCond.distFun + gapInit $methods.ObiwarpAdv.distFunCond.gapInit + gapExtend $methods.ObiwarpAdv.distFunCond.gapExtend + factorDiag $methods.ObiwarpAdv.factorDiag + factorGap $methods.ObiwarpAdv.factorGap + localAlignment $methods.ObiwarpAdv.localAlignmentCond.localAlignment + initPenalty $methods.ObiwarpAdv.localAlignmentCond.initPenalty #end if @COMMAND_FILE_LOAD@ @@ -41,44 +45,79 @@ <inputs> <param name="image" type="data" format="rdata.xcms.raw,rdata.xcms.group,rdata" label="xset RData file" help="output file from another function xcms (xcmsSet, retcor etc.)" /> <conditional name="methods"> - <param name="method" type="select" label="Method to use for retention time correction" help="[method] See the help section below" > - <option value="obiwarp" >obiwarp</option> - <option value="peakgroups" selected="true">peakgroups</option> + <param name="method" type="select" label="Method to use for retention time correction" help="See the help section below" > + <option value="PeakGroups" selected="true">PeakGroups - retention time correction based on aligment of features (peak groups) present in most/all samples.</option> + <option value="Obiwarp">Obiwarp - alignment based on the complete mz-rt data.</option> </param> - <when value="obiwarp"> - <param name="profStep" type="float" value="1" label="Step size (in m/z)" help="[profStep] to use for profile generation from the raw data files" /> + <when value="PeakGroups"> + <param argument="minFraction" type="float" value="0.9" min="0" max="1" label="Minimum required fraction of samples in which peaks for the peak group were identified" help="(previously missing)"/> + <param argument="extraPeaks" type="integer" value="1" label="Maximal number of additional peaks for all samples to be assigned to a peak group for retention time correction" help="For a data set with 6 samples, ‘extraPeaks = 1’ uses all peak groups with a total peak count lower or equal to ‘6 + 1’. The total peak count is the total number of peaks being assigned to a peak group and considers also multiple peaks within a sample being assigned to the group. (previously extra)" /> + <conditional name="smooth_cond"> + <param argument="smooth" type="select" label="Smooth method" > + <option value="loess" selected="true">loess - non-linear alignment</option> + <option value="linear">linear - linear alignment</option> + </param> + <when value="loess"> + <section name="PeakGroupsSmoothLoessAdv" title="Advanced Options" expanded="False"> + <param argument="span" type="float" value="0.2" label="Degree of smoothing for the loess fitting" /> + <param argument="family" type="select" label="Family" help="if gaussian fitting is by least-squares with no outlier removal, and if symmetric a re descending M estimator is used with Tukey's biweight function, allowing outlier removal"> + <option value="gaussian" selected="true">gaussian</option> + <option value="symmetric">symmetric</option> + </param> + </section> + </when> + <when value="linear" /> + </conditional> </when> - <when value="peakgroups"> - <param name="smooth" type="select" label="Smooth method" help="[smooth] either 'loess’ for non-linear alignment or ‘linear’ for linear alignment" > - <option value="loess">loess</option> - <option value="linear">linear</option> - </param> - <param name="extra" type="integer" value="1" label="Number of extra peaks to allow in retention time correction correction groups" help="[extra]" /> - <param name="missing" type="integer" value="1" label="Number of missing samples to allow in retention time correction groups" help="[missing]" /> - - <conditional name="options"> - <param name="option" type="select" label="Advanced options"> - <option value="show">show</option> - <option value="hide" selected="true">hide</option> - </param> - <when value="show"> - <param name="span" type="float" value="0.2" label="Degree of smoothing for local polynomial regression fitting" help="[span]"/> - - <param name="family" type="select" label="Family" help="[family] if gaussian fitting is by least-squares with no outlier removal, and if symmetric a re descending M estimator is used with Tukey's biweight function, allowing outlier removal"> - <option value="gaussian" selected="true">gaussian</option> - <option value="symmetric">symmetric</option> + <when value="Obiwarp"> + <param argument="binSize" type="float" value="1" label="Bin size (in mz dimension) to be used for the profile matrix generation" help="See ‘step’ parameter in ‘profile-matrix’ documentation for more details. (previously profStep)" /> + <section name="ObiwarpAdv" title="Advanced