<tool id="ribotaper_create_annotation" name="ribotaper part 1: creation of annotation files" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile='20.01'>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro='bio_tools'/>
    <expand macro='requirements'/>
    <stdio>
        <exit_code range="1:"/>
    </stdio>
    <command><![CDATA[
        #if $reference_genome.source == 'history':
            #set $ref_genome = 'reference.fasta'
            ln -s -f '${reference_genome.history_item}' $ref_genome &&
            samtools faidx $ref_genome &&
        #else:
            #set $ref_genome = $reference_genome.index.fields.path
        #end if
        create_annotations_files.bash
        '${gtf}'
        '${ref_genome}'
        $ccdsid
        $appris
        './annotation_path'
        &&
        tar czvf '${output2}' './annotation_path'

    ]]></command>
    <inputs>
        <param name="gtf" type="data" format="GTF" label="Annotation file"
            help="The GTF file should contain: 1) coding and non-coding genes, 2) a 'transcript_id' and a 'gene_id' field for each 'exon' and 'CDS' row."/>
        <conditional name="reference_genome">
            <param name="source" type="select" label="Source for the genome" help="Built-in references were created using default options.">
                <option value="indexed" selected="true">Use a built-in genome</option>
                <option value="history">Use a genome from history</option>
            </param>
            <when value="indexed">
                <param name="index" type="select" label="Select a reference genome" help="If your genome of interest is not listed, contact the Galaxy team.">
                    <options from_data_table="fasta_indexes">
                        <filter type="sort_by" column="2" />
                        <validator type="no_options" message="No genomes are available for the selected input dataset" />
                    </options>
                </param>
            </when>
            <when value="history">
                <param name="history_item" type="data" format="fasta" label="Reference genome" help="A reference genome in FASTA format" />
            </when>
        </conditional>
        <param name="ccdsid" type="boolean" falsevalue="false" truevalue="true" checked="true" 
            label="Use CCDS annotation (valid for Human Gencode 19 and Mouse Gencode M3)"
            help="If yes, only exons/transcripts with the CCDS tag will be used as CCDS exons/transcripts, otherwise all exons/transcripts with a CDS region are going to be annotated as CCDS."/>
        <param name="appris" type="boolean" falsevalue="false" truevalue="true" checked="true" label="Use Appris annotation (valid for Human Gencode 19 and Mouse Gencode M3)"
               help=" If yes, only exons/transcripts with the appris tag will be used, using only 1 transcript per appris gene (the appris_principal transcript or other appris transcript). 
                If a gene does not have appris transcript, all the annotated transcript structures are used."/>
    </inputs>
    <outputs>
        <data name="output1" format="bed" from_work_dir="annotation_path/start_stops_FAR.bed" label="${tool.name} on ${on_string}: start_stops FAR"/>
        <data name="output2" format="tgz" label="${tool.name} on ${on_string}: Annotation path"/>
    </outputs>
    <tests>
        <test expect_num_outputs="2">
            <param name="gtf" value="test.gtf"/>
            <conditional name="reference_genome">
                <param name="source" value="history"/>
                <param name="history_item" value="test.fa"/>
            </conditional>
            <param name="ccdsid" value="true"/>
            <param name="appris" value="true"/>
            <output name="output1" file="annotation_path/start_stops_FAR.bed"/>
        </test>
        <test expect_num_outputs="2">
            <param name="gtf" value="test.gtf"/>
            <conditional name="reference_genome">
                <param name="source" value="indexed"/>
                <param name="index" value="phix174"/>
            </conditional>
            <param name="ccdsid" value="true"/>
            <param name="appris" value="true"/>
            <output name="output1" file="annotation_path/start_stops_FAR_indexed.bed"/>
        </test>
    </tests>
    <help><![CDATA[
Overview
--------

RiboTaper is an analysis pipeline for Ribosome Profiling
(Ribo-seq) experiments,
which exploits the triplet periodicity of
ribosomal footprints to call translated regions.
See
https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/ for details.


The Ribotaper Galaxy tool set consists of three tools:

  - ``ribotaper part 1``: creation of annotation files
  - ``ribotaper part 2``: metagene analysis for P-sites definition
  - ``ribotaper part 3``: ribosome profiling

The order of execution should follow:
``ribotaper part 1, part 2 and part 3``.

The current tool is ``ribotaper part 1``,
creation of annotation files.

Output
------

``Ribotaper part 1`` builds a list of exon coordinates,
exon sequences and transcript structures.

``Ribotaper part 1`` generates two files:

  - **start_stops_FAR** in BED format
  - **annotation_path**  in format of tar

*Start_stops_FAR*
is used as an input for ``ribotaper part 2``.
*Annotation_path*
is used as an input for ``ribotaper part 3``.


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