Mercurial > repos > jjohnson > peptideshaker
changeset 1:fa76abf69433 draft
planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/peptideshaker commit e09348a0c372d4355c5dda6519e52ff17e0e8621-dirty
| author | jjohnson |
|---|---|
| date | Fri, 08 Jun 2018 15:58:53 -0400 |
| parents | 8b99cb00e1c4 |
| children | eea7e945f479 |
| files | README.rst datatypes_conf.xml fasta_cli.xml ident_params.xml macros.xml macros_basic.xml peptide_shaker.xml searchgui.xml test-data/IdentificationParametersAndFastaDefault.zip test-data/IdentificationParametersAndFastaSpecific.zip test-data/Identification_Parameters_default.par test-data/Identification_Parameters_specific.par |
| diffstat | 12 files changed, 148 insertions(+), 1631 deletions(-) [+] |
line wrap: on
line diff
--- a/README.rst Tue May 15 14:50:35 2018 -0400 +++ b/README.rst Fri Jun 08 15:58:53 2018 -0400 @@ -3,7 +3,7 @@ - Home: <https://github.com/galaxyproteomics/tools-galaxyp/> - Galaxy Tool Shed: <http://toolshed.g2.bx.psu.edu/view/galaxyp/peptideshaker> -- Tool ID: `peptideshaker`, `search_gui` +- Tools ID: `peptide_shaker`, `search_gui` Description @@ -11,7 +11,17 @@ Perform protein identification combining numerous search engines (using SearchGUI) followed by peptide and protein inference with PeptideShaker. -Includes tool wrappers for SearchGUI and PeptideShaker. The SearchGUI tool takes any number of mgf files and performs searches on these. It creates a large zip archive with all search results, the original database and spectra. This can then be fed to the PeptideShaker tool which merges the results and performs peptide and protein inference. +Includes tool wrappers for FastaCLI, IdentificationParametersCLI, SearchGUI and PeptideShaker. + + + +FastaCLI adds decoy sequences to any fasta file. + +IdentificationParametersCLI allows to create a compressed zip file with a parameters (par) file which can be (re)used later to parameterize SearchGUI or PeptideShaker, and the fasta file referred. + +The SearchGUI tool takes any number of mgf files and performs searches on these. It creates a large zip archive with all search results, the original database and spectra. + +This can then be fed to the PeptideShaker tool which merges the results and performs peptide and protein inference. General Requirements @@ -31,32 +41,30 @@ ----------------- Running MS Amanda on Linux requires that you have Mono installed. Mono 3.2.1 or newer is required. If you install via the toolshed Mono should be installed automatically, however if this does not work you can install it manually. - + On ubuntu Mono can be installed as follows sudo apt-get install mono-runtime sudo apt-get install libmono-system-core4.0-cil -For more help on installing Mono please see http://www.mono-project.com/download. +For more help on installing Mono please see http://www.mono-project.com/download. Note ---- -- Requires Galaxy release v15.10 or later, which fixes the installation of package_peptideshaker_1_1 and provides a searchgui_archive datatype that includes a version - -- PeptideShaker may require xvfb to simulate an X environment if this is installed on a headless server. +- Requires Galaxy release v16.01 or later. See: -* <https://code.google.com/p/peptide-shaker/> -* <https://code.google.com/p/searchgui/> +* <http://compomics.github.io/projects/peptide-shaker.html/> +* <http://compomics.github.io/projects/searchgui.html/> Search GUI - Fixed and Variable Modifications ------------------------------------------- - Options for modifications are read from local data file: searchgui_mods.loc - This is copied from searchgui_mods.loc.sample on the first installation. + This is copied from searchgui_mods.loc.sample on the first installation. The modifications are from: https://github.com/compomics/compomics-utilities/blob/master/src/main/java/com/compomics/util/experiment/identification/search_parameters_cli/IdentificationParametersInputBean.java
--- a/datatypes_conf.xml Tue May 15 14:50:35 2018 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,11 +0,0 @@ -<?xml version="1.0"?> -<datatypes> - <registration display_path="display_applications"> - <datatype extension="par" type="galaxy.datatypes.text:Json" display_in_upload="true" subclass="true" mimetype="application/json"> - </datatype> - - </registration> - <sniffers> - <sniffer type="galaxy.datatypes.text:Json"/> - </sniffers> -</datatypes>
--- a/fasta_cli.xml Tue May 15 14:50:35 2018 -0400 +++ b/fasta_cli.xml Fri Jun 08 15:58:53 2018 -0400 @@ -12,32 +12,28 @@ <expand macro="stdio" /> <command> <![CDATA[ - - ## #set $temp_stderr = "searchgui_stderr" #set $bin_dir = "bin" mkdir output; cwd=`pwd`; - export HOME=\$cwd; - ## echo the search engines to run - ##echo "$search_engines_options.engines"; - echo "DB: ${input_database.display_name} sequences: ${input_database.metadata.sequences}"; + echo 'DB: ${input_database.display_name} sequences: ${input_database.metadata.sequences}'; - cp "${input_database}" input_database.fasta; + cp '${input_database}' input_database.fasta; ########################################### #### Creating decoy database #### ########################################### - echo "Creating decoy database."; - searchgui eu.isas.searchgui.cmd.FastaCLI --exec_dir="\$cwd/${bin_dir}" -in input_database.fasta -decoy && + echo 'Creating decoy database.'; + searchgui eu.isas.searchgui.cmd.FastaCLI --exec_dir='./bin/' -in input_database.fasta -decoy && rm input_database.fasta; - echo "Decoy database:"; - echo "\$cwd/input_database_concatenated_target_decoy.fasta"; + echo 'Decoy database:'; + echo '\$cwd/input_database_concatenated_target_decoy.fasta'; + echo "new fasta"; + echo './input_database_concatenated_target_decoy.fasta'; exit_code_for_galaxy=\$?; - ## cat $temp_stderr 2>&1; (exit \$exit_code_for_galaxy) ]]> </command> @@ -57,7 +53,8 @@ <help> **What it does** -Appends decoy sequences to FASTA files. +Appends decoy sequences to FASTA files adding to the accessions (as a suffix) "_REVERSED". +This format is adequated to be used by SearchGUI and PeptideShaker tools. </help> <expand macro="citations" /> </tool>
--- a/ident_params.xml Tue May 15 14:50:35 2018 -0400 +++ b/ident_params.xml Fri Jun 08 15:58:53 2018 -0400 @@ -8,6 +8,7 @@ <requirements> <requirement type="package" version="@SEARCHGUI_VERSION@">searchgui</requirement> <requirement type="package" version="3.0">zip</requirement> + <requirement type="package">JQ</requirement> </requirements> <expand macro="stdio" /> <command> @@ -19,18 +20,22 @@ cwd=`pwd`; export HOME=\$cwd; - echo "DB: ${input_database.display_name} sequences: ${input_database.metadata.sequences}"; + echo 'DB: ${input_database.display_name} sequences: ${input_database.metadata.sequences}'; + + ## copy the input FASTA file to the working folder + cp '${input_database}' './input_database.fasta'; + ##################################################### ## generate IdentificationParameters for SearchGUI ## ##################################################### (searchgui eu.isas.searchgui.cmd.IdentificationParametersCLI - --exec_dir="\$cwd/${bin_dir}" - -out "\$cwd/SEARCHGUI_IdentificationParameters.par" + --exec_dir="./bin/" + -out './SEARCHGUI_IdentificationParameters_temp.par' ## SPECTRUM MATCHING PARAMETERS - -db "${input_database}" + -db './input_database.fasta' -frag_tol '${spectrum_matching_options.fragment_tol}' -frag_ppm '${spectrum_matching_options.fragment_tol_units}' @@ -102,15 +107,15 @@ ## PTM LOCALIZATION - -ptm_score "${advanced_options.ptm_localization_options.ptm_score.ptm_score_selector}" + -ptm_score '${advanced_options.ptm_localization_options.ptm_score.ptm_score_selector}' #if $advanced_options.ptm_localization_options.ptm_score.ptm_score_selector == 1 - -score_neutral_losses "${advanced_options.ptm_localization_options.ptm_score.neutral_losses}" + -score_neutral_losses '${advanced_options.ptm_localization_options.ptm_score.neutral_losses}' #if str($advanced_options.ptm_localization_options.ptm_score.ptm_threshold) != '' - -ptm_threshold "${advanced_options.ptm_localization_options.ptm_score.ptm_threshold}" + -ptm_threshold '${advanced_options.ptm_localization_options.ptm_score.ptm_threshold}' #end