Previous changeset 8:4f6cbe948065 (2013-06-09) Next changeset 10:86daefc0e88d (2014-06-13) |
Commit message:
Uploaded |
added:
README.md |
removed:
README msgfplus_search.xml repository_dependencies.xml tool-data/msgfplus_mods.loc.sample tool-data/pepxml_databases.loc.sample tool_dependencies.xml |
b |
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 |
b |
@@ -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 |
b |
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). + |
b |
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 |
b |
b'@@ -1,230 +0,0 @@\n-<tool id="proteomics_search_msgfplus_1" name="MSGF+ MSMS Search" version="1.0.1">\n-\n-\t<requirements>\n- \t<requirement type="package" version="1.2.2">galaxy_protk</requirement>\n- \t<requirement type="package" version="20130227">msgfplus</requirement>\n- \t<requirement type="package" version="3_0_4388">proteowizard</requirement>\n- \t</requirements>\n-\n-\n-\t<description>Run an MSGF+ Search</description>\n-\n-\t<command>\n-\t\trvm 1.9.3@protk-1.2.2 do msgfplus_search.rb\n-\t\t#if $database.source_select=="built_in":\n-\t\t --galaxy -d $database.dbkey\n-\t\t#else\n-\t\t--galaxy -d $database.fasta_file\n-\t\t#end if\n-\n-\t\t--var-mods=\'\n-\t\t$variable_mods\n-\t\t#for $custom_variable_mod in $custom_variable_mods:\n-\t\t,${custom_variable_mod.custom_mod}\n-\t\t#end for\n-\t\t\'\n-\n-\t\t--fix-mods=\'\n-\t\t$fixed_mods\n-\t\t#for $custom_fix_mod in $custom_fix_mods:\n-\t\t,${custom_fix_mod.custom_mod}\n-\t\t#end for\n-\t\t\'\n-\n-\t\t$input_file \n-\n-\t\t-o $output \n-\n-\t\t-r \n-\n-\t\t--enzyme=$enzyme \n-\n-\t\t--precursor-ion-tol-units=$precursor_tolu \n-\n-\t\t-v $missed_cleavages \n-\n-\t\t-f $fragment_ion_tol \n-\n-\t\t-p $precursor_ion_tol \n-\n-\t\t--instrument=$instrument\n-\t\t\n-\t\t--isotope-error-range=$isotope_error_range\n-\n-\t\t--fragment-method=$fragment_method\n-\n-\t\t--protocol=$protocol\n-\n-\t\t--min-pep-len=$min_pep_len\n-\t\t--max-pep-len=$max_pep_len\n-\t\t--max-pep-charge=$max_pep_charge\n-\t\t--min-pep-charge=$min_pep_charge\n-\t\t--num-reported-matches=$num_reported_matches\n-\n-\t\t--java-mem=$java_mem\n-\n-\t\t#if $pepxml_output_use\n-\n-\t\t#else\n-\t\t--no-pepxml\n-\t\t#end if\n-\n-\t</command>\n-\n-\t<inputs>\t\n-\t\t<conditional name="database">\n-\t\t\t<param name="source_select" type="select" label="Database source">\n-\t\t\t\t<option value="built_in">Built-In</option>\n-\t\t\t\t<option value="input_ref">Your Upload File</option>\n-\t\t\t</param>\n-\t\t\t<when value="built_in">\n-\t\t\t\t<param name="dbkey" type="select" format="text" >\n-\t\t\t\t\t<label>Database</label>\n-\t\t\t\t\t<options from_file="pepxml_databases.loc">\n-\t\t\t\t\t\t<column name="name" index="0" />\n-\t\t\t\t\t\t<column name="value" index="2" />\n-\t\t\t\t\t</options>\n-\t\t\t\t</param>\n-\t\t\t</when>\n-\t\t\t<when value="input_ref">\n-\t\t\t\t<param name="fasta_file" type="data" format="fasta" label="Uploaded FASTA file" />\n-\t\t\t</when>\n-\t\t</conditional>\n-\t\t\n-\t\t<param name="input_file" type="data" format="mzml" multiple="false" label="MSMS File" help="An mzML file with MS/MS data"/>\n-\n-\n-\t\t<param name="variable_mods" format="text" type="select" multiple="true" label="Variable Modifications" help="Multiple Selection Allowed">\n-\t\t\t<options from_file="msgfplus_mods.loc">\n-\t\t\t\t<column name="name" index="0" />\n-\t\t\t\t<column name="value" index="2" />\n-\t\t\t</options>\n-\t\t</param>\n-\n-\t\t<repeat