Mercurial > repos > galaxyp > peptideshaker
diff peptide_shaker.xml @ 18:a5f9b959d5d1 draft
Uploaded
| author | iracooke |
|---|---|
| date | Wed, 25 Jun 2014 11:49:45 -0400 |
| parents | |
| children | 2cafc729b2ae |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/peptide_shaker.xml Wed Jun 25 11:49:45 2014 -0400 @@ -0,0 +1,958 @@ +<tool id="peptide_shaker" name="Peptide Shaker" version="1.19.5.0"> + <description> + Perform protein identification using various search engines (using SearchGUI) and combine results with PeptideShaker. + </description> + <requirements> + <requirement type="package" version="0.31.4">peptide_shaker</requirement> + <requirement type="package" version="1.19.5">searchgui</requirement> + <!--<requirement type="package" version="2.2.29">blast+</requirement>--> + </requirements> + <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"/> + </stdio> + <command> + + #from datetime import datetime + #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 = 'macs2_stderr' + + mkdir output; + mkdir output_reports; + cwd=`pwd`; + #for $mgf in $peak_lists: + #set $input_name = $mgf.display_name.replace(".mgf", "") + ".mgf" + ln -s '${mgf}' '${input_name}'; + #end for + ##ln -s "${input_database}" input_database.fasta; + cp "${input_database}" input_database.fasta; + + ########################################### + #### Creating decoy database #### + ########################################### + #if $create_decoy: + echo "Creating decoy database."; + java -cp \$SEARCHGUI_JAR_PATH eu.isas.searchgui.cmd.FastaCLI -in input_database.fasta -decoy; + rm input_database.fasta; + cp input_database_concatenated_target_decoy.fasta input_database.fasta; + ##ln -sf input_database_concatenated_target_decoy.fasta input_database.fasta; + #end if + + ##################################################### + ## generate IdentificationParameters for SearchGUI ## + ##################################################### + + (java -cp \$SEARCHGUI_JAR_PATH eu.isas.searchgui.cmd.IdentificationParametersCLI + -out SEARCHGUI_IdentificationParameters.parameters + -prec_ppm "${precursor_ion_tol_units}" + -prec_tol "${precursor_ion_tol}" + -frag_tol "${fragment_tol}" + -enzyme "${enzyme}" + #set $fixed_mods_str = $fixed_modifications or '' + #set $variable_mods_str = $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 + -min_charge "${min_charge}" + -max_charge "${max_charge}" + -mc "${missed_cleavages}" + -fi "${forward_ion}" + -ri "${reverse_ion}" + -db input_database.fasta + + #if $advanced.advanced_type_selector == "advanced": + + #if $advanced.xtandem.xtandem_selector == "yes" + + -xtandem_npeaks ${advanced.xtandem.xtandem_npeaks} + -xtandem_min_peaks ${advanced.xtandem.xtandem_min_peaks} + -xtandem_min_frag_mz ${advanced.xtandem.xtandem_min_frag_mz} + -xtandem_min_prec_mass ${advanced.xtandem.xtandem_min_prec_mass} + -xtandem_noise_suppr ${advanced.xtandem.xtandem_noise_suppr} + + #if $advanced.xtandem.xtandem_refine.xtandem_refine_selector == "yes" + -xtandem_refine 1 + -xtandem_refine_unc ${advanced.xtandem.xtandem_refine.xtandem_refine_unc} + -xtandem_refine_semi ${advanced.xtandem.xtandem_refine.xtandem_refine_semi} + -xtandem_refine_p_mut ${advanced.xtandem.xtandem_refine.xtandem_refine_p_mut} + -xtandem_refine_snaps ${advanced.xtandem.xtandem_refine.xtandem_refine_snaps} + -xtandem_refine_spec_synt ${advanced.xtandem.xtandem_refine.xtandem_refine_spec_synt} + #end if + #end if + + #if $advanced.omssa.omssa_selector == "yes" + -omssa_hitlist_length ${advanced.omssa.hitlist_length} + -omssa_remove_prec ${advanced.omssa.remove_precursor} + -omssa_scale_prec ${advanced.omssa.scale_precursor} + -omssa_estimate_charge ${advanced.omssa.estimate_charge} + #end if + + #if $advanced.msgf.msgf_selector == "yes" + -msgf_decoy ${advanced.msgf.msgf_decoy} + -msgf_min_pep_length ${advanced.msgf.msgf_min_pep_length} + -msgf_max_pep_length ${advanced.msgf.msgf_max_pep_length} + -msgf_termini ${advanced.msgf.msgf_termini} + -msgf_num_ptms ${advanced.msgf.msgf_num_ptms} + #end if + + ##if $advanced.ms_amanda.ms_amanda_selector == "yes" + ##end if + + #end if + + 2> $temp_stderr) + && + + ################ + ## Search CLI ## + ################ + (java -Djava.awt.headless=true -cp \$SEARCHGUI_JAR_PATH eu.isas.searchgui.cmd.SearchCLI + -temp_folder `pwd` + -spectrum_files \$cwd + -output_folder \$cwd/output + -id_params SEARCHGUI_IdentificationParameters.parameters + + -threads "\${GALAXY_SLOTS:-12}" + -correct_titles "${correct_titles}" + $missing_titles + -mgf_splitting "${mgf_splitting}" + -mgf_spectrum_count "${mgf_spectrum_count}" + + ## Turn of the protein tree generation as it can produce errors if the search is finished before the tree is created + ## the tree is generated afterwards in PeptideShaker + -protein_index 0 + + ##-makeblastdb_folder \$BLAST_ROOT_DIR + + #if $advanced.advanced_type_selector == "advanced": + + #if $advanced.xtandem.xtandem_selector == "yes" + -xtandem 1 + #else + -xtandem 0 + #end if + + #if $advanced.omssa.omssa_selector == "yes" + -omssa 1 + #else + -omssa 0 + #end if + + #if $advanced.msgf.msgf_selector == "yes" + -msgf 1 + #else + -msgf 0 + #end if + + #if $advanced.ms_amanda.ms_amanda_selector == "yes" + -ms_amanda 1 + #else + -ms_amanda 0 + #end if + + #else + -ms_amanda 0 + #end if + + 2>> $temp_stderr) + && + + ######################################################### + ## generate IdentificationParameters for PeptideShaker ## + ######################################################### + (java -cp \$PEPTIDESHAKER_JAR_PATH