# HG changeset patch # User iracooke # Date 1418695092 18000 # Node ID 88d71afddaa46af88934c1895bc7cec5a72a273c # Parent fb19d519ad0a1aec0471140270eac78a466259b8 Uploaded diff -r fb19d519ad0a -r 88d71afddaa4 peptide_shaker.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/peptide_shaker.xml Mon Dec 15 20:58:12 2014 -0500 @@ -0,0 +1,650 @@ + + + Perform protein identification using various search engines based on results from SearchGUI + + + peptide_shaker + + + + +> $temp_stderr) + && + + ###################### + ## PeptideShakerCLI ## + ###################### + (java -cp \$PEPTIDESHAKER_JAR_PATH eu.isas.peptideshaker.cmd.PeptideShakerCLI + -temp_folder `pwd` + -experiment '${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 + + -threads "\${GALAXY_SLOTS:-12}" + + ##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) +]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + 'mzidentML' in outputs + + + 'cps' in outputs + + + '0' in outputs + + + '2' in outputs + + + '3' in outputs + + + '4' in outputs + + + '1' in outputs + + + + + + + + + + + + + + + + + + + + + + + + + + +**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 + + +