if #end if - -ptm_alignment "${advanced_options.ptm_localization_options.ptm_alignment}" - -ptm_sequence_matching_type "${advanced_options.ptm_localization_options.ptm_sequence_matching_type}" + -ptm_alignment '${advanced_options.ptm_localization_options.ptm_alignment}' + -ptm_sequence_matching_type '${advanced_options.ptm_localization_options.ptm_sequence_matching_type}' ## GENE ANNOTATION @@ -128,14 +133,14 @@ ## TODO: VALIDATION LEVELS - -protein_fdr "${advanced_options.validation_levels_options.protein_fdr}" - -peptide_fdr "${advanced_options.validation_levels_options.peptide_fdr}" - -psm_fdr "${advanced_options.validation_levels_options.psm_fdr}" + -protein_fdr '${advanced_options.validation_levels_options.protein_fdr}' + -peptide_fdr '${advanced_options.validation_levels_options.peptide_fdr}' + -psm_fdr '${advanced_options.validation_levels_options.psm_fdr}' ## FRACTION ANALYSIS - -protein_fraction_mw_confidence "${advanced_options.fraction_analysis_options.protein_fraction_mw_confidence}" + -protein_fraction_mw_confidence '${advanced_options.fraction_analysis_options.protein_fraction_mw_confidence}' ## -- SEARCH ENGINES SPECIFIC PARAMETERS -- @@ -222,15 +227,18 @@ #if $advanced_options.searchengines_advanced_options.msgf.msgf_advanced == "yes" -msgf_decoy ${advanced_options.searchengines_advanced_options.msgf.msgf_decoy} - -msgf_min_pep_length ${advanced_options.searchengines_advanced_options.msgf.msgf_min_pep_length} - -msgf_max_pep_length ${advanced_options.searchengines_advanced_options.msgf.msgf_max_pep_length} - -msgf_termini ${advanced_options.searchengines_advanced_options.msgf.msgf_termini} - -msgf_num_ptms ${advanced_options.searchengines_advanced_options.msgf.msgf_num_ptms} -msgf_instrument ${advanced_options.searchengines_advanced_options.msgf.msgf_instrument} -msgf_fragmentation ${advanced_options.searchengines_advanced_options.msgf.msgf_fragmentation} -msgf_protocol ${advanced_options.searchengines_advanced_options.msgf.msgf_protocol} + -msgf_termini ${advanced_options.searchengines_advanced_options.msgf.msgf_termini} + -msgf_min_pep_length ${advanced_options.searchengines_advanced_options.msgf.msgf_min_pep_length} + -msgf_max_pep_length ${advanced_options.searchengines_advanced_options.msgf.msgf_max_pep_length} + -msgf_num_ptms ${advanced_options.searchengines_advanced_options.msgf.msgf_num_ptms} -msgf_num_matches ${advanced_options.searchengines_advanced_options.msgf.msgf_num_matches} -msgf_additional ${advanced_options.searchengines_advanced_options.msgf.msgf_additional} + #if $advanced_options.searchengines_advanced_options.msgf.msgf_tasks.msgf_tasks_custom == "yes" + -msgf_num_tasks ${advanced_options.searchengines_advanced_options.msgf.msgf_tasks.msgf_num_tasks} + #end if #end if @@ -420,6 +428,27 @@ 2> $temp_stderr); + ## reading from the original .par file + content_par_target_path=`cat ./SEARCHGUI_IdentificationParameters_temp.par`; + ## modifying the .par file + ## First we establish the new content for the path: .searchParameters.fastaFile.path + new_content_par_target_path=`jq '.searchParameters.fastaFile.path = \$newVal' --arg newVal './input_database.fasta' <<< "\$content_par_target_path"`; + ## Secondly, for .proteinInferencePreferences.proteinSequenceDatabase.path + new_content_par_target_path=`jq '.proteinInferencePreferences.proteinSequenceDatabase.path = \$newVal' --arg newVal './input_database.fasta' <<< "\$new_content_par_target_path"`; + + ## we generate a new .par file filled with the new fasta path. + echo 'Final identification parameters file: '; + #set $new_par_target_path = './SEARCHGUI_IdentificationParameters.par'; + echo $new_par_target_path; + echo "\$new_content_par_target_path" >> $new_par_target_path; + + ## compress both parameters and fasta file for the output + (zip ./IdentificationParametersAndFasta.zip ./SEARCHGUI_IdentificationParameters.par 2>> $temp_stderr) + + && + + (zip -u ./IdentificationParametersAndFasta.zip ./input_database.fasta 2>> $temp_stderr); + exit_code_for_galaxy=\$?; cat $temp_stderr 2>&1; (exit \$exit_code_for_galaxy) @@ -807,32 +836,21 @@ <when value="no" /> <when value="yes"> <param name="msgf_decoy" type="boolean" truevalue="1" falsevalue="0" checked="false" - label="MSGF: Search Decoys" help="If yes then a decoy database will be generated and searched. Assumed input database contains no decoys"/> - <param name="msgf_min_pep_length" type="integer" value="6" - label="MSGF: Minimum Peptide Length" help="Minimum length for a peptide to be considered"/> - <param name="msgf_max_pep_length" type="integer" value="30" - label="MSGF: Maximum Peptide Length" help="Maximum length for a peptide to be considered"/> - <param name="msgf_termini" type="select" format="txt" - label="MSGF: Number of tolerable termini" help="Searches will take much longer if selecting a value other than 2"> - <option value="0">0 (ie non-specific cleavage)</option> - <option value="1">1 (ie semi-tryptic cleavage)</option> - <option value="2" selected="true">2 (ie fully-tryptic cleavage)</option> + label="MSGF: Search Decoy Database" help="If yes then a decoy database will be generated and searched. Assumed input database contains no decoys"/> + <param name="msgf_instrument" label="MSGF: MS/MS Detector" type="select" help="Identifier of the instrument to generate MS/MS spectra (used to determine the scoring model)"> + <option value="0" >Low-res LCQ/LTQ</option> + <option value="1" >Orbitrap/FTICR</option> + <option value="2" >TOF</option> + <option value="3" selected="True">Q-Exactive</option> </param> - <param name="msgf_num_ptms" label="MSGF: Max PTMs per peptide" type="integer" value="2"/> - - <param name="msgf_instrument" label="MSGF: Instrument type" type="select" help="Identifier of the instrument to generate MS/MS spectra (used to determine the scoring model)"> - <option value="0" selected="True">Low-res LCQ/LTQ</option> - <option value="1" >High-res LTQ</option> - <option value="2" >TOF</option> - <option value="3" >Q-Exactive</option> - </param> - <param name="msgf_fragmentation" label="MSGF: Fragmentation type" type="select" help="Fragmentation method identifier (used to determine the scoring model)"> - <option value="0" selected="True">As written in the spectrum or CID if no info</option> + <param name="msgf_fragmentation" label="MSGF: Fragmentation method" type="select" help="Fragmentation method identifier (used to determine the scoring model)"> + <option value="0" >As written in the spectrum or CID if no info</option> <option value="1" >CID</option> <option value="2" >ETD</option> - <option value="3" >HCD</option> + <option value="3" selected="True">HCD</option> + <option value="4" >UVPD</option> </param> - <param name="msgf_protocol" label="MSGF: Protocol type" type="select" help="Protocol identifier. Protocols are used to enable scoring parameters for enriched and/or labeled samples"> + <param name="msgf_protocol" label="MSGF: Protocol" type="select" help="Protocol identifier. Protocols are used to enable scoring parameters for enriched and/or labeled samples"> <option value="0" selected="True">Automatic</option> <option value="1" >Phosphorylation</option> <option value="2" >iTRAQ</option> @@ -840,11 +858,34 @@ <option value="4" >TMT</option> <option value="5" >Standard</option> </param> - <param name="msgf_num_matches" label="MSGF: Maximum Number of Spectrum Matches" type="integer" value="1" help="Number of peptide matches per spectrum to report" /> - <param name="msgf_additional" label="MS-GF+ additional features" type="select" help="Additional features to export"> + <param name="msgf_termini" type="select" format="txt" + label="MSGF: Enzymatic Terminals" help="Searches will take much longer if selecting a value other than 2"> + <option value="0">None required</option> + <option value="1">At least one</option> + <option value="2" selected="true">Both</option> + </param> + <param name="msgf_min_pep_length" type="integer" value="8" + label="MSGF: Minimum Peptide Length" help="Minimum length for a peptide to be considered"/> + <param name="msgf_max_pep_length" type="integer" value="30" + label="MSGF: Maximum Peptide Length" help="Maximum length for