changeset 0:a929e27eb203 draft

Uploaded

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/display_applications/proteomics/PepXml.xml	Thu Jun 21 22:30:48 2012 -0400
@@ -0,0 +1,18 @@
+<display id="proteomics_pepxml" version="1.0.0" name="view pepXML in">
+	<dynamic_links from_file="tool-data/protk_display_site.txt" skip_startswith="#" id="0" name="0">
+        <!-- Define parameters by column from file -->
+        <dynamic_param name="site_id" value="0"/>
+        <dynamic_param name="site_url" value="1"/>
+        <!-- We define url and params as normal, but values defined in dynamic_param are available by specified name -->
+        <url target_frame="galaxy_main">${site_url}/init_local?file=${encoded_filename.qp}&amp;type=pepxml</url>
+        <param type="data" name="pep_file" viewable="False" format="pepXML"/>
+        <param type="data" dataset="pep_file" name="pepxml_file" format="pepXML" viewable="False" />
+        <param type="template" name="encoded_filename" strip="True" >
+            #import binascii
+            ${binascii.hexlify( $pepxml_file.file_name )}
+        </param>
+        <param type="template" name="galaxy_url" strip="True" >
+                ${BASE_URL.split(":")[1][2:]}
+        </param>
+    </dynamic_links>
+</display>

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/display_applications/proteomics/ProtXml.xml	Thu Jun 21 22:30:48 2012 -0400
@@ -0,0 +1,18 @@
+<display id="proteomics_protxml" version="1.0.0" name="view protXML in">
+	<dynamic_links from_file="tool-data/protk_display_site.txt" skip_startswith="#" id="0" name="0">
+        <!-- Define parameters by column from file -->
+        <dynamic_param name="site_id" value="0"/>
+        <dynamic_param name="site_url" value="1"/>
+        <!-- We define url and params as normal, but values defined in dynamic_param are available by specified name -->
+        <url target_frame="galaxy_main">${site_url}/init_local?file=${encoded_filename.qp}&amp;type=protxml</url>
+        <param type="data" name="prot_file" viewable="False" format="protXML"/>
+        <param type="data" dataset="prot_file" name="protxml_file" format="protXML" viewable="False" />
+        <param type="template" name="encoded_filename" strip="True" >
+            #import binascii
+            ${binascii.hexlify( $protxml_file.file_name )}
+        </param>
+        <param type="template" name="galaxy_url" strip="True" >
+                ${BASE_URL.split(":")[1][2:]}
+        </param>
+    </dynamic_links>
+</display>
\ No newline at end of file

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/display_applications/proteomics/mzML.xml	Thu Jun 21 22:30:48 2012 -0400
@@ -0,0 +1,18 @@
+<display id="proteomics_mzml" version="1.0.2" name="view mzML data">
+	<dynamic_links from_file="tool-data/protk_display_site.txt" skip_startswith="#" id="0" name="0">
+        <!-- Define parameters by column from file -->
+        <dynamic_param name="site_id" value="0"/>
+        <dynamic_param name="site_url" value="1"/>
+        <!-- We define url and params as normal, but values defined in dynamic_param are available by specified name -->
+        <url target_frame="galaxy_main">${site_url}/init_local?file=${encoded_filename.qp}&amp;type=mzml</url>
+        <param type="data" name="raw_file" viewable="False" format="mzML"/>
+        <param type="data" dataset="raw_file" name="mzml_file" format="mzML" viewable="False" />
+        <param type="template" name="encoded_filename" strip="True" >
+            #import binascii
+            ${binascii.hexlify( $mzml_file.file_name )}
+        </param>
+        <param type="template" name="galaxy_url" strip="True" >
+                ${BASE_URL.split(":")[1][2:]}
+        </param>
+    </dynamic_links>
+</display>
\ No newline at end of file

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/interprophet.xml	Thu Jun 21 22:30:48 2012 -0400
@@ -0,0 +1,43 @@
+<tool id="proteomics_search_interprophet_1" name="InterProphet" version="1.0.0">
+	<requirements><requirement type="package">protk</requirement></requirements>
+  <description>Combine Peptide Prophet results from multiple search engines</description>
+
+  <command interpreter="ruby">
+
+	interprophet_wrapper.rb $output $use_nss $use_nrs $use_nse $use_nsi $use_nsm --minprob $minprob
+
+
+	## Inputs.
+	${first_input}
+	#for $input_file in $input_files:
+	${input_file.additional_input}
+	#end for  	
+
+  </command>
+
+  <inputs>
+
+	<param name="first_input" type="data" format="peptideprophet_pepxml" label="Peptide Prophet Results" help="These files will typically be outputs from search tools that have subsequently been run through peptide prophet"/> 	
+		
+	<repeat name="input_files" title="Additional PepXML Input Files">
+		<param format="peptideprophet_pepxml" name="additional_input" type="data" label="PepXML produced by Peptide Prophet" help=""/>
+	</repeat>
+	
+	<param name="use_nss" checked="true" type="boolean" label="Include NSS in Model" help="Include NSS (Number of Sibling Searches) in Statistical Model" truevalue="blank" falsevalue="--nonss"/>
+	<param name="use_nrs" checked="true" type="boolean" label="Include NRS in Model" help="Include NRS (Number of Replicate Spectra) in Statistical Model" truevalue="blank" falsevalue="--nonrs"/>
+	<param name="use_nse" checked="true" type="boolean" label="Include NSE in Model" help="Include NSE (Number of Sibling Experiments) in Statistical Model" truevalue="blank" falsevalue="--nonse"/>
+	<param name="use_nsi" checked="true" type="boolean" label="Include NSI in Model" help="Include NSI (Number of Sibling Ions) in Statistical Model" truevalue="blank" falsevalue="--nonsi"/>
+	<param name="use_nsm" checked="true" type="boolean" label="Include NSM in Model" help="Include NSM (Number of Sibling Modifications) in Statistical Model" truevalue="blank" falsevalue="--nonsm"/>
+	
+	<param name="minprob" type="text" label="Minimum threshod probability for reporting results"/>
+		
+  </inputs>
+  <outputs>
+    <data format="interprophet_pepxml" name="output" metadata_source="first_input" label="interprophet.${first_input.display_name}" from_work_dir="interprophet_output.pep.xml"/>
+  </outputs>
+
+  <help>
+	Run InterProphet
+  </help>
+
+</tool>

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/interprophet_wrapper.rb	Thu Jun 21 22:30:48 2012 -0400
@@ -0,0 +1,57 @@
+require 'pathname'
+
+$VERBOSE=nil
+
+# Hard-Coded argument order and number of arguments
+#
+actual_output_path_string=ARGV[0]
+use_nss=ARGV[1]
+use_nrs=ARGV[2]
+use_nse=ARGV[3]
+use_nsi=ARGV[4]
+use_nsm=ARGV[5]
+minprob=ARGV[6]
+minprob_val=ARGV[7]
+
+wd= Dir.pwd
+original_input_files=ARGV.drop(7)
+# End hard coded args #
+
+cmd=""
+
+output_substitution_cmds=""
+
+input_files=original_input_files.collect do |input|
+
+  # We append ".pep.xml" to the input file name because interprophet can't handle anything else
+  # In order for this to work properly we need to create a symbolic link our working directory
+  #
+  original_input_path=Pathname.new("#{input}")
+  actual_input_path_string="#{wd}/#{original_input_path.basename}.pep.xml"
+
+  cmd << "ln -s #{input} #{actual_input_path_string};"
+  output_substitution_cmds << "ruby -pi -e \"gsub('#{actual_input_path_string}', '#{input}.pep.xml')\" interprophet_output.pep.xml;"
+  actual_input_path_string
+end
+
+interprophet_path=%x[which interprophet.rb]
+cmd << interprophet_path.chomp
+
+cmd << " --no-nss" unless use_nss=="blank"
+cmd << " --no-nrs" unless use_nrs=="blank"
+cmd << " --no-nse" unless use_nse=="blank"
+cmd << " --no-nsi" unless use_nsi=="blank"
+cmd << " --no-nsm" unless use_nsm=="blank"
+
+
+input_files.each { |input|
+  cmd << " #{input}"
+}
+
+
+cmd << " -o interprophet_output.pep.xml -r"
+
+cmd << ";#{output_substitution_cmds}"
+
+%x[#{cmd}]
+

