| Next changeset 1:d6a4dfdad269 (2021-04-08) |
|
Commit message:
"planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/encyclopedia/tools/encyclopedia commit d94002fc79f552c8a64ffca86298396b1568df97" |
|
added:
encyclopedia_walnut.xml macros.xml static/images/SearchToLib_Workflow.png |
| b |
| diff -r 000000000000 -r ce1a157a41bd encyclopedia_walnut.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/encyclopedia_walnut.xml Mon Sep 14 17:06:23 2020 +0000 |
| [ |
| @@ -0,0 +1,113 @@ +<tool id="encyclopedia_walnut" name="Walnut" version="@VERSION@.0"> + <description>PeCAn-based Peptide Detection Directly from Data-Independent Acquisition (DIA) MS/MS Data</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements" /> + <command detect_errors="aggressive"><![CDATA[ + @CMD_IMPORTS@ + @LINK_SCAN_INPUT@ + @LINK_FASTA_INPUT@ + @LINK_TARGET_FASTA@ + EncyclopeDIA -Djava.awt.headless=true -Duser.language=en-US -Duser.region=US + -Xmx\$[ \${GALAXY_MEMORY_MB:-20480} / 1024 ]g -walnut + -numberOfThreadsUsed "\${GALAXY_SLOTS:-4}" + @SCAN_INPUT@ + @FASTA_INPUT@ + @TARGET_FASTA@ + @COMMON_OPTIONS@ + @MASS_LIBRARY_TOLERANCE@ + @PERCOLATOR_OPTIONS@ + @PEAK_OPTIONS@ + @WINDOW_OPTIONS@ + @MODIFICATION_OPTIONS@ + @SEARCH_OPTIONS@ + -o gxpedia + ]]></command> + <inputs> + <expand macro="scan_input"/> + <expand macro="fasta_input"/> + <expand macro="target_fasta"/> + <expand macro="options_section"/> + <param name="select_outputs" type="select" label="Select outputs" multiple="true"> + <option value="log" selected="true">log</option> + <option value="elib" selected="true">elib</option> + <option value="features" selected="false">features.txt</option> + <option value="pecan" selected="true">pecan.txt</option> + <option value="pecan_decoy" selected="false">pecan.decoy.txt</option> + </param> + </inputs> + <outputs> + <data name="log" format="txt" label="${tool.name} ${on_string} log" from_work_dir="gxpedia.log"> + <filter>'log' in select_outputs</filter> + </data> + <data name="elib" format="elib" label="${tool.name} ${on_string} elib" from_work_dir="gxpedia.elib"> + <filter>'elib' in select_outputs</filter> + </data> + <data name="features" format="tabular" label="${tool.name} ${on_string} features.txt" from_work_dir="gxpedia.features.txt"> + <filter>'features' in select_outputs</filter> + <actions> + <action name="column_names" type="metadata" default="id,TD,ScanNr,topN,rank,peakZScore,peakCalibratedScore,deltaSn,avgIdotp,midIdotp,peakScore,peakWeightedScore,NCI,CIMassErrMean,CIMassErrVar,precursorMassErrMean,precursorMassErrVar,peakSimilarity,sampledTimes,midTime,spectraNorm,pepLength,charge2,charge3,precursorMz,sequence,protein" /> + </actions> + </data> + <data name="pecan" format="tabular" label="${tool.name} ${on_string} pecan.txt" from_work_dir="gxpedia.pecan.txt"> + <filter>'pecan' in select_outputs</filter> + <actions> + <action name="column_names" type="metadata" default="PSMId,score,q-value,posterior_error_prob,peptide,proteinIds" /> + </actions> + </data> + <data name="pecan_decoy" format="tabular" label="${tool.name} ${on_string} pecan.decoy.txt" from_work_dir="gxpedia.pecan.decoy.txt"> + <filter>'pecan_decoy' in