a peptide to be considered"/> + <param name="msgf_num_ptms" label="MSGF: Max Variable PTMs per Peptide" type="integer" value="2"/> + <param name="msgf_num_matches" label="MSGF: Number of Spectrum Matches" type="integer" value="10" help="Number of peptide matches per spectrum to report" /> + <param name="msgf_additional" label="MS-GF+ additional Output" type="select" help="Additional features to export"> <option value="0" selected="True">output basic scores only</option> <option value="1" >output additional features</option> </param> + <conditional name="msgf_tasks"> + <param name="msgf_tasks_custom" type="select" label="Number of tasks to use on the threads"> + <option value="yes">Custom</option> + <option value="no" selected="True">Default</option> + </param> + <when value="no" /> + <when value="yes"> + <param name="msgf_num_tasks" type="integer" value="4" + label="MSGF: Custom number of tasks to use on the threads" + help="Manually set the number of tasks to create for the search. More tasks than threads will reduce the memory requirements of the search, but will be slower (how much depends on the inputs). Check the documentation carefully. "/> + </when> + </conditional> </when> </conditional> @@ -1222,14 +1263,15 @@ </inputs> <outputs> - <data name="Searchgui_Identification_Parameters" format="par" from_work_dir="SEARCHGUI_IdentificationParameters.par" label="${tool.name}: PAR file on ${on_string}" /> + <!-- <data name="Searchgui_Identification_Parameters" format="par" from_work_dir="SEARCHGUI_IdentificationParameters.par" label="${tool.name}: PAR file on ${on_string}" /> --> + <data name="Identification_Parameters_And_Fasta" format="zip" from_work_dir="IdentificationParametersAndFasta.zip" label="${tool.name}: Compressed PAR and FASTA files on ${on_string}" /> </outputs> <tests> <!-- Test that default parameters generates a standar par file --> <test> <param name="input_database" value="searchgui_tinydb1_concatenated_target_decoy.fasta" ftype="fasta"/> - <output name="Searchgui_Identification_Parameters" file="Identification_Parameters_default.par" ftype="par" compare="sim_size" delta="1000" /> + <output name="Identification_Parameters_And_Fasta" file="IdentificationParametersAndFastaDefault.zip" ftype="zip" compare="sim_size" delta="1000" /> </test> <!-- Test specific parameters --> <test> @@ -1241,18 +1283,19 @@ <param name="max_charge" value="3"/> <param name="xtandem_advanced" value="yes"/> <param name="xtandem_refine_selector" value="yes"/> - <output name="Searchgui_Identification_Parameters" file="Identification_Parameters_specific.par" ftype="par" compare="sim_size" delta="5000" /> + <output name="Identification_Parameters_And_Fasta" file="IdentificationParametersAndFastaSpecific.zip" ftype="zip" compare="sim_size" delta="1000" /> </test> </tests> <help> **What it does** -Creates a parameters file which can be used independently by SearchGUI or PeptideShaker apps. +Creates a zip file containing: -FASTA file used by this app must be kept in the history as the generated .par file will reference to it. +- A fasta file. +- A parameters file (.par) which can be used independently by SearchGUI or PeptideShaker apps. It makes reference to the previous fasta file. -A FASTA file with decoy sequences is recommended if SearchGUI and PeptideShaker are going to be used. +A FASTA file with decoy sequences generated by FastaCLI is recommended if SearchGUI and PeptideShaker are going to use the output of this tool. </help> <expand macro="citations" />
--- a/macros.xml Tue May 15 14:50:35 2018 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,179 +0,0 @@ -<macros> - <xml name="stdio"> - <stdio> - <exit_code range="1:" level="fatal" description="Job Failed" /> - <regex match="java.*Exception" level="fatal" description="Java Exception"/> - <regex match="Could not create the Java virtual machine" level="fatal" description="JVM Error"/> - <regex match="CompomicsError" level="fatal" description="Compomics Error"/> - </stdio> - </xml> - <token name="@GENERAL_PARAMETERS@"> - -frag_tol '${precursor_options.fragment_tol}' - -frag_ppm '${precursor_options.fragment_tol_units}' - -prec_tol '${precursor_options.precursor_ion_tol}' - -prec_ppm '${precursor_options.precursor_ion_tol_units}' - - -min_charge $precursor_options.min_charge - -max_charge $precursor_options.max_charge - -fi $precursor_options.forward_ion - -ri $precursor_options.reverse_ion - -min_isotope ${precursor_options.min_isotope} - -max_isotope ${precursor_options.max_isotope} - #if $protein_digest_options.digestion.cleavage == 'default': - ## -enzyme "Trysin" - -mc $protein_digest_options.digestion.missed_cleavages - #elif $protein_digest_options.digestion.cleavage == '0' and len($protein_digest_options.digestion.digests) > 0: - #set $enzymes = [] - #set $missed_cleavages = [] - ## #set $specificities = [] - #for $i, $digest in enumerate($protein_digest_options.digestion.digests): - #silent $enzymes.append(str($digest.enzyme)) - #silent $missed_cleavages.append(str($digest.missed_cleavages)) - ## #silent $specificities.append(str($digest.specificity)) - #end for - -enzyme "#echo ','.join($enzymes)#" - -mc "#echo ','.join($missed_cleavages)#" - ## -specificity "#echo ','.join($specificities)#" - #else: - -digestion $protein_digest_options.digestion.cleavage - #end if - - #set $fixed_mods_str = $protein_modification_options.fixed_modifications or '' - #set $variable_mods_str = $protein_modification_options.variable_modifications or '' - #if $fixed_mods_str - -fixed_mods "$fixed_mods_str" - #end if - #if $variable_mods_str - -variable_mods "$variable_mods_str" - #end if - - </token> - <token name="@SEARCHGUI_MAJOR_VERSION@">3</token> - <token name="@SEARCHGUI_VERSION@">3.2.24</token> - <xml name="general_options"> - - <section name="protein_digest_options" expanded="false" title="Protein Digestion Options"> - <conditional name="digestion"> - <param name="cleavage" type="select" label="Digestion"> - <option value="default" selected="true">Trypsin</option> - <option value="0">Select Enzymes</option> - <option value="1">Unspecific Cleavage</option> - <option value="2">Whole Protein</option> - </param> - <when value="default"> - <param name="missed_cleavages" type="integer" value="2" label="Maximum Missed Cleavages" - help="Allow peptides to contain up to this many missed enzyme cleavage sites."/> - </when> - <when value="0"> - <repeat name="digests" min="1" title="Enzymes"> - <param name="enzyme" type="select" label="Enzyme" - help="Which enzyme was used for protein digest in experiment? In most cases, trypsin is used"> - <option value="Trypsin">Trypsin</option> - <option value="Arg-C">Arg-C</option> - <option value="CNBr">CNBr</option> - <option value="Chymotrypsin (FYWL)">Chymotrypsin (FYWL)</option> - <option value="Formic Acid">Formic Acid</option> - <option value="Lys-C">Lys-C</option> - <option value="Lys-C, no P rule">Lys-C, no P rule</option> - <option value="Pepsin A">Pepsin A</option> - <option value="Trypsin + CNBr">Trypsin + CNBr</option> - <option value="Trypsin + Chymotrypsin (FYWLKR)">Trypsin + Chymotrypsin (FYWLKR)</option> - <option value="Trypsin, no P rule">Trypsin, no P rule</option> - <option value="Whole Protein">Whole Protein</option> - <option value="Asp-N">Asp-N</option> - <option value="Glu-C">Glu-C</option> - <option value="Asp-N + Glu-C">Asp-N + Glu-C</option> - <option value="Top-Down">Top-Down</option> - <option value="Semi-Tryptic">Semi-Tryptic</option> - <option value="Unspecific">Unspecific (No enzyme)</option> <!-- note: cleaves at every residue! --> - <option value="Chymotrypsin, no P rule (FYWL)">Chymotrypsin, no P rule (FYWL)</option> - <option value="Asp-N (DE)">Asp-N (DE)</option> - <option value="Glu-C (DE)">Glu-C (DE)</option> - <option value="Lys-N (K)">Lys-N (K)</option> - <option value="Thermolysin, no P rule">Thermolysin, no P rule</option> - <option value="Semi-Chymotrypsin (FYWL)">Semi-Chymotrypsin (FYWL)</option> - <option value="Semi-Glu-C">Semi-Glu-C</option> - <option value="LysargiNase">LysargiNase</option> - <option value="Semi-LysargiNase">Semi-LysargiNase</option> - <option value="Trypsin + Glu-C">Trypsin + Glu-C</option> - <option value="Semi-Arg-C">Semi-Arg-C</option> - <option value="Semi-Glu-C (DE)">Semi-Glu-C (DE)</option> - <option value="Arg-N">Arg-N</option> - <option value="Semi-Arg-N">Semi-Arg-N</option> - </param> - <param name="missed_cleavages" type="integer" value="2" label="Maximum Missed Cleavages" - help="Allow peptides to contain up to this many missed enzyme cleavage sites."