Mercurial > repos > galaxyp > msconvert
diff msconvert_macros.xml @ 6:6b6bba73eadb draft
planemo upload commit d56659dd48f8c554a832787e71aca6ae65c90848
| author | galaxyp |
|---|---|
| date | Tue, 14 Mar 2017 16:52:39 -0400 |
| parents | 637e309295cf |
| children | e638f7fad66a |
line wrap: on
line diff
--- a/msconvert_macros.xml Mon Dec 12 17:07:11 2016 -0500 +++ b/msconvert_macros.xml Tue Mar 14 16:52:39 2017 -0400 @@ -1,26 +1,50 @@ <macros> + <xml name="generic_requirements"> + <requirements> + <requirement type="package" version="3.0.9992">proteowizard</requirement> + </requirements> + </xml> + <token name="@VERSION@">3.0.9992</token> + <xml name="msconvertCommand"> - <command> + <command interpreter="python"> <![CDATA[ - #set $output_type_str = str($output_type) - #set $input_name = $input.display_name - #set $output_name = $input_name.split(".")[0] + "." + $output_type_str - ln -s '$input' '${input_name}' && + #import re + #set $ext = $input.ext - #if $data_processing.precursor_refinement.use_mzrefinement - #set $input_ident_name = $data_processing.precursor_refinement.input_ident.display_name - ln -s '${data_processing.precursor_refinement.input_ident}' '${input_ident_name}' && + ## sanitize display name for use as temp filename + #set basename = 'pwiz_in' + + #if hasattr($input, 'display_name') + ## explicit inclusion or exclusion ?? + #set basename = $re.sub(r'[^\w\.\-\+]','_',$input.display_name) + ##set basename = $re.sub(r'[\/\\\;\|\&\>\<]','_',$input.display_name) #end if - mkdir outdir && - msconvert ${input_name} --$output_type_str -o outdir --outfile '$output_name' + msconvert_wrapper.py + + #if $ext == 'wiff': + --input='${input.extra_files_path}/wiff' + --input_name='${basename}.wiff' + --implicit='${input.extra_files_path}/wiff_scan' + --input='${input.extra_files_path}/wiff_scan' + --input_name='${basename}.wiff.scan' + #else + --input='${input}' + --input_name='$basename' + #end if + --output='${output}' + ## BEGIN_VERSION_DEFAULT + --fromextension=$ext + ## END_VERSION_DEFAULT + --toextension=${output_type} ## DATA PROCESSING FILTERS (NOTE: FOR VENDOR METHOD TO WORK, PEAK PICKING MUST BE THE FIRST FILTER!) - #if $data_processing.peak_picking.pick_peaks - --filter "peakPicking $data_processing.peak_picking.pick_peaks_algorithm msLevel=$data_processing.peak_picking.pick_peaks_ms_levels" - #end if - #if $data_processing.precursor_refinement.use_mzrefinement + #set input_ident_name = ".".join(($basename, $data_processing.precursor_refinement.input_ident.ext)) + --ident='$data_processing.precursor_refinement.input_ident' + --ident_name='$input_ident_name' + --refinement='$output_refinement' --filter "mzRefiner $input_ident_name msLevels=$data_processing.precursor_refinement.precursor_refinement_ms_levels thresholdScore=$data_processing.precursor_refinement.thresholdScore @@ -29,6 +53,10 @@ maxSteps=$data_processing.precursor_refinement.thresholdMaxSteps" #end if + #if $data_processing.peak_picking.pick_peaks + --filter "peakPicking $data_processing.peak_picking.pick_peaks_algorithm msLevel=$data_processing.peak_picking.pick_peaks_ms_levels" + #end if + #if str($data_processing.charge_state_calculation.charge_state_calculation_method) == "predictor" --filter "chargeStatePredictor overrideExistingCharge=$data_processing.charge_state_calculation.predictor_overrideExistingCharge @@ -48,27 +76,27 @@ #end if #for threshold_entry in $data_processing.thresholds - --filter "threshold $threshold_entry.threshold_type $threshold_entry.value $threshold_entry.orientation" + --filter "threshold $threshold_entry.threshold_type $threshold_entry.value $threshold_entry.orientation" #end for #if $data_processing.filter_mz_windows.do_mzwindow_filter - --filter "mzWindow [$data_processing.filter_mz_windows.mz_window_from,$data_processing.filter_mz_windows.mz_window_to]" + --filter "mzWindow [$data_processing.filter_mz_windows.mz_window_from,$data_processing.filter_mz_windows.mz_window_to]" #end if #if $data_processing.etd_filtering.do_etd_filtering - --filter "ETDFilter $data_processing.etd_filtering.remove_precursor - $data_processing.etd_filtering.remove_charge_reduced - $data_processing.etd_filtering.remove_neutral_loss - $data_processing.etd_filtering.blanket_removal - $data_processing.etd_filtering.matching_tolerance $data_processing.etd_filtering.matching_tolerance_units" + --filter "ETDFilter $data_processing.etd_filtering.remove_precursor + $data_processing.etd_filtering.remove_charge_reduced + $data_processing.etd_filtering.remove_neutral_loss + $data_processing.etd_filtering.blanket_removal + $data_processing.etd_filtering.matching_tolerance $data_processing.etd_filtering.matching_tolerance_units" #end if #if $data_processing.ms2denoise.denoise - --filter "MS2Denoise $data_processing.ms2denoise.num_peaks $data_processing.ms2denoise.window_width $data_processing.ms2denoise.relax" + --filter "MS2Denoise $data_processing.ms2denoise.num_peaks $data_processing.ms2denoise.window_width $data_processing.ms2denoise.relax" #end if #if str($data_processing.ms2deisotope) == "true" - --filter "MS2Deisotope" + --filter "MS2Deisotope" #end if @@ -78,38 +106,39 @@ #end if #if len($filtering.indices) > 0 - --filter "index - #for $index in $filtering.indices - [${index.from},${index.to}] - #end for - " + --filter "index + #for $index in $filtering.indices + [${index.from},${index.to}] + #end for + " #end if #if len($filtering.scan_numbers) > 0 - --filter "scanNumber - #for $scan_number in $filtering.scan_numbers - [${scan_number.from},${scan_number.to}] - #end for - " + --filter "scanNumber + #for $scan_number in $filtering.scan_numbers + [${scan_number.from},${scan_number.to}] + #end for + " #end if #if $filtering.strip_it.value - --filter "stripIT" + --filter "stripIT" #end if #if $filtering.filter_ms_levels.do_ms_level_filter - --filter "msLevel [$filtering.filter_ms_levels.ms_level_from, $filtering.filter_ms_levels.ms_level_to]" + --filter "msLevel [$filtering.filter_ms_levels.ms_level_from, $filtering.filter_ms_levels.ms_level_to]" #end if #if str($filtering.polarity) != "false" - --filter "polarity $filtering.polarity" + --filter "polarity $filtering.polarity" #end if #if str($filtering.analyzer) != "false" - --filter "analyzer $filtering.analyzer" + --filter "analyzer $filtering.analyzer" #end if ## OUTPUT ENCODING + -- #set $mz_encoding = str($settings.mz_encoding) #set $intensity_encoding = str($settings.intensity_encoding) #if $mz_encoding == $intensity_encoding @@ -125,31 +154,23 @@ #set binary_compression = str($settings.binary_compression) #if $binary_compression == "zlib" - --zlib + --zlib #else if $binary_compression == "numpressLinearPic" - --numpressLinear --numpressPic + --numpressLinear --numpressPic #else if $binary_compression == "numpressLinearSlof" - --numpressLinear --numpressSlof + --numpressLinear --numpressSlof #else if $binary_compression == "numpressLinear" - --numpressLinear + --numpressLinear #else if $binary_compression == "numpressPic" - --numpressPic + --numpressPic #else if $binary_compression == "numpressSlof" - --numpressSlof + --numpressSlof #end if #if $settings.gzip_compression - --gzip + --gzip #end if - && - - #if $data_processing.precursor_refinement.use_mzrefinement - mv '${input.name.rsplit('.',1)[0]}.mzRefinement.tsv' output.refinement && - #end if - - mv 'outdir/$output_name' output && - rmdir outdir ]]> </command> </xml> @@ -187,8 +208,18 @@ <when value="false"></when> <when value="true"> <param name="input_ident" type="data" format="pepxml,mzid" label="MZRefinery - Input identification data" /> - <param name="thresholdScore" type="text" value="mvh" label="MZRefinery - Threshold Score Name" help="E.g. 