eu.isas.peptideshaker.cmd.IdentificationParametersCLI + -out PEPTIDESHAKER_IdentificationParameters.parameters + -prec_ppm "${precursor_ion_tol_units}" + -prec_tol "${precursor_ion_tol}" + -frag_tol "${fragment_tol}" + -enzyme "${enzyme}" + #set $fixed_mods_str = $fixed_modifications or '' + #set $variable_mods_str = $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 + -min_charge $min_charge + -max_charge $max_charge + -mc $missed_cleavages + -fi $forward_ion + -ri $reverse_ion + -db input_database.fasta + + 2>> $temp_stderr) + && + + ###################### + ## PeptideShakerCLI ## + ###################### + (java -cp \$PEPTIDESHAKER_JAR_PATH eu.isas.peptideshaker.cmd.PeptideShakerCLI + -temp_folder `pwd` + -experiment '${exp_str}' + -sample '${samp_str}' + -replicate 1 + -spectrum_files \$cwd + -identification_files \$cwd/output + -out \$cwd/peptide_shaker_output.cps + -id_params PEPTIDESHAKER_IdentificationParameters.parameters + + ##Optional gene annotation parameter + #if $species_type.species_type_selector != 'no_species_type': + -species_type "${species_type.species_type_selector}" + -species "${species_type.species}" + #end if + + ##Optional processing parameters: + #if $processing_options.processing_options_selector == "yes" + -protein_FDR "${processing_options.protein_fdr}" + -peptide_FDR "${processing_options.peptide_fdr}" + -psm_FDR "${processing_options.psm_fdr}" + -ptm_score "${processing_options.ptm_score.ptm_score_selector}" + #if $processing_options.ptm_score.ptm_score_selector == 1 + -score_neutral_losses "${processing_options.ptm_score.neutral_losses}" + #if str($processing_options.ptm_score.ptm_threshold) != '' + -ptm_threshold "${processing_options.ptm_score.ptm_threshold}" + #end if + #end if + -protein_fraction_mw_confidence "${processing_options.protein_fraction_mw_confidence}" + #end if + + ##Optional filtering parameters: + #if $filtering_options.filtering_options_selector == "yes": + -min_peptide_length "${filtering_options.min_peptide_length}" + -max_peptide_length "${filtering_options.max_peptide_length}" + -max_precursor_error "${filtering_options.max_precursor_error}" + -max_precursor_error_type "${filtering_options.max_precursor_error_type}" + -max_xtandem_e "${filtering_options.max_xtandem_e}" + -max_omssa_e "${filtering_options.max_omssa_e}" + -max_mascot_e "${filtering_options.max_mascot_e}" + -exclude_unknown_ptms "${filtering_options.exclude_unknown_ptms}" + #end if + + 2>> $temp_stderr) + && + + ################################## + ## PeptideShaker Report options ## + ################################## + (java -cp \$PEPTIDESHAKER_JAR_PATH eu.isas.peptideshaker.cmd.ReportCLI + -temp_folder `pwd` + -in \$cwd/peptide_shaker_output.cps + -out_reports \$cwd/output_reports + #set $cleaned_list = str($outputs).split(',') + #if 'cps' in $cleaned_list: + #silent $cleaned_list.remove('cps') + #end if + #if 'mzidentML' in $cleaned_list: + #silent $cleaned_list.remove('mzidentML') + #end if + -reports #echo ','.join($cleaned_list)# + + 2>> $temp_stderr) + && + + #if 'mzidentML' in str($outputs).split(','): + java -cp \$PEPTIDESHAKER_JAR_PATH eu.isas.peptideshaker.cmd.MzidCLI + -in \$cwd/peptide_shaker_output.cps + -output_file output.mzid + -contact_first_name 'Proteomics' + -contact_last_name 'Galaxy' + -contact_email 'galaxyp@umn.edu' + -contact_address 'galaxyp@umn.edu' + -organization_name 'University of Minnesota' + -organization_email 'galaxyp@umn.edu' + -organization_address 'Minneapolis, MN 55455, Vereinigte Staaten' + ; + #end if + #if '0' in str($outputs).split(','): + find \$cwd/output_reports -name '*Certificate*' -exec bash -c 'mv "$0" "certificate.txt"' {} \; + ; + #end if + #if '2' in str($outputs).split(','): + find \$cwd/output_reports -name '*PSM*' -exec bash -c 'mv "$0" "psm.txt"' {} \; + ; + #end if + #if '3' in str($outputs).split(','): + find \$cwd/output_reports -name '*Peptide*' -exec bash -c 'mv "$0" "peptides.txt"' {} \; + ; + #end if + #if '4' in str($outputs).split(','): + find \$cwd/output_reports -name '*Protein*' -exec bash -c 'mv "$0" "proteins.txt"' {} \; + ; + #end if + #if '1' in str($outputs).split(','): + find \$cwd/output_reports -name '*Hierarchical*' -exec bash -c 'mv "$0" "hierarchical.txt"' {} \; + ; + #end if + + exit_code_for_galaxy=\$?; + cat $temp_stderr 2>&1; + (exit \$exit_code_for_galaxy) + + </command> + <inputs> + <param format="fasta" name="input_database" type="data" label="Protein Database" + help="Select FASTA database from history"/> + + <param name="create_decoy" label="Create a concatenated target/decoy database before running PeptideShaker." type="boolean" truevalue="True" falsevalue="False" checked="true" help="Selecting this option will help PeptideShaker calculate FDR values" /> + + <param format="mgf" name="peak_lists" type="data" multiple="true" label="Input Peak Lists (mgf)" + help="Select appropriate MGF dataset(s) from history" /> + <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="Percursor Ion Tolerance" + help="Provide error value for precursor ion, based on instrument used. 10 ppm recommended for Orbitrap instrument"/> + <param name="fragment_tol" type="float" value="0.5" label="Fragment Tolerance (Daltons)" + help="Provide error value for fragment ions, based on instrument used"/> + <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="No enzyme">No enzyme</option> + <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> + </param> + + <param name="correct_titles" type="select" label="How should PeptideShaker deal with duplicate spectra?" + help="Unless you suspect some input files to