annotate omssa.xml @ 7:51f6c6446e69 draft

Docker support and update for protk 1.4

<tool id="proteomics_search_omssa_1" name="OMSSA MSMS Search" version="1.1.0">

   <requirements>
        <container type="docker">iracooke/protk-1.4.1</container>
	    <requirement type="package" version="1.4">protk</requirement>
    	<requirement type="package" version="2.1.9">omssa</requirement>
    	<requirement type="package" version="2.2.29">blast+</requirement>
   </requirements>


	<description>Run an OMSSA MS/MS Search</description>
		
	<command>omssa_search.rb

		#if $database.source_select=="built_in":
		-d $database.dbkey 
		#else
		-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 selected="true" 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 selected="true" 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="0.5" 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="10000.0" 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="10" 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 value="0">a</option>
			<option selected="true" value="1">b</option>
			<option value="2">c</option>
			<option 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>

	<tests>
		<!-- Just test that the tool runs and produces vaguely correct output -->
		<test>
		    <param name="source_select" value="input_ref"/>
		    <param name="fasta_file" value="AASequences.fasta" format="fasta"/>
		    <param name="input_file" value="mr176-BSA100fmole_BA3_01_8168.d.mgf" format="mgf"/>
            <param name="max_hit_expect" value="1000"/>
            <param name="precursor_ion_tol" value="1.2"/>
            <param name="precursor_tolu" value="Da"/>
            <param name="fix_mods" value="3"/>
            <param name="variable_mods" value="1"/>


		    <output name="output" format="raw_pepxml">
		        <assert_contents>
					<has_text text="VLFSQAQVYELERRFK" />
		        </assert_contents>
		    </output>
		</test>
	</tests>

	<help>
**What it does**

Runs an MS/MS database search using the OMSSA search engine. Output is in the form of a pepXML file containing identified peptides along with their raw search scores.

----

**Citation**

If you use this tool please read and cite the paper describing OMSSA. 

Geer L. Y., et al. “Open mass spectrometry search algorithm” *J. Proteome Res.* 3(5), 958-964 (2004).

	</help>
</tool>