annotate gemini_lof_sieve.xml @ 4:93a391b4602c draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gemini commit 283362494058ed64143b1f27afb447b8a1cb4313

<tool id="gemini_@BINARY@" name="GEMINI @BINARY@" version="@VERSION@.1">
    <description>Filter LoF variants by transcript position and type</description>
    <macros>
        <import>gemini_macros.xml</import>
        <token name="@BINARY@">lof_sieve</token>
    </macros>
    <expand macro="requirements" />
    <expand macro="stdio" />
    <expand macro="version_command" />
    <command>
<![CDATA[
        gemini @BINARY@
            "${ infile }"
            > "${ outfile }"
]]>
    </command>
    <inputs>
        <expand macro="infile" />
    </inputs>
    <outputs>
        <data name="outfile" format="tabular" />
    </outputs>
    <tests>
        <test>
            <param name="infile" value="gemini_load_result1.db" ftype="gemini.sqlite" />
            <output name="outfile">
                <assert_contents>
                    <has_line_matching expression="chrom&#009;start&#009;end&#009;.*highest_impact.*" />
                </assert_contents>
            </output>
        </test>
    </tests>
    <help><![CDATA[
**What it does**

*Filter LoF variants by transcript position and type*

Not all candidate LoF variants are created equal. For e.g, a nonsense (stop gain) variant impacting the first 5% of a polypeptide is far
more likely to be deleterious than one affecting the last 5%. Assuming you’ve annotated your VCF with snpEff v3.0+, the lof_sieve tool
reports the fractional position (e.g. 0.05 for the first 5%) of the mutation in the amino acid sequence.
In addition, it also reports the predicted function of the transcript so that one can segregate candidate
LoF variants that affect protein_coding transcripts from processed RNA, etc.

**Example**

Output with default settings::

 chrom   start       end        ref  alt  highest_impact  aa_change   var_trans_pos   trans_aa_length var_trans_pct   sample   genotype    gene    transcript       trans_type
 chr22   17072346    17072347   C    T    stop_gain       W365*       365             557             0.655296229803  NA19327  C|T         CCT8L2  ENST00000359963  protein_coding
 chr22   17072346    17072347   C    T    stop_gain       W365*       365             557             0.655296229803  NA19375  T|C         CCT8L2  ENST00000359963  protein_coding
 chr22   17129539    17129540   C    T    splice_donor    None        None            None            None            NA18964  T|C         TPTEP1  ENST00000383140  lincRNA
 chr22   17129539    17129540   C    T    splice_donor    None        None            None            None            NA19675  T|C         TPTEP1  ENST00000383140  lincRNA

    ]]></help>
    <expand macro="citations"/>
</tool>