be genuine duplicates then rename spectra is the safest option"> + <option value="0">no correction</option> + <option value="1" selected="True">rename spectra</option> + <option value="2">delete spectra</option> + </param> + + <param name="missing_titles" label="Add missing spectrum titles" type="boolean" checked="false" truevalue="-missing_titles 1" falsevalue="-missing_titles 0" help="(-missing_titles)"/> + + <param name="mgf_splitting" type="integer" value="1000" label="The maximum mgf file size in MB before splitting the mgf" + help="Choose a smaller value if you are running on a machine with limited memory"/> + <param name="mgf_spectrum_count" type="integer" value="25000" label="The maximum number of spectra per mgf file when splitting" + help="Choose a smaller value if you are running on a machine with limited memory"/> + + <conditional name="species_type"> + <param name="species_type_selector" type="select" optional="true" label="The species type to use for the gene annotation" + help="(Optional) If your species is supported under one of the groups, selecting it will allow GO annotations and other information to be included in the results"> + <option value="Fungi">Fungi</option> + <option value="Plants">Plants</option> + <option value="Metazoa">Metazoa</option> + <option value="Vertebrates">Vertebrates</option> + <option value="Protists">Protists</option> + <option value="no_species_type" selected="true">No species restriction</option> + </param> + <when value="Protists"> + <param name="species" type="select" label="The species to use for the gene annotation" + help=""> + <option value="Albugo laibachii">Albugo laibachii</option> + <option value="Dictyostelium discoideum">Dictyostelium discoideum</option> + <option value="Entamoeba histolytica">Entamoeba histolytica</option> + <option value="Giardia lamblia">Giardia lamblia</option> + <option value="Guillardia theta CCMP2712">Guillardia theta CCMP2712</option> + <option value="Hyaloperonospora arabidopsidis">Hyaloperonospora arabidopsidis</option> + <option value="Leishmania major">Leishmania major</option> + <option value="Phaeodactylum tricornutum">Phaeodactylum tricornutum</option> + <option value="Phytophthora infestans">Phytophthora infestans</option> + <option value="Phytophthora ramorum">Phytophthora ramorum</option> + <option value="Phytophthora sojae">Phytophthora sojae</option> + <option value="Plasmodium berghei">Plasmodium berghei</option> + <option value="Plasmodium chabaudi">Plasmodium chabaudi</option> + <option value="Plasmodium falciparum">Plasmodium falciparum</option> + <option value="Plasmodium knowlesi">Plasmodium knowlesi</option> + <option value="Plasmodium vivax">Plasmodium vivax</option> + <option value="Pythium ultimum">Pythium ultimum</option> + <option value="Tetrahymena thermophila">Tetrahymena thermophila</option> + <option value="Thalassiosira pseudonana">Thalassiosira pseudonana</option> + <option value="Toxoplasma gondii">Toxoplasma gondii</option> + <option value="Trypanosoma brucei">Trypanosoma brucei</option> + </param> + </when> + <when value="Plants"> + <param name="species" type="select" label="The species to use for the gene annotation" + help=""> + <option value="Arabidopsis lyrata">Arabidopsis lyrata</option> + <option value="Arabidopsis thaliana">Arabidopsis thaliana</option> + <option value="Brachypodium distachyon">Brachypodium distachyon</option> + <option value="Brassica rapa genes">Brassica rapa genes</option> + <option value="Chlamydomonas reinhardtii">Chlamydomonas reinhardtii</option> + <option value="Cyanidioschyzon merolae">Cyanidioschyzon merolae</option> + <option value="Glycine max">Glycine max</option> + <option value="Hordeum vulgare">Hordeum vulgare</option> + <option value="Medicago truncatula">Medicago truncatula</option> + <option value="Musa acuminata">Musa acuminata</option> + <option value="Oryza brachyantha">Oryza brachyantha</option> + <option value="Oryza glaberrima">Oryza glaberrima</option> + <option value="Oryza sativa Indica Group">Oryza sativa Indica Group</option> + <option value="Oryza sativa">Oryza sativa</option> + <option value="Physcomitrella patens">Physcomitrella patens</option> + <option value="Populus trichocarpa">Populus trichocarpa</option> + <option value="Selaginella moellendorffii">Selaginella moellendorffii</option> + <option value="Setaria italica">Setaria italica</option> + <option value="Solanum lycopersicum">Solanum lycopersicum</option> + <option value="Solanum tuberosum">Solanum tuberosum</option> + <option value="Sorghum bicolor">Sorghum bicolor</option> + <option value="Vitis vinifera">Vitis vinifera</option> + <option value="Zea mays">Zea mays</option> + </param> + </when> + <when value="Metazoa"> + <param name="species" type="select" label="The species to use for the gene annotation" + help=""> + <option value="Acyrthosiphon pisum">Acyrthosiphon pisum</option> + <option value="Aedes aegypti">Aedes aegypti</option> + <option value="Amphimedon queenslandica">Amphimedon queenslandica</option> + <option value="Anopheles darlingi">Anopheles darlingi</option> + <option value="Anopheles gambiae">Anopheles gambiae</option> + <option value="Apis mellifera">Apis mellifera</option> + <option value="Atta cephalotes">Atta cephalotes</option> + <option value="Bombyx mori">Bombyx mori</option> + <option value="Brugia malayi">Brugia malayi</option> + <option value="Caenorhabditis brenneri">Caenorhabditis brenneri</option> + <option value="Caenorhabditis briggsae">Caenorhabditis briggsae</option> + <option value="Caenorhabditis