name="custom_variable_mods" title="Custom Variable Modifications" help="See https://bix-lab.ucsd.edu/pages/viewpage.action?pageId=13533355 for details on how to create these">\n-\t\t\t<param name="custom_mod" type="text">\n-\t\t\t</param>\n-\t\t</repeat>\n-\t\t\n-\t\t\n-\t\t<param name="fixed_mods" format="text" type="select" multiple="true" label="Fixed Modifications" help="Multiple Selection Allowed">\n-\t\t\t<options from_file="msgfplus_mods.loc">\n-\t\t\t\t<column name="name" index="0" />\n-\t\t\t\t<column name="value" index="2" />\n-\t\t\t</options>\n-\t\t</param>\n-\n-\t\t<repeat name="custom_fix_mods" title="Custom Fixed Modifications" help="See https://bix-lab.ucsd.edu/pages/viewpage.action?pageId=13533355 for details on how to create these">\n-\t\t\t<param name="custom_mod" type="text">\n-\t\t\t</param>\n-\t\t</repeat>\n-\t\t\n-\t\t\n-\n-\t\t<param name="missed_cleavages" type="select" format="text" help="Allow peptides to contain up to this many missed enzyme cleavage sites">\n-\t\t\t<label>Missed Cleavages Allowed</label>\n-\t\t <option value="0">0</option>\t\t\n-\t\t\t<option value="1">1</option>\n-\t\t\t<option value="2">2</option>\n-\t\t</param>\n-\t\t\n-\t\t<param name="enzyme" type="select" format="text">\n-\t\t <label>Enzyme</label>\n-\t\t <option value="0">unspecific cleavage</option>\n-\t\t <option value="1">Trypsin</option>\n-\t\t <option value="2">Chymotrypsin</option>\n-\t\t <option value="3">Lys-C</option>\n-\t\t '..b'no cleavage</option>\n-\t\t</param>\n-\t\t\n-\t\t<param name="instrument" type="select" format="text">\n-\t \t<label>Instrument Type</label>\n-\t\t\t<option value="2">TOF</option>\n-\t\t\t<option value="0">Low-res LCQ/LTQ</option>\n-\t\t\t<option value="1">High-res LTQ</option>\n-\t\t</param>\n-\n-\t\t<param name="fragment_method" type="select" format="text">\n-\t \t<label>Fragmentation Method</label>\n-\t\t\t<option value="0">Respect Input File</option>\n-\t\t\t<option value="1">CID</option>\n-\t\t\t<option value="2">ETD</option>\n-\t\t\t<option value="3">HCD</option>\n-\t\t\t<option value="4">Merge spectra from same precursor</option>\n-\t\t</param>\n-\n-\t\t<param name="protocol" type="select" format="text">\n-\t \t<label>Protocol</label>\n-\t\t\t<option value="0">NoProtocol</option>\n-\t\t\t<option value="1">Phosphorylation</option>\n-\t\t\t<option value="2">iTRAQ</option>\n-\t\t\t<option value="3">iTRAQPhospho</option>\n-\t\t</param>\n-\n-\t\t<param name="fragment_ion_tol" help="Fragment Ion Tolerance in Daltons" type="float" value="0.65" min="0" max="10000" label="Fragment ion tolerance"/>\n-\n-\t\t<param name="precursor_ion_tol" help="Precursor Ion Tolerance (Da or ppm)" type="float" value="100" min="0" max="10000" label="Precursor ion tolerance"/>\n-\t\t<param name="precursor_tolu" type="select" format="text">\n-\t\t <label>Precursor Ion Tolerance Units</label>\n-\t\t <option value="ppm">ppm</option>\t\t\n-\t\t\t<option value="Da">Da</option>\n-\t\t</param>\n-\t\t\n-\t\t<param name="isotope_error_range" help="Takes into account of the error introduced by chooosing a non-monoisotopic peak for fragmentation." type="text" size="80" value="0,1" label="Isotope Error Range"/>\n-\n-\t\t<param name="min_pep_len" help="" type="integer" value="6" label="Minimum Peptide Length"/>\n-\t\t<param name="max_pep_len" help="" type="integer" value="40" label="Maximum Peptide Length"/>\n-\t\t<param name="min_pep_charge" help="" type="integer" value="2" label="Minimum