select_outputs</filter> + <actions> + <action name="column_names" type="metadata" default="PSMId,score,q-value,posterior_error_prob,peptide,proteinIds" /> + </actions> + </data> + </outputs> + <tests> + <test> + <param name="scan_input" ftype="mzml" value="BCS_hela_narrow_3_1.mzML"/> + <param name="fasta" ftype="fasta" value="uniprot_tiny_human.fasta"/> + <param name="select_outputs" value="log,features,pecan"/> + <output name="features" ftype="tabular"> + <assert_contents> + <has_text text="LHYNEGLNIK"/> + </assert_contents> + </output> + </test> + </tests> + <help><![CDATA[ +**Walnut** + +@ENCYCLOPEDIA_WIKI@ + +Walnut is a FASTA database search engine for Data-Independent Acquisition (DIA) MS/MS data. +Walnut uses PeCAn-style scoring to extract peptide fragmentation chromatograms from MZML files, assign peaks, and calculate various peak features. These features are interpreted by Percolator to identify peptides. + + + +**Inputs** + + - A spectrum file in mzML format + - A protein data base in fasta format + +@MSCONVERT_HELP@ + +**Outputs** + + - A log file + - A Chromatogram Library (.elib) + - The identified features in tabular format + Feature values of scans that are used by percolator to determine matches. + - The identified Peptide Spectral Match results in tabular format + Columns: PSMId, score, q-value, posterior_error_prob, peptide, proteinIds + - The identified peptides in tabular format + Per peptide: the normalized intensity for each scan file. + Columns: Peptide, Protein, numFragments, intensity_in_file1, intensity_in_file2, ... + - The identified proteins in tabular format + Per protein: the normalized intensity for each scan file. + Columns: Protein, NumPeptides, PeptideSequences, intensity_in_file1, intensity_in_file2, ... + + + ]]></help> + <expand macro="citations" /> +</tool> |
| b |
| diff -r 000000000000 -r ce1a157a41bd macros.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/macros.xml Mon Sep 14 17:06:23 2020 +0000 |
| [ |
| b'@@ -0,0 +1,551 @@\n+<macros>\n+ <token name="@VERSION@">0.9.5</token>\n+ <xml name="requirements">\n+ <requirements>\n+ <requirement type="package" version="@VERSION@">encyclopedia</requirement>\n+ <yield/>\n+ </requirements>\n+ </xml>\n+\n+ <token name="@ENCYCLOPEDIA_WIKI@">\n+EncyclopeDIA_ is library search engine comprised of several algorithms for DIA data analysis and can search for peptides using either DDA-based spectrum libraries or DIA-based chromatogram libraries. See: https://bitbucket.org/searleb/encyclopedia/wiki/Home\n+\n+.. _EncyclopeDIA: https://bitbucket.org/searleb/encyclopedia/wiki/Home\n+ </token>\n+ <xml name="citations">\n+ <citations>\n+ <citation type="doi">10.1038/s41467-018-07454-w</citation>\n+ <citation type="doi">10.1038/s41467-020-15346-1</citation>\n+ <citation type="doi">10.1074/mcp.P119.001913</citation>\n+ <yield/>\n+ </citations>\n+ </xml>\n+\n+ <token name="@CMD_IMPORTS@">\n+#import re\n+#def identifier_or_name($input1)\n+ #if hasattr($input1, \'element_identifier\')\n+ #return $input1.element_identifier\n+ #else\n+ #return $input1.name\n+ #end if\n+#end def\n+#def clean($name1)\n+ #set $name_clean = $re.sub(\'[^\\w\\-_]\', \'_\', $re.sub(\'(?i)[.](fa|fasta|imzml|mzml)$\',\'\', $re.sub(\'.