elegans">Caenorhabditis elegans</option> + <option value="Caenorhabditis japonica">Caenorhabditis japonica</option> + <option value="Caenorhabditis remanei">Caenorhabditis remanei</option> + <option value="Culex quinquefasciatus">Culex quinquefasciatus</option> + <option value="Danaus plexippus">Danaus plexippus</option> + <option value="Daphnia pulex">Daphnia pulex</option> + <option value="Drosophila ananassae">Drosophila ananassae</option> + <option value="Drosophila erecta">Drosophila erecta</option> + <option value="Drosophila grimshawi">Drosophila grimshawi</option> + <option value="Drosophila melanogaster">Drosophila melanogaster</option> + <option value="Drosophila mojavensis">Drosophila mojavensis</option> + <option value="Drosophila persimilis">Drosophila persimilis</option> + <option value="Drosophila pseudoobscura">Drosophila pseudoobscura</option> + <option value="Drosophila sechellia">Drosophila sechellia</option> + <option value="Drosophila simulans">Drosophila simulans</option> + <option value="Drosophila virilis">Drosophila virilis</option> + <option value="Drosophila willistoni">Drosophila willistoni</option> + <option value="Drosophila yakuba">Drosophila yakuba</option> + <option value="Heliconius melpomene">Heliconius melpomene</option> + <option value="Ixodes scapularis">Ixodes scapularis</option> + <option value="Loa loa">Loa loa</option> + <option value="Megaselia scalaris">Megaselia scalaris</option> + <option value="Nasonia vitripennis">Nasonia vitripennis</option> + <option value="Nematostella vectensis">Nematostella vectensis</option> + <option value="Pediculus humanus">Pediculus humanus</option> + <option value="Pristionchus pacificus">Pristionchus pacificus</option> + <option value="Schistosoma mansoni">Schistosoma mansoni</option> + <option value="Strigamia maritima">Strigamia maritima</option> + <option value="Strongylocentrotus purpuratus">Strongylocentrotus purpuratus</option> + <option value="Tribolium castaneum">Tribolium castaneum</option> + <option value="Trichinella spiralis">Trichinella spiralis</option> + <option value="Trichoplax adhaerens">Trichoplax adhaerens</option> + </param> + </when> + <when value="Fungi"> + <param name="species" type="select" label="The species to use for the gene annotation" + help=""> + <option value="Ashbya gossypii">Ashbya gossypii</option> + <option value="Aspergillus clavatus">Aspergillus clavatus</option> + <option value="Aspergillus flavus">Aspergillus flavus</option> + <option value="Aspergillus fumigatus">Aspergillus fumigatus</option> + <option value="Aspergillus fumigatusa1163">Aspergillus fumigatusa1163</option> + <option value="Aspergillus nidulans">Aspergillus nidulans</option> + <option value="Aspergillus niger">Aspergillus niger</option> + <option value="Aspergillus oryzae">Aspergillus oryzae</option> + <option value="Aspergillus terreus">Aspergillus terreus</option> + <option value="Botryotinia fuckeliana">Botryotinia fuckeliana</option> + <option value="Cryptococcus neoformans">Cryptococcus neoformans</option> + <option value="Fusarium oxysporum">Fusarium oxysporum</option> + <option value="Gaeumannomyces graminis">Gaeumannomyces graminis</option> + <option value="Gibberella moniliformis">Gibberella moniliformis</option> + <option value="Gibberella zeae">Gibberella zeae</option> + <option value="Glomerella graminicola">Glomerella graminicola</option> + <option value="Komagataella pastoris">Komagataella pastoris</option> + <option value="Leptosphaeria maculans">Leptosphaeria maculans</option> + <option value="Magnaporthe oryzae">Magnaporthe oryzae</option> + <option value="Magnaporthe poae">Magnaporthe poae</option> + <option value="Melampsora larici-populina">Melampsora larici-populina</option> + <option value="Nectria haematococca">Nectria haematococca</option> + <option value="Neosartorya fischeri">Neosartorya fischeri</option> + <option value="Neurospora crassa">Neurospora crassa</option> + <option value="Phaeosphaeria nodorum">Phaeosphaeria nodorum</option> + <option value="Puccinia graminis">Puccinia graminis</option> + <option value="Puccinia triticina">Puccinia triticina</option> + <option value="Pyrenophora teres">Pyrenophora teres</option> + <option value="Pyrenophora tritici-repentis">Pyrenophora tritici-repentis</option> + <option value="Saccharomyces cerevisiae">Saccharomyces cerevisiae</option> + <option value="Schizosaccharomyces pombe">Schizosaccharomyces pombe</option> + <option value="Sclerotinia sclerotiorum">Sclerotinia sclerotiorum</option> + <option value="Sporisorium reilianum">Sporisorium reilianum</option> + <option value="Trichoderma reesei">Trichoderma reesei</option> + <option value="Trichoderma virens">Trichoderma virens</option> + <option value="Tuber melanosporum">Tuber melanosporum</option> + <option value="Ustilago maydis">Ustilago maydis</option> + <option value="Yarrowia lipolytica">Yarrowia lipolytica</option> + <option value="Zymoseptoria tritici">Zymoseptoria tritici</option> + </param> + </when> + <when value="Vertebrates"> + <param name="species" type="select" label="The species to use for the gene annotation" + help=""> + <option value="Ailuropoda melanoleuca">Ailuropoda melanoleuca</option> + <option value="Anolis carolinensis">Anolis carolinensis</option> + <option value="Bos taurus">Bos taurus</option> + <option value="Caenorhabditis elegans">Caenorhabditis elegans</option> + <option value="Callithrix jacchus">Callithrix jacchus</option> + <option value="Canis familiaris">Canis familiaris</option> + <option value="Cavia porcellus">Cavia