'mvh' for MyriMatch, 'xcorr' for Sequest, 'specevalue' for MS-GF+" /> - <param name="thresholdValue" type="text" value="50-" label="MZRefinery - Threshold Score Value" help="MZRefinery uses peptide-spectrum-matches with scores from this range to build its model. '100-' means score equal to or greater than 100. '-1e-10' means less than or equal to 1e-10." /> + <param name="thresholdScore" type="text" value="mvh" label="MZRefinery - Threshold Score Name" help="E.g. 'mvh' for MyriMatch, 'xcorr' for Sequest, 'specevalue' for MS-GF+"> + <sanitizer> + <valid initial="string.letters" /> + </sanitizer> + </param> + <param name="thresholdValue" type="text" value="50-" label="MZRefinery - Threshold Score Value" help="MZRefinery uses peptide-spectrum-matches with scores from this range to build its model. '100-' means score equal to or greater than 100. '-1e-10' means less than or equal to 1e-10."> + <sanitizer> + <valid initial="string.letters,string.digits"> + <add value="-" /> + </valid> + </sanitizer> + </param> <param name="thresholdStep" type="float" value="0" label="MZRefinery - Threshold Score Step" help="If there are not enough quality hits at the given score threshold value, the threshold can be increased by this step (until maxSteps is reached)." /> <param name="thresholdMaxSteps" type="integer" value="0" label="MZRefinery - At most, how many steps to widen the threshold?" /> <param name="precursor_refinement_ms_levels" type="select" label="MZRefinery - Apply to MS Levels"> @@ -301,14 +332,14 @@ <option value="CID">CID</option> <option value="SA">SA</option> <option value="HCD">HCD</option> - <option>BIRD</option> - <option>ECD</option> - <option>IRMPD</option> - <option>PD</option> - <option>PSD</option> - <option>PQD</option> - <option>SID</option> - <option>SORI</option> + <option value="BIRD">BIRD</option> + <option value="ECD">ECD</option> + <option value="IRMPD">IRMPD</option> + <option value="PD">PD</option> + <option value="PSD">PSD</option> + <option value="PQD">PQD</option> + <option value="SID">SID</option> + <option value="SORI">SORI</option> </param> <repeat name="indices" title="Filter Scan Indices"> @@ -373,7 +404,7 @@ <xml name="msconvertOutput"> <outputs> - <data format="mzml" name="output" from_work_dir="output" label="${input.name.rsplit('.',1)[0]}.${output_type}" > + <data format="mzml" name="output" label="${input.name.rsplit('.',1)[0]}.${output_type}" > <change_format> <when input="output_type" value="mz5" format="mz5" /> <when input="output_type" value="mzXML" format="mzxml" /> @@ -381,9 +412,274 @@ <when input="output_type" value="mgf" format="mgf" /> </change_format> </data> - <data format="csv" name="output.refinement" from_work_dir="output.refinement" label="${input.name.rsplit('.',1)[0]}.mzRefinement.tsv"> + <data format="csv" name="output_refinement" label="${input.name.rsplit('.',1)[0]}.mzRefinement.tsv"> <filter>data_processing['precursor_refinement']['use_mzrefinement'] == True</filter> </data> </outputs> </xml> + + + <xml name="msconvert_tests"> + <test> + <param name="input" value="small.mzML" /> + <param name="output_type" value="mzML" /> + <param name="pick_peaks" value="true" /> + <param name="pick_peaks_algorithm" value="cwt" /> + <param name="pick_peaks_ms_levels" value="1-" /> + <output name="output" file="small-peakpicking-cwt-allMS.mzML" /> + </test> + + <!