annotate htseq_clip.xml @ 0:94a987a7da69 draft default tip

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/rna_tools/htseq-clip commit 4879439f0df3386b97d8507c5991051fbdda053a

<tool id="htseq_clip" name="htseq-clip" version="0.1.0+galaxy0" python_template_version="3.5" profile="21.05">

    <description>- A toolset for the analysis of eCLIP/iCLIP datasets</description>
    <requirements>
        <requirement type="package" version="2.14.0b0">htseq-clip</requirement>
        <requirement type="package" version="2.30.0">bedtools</requirement>
    </requirements>

    <command detect_errors="exit_code"><![CDATA[


        #if $action_type.action_type_selector == 'create_sliding_windows':
            python '$__tool_directory__/htsc_create_sliding_windows.py'
                --gff '$action_type.gff_file'
                --out ./
                $action_type.gff_unsorted
                --hcw-w $action_type.hcw_options.hcw_w
                --hcw-s $action_type.hcw_options.hcw_s
                --no-zipper
        #elif $action_type.action_type_selector == 'create_count_table':
            python '$__tool_directory__/htsc_create_count_table.py'
                --win-bed '$action_type.win_bed_file'
                --exp-bams 
                #for $i in $action_type.exp_bams:
                    $i.exp_bam 
                #end for
                --ctr-bams 
                #for $i in $action_type.ctr_bams:
                    $i.ctr_bam 
                #end for
                --data-id '$action_type.data_id'
                --out ./
                --hce-e $action_type.hce_options.hce_e
                --hce-s '${action_type.hce_options.hce_s}'
                --hce-g $action_type.hce_options.hce_g
                --hce-q $action_type.hce_options.hce_q
                $action_type.hce_options.hce_primary
                --hce-c \${GALAXY_SLOTS:-1}
                --hce-m $action_type.hce_options.hce_m
                --hce-x $action_type.hce_options.hce_x
                --hce-l $action_type.hce_options.hce_l
                #if $action_type.hce_options.hce_f:
                    --hce-f '$action_type.hce_options.hce_f'
                #end if
                #if $action_type.hce_options.filter_bed:
                    --filter-bed '$action_type.hce_options.filter_bed'
                    --filter-mode $action_type.hce_options.filter_mode
                #end if
                $action_type.hcc_options.hcc_unstranded
                --no-zipper
        #end if

    ]]></command>

    <inputs>
        <conditional name="action_type">
        
            <param name="action_type_selector" type="select" label="Select an action">
                <option value="create_sliding_windows" selected="true">Create sliding windows</option>
                <option value="create_count_table">Create count table </option>
            </param>

            <when value="create_sliding_windows">

                <param name="gff_file" type="data" format="gff3"
                       label="GFF annotation file"
                       help="Provide a genomic annotation file in GFF3 format"/>
                <param name="gff_unsorted" label="Is the GFF file unsorted?" type="boolean"
                       truevalue="--hca-unsorted" falsevalue="" checked="False"
                       help="Check if GFF file is unsorted (default: GFF file is assumed to be sorted)"/>

                <section name="hcw_options" title="Sliding window settings">
                    <param name="hcw_w" type="integer" value="50"
                           label="Sliding window size"
                           help="Set the sliding window size in nucleotides. If unsure, try 75-100 (default: 50)"/>
                    <param name="hcw_s" type="integer" value="20"
                           label="Sliding window step size"
                           help="Set the sliding window step size (default: 20)"/>
                </section>

                <section name="win_out_options" title="Output options">
                    <param name="annot_bed_out" label="Output annotation BED file" type="boolean"
                               checked="False"
                               help="Output annotation BED file used for creating sliding windows"/>
                </section>