/> - <!-- - <param name="specificity" type="select" label="Specificity"> - <option value="0" selected="true">Specific at both termini</option> - <option value="1">Semi-Specific - one terminus</option> - <option value="2">Specific at the N-terminus only</option> - <option value="3">Specific at the C-terminus only</option> - </param> - --> - </repeat> - </when> - <when value="1"/> - <when value="2"/> - </conditional> - </section> - - <section name="precursor_options" expanded="false" title="Precursor Options"> - <param name="precursor_ion_tol_units" type="select" label="Precursor Ion Tolerance Units" - help="Select based on instrument used, as different machines provide different quality of spectra. ppm is a standard for most precursor ions"> - <option value="1">Parts per million (ppm)</option> - <option value="0">Daltons</option> - </param> - <param name="precursor_ion_tol" type="float" value="10" label="Precursor Ion Tolerance" - help="Provide error value for precursor ion, based on instrument used. 10 ppm recommended for Orbitrap instrument"/> - <param name="fragment_tol_units" type="select" label="Fragment Tolerance Units" - help="Select based on instrument used, as different machines provide different quality of spectra. ppm is a standard for most precursor ions"> - <option value="1">Parts per million (ppm)</option> - <option value="0" selected="true">Daltons</option> - </param> - <param name="fragment_tol" type="float" value="0.5" label="Fragment Tolerance" - help="Provide error value for fragment ions, based on instrument used"/> - <param name="min_charge" label="Minimum Charge" value="2" type="integer" help="Lowest searched charge value for fragment ions"/> - <param name="max_charge" label="Maximum Charge" value="4" type="integer" help="Highest searched charge value for fragment ions"/> - <param name="forward_ion" label="Forward Ion" type="select" help="Searched fragment ion type. Select a, b or c based on collisions induced in experiment"> - <option value="a">a</option> - <option value="b" selected="true">b</option> - <option value="c">c</option> - </param> - <param name="reverse_ion" label="Reverse Ion" type="select" help="Searched fragment ion type. Select x, y, or z based on collisions induced in experiment"> - <option value="x">x</option> - <option value="y" selected="true">y</option> - <option value="z">z</option> - </param> - <param name="min_isotope" label="Minimum precursor isotope" type="integer" value="0" help="default: 0" /> - <param name="max_isotope" label="Maximum precursor isotope" type="integer" value="1" help="default: 1" /> - </section> - - <section name="protein_modification_options" expanded="false" title="Protein Modification Options"> - <param name="fixed_modifications" type="select" label="Fixed Modifications" multiple="true" - help="Occurs in known places on peptide sequence. Hold the appropriate key while clicking to select multiple items"> - <options from_file="searchgui_mods.loc"> - <column name="name" index="0" /> - <column name="value" index="0" /> - </options> - </param> - <param name="variable_modifications" type="select" label="Variable Modifications" multiple="true" - help="Can occur anywhere on the peptide sequence; adds additional error to search score. Hold the appropriate key while clicking to select multiple items"> - <options from_file="searchgui_mods.loc"> - <column name="name" index="0" /> - <column name="value" index="0" /> - </options> - </param> - </section> - - </xml> - - <xml name="citations"> - <citations> - <citation type="doi">10.1186/1471-2105-12-70</citation> - <citation type="doi">10.1002/pmic.201000595</citation> - <citation type="doi">doi:10.1038/nbt.3109</citation> - </citations> - </xml> - -</macros>
--- a/macros_basic.xml Tue May 15 14:50:35 2018 -0400 +++ b/macros_basic.xml Fri Jun 08 15:58:53 2018 -0400 @@ -3,12 +3,13 @@ <stdio> <exit_code range="1:" level="fatal" description="Job Failed" /> <regex match="java.*Exception" level="fatal" description="Java Exception"/> + <regex match="Could not reserve enough space for * object heap" level="fatal" description="Out of memory"/> <regex match="Could not create the Java virtual machine" level="fatal" description="JVM Error"/> <regex match="CompomicsError" level="fatal" description="Compomics Error"/> </stdio> </xml> <token name="@SEARCHGUI_MAJOR_VERSION@">3</token> - <token name="@SEARCHGUI_VERSION@">3.2.26</token> + <token name="@SEARCHGUI_VERSION@">3.3.1</token> <xml name="citations"> <citations> <citation type="doi">10.1186/1471-2105-12-70</citation>
--- a/peptide_shaker.xml Tue May 15 14:50:35 2018 -0400 +++ b/peptide_shaker.xml Fri Jun 08 15:58:53 2018 -0400 @@ -1,4 +1,4 @@ -<tool id="peptide_shaker" name="Peptide Shaker" version="1.16.22.0"> +<tool id="peptide_shaker" name="Peptide Shaker" version="1.16.23.0"> <description> Perform protein identification using various search engines based on results from SearchGUI </description> @@ -6,7 +6,7 @@ <import>macros_basic.xml</import> </macros> <requirements> - <requirement type="package" version="1.16.22">peptide-shaker</requirement> + <requirement type="package" version="1.16.23">peptide-shaker</requirement> </requirements> <expand macro="stdio" /> <command>
--- a/searchgui.xml Tue May 15 14:50:35 2018 -0400 +++ b/searchgui.xml Fri Jun 08 15:58:53 2018 -0400 @@ -8,14 +8,13 @@ <requirements> <requirement type="package" version="@SEARCHGUI_VERSION@">searchgui</requirement> <requirement type="package" version="3.0">zip</requirement> - <requirement type="package">JQ</requirement> </requirements> <expand macro="stdio" /> <command> <![CDATA[ #from datetime import datetime #import json - #import os; + #import os #set $exp_str = "Galaxy_Experiment_%s" % datetime.now().strftime("%Y%m%d%H%M%s") #set $samp_str = "Sample_%s" % datetime.now().strftime("%Y%m%d%H%M%s") #set $temp_stderr = "searchgui_stderr" @@ -27,7 +26,7 @@ export HOME=\$cwd; ## echo the search engines to run - echo "$search_engines_options.engines"; + echo '$search_engines_options.engines'; ##Create a searchgui.properties file for the version, which will be added to the searchgui_results if not already present echo "searchgui.version=@SEARCHGUI_VERSION@" >> searchgui.properties; @@ -36,54 +35,27 @@ #set $input_name = $mgf.display_name.split('/')[-1].replace(".mgf", "") + ".mgf" ln -s -f '${mgf}' '${input_name}'; #set $encoded_id = $__app__.security.encode_id($mgf.id) - echo "Spectrums:${mgf.display_name}(API:${encoded_id}) "; + echo 'Spectrums:${mgf.display_name}(API:${encoded_id}) '; #end for - - - ## Necessary for executing tests. The FASTA file has to be manually copied from the test-data folder to the working directory in order it can be found when using the PAR file. - cp '$__tool_directory__/test-data/searchgui_tinydb1_concatenated_target_decoy.fasta' "\$cwd/searchgui_tinydb1_concatenated_target_decoy.fasta"; - - - ## copy the input .par file to the working folder - cp "${input_par}" "\$cwd/SEARCHGUI_IdentificationParameters.par"; - echo "-.par source file:"; - echo "${input_par}"; + cp '${input_zip}' './input_par_fasta.zip'; + echo '-.zip source file:'; + echo '${input_zip}'; - ## (local) PAR file points to a FASTA file with .dat extension, which gives problems with many search engines. We should rename it to a .fasta file before passing it to SearchGUI - #set $par_target_path = "$cwd/SEARCHGUI_IdentificationParameters.par"; - echo "-.par target file:"; - echo $par_target_path; - - ## reading from the original .par file the path of the source .dat (fasta) file to be used - content_par_target_path=`cat $par_target_path`; - dat_path=`jq -r '.searchParameters.fastaFile.path' <<< "\$content_par_target_path"`; - echo "-.dat file path from target .par: "; - echo "\$dat_path"; - ## copy original .data fasta file