-- this data file only has profile MS1, so the result is the same --> + <test> + <param name="input" value="small.mzML" /> + <param name="output_type" value="mzML" /> + <param name="pick_peaks" value="true" /> + <param name="pick_peaks_algorithm" value="cwt" /> + <param name="pick_peaks_ms_levels" value="1" /> + <output name="output" file="small-peakpicking-cwt-allMS.mzML" /> + </test> + <test> + <param name="input" value="small-peakpicking-cwt-allMS.mzML" /> + <param name="output_type" value="mz5" /> + <param name="mz_encoding" value="64" /> + <param name="intensity_encoding" value="64" /> + <output name="output" file="small-zlib-64.mz5" compare="sim_size" delta="150000" /> + </test> + <test> + <param name="input" value="small-peakpicking-cwt-allMS.mzML" /> + <param name="output_type" value="mzXML" /> + <param name="mz_encoding" value="32" /> + <param name="intensity_encoding" value="32" /> + <output name="output" file="small-zlib-32.mzXML" /> + </test> + <!-- TODO: how to test gzipped output? + <test> + <param name="input" value="small-peakpicking-cwt-allMS.mzML" /> + <param name="output_type" value="mzXML" /> + <param name="mz_encoding" value="32" /> + <param name="intensity_encoding" value="32" /> + <param name="binary_compression" value="false" /> + <param name="gzip_compression" value="true" /> + <output name="output" file="small-off-32.mzXML.gz" compare="sim_size" delta="100" /> + </test> + <test> + <param name="input" value="small-peakpicking-cwt-allMS.mzML" /> + <param name="output_type" value="mzML" /> + <param name="mz_encoding" value="32" /> + <param name="intensity_encoding" value="32" /> + <param name="binary_compression" value="false" /> + <param name="gzip_compression" value="true" /> + <output name="output" file="small-off-32.mzML.gz" compare="sim_size" delta="100" /> + </test>--> + + <test> + <param name="input" value="small-peakpicking-cwt-allMS.mzML" /> + <param name="output_type" value="mzML" /> + <param name="binary_compression" value="numpressLinearPic" /> + <output name="output" file="small-numpressLP.mzML" /> + </test> + + <test> + <param name="input" value="small-peakpicking-cwt-allMS.mzML" /> + <param name="output_type" value="mzML" /> + <param name="binary_compression" value="numpressLinearSlof" /> + <output name="output" file="small-numpressLS.mzML" /> + </test> + + <test> + <param name="input" value="small-peakpicking-cwt-allMS.mzML" /> + <param name="output_type" value="mzML" /> + <param name="binary_compression" value="numpressLinear" /> + <output name="output" file="small-numpressL.mzML" /> + </test> + + <test> + <param name="input" value="small-peakpicking-cwt-allMS.mzML" /> + <param name="output_type" value="mzML" /> + <param name="binary_compression" value="numpressPic" /> + <output name="output" file="small-numpressP.mzML" /> + </test> + + <test> + <param name="input" value="small-peakpicking-cwt-allMS.mzML" /> + <param name="output_type" value="mzML" /> + <param name="binary_compression" value="numpressSlof" /> + <output name="output" file="small-numpressS.mzML" /> + </test> + + <test> + <param name="input" value="Rpal_01.mz5" /> + <param name="output_type" value="mzML" /> + <param name="binary_compression" value="numpressLinearPic" /> + <param name="use_mzrefinement" value="true" /> + <param name="input_ident" value="Rpal_01.pepXML" /> + <param name="thresholdScore" value="mvh" /> + <param name="thresholdValue" value="40-" /> + <output name="output" file="Rpal_01-mzRefinement.mzML" compare="sim_size" delta="0" /> + <output name="output_refinement" file="Rpal_01.pepXML.mzRefinement.tsv" /> + </test> + + <test> + <param