Mercurial > repos > iracooke > xtandem

changeset 11:618d74240c7f draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author iracooke
date Mon, 16 Jun 2014 05:47:55 -0400
parents ffd1d25b8080
children f9271f6991b1
files README README.md repository_dependencies.xml tandem.xml tandem_to_pepxml.xml tool-data/pepxml_databases.loc.sample tool-data/tandem_mods.loc.sample
diffstat 7 files changed, 233 insertions(+), 31 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/README	Mon Jun 16 05:47:55 2014 -0400
@@ -0,0 +1,6 @@
+Galaxy wrapper for running the X!Tandem search engine and converting results to pepXML
+
+Requirements:
+This package uses protk and the trans_proteomic_pipeline. These must be installed separately. 
+
+For instructions please see: https://github.com/iracooke/protk/#galaxy-integration
\ No newline at end of file
--- a/README.md	Mon Jun 16 05:47:38 2014 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,6 +0,0 @@
-## What is it?
-Galaxy tool definition file and wrapper scripts for the [X!Tandem search engine](http://www.thegpm.org/tandem/index.html).
-
-## This tool requires that the protk rubygem and X!Tandem itself are installed.
-
-
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/repository_dependencies.xml	Mon Jun 16 05:47:55 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/tandem.xml	Mon Jun 16 05:47:55 2014 -0400
@@ -0,0 +1,204 @@
+<tool id="proteomics_search_tandem_1" name="X!Tandem MSMS Search" version="1.0.2">
+
+   <requirements>
+	    <requirement type="package" version="1.3.0">protk</requirement>
+   </requirements>
+
+	<description>Run an X!Tandem Search</description>
+
+	<command>
+		#if $database.source_select=="built_in":
+		tandem_search.rb -d $database.dbkey 
+		#else 
+		tandem_search.rb -d $database.fasta_file
+		#end if
+
+		#if $tandem_params.source_select=="built_in":
+		-T $tandem_params.paramskey 
+		#else 
+		-T $tandem_params.params_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 
+
+		$allow_multi_isotope_search 
+
+		$acetyl_protein_nterm
+
+		$cleavage_semi
+
+		$keep_spectra
+
+		--threads $threads
+		
+	</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>
+		
+		<conditional name="tandem_params">
+			<param name="source_select" type="select" label="Baseline Parameters">
+				<option value="built_in" selected="true">Built-In</option>
+				<option value="input_ref">Custom parameter file</option>
+			</param>
+			<when value="built_in">
+				<param name="paramskey" type="select" format="text" >
+					<label>Paramset</label>
+				    <option value="isb_native">ISB Native</option>		
+					<option value="isb_kscore">ISB K-Score</option>
+				</param>
+			</when>
+			<when value="input_ref">
+				<param name="params_file" type="data" format="xml" label="Custom X!Tandem Parameters" />
+			</when>
+		</conditional>
+
+		<param name="input_file" type="data" format="mzml,mgf" multiple="false" label="MSMS File" help="A 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="tandem_mods.loc">
+				<column name="name" index="0" />
+				<column name="value" index="2" />
+			</options>
+		</param>
+
+		<repeat name="custom_variable_mods" title="Custom Variable Modifications" help="You can specify a modification when present in a motif. For instance, 0.998@N!{P}[ST] is a deamidation modification on N only if it is present in an N[any but P][S or T] motif (N-glycosite).">
+			<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="tandem_mods.loc">
+				<column name="name" index="0" />
+				<column name="value" index="2" />
+			</options>
+		</param>
+
+		<repeat name="custom_fix_mods" title="Custom Fixed Modifications" help="You can specify a modification when present in a motif. For instance, 0.998@N!{P}[ST] is a deamidation modification on N only if it is present in an N[any but P][S or T] motif (N-glycosite).">
+			<param name="custom_mod" type="text">
+			</param>
+		</repeat>
+
+		<param name="acetyl_protein_nterm" type="boolean" label="Allow N-terminal protein acetylation as a variable modification" truevalue="-y" falsevalue="" />		
+		
+
+		<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="--cleavage-semi" falsevalue=""/>
+
+		<param name="keep_spectra" type="boolean" label="Keep Spectra" help="Include spectra in the output" truevalue="--output-spectra" falsevalue=""/>