to a local .fasta file - new_fasta_file_path="\$cwd/input_database.fasta"; - cp "\$dat_path" "\$new_fasta_file_path"; - echo "-new .fasta file path copied from source .dat file: "; - echo "\$new_fasta_file_path"; + ## Necessary for executing tests. Specific par files need to be uncompressed to be used by the tool. + jar xvf './input_par_fasta.zip' 'Identification_Parameters_default.par' 'searchgui_tinydb1_concatenated_target_decoy.fasta'; + jar xvf './input_par_fasta.zip' Identification_Parameters_specific.par searchgui_tinydb1_concatenated_target_decoy.fasta; + if [ -f ./Identification_Parameters_default.par ];then + mv ./Identification_Parameters_default.par ./SEARCHGUI_IdentificationParameters.par; + fi; + if [ -f ./Identification_Parameters_specific.par ];then + mv './Identification_Parameters_specific.par' './SEARCHGUI_IdentificationParameters.par'; + fi; - ## modifying the .par file!! - ## First we establish the new content for the path: .searchParameters.fastaFile.path - new_content_par_target_path=`jq '.searchParameters.fastaFile.path = \$newVal' --arg newVal "\$new_fasta_file_path" <<< "\$content_par_target_path"`; - ## Secondly, for .proteinInferencePreferences.proteinSequenceDatabase.path - new_content_par_target_path=`jq '.proteinInferencePreferences.proteinSequenceDatabase.path = \$newVal' --arg newVal "\$new_fasta_file_path" <<< "\$new_content_par_target_path"`; - - ## we generate a new .par file filled with the new fasta path. - #set $new_par_target_path = "$cwd/SEARCHGUI_IdentificationParameters_new.par"; - echo "\$new_content_par_target_path" >> $new_par_target_path; - echo "-new par target path: "; - echo $new_par_target_path; - - ## As PeptideShaker waits for "SEARCHGUI_IdentificationParameters.par" name, we overwrite the original file with the "_new" file - ##mv "\$cwd/SEARCHGUI_IdentificationParameters_new.par" "\$cwd/SEARCHGUI_IdentificationParameters.par" - rm $par_target_path; - mv $new_par_target_path $par_target_path; + ## By default we will always try to uncompress SEARCHGUI_IdentificationParameters.par and input_database.fasta + jar xvf './input_par_fasta.zip' SEARCHGUI_IdentificationParameters.par input_database.fasta; ################ @@ -94,7 +66,7 @@ -temp_folder `pwd` -spectrum_files \$cwd -output_folder \$cwd/output - -id_params $par_target_path + -id_params ./SEARCHGUI_IdentificationParameters.par -threads "\${GALAXY_SLOTS:-12}" @@ -194,8 +166,8 @@ ]]> </command> <inputs> - <param format="par" name="input_par" type="data" label="Identification Parameters file" - help="Select PAR file from history"/> + <param format="zip" name="input_zip" type="data" label="Identification Parameters and fasta file" + help="Select a zip file with Identification Parameters (.par) and a fasta file from history"/> <param name="peak_lists" format="mgf" type="data" multiple="true" label="Input Peak Lists (mgf)" help="Select appropriate MGF dataset(s) from history" /> @@ -258,16 +230,18 @@ <!-- Test that specifying non-default search engines works --> <test> <param name="peak_lists" value="searchgui_tinyspectra1.mgf"/> - <param name="input_par" value="Identification_Parameters_specific.par"/> + <!-- <param name="input_par" value="Identification_Parameters_specific.par"/>--> + <param name="input_zip" value="IdentificationParametersAndFastaSpecific.zip" ftype="zip" /> <param name="engines" value="X!Tandem,MSGF,MyriMatch,OMSSA,Comet"/> - <output name="output" file="tiny_searchgui_result1.zip" ftype="searchgui_archive" compare="sim_size" delta="30000" /> + <output name="searchgui_results" file="tiny_searchgui_result1.zip" ftype="searchgui_archive" compare="sim_size" delta="30000" /> </test> <!-- Test that search works with MSAmanda --> <test> <param name="peak_lists" value="searchgui_smallspectra.mgf"/> - <param name="input_par" value="Identification_Parameters_default.par"/> + <!-- <param name="input_par" value="Identification_Parameters_default.par"/>--> + <param name="input_zip" value="IdentificationParametersAndFastaDefault.zip" ftype="zip" /> <param name="engines" value="MS_Amanda"/> - <output name="output" file="smallsearch_result_amandaonly.zip" ftype="searchgui_archive" compare="sim_size" delta="5000" /> + <output name="searchgui_results" file="smallsearch_result_amandaonly.zip" ftype="searchgui_archive" compare="sim_size" delta="5000" /> </test> </tests>
--- a/test-data/Identification_Parameters_default.par Tue May 15 14:50:35 2018 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,577 +0,0 @@ -{ - "marshallableParameterType": "identification_parameters", - "name": "SEARCHGUI_IdentificationParameters", - "description": "DB: dataset_118.dat.\n", - "defaultDescription": true, - "searchParameters": { - "precursorAccuracyType": "PPM", - "fragmentAccuracyType": "DA", - "precursorTolerance": 10.0, - "precursorToleranceDalton": 0.5, - "fragmentIonMZTolerance": 0.5, - "ptmSettings": { - "fixedModifications": [], - "variableModifications": [], - "refinementVariableModifications": [], - "refinementFixedModifications": [], - "colors": {}, - "backUp": {} - }, - "nMissedCleavages": 2, - "digestionPreferences": { - "cleavagePreference": "enzyme", - "enzymes": [ - { - "id": 0, - "name": "Trypsin", - "aminoAcidBefore": [], - "aminoAcidAfter": [], - "restrictionBefore": [], - "restrictionAfter": [], - "aminoAcidBeforeSet": [ - "R", - "K" - ], - "aminoAcidAfterSet": [], - "restrictionBeforeSet": [], - "restrictionAfterSet": [ - "P" - ], - "isSemiSpecific": false, - "isWholeProtein": false, - "cvTerm": { - "ontology": "PSI-MS", - "accession": "MS:1001251", - "name": "Trypsin" - } - } - ], - "nMissedCleavages": { - "Trypsin": 2 - }, - "specificity": { - "Trypsin": "specific" - } - }, - "fastaFile": { - "path": "./searchgui_tinydb1_concatenated_target_decoy.fasta" - }, - "parametersFile": {}, - "forwardIons": [ - 1 - ], - "rewindIons": [ - 4 - ], - "minChargeSearched": { - "sign": 1, - "value": 2 - }, - "maxChargeSearched": { - "sign": 1, - "value": 4 - }, - "minIsotopicCorrection": 0, - "maxIsotopicCorrection": 1, - "refMass": 2000.0, - "algorithmParameters": { - "1": { - "type": "com.compomics.util.experiment.identification.identification_parameters.tool_specific.OmssaParameters", - "data": { - "maxEValue": 100.0, - "hitListLength": 10, - "minimalChargeForMultipleChargedFragments": { - "sign": 1, - "value": 3 - }, - "minPeptideLength": 8, - "maxPeptideLength": 30, - "removePrecursor": false, - "scalePrecursor": true, - "estimateCharge": true, - "selectedOutput": "OMX", - "memoryMappedSequenceLibraries": false, - "numberOfItotopicPeaks": 0, - "neutronThreshold": 1446.94, - "lowIntensityCutOff": 0.0, - "highIntensityCutOff": 0.2, - "intensityCutOffIncrement": 5.0E-4, - "singleChargeWindow": 27, - "doubleChargeWindow": 14, - "nPeaksInSingleChargeWindow": 2, - "nPeaksInDoubleChargeWindow": 2, - "maxHitsPerSpectrumPerCharge": 30, - "nAnnotatedMostIntensePeaks": 6, - "minAnnotatedPeaks": 2, - "minPeaks": 4, - "cleaveNtermMethionine": true, - "maxMzLadders": 128, - "maxFragmentCharge": 2, - "fractionOfPeaksForChargeEstimation": 0.95, - "determineChargePlusOneAlgorithmically": true, - "searchPositiveIons": true, - "minPrecPerSpectrum": 1, - "searchForwardFragmentFirst": false, - "searchRewindFragments": true, - "maxFragmentPerSeries": 100, - "useCorrelationCorrectionScore": true, - "consecutiveIonProbability": 0.5, - "iterativeSequenceEvalue": 0.0, - "iterativeReplaceEvalue": 0.0, - "iterativeSpectrumEvalue": 0.01, - "noProlineRuleSeries": [], - "ptmIndexes": {} - } - }, - "2": { - "type": "com.compomics.util.experiment.identification.identification_parameters.tool_specific.XtandemParameters", - "data": { - "maxEValue": 0.01, - "outputResults": "all", - "dynamicRange": 100.0, - "nPeaks": 50, - "minPrecursorMass": 500.0, - "minFragmentMz": 200.0, - "minPeaksPerSpectrum": 5, - "proteinQuickAcetyl": true, - "quickPyrolidone": true, - "refine": true, - "refineSemi": false, - "refinePointMutations": false, - "refineSpectrumSynthesis": true, - "refineUnanticipatedCleavages": true, - "refineSnaps": true, - "maximumExpectationValueRefinement": 