<?xml version="1.0" encoding="UTF-8"?>
<tool id="rcas" name="RNA Centric Annotation System" version="1.1.1">
    <requirements>
        <requirement type="package" version="1.1.1">bioconductor-rcas</requirement>
    </requirements>
    <stdio>
        <regex match="Execution halted" source="both" level="fatal" description="Execution halted." />
        <exit_code range="1:" />
    </stdio>
    <command><![CDATA[Rscript '$script_file'

            &&
            mv *RCAS.report.html RCAS.report.html


            #if $run_anot == "TRUE":
                &&
                mv Figure*summarizeQueryRegions.data.tsv summarizeQueryRegions.data.tsv &&
                mv Figure*query_gene_types.data.tsv query_gene_types.data.tsv &&
                mv Figure*transcriptBoundaryCoverage.fiveprime.data.tsv transcriptBoundaryCoverage.fiveprime.data.tsv &&
                mv Figure*transcriptBoundaryCoverage.threeprime.data.tsv transcriptBoundaryCoverage.threeprime.data.tsv &&
                mv Figure*exonIntronBoundaryCoverage.fiveprime.data.tsv exonIntronBoundaryCoverage.fiveprime.data.tsv &&
                mv Figure*exonIntronBoundaryCoverage.threeprime.data.tsv exonIntronBoundaryCoverage.threeprime.data.tsv &&
                mv Figure*coverageprofilelist.data.tsv coverageprofilelist.data.tsv &&
                mv Table*getTargetedGenesTable.data.tsv getTargetedGenesTable.data.tsv
            #end if


            #if $run_GOrich == "TRUE":
                &&
                mv Table*goBP.data.tsv goBP.data.tsv &&
                mv Table*goMF.data.tsv goMF.data.tsv &&
                mv Table*goCC.data.tsv goCC.data.tsv
            #end if


            #if $choice.run_PATHrich == "TRUE":
                &&
                mv Table*GSEA.data.tsv GSEA.data.tsv
            #end if


            #if $run_motif == "TRUE":
                &&
                mv Table*motif_analysis_table.data.tsv motif_analysis_table.data.tsv
            #end if]]></command>
    <configfiles>
        <configfile name="script_file">library("RCAS")

           runReport(queryFilePath = '${input_BED}',

           gffFilePath = '${input_GTF}',

           #if $choice.run_PATHrich == "TRUE":
                msigdbFilePath = '${choice.input_human_msigdb_gmt}',
           #end if