            </when>

            <when value="create_count_table">
                <repeat name="exp_bams" min="1" title="CLIP-seq experiment BAM inputs">
                    <param name="exp_bam" type="data" format="bam" label="BAM files belonging to the CLIP-seq experiment" help="Select BAM file belonging to the CLIP-seq experiment. NOTE that order determines replicate numbering in output tables"/>
                </repeat>
                <repeat name="ctr_bams" min="1" title="CLIP-seq control BAM inputs">
                    <param name="ctr_bam" type="data" format="bam" label="BAM files belonging to the CLIP-seq control" help="Select BAM file belonging to the CLIP-seq control. NOTE that order determines replicate numbering in output tables"/>
                </repeat>
                <param name="win_bed_file" type="data" format="bed"
                       label="Sliding windows BED file"
                       help="Provide a genomic regions BED file for calculating crosslink site overlap counts. Typically this is the sliding windows BED file created with htseq-clip's 'Create sliding windows' procedure"/>
                <param name="data_id" type="text" value="Rbp"
                       label="Dataset ID"
                       help="Provide a dataset ID (e.g., RNA-binding protein name) used in the generated data table (default: Rbp)"/>
                <section name="hce_options" title="Crosslink site extraction settings">
                    <param name="hce_e" type="integer" value="1" min="1" max="2"
                           label="Read mate to extract crosslink sites from"
                           help="Select the read mate (1, 2) to extract crosslink sites from. For single-end CLIP-seq data, select 1 (default: 1)"/>
                    <param name="hce_s" type="select" label="Specify crosslink site position on read"
                        help="Specify crosslink site position in the read, i.e., the genomic position to be extrated (default: middle position)">
                        <option value="m" selected="true">Middle position of read</option>
                        <option value="s">First position of read</option>
                        <option value="e">Last position of read</option>
                        <option value="i">Insertion site</option>
                        <option value="d">Deletion site</option>
                    </param>
                    <param name="hce_g" type="integer" value="0"
                           label="Crosslink site offset"
                           help="Number of nucleotides to offset for crosslink sites. Can be positive (upstream direction) or negative (downstream direction) (default: 0)"/>
                    <param name="hce_q" type="integer" value="10"
                           label="Minimum alignment quality"
                           help="Minimum alignment quality for filtering input BAM files. BAM entries greater than set quality will be filtered out (default: 10)"/>
                    <param name="hce_primary" label="Use only primary positions of multimapping reads?" type="boolean"
                        truevalue="--hce-primary" falsevalue="" checked="False"
                        help="Check if only primary positions of multimapping reads should be kept"/>
                    <param name="hce_m" type="integer" value="0"
                           label="Minimum read length"
                           help="Minimum read length for filtering input BAM files (default: 0)"/>
                    <param name="hce_x" type="integer" value="500"
                           label="Maximum read length"
                           help="Maximum read length for filtering input BAM files (default: 500)"/>
                    <param name="hce_l" type="integer" value="10000"
                           label="Maximum read interval length"
                           help="Maximum read interval length for filtering input BAM files (default: 10000)"/>
                    <param name="hce_f" type="data" format="txt" optional="True"
                        label="Specify chromosomes to extract crosslink sites from"
                        help="Extract crosslink sites only from chromosomes given in this file (format: one chromsome ID per file)"/>
                    <param name="filter_bed" type="data" format="bed" optional="True"
                        label="BED file for filtering out BAM entries"
                        help="Provide BED file to filter BAM entries based on their overlap with genomic regions inside the provided BED file"/>
                    <param name="filter_mode" type="select" label="Filtering mode for BED filtering"
                        help="Specify mode of filtering out BAM entries, with respect to the genomic regions inside the provided BED file)">
                        <option value="1" selected="true">Keep BAM entries not overlapping with BED regions</option>
                        <option value="2">Keep only BAM entries overlapping with BED regions</option>
                    </param>
                </section>

                <section name="hcc_options" title="Overlap count settings">
                    <param name="hcc_unstranded" label="Should crosslink site counting be non-strand-specific?" type="boolean"
                        truevalue="--hcc-unstranded" falsevalue="" checked="False"
                        help="Check if crosslink site position should be counted for overlapping features on both strands"/>
                </section>
            </when>


        </conditional>


    </inputs>

    <outputs>

        <data name="annotation_bed_file" format="bed" from_work_dir="annotation.bed" label="${tool.name} on ${on_string}: Annotation BED file">
            <filter>action_type["action_type_selector"] == "create_sliding_windows" and action_type["win_out_options"]["annot_bed_out"]</filter>
        </data>
        <data name="windows_bed_file" format="bed" from_work_dir="windows.bed" label="${tool.name} on ${on_string}: Sliding windows BED file">
            <filter>action_type["action_type_selector"] == "create_sliding_windows"</filter>
        </data>
        <data name="windows_txt_file" format="tabular" from_work_dir="windows_mapped_to_ids.txt" label="${tool.name} on ${on_string}: Windows annotation table file (DEWSeq input)">
            <filter>action_type["action_type_selector"] == "create_sliding_windows"</filter>
        </data>
        <data name="sample_info_file" format="tabular" from_work_dir="sample_info.txt" label="${tool.name} on ${on_string}: Sample information table file (DEWSeq input)">
            <filter>action_type["action_type_selector"] == "create_count_table"</filter>
        </data>
        <data name="count_matrix_file" format="tabular" from_work_dir="count_matrix.txt" label="${tool.name} on ${on_string}: Count table file (DEWSeq input)">
            <filter>action_type["action_type_selector"] == "create_count_table"</filter>
        </data>
    </outputs>
    <tests>

