annotate genome_editor.xml @ 3:134bb2d7cdfd draft

planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c

<tool id="edu.tamu.cpt.gff3.genome_editor" name="Genome Editor" version="2.1">
    <description>allows you to re-arrange a genome</description>
    <macros>
        <import>macros.xml</import>
        <import>cpt-macros.xml</import>
    </macros>
    <expand macro="requirements"/>
    <command><![CDATA[
@GENOME_SELECTOR_PRE@
'python $__tool_directory__/genome_editor.py'

@GENOME_SELECTOR@
@INPUT_GFF@
"$new_id"

--out_fasta "$out_fasta"
--out_gff3 "$out_gff3"
--out_simpleChain "$out_chain"
--customSeqs "$custom_seqs"
--changes
#for $idx, $change in enumerate($changes):
	#if $change.input_type.input_type_select == "region":
		${change.input_type.start},${change.input_type.end},${change.input_type.revcom}
	#else
		custom${idx}
	#end if
#end for
]]></command>
    <configfiles>
        <configfile name="custom_seqs">
		<![CDATA[
#for $idx, $change in enumerate($changes):
	#if $change.input_type.input_type_select == "custom":
>custom${idx}
${change.input_type.seq}
	#end if
#end for
		]]>
		</configfile>
    </configfiles>
    <inputs>
        <expand macro="input/gff3+fasta"/>
        <param label="New ID" name="new_id" type="text" help="New ID for the sequence to uniquely identify it from the previous build of the sequence. E.g. append Miro could become Miro.2 or Miro.v2 ">
            <validator type="expression" message="You must specify a new ID"><![CDATA[value and len(value) > 0]]></validator>
        </param>
        <repeat name="changes" title="Sequence Component Selections">
            <conditional name="input_type">
                <param name="input_type_select" type="select" label="Data Source">
                    <option value="region" selected="True">Region from FASTA file</option>
                    <option value="custom">Custom Additional Sequence</option>
                </param>
                <when value="region">
                    <param label="Start" name="start" type="integer" min="1" value="1" help="Inclusive range, 1-indexed genome. (I.e. specifying 1-2000 will include base number 1)"/>
                    <param label="End" name="end" type="integer" min="1" value="1" help="Inclusive range. (I.e. specifying 1-2000 will include base number 2000)"/>
                    <param label="Reverse + Complement" name="revcom" type="boolean" truevalue="-" falsevalue="+"/>
                </when>
                <when value="custom">
                    <param label="Custom Sequence" name="seq" type="text" help="Enter the sequence, e.g. 'ACTG'. No FASTA definition line."/>
                </when>
            </conditional>
        </repeat>
    </inputs>
    <outputs>
        <data format="gff3" name="out_gff3" label="${new_id} Features"/>
        <data format="fasta" name="out_fasta" label="${new_id}"/>
        <data format="tabular" name="out_chain" label="${new_id} Change Table"/>
    </outputs>
    <tests>
        <test>
            <param name="reference_genome_source" value="history"/>
            <param name="genome_fasta" value="genome_editor.simple.fa"/>
            <param name="gff3_data" value="genome_editor.simple.gff3"/>
            <param name="new_id" value="test2"/>
            <repeat name="changes">
                <conditional name="input_type">
                    <param name="input_type_select" value="region"/>
                    <param name="start" value="1"/>
                    <param name="end" value="4"/>
                    <param name="revcom" value="+"/>
                </conditional>
            </repeat>
            <repeat name="changes">
                <conditional name="input_type">
                    <param name="input_type_select" value="custom"/>
                    <param name="seq" value="cccggg"/>
                </conditional>
            </repeat>
            <repeat name="changes">
                <conditional name="input_type">
                    <param name="input_type_select" value="region"/>
                    <param name="start" value="5"/>
                    <param name="end" value="8"/>
                    <param name="revcom" value="-"/>
                </conditional>
            </repeat>
            <output name="out_gff3" file="genome_editor.simple.out.gff3"/>
            <output name="out_fasta" file="genome_editor.simple.out.fa"/>
            <output name="out_chain" file="genome_editor.simple.out.chain"/>
        </test>
        <test>
            <param name="reference_genome_source" value="history"/>
            <param name="genome_fasta" value="miro.fa"/>
            <param name="gff3_data" value="miro.2.gff3"/>
            <param name="new_id" value="Miro.v2"/>
            <repeat name="changes">
                <conditional name="input_type">
                    <param name="input_type_select" value="region"/>
                    <param name="start" value="1"/>
                    <param name="end" value="950"/>
                    <param name="revcom" value="+"/>
                </conditional>
            </repeat>
            <repeat name="changes">
                <conditional name="input_type">
                    <param name="input_type_select" value="custom"/>
                    <param name="seq" value="aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa"/>
                </conditional>
            </repeat>
            <repeat name="changes">
                <conditional name="input_type">
                    <param name="input_type_select" value="region"/>
                    <param name="start" value="3170"/>
                    <param name="end" value="3450"/>
                    <param name="revcom" value="+"/>
                </conditional>
            </repeat>
            <output name="out_gff3" file="genome_editor.mirov2.gff3"/>
            <output name="out_fasta" file="genome_editor.mirov2.fa"/>
            <output name="out_chain" file="genome_editor.mirov2.chain"/>
        </test>
    </tests>
    <help><![CDATA[
**What it does**

Allows for re-arranging a FASTA genomic sequence, and remaps the associated features 
from a gff3 file with the new coordinates. Segments of the genome are moved around 
and stitched back together according to user-specified positions. 

**Example FASTA input** (spaces added for clarity)::
	>Miro
	TTA GTA ATG GCT AAA

With user-specified *sequence component selections*:

- start: 1, end: 10, strand: +
- start: 6, end: 10, strand: +

the first ten bases will be listed, followed by a duplication of bases 6-10. 
Bases 11-15 are not part of the sequence component selection parameters and 
are therefore not in the output:: 

	>Miro.v2
	TTA GTA ATG GAA TGG

Alternatively, with user-specified *sequence component selections*::

- start: 1, end: 10, strand: +
- start: 6, end: 10, strand: -

the last section with be reverse-complemented and give the following output::

	>Miro.v2
	TTA GTA ATG GCC ATT

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