porcellus</option> + <option value="Choloepus hoffmanni">Choloepus hoffmanni</option> + <option value="Ciona intestinalis">Ciona intestinalis</option> + <option value="Ciona savignyi">Ciona savignyi</option> + <option value="Danio rerio">Danio rerio</option> + <option value="Dasypus novemcinctus">Dasypus novemcinctus</option> + <option value="Dipodomys ordii">Dipodomys ordii</option> + <option value="Drosophila melanogaster">Drosophila melanogaster</option> + <option value="Echinops telfairi">Echinops telfairi</option> + <option value="Equus caballus">Equus caballus</option> + <option value="Erinaceus europaeus">Erinaceus europaeus</option> + <option value="Felis catus">Felis catus</option> + <option value="Gallus gallus">Gallus gallus</option> + <option value="Gasterosteus aculeatus">Gasterosteus aculeatus</option> + <option value="Gorilla gorilla">Gorilla gorilla</option> + <option value="Homo sapiens">Homo sapiens</option> + <option value="Ictidomys tridecemlineatus">Ictidomys tridecemlineatus</option> + <option value="Latimeria chalumnae">Latimeria chalumnae</option> + <option value="Loxodonta africana">Loxodonta africana</option> + <option value="Macaca mulatta">Macaca mulatta</option> + <option value="Macropus eugenii">Macropus eugenii</option> + <option value="Meleagris gallopavo">Meleagris gallopavo</option> + <option value="Microcebus murinus">Microcebus murinus</option> + <option value="Monodelphis domestica">Monodelphis domestica</option> + <option value="Mus musculus">Mus musculus</option> + <option value="Mustela putorius furo">Mustela putorius furo</option> + <option value="Myotis lucifugus">Myotis lucifugus</option> + <option value="Nomascus leucogenys">Nomascus leucogenys</option> + <option value="Ochotona princeps">Ochotona princeps</option> + <option value="Oreochromis niloticus">Oreochromis niloticus</option> + <option value="Ornithorhynchus anatinus">Ornithorhynchus anatinus</option> + <option value="Oryctolagus cuniculus">Oryctolagus cuniculus</option> + <option value="Oryzias latipes">Oryzias latipes</option> + <option value="Otolemur garnettii">Otolemur garnettii</option> + <option value="Pan troglodytes">Pan troglodytes</option> + <option value="Petromyzon marinus">Petromyzon marinus</option> + <option value="Pelodiscus sinensis">Pelodiscus sinensis</option> + <option value="Pongo abelii">Pongo abelii</option> + <option value="Procavia capensis">Procavia capensis</option> + <option value="Pteropus vampyrus">Pteropus vampyrus</option> + <option value="Rattus norvegicus">Rattus norvegicus</option> + <option value="Saccharomyces cerevisiae">Saccharomyces cerevisiae</option> + <option value="Sarcophilus harrisii">Sarcophilus harrisii</option> + <option value="Sorex araneus">Sorex araneus</option> + <option value="Sus scrofa">Sus scrofa</option> + <option value="Taeniopygia guttata">Taeniopygia guttata</option> + <option value="Takifugu rubripes">Takifugu rubripes</option> + <option value="Tarsius syrichta">Tarsius syrichta</option> + <option value="Tetraodon nigroviridis">Tetraodon nigroviridis</option> + <option value="Tupaia belangeri">Tupaia belangeri</option> + <option value="Tursiops truncatus">Tursiops truncatus</option> + <option value="Vicugna pacos">Vicugna pacos</option> + <option value="Xenopus tropicalis">Xenopus tropicalis</option> + <option value="Xiphophorus maculatus">Xiphophorus maculatus</option> + </param> + </when> + </conditional> + + <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="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> + <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> + <conditional name="advanced"> + <param name="advanced_type_selector" type="select" label="Basic or Advanced Search options"> + <option value="basic" selected="True">Basic</option> + <option value="advanced">Advanced</option> + </param> + <when value="basic" /> + <when value="advanced"> + <conditional name="xtandem"> + <param name="xtandem_selector" type="select" label="Run X!Tandem search"> + <option value="yes" selected="True">Search with X!Tandem</option> + <option value="no">No X!Tandem search</option> + </param> + <when value="no" /> + <when value="yes"> + <param name="xtandem_npeaks" label="X!Tandem: Total Peaks" type="integer" value="50" help="Maximum number of peaks to be used from a spectrum"/> + <param name="xtandem_min_peaks" label="X!Tandem: Min Peaks" type="integer" value="15" help="Minimum number of peaks required for a spectrum to be considered"/> + <param name="xtandem_min_frag_mz" label="X!Tandem: Min Frag m/z" type="integer" value="200" help="Fragment mass peaks with m/z less than this value will be discarded"/> + <param name="xtandem_min_prec_mass" label="X!Tandem: Min Precursor Mass" type="integer" value="200" help="Minimum mass of 1+ mass of parent ion to be considered"/> + <param name="xtandem_noise_suppr" label="X!Tandem: Noise Suppression" type="boolean" checked="true" truevalue="1" falsevalue="0" help="Use noise suppression"/> + + <conditional name="xtandem_refine"><!