        <test>
            <param name="action_type_selector" value="create_sliding_windows"/>
            <param name="gff_file" value="paper_tus.Synechocystis_pSYSM.gff3" ftype="gff3"/>
            <param name="hcw_w" value="50"/>
            <param name="hcw_s" value="20"/>
            <param name="annot_bed_out" value="True"/>
            <output name="annotation_bed_file" file="annotation.exp.bed"/>
            <output name="windows_bed_file" file="windows.exp.bed"/>
            <output name="windows_txt_file" file="windows.exp.txt"/>
        </test>

        <test>
            <param name="action_type_selector" value="create_count_table"/>
            <param name="win_bed_file" value="windows.exp.bed" ftype="bed"/>           
            <param name="data_id" value="Rbp"/>
            <repeat name="exp_bams">
                <param name="exp_bam" value="Rbp_exp_rep1.Synechocystis_pSYSM.bam"/>
            </repeat>
            <repeat name="exp_bams">
                <param name="exp_bam" value="Rbp_exp_rep2.Synechocystis_pSYSM.bam"/>
            </repeat>
            <repeat name="ctr_bams">
                <param name="ctr_bam" value="Rbp_ctrl_rep1.Synechocystis_pSYSM.bam"/>
            </repeat>
            <output name="sample_info_file" file="sample_info.exp.txt"/>
            <output name="count_matrix_file" file="Rbp_count_matrix.exp.txt" sort="true"/>
        </test>

    </tests>
    <help><![CDATA[

**Overview**

htseq-clip is a toolset for the analysis of eCLIP/iCLIP datasets. It can be used to generate files necessary for data analysis using the companion R/Bioconductor package DEWSeq_ (available on Galaxy as well).

The Galaxy wrapper of htseq-clip provides the following two functionalities: 

1) Create sliding windows
2) Create count table


**Create sliding windows**

In this mode, htseq-clip takes a genomic annotation file (GFF3 format, tested with GENCODE_ GFF3 files), flattens it (i.e., overlapping regions get merged), 
and based on the flattened annotation BED file creates a sliding windows BED file. The window size and step size can be specified. 
E.g., a window size of 50 and a step size of 20 means that a window of 50 nt is extracted at every 20 nt step along each of the regions in the annotation BED file.
In the end, a table file is output, containing the windows and additional annotation information. This table file serves as one of the input files for DEWSeq. 
In addition, the windows BED file is output, which is needed as input for the "Create count table" mode.


**Create count table**

In this mode, htseq-clip takes the windows BED file created in "Create count table" mode, as well as the CLIP-seq BAM files (experiment BAMs and control BAMs). 
Various options are available for filtering the BAM files and modifying the counting procedure. htseq-clip then counts the number of overlapping BAM entries 
for each BAM file and each window in the input BED file. In the end, a count table file is output, as well as a sample information table file, which both 
serve as input files for DEWSeq.


**Documentation and Repository**

htseq-clip's online documentation can be found at:

https://htseq-clip.readthedocs.io

Its GitHub page is available at:

https://github.com/EMBL-Hentze-group/htseq-clip


.. _DEWSeq: https://bioconductor.org/packages/release/bioc/html/DEWSeq.html
.. _GENCODE: http://gencodegenes.org

    ]]></help>
    <citations>
        <citation type="bibtex">
            @incollection{sahadevan2022pipeline,
                doi={0.1007/978-1-0716-1851-6_10},
                url={https://doi.org/10.1007/978-1-0716-1851-6_10},
                title={A Pipeline for Analyzing eCLIP and iCLIP Data with Htseq-clip and DEWSeq},
                author={Sahadevan, Sudeep and Sekaran, Thileepan and Schwarzl, Thomas},
                booktitle={Post-Transcriptional Gene Regulation},
                pages={189--205},
                year={2022},
                publisher={Springer}
              }
        </citation>
    </citations>
</tool>