0.01, - "potentialModificationsForFullRefinment": false, - "skylinePath": "", - "outputProteins": true, - "outputSequences": false, - "outputSpectra": true, - "outputHistograms": false, - "stpBias": false, - "useNoiseSuppression": false, - "proteinPtmComplexity": 6.0 - } - }, - "3": { - "type": "com.compomics.util.experiment.identification.identification_parameters.tool_specific.PepnovoParameters", - "data": { - "hitListLength": 10, - "estimateCharge": true, - "correctPrecursorMass": false, - "discardLowQualitySpectra": true, - "fragmentationModel": "CID_IT_TRYP", - "generateQuery": false - } - }, - "4": { - "type": "com.compomics.util.experiment.identification.identification_parameters.tool_specific.AndromedaParameters", - "data": { - "maxPeptideMass": 4600.0, - "maxCombinations": 250, - "topPeaks": 8, - "topPeaksWindow": 100, - "includeWater": true, - "includeAmmonia": true, - "dependentLosses": true, - "fragmentAll": false, - "empiricalCorrection": true, - "higherCharge": true, - "fragmentationMethod": "CID", - "maxNumberOfModifications": 5, - "minPeptideLengthNoEnzyme": 8, - "maxPeptideLengthNoEnzyme": 25, - "equalIL": false, - "numberOfCandidates": 10, - "ptmIndexes": {}, - "decoyMode": "none" - } - }, - "5": { - "type": "com.compomics.util.experiment.identification.identification_parameters.tool_specific.MsAmandaParameters", - "data": { - "generateDecoy": false, - "instrumentID": "b, y", - "maxRank": 10, - "monoisotopic": true, - "lowMemoryMode": true - } - }, - "7": { - "type": "com.compomics.util.experiment.identification.identification_parameters.tool_specific.MsgfParameters", - "data": { - "searchDecoyDatabase": false, - "instrumentID": 3, - "fragmentationType": 3, - "protocol": 0, - "minPeptideLength": 8, - "maxPeptideLength": 30, - "numberOfSpectrumMarches": 10, - "additionalOutput": false, - "lowerIsotopeErrorRange": -1, - "upperIsotopeErrorRange": 2, - "numberTolerableTermini": 2, - "numberOfPtmsPerPeptide": 2 - } - }, - "8": { - "type": "com.compomics.util.experiment.identification.identification_parameters.tool_specific.DirecTagParameters", - "data": { - "ticCutoffPercentage": 100.0, - "maxPeakCount": 100, - "numIntensityClasses": 3, - "adjustPrecursorMass": false, - "minPrecursorAdjustment": -0.5, - "maxPrecursorAdjustment": 1.5, - "precursorAdjustmentStep": 0.1, - "numChargeStates": 3, - "outputSuffix": "", - "useChargeStateFromMS": true, - "duplicateSpectra": true, - "deisotopingMode": 0, - "isotopeMzTolerance": 0.25, - "complementMzTolerance": 0.1, - "tagLength": 4, - "maxDynamicMods": 2, - "maxTagCount": 10, - "intensityScoreWeight": 1.0, - "mzFidelityScoreWeight": 1.0, - "complementScoreWeight": 1.0, - "variablePtms": [] - } - }, - "10": { - "type": "com.compomics.util.experiment.identification.identification_parameters.tool_specific.CometParameters", - "data": { - "numberOfSpectrumMatches": 10, - "maxVariableMods": 10, - "requireVariableMods": false, - "minPeaks": 10, - "minPeakIntensity": 0.0, - "removePrecursor": 0, - "removePrecursorTolerance": 1.5, - "lowerClearMzRange": 0.0, - "upperClearMzRange": 0.0, - "enzymeType": 2, - "isotopeCorrection": 1, - "minPrecursorMass": 600.0, - "maxPrecursorMass": 5000.0, - "maxFragmentCharge": 3, - "removeMethionine": false, - "batchSize": 0, - "theoreticalFragmentIonsSumOnly": false, - "fragmentBinOffset": 0.0, - "useSparseMatrix": true, - "selectedOutputFormat": "PepXML", - "printExpectScore": true - } - }, - "27": { - "type": "com.compomics.util.experiment.identification.identification_parameters.tool_specific.PNovoParameters", - "data": { - "numberOfPeptides": 10, - "lowerPrecursorMass": 300, - "upperPrecursorMass": 5000, - "acticationType": "HCD" - } - }, - "28": { - "type": "com.compomics.util.experiment.identification.identification_parameters.tool_specific.TideParameters", - "data": { - "fastIndexFolderName": "fasta-index", - "maxVariablePtmsPerTypePerPeptide": 2, - "minPeptideLength": 6, - "maxPeptideLength": 30, - "minPrecursorMass": 200.0, - "maxPrecursorMass": 7200.0, - "decoyFormat": "none", - "keepTerminalAminoAcids": "NC", - "decoySeed": 1, - "outputFolderName": "crux-output", - "printPeptides": false, - "verbosity": 30, - "monoisotopicPrecursor": true, - "clipNtermMethionine": false, - "digestionType": "full-digest", - "computeSpScore": false, - "numberOfSpectrumMatches": 10, - "computeExactPValues": false, - "minSpectrumMz": 0.0, - "minSpectrumPeaks": 20, - "spectrumCharges": "all", - "removePrecursor": false, - "removePrecursorTolerance": 1.5, - "printProgressIndicatorSize": 1000, - "useFlankingPeaks": false, - "useNeutralLossPeaks": false, - "mzBinWidth": 0.02, - "mzBinOffset": 0.0, - "concatenateTargetDecoy": false, - "textOutput": true, - "sqtOutput": false, - "pepXmlOutput": false, - "mzidOutput": false, - "pinOutput": false, - "removeTempFolders": true - } - }, - "13": { - "type": "com.compomics.util.experiment.identification.identification_parameters.tool_specific.MyriMatchParameters", - "data": { - "minPeptideLength": 8, - "maxPeptideLength": 30, - "numberOfSpectrumMatches": 10, - "ticCutoffPercentage": 0.98, - "maxDynamicMods": 2, - "minTerminiCleavages": 2, - "minPrecursorMass": 600.0, - "maxPrecursorMass": 5000.0, - "useSmartPlusThreeModel": true, - "computeXCorr": false, - "numIntensityClasses": 3, - "classSizeMultiplier": 2, - "numberOfBatches": 50, - "lowerIsotopeCorrection": -1, - "upperIsotopeCorrection": 2, - "fragmentationRule": "CID", - "maxPeakCount": 300, - "outputFormat": "mzIdentML" - } - }, - "29": { - "type": "com.compomics.util.experiment.identification.identification_parameters.tool_specific.NovorParameters", - "data": { - "fragmentationMethod": "HCD", - "massAnalyzer": "FT" - } - } - } - }, - "annotationSettings": { - "yAxisZoomExcludesBackgroundPeaks": true, - "showAllPeaks": false, - "intensityThresholdType": "percentile", - "intensityLimit": 0.75, - "automaticAnnotation": true, - "selectedIonsMap": { - "TAG_FRAGMENT_ION": [ - 4, - 1 - ], - "REPORTER_ION": [], - "RELATED_ION": [ - 0, - 1, - 2, - 3, - 4, - 5, - 6, - 7, - 8, - 9, - 10, - 11, - 12, - 13, - 14, - 15, - 16, - 17, - 18 - ], - "PEPTIDE_FRAGMENT_ION": [ - 4, - 1 - ], - "PRECURSOR_ION": [ - 0 - ], - "IMMONIUM_ION": [ - 0, - 1, - 2, - 3, - 4, - 5, - 6, - 7, - 8, - 9, - 10, - 11, - 12, - 13, - 14, - 15, - 16, - 17, - 18, - 19, - 20 - ] - }, - "neutralLossesList": [ - { - "composition": { - "atomChain": [ - { - "atomSymbol": "H", - "isotope": 0 - }, - { - "atomSymbol": "H", - "isotope": 0 - }, - { - "atomSymbol": "O", - "isotope": 0 - } - ], - "mass1": -1.0, - "stringValue1": "H(2)O" - }, - "name": "H2O", - "fixed": false, - "aminoAcids": [ - "D", - "E", - "S", - "T" - ] - }, - { - "composition": { - "atomChain": [ - { - "atomSymbol": "N", - "isotope": 0 - }, - { - "atomSymbol": "H", - "isotope": 0 - }, - { - "atomSymbol": "H", - "isotope": 0 - }, - { - "atomSymbol": "H", - "isotope": 0 - } - ], - "mass1": -1.0, - "stringValue1": "H(3)N" - }, - "name": "NH3", - "fixed": false, - "aminoAcids": [ - "K", - "N", - "Q", - "R" - ] - } - ], - "neutralLossesAuto": true, - "reporterIons": true, - "relatedIons": true, - "fragmentIonAccuracy": 0.5, - "fragmentIonPpm": false, - "showForwardIonDeNovoTags": false, - "showRewindIonDeNovoTags": false, - "deNovoCharge": 1, - "highResolutionAnnotation": true, - "tiesResolution": "mostAccurateMz" - }, - "sequenceMatchingPreferences": { - "sequenceMatchingType": "indistiguishableAminoAcids", - "limitX": 0.25, - "peptideMapperType": "fm_index" - }, - "peptideVariantsPreferences": { - "useSpecificCount": false, - "nVariants": 0, - "nAaDeletions": 0, - "nAaInsertions": 0, - "nAaSubstitutions": 0, - "nAaSwap": 0, - "aaSubstitutionMatrix": { - "name": "No Substitution", - "description": "No substitution", - "substitutions": {}, - "reverseMap": {} - } - }, - "genePreferences": { - "autoUpdate": false, - "useGeneMapping": false - }, - "psmScoringPreferences": { - "spectrumMatchingScores": { - "8": [ - 1 - ], - "3": [ - 1 - ], - "27": [ - 1 - ] - }, - "defaultScores": [ - -1 - ], - "minDecoysInBin": 10 - }, - "peptideAssumptionFilter": { - "minPepLength": 8, - "maxPepLength": 30, - "maxMassDeviation": 10.0, - "isPpm": true, - "unknownPtm": true, - "minIsotopes": 0, - "maxIsotopes": 1 - }, - "ptmScoringPreferences": { - "flr": 1.0, - "probabilitsticScoreCalculation": true, - "selectedProbabilisticScore": "PhosphoRS", - "estimateFlr": false, - "probabilisticScoreThreshold": 95.0, - "probabilisticScoreNeutralLosses": false, - "sequenceMatchingPreferences": { - "sequenceMatchingType": "aminoAcid", - "limitX": 0.25, - "peptideMapperType": "fm_index" - }, - "alignNonConfidentPTMs": true - }, - "proteinInferencePreferences": { - "proteinSequenceDatabase": { - "path": "./searchgui_tinydb1_concatenated_target_decoy.fasta" - }, - "simplifyProteinGroups": true, - "simplifyGroupsScore": true, - "simplifyGroupsEvidence": true, - "simplifyGroupsEnzymaticity": true, - "simplifyGroupsUncharacterized": true - }, - "idValidationPreferences": { - "defaultProteinFDR": 1.0, - "defaultPeptideFDR": 1.0, - "defaultPsmFDR": 1.0, - "separatePeptides": true, - "separatePsms": true, - "mergeSmallSubgroups": true, - "validationQCPreferences": { - "dbSize": false, - "firstDecoy": true, - "confidenceMargin": 1.0 - } - }, - "fractionSettings": { - "proteinConfidenceMwPlots": 95.0, - "fractionMolecularWeightRanges": {} - } -}
