| Next changeset 1:50002ff2c1f3 (2013-03-04) |
|
Commit message:
Uploaded |
|
added:
msgfplus_search.xml tool-data/msgfplus_mods.loc.sample tool-data/pepxml_databases.loc.sample |
| b |
| diff -r 000000000000 -r 1049de3f4aed msgfplus_search.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/msgfplus_search.xml Sun Jan 06 20:06:08 2013 -0500 |
| b |
| @@ -0,0 +1,133 @@ +<tool id="proteomics_search_msgfplus_1" name="MSGF+ MSMS Search" version="1.0.0"> + <requirements><requirement type="package">protkgem</requirement></requirements> + <description>Run an MSGF+ Search</description> + + <command> + #if $database.source_select=="built_in": + msgfplus_search.rb --galaxy -d $database.dbkey --java-mem 8000M + #else #msgfplus_search.rb -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 + + + + </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">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="Hold the appropriate key while + clicking to select multiple items"> + <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"> + </param> + </repeat> + + + <param name="fixed_mods" format="text" type="select" multiple="true" label="Fixed Modifications" help="Hold the appropriate key while + clicking to select multiple items"> + <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="enzyme" type="select" format="text"> + <label>Enzyme</label> + <option value="Trypsin">Trypsin</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_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> + + </inputs> + + + <outputs> + <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"/> + </outputs> + + + <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> |
| b |
| diff -r 000000000000 -r 1049de3f4aed tool-data/msgfplus_mods.loc.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/msgfplus_mods.loc.sample Sun Jan 06 20:06:08 2013 -0500 |
| [ |
| @@ -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 |
| b |
| diff -r 000000000000 -r 1049de3f4aed tool-data/pepxml_databases.loc.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/pepxml_databases.loc.sample Sun Jan 06 20:06:08 2013 -0500 |
| b |
| @@ -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_ |