view all stuff/differenceFinder.xml @ 5:f375051b0fcd draft

Uploaded

<tool id="commonality_r" name="difference_finder" version="17.0.0">
    <description>finds differences</description>
    <requirements>
       <requirement type="package">R</requirement>
    </requirements>
    <command><![CDATA[
		ln -s '$input1' S1.csv &&
		ln -s '$input2' SBF1.csv &&
		ln -s '$input3' S2.csv &&
		ln -s '$input4' SBF2.csv &&
		
		Rscript '$__tool_directory__/Difference finder MADE 7 TO 7 4-18-2019.R'
    ]]></command>
    <inputs>
		<param format="csv" name="input1" type="data" label="First Substrate Set"/>
		<param format="csv" name="input2" type="data" label="First Substrate Background Frequency"/>
		<param format="csv" name="input3" type="data" label="Second Substrate Set"/>
		<param format="csv" name="input4" type="data" label="Second Substrate Background Frequency"/>
		<param name="outGroup" type="text" value="kinase" label="Kinase Name"/>
    </inputs>      
    <outputs>
		<data format="csv" name="substrates1" from_work_dir="1RS.csv" label="${outGroup}_First_Unshared_Substrates.csv"/>
		<data format="csv" name="SBF1" from_work_dir="1RSBF.csv" label="${outGroup}_First_Unshared_SBF.csv"/>
		 <data format="csv" name="substrates2" from_work_dir="2RS.csv" label="${outGroup}_Second_Unshared_Substrates.csv"/>
		<data format="csv" name="SBF2" from_work_dir="2RSBF.csv" label="${outGroup}_Second_Unshared_SubstratesSBF.csv"/>
    </outputs>
    <tests>
        <test>
            <param name="input1.csv" ftype="csv" value="input1.csv"/>
            <param name="positives" ftype="csv" value="substrates.csv"/>
            <param name="SBF" ftype="csv" value="SBF.csv"/>
			<output name="Negatives" file="negatives.csv"/>
        </test>
    </tests>
    <help><![CDATA[
	This tool takes two Kinamine outputs (substrates and substrate background frequency files) and finds the two halves of the symmetrical difference.  https://en.wikipedia.org/wiki/Symmetric_difference
	
	Let us call the two INPUT substrate files 'A' and 'B'.  Let us call the two OUTPUT substrate files 'Y' and 'Z'.  'Y' consists of all 'A' that are not in 'B'.  'Z' consists of all 'B' that are not in 'A'.  In symbolic logic:
	
	Y ⇔ A ∧ ¬B
	
	Z ⇔ B ∧ ¬A
	
	The associated Substrate Background Frequency files for each consists of all the proteins associated with that substrate file.
    ]]></help>
    <citations>
        <citation type="doi">10.1074/mcp.RA118.001111</citation>
    </citations>
</tool>