annotate chipseeker.xml @ 7:1b9a9409831d draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/chipseeker commit e07ee851144e07fde91877727d6a39a1906f7639

<tool id="chipseeker" name="ChIPseeker" version="1.18.0+galaxy1">
    <description>for ChIP peak annotation and visualization</description>
    <requirements>
        <requirement type="package" version="1.18.0">bioconductor-chipseeker</requirement>
        <requirement type="package" version="1.6.1">r-optparse</requirement>
    </requirements>
    <version_command><![CDATA[
echo $(R --version | grep version | grep -v GNU)", ChIPseeker version" $(R --vanilla --slave -e "library(ChIPseeker); cat(sessionInfo()\$otherPkgs\$ChIPseeker\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", optparse version" $(R --vanilla --slave -e "library(optparse); cat(sessionInfo()\$otherPkgs\$optparse\$Version)" 2> /dev/null | grep -v -i "WARNING: ")
    ]]></version_command>
    <command detect_errors="exit_code"><![CDATA[
        #set gtf = "refgtf"
        #if $gtf_source.gtf_source_select == "history":
            ln -s '${gtf_source.gtf_hist}' $gtf &&
        #else if $gtf_source.gtf_source_select == "cached":
            ln -s '${gtf_source.gtf_builtin.fields.path}' $gtf &&
        #end if

        #if $rscript:
            cp '$__tool_directory__/chipseeker.R' '$out_rscript' &&
        #end if

        Rscript '$__tool_directory__/chipseeker.R'

        -i '$peaks'
        -H $header
        -G '$gtf'
        -u $adv.upstream
        -d $adv.downstream

        #if $adv.flankgeneinfo:
            -F $adv.flankgeneinfo
        #end if

        -D $adv.flankgenedist

        #if $adv.ignoreUpstream:
            -j $adv.ignoreUpstream
        #end if

        #if $adv.ignoreDownstream:
            -k $adv.ignoreDownstream
        #end if

        -f $format

        #if $pdf:
            -p $pdf
        #end if

        -r $rdata
    ]]>
    </command>
    <inputs>
        <param name="peaks" type="data" format="bed,interval,tabular" label="Peaks file" help="A peaks file in BED format." />
        <param name="header" type="boolean" truevalue="True" falsevalue="False" checked="False" label="Peaks file has header?" help="If this option is set to Yes, the tool will assume that the peak file has column headers in the first row. Default: No" />
        <conditional name="gtf_source">
            <param name="gtf_source_select" type="select" label="Annotation source" help="Select a GTF to use for annotation source.">
                <option value="cached" selected="true">Use a built-in GTF</option>
                <option value="history">Use a GTF from history</option>
            </param>
            <when value="cached">
                 <param name="gtf_builtin" type="select" label="Select a built-in GTF" help="If the GTF file for your transcriptome of interest is not listed, contact your Galaxy administrator">
                     <options from_data_table="gene_sets">
                         <filter type="sort_by" column="2" />
                         <validator type="no_options" message="No GTF file is available." />
                     </options>
                 </param>
            </when>
            <when value="history">
                <param name="gtf_hist" type="data" format="gtf" label="Select a history GTF" />
            </when>
        </conditional>
        <param name="format" type="select" label="Output Format">
            <option value="interval" selected="True">Interval</option>
            <option value="tabular">Tabular (tab-separated)</option>
        </param>
        <param name="pdf" type="boolean" truevalue="True" falsevalue="" checked="True" label="Output PDF of plots?" help="Default: Yes" />
        <param name="rscript" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="False" label="Output Rscript?" help="If this option is set to Yes, the Rscript used to annotate the IDs will be provided as a text file in the output. Default: No" />
        <param name="rdata" type="boolean" truevalue="True" falsevalue="False" checked="False" label="Output RData file?"
            help="Output all the data used by R to construct the tables and plots, can be loaded into R. Default: No">
        </param>

        <section name="adv" expanded="false" title="Advanced Options">
            <param name="upstream" type="integer" min="0" value="3000" label="TSS upstream region" help="User can define TSS (transcription start site) region, by default TSS is defined from -3kb to +3kb." />
            <param name="downstream" type="integer" min="0" value="3000" label="TSS downstream region" help="User can define TSS (transcription start site) region, by default TSS is defined from -3kb to +3kb."/>
            <param name="flankgeneinfo" type="boolean" truevalue="True" falsevalue="False" checked="False" label="Add flanking gene information?" help="If specified all genes within the flanking gene distance are reported for each peak. Default: No."/>
            <param name="flankgenedist" type="integer" min="0" value="5000" label="Flanking gene distance" help="If flanking gene info is turned on the flanking distance can be specified. Default: 5000."/>
            <param name="ignoreUpstream" type="boolean" truevalue="True" falsevalue="False" checked="False" label="Ignore upstream?" help="If Yes only annotate gene at the 3’ of the peak. Default: No."/>
            <param name="ignoreDownstream" type="boolean" truevalue="True" falsevalue="False" checked="False" label="Ignore downstream?" help="If Yes only annotate gene at the 5’ of the peak. Default: No."/>
        </section>
    </inputs>