Options" expanded="False"> + <param argument="centerSample" type="integer" value="" optional="true" label="Index of the center sample in the experiment" help="It defaults to ‘floor(median(1:length(fileNames(object))))’" /> + <param argument="response" type="integer" value="1" label="Defining the responsiveness of warping" help="with ‘response = 0’ giving linear warping on start and end points and ‘response = 100’ warping using all bijective anchors." /> + <conditional name="distFunCond"> + <param argument="distFun" type="select" label="Distance function to be used"> + <option value="cor_opt" selected="true">cor_opt - calculate only 10% diagonal band of distance matrix; better runtime</option> + <option value="cor">cor - Pearson's correlation</option> + <option value="cov">cov - covariance</option> + <option value="prd">prd - product</option> + <option value="euc">euc - Euclidian distance</option> </param> - - <param name="plottype" type="select" help="[plottype] if deviation plot retention time deviation points and regression fit, and if mdevden also plot peak overall peak density and retention time correction peak density"> - <option value="none" selected="true">none</option> - <option value="deviation">deviation</option> - <option value="mdevden">mdevden</option> + <when value="cor_opt"> + <param argument="gapInit" type="float" value="0.3" label="Penalty for gap opening" /> + <param argument="gapExtend" type="float" value="2.4" label="Penalty for gap enlargement" /> + </when> + <when value="cor"> + <param argument="gapInit" type="float" value="0.3" label="Penalty for gap opening" /> + <param argument="gapExtend" type="float" value="2.4" label="Penalty for gap enlargement" /> + </when> + <when value="cov"> + <param argument="gapInit" type="float" value="0.0" label="Penalty for gap opening" /> + <param argument="gapExtend" type="float" value="11.7" label="Penalty for gap enlargement" /> + </when> + <when value="prd"> + <param argument="gapInit" type="float" value="0.0" label="Penalty for gap opening" /> + <param argument="gapExtend" type="float" value="7.8" label="Penalty for gap enlargement" /> + </when> + <when value="euc"> + <param argument="gapInit" type="float" value="0.9" label="Penalty for gap opening" /> + <param argument="gapExtend" type="float" value="1.8" label="Penalty for gap enlargement" /> + </when> + </conditional> + <param argument="factorDiag" type="float" value="2" label="Local weight applied to diagonal moves in the alignment" /> + <param argument="factorGap" type="float" value="1" label="local weight for gap moves in the alignment" /> + <conditional name="localAlignmentCond"> + <param argument="localAlignment" type="select" label="Whether a local alignment should be performed instead of the default global alignment"> + <option value="FALSE" selected="true">FALSE</option> + <option value="TRUE">TRUE</option> </param> - - </when> - <when value="hide"> - </when> - </conditional> + <when value="FALSE"> + <param argument="initPenalty" type="hidden" value="0" label="Penalty for initiating an alignment" /> + </when> + <when value="TRUE"> + <param argument="initPenalty" type="float" value="0" label="Penalty for initiating an alignment" /> + </when> + </conditional> + </section> </when> </conditional> @@ -87,95 +126,100 @@ </inputs> <outputs> - <data name="xsetRData" format="rdata.xcms.retcor" label="${image.name[:-6]}.retcor.RData" /> - <data name="rplotsPdf" format="pdf" label="${image.name[:-6]}.retcor.Rplots.pdf"> - <filter>(methods['method'] == 'peakgroups')</filter> - <filter>(options['option'] == 'show')</filter> - <filter>(family == 'symmetric')</filter> - <filter>(plottype != 'none')</filter> - </data> - <data name="ticsCorPdf" format="pdf" label="${image.name[:-6]}.retcor.TICs_corrected.pdf" /> - <data name="bpcsCorPdf" format="pdf" label="${image.name[:-6]}.retcor.BPCs_corrected.pdf" /> - <data name="log" format="txt" label="xset.log.txt" hidden="true" /> + <data name="xsetRData" format="rdata.xcms.retcor" label="${image.name[:-6]}.retcor.RData" from_work_dir="retcor.RData" /> + <data name="rawVSadjustedPdf" format="pdf" label="${image.name[:-6]}_rawVSadjusted.retcor.Rplots.pdf" from_work_dir="raw_vs_adjusted_rt.pdf" /> + <data name="ticsCorPdf" format="pdf" label="${image.name[:-6]}.retcor.TICs_corrected.pdf" from_work_dir="TICs.pdf"/> + <data name="bpcsCorPdf" format="pdf" label="${image.name[:-6]}.retcor.BPCs_corrected.pdf" from_work_dir="BICs.pdf" /> </outputs> <tests> - <!