Mercurial > repos > iracooke > msgfplus
changeset 10:86daefc0e88d draft
Uploaded
author | iracooke |
---|---|
date | Fri, 13 Jun 2014 18:36:52 -0400 |
parents | e0a1e8a0500a |
children | deb61a965680 |
files | README README.md msgfplus_search.xml repository_dependencies.xml tool-data/msgfplus_mods.loc.sample tool-data/pepxml_databases.loc.sample |
diffstat | 6 files changed, 261 insertions(+), 8 deletions(-) [+] |
line wrap: on
line diff
--- /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
--- 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). -
--- /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 @@ +<tool id="proteomics_search_msgfplus_1" name="MSGF+ MSMS Search" version="1.0.3"> + <description>Run an MSGF+ Search</description> + <requirements> + <requirement type="package" version="1.3">protk</requirement> + <requirement type="package" version="20140210">msgfplus</requirement> + <requirement type="package" version="3_0_4388">proteowizard</requirement> + </requirements> + <command> + 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 + </command> + + <inputs> + <conditional name="database"> + <param name="source_select" type="select" label="Database source"> + <option value="built_in">Built-In</option> + <option value="input_ref" selected="true">Your Upload File</option> + </param> + <when value="built_in"> + <param name="dbkey" type="select" format="text" > + <label>Database</label> + <options from_file="pepxml_databases.loc"> + <column name="name" index="0" /> + <column name="value" index="2" /> + </options> + </param> + </when> + <when value="input_ref"> + <param name="fasta_file" type="data" format="fasta" label="Uploaded FASTA file" /> + </when> + </conditional> + <param name="input_file" type="data" format="mzml" multiple="false" label="MSMS File" help="An mzML file with MS/MS data"/> + <param name="variable_mods" format="text" type="select" multiple="true" label="Variable Modifications" help="Multiple Selection Allowed"> + <options from_file="msgfplus_mods.loc"> + <column name="name" index="0" /> + <column name="value" index="2" /> + </options> + </param> + <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"> + <param name="custom_mod" type="text" /> + </repeat> + <param name="fixed_mods" format="text" type="select" multiple="true" label="Fixed Modifications" help="Multiple Selection Allowed"> + <options from_file="msgfplus_mods.loc"> + <column name="name" index="0" /> + <column name="value" index="2" /> + </options> + </param> + <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"> + <param name="custom_mod" type="text"> + </param> + </repeat> + <param name="missed_cleavages" type="select" format="text" help="Allow peptides to contain up to this many missed enzyme cleavage sites"> + <label>Missed Cleavages Allowed</label> + <option value="0">0</option> + <option value="1">1</option> + <option value="2">2</option> + </param> + + <param name="cleavage_semi" type="boolean" label="Allow semi-cleaved peptides" help="This can increase search time dramatically" truevalue="" falsevalue="--no-cleavage-semi" /> + + <param name="enzyme" type="select" format="text"> + <label>Enzyme</label> + <option value="0">unspecific cleavage</option> + <option value="1">Trypsin</option> + <option value="2">Chymotrypsin</option> + <option value="3">Lys-C</option> + <option value="4">Lys-N</option> + <option value="5">glutamyl endopeptidase</option> + <option value="6">Arg-C</option> + <option value="7">Asp-N</option> + <option value="8">alphaLP</option> + <option value="9">no cleavage</option> + </param> + + <param name="instrument" type="select" format="text"> + <label>Instrument Type</label> + <option value="2">TOF</option> + <option value="0">Low-res LCQ/LTQ</option> + <option value="1">High-res LTQ</option> + </param> + + <param name="fragment_method" type="select" format="text"> + <label>Fragmentation Method</label> + <option value="0">Respect Input File</option> + <option value="1">CID</option> + <option value="2">ETD</option> + <option value="3">HCD</option> + <option value="4">Merge spectra from same precursor</option> + </param> + + <param name="protocol" type="select" format="text"> + <label>Protocol</label> + <option value="0">NoProtocol</option> + <option value="1">Phosphorylation</option> + <option value="2">iTRAQ</option> + <option value="3">iTRAQPhospho</option> + </param> + + <param name="fragment_ion_tol" help="Fragment Ion Tolerance in Daltons" type="float" value="0.65" min="0" max="10000" label="Fragment ion tolerance"/> + + <param name="precursor_ion_tol" help="Precursor Ion Tolerance (Da or ppm)" type="float" value="100" min="0" max="10000" label="Precursor ion tolerance"/> + <param name="precursor_tolu" type="select" format="text"> + <label>Precursor Ion Tolerance Units</label> + <option value="ppm">ppm</option> + <option value="Da">Da</option> + </param> + + <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"/> + <param name="min_pep_len" help="" type="integer" value="6" label="Minimum Peptide Length"/> + <param name="max_pep_len" help="" type="integer" value="40" label="Maximum Peptide Length"/> + <param name="min_pep_charge" help="" type="integer" value="2" label="Minimum Peptide Charge"/> + <param name="max_pep_charge" help="" type="integer" value="3" label="Maximum Peptide Charge"/> + <param name="num_reported_matches" help="Number of matches per spectrum to be reported" type="integer" value="1" label="Num reported matches"/> + <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"/> + <param name="pepxml_output_use" type="boolean" label="Convert results to pepXML" help="" truevalue="true" falsevalue="false" /> + </inputs> + <outputs> + <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}.${input_file.display_name}"> + <change_format> + <when input="pepxml_output_use" value="true" format="raw_pepxml" metadata_source="input_file" + label="MSGF+_vs_${database.dbkey if $database.has_key('dbkey') else $database.fasta_file.display_name}.${input_file.display_name}.${input_file.display_name}"/> + </change_format> + </data> + </outputs> + <tests> + <test> + <param name="source_select" value="input_ref"/> + <param name="fasta_file" value="bsa.fasta"/> + <param name="input_file" value="bsa.mzML"/> + <output name="output" file="bsa.mzid" compare="sim_size" delta="600" /> + </test> + </tests> + <help> + +**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 + + </help> +</tool>
--- /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 @@ +<?xml version="1.0"?> +<repositories description="Proteomics datatypes"> + <repository changeset_revision="f66f8ca7b7b9" name="proteomics_datatypes" owner="iracooke" toolshed="http://toolshed.g2.bx.psu.edu" /> + </repositories>
--- /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 +#<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
--- /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_