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/lib/galaxy/datatypes/proteomics.py	Thu Jun 21 22:30:48 2012 -0400
@@ -0,0 +1,181 @@
+"""
+Proteomics format classes
+"""
+import logging
+import re
+from galaxy.datatypes.data import *
+from galaxy.datatypes.xml import *
+from galaxy.datatypes.sniff import *
+from galaxy.datatypes.binary import *
+
+log = logging.getLogger(__name__)
+
+
+class Xls( Binary ):
+    """Class describing a binary excel spreadsheet file"""
+    file_ext = "xls"
+
+    def set_peek( self, dataset, is_multi_byte=False ):
+        if not dataset.dataset.purged:
+            dataset.peek  = "Excel Spreadsheet file"
+            dataset.blurb = data.nice_size( dataset.get_size() )
+        else:
+            dataset.peek = 'file does not exist'
+            dataset.blurb = 'file purged from disk'
+    def display_peek( self, dataset ):
+        try:
+            return dataset.peek
+        except:
+            return "Binary xls file (%s)" % ( data.nice_size( dataset.get_size() ) )
+
+class PepXml(GenericXml):
+    """pepXML data"""
+    file_ext = "pepxml"
+
+    def set_peek( self, dataset, is_multi_byte=False ):
+        """Set the peek and blurb text"""
+        if not dataset.dataset.purged:
+            dataset.peek = data.get_file_peek( dataset.file_name, is_multi_byte=is_multi_byte )
+            dataset.blurb = 'pepXML data'
+        else:
+            dataset.peek = 'file does not exist'
+            dataset.blurb = 'file purged from disk'
+    def sniff( self, filename ):
+        """
+        Determines whether the file is pepXML
+        """
+        #TODO - Use a context manager on Python 2.5+ to close handle
+        handle = open(filename)
+        xmlns_re = re.compile(".*pepXML\"")
+        for i in range(3):
+            line = handle.readline()
+            if xmlns_re.match(line.strip()):
+                handle.close()
+                return True
+
+        handle.close()
+        return False
+
+class MzML( GenericXml ):
+    """mzML data"""
+    file_ext = "mzml"
+    
+    def set_peek( self, dataset, is_multi_byte=False ):
+        """Set the peek and blurb text"""
+        if not dataset.dataset.purged:
+            dataset.peek = data.get_file_peek( dataset.file_name, is_multi_byte=is_multi_byte )
+            dataset.blurb = 'mzML Mass Spectrometry data'
+        else:
+            dataset.peek = 'file does not exist'
+            dataset.blurb = 'file purged from disk'
+
+    def sniff( self, filename ):
+        handle = open(filename)
+        xmlns_re = re.compile("^<mzML")
+        for i in range(3):
+            line = handle.readline()
+            if xmlns_re.match(line.strip()):
+                handle.close()
+                return True
+
+        handle.close()
+        return False
+
+
+class ProtXML( Text ):
+    """protXML data"""
+    file_ext = "protxml"
+
+    def set_peek( self, dataset, is_multi_byte=False ):
+        """Set the peek and blurb text"""
+        if not dataset.dataset.purged:
+            dataset.peek = data.get_file_peek( dataset.file_name, is_multi_byte=is_multi_byte )
+            dataset.blurb = 'prot XML Search Results'
+        else:
+            dataset.peek = 'file does not exist'
+            dataset.blurb = 'file purged from disk'
+    def sniff( self, filename ):
+        protxml_header = [ '<?xml version="1.0" encoding="ISO-8859-1"?>',
+        'xmlns="http://regis-web.systemsbiology.net/protXML"' ]
+
+        for i, line in enumerate( file( filename ) ):
+            if i >= len( pepxml_header ):
+                return True
+            line = line.rstrip( '\n\r' )
+            if protxml_header[ i ] not in line:
+                return False
+
+
+
+class MzXML( Text ):
+    """mzXML data"""
+    file_ext = "mzXML"
+
+    def set_peek( self, dataset, is_multi_byte=False ):
+        """Set the peek and blurb text"""
+        if not dataset.dataset.purged:
+            dataset.peek = data.get_file_peek( dataset.file_name, is_multi_byte=is_multi_byte )
+            dataset.blurb = 'mzXML Mass Spectrometry data'
+        else:
+            dataset.peek = 'file does not exist'
+            dataset.blurb = 'file purged from disk'
+    def sniff( self, filename ):
+        mzxml_header = [ '<?xml version="1.0" encoding="ISO-8859-1"?>',
+        '<mzXML xmlns="http://sashimi.sourceforge.net/schema_revision/mzXML_2.1" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://sashimi.sourceforge.net/schema_revision/mzXML_2.1 http://sashimi.sourceforge.net/schema_revision/mzXML_2.1/mzXML_idx_2.1.xsd">' ]
+        for i, line in enumerate( file( filename ) ):
+            if i >= len( mzxml_header ):
+                return True
+            line = line.rstrip( '\n\r' )
+            if line != mzxml_header[ i ]:
+                return False        
+ 
+class Mgf( Text ):
+    """Mascot Generic Format data"""
+    file_ext = "mgf"
+
+    def set_peek( self, dataset, is_multi_byte=False ):
+        """Set the peek and blurb text"""
+        if not dataset.dataset.purged:
+            dataset.peek = data.get_file_peek( dataset.file_name, is_multi_byte=is_multi_byte )
+            dataset.blurb = 'mgf Mascot Generic Format'
+        else:
+            dataset.peek = 'file does not exist'
+            dataset.blurb = 'file purged from disk'
+
+
+    def sniff( self, filename ):
+        mgf_begin_ions = "BEGIN IONS"
+        max_lines=100
+
+        for i, line in enumerate( file( filename ) ):
+            line = line.rstrip( '\n\r' )
+            if line==mgf_begin_ions:
+                return True
+            if i>max_lines:
+                return False
+            
+                
+class MascotDat( Text ):
+    """Mascot search results """
+    file_ext = "mascotdat"
+
+    def set_peek( self, dataset, is_multi_byte=False ):
+        """Set the peek and blurb text"""
+        if not dataset.dataset.purged:
+            dataset.peek = data.get_file_peek( dataset.file_name, is_multi_byte=is_multi_byte )
+            dataset.blurb = 'mascotdat Mascot Search Results'
+        else:
+            dataset.peek = 'file does not exist'
+            dataset.blurb = 'file purged from disk'
+
+
+    def sniff( self, filename ):
+        mime_version = "MIME-Version: 1.0 (Generated by Mascot version 1.0)"
+        max_lines=10
+
+        for i, line in enumerate( file( filename ) ):
+            line = line.rstrip( '\n\r' )
+            if line==mime_version:
+                return True
+            if i>max_lines:
+                return False

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/make_decoy.xml	Thu Jun 21 22:30:48 2012 -0400
@@ -0,0 +1,26 @@
+<tool id="make_decoy_1" name="Create decoy databases" version="1.0.0">
+	<requirements>
+		<requirement type="package">protk</requirement>
+	</requirements>
+	
+	<description>Creates a random protein database with similar properties to a real protein database</description>
+
+	<command>make_decoy.rb $input_file -o $output -L $length -P $prefix $append</command>
+
+	<inputs>
+
+		<param name="input_file" type="data" format="fasta"  multiple="false" label="Input File" help="Real protein sequences. Take care that these are fasta formatted with no more than 80 amino acids per line. There should be no whitespace in the sequences."/>
+		<param name="prefix" type="text" label="String to prepend to generated protein ID's" size="60" value="decoy_"/>
+		<param name="length" type="text" label="Number of random sequences to generate" help="If 0, a database of equal size to the input database will be generated" size="60" value="0"/>
+		<param name="append" type="boolean" checked="true" label="Append input dataset to the generated sequences" truevalue="-A" falsevalue=""/>
+	</inputs>
+	
+	<outputs>
+		<data format="fasta" name="output" metadata_source="input_file" label="Random sequences from ${input_file.display_name}" from_work_dir="random.fasta"/>
+	</outputs>
+
+	<help>
+		Create random protein sequences
+	</help>
+
+</tool>

