annotate rnasnp.xml @ 0:327f5721612f draft default tip

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/rnasnp commit 6e51a331dbeab2786d8df5fd379ae3a63eb61d83

<tool id="rnasnp" name="RNAsnp" version="1.2.0">
    <description> Efficient detection of local RNA secondary structure changes induced by SNPs </description>

    <requirements>
        <requirement type="package" version="1.2">rnasnp</requirement>
    </requirements>

    <stdio>
        <exit_code range="1" level="fatal" description="Error occurred. Please check Tool Standard Error" />
        <exit_code range=":-1" level="fatal" description="Error occurred. Please check Tool Standard Error" />
        <exit_code range="2:" level="warning" description="Warning: Tool exited with error_code != 0" />
    </stdio>

    <version_command>RNAsnp --version</version_command>
    <command>
<![CDATA[

    RNAsnp
        --seq='$seq'
        --mode=$mode.mode_selector
        #if $mode.mode_selector == "1"
            --snp=$mode.snp
            --cutoff=$mode.cutoff
            --minLen=$mode.minLen
        #end if
        #if $mode.mode_selector == "2"
            --snp=$mode.snp
            --winsize=$mode.winsize
            --span=$mode.span
            --regionX=$mode.regionX
            --regionY=$mode.regionY
        #end if
        #if $mode.mode_selector == "3"
            --pvalue1=$mode.pvalue1
            --pvalue2=$mode.pvalue2
            --winsizeExt=$mode.winsizeExt
        #end if
        --edist=$edist
        --boltzmannPreFactor=$boltzmannPreFactor
        --winsizeFold=$mode.winsizeFold
        > '$outfile'

]]>
    </command>
    <inputs>
        <param argument="--seq" format="txt" type="data" label="Input Alignment File" />
        <conditional name="mode">
            <param name="mode_selector" type="select" label="Mode of operation">
                <option value="1" selected="true">1: Perform global folding by using RNAfold</option>
                <option value="2">2: Perform local folding by using RNAplfold</option>
                <option value="3">3: Screen putative structure-disruptive SNPs in an RNA sequence</option>
            </param>
            <when value="1">
                <param argument="--snp" format="txt" type="data" label="List of SNP"  help="The list of SNPs to be tested have to be provided in separate lines"/>
                <param argument="--winsizeFold" type="select" label="Folding windows size" help="Length of flanking sequence on either side of SNP considered for folding. please make sure that the input sequence is at least twice the size of chosen flanking. This restriction is necessary to keep the size of parameter tables for the p-value calculations manageable. In case the input sequence is less than twice the size of chosen flanking, the RNAsnp takes the nts up to the start and end position of the given sequence from the SNP position and perform the analysis.">
                    <option value="100"></option> <option value="150" ></option>
                    <option value="200" selected ="true"></option> <option value="250"></option> <option value="300"></option> <option value="350"></option> <option value="400"></option> <option value="450"></option>
                    <option value="500"></option> <option value="600"></option> <option value="650"></option> <option value="700"></option> <option value="750"></option> <option value="800"></option>
                </param>

                <param argument="--cutoff" type="float" value="0.01" label="Cut-off" help="Cut-off for the base pair probabilities."/>
                <param argument="--minLen" type="integer" value="50" min="1"  label="Minimum length of the sequence interval" help="The structural difference between wild-type and mutant is computed for all sequence intervals with the selected minimum length" />
            </when>
            <when value="2">
                <param argument="--snp" format="txt" type="data" label="List of SNP" help="The list of SNPs to be tested have to be provided in separate lines"/>
                <param argument="--winsizeFold" type="select" label="Folding windows size" help="Length of flanking sequence on either side of SNP considered for folding. please make sure that the input sequence is at least twice the size of chosen flanking. This restriction is necessary to keep the size of parameter tables for the p-value calculations manageable. In case the input sequence is less than twice the size of chosen flanking, the RNAsnp takes the nts up to the start and end position of the given sequence from the SNP position and perform the analysis.">
                    <option value="200" selected ="true"></option> <option value="250"></option> <option value="300"></option> <option value="350"></option> <option value="400"></option> <option value="450"></option>
                    <option value="500"></option> <option value="600"></option> <option value="650"></option> <option value="700"></option> <option value="750"></option> <option value="800"></option>
                </param>

