# HG changeset patch # User iracooke # Date 1402698993 14400 # Node ID e0a1e8a0500ac4f1032d21cd7c4f48a941a77cf8 # Parent 4f6cbe948065d78f6aabb242d2639177738e1973 Uploaded diff -r 4f6cbe948065 -r e0a1e8a0500a README --- a/README Sun Jun 09 08:17:57 2013 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,7 +0,0 @@ -This package is a galaxy wrapper for the MSGF+ search tool. - -Requirements: -This package depends on the galaxy_protk, protk_msgfplus, protk_proteowizard packages -Please see instructions for those packages before installing - -In addition to basic requirements you must also have unzip and java 6 runtime (or greater) installed diff -r 4f6cbe948065 -r e0a1e8a0500a README.md --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/README.md Fri Jun 13 18:36:33 2014 -0400 @@ -0,0 +1,8 @@ +## What is it? +Galaxy tool definition file and wrapper scripts for the [MSGF+ Search Engine](http://proteomics.ucsd.edu/Software/MSGFPlus.html). + +## Installation +Install from the main galaxy toolshed at http://toolshed.g2.bx.psu.edu/ + +Depends on command-line scripts and databases available in the [protk ruby gem](https://bitbucket.org/iracooke/protk). + diff -r 4f6cbe948065 -r e0a1e8a0500a msgfplus_search.xml --- a/msgfplus_search.xml Sun Jun 09 08:17:57 2013 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,230 +0,0 @@ - - - - galaxy_protk - msgfplus - proteowizard - - - - Run an MSGF+ Search - - - rvm 1.9.3@protk-1.2.2 do msgfplus_search.rb - #if $database.source_select=="built_in": - --galaxy -d $database.dbkey - #else - --galaxy -d $database.fasta_file - #end if - - --var-mods=' - $variable_mods - #for $custom_variable_mod in $custom_variable_mods: - ,${custom_variable_mod.custom_mod} - #end for - ' - - --fix-mods=' - $fixed_mods - #for $custom_fix_mod in $custom_fix_mods: - ,${custom_fix_mod.custom_mod} - #end for - ' - - $input_file - - -o $output - - -r - - --enzyme=$enzyme - - --precursor-ion-tol-units=$precursor_tolu - - -v $missed_cleavages - - -f $fragment_ion_tol - - -p $precursor_ion_tol - - --instrument=$instrument - - --isotope-error-range=$isotope_error_range - - --fragment-method=$fragment_method - - --protocol=$protocol - - --min-pep-len=$min_pep_len - --max-pep-len=$max_pep_len - --max-pep-charge=$max_pep_charge - --min-pep-charge=$min_pep_charge - --num-reported-matches=$num_reported_matches - - --java-mem=$java_mem - - #if $pepxml_output_use - - #else - --no-pepxml - #end if - - - - - - - - - - - - Database - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - Missed Cleavages Allowed - - - - - - - Enzyme - - - - - - - - - - - - - - Instrument Type - - - - - - - Fragmentation Method - - - - - - - - - Protocol - - - - - - - - - - - Precursor Ion Tolerance Units - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -**What it does** - -Runs an MS/MS database search using the MSGFPlus search engine. Output is in the form of a pepXML file containing identified peptides along with their raw search scores. - ----- - -**References** - -Please see http://proteomics.ucsd.edu/Software/MSGFPlus.html for details of the MSGFPlus search engine and references describing its algorithm - - - - diff -r 4f6cbe948065 -r e0a1e8a0500a repository_dependencies.xml --- a/repository_dependencies.xml Sun Jun 09 08:17:57 2013 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,6 +0,0 @@ - - - - - - diff -r 4f6cbe948065 -r e0a1e8a0500a tool-data/msgfplus_mods.loc.sample --- a/tool-data/msgfplus_mods.loc.sample Sun Jun 09 08:17:57 2013 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,50 +0,0 @@ -#This file lists the names of inbuilt chemical modifications accepted by msgfplus -#Each entry consists of 4 tab separated fields like this -# -# -#Modification strings should conform to the