*/\',\'\', $name1.rstrip(\'.gz\'))))\n+ #return $name_clean\n+#end def\n+#def ln_name($ds) \n+ #set $ext = \'\'\n+ #if $ds.is_of_type(\'mzml\') or $ds.is_of_type(\'imzml\')\n+ #set $ext = ".mzML"\n+ #else if $ds.is_of_type(\'elib\')\n+ #set $ext = ".elib"\n+ #else if $ds.is_of_type(\'dlib\')\n+ #set $ext = ".dlib"\n+ #else if $ds.is_of_type(\'blib\')\n+ #set $ext = ".blib"\n+ #else if $ds.is_of_type(\'fasta\')\n+ #set $ext = ".fasta"\n+ #else if $ds.is_of_type(\'fasta.gz\')\n+ #set $ext = ".fasta.gz"\n+ #end if\n+ #set $name = "%s%s" % ($clean($identifier_or_name($ds)),$ext) \n+ #return $name\n+#end def\n+#set $i_name = None\n+#set $f_name = None\n+#set $l_name = None\n+#set $t_name = None\n+ </token>\n+\n+ <xml name="scan_input">\n+ <param name="scan_input" argument="-i" type="data" format="imzml,mzml" label="Spectrum file in mzML format"> \n+ <help>@MSCONVERT_RAW@</help>\n+ </param>\n+ </xml>\n+ <token name="@LINK_SCAN_INPUT@"><![CDATA[\n+ #set $i_name = $ln_name($scan_input)\n+ ln -s \'$scan_input\' \'$i_name\' &&\n+ ]]></token>\n+ <token name="@SCAN_INPUT@">\n+ -i \'$i_name\'\n+ </token>\n+\n+ <xml name="scan_inputs">\n+ <param name="scan_inputs" argument="-i" type="data" format="imzml,mzml" multiple="true" label="Spectrum files in mzML format">\n+ <help>@MSCONVERT_RAW@</help>\n+ </param>\n+ </xml>\n+ <token name="@LINK_SCAN_INPUTS@"><![CDATA[\n+ #set $inputs_dir = \'inputs\'\n+ mkdir -p $inputs_dir &&\n+ #for $sf in $scan_inputs\n+ #set $i_name = $ln_name($sf)\n+ ln -s \'$sf\' \'${inputs_dir}/${i_name}\' &&\n+ #end for\n+ ]]></token>\n+ <token name="@SCAN_INPUTS@">\n+ -i \'$inputs_dir\'\n+ </token>\n+\n+ <xml name="fasta_input">\n+ <param name="fasta" argument="-f" type="data" format="fasta" label="Background proteome protein fasta database"> \n+ <help>provides the necessary peptide-to-protein links not specified in the spectrum library</help>\n+ </param>\n+ </xml>\n+ <token name="@LINK_FASTA_INPUT@"><![CDATA[\n+ #set $f_name = $ln_name($fasta)\n+ ln -s \'$fasta\' \'$f_name\' &&\n+ ]]></token>\n+ <token name="@FASTA_INPUT@">\n+ -f \'$f_name\'\n+ </token>\n+\n+ <xml name="target_fasta">\n+ <param name="target_fasta" argument="-t" type="data" format="fasta" label="Target fasta database" optional="true"> \n+ <help>Optional - Only analyze this subset of the background fasta proteome</help>\n+ </param>\n+ <param argument="-tp" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Target FASTA file contains peptides">\n+ '..b' <param argument="-numberOfQuantitativePeaks" type="integer" value="3" min="1" max="10" label="numberOfQuantitativePeaks" optional="true"/>\n+<!