# HG changeset patch
# User iracooke
# Date 1402699012 14400
# Node ID 86daefc0e88dc4ae7be1a973225aa0f93e7558e9
# Parent e0a1e8a0500ac4f1032d21cd7c4f48a941a77cf8
Uploaded
diff -r e0a1e8a0500a -r 86daefc0e88d README
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/README Fri Jun 13 18:36:52 2014 -0400
@@ -0,0 +1,6 @@
+This package is a galaxy wrapper for the MSGF+ search tool.
+
+Requirements:
+This package uses protk, msgfplus and proteowizard, which must be installed separately.
+
+For instructions please see: https://github.com/iracooke/protk/#galaxy-integration
\ No newline at end of file
diff -r e0a1e8a0500a -r 86daefc0e88d README.md
--- a/README.md Fri Jun 13 18:36:33 2014 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
@@ -1,8 +0,0 @@
-## 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 e0a1e8a0500a -r 86daefc0e88d msgfplus_search.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/msgfplus_search.xml Fri Jun 13 18:36:52 2014 -0400
@@ -0,0 +1,188 @@
+
+ Run an MSGF+ Search
+
+ protk
+ msgfplus
+ proteowizard
+
+
+ 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
+ $cleavage_semi
+ -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
+ #unless $pepxml_output_use:
+ --no-pepxml
+ #end unless
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+**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 e0a1e8a0500a -r 86daefc0e88d repository_dependencies.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/repository_dependencies.xml Fri Jun 13 18:36:52 2014 -0400
@@ -0,0 +1,4 @@
+
+
+
+
diff -r e0a1e8a0500a -r 86daefc0e88d tool-data/msgfplus_mods.loc.sample
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/msgfplus_mods.loc.sample Fri Jun 13 18:36:52 2014 -0400
@@ -0,0 +1,50 @@
+#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 e0a1e8a0500a -r 86daefc0e88d tool-data/pepxml_databases.loc.sample
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/pepxml_databases.loc.sample Fri Jun 13 18:36:52 2014 -0400
@@ -0,0 +1,13 @@
+#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_