name="input" value="small-peakpicking-cwt-allMS.mzML" /> + <param name="output_type" value="mzML" /> + <param name="binary_compression" value="numpressLinearPic" /> + <param name="charge_state_calculation_method" value="predictor" /> + <param name="predictor_overrideExistingCharge" value="true" /> + <param name="minMultipleCharge" value="2" /> + <param name="maxMultipleCharge" value="5" /> + <param name="singleChargeFractionTIC" value="0.95" /> + <param name="maxKnownCharge" value="8" /> + <output name="output" file="small-chargeStatePredictor.mzML" /> + </test> + <test> + <param name="input" value="small-peakpicking-cwt-allMS.mzML" /> + <param name="output_type" value="mzML" /> + <param name="binary_compression" value="numpressLinearPic" /> + <param name="charge_state_calculation_method" value="turbocharger" /> + <param name="minCharge" value="1" /> + <param name="maxCharge" value="5" /> + <param name="precursorsBefore" value="1" /> + <param name="precursorsAfter" value="1" /> + <param name="halfIsoWidth" value="1.5" /> + <param name="defaultMinCharge" value="1" /> + <param name="defaultMaxCharge" value="5" /> + <output name="output" file="small-turbocharger.mzML" /> + </test> + <test> + <param name="input" value="D100930_yeast_SCX10S_rak_ft8E_pc_01.mz5" /> + <param name="output_type" value="mzML" /> + <param name="do_etd_filtering" value="true" /> + <param name="remove_precursor" value="true" /> + <param name="remove_charge_reduced" value="true" /> + <param name="remove_neutral_loss" value="false" /> + <param name="blanket_removal" value="false" /> + <param name="matching_tolerance" value="50" /> + <param name="matching_tolerance_units" value="ppm" /> + <param name="binary_compression" value="numpressLinearPic" /> + <output name="output" file="D100930_yeast_SCX10S_rak_ft8E_pc_01-etdfilter.mzML" /> + </test> + <test> + <param name="input" value="small-peakpicking-cwt-allMS.mzML" /> + <param name="output_type" value="mzML" /> + <param name="thresholds_0|threshold_type" value="count" /> + <param name="thresholds_0|value" value="100" /> + <param name="thresholds_0|orientation" value="most-intense" /> + <param name="thresholds_1|threshold_type" value="absolute" /> + <param name="thresholds_1|value" value="1" /> + <param name="thresholds_1|orientation" value="most-intense" /> + <param name="binary_compression" value="numpressLinearPic" /> + <output name="output" file="small-threshold.mzML" /> + </test> + <test> + <param name="input" value="small-peakpicking-cwt-allMS.mzML" /> + <param name="output_type" value="mzML" /> + <param name="do_mzwindow_filter" value="true" /> + <param name="mz_window_from" value="420" /> + <param name="mz_window_to" value="840" /> + <param name="binary_compression" value="numpressLinearPic" /> + <output name="output" file="small-mzWindow.mzML" /> + </test> + <test> + <param name="input" value="small-peakpicking-cwt-allMS.mzML" /> + <param name="output_type" value="mzML" /> + <param name="denoise" value="true" /> + <param name="num_peaks" value="10" /> + <param name="window_width" value="40" /> + <param name="relax" value="false" /> + <param name="binary_compression" value="numpressLinearPic" /> + <output name="output" file="small-denoise.mzML" /> + </test> + <test> + <param name="input" value="small-peakpicking-cwt-allMS.mzML" /> + <param name="output_type" value="mzML" /> + <param name="ms2deisotope" value="true" /> + <param name="binary_compression" value="numpressLinearPic" /> + <output name="output" file="small-deisotope.mzML" /> + </test> + <test> + <param name="input" value="small-peakpicking-cwt-allMS.mzML" /> + <param