--\n+ <param argument="-addDecoysToBackground" type="boolean" truevalue="true" falsevalue="false" checked="false" label="addDecoysToBackground"/>\n+ <param argument="-dontRunDecoys" type="boolean" truevalue="true" falsevalue="false" checked="false" label="dontRunDecoys"/>\n+-->\n+ </when>\n+ </conditional>\n+ </xml>\n+ <token name="@SEARCH_OPTIONS@">\n+ #if $options.search.set_search == \'yes\'\n+ -minCharge $options.search.minCharge\n+ -maxCharge $options.search.maxCharge\n+ -minLength $options.search.minLength\n+ -maxLength $options.search.maxLength\n+ -minEluteTime $options.search.minEluteTime\n+ -maxMissedCleavage $options.search.maxMissedCleavage\n+ -minQuantitativeIonNumber $options.search.minQuantitativeIonNumber\n+ -minNumOfQuantitativePeaks $options.search.minNumOfQuantitativePeaks\n+ -numberOfQuantitativePeaks $options.search.numberOfQuantitativePeaks\n+ ## -addDecoysToBackground $options.search.addDecoysToBackground\n+ ## -dontRunDecoys $options.search.dontRunDecoys\n+ #end if\n+ </token>\n+\n+ <xml name="options_section">\n+ <section name="options" title="Parameter Settings" expanded="false">\n+ <expand macro="common_options"/>\n+ <expand macro="mass_library_tolerance"/>\n+ <expand macro="percolator_options"/>\n+ <expand macro="peak_options"/>\n+ <expand macro="window_options"/>\n+ <expand macro="modification_options"/>\n+ <expand macro="search_options"/>\n+ </section>\n+ </xml>\n+\n+ <xml name="libexport">\n+ <param argument="-a" type="boolean" truevalue="true" falsevalue="false" checked="false" label="align between files"/>\n+ </xml>\n+\n+ <token name="@SEARCH2LIB_CMDS@"><![CDATA[\n+ @CMD_IMPORTS@\n+ @LINK_SCAN_INPUTS@\n+ @LINK_FASTA_INPUT@\n+ @LINK_TARGET_FASTA@\n+ @LINK_LIB_INPUT@\n+ for SCAN_FILE in `ls -1 inputs/*`; do\n+ echo "\\$SCAN_FILE" &&\n+ EncyclopeDIA -Djava.awt.headless=true -Duser.language=en-US -Duser.region=US\n+ -Xmx\\$[ \\${GALAXY_MEMORY_MB:-20480} / 1024 ]g\n+ -numberOfThreadsUsed "\\${GALAXY_SLOTS:-4}"\n+ #if not $library\n+ -walnut\n+ #end if\n+ -i \\$SCAN_FILE\n+ @FASTA_INPUT@\n+ @TARGET_FASTA@\n+ @LIB_INPUT@\n+ @COMMON_OPTIONS@\n+ @MASS_LIBRARY_TOLERANCE@\n+ @PERCOLATOR_OPTIONS@\n+ @PEAK_OPTIONS@\n+ @WINDOW_OPTIONS@\n+ @MODIFICATION_OPTIONS@\n+ @SEARCH_OPTIONS@ | tee -a search2lib.log\n+ ; done &&\n+ for TXT in `find inputs/*.mzML.[efw]*[ast].txt`; do TRGT=`echo \\$TXT | sed \'s/mzML/dia/\'`; ln -s \\$TXT \\$TRGT; done &&\n+ EncyclopeDIA -Djava.awt.headless=true -Duser.language=en-US -Duser.region=US -Xmx\\$[ \\${GALAXY_MEMORY_MB:-20480} / 1024 ]g -libexport\n+ #if not $library\n+ -pecan\n+ #end if\n+ @SCAN_INPUTS@\n+ @FASTA_INPUT@\n+ @TARGET_FASTA@\n+ @LIB_INPUT@\n+ -a $a\n+ -o chromatogram_library.elib\n+ && ls -l ./*.* inputs/*\n+ | tee -a search2lib.log\n+]]>\n+ </token>\n+ <token name="@MSCONVERT_CMD@"><![CDATA[\n+ msconvert --zlib --64 --mzML --simAsSpectra --filter "peakPicking true 1-" --filter "demultiplex optimization=overlap_only" *.raw\n+]]>\n+ </token>\n+ <token name="@MSCONVERT_RAW@"><![CDATA[\n+mzML conversion from RAW requires special options: @MSCONVERT_CMD@\n+]]>\n+ </token>\n+ <token name="@MSCONVERT_HELP@"><![CDATA[\n+\n+ The MSConvert command can be used to convert and deconvolute DIA raw files to mzML format. You need to use these options:\n+\n+ ::\n+\n+ @MSCONVERT_CMD@\n+\n+]]>\n+ </token>\n+</macros>\n' |
| b |
| diff -r 000000000000 -r ce1a157a41bd static/images/SearchToLib_Workflow.png |
| b |
| Binary file static/images/SearchToLib_Workflow.png has changed |