--<test> - <param name="image" value="xset.group.RData"/> - <param name="methods|method" value="peakgroups"/> - <param name="methods|smooth" value="loess"/> - <param name="methods|extra" value="1"/> - <param name="methods|missing" value="1"/> - <param name="methods|options|option" value="show"/> - <param name="methods|options|span" value="0.2"/> - <param name="methods|options|family" value="gaussian"/> - <param name="methods|options|plottype" value="deviation"/> - <param name="zipfile_load_conditional|zipfile_load_select" value="yes" /> - <param name="zipfile_load_conditional|zip_file" value="sacuri_dir_root.zip" ftype="zip" /> - <output name="log"> - <assert_contents> - <has_text text="object with 4 samples" /> - <has_text text="Time range: 0.2-1140.1 seconds (0-19 minutes)" /> - <has_text text="Mass range: 50.0021-999.9863 m/z" /> - <has_text text="Peaks: 59359 (about 14840 per sample)" /> - <has_text text="Peak Groups: 0" /> - <has_text text="Sample classes: bio, blank" /> - </assert_contents> - </output> - </test>--> + <test> + <param name="image" value="faahKO-single-class.xset.group.RData"/> + <conditional name="methods"> + <param name="method" value="PeakGroups"/> + <param name="extraPeaks" value="1"/> + <param name="minFraction" value="1"/> + <conditional name="smooth_cond"> + <param name="smooth" value="loess"/> + <section name="PeakGroupsSmoothLoessAdv"> + <param name="span" value="0.2"/> + <param name="family" value="gaussian"/> + </section> + </conditional> + </conditional> + <expand macro="test_file_load_single"/> + <assert_stdout> + <has_text text="extraPeaks: 1" /> + <has_text text="minFraction: 1" /> + <has_text text="span: 0.2" /> + <has_text text="object with 4 samples" /> + <has_text text="Time range: 2509.2-4480.3 seconds (41.8-74.7 minutes)" /> + <has_text text="Mass range: 200.1-600 m/z" /> + <has_text text="Peaks: 9251 (about 2313 per sample)" /> + <has_text text="Peak Groups: 0" /> + <has_text text="Sample classes: KO, WT" /> + </assert_stdout> + </test> + <!-- DISABLE FOR TRAVIS : Zip <test> <param name="image" value="faahKO.xset.group.RData"/> - <param name="methods|method" value="peakgroups"/> - <param name="methods|smooth" value="loess"/> - <param name="methods|extra" value="1"/> - <param name="methods|missing" value="1"/> - <param name="methods|options|option" value="show"/> - <param name="methods|options|span" value="0.2"/> - <param name="methods|options|family" value="gaussian"/> - <param name="methods|options|plottype" value="deviation"/> + <conditional name="methods"> + <param name="method" value="PeakGroups"/> + <param name="extraPeaks" value="1"/> + <param name="minFraction" value="1"/> + <conditional name="smooth_cond"> + <param name="smooth" value="loess"/> + <section name="PeakGroupsSmoothLoessAdv"> + <param name="span" value="0.2"/> + <param name="family" value="gaussian"/> + </section> + </conditional> + </conditional> <expand macro="test_file_load_zip"/> - <output name="log"> - <assert_contents> - <has_text text="object with 4 samples" /> - <has_text text="Time range: 2507.7-4481.7 seconds (41.8-74.7 minutes)" /> - <has_text text="Mass range: 200.1-600 m/z" /> - <has_text text="Peaks: 9251 (about 2313 per sample)" /> - <has_text text="Peak Groups: 0" /> - <has_text text="Sample classes: KO, WT" /> - </assert_contents> - </output> + <assert_stdout> + <has_text text="object with 4 samples" /> + <has_text text="Time range: 2509.2-4480.3 seconds (41.8-74.7 minutes)" /> + <has_text text="Mass range: 200.1-600 m/z" /> + <has_text text="Peaks: 9251 (about 2313 per sample)" /> + <has_text text="Peak Groups: 0" /> + <has_text text="Sample classes: KO, WT" /> + </assert_stdout> </test> + --> + <!-- DISABLE FOR TRAVIS + Test to test the different methods parameters <test> <param name="image" value="faahKO-single-class.xset.group.RData"/> - <param name="methods|method" value="peakgroups"/> - <param name="methods|smooth" value="loess"/> - <param name="methods|extra" value="1"/> - <param name="methods|missing" value="1"/> - <param name="methods|options|option" value="show"/> - <param name="methods|options|span" value="0.2"/> - <param name="methods|options|family" value="gaussian"/> - <param name="methods|options|plottype" value="deviation"/> + <conditional name="methods"> + <param name="method" value="Obiwarp"/> + <section name="ObiwarpAdv"> + <param name="centerSample" value="1"/> + <param name="response" value="0"/> + <conditional name="distFunCond"> + <param name="distFun" value="cov"/> + <param name="gapInit" value="0.1" /> + </conditional> + </section> + </conditional> <expand macro="test_file_load_single"/> - <output name="log"> - <assert_contents> - <has_text