name="output_type" value="mzML" /> + <param name="activation" value="CID" /> + <param name="binary_compression" value="numpressLinearPic" /> + <output name="output" file="small-activation.mzML" /> + </test> + <test> + <param name="input" value="small-peakpicking-cwt-allMS.mzML" /> + <param name="output_type" value="mzML" /> + <param name="indices_0|from" value="2" /> + <param name="indices_0|to" value="4" /> + <param name="indices_1|from" value="10" /> + <param name="indices_1|to" value="10" /> + <param name="indices_2|from" value="13" /> + <param name="indices_2|to" value="15" /> + <param name="binary_compression" value="numpressLinearPic" /> + <output name="output" file="small-index-filter.mzML" /> + </test> + <test> + <param name="input" value="small-peakpicking-cwt-allMS.mzML" /> + <param name="output_type" value="mzML" /> + <param name="strip_it" value="true" /> + <param name="binary_compression" value="numpressLinearPic" /> + <output name="output" file="small-strip-it.mzML" /> + </test> + <test> + <param name="input" value="small-peakpicking-cwt-allMS.mzML" /> + <param name="output_type" value="mzML" /> + <param name="do_ms_level_filter" value="true" /> + <param name="ms_level_from" value="2" /> + <param name="ms_level_to" value="2" /> + <param name="binary_compression" value="numpressLinearPic" /> + <output name="output" file="small-ms-level-filter.mzML" /> + </test> + <test> + <param name="input" value="small-peakpicking-cwt-allMS.mzML" /> + <param name="output_type" value="mzML" /> + <param name="polarity" value="positive" /> + <param name="binary_compression" value="numpressLinearPic" /> + <output name="output" file="small-polarity-filter.mzML" /> + </test> + <test> + <param name="input" value="small-peakpicking-cwt-allMS.mzML" /> + <param name="output_type" value="mzML" /> + <param name="analyzer" value="IT" /> + <param name="binary_compression" value="numpressLinearPic" /> + <output name="output" file="small-analyzer-filter.mzML" /> + </test> + <test> + <param name="input" value="small-peakpicking-cwt-allMS.mzML" /> + <param name="output_type" value="mzML" /> + <param name="scan_numbers_0|from" value="3" /> + <param name="scan_numbers_0|to" value="5" /> + <param name="scan_numbers_1|from" value="11" /> + <param name="scan_numbers_1|to" value="11" /> + <param name="scan_numbers_2|from" value="14" /> + <param name="scan_numbers_2|to" value="16" /> + <param name="binary_compression" value="numpressLinearPic" /> + <output name="output" file="small-index-filter.mzML" /> <!-- the scan numbers here produce the same output as the index test above --> + </test> + <!--<test> + <param name="input" value="small.mzML" /> + <param name="output_type" value="mzML" /> + <param name="binary_compression" value="numpressLinearPic" /> + <output name="output" file="small-deisotope-poisson.mzML" /> + </test>--> + </xml> + <xml name="msconvert_help"> +**What it does** + +Allows interconversion within various mass spectrometry peak list formats. Additional options such as filtering and/or precursor recalculation are available. + +You can view the original documentation here_. + +.. _here: http://proteowizard.sourceforge.net/tools/msconvert.html + </xml> + + <xml name="citations"> + <citations> + <citation type="doi">10.1093/bioinformatics/btn323</citation> + <citation type="bibtex">@misc{toolsGalaxyP, author = {Chilton, J, Chambers MC, et al.}, title = {Galaxy Proteomics Tools}, publisher = {GitHub}, journal = {GitHub repository}, + year = {2015}, url = {https://github.com/galaxyproteomics/tools-galaxyp}}</citation> <!-- TODO: fix substitution of commit ", commit = {$sha1$}" --> + </citations> + </xml> + </macros>