Mercurial > repos > jjohnson > encyclopedia_quantify
diff encyclopedia_quantify.xml @ 0:d3a6bc607825 draft
"planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/encyclopedia/tools/encyclopedia commit d0ac7888263b785e5aa039be6454d665b239e808-dirty"
author | jjohnson |
---|---|
date | Tue, 30 Jun 2020 11:34:57 -0400 |
parents | |
children | acf6acfc8632 |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/encyclopedia_quantify.xml Tue Jun 30 11:34:57 2020 -0400 @@ -0,0 +1,130 @@ +<tool id="encyclopedia_quantify" name="EncyclopeDIA Quantify" version="@VERSION@.0"> + <description>samples from Data-Independent Acquisition (DIA) MS/MS Data</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements" /> + <command detect_errors="exit_code"><![CDATA[ + @CMD_IMPORTS@ + @LINK_SCAN_INPUTS@ + @LINK_FASTA_INPUT@ + @LINK_TARGET_FASTA@ + @LINK_LIB_INPUT@ + for SCAN_FILE in `ls -1 inputs/*`; do + echo "\$SCAN_FILE" && + EncyclopeDIA -Djava.awt.headless=true -Xmx20g + -i \$SCAN_FILE + @FASTA_INPUT@ + @TARGET_FASTA@ + @LIB_INPUT@ + @COMMON_OPTIONS@ + @MASS_LIBRARY_TOLERANCE@ + @PERCOLATOR_OPTIONS@ + @PEAK_OPTIONS@ + @WINDOW_OPTIONS@ + @MODIFICATION_OPTIONS@ + @SEARCH_OPTIONS@ | tee -a search2lib.log + ; done && + EncyclopeDIA -Djava.awt.headless=true -Xmx12g -libexport + @SCAN_INPUTS@ + @FASTA_INPUT@ + @TARGET_FASTA@ + @LIB_INPUT@ + -a $a + -o chromatogram_library.elib + | tee -a search2lib.log + ]]></command> + <inputs> + <expand macro="scan_inputs"/> + <expand macro="lib_input" optional="false" libhelp="Use a Chromatogram elib from SearchToLib"/> + <expand macro="fasta_input"/> + <expand macro="target_fasta"/> + <param argument="-a" type="boolean" truevalue="true" falsevalue="false" checked="true" label="align between files" help="retention-time alignment of peptides should be enabled when quantifying samples"/> + <expand macro="common_options"/> + <expand macro="mass_library_tolerance"/> + <expand macro="percolator_options"/> + <expand macro="peak_options"/> + <expand macro="window_options"/> + <expand macro="modification_options"/> + <expand macro="search_options"/> + <param name="select_outputs" type="select" label="Select outputs" multiple="true"> + <option value="log" selected="true">log</option> + <option value="elib" selected="true">elib</option> + <option value="features" selected="true">concatenated_features.txt</option> + <option value="results" selected="true">concatenated_results.txt</option> + <option value="decoy" selected="false">concatenated_decoy.txt</option> + <option value="peptides" selected="true">peptides.txt (requires align between files)</option> + <option value="proteins" selected="true">proteins.txt (requires align between files)</option> + </param> + </inputs> + <outputs> + <data name="log" format="txt" label="${tool.name} ${on_string} log" from_work_dir="search2lib.log"> + <filter>'log' in select_outputs</filter> + </data> + <data name="elib" format="elib" label="${tool.name} ${on_string} elib" from_work_dir="chromatogram_library.elib"> + <filter>'elib' in select_outputs</filter> + </data> + <data name="features" format="tabular" label="${tool.name} ${on_string} concatenated_features.txt" from_work_dir="inputs/chromatogram_library_concatenated_features.txt"> + <filter>'features' in select_outputs</filter> + <actions> + <action name="column_names" type="metadata" default="id,TD,ScanNr,topN,rank,peakZScore,peakCalibratedScore,deltaSn,avgIdotp,midIdotp,peakScore,peakWeightedScore,NCI,CIMassErrMean,CIMassErrVar,precursorMassErrMean,precursorMassErrVar,peakSimilarity,sampledTimes,midTime,spectraNorm,pepLength,charge2,charge3,precursorMz,sequence,protein" /> + </actions> + </data> + <data name="results" format="tabular" label="${tool.name} ${on_string} concatenated_results.txt" from_work_dir="inputs/chromatogram_library_concatenated_results.txt"> + <filter>'results' in select_outputs</filter> + <actions> + <action name="column_names" type="metadata" default="PSMId,score,q-value,posterior_error_prob,peptide,proteinIds" /> + </actions> + </data> + <data name="decoy" format="tabular" label="${tool.name} ${on_string} concatenated_decoy.txt" from_work_dir="inputs/chromatogram_library_concatenated_decoy.txt"> + <filter>'decoy' in select_outputs</filter> + <actions> + <action name="column_names" type="metadata" default="PSMId,score,q-value,posterior_error_prob,peptide,proteinIds" /> + </actions> + </data> + <data name="peptides" format="tabular" label="${tool.name} ${on_string} peptides.txt" from_work_dir="chromatogram_library.peptides.txt"> + <filter>a and 'peptides' in select_outputs</filter> + <actions> + <action name="column_names" type="metadata" default="Peptide,Protein,numFragments" /> + </actions> + </data> + <data name="proteins" format="tabular" label="${tool.name} ${on_string} proteins.txt" from_work_dir="chromatogram_library.proteins.txt"> + <filter>a and 'proteins' in select_outputs</filter> + <actions> + <action name="column_names" type="metadata" default="Protein,NumPeptides,PeptideSequences" /> + </actions> + </data> + </outputs> + <help><![CDATA[ + +**EncyclopeDIA Quantify** + +@ENCYCLOPEDIA_WIKI@ + +EncyclopeDIA Quantify retention-time aligns peptides from the chromatogram library and produces quantitation results. + +@MSCONVERT_HELP@ + +**Typical DIA SearchToLib Workflow** + +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. + + 1. SearchToLib is first run with the pooled narrow-window mzML files to create a combined DIA elib chromatogram library. + If a Spectral library argument is provided, for example from **Prosit**, SearchToLIB uses EncyclopeDIA to search each input spectrum mzML file. + Otherwise, SearchToLIB uses Walnut, a FASTA database search engine for DIA data that uses PECAN-style scoring. + + + * 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. + + + 2. EncyclopeDIA Quantify is then run on the wide-window quantitative replicate mzML files using that chromatogram library, with the *align between files* option, to produce quantification results. + +.. image:: SearchToLib_Workflow.png + :height: 439 + :width: 768 + +.. _Prosit: https://www.proteomicsdb.org/prosit + + ]]></help> + <expand macro="citations" /> +</tool>