+
+		<param name="threads" type="integer" value="1" label="Threads" help="Number of threads to use for search. Maximum is 16"/>
+		
+		<param name="enzyme" type="select" format="text">
+		    <label>Enzyme</label>
+			<option value="[R]|{P}">argc - [R]|{P}</option>
+			<option value="[X]|[D]">aspn - [X]|[D]</option>
+			<option value="[FLMWY]|{P}">chymotrypsin - [FLMWY]|{P}</option>
+			<option value="[R]|[X]">clostripain - [R]|[X]</option>
+			<option value="[M]|{P}">cnbr - [M]|{P}</option>
+			<option value="[AGILV]|{P}">elastase - [AGILV]|{P}</option>
+			<option value="[D]|{P}">formicacid - [D]|{P}</option>
+			<option value="[DE]|{P}">gluc - [DE]|{P}</option>
+			<option value="[E]|{P}">gluc_bicarb - [E]|{P}</option>
+			<option value="[W]|[X]">iodosobenzoate - [W]|[X]</option>
+			<option value="[K]|{P}">lysc - [K]|{P}</option>
+			<option value="[K]|[X]">lysc-p - [K]|[X]</option>
+			<option value="[X]|[K]">lysn - [X]|[K]</option>
+			<option value="[X]|[AKRS]">lysn_promisc - [X]|[AKRS]</option>
+			<option value="[X]|[X]">nonspecific - [X]|[X]</option>
+			<option value="[FL]|[X]">pepsina - [FL]|[X]</option>
+			<option value="[P]|[X]">protein_endopeptidase - [P]|[X]</option>
+			<option value="[E]|[X]">staph_protease - [E]|[X]</option>
+			<option value="[FMWY]|{P},[KR]|{P},[X]|[D]">tca - [FMWY]|{P},[KR]|{P},[X]|[D]</option>
+			<option value="[KR]|{P}" selected="true">trypsin - [KR]|{P}</option>
+			<option value="[FKLMRWY]|{P}">trypsin/chymotrypsin - [FKLMRWY]|{P}</option>
+			<option value="[KR]|{P},[M]|{P}">trypsin/cnbr - [KR]|{P},[M]|{P}</option>
+			<option value="[DEKR]|{P}">trypsin_gluc - [DEKR]|{P}</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="allow_multi_isotope_search" type="boolean" label="Allow multi-isotope search" help="This allows peptide candidates in windows around -1 Da and -2 Da from the acquired mass to be considered. Only applicable when the minus/plus window above is set to less than 0.5 Da. Good for accurate-mass instruments for which the reported precursor mass is not corrected to the monoisotopic mass." truevalue="" falsevalue=""/>
+
+	</inputs>
+
+
+	<outputs>
+		<data format="tandem" name="output" metadata_source="input_file" label="X!Tandem_vs_${database.dbkey if $database.has_key('dbkey') else $database.fasta_file.display_name}.${input_file.display_name}.${input_file.display_name}.tandem"/>
+	</outputs>
+
+
+  <help>
+
+**What it does**
+
+Runs an MS/MS database search using the X!Tandem search engine. Output is in the form of a pepXML file containing identified peptides along with their raw search scores.
+
+----
+
+**References**
+
+Please see http://www.thegpm.org/GPM/references.html for details of references describing the X!Tandem search engine.
+
+  </help>
+
+</tool>
--- a/tandem_to_pepxml.xml	Mon Jun 16 05:47:38 2014 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,25 +0,0 @@
-<tool id="tandem_to_pepxml_1" name="Tandem to pepXML" version="1.0.1">
-	<requirements>
-	    <requirement type="package" version="1.3.0">protk</requirement>
-	    <requirement type="package" version="4.6.3">trans_proteomic_pipeline</requirement>
-   </requirements>
-
-  <description>Converts a tandem result file to pepXML</description>
-
-<command>
-	tandem_to_pepxml.rb $input_file -o $output 
-</command>
-
-<inputs>
-	<param name="input_file" type="data" format="tandem" multiple="false" label="Input File" help="X!Tandem results file"/>
-</inputs>
-
-<outputs>
-	<data format="raw_pepxml" metadata_source="input_file" name="output" label="${input_file.display_name}.pepXML" />
-</outputs>
-
-<help>
-	Convert X!Tandem results to pepXML
-</help>
-
-</tool>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/pepxml_databases.loc.sample	Mon Jun 16 05:47:55 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_
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/tandem_mods.loc.sample	Mon Jun 16 05:47:55 2014 -0400
@@ -0,0 +1,6 @@
+#This file lists the names of inbuilt chemical modifications accepted by X!Tandem
+#
+#
+Carbamidomethyl C	carbamidomethyl_c_	57.021464@C	carbamidomethyl_c_
+Glycocapture-N	glycocapture_n_	0.998@N!{P}[ST]	glycocapture_n_
+Oxidation M	oxidation_m_	15.994915@M	oxidation_m_
\ No newline at end of file