Galaxy |

Changeset 0:62a718b76f62 (2020-09-14)

Next changeset 1:36880dfd9fa7 (2021-04-08)

Commit message:
"planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/encyclopedia/tools/encyclopedia commit d94002fc79f552c8a64ffca86298396b1568df97"

added:
encyclopedia_searchtolib.xml
macros.xml
static/images/SearchToLib_Workflow.png

diff -r 000000000000 -r 62a718b76f62 encyclopedia_searchtolib.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/encyclopedia_searchtolib.xml Mon Sep 14 17:06:51 2020 +0000

[

b'@@ -0,0 +1,152 @@\n+<tool id="encyclopedia_searchtolib" name="SearchToLib" version="@VERSION@.0">\n+ <description>Build a Chromatogram Library from Data-Independent Acquisition (DIA) MS/MS Data</description>\n+ <macros>\n+ <import>macros.xml</import>\n+ </macros>\n+ <expand macro="requirements" />\n+ <command detect_errors="aggressive"><![CDATA[\n+ @SEARCH2LIB_CMDS@\n+ ]]></command>\n+ <inputs>\n+ <expand macro="scan_inputs"/>\n+ <expand macro="lib_input" optional="true" libhelp="Use a Prosit dlib spectral library to make a chromatogram elib using EncyclopeDIA, or else leave blank to make a Chromatogram library from just the fasta using Walnut"/>\n+ <expand macro="fasta_input"/>\n+ <expand macro="target_fasta"/>\n+ <expand macro="options_section"/>\n+ <param argument="-a" type="boolean" truevalue="true" falsevalue="false" checked="false" label="align between files" help="retention-time alignment of peptides is generally not needed when when building a library from narrow-window spectrums"/>\n+ <param name="select_outputs" type="select" label="Select outputs" multiple="true">\n+ <option value="log" selected="true">log</option>\n+ <option value="elib" selected="true">elib</option>\n+ <option value="features" selected="false">concatenated_features.txt</option>\n+ <option value="results" selected="false">concatenated_results.txt</option>\n+ <option value="decoy" selected="false">concatenated_decoy.txt</option>\n+ <option value="rt_plots" selected="false">Retention Time Plots (requires library)</option>\n+ <option value="rt_tables" selected="false">Retention Time Tables (requires library)</option>\n+ <option value="peptides" selected="false">peptides.txt (requires align between files)</option>\n+ <option value="proteins" selected="false">proteins.txt (requires align between files)</option>\n+ </param>\n+ </inputs>\n+ <outputs>\n+ <data name="log" format="txt" label="${tool.name} ${on_string} log" from_work_dir="search2lib.log">\n+ <filter>\'log\' in select_outputs</filter>\n+ </data>\n+ <data name="elib" format="elib" label="${tool.name} ${on_string} elib" from_work_dir="chromatogram_library.elib">\n+ <filter>\'elib\' in select_outputs</filter>\n+ </data>\n+ <data name="features" format="tabular" label="${tool.name} ${on_string} concatenated_features.txt" from_work_dir="inputs/chromatogram_library_concatenated_features.txt">\n+ <filter>\'features\' in select_outputs</filter>\n+ <actions>\n+ <action name="column_names" type="metadata" default="id,TD,ScanNr,topN,rank,peakZScore,peakCalibratedScore,deltaSn,avgIdotp,midIdotp,peakScore,peakWeightedScore,NCI,CIMassErrMean,CIMassErrVar,precursorMassErrMean,precursorMassErrVar,peakSimilarity,sampledTimes,midTime,spectraNorm,pepLength,charge2,charge3,precursorMz,sequence,protein" />\n+ </actions>\n+ </data>\n+ <data name="results" format="tabular" label="${tool.name} ${on_string} concatenated_results.txt" from_work_dir="inputs/chromatogram_library_concatenated_results.txt">\n+ <filter>\'results\' in select_outputs</filter>\n+ <actions>\n+ <action name="column_names" type="metadata" default="PSMId,score,q-value,posterior_error_prob,peptide,proteinIds" />\n+ </actions>\n+ </data>\n+ <data name="decoy" format="tabular" label="${tool.name} ${on_string} concatenated_decoy.txt" from_work_dir="inputs/chromatogram_library_concatenated_decoy.txt">\n+ <filter>\'decoy\' in select_outputs</filter>\n+ <actions>\n+ <action name="column_names" type="metadata" default="PSMId,score,q-value,posterior_error_prob,peptide,proteinIds" />\n+ </actions>\n+ </data>\n+ <collection name="rt_plots" type="list" label="${tool.name} - ${on_string}: Ret'..b'ram_library.elib.proteins.txt">\n+ <filter>a and \'proteins\' in select_outputs</filter>\n+ <actions>\n+ <action name="column_names" type="metadata" default="Protein,NumPeptides,PeptideSequences" />\n+ </actions>\n+ </data>\n+ </outputs>\n+ <tests>\n+ <test>\n+ <param name="scan_inputs" ftype="mzml" value="BCS_hela_narrow_3_1.mzML,BCS_hela_narrow_3_2.mzML"/>\n+ <param name="library" ftype="dlib" value="small_pan_human_library.dlib"/>\n+ <param name="fasta" ftype="fasta" value="uniprot_human.fasta"/>\n+ <param name="select_outputs" value="log,elib,features,results"/>\n+ <output name="results" ftype="tabular">\n+ <assert_contents>\n+ <has_text text="QDSAAVGFDYK"/>\n+ </assert_contents>\n+ </output>\n+ </test>\n+ <test>\n+ <param name="scan_inputs" ftype="mzml" value="BCS_hela_narrow_3_1.mzML,BCS_hela_narrow_3_2.mzML"/>\n+ <param name="fasta" ftype="fasta" value="uniprot_human.fasta"/>\n+ <param name="select_outputs" value="log,elib,features,results"/>\n+ <output name="results" ftype="tabular">\n+ <assert_contents>\n+ <has_text text="QDSAAVGFDYK"/>\n+ </assert_contents>\n+ </output>\n+ </test>\n+ </tests>\n+ <help><![CDATA[\n+**SearchToLIB**\n+\n+@ENCYCLOPEDIA_WIKI@\n+\n+SearchToLIB uses the EncyclopeDIA algorithm, or the Walnut (Pecan) algorithm, to search Data-Independent Acquisition (DIA) MS/MS spectrum files and creates a DIA elib chromatogram library for EncyclopeDIA DIA quantitation search. \n+\n+\n+**Inputs**\n+\n+ - Spectrum files in mzML format\n+ - A protein data base in fasta format\n+ - An optional DDA Spectral library (.dlib) that can be generated by Prosit\n+ - *SearchToLIB uses Enclopedia if the Prosit dlib is provided, otherwise it uses Walnut with just a fasta.*\n+\n+@MSCONVERT_HELP@\n+\n+**Outputs**\n+\n+ - A log file\n+ - A Chromatogram Library (.elib)\n+ - The identified features in tabular format\n+ Feature values of scans that are used by percolator to determine matches.\n+ - The identified Peptide Spectral Match results in tabular format\n+ Columns: PSMId, score, q-value, posterior_error_prob, peptide, proteinIds\n+ - The identified peptides in tabular format\n+ Per peptide: the normalized intensity for each scan file.\n+ Columns: Peptide, Protein, numFragments, intensity_in_file1, intensity_in_file2, ...\n+ - The identified proteins in tabular format\n+ Per protein: the normalized intensity for each scan file.\n+ Columns: Protein, NumPeptides, PeptideSequences, intensity_in_file1, intensity_in_file2, ...\n+\n+**Typical DIA Workflow**\n+\n+Two sets of Mass Spec MS/MS DIA data are collected for the experiment. In addition to collecting wide-window DIA experiments on each quantitative replicate, a pool containing peptides from every condition is measured using several staggered narrow-window DIA experiments.\n+\n+ 1. SearchToLib is first run with the pooled narrow-window mzML files to create a combined DIA elib chromatogram library. \n+ If a Spectral library argument is provided, for example from **Prosit**, SearchToLIB uses EncyclopeDIA to search each input spectrum mzML file. \n+ Otherwise, SearchToLIB uses Walnut, a FASTA database search engine for DIA data that uses PECAN-style scoring.\n+\n+\n+ * Prosit_ generates a predicted spectrum library of fragmentation patterns and retention times for every +2H and +3H tryptic peptide in a FASTA database, with up to one missed cleavage.\n+\n+\n+ 2. EncyclopeDIA Quantify is then run on the wide-window quantitative replicate mzML files using that chromatogram library to produce quantification results.\n+\n+.. image:: SearchToLib_Workflow.png\n+ :width: 810\n+ :height: 580\n+\n+.. _Prosit: https://www.proteomicsdb.org/prosit\n+\n+ ]]></help>\n+ <expand macro="citations" />\n+</tool>\n'

diff -r 000000000000 -r 62a718b76f62 macros.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/macros.xml Mon Sep 14 17:06:51 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+ </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'

diff -r 000000000000 -r 62a718b76f62 static/images/SearchToLib_Workflow.png

Binary file static/images/SearchToLib_Workflow.png has changed