                <param argument="--cutoff" type="float" value="0.01" min="0" label="Cut-off" help="Cut-off for the base pair probabilities."/>
                <param argument="--winsize" type="integer"  value="200" min="1" label="Windows size" help="Average the pair probabilities over windows of given size"/>
                <param argument="--span" type="integer"  value="120" min="1" label="Span" help="Set the maximum allowed separation of a base pair to span. i.e. no pairs (i,j) with j-i > L will be allowed."/>
                <param argument="--regionX" type="integer" value="20" min="1" label="Length of the local structural element that we expect to have an effect" help=""/>
                <param argument="--regionY" type="integer" value="120" min="1" label="Length of the interval over which the local structural changes are evaluated" help=""/>
            </when>
            <when value="3">
                <param argument="--winsizeFold" type="select" label="Folding windows size" help="Length of flanking sequence on either side of SNP considered for folding. please make sure that the input sequence is at least twice the size of chosen flanking. This restriction is necessary to keep the size of parameter tables for the p-value calculations manageable. In case the input sequence is less than twice the size of chosen flanking, the RNAsnp takes the nts up to the start and end position of the given sequence from the SNP position and perform the analysis.">
                    <option value="200" selected ="true"></option> <option value="250"></option> <option value="300"></option> <option value="350"></option> <option value="400"></option> <option value="450"></option>
                    <option value="500"></option> <option value="600"></option> <option value="650"></option> <option value="700"></option> <option value="750"></option> <option value="800"></option>
                </param>
                <param argument="--pvalue1" type="float" value="0.4" min="0" label="p-value threshold to filter SNPs that are predicted using Mode 2" help=""/>
                <param argument="--pvalue2" type="float" value="0.1" min="0" label="p-value threshold to filter SNPs that are predicted using Mode 1" help=""/>
                <param argument="--winsizeExt" type="integer" value="200" min="1" label="Windows size" help="size of the flanking region on either side of SNP that includes the local window returned by Mode 2. This subsequence is then passed to Mode 1 for re-computation"/>
            </when>
        </conditional>
        <param argument="--edist" type="integer" value="0" min="0" label="Ensemble Euclidean distance" help="compute ensemble Euclidean distance between the distribution of structures between two sequences"/>
        <param argument="--boltzmannPreFactor" type="float"  value="1" label="Boltzmann PreFactor" help="Multiply the bolztmann factor with a prefactor alpha"/>

    </inputs>
    <outputs>
        <data name="outfile" format="tabular" />
    </outputs>
    <tests>
        <test>
            <param name="seq" value="seq1.txt"/>
            <conditional name="mode">
                <param name="mode_selector" value="1"/>
                <param name="snp" value="snp1.txt"/>
            </conditional>
            <output name="outfile" file="seq1_snp1_mode1.out"/>
        </test>
    </tests>

    <help>
<![CDATA[

**What it does**
 Efficient detection of local RNA secondary structure changes induced by SNPs


 RNAsnp requires an RNA sequence and optionally a list of SNPs to be analyzed. The effect of SNPs on local RNA secondary structure can be detected in three possible modes,

    Mode 1: The first mode is designed to compute the effect of SNPs by using global folding. This option should be used only for short input sequences, since the base pair probabilities are calculated using RNAfold.

    Mode 2: The second mode is designed to compute the effect of SNPs on large sequences. Here the local base pair probabilities are calculated using RNAplfold (with the parameters -W 200 and -L 120).

    Mode 3: The third mode is the combination of the above two. It is intended to determine the positions of putative structure-disruptive SNPs using either transcript or genome sequence.


**Input**

Sequence file must contain one sequence (preferably in FASTA format).

SNP file must contain the list of SNPs that are given in separate lines. The
SNPs are described as, wild-type nucleotide followed by nucleotide position
followed by mutant nucleotide. In case of multiple SNPs, the SNPs are delimited
by the special character "-".

Example formats:
Single SNP: A201G
where, A is the wild-type nucleotide in the given sequence, 201 is the sequence
position of wild-type nucleotide and G is the mutant (or SNP).

Multiple SNPs: A201G-U257A-C260G
The multiple SNPs (which occurs together) are defined next to each other with
the delimiter "-" between them.


**Output**

SNP  w	Slen   GC  interval d  pvalue1 ewin	interval d_max	pvalue2

G1C 200	3344 0.5522 1-46    0.0421 0.0755  200   1-50	0.1581	0.0183

G7A 200	3344 0.5556 1-43    0.2236 0.0207  200	 1-50	0.1570	0.0996


Output details:

Column 1: details of the screened SNPs

Column 2: length of the flanking region considered on either side of the SNP to fold

Column 3: length of the given input sequence

Column 4: GC percent of the sequence interval considered for folding

Column 5-7: results of initial screen returned by mode 2

Column 8: ewin is the length of the flanking region considered on either of the SNP that also includes the local interval returned by mode 2. This subsequence is then passed to mode 1 to compute the d_max

Column 9-11: results of final screen returned by mode 1


Note: By default, the ewin(-e) uses the window length of 200. A higher computation speed is achieved if the ewin value is reduced to 100 or 150, however, there will be little difference in the result compare to ewin with 200. In addition, RNAsnp does automatically increase the length of ewin if the defined length is not enough to cover the local interval returned by mode 2.

]]>

    </help>

    <citations>
        <citation type="doi">10.1002/humu.22273</citation>
    </citations>

</tool>