view CpGoe.xml @ 0:1535ffddeff4 draft

planemo upload commit a7ac27de550a07fd6a3e3ea3fb0de65f3a10a0e6-dirty

<tool id="CpGoe" name="Calculate CpNo/e" version="1.0.0">
    <requirements>
        <requirement type="package" version="5.8.0">perl</requirement>
    </requirements>
    <stdio>
        <exit_code range="1:" />
    </stdio>
    <command><![CDATA[
		perl ${__tool_directory__}/CpGoe.pl -f $fastafile -a $algo -c $context -o $outfile -m $minlength
    ]]></command>
    <inputs>
		<param name="fastafile" type="data" format="fasta" />
		<param name="context" type="select" label="Select context to calculate the CpNo/e ratio" >
			<option value="CpG" selected="selected">CpG</option>
			<option value="CpA">CpA</option>
			<option value="CpC">CpC</option>
			<option value="CpT">CpT</option>
		</param>
		<param name="algo" type="select" label="Select algorithm to calculate the CpGo/e ratio" >
			<option value="1">(CpG / (C * G)) * (L^2 / L-1)</option>
			<option value="2">Gardiner-Garden and Frommer (CpG / (G + C))*L</option>
			<option value="3">Zeng and Yi (CpG / L) / ((C + G)/L)^2</option>
			<option value="4">Saxonov, Berg and Brutlag CpG / ((C + G)/2)^2</option>
		</param>
		<param name="minlength" type="integer" value="200" help="Minimum length of the sequence to calculate CpGo/e ratio" />
    </inputs>
    <outputs>
		<data name="outfile" format="tabular" />
    </outputs>
	<tests>
		<test>
			<param name="fastafile" value="9_seqs.fa"/>
			<output name="outfile1" file="9_seqs_cpgoe.csv"/>
		</test>
	</tests>
    <help><![CDATA[
	CpGoe.pl -f fasta-file -a algo -c context -o output_file -m minlength

	Reads multi fasta files, writes name, length, CpGs and GpCs, CpGo/e ratios and other quantities into TAB file for each sequence.

	The available contexts (-c) are CpG, CpA, CpC, CpT. Default CpG.

	The algorithms (-a) available for -a are the following::

		1 => (CpG / (C * G)) * (L^2 / L-1)
		2 => (CpG / (C * G)) * L
		3 => (CpG / L) / ((C + G) / L)^2
		4 => (CpG / (C + G)/2)^2

	Where L represents the length of the sequence, CpG represents the count of CG dinucleotide, C and G represent the count for the respective bases and TG represents the number of TG dinucleotides.
    ]]></help>
    <citations>
        <citation>
          <citation type="doi">10.1101/180463</citation>
        </citation>
    </citations>
</tool>