        <outputs>
            <data name="out_tab" format="interval" from_work_dir="out.tab" label="${tool.name} on ${on_string}: Annotated Peaks" >
                <change_format>
                    <when input="format" value="tabular" format="tabular" />
                </change_format>
            </data>
            <data name="out_plots" format="pdf" from_work_dir="out.pdf" label="${tool.name} on ${on_string}: Plots">
                <filter>pdf</filter>
            </data>
            <data name="out_rscript" format="txt" from_work_dir="out_rscript.txt" label="${tool.name} on ${on_string}: Rscript">
                <filter>rscript</filter>
            </data>
            <data name="out_rdata" format="rdata" from_work_dir="ChIPseeker_analysis.RData" label="${tool.name} on ${on_string}: RData file">
                <filter>rdata</filter>
            </data>
        </outputs>

    <tests>
        <!-- Ensure bed and GTF inputs and all outputs work -->
        <test expect_num_outputs="4">
            <param name="peaks" value="in.bed" ftype="bed"/>
            <param name="gtf_source_select" value="history"/>
            <param name="gtf_hist" value="in.gtf"/>
            <param name="rscript" value="True"/>
            <param name="rdata" value="True"/>
            <output name="out_tab" ftype="interval" file="out.int" />
            <output name="out_plots" file="out.pdf" compare="sim_size"/>
            <output name="out_rscript" >
                <assert_contents>
                    <has_text_matching expression="peakAnno.*annotatePeak" />
                </assert_contents>
            </output>
            <output name="out_rdata" file="out.rdata" compare="sim_size" />
        </test>
        <!-- Ensure built-in GTF works -->
        <test expect_num_outputs="2">
            <param name="peaks" value="in.interval" ftype="interval"/>
            <param name="gtf_source_select" value="cached"/>
            <output name="out_tab" ftype="interval" file="outint.int" />
            <output name="out_plots" file="out.pdf" compare="sim_size"/>
        </test>
        <!-- Ensure tabular output works -->
        <test expect_num_outputs="2">
            <param name="peaks" value="in.interval" ftype="interval"/>
            <param name="gtf_source_select" value="history"/>
            <param name="gtf_hist" value="in.gtf"/>
            <param name="format" value="tabular"/>
            <output name="out_tab" ftype="tabular" file="outint.tab" />
            <output name="out_plots" file="out.pdf" compare="sim_size"/>
        </test>
        <!-- Ensure TSS region specification works -->
        <test expect_num_outputs="2">
            <param name="peaks" value="in.interval" ftype="interval"/>
            <param name="gtf_source_select" value="history"/>
            <param name="gtf_hist" value="in.gtf"/>
            <param name="upstream" value="1000" />
            <param name="downstream" value="1000" />
            <param name="format" value="tabular"/>
            <output name="out_tab" ftype="tabular" file="outtss.tab" />
            <output name="out_plots" file="out.pdf" compare="sim_size"/>
        </test>
        <!-- Ensure flanking genes works -->
        <test expect_num_outputs="2">
            <param name="peaks" value="in.interval" ftype="interval"/>
            <param name="gtf_source_select" value="history"/>
            <param name="gtf_hist" value="in.gtf"/>
            <param name="flankgeneinfo" value="True" />
            <param name="format" value="tabular"/>
            <output name="out_tab" ftype="tabular" file="outflank.tab" />
            <output name="out_plots" file="out.pdf" compare="sim_size"/>
        </test>
        <!-- Ensure the tool works when no plots are outputed -->
        <test expect_num_outputs="1">
            <param name="peaks" value="in.interval" ftype="interval"/>
            <param name="gtf_source_select" value="cached"/>
            <param name="pdf" value=""/>
            <output name="out_tab" ftype="interval" file="outint.int" />
        </test>
    </tests>
    <help><![CDATA[

.. class:: infomark

**What it does**

ChIPseeker_ is a Bioconductor package for annotating ChIP-seq data analysis. Peak Annotation is performed by the annotatePeak function. The position and strand information of nearest genes are reported, in addition to the distance from the peak to the TSS of its nearest gene. Users can define the TSS (transcription start site) region under **Advanced Options**, by default the TSS region is defined from -3kb to +3kb. The genomic region of the peak is reported in the annotation column. Since some annotations may overlap for a peak, ChIPseeker adopts the following priority in genomic annotation:

* Promoter
* 5’ UTR
* 3’ UTR
* Exon
* Intron
* Downstream
* Intergenic

ChIPseeker also produces plots to help users visualise the overlaps in annotation for peaks, for example, the vennpie and upsetplot. See the `ChIPseeker vignette`_ for more information.

-----

**Inputs**

A peaks file in BED, Interval or Tabular format e.g from MACS2 or DiffBind. Note that there is an option to specify if the input peaks file has a header row. No header row is assumed by default, which is usually the case for BED format e.g. MACS narrowpeak, however other formats e.g. MACS tabular format, may contain a header row.