           annotationSummary = ${run_anot},

           goAnalysis = ${run_GOrich},

           msigdbAnalysis = ${choice.run_PATHrich},

           motifAnalysis = ${run_motif},

           genomeVersion = '${genomeVersion}',

           outDir = getwd(),

           printProcessedTables = TRUE,

           sampleN = '${downsampling}',

           selfContained = TRUE)</configfile>
    </configfiles>
    <inputs>
        <param name="genomeVersion" type="select" label="Genome Version">
            <option value="hg19" selected="true">hg19</option>
            <option value="dm3">dm3</option>
            <option value="ce10">ce10</option>
            <option value="mm9">mm9</option>
        </param>
        <param name="input_BED" type="data" format="BED" label="Target regions in BED format" help="The coordinates should be in accord with Genome Version." />
        <param name="input_GTF" type="data" format="GTF" label="Reference annotation in ENSEMBL GTF format" />
        <param name="run_anot" label="Run annotation." type="boolean" falsevalue="FALSE" truevalue="TRUE" checked="True" help="Use this option if you want to run annotation." />
        <param name="run_GOrich" label="Run GO term enrichment" type="boolean" falsevalue="FALSE" truevalue="TRUE" checked="False" help="Use this option if you want to run GO term enrichment (supported genome versions: hg19, mm9, dm3)." />
        <conditional name="choice">
            <param name="run_PATHrich" type="select" label="Run gene set enrichment" help="Use this option if you want to run gene set enrichment.">
                <option value="FALSE" selected="True">No</option>
                <option value="TRUE">Yes</option>
            </param>
            <when value="TRUE">
                <param name="input_human_msigdb_gmt" type="data" format="tabular" label="Human Molecular Signatures Database (MSigDB)" help="The database is usesd for gene set enrichment (supported genome versions: hg19, mm9, dm3). For non-human species, the human MSigDB will be automatically converted accordingly." />
            </when>
            <when value="FALSE" />
        </conditional>
        <param name="run_motif" label="Run motif search" type="boolean" falsevalue="FALSE" truevalue="TRUE" checked="False" help="Use this option if you want to run motif search." />
        <param name="downsampling" label="Downsampling (N)" type="text" value="0" help="Randomly sample query regions down to (N)" />
    </inputs>
    <outputs>
        <data name="report" format="html" from_work_dir="RCAS.report.html" label="${tool.name} on ${on_string}: dynamic HTML" />
        <data name="summarizeQueryRegions" format="tsv" from_work_dir="summarizeQueryRegions.data.tsv" label="${tool.name} on ${on_string}: Query regions summary">
            <filter>run_anot == True</filter>
        </data>
        <data name="query_gene_types" format="tsv" from_work_dir="query_gene_types.data.tsv" label="${tool.name} on ${on_string}: Query gene types">
            <filter>run_anot == True</filter>
        </data>
        <data name="transcriptBoundaryCoverage.fiveprime" format="tsv" from_work_dir="transcriptBoundaryCoverage.fiveprime.data.tsv" label="${tool.name} on ${on_string}: Transcript boundary coverage (5')">
            <filter>run_anot == True</filter>
        </data>
        <data name="transcriptBoundaryCoverage.threeprime" format="tsv" from_work_dir="transcriptBoundaryCoverage.threeprime.data.tsv" label="${tool.name} on ${on_string}: Transcript boundary coverage (3')">
            <filter>run_anot == True</filter>
        </data>
        <data name="exonIntronBoundaryCoverage.fiveprime" format="tsv" from_work_dir="exonIntronBoundaryCoverage.fiveprime.data.tsv" label="${tool.name} on ${on_string}: Exon-intron boundary coverage (5')">
            <filter>run_anot == True</filter>
        </data>
        <data name="exonIntronBoundaryCoverage.threeprime" format="tsv" from_work_dir="exonIntronBoundaryCoverage.threeprime.data.tsv" label="${tool.name} on ${on_string}: Exon-intron boundary coverage (3')">
            <filter>run_anot == True</filter>
        </data>
        <data name="coverageprofilelist" format="tsv" from_work_dir="coverageprofilelist.data.tsv" label="${tool.name} on ${on_string}: Coverage profile list">
            <filter>run_anot == True</filter>
        </data>
        <data name="getTargetedGenesTable" format="tsv" from_work_dir="getTargetedGenesTable.data.tsv" label="${tool.name} on ${on_string}: Targeted genes">
            <filter>run_anot == True</filter>
        </data>
        <data name="goCC" format="tsv" from_work_dir="goCC.data.tsv" label="${tool.name} on ${on_string}: GO term enrichment (cellular compartments)">
            <filter>run_GOrich == True</filter>
        </data>
        <data name="goBP" format="tsv" from_work_dir="goBP.data.tsv" label="${tool.name} on ${on_string}: GO term enrichment (biological processes)">
            <filter>run_GOrich == True</filter>
        </data>
        <data name="goMF" format="tsv" from_work_dir="goMF.data.tsv" label="${tool.name} on ${on_string}: GO term enrichment (molecular functions)">
            <filter>run_GOrich == True</filter>
        </data>
        <data name="GSEA" format="tsv" from_work_dir="GSEA.data.tsv" label="${tool.name} on ${on_string}: Gene set enrichment analysis">
            <filter>choice['run_PATHrich'] == "TRUE"</filter>
        </data>
        <data name="motif" format="tsv" from_work_dir="motif_analysis_table.data.tsv" label="${tool.name} on ${on_string}: Motif">
            <filter>run_motif == True</filter>
        </data>
    </outputs>
    <tests>
        <test>
            <param name="input_BED" value="input.TIA1.bed" />
            <param name="input_GTF" value="input.Homo_sapiens.GRCh37-chr1-f10k.75.gtf" />
            <param name="input_human_msigdb_gmt" value="input.msigdb_test.gmt" />
            <param name="run_anot" value="TRUE" />
            <param name="run_GOrich" value="TRUE" />
            <param name="run_PATHrich" value="TRUE" />
            <param name="run_motif" value="TRUE" />
            <param name="genomeVersion" value="hg19" />
            <output name="report" file="output.TIA1.bed.RCAS.report.html" ftype="html" compare="sim_size" />
            <output name="summarizeQueryRegions" file="summarizeQueryRegions.data.tsv" ftype="tsv" />
            <output name="query_gene_types" file="query_gene_types.data.tsv" ftype="tsv" />
            <output name="transcriptBoundaryCoverage.fiveprime" file="transcriptBoundaryCoverage.fiveprime.data.tsv" ftype="tsv" />
            <output name="transcriptBoundaryCoverage.threeprime" file="transcriptBoundaryCoverage.threeprime.data.tsv" ftype="tsv" />
            <output name="exonIntronBoundaryCoverage.fiveprime" file="exonIntronBoundaryCoverage.fiveprime.data.tsv" ftype="tsv" />
            <output name="exonIntronBoundaryCoverage.threeprime" file="exonIntronBoundaryCoverage.threeprime.data.tsv" ftype="tsv" />
            <output name="coverageprofilelist" file="coverageprofilelist.data.tsv" ftype="tsv" />
            <output name="getTargetedGenesTable" file="getTargetedGenesTable.data.tsv" ftype="tsv" />
            <output name="goCC" file="goCC.data.tsv" ftype="tsv" compare="sim_size"/>
            <output name="goBP" file="goBP.data.tsv" ftype="tsv" compare="sim_size"/>
            <output name="goMF" file="goMF.data.tsv" ftype="tsv" compare="sim_size"/>
            <output name="GSEA" file="GSEA.data.tsv" ftype="tsv" />
            <output name="motif" file="motif_analysis_table.data.tsv" ftype="tsv" compare="sim_size" />
        </test>
    </tests>
    <help><![CDATA[.. class:: infomark