standard MSGFPlus syntax with the following exception -#The ModType field is overridden by the msgfplus_search.rb tool. In other words any of these mods -#May be passed to the tool as a variable or fixed mod and the tool will substitute the appropriate ModType -#value -# -#Standard MSGFPlus syntax is -# -# To input a modification, use the following command: -# Mass or CompositionStr, Residues, ModType, Position, Name (all the five fields are required). -# CompositionStr (C[Num]H[Num]N[Num]O[Num]S[Num]P[Num]) -# - C (Carbon), H (Hydrogen), N (Nitrogen), O (Oxygen), S (Sulfer) and P (Phosphorus) are allowed. -# - Atom can be omitted. The sequence of atoms must be followed. -# - Negative numbers are allowed. -# - E.g. C2H2O1 (valid), H2C1O1 (invalid) -# Mass can be used instead of CompositionStr. It is important to specify accurate masses (integer masses are insufficient). -# - E.g. 15.994915 -# Residues: affected amino acids (must be upper letters) -# - Must be uppor letters or * -# - Use * if this modification is applicable to any residue. -# - * should not be "anywhere" modification (e.g. "15.994915, *, opt, any, Oxidation" is not allowed.) -# - E.g. NQ, * -# ModType: "fix" for fixed modifications, "opt" for variable modifications (case insensitive) -# Position: position in the peptide where the modification can be attached. -# - One of the following five values should be used: -# - any (anywhere), N-term (peptide N-term), C-term (peptide C-term), Prot-N-term (protein N-term), Prot-C-term (protein C-term) -# - Case insensitive -# - "-" can be omitted -# - E.g. any, Any, Prot-n-Term, ProtNTerm => all valid -# Name: name of the modification (Unimod PSI-MS name) -# - For proper mzIdentML output, this name should be the same as the Unimod PSI-MS name -# - E.g. Phospho, Acetyl -#C2H3N1O1,C,fix,any,Carbamidomethyl # Fixed Carbamidomethyl C -# Variable Modifications (default: none) -#O1,M,opt,any,Oxidation # Oxidation M -#15.994915,M,opt,any,Oxidation # Oxidation M (mass is used instead of CompositionStr) -#H-1N-1O1,NQ,opt,any,Deamidated # Negative numbers are allowed. -#C2H3NO,*,opt,N-term,Carbamidomethyl # Variable Carbamidomethyl N-term -#H-2O-1,E,opt,N-term,Pyro_glu # Pyro-glu from E -#H-3N-1,Q,opt,N-term,Pyro-glu # Pyro-glu from Q -#C2H2O,*,opt,Prot-N-term,Acetyl # Acetylation Protein N-term -#C2H2O1,K,opt,any,Acetyl # Acetylation K -#CH2,K,opt,any,Methy # Methylation K -#HO3P,STY,opt,any,Phospho # Phosphorylation STY - -Carbamidomethyl C carbamidomethyl_c_ C2H3N1O1,C,opt,any,Carbamidomethyl carbamidomethyl_c_ -Oxidation M oxidation_m_ O1,M,opt,any,Oxidation oxidation_m_ \ No newline at end of file diff -r 4f6cbe948065 -r e0a1e8a0500a tool-data/pepxml_databases.loc.sample --- a/tool-data/pepxml_databases.loc.sample Sun Jun 09 08:17:57 2013 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,13 +0,0 @@ -#This file lists the names of protein databases installed locally in protk. -# These are used by omssa and x!tandem as well as the "mascot to pepxml" tool -# In order to combine search results with Interprophet searches must be run against an identical database -# -# Entries should follow the be structured as follows -# Display_name omssa_tandem_dbname dbkey -# -# -Swissprot spall_ spall spall_ -Combined PlasmboDB (falciparum) and Swissprot Human plasmodb_pfalciparum_sphuman_ plasmodb_pfalciparum_sphuman plasmodb_pfalciparum_sphuman_ -Swissprot Human sphuman_ sphuman sphuman_ -Combined Swissprot/TRembl Human sptrhuman_ sptrhuman sptrhuman_ -Swissprot Mouse spmouse_ spmouse spmouse_ diff -r 4f6cbe948065 -r e0a1e8a0500a tool_dependencies.xml --- a/tool_dependencies.xml Sun Jun 09 08:17:57 2013 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,18 +0,0 @@ - - - - - - - - - - - - - - - - - -