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/mzml_to_mgf.xml	Thu Jun 21 22:30:48 2012 -0400
@@ -0,0 +1,25 @@
+<tool id="mzml_to_mgf_1" name="MzML to mgf" version="1.0.0">
+	<requirements>
+		<requirement type="package">protk</requirement>
+	</requirements>
+	
+	<description>Converts an mzML file to mgf suitable for searching by omssa</description>
+
+	<command>file_convert.rb $input_file -o $output $maldi</command>
+
+	<inputs>
+
+		<param name="input_file" type="data" format="mzml"  multiple="false" label="Input File" help="Line Spectra in mzML format"/>
+		<param name="maldi" type="boolean" label="Is the data from a MALDI instrument" truevalue="-l" falsevalue=""/>
+
+	</inputs>
+	
+	<outputs>
+		<data format="mgf" name="output" metadata_source="input_file" label="${input_file.display_name}.mgf" from_work_dir="converted.mgf"/>
+	</outputs>
+
+	<help>
+		Convert line spectra to Mascot Generic Format
+	</help>
+
+</tool>

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/omssa.xml	Thu Jun 21 22:30:48 2012 -0400
@@ -0,0 +1,150 @@
+<tool id="proteomics_search_omssa_1" name="OMSSA MSMS Search" version="1.0.0">
+	<requirements>
+		<requirement type="package">protk</requirement>
+	</requirements>
+	
+	<description>Run an OMSSA MS/MS Search</description>
+		
+	<command>#if $database.source_select=="built_in":
+		omssa_search.rb -d $database.dbkey 
+		#else #omssa_search.rb -d $database.fasta_file
+		#end if
+		
+		--var-mods='
+		$variable_mods
+		'
+		
+		--fix-mods='
+		$fixed_mods
+		'
+		
+		--searched-ions='
+		$searched_ions
+		'
+		
+		$input_file -o $output -r --enzyme=$enzyme --precursor-ion-tol-units=$precursor_tolu -v $missed_cleavages -f $fragment_ion_tol -p $precursor_ion_tol --num-peaks-for-multi-isotope-search $multi_isotope $use_average_mass $respect_precursor_charges --max-hit-expect $max_hit_expect --intensity-cut-off $intensity_cut_off
+
+	</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">Uploaded fasta 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="mgf" multiple="false" label="MSMS File" help="An mgf 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="omssa_mods.loc">
+				<column name="name" index="0" />
+				<column name="value" index="2" />
+			</options>
+		</param>		
+
+		<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="omssa_mods.loc">
+				<column name="name" index="0" />
+				<column name="value" index="2" />
+			</options>
+		</param>
+
+		
+		<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="0">Trypsin</option>
+			<option value="1">Arg-C</option>
+			<option value="2">CNBr</option>
+			<option value="3">Chymotrypsin (FYWL)</option>
+			<option value="4">Formic Acid</option>
+			<option value="5">Lys-C</option>
+			<option value="6">Lys-C, no P rule</option>
+			<option value="7">Pepsin A</option>
+			<option value="8">Trypsin+CNBr</option>
+			<option value="9">Trypsin+Chymotrypsin (FYWLKR)</option>
+			<option value="10">Trypsin, no P rule</option>
+			<option value="11">Whole protein</option>
+			<option value="12">Asp-N</option>
+			<option value="13">Glu-C</option>
+			<option value="14">Asp-N+Glu-C</option>
+			<option value="15">Top-Down</option>
+			<option value="16">Semi-Tryptic</option>
+			<option value="17">No Enzyme</option>
+			<option value="18">Chymotrypsin, no P rule (FYWL)</option>
+			<option value="19">Asp-N (DE)</option>
+			<option value="20">Glu-C (DE)</option>
+			<option value="21">Lys-N (K)</option>
+			<option value="22">Thermolysin, no P rule</option>
+			<option value="23">Semi-Chymotrypsin (FYWL)</option>
+			<option value="24">Semi-Glu-C</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="max_hit_expect" help="Expect values less than this are considered to be hits. Use a large value, eg 10000 when results will be processed downstream with Peptide Prophet" type="float" value="1.0" min="0" max="10000000" label="Maximum Expect value allowed in the hit list"/><!-- -he-->
+		<param name="intensity_cut_off" help="Peak intensity cut-off as a fraction of maximum peak intensity" type="float" value="0.0005" min="0" max="1" label="Peak intensity cut-off"/><!-- -ci-->
+
+
+		<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="use_average_mass" type="boolean" label="Use average precursor masses" help="Match precursor to average mass of the parent ion instead of its monoisotopic mass" truevalue="-a average" falsevalue=""/>
+		<param name="respect_precursor_charges" type="boolean" label="Respect precursor charges" help="Use precursor charge information in input file rather than OMSSA's inferred value" truevalue="--respect-charges" falsevalue=""/>
+		
+		<param name="multi_isotope" type="select" format="text" help="Include this many neighbouring peaks when searching for a match to the precursor mass. Only used when doing monoisotopic search">
+			<label>Multi-isotope search.</label>
+		    <option value="0">0</option>
+			<option value="1">1</option>
+			<option value="2">2</option>
+			<option value="3">3</option>
+			<option value="4">4</option>
+		</param>
+
+		<param name="searched_ions" display="checkboxes" type="select" multiple="true" format="text" label="Ions included in search" help="">
+		    <option selected="true" value="0">a</option>
+			<option selected="true" value="1">b</option>
+			<option value="2">c</option>
+			<option selected="true" value="3">x</option>
+			<option selected="true" value="4">y</option>
+			<option value="5">zdot</option>
+			<option value="10">adot</option>
+			<option value="11">x-CO2</option>
+			<option value="12">adot-CO2</option>
+		</param>
+		
+	</inputs>
+
+	<outputs>
+		<data format="raw_pepxml" name="output" metadata_source="input_file" label="omssa_vs_${database.dbkey if $database.has_key('dbkey') else $database.fasta_file.display_name}.${input_file.display_name}.pepXML"/>
+	</outputs>
+
+	<help>
+		Run an OMSSA Search
+	</help>
+</tool>