-- -xtandem_refine --> + <param name="xtandem_refine_selector" type="select" label="X!Tandem peptide model refinement"> + <option value="no" selected="True">Don't refine</option> + <option value="yes" >Use refinement</option> + </param> + <when value="no"/> + <when value="yes"> + <param name="xtandem_refine_unc" label="X!Tandem: Unanticipated cleavage, refinement" type="boolean" truevalue="1" falsevalue="0" help="Allow for unanticipated cleavage during refinement"/> + <param name="xtandem_refine_semi" label="X!Tandem: Cleavage semi, refinement" type="boolean" truevalue="1" falsevalue="0" help="Search for semi-tryptic peptides during refinement"/> + <param name="xtandem_refine_p_mut" label="X!Tandem: Point mutations, refinement" type="boolean" truevalue="1" falsevalue="0" help="Allow for point mutations during refinement"/> + <param name="xtandem_refine_snaps" label="X!Tandem: snAPs, refinement" type="boolean" truevalue="1" falsevalue="0" help="Search for known single amino acid polymorphisms during refinement"/> + <param name="xtandem_refine_spec_synt" label="X!Tandem: Spectrum synthesis, refinement" type="boolean" truevalue="1" falsevalue="0" help="Use spectrum synthesis scoring"/> + </when> + </conditional> + </when> + </conditional> + + <conditional name="omssa"> + <param name="omssa_selector" type="select" label="Run OMSSA search"> + <option value="yes" selected="True">Search with OMSSA</option> + <option value="no">No OMSSA search</option> + </param> + <when value="no" /> + <when value="yes"> + <param name="hitlist_length" label="OMSSA: Hit List Length" type="integer" value="25" /> + <param name="remove_precursor" label="OMSSA: Remove Precurosr" type="boolean" truevalue="1" falsevalue="0" checked="true"/> + <param name="scale_precursor" label="OMSSA: Scale Precursor Mass" type="boolean" truevalue="1" falsevalue="0" checked="false"/> + <param name="estimate_charge" label="OMSSA: Estimate Charge" type="boolean" truevalue="1" falsevalue="0" checked="true" /> + </when> + </conditional> + + <conditional name="msgf"> + <param name="msgf_selector" type="select" label="Run MSGF search"> + <option value="yes" selected="True">Search with MSGF</option> + <option value="no">No MSGF search</option> + </param> + <when value="no" /> + <when value="yes"> + <param name="msgf_decoy" label="Search Decoys" type="boolean" truevalue="1" falsevalue="0" help="If yes then a decoy database will be generated and searched. Assumed input database contains no decoys"/> + <param name="msgf_min_pep_length" label="Minimum Peptide Length" type="integer" value="6" help="Minimum length for a peptide to be considered"/> + <param name="msgf_max_pep_length" label="Maximum Peptide Length" type="integer" value="30" help="Maximum length for a peptide to be considered"/> + <param name="msgf_termini" label="Number of tolerable termini" type="select" format="text" 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> + </param> + <param name="msgf_num_ptms" label="Max PTMs per peptide" type="integer" value="2"/> + </when> + </conditional> + + <conditional name="ms_amanda"> + <param name="ms_amanda_selector" type="select" label="Run MS Amanda search"> + <option value="yes">Search with MS Amanda</option> + <option value="no" selected="True">No MS Amanda search</option> + </param> + <when value="no" /> + <when value="yes"> + </when> + </conditional> + </when> + </conditional> + <conditional name="processing_options"> + <param name="processing_options_selector" type="select" label="Specify Advanced PeptideShaker Processing Options"> + <option value="no" selected="True">Default Processing Options</option> + <option value="yes">Advanced Processing Options</option> + </param> + <when value="no" /> + <when value="yes"> + <param name="protein_fdr" label="FDR at the protein level" help="In percent (default 1% FDR: '1')" value="1" type="float" /> + <param name="peptide_fdr" label="FDR at the peptide level" help="In percent (default 1% FDR: '1')" value="1" type="float" /> + <param name="psm_fdr" label="FDR at the PSM level" help="In percent (default 1% FDR: '1')" value="1" type="float" /> + <param name="protein_fraction_mw_confidence" label="Minimum confidence required for a protein in the fraction MW plot" value="" type="float" + help="default 95%: '95.0'" /> + <conditional name="ptm_score"> + <param name="ptm_score_selector" type="select" label="The PTM probabilistic score to use for PTM localization"> + <option value="0" selected="True">A-score</option> + <option value="1">PhosphoRS</option> + </param> + <when value="0" /> + <when value="1"> + <param name="score_neutral_losses" label="Include Neutral Losses in A Score" type="boolean" truevalue="1" falsevalue="0" /> + <param name="ptm_threshold" label="The threshold to use for the PTM scores" value="" type="float" + help="Automatic mode will be used if not set" /> + </when> + </conditional> + <!-- SKIPPING -protein_fraction_mw_confidence ${processing_options.protein_fraction_mw_confidence} --> + </when> + </conditional> + <conditional name="filtering_options"> + <param name="filtering_options_selector" type="select" label="Specify Advanced Filtering Options" + help="Filter based on peptide lengths, precursor mass error, E value errors from X! Tandem and OMSSA, and include/exclude unknown PTM’s"> + <option value="no" selected="True">Default Filtering Options</option> + <option value="yes">Advanced Processing Options</option> + </param> + <when value="no" /> + <when value="yes"> + <param name="min_peptide_length" label="Minimum Peptide Length" value="6" type="integer" /> + <param name="max_peptide_length" label="Maximum Peptide Length" value="30" type="integer" /> + <param name="max_precursor_error" label="Maximum Precursor Error" value="10" type="float" help="Next option specifies units (Da or ppm)" /> + <param name="max_precursor_error_type" label="Maximum Precursor Error Type" type="select"> + <option value="0">ppm</option> + <option value="1">Daltons</option> + </param> + <param name="max_xtandem_e" label="Maximum X! Tandem e-value" value="100" type="float" help="" /> + <param name="max_omssa_e" label="Maximum