--- a/test-data/Identification_Parameters_specific.par Tue May 15 14:50:35 2018 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,739 +0,0 @@ -{ - "marshallableParameterType": "identification_parameters", - "name": "SEARCHGUI_IdentificationParameters", - "description": "Fixed: Carbamidomethylation of C.\nVariable: Oxidation of M.\nPrecursor Tolerance: 100.0 ppm.\nCharge: 1-3.\nDB: dataset_118.dat.\n", - "defaultDescription": true, - "searchParameters": { - "precursorAccuracyType": "PPM", - "fragmentAccuracyType": "DA", - "precursorTolerance": 100.0, - "precursorToleranceDalton": 0.5, - "fragmentIonMZTolerance": 0.5, - "ptmSettings": { - "fixedModifications": [ - "Carbamidomethylation of C" - ], - "variableModifications": [ - "Oxidation of M" - ], - "refinementVariableModifications": [], - "refinementFixedModifications": [], - "colors": {}, - "backUp": { - "Oxidation of M": { - "type": 0, - "name": "Oxidation of M", - "shortName": "ox", - "neutralLosses": [ - { - "composition": { - "atomChain": [ - { - "atomSymbol": "C", - "isotope": 0 - }, - { - "atomSymbol": "H", - "isotope": 0 - }, - { - "atomSymbol": "H", - "isotope": 0 - }, - { - "atomSymbol": "H", - "isotope": 0 - }, - { - "atomSymbol": "H", - "isotope": 0 - }, - { - "atomSymbol": "O", - "isotope": 0 - }, - { - "atomSymbol": "S", - "isotope": 0 - } - ], - "mass1": -1.0 - }, - "name": "CH4OS", - "fixed": false - } - ], - "reporterIons": [], - "pattern": { - "length": 0, - "residueTargeted": { - "0": [ - "M" - ] - } - }, - "atomChainAdded": { - "atomChain": [ - { - "atomSymbol": "O", - "isotope": 0 - } - ], - "mass1": -1.0 - }, - "cvTerm": { - "ontology": "UNIMOD", - "accession": "UNIMOD:35", - "name": "Oxidation" - } - }, - "Carbamidomethylation of C": { - "type": 0, - "name": "Carbamidomethylation of C", - "shortName": "cmm", - "neutralLosses": [], - "reporterIons": [], - "pattern": { - "length": 0, - "residueTargeted": { - "0": [ - "C" - ] - } - }, - "atomChainAdded": { - "atomChain": [ - { - "atomSymbol": "C", - "isotope": 0 - }, - { - "atomSymbol": "C", - "isotope": 0 - }, - { - "atomSymbol": "H", - "isotope": 0 - }, - { - "atomSymbol": "H", - "isotope": 0 - }, - { - "atomSymbol": "H", - "isotope": 0 - }, - { - "atomSymbol": "N", - "isotope": 0 - }, - { - "atomSymbol": "O", - "isotope": 0 - } - ], - "mass1": -1.0 - }, - "cvTerm": { - "ontology": "UNIMOD", - "accession": "UNIMOD:4", - "name": "Carbamidomethyl" - } - } - } - }, - "nMissedCleavages": 2, - "digestionPreferences": { - "cleavagePreference": "enzyme", - "enzymes": [ - { - "id": 0, - "name": "Trypsin", - "aminoAcidBefore": [], - "aminoAcidAfter": [], - "restrictionBefore": [], - "restrictionAfter": [], - "aminoAcidBeforeSet": [ - "R", - "K" - ], - "aminoAcidAfterSet": [], - "restrictionBeforeSet": [], - "restrictionAfterSet": [ - "P" - ], - "isSemiSpecific": false, - "isWholeProtein": false, - "cvTerm": { - "ontology": "PSI-MS", - "accession": "MS:1001251", - "name": "Trypsin" - } - } - ], - "nMissedCleavages": { - "Trypsin": 2 - }, - "specificity": { - "Trypsin": "specific" - } - }, - "fastaFile": { - "path": "./searchgui_tinydb1_concatenated_target_decoy.fasta" - }, - "parametersFile": {}, - "forwardIons": [ - 1 - ], - "rewindIons": [ - 4 - ], - "minChargeSearched": { - "sign": 1, - "value": 1 - }, - "maxChargeSearched": { - "sign": 1, - "value": 3 - }, - "minIsotopicCorrection": 0, - "maxIsotopicCorrection": 1, - "refMass": 2000.0, - "algorithmParameters": { - "1": { - "type": "com.compomics.util.experiment.identification.identification_parameters.tool_specific.OmssaParameters", - "data": { - "maxEValue": 100.0, - "hitListLength": 10, - "minimalChargeForMultipleChargedFragments": { - "sign": 1, - "value": 3 - }, - "minPeptideLength": 8, - "maxPeptideLength": 30, - "removePrecursor": false, - "scalePrecursor": true, - "estimateCharge": true, - "selectedOutput": "OMX", - "memoryMappedSequenceLibraries": false, - "numberOfItotopicPeaks": 0, - "neutronThreshold": 1446.94, - "lowIntensityCutOff": 0.0, - "highIntensityCutOff": 0.2, - "intensityCutOffIncrement": 5.0E-4, - "singleChargeWindow": 27, - "doubleChargeWindow": 14, - "nPeaksInSingleChargeWindow": 2, - "nPeaksInDoubleChargeWindow": 2, - "maxHitsPerSpectrumPerCharge": 30, - "nAnnotatedMostIntensePeaks": 6, - "minAnnotatedPeaks": 2, - "minPeaks": 4, - "cleaveNtermMethionine": true, - "maxMzLadders": 128, - "maxFragmentCharge": 2, - "fractionOfPeaksForChargeEstimation": 0.95, - "determineChargePlusOneAlgorithmically": true, - "searchPositiveIons": true, - "minPrecPerSpectrum": 1, - "searchForwardFragmentFirst": false, - "searchRewindFragments": true, - "maxFragmentPerSeries": 100, - "useCorrelationCorrectionScore": true, - "consecutiveIonProbability": 0.5, - "iterativeSequenceEvalue": 0.0, - "iterativeReplaceEvalue": 0.0, - "iterativeSpectrumEvalue": 0.01, - "noProlineRuleSeries": [], - "ptmIndexes": {} - } - }, - "2": { - "type": "com.compomics.util.experiment.identification.identification_parameters.tool_specific.XtandemParameters", - "data": { - "maxEValue": 0.01, - "outputResults": "0", - "dynamicRange": 100.0, - "nPeaks": 50, - "minPrecursorMass": 200.0, - "minFragmentMz": 200.0, - "minPeaksPerSpectrum": 15, - "proteinQuickAcetyl": true, - "quickPyrolidone": true, - "refine": true, - "refineSemi": false, - "refinePointMutations": false, - "refineSpectrumSynthesis": true, - "refineUnanticipatedCleavages": true, - "refineSnaps": true, - "maximumExpectationValueRefinement": 0.01, - "potentialModificationsForFullRefinment": false, - "skylinePath": "", - "outputProteins": true, - "outputSequences": false, - "outputSpectra": true, - "outputHistograms": false, - "stpBias": false, - "useNoiseSuppression": true, - "proteinPtmComplexity": 6.0 - } - }, - "3": { - "type": "com.compomics.util.experiment.identification.identification_parameters.tool_specific.PepnovoParameters", - "data": { - "hitListLength": 10, - "estimateCharge": true, - "correctPrecursorMass": false, - "discardLowQualitySpectra": true, - "fragmentationModel": "CID_IT_TRYP", - "generateQuery": false - } - }, - "4": { - "type": "com.compomics.util.experiment.identification.identification_parameters.tool_specific.AndromedaParameters", - "data": { - "maxPeptideMass": 4600.0, - "maxCombinations": 250, - "topPeaks": 8, - "topPeaksWindow": 100, - "includeWater": true, - "includeAmmonia": true, - "dependentLosses": true, - "fragmentAll": false, - "empiricalCorrection": true, - "higherCharge": true, - "fragmentationMethod": "CID", - "maxNumberOfModifications": 5, - "minPeptideLengthNoEnzyme": 8, - "maxPeptideLengthNoEnzyme": 25, - "equalIL": false, - "numberOfCandidates": 10, - "ptmIndexes": {}, - "decoyMode": "none" - } - }, - "5": { - "type": "com.compomics.util.experiment.identification.identification_parameters.tool_specific.MsAmandaParameters", - "data": { - "generateDecoy": false, - "instrumentID": "b, y", - "maxRank": 10, - "monoisotopic": true, - "lowMemoryMode": true - } - }, - "7": { - "type": "com.compomics.util.experiment.identification.identification_parameters.tool_specific.MsgfParameters", - "data": { - "searchDecoyDatabase": false, - "instrumentID": 