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/peptide_prophet.xml	Thu Jun 21 22:30:48 2012 -0400
@@ -0,0 +1,66 @@
+<tool id="proteomics_search_peptide_prophet_1" name="Peptide Prophet" version="1.0.0">
+	<requirements><requirement type="package">protk</requirement></requirements>
+	<description>Calculate Peptide Prophet statistics on search results</description>
+
+	<command interpreter="ruby">peptide_prophet_wrapper.rb ${output} ${input_file}  -r $glyco $useicat $phospho $usepi $usert $accurate_mass $no_ntt $no_nmc $use_gamma $use_only_expect $force_fit $allow_alt_instruments $maldi
+	</command>
+
+	<inputs>
+	
+    <param name="input_file" type="data" format="raw_pepxml" multiple="false" label="Raw Search Results" help="These files will typically be outputs from omssa or xtandem search tools"/>
+
+	<param name="glyco" type="boolean" label="Expect true positives to have a glycocapture motif" truevalue="--glyco" falsevalue=""/>
+	<param name="useicat" type="boolean" label="Use icat information" truevalue="--useicat" falsevalue="--no-useicat"/>
+	<param name="phospho" type="boolean" label="Use phospho information" truevalue="--phospho" falsevalue=""/>
+	<param name="usepi" type="boolean" label="Use pI information" truevalue="--usepi" falsevalue=""/>
+	<param name="usert" type="boolean" label="Use hydrophobicity / RT information" truevalue="--usert" falsevalue=""/>
+	<param name="accurate_mass" type="boolean" label="Use accurate mass binning" truevalue="--accurate-mass" falsevalue=""/>
+	<param name="no_ntt" type="boolean" label="Don't use NTT model" truevalue="--no-ntt" falsevalue=""/>
+	<param name="no_nmc" type="boolean" label="Don't use NMC model" truevalue="--no-nmc" falsevalue=""/>
+	<param name="use_gamma" type="boolean" label="Use Gamma distribution to model the negatives" help="Applies only to X!Tandem results" truevalue="--usegamma" falsevalue=""/>
+	<param name="use_only_expect" type="boolean" label="Only use Expect Score as the discriminant" help="Applies only to X!Tandem results. 
+        Helpful for data with homologous top hits e.g. phospho or glyco" truevalue="--use-only-expect" falsevalue=""/>
+	<param name="force_fit" type="boolean" label="Force fitting" help="Bypasses automatic mixture model checks and forces fitting of a mixture model" truevalue="--force-fit" falsevalue=""/>
+	<param name="allow_alt_instruments" type="boolean" label="Allow multiple instrument types" help="Warning instead of exit with error if instrument types between runs is different" truevalue="--allow-alt-instruments" falsevalue=""/>
+	<param name="maldi" type="boolean" label="Maldi data" truevalue="-l" falsevalue=""/>
+	
+	
+  </inputs>
+  <outputs>
+    <data format="peptideprophet_pepxml" name="output" metadata_source="input_file" label="peptide_prophet.${input_file.display_name}.pep.xml" from_work_dir="peptide_prophet_output.pep.xml"/>
+  </outputs>
+
+  <help>
+	Run Peptide Prophet
+  </help>
+
+
+<!--PeptideProphet options [following the 'O']:
+                 i [use icat information in PeptideProphet]
+                 f [do not use icat information in PeptideProphet]
+                 g [use N-glyc motif information in PeptideProphet]
+                 H [use Phospho information in PeptideProphet]
+                 m [maldi data]
+                 I [use pI information in PeptideProphet]
+                 R [use Hydrophobicity / RT information in PeptideProphet]
+                 F [force the fitting of the mixture model, bypass automatic mixture model checks]
+                 A [use accurate mass binning in PeptideProphet]
+                 w [warning instead of exit with error if instrument types between runs is different]
+                 x [exclude all entries with asterisked score values in PeptideProphet]
+                 l [leave alone all entries with asterisked score values in PeptideProphet]
+                 n [use hardcoded default initialization parameters of the distributions]
+                 P [use Non-parametric model, can only be used with decoy option]
+                 N [do not use the NTT model]
+                 M [do not use the NMC model]
+                 G [use Gamma Distribution to model the Negatives (applies only to X!Tandem data)]
+                 E [only use Expect Score as the Discriminant(applies only to X!Tandem data, 
+                    helpful for data with homologous top hits e.g. phospho or glyco)]
+                 d [report decoy hits with a computed probability based on the model learned]
+                 p [run ProteinProphet afterwards]
+                 t [do not create png data plot]
+                 u [do not assemble protein groups in ProteinProphet analysis]
+                 s [do not use Occam's Razor in ProteinProphet analysis to 
+                    derive the simplest protein list to explain observed peptides]
+-->
+
+</tool>

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/peptide_prophet_wrapper.rb	Thu Jun 21 22:30:48 2012 -0400
@@ -0,0 +1,38 @@
+require 'pathname'
+
+$VERBOSE=nil
+
+peptide_prophet_path=%x[which peptide_prophet.rb]
+
+actual_output_path_string=ARGV.shift
+
+# Second argument is the original input file name ... we'll change this below
+original_input_file=ARGV[0]
+
+# Before doing anything we append create a link to the input file in our working dir with ".pep.xml" appended to the input 
+# name because peptide prophet can't handle anything else
+
+wd= Dir.pwd
+
+original_input_path=Pathname.new("#{original_input_file}")
+actual_input_path_string="#{wd}/#{original_input_path.basename}.pep.xml"
+full_tmp_output_path_string="#{wd}/peptide_prophet_output.pep.xml"
+
+cmd = "ln -s #{original_input_file} #{actual_input_path_string};"
+
+cmd << peptide_prophet_path.chomp
+
+
+ARGV[0]="#{actual_input_path_string}"
+
+ARGV.each { |a|    
+  cmd << " #{a}" 
+}
+
+cmd << " -o peptide_prophet_output.pep.xml"
+
+# Finally we need to fix up the output file so any references to the temporary working file are changed to refs to the original input file
+cmd << ";ruby -pi -e \"gsub('#{actual_input_path_string}', '#{original_input_file}')\" peptide_prophet_output.pep.xml"
+cmd << ";ruby -pi -e \"gsub('#{full_tmp_output_path_string}', '#{actual_output_path_string}')\" peptide_prophet_output.pep.xml"
+
+%x[#{cmd}]

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/pepxml_to_table.xml	Thu Jun 21 22:30:48 2012 -0400
@@ -0,0 +1,23 @@
+<tool id="pepxml_to_table_1" name="PepXML to Table" version="1.0.0">
+	<requirements><requirement type="package">protk</requirement></requirements>
+  <description>Converts a pepXML file to a tab delimited text file</description>
+
+
+<!-- Note .. the input file is assumed to be the first argument -->
+<command>pepxml_to_table.rb $input_file -o $output</command>
+
+
+<inputs>
+
+	<param name="input_file" type="data" format="pepxml"  multiple="false" label="Input File" help="A pepXML file"/>
+
+</inputs>
+<outputs>
+	<data format="csv" name="output" metadata_source="input_file" label="${input_file.display_name}.csv" />
+</outputs>
+
+<help>
+	Convert a pepXML file to Tab delimited text
+</help>
+
+</tool>

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/protein_prophet.xml	Thu Jun 21 22:30:48 2012 -0400
@@ -0,0 +1,54 @@
+<tool id="proteomics_search_protein_prophet_1" name="Protein Prophet" version="1.0.0">
+	<requirements><requirement type="package">protk</requirement></requirements>
+  <description>Calculate Protein Prophet statistics on search results</description>
+
+
+<!-- Note .. the input file is assumed to be the first argument -->
+  <command interpreter="ruby">protein_prophet_wrapper.rb $output $input_file -r $iproph $nooccam $groupwts $normprotlen $logprobs $confem $allpeps $unmapped $instances $delude --minprob=$minprob --minindep=$minindep </command>
+  <inputs>
+	
+    <param name="input_file" type="data" format="pepxml" multiple="false" label="Peptide Prophet Results" help="These files will typically be outputs from peptide prophet or interprophet"/>
+
+
+	<param name="iproph" selected="true" type="boolean" label="Inputs are from iProphet" truevalue="--iprophet-input" falsevalue=""/>
+	<param name="nooccam" type="boolean" label="Don't apply Occam's razor" help="When selected no attempt will be made to derive the simplest protein list explaining observed peptides" truevalue="--no-occam" falsevalue=""/>
+	<param name="groupwts" type="boolean" label="Use group weights" help="Check peptide's total weight (rather than actual weight) in the Protein Group against the threshold" truevalue="--group-wts" falsevalue=""/>
+	<param name="normprotlen" type="boolean" label="Normalize NSP using Protein Length" truevalue="--norm-protlen" falsevalue=""/>
+	<param name="logprobs" type="boolean" label="Use the log of probability in the confidence calculations" truevalue="--log-prob" falsevalue=""/>
+	<param name="confem" type="boolean" label="Use the EM to compute probability given the confidenct" truevalue="--confem" falsevalue=""/>
+	<param name="allpeps" type="boolean" label="Consider all possible peptides in the database in the confidence model" truevalue="--allpeps" falsevalue=""/>
+	<param name="unmapped" type="boolean" label="Report results for unmapped proteins" truevalue="--unmapped" falsevalue=""/>
+	<param name="instances" type="boolean" label="Use Expected Number of Ion Instances to adjust the peptide probabilities prior to NSP adjustment" truevalue="--instances" falsevalue=""/>
+	<param name="delude" type="boolean" label="Do NOT use peptide degeneracy information when assessing proteins" truevalue="--delude" falsevalue=""/>
+
+	<param name="minprob" type="text" label="Minimum peptide prophet probability for peptides to be considered" value="0.05"/>
+	<param name="minindep" type="text" label="Minimum percentage of independent peptides required for a protein" value="0"/>
+	
+  </inputs>
+  <outputs>
+    <data format="protxml" name="output" metadata_source="input_file" label="protein_prophet.${input_file.display_name}.protXML" from_work_dir="protein_prophet_results.prot.xml"/>
+  </outputs>
+
+
+<!--NOPLOT: do not generate plot png file
+		NOOCCAM: non-conservative maximum protein list
+		GROUPWTS: check peptide's total weight in the Protein Group against the threshold (default: check peptide's actual weight against threshold)   
+		NORMPROTLEN: Normalize NSP using Protein Length
+		LOGPROBS: Use the log of the probabilities in the Confidence calculations
+		CONFEM: Use the EM to compute probability given the confidence 
+		ALLPEPS: Consider all possible peptides in the database in the confidence model
+		UNMAPPED: Report results for UNMAPPED proteins
+		INSTANCES: Use Expected Number of Ion Instances to adjust the peptide probabilities prior to NSP adjustment
+		DELUDE: do NOT use peptide degeneracy information when assessing proteins
+		
+		MINPROB: peptideProphet probabilty threshold (default=0.05) 
+		MININDEP: minimum percentage of independent peptides required for a protein (default=0) 
+		
+		
+-->
+
+  <help>
+	Run Peptide Prophet
+  </help>
+
+</tool>