OMSSA e-value" value="100" type="float" help="" /> + <param name="max_mascot_e" label="Maximum Mascot e-value filter" value="100" type="float" help="" /> + <param name="exclude_unknown_ptms" label="Exclude Unknown PTMs" type="boolean" truevalue="1" falsevalue="0" checked="true" /> + </when> + </conditional> + + <param name="outputs" type="select" display="checkboxes" multiple="True" label="Output options"> + <option value="mzidentML" selected="True">mzidentML File</option> + <option value="3" selected="True">Peptide Report</option> + <option value="4" selected="True">Protein Report</option> + <option value="2">PSM Report</option> + <option value="0">Certificate of Analysis</option> + <option value="1">Hierarchical Report</option> + <option value="cps">CPS file</option> + <validator type="no_options" message="Please select at least one output file" /> + </param> + </inputs> + <outputs> + <data format="mzid" name="mzidentML" from_work_dir="output.mzid" label="${tool.name} on ${on_string}: mzidentML file"> + <filter>'mzidentML' in outputs</filter> + </data> + <data format="cps" name="output" from_work_dir="peptide_shaker_output.cps" label="${tool.name} on ${on_string}: CPS file"> + <filter>'cps' in outputs</filter> + </data> + <data format="txt" name="output_certificate" from_work_dir="certificate.txt" label="${tool.name} on ${on_string}: Parameters"> + <filter>'0' in outputs</filter> + </data> + <data format="tabular" name="output_psm" from_work_dir="psm.txt" label="${tool.name} on ${on_string}: PSM Report"> + <filter>'2' in outputs</filter> + </data> + <data format="tabular" name="output_peptides" from_work_dir="peptides.txt" label="${tool.name} on ${on_string}: Peptide Report"> + <filter>'3' in outputs</filter> + </data> + <data format="tabular" name="output_proteins" from_work_dir="proteins.txt" label="${tool.name} on ${on_string}: Protein Report"> + <filter>'4' in outputs</filter> + </data> + <data format="tabular" name="output_hierarchical" from_work_dir="hierarchical.txt" label="${tool.name} on ${on_string}: Hierarchical Report"> + <filter>'1' in outputs</filter> + </data> + </outputs> + <tests> + <test> + <param name="input_database" value="tinydb.fasta"/> + <param name="peak_lists" value="tinyspectra.mgf"/> + <param name="precursor_ion_tol" value="100"/> + <param name="fixed_modifications" value="carbamidomethyl c"/> + <param name="variable_modifications" value="oxidation of m"/> + <param name="min_charge" value="1"/> + <param name="max_charge" value="3"/> + <param name="advanced_type_selector" value="advanced"/> + <param name="species_type_selector" value="no_species_type"/> + <param name="processing_options_selector" value="no"/> + <param name="filtering_options_selector" value="no"/> + <!--param name="xtandem_selector" value="no"/>--> + <param name="xtandem_selector" value="yes"/> + <param name="xtandem_selector.xtandem_refine_selector" value="yes"/> + + <param name="omssa_selector" value="no"/> + <param name="msgf_selector" value="yes"/> + <param name="ms_amanda_selector" value="no"/> + + <output name="output" file="tinyoutput.cps" compare="sim_size" delta="600" /> + </test> + </tests> + <help> +**What it does** + +Runs multiple search engines (X! Tandem, OMSSA and MS-GF+) on any number of MGF peak lists using the SearchGUI application and combines the results. + +https://code.google.com/p/peptide-shaker/ + +https://code.google.com/p/searchgui/ + +---- + +Reports +======= + + +PSM Report +---------- + +* Protein(s): Protein(s) to which the peptide can be attached +* Sequence: Sequence of the peptide +* Variable Modifications: The variable modifications +* D-score: D-score for variable PTM localization +* probabilistic PTM score: The probabilistic score (e.g. A-score or PhosphoRS) used for variable PTM localization. +* Localization Confidence: The confidence in variable PTM localization. +* Fixed Modifications: The fixed modifications. +* Spectrum File: The spectrum file. +* Spectrum Title: The title of the spectrum. +* Spectrum Scan Number: The spectrum scan number. +* RT: Retention time +* m/z: Measured m/z +* Measured Charge: The charge as given in the spectrum file. +* Identification Charge: The charge as inferred by the search engine. +* Theoretical Mass: The theoretical mass of the peptide. +* Isotope Number: The isotope number targetted by the instrument. +* Precursor m/z Error: The precursor m/z matching error. +* Score: Score of the retained peptide as a combination of the algorithm scores (used to rank PSMs). +* Confidence: Confidence in percent associated to the retained PSM. +* Decoy: Indicates whether the peptide is a decoy (1: yes, 0: no). +* Validation: Indicates the validation level of the protein group. + + +Protein Report +-------------- + +* Main Accession: Main accession of the protein group. +* Description: Description of the protein designed by the main accession. +* Gene Name: The gene names of the Ensembl gene ID associated to the main accession. +* Chromosome: The chromosome of the Ensembl gene ID associated to the main accession. +* PI: Protein Inference status of the protein group. +* Secondary Accessions: Other accessions in the protein group (alphabetical order). +* Protein Group: The complete protein group (alphabetical order). +* #Peptides: Total number of peptides. +* #Validated Peptides: Number of validated peptides. +* #Unique: Total number of peptides unique to this protein group. +* #PSMs: Number of PSMs +* #Validated PSMs: Number of validated PSMs +* Coverage (%): Sequence coverage in percent of the protein designed by