Peptide Charge"/>\n-\t\t<param name="max_pep_charge" help="" type="integer" value="3" label="Maximum Peptide Charge"/>\n-\t\t<param name="num_reported_matches" help="Number of matches per spectrum to be reported" type="integer" value="1" label="Num reported matches"/>\n-\t\t<param name="java_mem" help="Increase this value if you get out of memory errors" type="text" size="80" value="3500M" label="Java Memory Limit"/>\n-\n-\n-\t\t<param name="pepxml_output_use" type="boolean" label="Convert results to pepXML" help="" truevalue="true" falsevalue="false" />\n-\n-\t</inputs>\n-\n-\n-<!-- \t<outputs>\n-\t\t<data format="raw_pepxml" name="output" metadata_source="input_file" label="MSGF+_vs_${database.dbkey if $database.has_key(\'dbkey\') else $database.fasta_file.display_name}.${input_file.display_name}.${input_file.display_name}.pepXML"/>\n-\t</outputs>\n- -->\n-\t<outputs>\n- \t<data format="mzid" name="output" metadata_source="input_file" label="MSGF+_vs_${database.dbkey if $database.has_key(\'dbkey\') else $database.fasta_file.display_name}.${input_file.display_name}.${input_file.display_name}">\n- <change_format>\n- <when input="pepxml_output_use" value="true" format="raw_pepxml" metadata_source="input_file" label="MSGF+_vs_${database.dbkey if $database.has_key(\'dbkey\') else $database.fasta_file.display_name}.${input_file.display_name}.${input_file.display_name}"/>\n- </change_format>\n- </data>\n- </outputs>\n-\n-\n-\t<tests>\n- \t<test>\n- \t\t<param name="source_select" value="input_ref"/>\n-\t \t<param name="fasta_file" value="bsa.fasta"/>\n- \t\t \t<param name="input_file" value="bsa.mzML"/>\n- \t\t<output name="output" file="bsa.mzid" compare="sim_size" delta="600" /> \n- \t</test>\n- \t</tests>\n-\n-\n- <help>\n-\n-**What it does**\n-\n-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.\n-\n-----\n-\n-**References**\n-\n-Please see http://proteomics.ucsd.edu/Software/MSGFPlus.html for details of the MSGFPlus search engine and references describing its algorithm\n-\n- </help>\n-\n-</tool>\n' |
b |
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 |
b |
@@ -1,6 +0,0 @@ -<?xml version="1.0"?> -<repositories description="Proteomics datatypes, MSGF+ and Protk"> - - <repository toolshed="http://toolshed.g2.bx.psu.edu" name="proteomics_datatypes" owner="iracooke" changeset_revision="09b89b345de2"/> - - </repositories> |
b |
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 -#<Displayed Name> <DBKey> <Modification String> <DBKey> -# -#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 |
b |
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 |
b |
@@ -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_ |
b |
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 |
b |
@@ -1,18 +0,0 @@ -<?xml version="1.0"?> -<tool_dependency> - - - <package name="galaxy_protk" version="1.2.2"> - <repository toolshed="http://toolshed.g2.bx.psu.edu" name="galaxy_protk" owner="iracooke" changeset_revision="c25df71f7b68" prior_installation_required="True"/> - </package> - - <package name="proteowizard" version="3_0_4388"> - <repository toolshed="http://toolshed.g2.bx.psu.edu" name="protk_proteowizard" owner="iracooke" changeset_revision="863462ea0187"/> - </package> - - <package name="msgfplus" version="20130227"> - <repository toolshed="http://toolshed.g2.bx.psu.edu" name="protk_msgfplus" owner="iracooke" changeset_revision="75a2edcb6d0c"/> - </package> - - -</tool_dependency> |