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/protein_prophet_wrapper.rb	Thu Jun 21 22:30:48 2012 -0400
@@ -0,0 +1,37 @@
+require 'pathname'
+
+$VERBOSE=nil
+
+protein_prophet_path=%x[which protein_prophet.rb]
+
+actual_output_path_string=ARGV.shift
+
+# Second argument is the original input file name ... we'll change this below
+original_input_file=ARGV[0]
+
+# Before doing anything we append create a link to the input file in our working dir with ".pep.xml" appended to the input 
+# name because peptide prophet can't handle anything else
+
+wd= Dir.pwd
+
+original_input_path=Pathname.new("#{original_input_file}")
+actual_input_path_string="#{wd}/#{original_input_path.basename}.pep.xml"
+
+cmd = "ln -s #{original_input_file} #{actual_input_path_string};"
+
+cmd << protein_prophet_path.chomp
+
+
+ARGV[0]="#{actual_input_path_string}"
+
+ARGV.each { |a| 
+    
+  cmd << " #{a}" 
+}
+
+cmd << " -o protein_prophet_results.prot.xml"
+
+cmd << ";ruby -pi -e \"gsub('#{actual_input_path_string}', '#{original_input_file}.pep.xml')\" protein_prophet_results.prot.xml"
+
+%x[#{cmd}]
+

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tandem.xml	Thu Jun 21 22:30:48 2012 -0400
@@ -0,0 +1,118 @@
+<tool id="proteomics_search_tandem_1" name="X!Tandem MSMS Search" version="1.0.0">
+	<requirements><requirement type="package">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
+
+		--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 --keep-params-files
+		
+		
+		
+	</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="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="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="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="--strict-monoisotopic-mass"/>
+
+	</inputs>
+
+
+	<outputs>
+		<data format="raw_pepxml" 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}.pepXML"/>
+	</outputs>
+
+
+  <help>
+	Run an X!Tandem Search
+  </help>
+
+</tool>

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/datatypes_conf.xml	Thu Jun 21 22:30:48 2012 -0400
@@ -0,0 +1,37 @@
+<?xml version="1.0"?>
+<datatypes>
+  <datatype_files>
+    <datatype_file name="proteomics.py"/>
+  </datatype_files>		
+  <registration display_path="display_applications">	
+    <datatype extension="pepxml" type="galaxy.datatypes.proteomics:PepXml" mimetype="application/xml" display_in_upload="true">
+      <display file="proteomics/PepXml.xml" />
+    </datatype>
+    <datatype extension="raw_pepxml" type="galaxy.datatypes.proteomics:PepXml" subclass="true">
+      <display file="proteomics/PepXml.xml" />
+    </datatype>
+    <datatype extension="peptideprophet_pepxml" type="galaxy.datatypes.proteomics:PepXml" subclass="true">
+      <display file="proteomics/PepXml.xml" />
+    </datatype>
+    <datatype extension="interprophet_pepxml" type="galaxy.datatypes.proteomics:PepXml" subclass="true">
+      <display file="proteomics/PepXml.xml" />
+    </datatype>
+    <datatype extension="protxml" type="galaxy.datatypes.proteomics:ProtXML" display_in_upload="true" >
+      <display file="proteomics/ProtXml.xml"/>
+    </datatype>
+    <datatype extension="mascotdat" type="galaxy.datatypes.proteomics:MascotDat" display_in_upload="false" />
+    <datatype extension="mzml" type="galaxy.datatypes.proteomics:MzML" mimetype="application/xml" display_in_upload="true">
+      <display file="proteomics/mzML.xml"/>
+    </datatype>
+    <datatype extension="mgf" type="galaxy.datatypes.proteomics:Mgf" display_in_upload="true" />		
+      <datatype extension="xls" type="galaxy.datatypes.proteomics:Xls" display_in_upload="true" />
+  </registration>
+  <sniffers>
+    <sniffer type="galaxy.datatypes.proteomics:MzML"/>        
+    <sniffer type="galaxy.datatypes.proteomics:PepXml"/>
+    <sniffer type="galaxy.datatypes.proteomics:Mgf"/>
+    <sniffer type="galaxy.datatypes.proteomics:ProtXML"/>
+    <sniffer type="galaxy.datatypes.proteomics:MzXML"/>
+    <sniffer type="galaxy.datatypes.proteomics:Xls"/>
+  </sniffers>
+</datatypes>

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/mascot_databases.loc.sample	Thu Jun 21 22:30:48 2012 -0400
@@ -0,0 +1,13 @@
+#This file lists the names of protein databases installed on Mascot
+#
+#In order to use interprophet to combine results from different search engines
+#it is important that all searches are performed on the same database
+#you should therefore ensure that each database installed on mascot has an equivalent
+#database installed in the Protk databases directory (databases used by omssa and x!tandem)
+#the mascot_to_pepxml tool will ask for this database when performing the conversion.
+#
+# Entries should follow the be structured as follows
+# Display_name dbkey dbNameOnMascot dbkey
+#
+Swissprot	spall_	SPAll	spall_
+Swissprot Human	sphuman_	SPHuman	sphuman_
\ No newline at end of file