the main accession. +* Possible Coverage (%): Possible sequence coverage in percent of the protein designed by the main accession according to the search settings. +* MW (kDa): Molecular Weight. +* Spectrum Counting NSAF: Normalized Spectrum Abundance Factor (NSAF) +* Spectrum Counting emPAI: exponentially modified Protein Abundance Index (emPAI) +* Confident Modification Sites: Number of Confident Modification Sites List of the sites where a variable modification was confidently localized. +* Other Modification Sites: Number of other Modification Sites List of the non*confident sites where a variable modification was localized. +* Score: Score of the protein group. +* Confidence: Confidence in percent associated to the protein group. +* Decoy: Indicates whether the protein group is a decoy (1: yes, 0: no). +* Validation: Indicates the validation level of the protein group. + + +Peptide Report +-------------- + + +* Protein(s): Protein(s) to which this peptide can be attached. +* AAs Before: The amino-acids before the sequence. +* Sequence: Sequence of the peptide. +* AAs After: The amino-acids after the sequence. +* Modified Sequence: The peptide sequence annotated with variable modifications. +* Variable Modifications: The variable modifications. +* Localization Confidence: The confidence in PTMs localization. +* Fixed Modifications: The fixed modifications. +* #Validated PSMs: Number of validated PSMs. +* #PSMs: Number of PSMs. +* Score: Score of the peptide. +* Confidence: Confidence in percent associated to the peptide. +* Decoy: Indicates whether the peptide is a decoy (1: yes, 0: no). +* Validation: Indicates the validation level of the protein group. + + +Hierachical Report +------------------ + +* Main Accession: Main accession of the protein group. +* Description: Description of the protein designed by the main accession. +* PI: Protein Inference status of the protein group. +* Secondary Accessions: Other accessions in the protein group (alphabetical order). +* Protein Group: The complete protein group (alphabetical order). +* #Peptides: Total number of peptides. +* #Validated Peptides: Number of validated peptides. +* #Unique: Total number of peptides unique to this protein group. +* #PSMs: Number of PSMs +* #Validated PSMs: Number of validated PSMs +* Coverage (%): Sequence coverage in percent of the protein designed by the main accession. +* Possible Coverage (%): Possible sequence coverage in percent of the protein designed by the main accession according to the search settings. +* MW (kDa): Molecular Weight. +* Spectrum Counting NSAF: Normalized Spectrum Abundance Factor (NSAF) +* Spectrum Counting emPAI: exponentially modified Protein Abundance Index (emPAI) +* Confident Modification Sites: # Confident Modification Sites List of the sites where a variable modification was confidently localized. +* Other Modification Sites: # Other Modification Sites List of the non-confident sites where a variable modification was localized. +* Score: Score of the protein group. +* Confidence: Confidence in percent associated to the protein group. +* Decoy: Indicates whether the protein group is a decoy (1: yes, 0: no). +* Validation: Indicates the validation level of the protein group. +* Protein(s): Protein(s) to which this peptide can be attached. +* AAs Before: The amino-acids before the sequence. +* Sequence: Sequence of the peptide. +* AAs After: The amino-acids after the sequence. +* Variable Modifications: The variable modifications. +* Localization Confidence: The confidence in PTMs localization. +* Fixed Modifications: The fixed modifications. +* #Validated PSMs: Number of validated PSMs. +* #PSMs: Number of PSMs. +* Score: Score of the peptide. +* Confidence: Confidence in percent associated to the peptide. +* Decoy: Indicates whether the peptide is a decoy (1: yes, 0: no). +* Validation: Indicates the validation level of the protein group. +* Protein(s): Protein(s) to which the peptide can be attached. +* Sequence: Sequence of the peptide. +* Modified Sequence: The peptide sequence annotated with variable modifications. +* Variable Modifications: The variable modifications. +* D-score: D-score for variable PTM localization. +* probabilistic PTM score: The probabilistic score (e.g. A-score or PhosphoRS) used for variable PTM localization. +* Localization Confidence: The confidence in variable PTM localization. +* Fixed Modifications: The fixed modifications. +* Spectrum File: The spectrum file. +* Spectrum Title: The title of the spectrum. +* Spectrum Scan Number: The spectrum scan number. +* RT: Retention time +* m/z: Measured m/z +* Measured Charge: The charge as given in the spectrum file. +* Identification Charge: The charge as inferred by the search engine. +* Theoretical Mass: The theoretical mass of the peptide. +* Isotope Number: The isotope number targetted by the instrument. +* Precursor m/z Error: The precursor m/z matching error. +* Score: Score of the retained peptide as a combination of the algorithm scores (used to rank PSMs). +* Confidence: Confidence in percent associated to the retained PSM. +* Decoy: Indicates whether the peptide is a decoy (1: yes, 0: no). +* Validation: Indicates the validation level of the protein group. + + + + +------ + +**Citation** + +To cite the underlying tools (PeptideShaker and SearchGUI) please refer to the list of papers at http://peptide-shaker.googlecode.com + +If you use this tool in Galaxy, please cite Chilton J, Ira Cooke, Bjoern Gruening et al. https://bitbucket.org/galaxyp/peptideshaker + </help> +</tool>