Example:

    =====  ======  ======  ========  =====  ======
    Chrom  Start   End     Name      Score  Strand
    =====  ======  ======  ========  =====  ======
    18     394599  396513  DiffBind  0      .
    18     111566  112005  DiffBind  0      .
    18     346463  347342  DiffBind  0      .
    18     399013  400382  DiffBind  0      .
    18     371109  372102  DiffBind  0      .
    =====  ======  ======  ========  =====  ======

A GTF file for annotation. The GTF file must have fields called "gene_id" and gene_name".

-----

**Outputs**

This tool outputs

    * a file of annotated peaks in Interval or Tabular format
    * a PDF of plots (plotAnnoPie, plotAnnoBar, vennpie, upsetplot, plotDistToTSS)

Optionally, you can choose to output

    * the R script used by this tool
    * an RData file

**Annotated peaks**

Annotation similar to below will be added to the input file.

Example - **Interval format**:

    =====  ======  ======  =====================================================================================================================================================
    Chrom  Start   End     Comment
    =====  ======  ======  =====================================================================================================================================================
    18     394599  396513  DiffBind|0|.|Intron (ENST00000400256/ENSG00000158270, intron 1 of 1)|1|346465|400382|53918|2|ENST00000400256| 3869|COLEC12|ENSG00000158270
    18     346463  347342  DiffBind|0|.|Exon (ENST00000400256/ENSG00000158270, exon 1 of 1)|1|346465|400382|53918|2|ENST00000400256|53040|COLEC12|ENSG00000158270
    18     399013  400382  DiffBind|0|.|Promoter (<=1kb)|1|346465|400382|53918|2|ENST00000400256|    0|COLEC12|ENSG00000158270
    18     371109  372102  DiffBind|0|.|Intron (ENST00000400256/ENSG00000158270, intron 1 of 1)|1|346465|400382|53918|2|ENST00000400256|28280|COLEC12|ENSG00000158270
    18     111566  112005  DiffBind|0|.|Promoter (<=1kb)|1|111568|112005|  438|1|ENST00000608049|    0|ROCK1P1|ENSG00000263006
    =====  ======  ======  =====================================================================================================================================================

    Columns contain the following data:

* **Chrom**: Chromosome name
* **Start**: Start position of site
* **End**: End position of site
* **Comment**: The pipe ("|") separated values in this column correspond to:

    * *<Any additional input columns>*
    * *annotation* (Promoter, 5’ UTR, 3’ UTR, Exon, Intron, Downstream, Intergenic)
    * *geneChr*
    * *geneStart*
    * *geneEnd*
    * *geneLength*
    * *geneStrand*
    * *transcriptId*
    * *distanceToTSS*
    * *geneName*
    * *geneId*

Example - **Tabular format**:

    =====  ======  ======  ========  ====== ======  ===========================================  ======================================================= ======= ========= ======= ========== ========== =============== ============= ======== ===============
    Chrom  Start   End     Name      Score  Strand  Comment                                      annotation                                              geneChr geneStart geneEnd geneLength geneStrand transcriptId    distanceToTSS geneName geneId
    =====  ======  ======  ========  ====== ======  ===========================================  ======================================================= ======= ========= ======= ========== ========== =============== ============= ======== ===============
    18     394599  396513  DiffBind    0    .       1914|7.15|5.55|7.89|-2.35|7.06e-24|9.84e-21  Intron (ENST00000400256/ENSG00000158270, intron 1 of 1) 1       346465    400382  53918      2          ENST00000400256 3869          COLEC12  ENSG00000158270
    18     346463  347342  DiffBind    0    .       879|5|5.77|3.24|2.52|6.51e-06|0.00303        Exon (ENST00000400256/ENSG00000158270, exon 1 of 1)     1       346465    400382  53918      2          ENST00000400256 53040         COLEC12  ENSG00000158270
    18     399013  400382  DiffBind    0    .       1369|7.62|7|8.05|-1.04|1.04e-05|0.00364      Promoter (<=1kb)                                        1       346465    400382  53918      2          ENST00000400256 0             COLEC12  ENSG00000158270
    18     371109  372102  DiffBind    0    .       993|4.63|3.07|5.36|-2.3|8.1e-05|0.0226       Intron (ENST00000400256/ENSG00000158270, intron 1 of 1) 1       346465    400382  53918      2          ENST00000400256 28280         COLEC12  ENSG00000158270
    18     111566  112005  DiffBind    0    .       439|5.71|6.53|3.63|2.89|1.27e-08|8.88e-06    Promoter (<=1kb)                                        1       111568    112005  438        1          ENST00000608049 0             ROCK1P1  ENSG00000263006
    =====  ======  ======  ========  ====== ======  ===========================================  ======================================================= ======= ========= ======= ========== ========== =============== ============= ======== ===============

.. _ChIPseeker: https://bioconductor.org/packages/release/bioc/html/ChIPseeker.html
.. _`ChIPseeker vignette`: http://bioconductor.org/packages/release/bioc/vignettes/ChIPseeker/inst/doc/ChIPseeker.html

]]></help>
    <citations>
        <citation type="doi">10.1093/bioinformatics/btv145</citation>
    </citations>
</tool>