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/mascot_mods.loc.sample	Thu Jun 21 22:30:48 2012 -0400
@@ -0,0 +1,77 @@
+#This file lists the names of chemical modifications acceptable for proteomics search engines
+#
+#
+Acetyl (K)	acetyl_k_	Acetyl (K)	acetyl_k_
+Acetyl (N-term)	acetyl_n-term_	Acetyl (N-term)	acetyl_n-term_
+Acetyl (Protein N-term)	acetyl_proteinn-term_	Acetyl (Protein N-term)	acetyl_proteinn-term_
+Amidated (C-term)	amidated_c-term_	Amidated (C-term)	amidated_c-term_
+Amidated (Protein C-term)	amidated_proteinc-term_	Amidated (Protein C-term)	amidated_proteinc-term_
+Ammonia-loss (N-term C)	ammonia-loss_n-termc_	Ammonia-loss (N-term C)	ammonia-loss_n-termc_
+Biotin (K)	biotin_k_	Biotin (K)	biotin_k_
+Biotin (N-term)	biotin_n-term_	Biotin (N-term)	biotin_n-term_
+Carbamidomethyl (C)	carbamidomethyl_c_	Carbamidomethyl (C)	carbamidomethyl_c_
+Carbamyl (K)	carbamyl_k_	Carbamyl (K)	carbamyl_k_
+Carbamyl (N-term)	carbamyl_n-term_	Carbamyl (N-term)	carbamyl_n-term_
+Carboxymethyl (C)	carboxymethyl_c_	Carboxymethyl (C)	carboxymethyl_c_
+Cation:Na (C-term)	cation_na_c-term_	Cation:Na (C-term)	cation_na_c-term_
+Cation:Na (DE)	cation_na_de_	Cation:Na (DE)	cation_na_de_
+Deamidated (NQ)	deamidated_nq_	Deamidated (NQ)	deamidated_nq_
+Deamidated-N (N)	deamidated-n_n_	Deamidated-N (N)	deamidated-n_n_
+Dehydrated (N-term C)	dehydrated_n-termc_	Dehydrated (N-term C)	dehydrated_n-termc_
+Dehydro (C)	dehydro_c_	Dehydro (C)	dehydro_c_
+Dioxidation (M)	dioxidation_m_	Dioxidation (M)	dioxidation_m_
+Ethanolyl (C)	ethanolyl_c_	Ethanolyl (C)	ethanolyl_c_
+ExacTagAmine (K)	exactagamine_k_	ExacTagAmine (K)	exactagamine_k_
+ExacTagThiol (C)	exactagthiol_c_	ExacTagThiol (C)	exactagthiol_c_
+Formyl (N-term)	formyl_n-term_	Formyl (N-term)	formyl_n-term_
+Formyl (Protein N-term)	formyl_proteinn-term_	Formyl (Protein N-term)	formyl_proteinn-term_
+Gln->pyro-Glu (N-term Q)	gln_pyro-glu_n-termq_	Gln->pyro-Glu (N-term Q)	gln_pyro-glu_n-termq_
+Glu->pyro-Glu (N-term E)	glu_pyro-glu_n-terme_	Glu->pyro-Glu (N-term E)	glu_pyro-glu_n-terme_
+Guanidinyl (K)	guanidinyl_k_	Guanidinyl (K)	guanidinyl_k_
+ICAT-C (C)	icat-c_c_	ICAT-C (C)	icat-c_c_
+ICAT-C:13C(9) (C)	icat-c_13c_9__c_	ICAT-C:13C(9) (C)	icat-c_13c_9__c_
+ICPL (K)	icpl_k_	ICPL (K)	icpl_k_
+ICPL (Protein N-term)	icpl_proteinn-term_	ICPL (Protein N-term)	icpl_proteinn-term_
+ICPL:13C(6) (K)	icpl_13c_6__k_	ICPL:13C(6) (K)	icpl_13c_6__k_
+ICPL:13C(6) (Protein N-term)	icpl_13c_6__proteinn-term_	ICPL:13C(6) (Protein N-term)	icpl_13c_6__proteinn-term_
+ICPL:13C(6)2H(4) (K)	icpl_13c_6_2h_4__k_	ICPL:13C(6)2H(4) (K)	icpl_13c_6_2h_4__k_
+ICPL:13C(6)2H(4) (N-term)	icpl_13c_6_2h_4__n-term_	ICPL:13C(6)2H(4) (N-term)	icpl_13c_6_2h_4__n-term_
+ICPL:13C(6)2H(4) (Protein N-term)	icpl_13c_6_2h_4__proteinn-term_	ICPL:13C(6)2H(4) (Protein N-term)	icpl_13c_6_2h_4__proteinn-term_
+ICPL:2H(4) (K)	icpl_2h_4__k_	ICPL:2H(4) (K)	icpl_2h_4__k_
+ICPL:2H(4) (Protein N-term)	icpl_2h_4__proteinn-term_	ICPL:2H(4) (Protein N-term)	icpl_2h_4__proteinn-term_
+iTRAQ4plex (K)	itraq4plex_k_	iTRAQ4plex (K)	itraq4plex_k_
+iTRAQ4plex (N-term)	itraq4plex_n-term_	iTRAQ4plex (N-term)	itraq4plex_n-term_
+iTRAQ4plex (Y)	itraq4plex_y_	iTRAQ4plex (Y)	itraq4plex_y_
+iTRAQ8plex (K)	itraq8plex_k_	iTRAQ8plex (K)	itraq8plex_k_
+iTRAQ8plex (N-term)	itraq8plex_n-term_	iTRAQ8plex (N-term)	itraq8plex_n-term_
+iTRAQ8plex (Y)	itraq8plex_y_	iTRAQ8plex (Y)	itraq8plex_y_
+Label:18O(1) (C-term)	label_18o_1__c-term_	Label:18O(1) (C-term)	label_18o_1__c-term_
+Label:18O(2) (C-term)	label_18o_2__c-term_	Label:18O(2) (C-term)	label_18o_2__c-term_
+Met->Hse (C-term M)	met_hse_c-termm_	Met->Hse (C-term M)	met_hse_c-termm_
+Met->Hsl (C-term M)	met_hsl_c-termm_	Met->Hsl (C-term M)	met_hsl_c-termm_
+Methyl (C-term)	methyl_c-term_	Methyl (C-term)	methyl_c-term_
+Methyl (DE)	methyl_de_	Methyl (DE)	methyl_de_
+Methylthio (C)	methylthio_c_	Methylthio (C)	methylthio_c_
+mTRAQ (K)	mtraq_k_	mTRAQ (K)	mtraq_k_
+mTRAQ (N-term)	mtraq_n-term_	mTRAQ (N-term)	mtraq_n-term_
+mTRAQ (Y)	mtraq_y_	mTRAQ (Y)	mtraq_y_
+mTRAQ:13C(3)15N(1) (K)	mtraq_13c_3_15n_1__k_	mTRAQ:13C(3)15N(1) (K)	mtraq_13c_3_15n_1__k_
+mTRAQ:13C(3)15N(1) (N-term)	mtraq_13c_3_15n_1__n-term_	mTRAQ:13C(3)15N(1) (N-term)	mtraq_13c_3_15n_1__n-term_
+mTRAQ:13C(3)15N(1) (Y)	mtraq_13c_3_15n_1__y_	mTRAQ:13C(3)15N(1) (Y)	mtraq_13c_3_15n_1__y_
+NIPCAM (C)	nipcam_c_	NIPCAM (C)	nipcam_c_
+Oxidation (HW)	oxidation_hw_	Oxidation (HW)	oxidation_hw_
+Oxidation (M)	oxidation_m_	Oxidation (M)	oxidation_m_
+Phospho (ST)	phospho_st_	Phospho (ST)	phospho_st_
+Phospho (Y)	phospho_y_	Phospho (Y)	phospho_y_
+Propionamide (C)	propionamide_c_	Propionamide (C)	propionamide_c_
+Pyridylethyl (C)	pyridylethyl_c_	Pyridylethyl (C)	pyridylethyl_c_
+Pyro-carbamidomethyl (N-term C)	pyro-carbamidomethyl_n-termc_	Pyro-carbamidomethyl (N-term C)	pyro-carbamidomethyl_n-termc_
+Sulfo (S)	sulfo_s_	Sulfo (S)	sulfo_s_
+Sulfo (T)	sulfo_t_	Sulfo (T)	sulfo_t_
+Sulfo (Y)	sulfo_y_	Sulfo (Y)	sulfo_y_
+TMT (K)	tmt_k_	TMT (K)	tmt_k_
+TMT (N-term)	tmt_n-term_	TMT (N-term)	tmt_n-term_
+TMT2plex (K)	tmt2plex_k_	TMT2plex (K)	tmt2plex_k_
+TMT2plex (N-term)	tmt2plex_n-term_	TMT2plex (N-term)	tmt2plex_n-term_
+TMT6plex (K)	tmt6plex_k_	TMT6plex (K)	tmt6plex_k_
+TMT6plex (N-term)	tmt6plex_n-term_	TMT6plex (N-term)	tmt6plex_n-term_