3, - "fragmentationType": 3, - "protocol": 0, - "minPeptideLength": 8, - "maxPeptideLength": 30, - "numberOfSpectrumMarches": 10, - "additionalOutput": false, - "lowerIsotopeErrorRange": -1, - "upperIsotopeErrorRange": 2, - "numberTolerableTermini": 2, - "numberOfPtmsPerPeptide": 2 - } - }, - "8": { - "type": "com.compomics.util.experiment.identification.identification_parameters.tool_specific.DirecTagParameters", - "data": { - "ticCutoffPercentage": 100.0, - "maxPeakCount": 100, - "numIntensityClasses": 3, - "adjustPrecursorMass": false, - "minPrecursorAdjustment": -0.5, - "maxPrecursorAdjustment": 1.5, - "precursorAdjustmentStep": 0.1, - "numChargeStates": 3, - "outputSuffix": "", - "useChargeStateFromMS": true, - "duplicateSpectra": true, - "deisotopingMode": 0, - "isotopeMzTolerance": 0.25, - "complementMzTolerance": 0.1, - "tagLength": 4, - "maxDynamicMods": 2, - "maxTagCount": 10, - "intensityScoreWeight": 1.0, - "mzFidelityScoreWeight": 1.0, - "complementScoreWeight": 1.0, - "variablePtms": [] - } - }, - "10": { - "type": "com.compomics.util.experiment.identification.identification_parameters.tool_specific.CometParameters", - "data": { - "numberOfSpectrumMatches": 10, - "maxVariableMods": 10, - "requireVariableMods": false, - "minPeaks": 10, - "minPeakIntensity": 0.0, - "removePrecursor": 0, - "removePrecursorTolerance": 1.5, - "lowerClearMzRange": 0.0, - "upperClearMzRange": 0.0, - "enzymeType": 2, - "isotopeCorrection": 1, - "minPrecursorMass": 600.0, - "maxPrecursorMass": 5000.0, - "maxFragmentCharge": 3, - "removeMethionine": false, - "batchSize": 0, - "theoreticalFragmentIonsSumOnly": false, - "fragmentBinOffset": 0.0, - "useSparseMatrix": true, - "selectedOutputFormat": "PepXML", - "printExpectScore": true - } - }, - "27": { - "type": "com.compomics.util.experiment.identification.identification_parameters.tool_specific.PNovoParameters", - "data": { - "numberOfPeptides": 10, - "lowerPrecursorMass": 300, - "upperPrecursorMass": 5000, - "acticationType": "HCD" - } - }, - "28": { - "type": "com.compomics.util.experiment.identification.identification_parameters.tool_specific.TideParameters", - "data": { - "fastIndexFolderName": "fasta-index", - "maxVariablePtmsPerTypePerPeptide": 2, - "minPeptideLength": 6, - "maxPeptideLength": 30, - "minPrecursorMass": 200.0, - "maxPrecursorMass": 7200.0, - "decoyFormat": "none", - "keepTerminalAminoAcids": "NC", - "decoySeed": 1, - "outputFolderName": "crux-output", - "printPeptides": false, - "verbosity": 30, - "monoisotopicPrecursor": true, - "clipNtermMethionine": false, - "digestionType": "full-digest", - "computeSpScore": false, - "numberOfSpectrumMatches": 10, - "computeExactPValues": false, - "minSpectrumMz": 0.0, - "minSpectrumPeaks": 20, - "spectrumCharges": "all", - "removePrecursor": false, - "removePrecursorTolerance": 1.5, - "printProgressIndicatorSize": 1000, - "useFlankingPeaks": false, - "useNeutralLossPeaks": false, - "mzBinWidth": 0.02, - "mzBinOffset": 0.0, - "concatenateTargetDecoy": false, - "textOutput": true, - "sqtOutput": false, - "pepXmlOutput": false, - "mzidOutput": false, - "pinOutput": false, - "removeTempFolders": true - } - }, - "13": { - "type": "com.compomics.util.experiment.identification.identification_parameters.tool_specific.MyriMatchParameters", - "data": { - "minPeptideLength": 8, - "maxPeptideLength": 30, - "numberOfSpectrumMatches": 10, - "ticCutoffPercentage": 0.98, - "maxDynamicMods": 2, - "minTerminiCleavages": 2, - "minPrecursorMass": 600.0, - "maxPrecursorMass": 5000.0, - "useSmartPlusThreeModel": true, - "computeXCorr": false, - "numIntensityClasses": 3, - "classSizeMultiplier": 2, - "numberOfBatches": 50, - "lowerIsotopeCorrection": -1, - "upperIsotopeCorrection": 2, - "fragmentationRule": "CID", - "maxPeakCount": 300, - "outputFormat": "mzIdentML" - } - }, - "29": { - "type": "com.compomics.util.experiment.identification.identification_parameters.tool_specific.NovorParameters", - "data": { - "fragmentationMethod": "HCD", - "massAnalyzer": "FT" - } - } - } - }, - "annotationSettings": { - "yAxisZoomExcludesBackgroundPeaks": true, - "showAllPeaks": false, - "intensityThresholdType": "percentile", - "intensityLimit": 0.75, - "automaticAnnotation": true, - "selectedIonsMap": { - "TAG_FRAGMENT_ION": [ - 4, - 1 - ], - "REPORTER_ION": [], - "RELATED_ION": [ - 0, - 1, - 2, - 3, - 4, - 5, - 6, - 7, - 8, - 9, - 10, - 11, - 12, - 13, - 14, - 15, - 16, - 17, - 18 - ], - "PEPTIDE_FRAGMENT_ION": [ - 4, - 1 - ], - "PRECURSOR_ION": [ - 0 - ], - "IMMONIUM_ION": [ - 0, - 1, - 2, - 3, - 4, - 5, - 6, - 7, - 8, - 9, - 10, - 11, - 12, - 13, - 14, - 15, - 16, - 17, - 18, - 19, - 20 - ] - }, - "neutralLossesList": [ - { - "composition": { - "atomChain": [ - { - "atomSymbol": "H", - "isotope": 0 - }, - { - "atomSymbol": "H", - "isotope": 0 - }, - { - "atomSymbol": "O", - "isotope": 0 - } - ], - "mass1": -1.0, - "stringValue1": "H(2)O" - }, - "name": "H2O", - "fixed": false, - "aminoAcids": [ - "D", - "E", - "S", - "T" - ] - }, - { - "composition": { - "atomChain": [ - { - "atomSymbol": "N", - "isotope": 0 - }, - { - "atomSymbol": "H", - "isotope": 0 - }, - { - "atomSymbol": "H", - "isotope": 0 - }, - { - "atomSymbol": "H", - "isotope": 0 - } - ], - "mass1": -1.0, - "stringValue1": "H(3)N" - }, - "name": "NH3", - "fixed": false, - "aminoAcids": [ - "K", - "N", - "Q", - "R" - ] - }, - { - "composition": { - "atomChain": [ - { - "atomSymbol": "C", - "isotope": 0 - }, - { - "atomSymbol": "H", - "isotope": 0 - }, - { - "atomSymbol": "H", - "isotope": 0 - }, - { - "atomSymbol": "H", - "isotope": 0 - }, - { - "atomSymbol": "H", - "isotope": 0 - }, - { - "atomSymbol": "O", - "isotope": 0 - }, - { - "atomSymbol": "S", - "isotope": 0 - } - ], - "mass1": -1.0 - }, - "name": "CH4OS", - "fixed": false - } - ], - "neutralLossesAuto": true, - "reporterIons": true, - "relatedIons": true, - "fragmentIonAccuracy": 0.5, - "fragmentIonPpm": false, - "showForwardIonDeNovoTags": false, - "showRewindIonDeNovoTags": false, - "deNovoCharge": 1, - "highResolutionAnnotation": true, - "tiesResolution": "mostAccurateMz" - }, - "sequenceMatchingPreferences": { - "sequenceMatchingType": "indistiguishableAminoAcids", - "limitX": 0.25, - "peptideMapperType": "fm_index" - }, - "peptideVariantsPreferences": { - "useSpecificCount": false, - "nVariants": 0, - "nAaDeletions": 0, - "nAaInsertions": 0, - "nAaSubstitutions": 0, - "nAaSwap": 0, - "aaSubstitutionMatrix": { - "name": "No Substitution", - "description": "No substitution", - "substitutions": {}, - "reverseMap": {} - } - }, - "genePreferences": { - "autoUpdate": false, - "useGeneMapping": false - }, - "psmScoringPreferences": { - "spectrumMatchingScores": { - "8": [ - 1 - ], - "3": [ - 1 - ], - "27": [ - 1 - ] - }, - "defaultScores": [ - -1 - ], - "minDecoysInBin": 10 - }, - "peptideAssumptionFilter": { - "minPepLength": 8, - "maxPepLength": 30, - "maxMassDeviation": 10.0, - "isPpm": true, - "unknownPtm": true, - "minIsotopes": 0, - "maxIsotopes": 1 - }, - "ptmScoringPreferences": { - "flr": 1.0, - "probabilitsticScoreCalculation": true, - "selectedProbabilisticScore": "PhosphoRS", - "estimateFlr": false, - "probabilisticScoreThreshold": 95.0, - "probabilisticScoreNeutralLosses": false, - "sequenceMatchingPreferences": { - "sequenceMatchingType": "aminoAcid", - "limitX": 0.25, - "peptideMapperType": "fm_index" - }, - "alignNonConfidentPTMs": true - }, - "proteinInferencePreferences": { - "proteinSequenceDatabase": { - "path": "./searchgui_tinydb1_concatenated_target_decoy.fasta" - }, - "simplifyProteinGroups": true, - "simplifyGroupsScore": true, - "simplifyGroupsEvidence": true, - "simplifyGroupsEnzymaticity": true, - "simplifyGroupsUncharacterized": true - }, - "idValidationPreferences": { - "defaultProteinFDR": 1.0, - "defaultPeptideFDR": 1.0, - "defaultPsmFDR": 1.0, - "separatePeptides": true, - "separatePsms": true, - "mergeSmallSubgroups": true, - "validationQCPreferences": { - "dbSize": false, - "firstDecoy": true, - "confidenceMargin": 1.0 - } - }, - "fractionSettings": { - "proteinConfidenceMwPlots": 95.0, - "fractionMolecularWeightRanges": {} - } -}