**Purpose**

RNA Centric Annotation System (RCAS) automatically generates
dynamic annotations for custom input files
that contain transcriptomic target regions.
RCAS automatically summarizes annotated features
that overlap with targets in the BED file,
and perform enrichment analysis of
Gene Ontology (GO) terms, gene set and motifs.

-----

.. class:: infomark

**Inputs**

1. A target region file in BED format
2. A reference annotation file in GTF format
3. A Human Molecular Signatures Database (MSigDB) (only needed for gene set enrichment)

-----

.. class:: infomark

**Outputs**

The outputs consist of a dynamic HTML file and
a dozen of tabular files.
The dynamic HTML file is composed of the interactive tables and figures,
which can be downloaded and viewed with a web browser.

The tabular files correspond to the respective figures in the HTML file,
which are the results
of different RCAS analysis, as following:

1. Annotation summary for query regions

  * Query regions summary
  * Query gene types
  * Transcript boundary coverage (5')
  * Transcript boundary coverage (3')
  * Exon-intron boundary coverage (5')
  * Exon-intron boundary coverage (3')
  * Coverage profile list
  * Targeted genes

2. GO term analysis results

  * GO term enrichment (cellular compartments)
  * GO term enrichment (biological processes)
  * GO term enrichment (molecular functions)

3. Gene set enrichment analysis results

4. Motif analysis results]]></help>
    <citations>
        <citation type="doi">10.1093/nar/gkx120</citation>
    </citations>
</tool>