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/omssa_mods.loc.sample	Thu Jun 21 22:30:48 2012 -0400
@@ -0,0 +1,181 @@
+#This file lists the names of chemical modifications accepted by OMMSA
+#
+#
+2-amino-3-oxo-butanoic acid T	2-amino-3-oxo-butanoicacidt_	23	2-amino-3-oxo-butanoicacidt_
+Asparagine HexNAc	asparaginehexnac_	182	asparaginehexnac_
+Asparagine dHexHexNAc	asparaginedhexhexnac_	183	asparaginedhexhexnac_
+CAMthiopropanoyl K	camthiopropanoylk_	131	camthiopropanoylk_
+CHD2-di-methylation of K	chd2-di-methylationofk_	189	chd2-di-methylationofk_
+CHD2-di-methylation of peptide n-term	chd2-di-methylationofpeptiden-term_	190	chd2-di-methylationofpeptiden-term_
+ICAT heavy	icatheavy_	130	icatheavy_
+ICAT light	icatlight_	129	icatlight_
+M cleavage from protein n-term	mcleavagefromproteinn-term_	9	mcleavagefromproteinn-term_
+MMTS on C	mmtsonc_	179	mmtsonc_
+Maleimide-PEO2-Biotin of C	maleimide-peo2-biotinofc_	191	maleimide-peo2-biotinofc_
+NEM C	nemc_	83	nemc_
+NIPCAM	nipcam_	84	nipcam_
+O18 on peptide n-term	o18onpeptiden-term_	87	o18onpeptiden-term_
+PNGasF in O18 water	pngasfino18water_	139	pngasfino18water_
+SeMet	semet_	113	semet_
+Serine HexNAc	serinehexnac_	184	serinehexnac_
+TMT 6-plex on K	tmt6-plexonk_	198	tmt6-plexonk_
+TMT 6-plex on n-term peptide	tmt6-plexonn-termpeptide_	199	tmt6-plexonn-termpeptide_
+Threonine HexNAc	threoninehexnac_	185	threoninehexnac_
+Uniblue A on K	uniblueaonk_	195	uniblueaonk_
+acetylation of K	acetylationofk_	24	acetylationofk_
+acetylation of protein n-term	acetylationofproteinn-term_	10	acetylationofproteinn-term_
+amidation of peptide c-term	amidationofpeptidec-term_	25	amidationofpeptidec-term_
+arginine to ornithine	argininetoornithine_	163	argininetoornithine_
+beta elimination of S	betaeliminationofs_	140	betaeliminationofs_
+beta elimination of T	betaeliminationoft_	141	betaeliminationoft_
+beta methythiolation of D	betamethythiolationofd_	13	betamethythiolationofd_
+beta-carboxylation of D	beta-carboxylationofd_	47	beta-carboxylationofd_
+beta-methylthiolation of D (duplicate of 13)	beta-methylthiolationofd_duplicateof13__	26	beta-methylthiolationofd_duplicateof13__
+carbamidomethyl C	carbamidomethylc_	3	carbamidomethylc_
+carbamylation of K	carbamylationofk_	31	carbamylationofk_
+carbamylation of n-term peptide	carbamylationofn-termpeptide_	32	carbamylationofn-termpeptide_
+carboxyamidomethylation of D	carboxyamidomethylationofd_	29	carboxyamidomethylationofd_
+carboxyamidomethylation of E	carboxyamidomethylationofe_	30	carboxyamidomethylationofe_
+carboxyamidomethylation of H	carboxyamidomethylationofh_	28	carboxyamidomethylationofh_
+carboxyamidomethylation of K	carboxyamidomethylationofk_	27	carboxyamidomethylationofk_
+carboxykynurenin of W	carboxykynureninofw_	165	carboxykynureninofw_
+carboxymethyl C	carboxymethylc_	2	carboxymethylc_
+carboxymethylated selenocysteine	carboxymethylatedselenocysteine_	207	carboxymethylatedselenocysteine_
+citrullination of R	citrullinationofr_	33	citrullinationofr_
+deamidation of N	deamidationofn_	196	deamidationofn_
+deamidation of N and Q	deamidationofnandq_	4	deamidationofnandq_
+dehydro of S and T	dehydroofsandt_	164	dehydroofsandt_
+di-O18 on peptide n-term	di-o18onpeptiden-term_	88	di-o18onpeptiden-term_
+di-iodination of Y	di-iodinationofy_	35	di-iodinationofy_
+di-methylation of K	di-methylationofk_	36	di-methylationofk_
+di-methylation of R	di-methylationofr_	37	di-methylationofr_
+di-methylation of peptide n-term	di-methylationofpeptiden-term_	38	di-methylationofpeptiden-term_
+farnesylation of C	farnesylationofc_	42	farnesylationofc_
+fluorophenylalanine	fluorophenylalanine_	46	fluorophenylalanine_
+formylation of K	formylationofk_	43	formylationofk_
+formylation of peptide n-term	formylationofpeptiden-term_	44	formylationofpeptiden-term_
+formylation of protein n-term	formylationofproteinn-term_	82	formylationofproteinn-term_
+gamma-carboxylation of E	gamma-carboxylationofe_	48	gamma-carboxylationofe_
+gammathiopropionylation of K	gammathiopropionylationofk_	40	gammathiopropionylationofk_
+gammathiopropionylation of peptide n-term	gammathiopropionylationofpeptiden-term_	41	gammathiopropionylationofpeptiden-term_
+geranyl-geranyl	geranyl-geranyl_	49	geranyl-geranyl_
+glucuronylation of protein n-term	glucuronylationofproteinn-term_	50	glucuronylationofproteinn-term_
+glutathione disulfide	glutathionedisulfide_	51	glutathionedisulfide_
+guanidination of K	guanidinationofk_	53	guanidinationofk_
+heavy arginine-13C6	heavyarginine-13c6_	136	heavyarginine-13c6_
+heavy arginine-13C6-15N4	heavyarginine-13c6-15n4_	137	heavyarginine-13c6-15n4_
+heavy lysine - 13C6 15N2	heavylysine-13c615n2_	181	heavylysine-13c615n2_
+heavy lysine - 2H4	heavylysine-2h4_	180	heavylysine-2h4_
+heavy lysine-13C6	heavylysine-13c6_	138	heavylysine-13c6_
+homoserine	homoserine_	56	homoserine_
+homoserine lactone	homoserinelactone_	57	homoserinelactone_
+hydroxylation of  Y	hydroxylationofy_	64	hydroxylationofy_
+hydroxylation of D	hydroxylationofd_	59	hydroxylationofd_
+hydroxylation of F	hydroxylationoff_	63	hydroxylationoff_
+hydroxylation of K	hydroxylationofk_	60	hydroxylationofk_
+hydroxylation of N	hydroxylationofn_	61	hydroxylationofn_
+hydroxylation of P	hydroxylationofp_	62	hydroxylationofp_
+iTRAQ114 on K	itraq114onk_	168	itraq114onk_
+iTRAQ114 on Y	itraq114ony_	169	itraq114ony_
+iTRAQ114 on nterm	itraq114onnterm_	167	itraq114onnterm_
+iTRAQ115 on K	itraq115onk_	171	itraq115onk_
+iTRAQ115 on Y	itraq115ony_	172	itraq115ony_
+iTRAQ115 on nterm	itraq115onnterm_	170	itraq115onnterm_
+iTRAQ116 on K	itraq116onk_	174	itraq116onk_
+iTRAQ116 on Y	itraq116ony_	175	itraq116ony_
+iTRAQ116 on nterm	itraq116onnterm_	173	itraq116onnterm_
+iTRAQ117 on K	itraq117onk_	177	itraq117onk_
+iTRAQ117 on Y	itraq117ony_	178	itraq117ony_
+iTRAQ117 on nterm	itraq117onnterm_	176	itraq117onnterm_
+iTRAQ8plex	itraq8plex_	204	itraq8plex_
+iTRAQ8plex	itraq8plex_	205	itraq8plex_
+iTRAQ8plex	itraq8plex_	203	itraq8plex_
+iTRAQ8plex	itraq8plex_	201	itraq8plex_
+iTRAQ8plex	itraq8plex_	202	itraq8plex_
+iTRAQ8plex	itraq8plex_	200	itraq8plex_
+iodination of Y	iodinationofy_	65	iodinationofy_
+lipoyl K	lipoylk_	67	lipoylk_
+methyl C	methylc_	73	methylc_
+methyl H	methylh_	74	methylh_
+methyl N	methyln_	75	methyln_
+methyl R	methylr_	77	methylr_
+methyl ester of D	methylesterofd_	69	methylesterofd_
+methyl ester of E (duplicate of 17)	methylesterofe_duplicateof17__	70	methylesterofe_duplicateof17__
+methyl ester of S	methylesterofs_	71	methylesterofs_
+methyl ester of Y	methylesterofy_	72	methylesterofy_
+methyl ester of peptide c-term (duplicate of 18)	methylesterofpeptidec-term_duplicateof18__	68	methylesterofpeptidec-term_duplicateof18__
+methylation of D	methylationofd_	16	methylationofd_
+methylation of E	methylationofe_	17	methylationofe_
+methylation of K	methylationofk_	0	methylationofk_
+methylation of Q	methylationofq_	14	methylationofq_
+methylation of peptide c-term	methylationofpeptidec-term_	18	methylationofpeptidec-term_
+methylation of peptide n-term	methylationofpeptiden-term_	76	methylationofpeptiden-term_
+methylation of protein n-term	methylationofproteinn-term_	11	methylationofproteinn-term_
+myristoleylation of G	myristoleylationofg_	78	myristoleylationofg_
+myristoyl-4H of G	myristoyl-4hofg_	79	myristoyl-4hofg_
+myristoylation of K	myristoylationofk_	81	myristoylationofk_
+myristoylation of peptide n-term G	myristoylationofpeptiden-termg_	80	myristoylationofpeptiden-termg_
+n-acyl diglyceride cysteine	n-acyldiglyceridecysteine_	118	n-acyldiglyceridecysteine_
+n-formyl met addition	n-formylmetaddition_	22	n-formylmetaddition_
+oxidation of C	oxidationofc_	193	oxidationofc_
+oxidation of C to cysteic acid	oxidationofctocysteicacid_	34	oxidationofctocysteicacid_
+oxidation of C to sulfinic acid	oxidationofctosulfinicacid_	162	oxidationofctosulfinicacid_
+oxidation of F to dihydroxyphenylalanine	oxidationofftodihydroxyphenylalanine_	39	oxidationofftodihydroxyphenylalanine_
+oxidation of H	oxidationofh_	89	oxidationofh_
+oxidation of H to D	oxidationofhtod_	55	oxidationofhtod_
+oxidation of H to N	oxidationofhton_	54	oxidationofhton_
+oxidation of M	oxidationofm_	1	oxidationofm_
+oxidation of P to pyroglutamic acid	oxidationofptopyroglutamicacid_	111	oxidationofptopyroglutamicacid_
+oxidation of W	oxidationofw_	90	oxidationofw_
+oxidation of W to formylkynurenin	oxidationofwtoformylkynurenin_	45	oxidationofwtoformylkynurenin_
+oxidation of W to hydroxykynurenin	oxidationofwtohydroxykynurenin_	58	oxidationofwtohydroxykynurenin_
+oxidation of W to kynurenin	oxidationofwtokynurenin_	66	oxidationofwtokynurenin_
+oxidation of W to nitro	oxidationofwtonitro_	85	oxidationofwtonitro_
+oxidation of Y (duplicate of 64)	oxidationofy_duplicateof64__	194	oxidationofy_duplicateof64__
+oxidation of Y to nitro	oxidationofytonitro_	86	oxidationofytonitro_
+palmitoleyl of C	palmitoleylofc_	187	palmitoleylofc_
+palmitoleyl of S	palmitoleylofs_	186	palmitoleylofs_
+palmitoleyl of T	palmitoleyloft_	188	palmitoleyloft_
+palmitoylation of C	palmitoylationofc_	92	palmitoylationofc_
+palmitoylation of K	palmitoylationofk_	93	palmitoylationofk_
+palmitoylation of S	palmitoylationofs_	94	palmitoylationofs_
+palmitoylation of T	palmitoylationoft_	95	palmitoylationoft_
+phosphopantetheine S	phosphopantetheines_	91	phosphopantetheines_
+phosphorylation of H	phosphorylationofh_	192	phosphorylationofh_
+phosphorylation of S	phosphorylationofs_	6	phosphorylationofs_
+phosphorylation of S with ETD loss	phosphorylationofswithetdloss_	134	phosphorylationofswithetdloss_
+phosphorylation of S with prompt loss	phosphorylationofswithpromptloss_	96	phosphorylationofswithpromptloss_
+phosphorylation of T	phosphorylationoft_	7	phosphorylationoft_
+phosphorylation of T with ETD loss	phosphorylationoftwithetdloss_	135	phosphorylationoftwithetdloss_
+phosphorylation of T with prompt loss	phosphorylationoftwithpromptloss_	97	phosphorylationoftwithpromptloss_
+phosphorylation of Y	phosphorylationofy_	8	phosphorylationofy_
+phosphorylation with neutral loss on C	phosphorylationwithneutrallossonc_	99	phosphorylationwithneutrallossonc_
+phosphorylation with neutral loss on D	phosphorylationwithneutrallossond_	100	phosphorylationwithneutrallossond_
+phosphorylation with neutral loss on H	phosphorylationwithneutrallossonh_	101	phosphorylationwithneutrallossonh_
+phosphorylation with neutral loss on S	phosphorylationwithneutrallossons_	132	phosphorylationwithneutrallossons_
+phosphorylation with neutral loss on T	phosphorylationwithneutrallossont_	133	phosphorylationwithneutrallossont_
+phosphorylation with prompt loss on Y	phosphorylationwithpromptlossony_	98	phosphorylationwithpromptlossony_
+propionamide C	propionamidec_	5	propionamidec_
+propionyl heavy K	propionylheavyk_	104	propionylheavyk_
+propionyl heavy peptide n-term	propionylheavypeptiden-term_	105	propionylheavypeptiden-term_
+propionyl light K	propionyllightk_	102	propionyllightk_
+propionyl light on peptide n-term	propionyllightonpeptiden-term_	103	propionyllightonpeptiden-term_
+pyridyl K	pyridylk_	106	pyridylk_
+pyridyl peptide n-term	pyridylpeptiden-term_	107	pyridylpeptiden-term_
+pyro-cmC	pyro-cmc_	108	pyro-cmc_
+pyro-glu from n-term E	pyro-glufromn-terme_	109	pyro-glufromn-terme_
+pyro-glu from n-term Q	pyro-glufromn-termq_	110	pyro-glufromn-termq_
+s-pyridylethylation of C	s-pyridylethylationofc_	112	s-pyridylethylationofc_
+selenocysteine	selenocysteine_	206	selenocysteine_
+sulfation of Y	sulfationofy_	114	sulfationofy_
+sulphone of M	sulphoneofm_	115	sulphoneofm_
+sumoylation of K	sumoylationofk_	166	sumoylationofk_
+tri-deuteromethylation of D	tri-deuteromethylationofd_	19	tri-deuteromethylationofd_
+tri-deuteromethylation of E	tri-deuteromethylationofe_	20	tri-deuteromethylationofe_
+tri-deuteromethylation of peptide c-term	tri-deuteromethylationofpeptidec-term_	21	tri-deuteromethylationofpeptidec-term_
+tri-iodination of Y	tri-iodinationofy_	116	tri-iodinationofy_
+tri-methylation of K	tri-methylationofk_	15	tri-methylationofk_
+tri-methylation of R	tri-methylationofr_	117	tri-methylationofr_
+tri-methylation of protein n-term	tri-methylationofproteinn-term_	12	tri-methylationofproteinn-term_
+trideuteration of L (SILAC)	trideuterationofl_silac__	197	trideuterationofl_silac__
+ubiquitinylation residue	ubiquitinylationresidue_	52	ubiquitinylationresidue_