text="object with 4 samples" /> - <has_text text="Time range: 2507.7-4481.7 seconds (41.8-74.7 minutes)" /> - <has_text text="Mass range: 200.1-600 m/z" /> - <has_text text="Peaks: 9251 (about 2313 per sample)" /> - <has_text text="Peak Groups: 0" /> - <has_text text="Sample classes: KO, WT" /> - </assert_contents> - </output> + <assert_stdout> + <has_text text="centerSample: 1" /> + <has_text text="response: 0" /> + <has_text text="distFun: cov" /> + <has_text text="gapInit: 0.1" /> + <has_text text="gapExtend: 11.7" /> + </assert_stdout> </test> + --> </tests> <help><![CDATA[ @HELP_AUTHORS@ -=========== -Xcms.retcor -=========== +================ +xcms adjustRtime +================ ----------- Description @@ -191,7 +235,7 @@ .. class:: warningmark -**After an retcor step, it is mandatory to do a group step, otherwise the rest of the workflow will not work with the RData file. (the initial peak grouping becomes invalid and is +**After an adjustRtime step, it is mandatory to do a groupChromPeaks step, otherwise the rest of the workflow will not work with the RData file. (the initial peak grouping becomes invalid and is discarded)** @@ -244,17 +288,20 @@ Method ------ -**peakgroups** +**PeakGroups** - | xcms ignores those groups by only considering well-behaved peak groups which are missing at most one sample and have at most one extra peak. (Those values can be changed with the **missing** and **extra** arguments.) - | For each of those well-behaved groups, the algorithm calculates a median retention time and, for every sample, a deviation from that median. Within a sample, the observed deviation generally changes over time in a nonlinear fashion. Those changes are approximated using a local polynomial regression technique implemented in the **loess** function. By default, the curve fitting is done using least-squares on all data points. - | However, it is possible to enable outlier detection and removal by setting the **family** argument to **symmetric**. + | This method performs retention time adjustment based on the alignment of chromatographic peak groups present in all/most samples (hence corresponding to house keeping compounds). First the retention time deviation of these peak groups is described by fitting either a polynomial (‘smooth = "loess"’) or a linear ( ‘smooth = "linear"’) model to the data points. These models are subsequently used to adjust the retention time of each spectrum in each sample. + | See the PeakGroups_manual_ + +**Obiwarp** -**obiwarp** + | This method performs retention time adjustment using the Obiwarp method [Prince 2006]. It is based on the code at http://obi-warp.sourceforge.net but supports alignment of multiple samples by aligning each against a _center_ sample. The alignment is performed directly on the ‘profile-matrix’ and can hence be performed independently of the peak detection or peak grouping. + | See the Obiwarp_manual_ - | Calculate retention time deviations for each sample using the obiwarp code at "http://obi-warp.sourceforge.net/". This function is able to align multiple samples by a center-star strategy. Ordered Bijective Interpolated Warping (OBI-Warp) aligns matrices along a single axis using Dynamic Time Warping (DTW) and a one-to-one (bijective) interpolated warp function. OBI-Warp harnesses the non-linear, comprehensive alignment power of DTW and builds on the discrete, non-bijective output of DTW to give natural interpolants that can be used across multiple datasets. - | For the original publication see :**Chromatographic Alignment of ESI-LC-MS Proteomics Data Sets by Ordered Bijective Interpo-lated Warping John T. Prince and, Edward M. Marcotte Analytical Chemistry 2006 78 (17), 6140-6152.** +.. _PeakGroups_manual: https://rdrr.io/bioc/xcms/man/adjustRtime-peakGroups.html#heading-2 +.. _Obiwarp_manual: https://rdrr.io/bioc/xcms/man/adjustRtime-obiwarp.html +@HELP_XCMS_MANUAL@ ------------ Output files @@ -294,10 +341,10 @@ Parameters ---------- - | Method: -> **peakgroups** + | Method: -> **PeakGroups** | smooth: -> **loess** - | extra: -> **1** - | missing -> **1** + | extraPeaks: -> **1** + | minFraction -> **1** | Advanced options: -> **show** | span -> **0.2** | family -> **gaussian** @@ -319,6 +366,10 @@ Changelog/News -------------- +**Version 3.0.0.0 - 14/02/2018** + +- UPGRADE: upgrade the xcms version from 1.46.0 to 3.0.0. So refactoring of a lot of underlining codes and methods + **Version 2.1.1 - 29/11/2017** - BUGFIX: To avoid issues with accented letter in the parentFile tag of the mzXML files, we changed a hidden mechanim to LC_ALL=C