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/pepxml_databases.loc.sample	Thu Jun 21 22:30:48 2012 -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/protk_display_site.txt.sample	Thu Jun 21 22:30:48 2012 -0400
@@ -0,0 +1,3 @@
+#Proteomic Visualization application should be hosted on the same server as galaxy
+#Entries in this file are of the format "site_id" site_url
+Proteomics Visualize	http://127.0.0.1:8500

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/tandem_mods.loc.sample	Thu Jun 21 22:30:48 2012 -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

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/xls_to_table.xml	Thu Jun 21 22:30:48 2012 -0400
@@ -0,0 +1,23 @@
+<tool id="xls_to_table_1" name="Excel to Table" version="1.0.0">
+	<requirements><requirement type="package">protk</requirement></requirements>
+  <description>Converts an excel spreadsheet to a tab delimited text file</description>
+
+
+<!-- Note .. the input file is assumed to be the first argument -->
+<command>xls_to_table.rb $input_file -o $output</command>
+
+
+<inputs>
+
+	<param name="input_file" type="data" format="xls"  multiple="false" label="Input File" help="An Excel Spreadsheet"/>
+
+</inputs>
+<outputs>
+	<data format="csv" name="output" metadata_source="input_file" label="${input_file.display_name}.csv" />
+</outputs>
+
+<help>
+	Convert an Excel Spreadsheet to Tab delimited text
+</help>
+
+</tool>