annotate repenrich.xml @ 15:2e3d976e7d5d draft default tip

planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/main/tools/repenrich commit 03183e29f807ec33548016a7c4144f52720b7b9e

<tool id="repenrich" name="RepEnrich" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
    <description>Repeat Element Profiling</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="repenrich_requirements"/>
    <stdio>
        <exit_code range="1:" level="fatal" description="Tool exception" />
    </stdio>
    <command detect_errors="exit_code"><![CDATA[
        #import re
        ## uncompress fastq.gz or fastqsanger.gz if needed
        #if $seq_method.seq_method_list == "single-read":
            #if $seq_method.input_fastq.is_of_type("fastq.gz", "fastqsanger.gz"):
                gunzip < '$seq_method.input_fastq' > 'input.fastq' &&
            #else:
                ln -f -s '$seq_method.input_fastq' 'input.fastq' &&
            #end if
        #elif $seq_method.seq_method_list == 'paired_collection':
            #if $seq_method.input_fastq.forward.is_of_type("fastq.gz", "fastqsanger.gz"):
                gunzip < '$seq_method.input_fastq.forward' > 'input.fastq' &&
                gunzip < '$seq_method.input_fastq.reverse' > 'input_2.fastq' &&
            #else:
                ln -f -s '$seq_method.input_fastq.forward' 'input.fastq' &&
                ln -f -s '$seq_method.input_fastq.reverse' 'input_2.fastq' &&
            #end if
        #else:
            #if $seq_method.input2_fastq.is_of_type("fastq.gz", "fastqsanger.gz"):
                gunzip < '$seq_method.input_fastq' > 'input.fastq' &&
                gunzip < '$seq_method.input2_fastq' > 'input_2.fastq' &&
            #else:
                ln -f -s '$seq_method.input_fastq' 'input.fastq' &&
                ln -f -s '$seq_method.input2_fastq' 'input_2.fastq' &&
            #end if
        #end if
        ln -f -s '$genome' 'genome.fa' &&
        bowtie-build --threads \${GALAXY_SLOTS:-1} '$genome' genome &&
        python $__tool_directory__/RepEnrich_setup.py
            --annotation_file '$repeatmasker'
            --genomefasta 'genome.fa'
            --cpus "\${GALAXY_SLOTS:-4}" &&
        #if $seq_method.seq_method_list == "single-read":
            bowtie genome -p \${GALAXY_SLOTS:-4} -t -m 1 -S --max multimap.fastq input.fastq input_unique.sam 2>bowtie_alignments.txt &&
        #else:
            bowtie genome -p \${GALAXY_SLOTS:-4} -t -m 1 -S --max multimap.fastq -1 input.fastq -2 input_2.fastq input_unique.sam 2>bowtie_alignments.txt &&
        #end if
        samtools view -@ \${GALAXY_SLOTS:-4} -bS 'input_unique.sam' | samtools sort -@ \${GALAXY_SLOTS:-4} -O bam -o 'input_unique.bam' &&
        samtools index input_unique.bam &&
        python $__tool_directory__/RepEnrich.py
            --annotation_file $repeatmasker
            --alignment_bam input_unique.bam
            --cpus "\${GALAXY_SLOTS:-4}"
        #if $seq_method.seq_method_list == "single-read":
            --fastqfile multimap.fastq
        #else:
            --fastqfile multimap_1.fastq
            --fastqfile2 multimap_2.fastq
        #end if
    ]]></command>
    <!-- basic error handling -->
    <inputs>
    <conditional name="seq_method">
        <param help="Paired-end or single-read sequencing" label="Sequencing method" name="seq_method_list" type="select">
            <option selected="True" value="single-read">Single-read sequencing</option>
            <option value="paired-end">Paired-end sequencing</option>
            <option value="paired_collection">Paired-end Dataset Collection</option>
        </param>
        <when value="single-read">
            <param format="fastq,fastqsanger,fastq.gz,fastqsanger.gz" label="Single-reads" name="input_fastq" type="data" help="accepted formats: fastq, fastqsanger" />
        </when>
        <when value="paired-end">
            <param format="fastq,fastqsanger,fastq.gz,fastqsanger.gz" label="1st paired-end sequencing dataset" name="input_fastq" type="data" help="accepted formats: fastq, fastqsanger" />
            <param format="fastq,fastqsanger,fastq.gz,fastqsanger.gz" label="2nd paired-end sequencing dataset" name="input2_fastq" type="data" help="accepted formats: fastq, fastqsanger" />
        </when>
        <when value="paired_collection">
            <param name="input_fastq" format="fastq,fastqsanger,fastq.gz,fastqsanger.gz" type="data_collection" collection_type="paired" label="Paired Collection" help="Must be of datatype &quot;fastqsanger&quot; or &quot;fasta&quot;" />
        </when>
    </conditional>
    <param format="fasta" label="Reference genome in fasta format" name="genome" type="data" />
    <param format="txt" label="RepeatMasker description file" name="repeatmasker" type="data" help="see help section"/>
    </inputs>

    <outputs>
        <data format="tabular" name="class_fraction_counts" label="RepEnrich on ${on_string}: class fraction counts" from_work_dir="class_fraction_counts.tsv" />
        <data format="tabular" name="family_fraction_counts" label="RepEnrich on ${on_string}: family fraction counts" from_work_dir="family_fraction_counts.tsv" />
        <data format="tabular" name="fraction_counts" label="RepEnrich on ${on_string}: fraction counts" from_work_dir="fraction_counts.tsv" />
   </outputs>

    <tests>
        <test>
            <param name="seq_method_list" value="single-read"/>
            <param name="input_fastq" value="chrY-500k.R1.fastqsanger.gz" ftype="fastq.gz"/>
            <param name="genome" value="chrY-1-500k.fa" ftype="fasta"/>
            <param name="repeatmasker" value="chrY-1-500k.fa.out" ftype="txt"/>
            <output name="class_fraction_counts" file="chrY_single_class_fraction_counts.tab" ftype="tabular"/>
            <output name="family_fraction_counts" file="chrY_single_family_fraction_counts.tab" ftype="tabular"/>
            <output name="fraction_counts" file="chrY_single_fraction_counts.tab" ftype="tabular"/>
        </test>
         <test>
            <param name="seq_method_list" value="paired-end"/>
            <param name="input_fastq" value="chrY-500k.R1.fastqsanger.gz" ftype="fastq.gz"/>
            <param name="input2_fastq" value="chrY-500k.R2.fastqsanger.gz" ftype="fastq.gz"/>
            <param name="genome" value="chrY-1-500k.fa" ftype="fasta"/>
            <param name="repeatmasker" value="chrY-1-500k.fa.out" ftype="txt"/>
            <output name="class_fraction_counts" file="chrY_paired_class_fraction_counts.tab" ftype="tabular"/>
            <output name="family_fraction_counts" file="chrY_paired_family_fraction_counts.tab" ftype="tabular"/>
            <output name="fraction_counts" file="chrY_paired_fraction_counts.tab" ftype="tabular"/>
        </test>
  </tests>

    <help>

**What it does**

Reads are mapped to the genome using the Bowtie1 aligner. Reads mapping uniquely to the
genome are assigned to subfamilies of repetitive elements based on their degree of overlap
to RepeatMasker annotated genomic instances of each repetitive element subfamily.

Reads mapping to multiple locations are separately mapped to repetitive element assemblies
– referred to as repetitive element psuedogenomes – built from RepeatMasker annotated
genomic instances of repetitive element subfamilies.

RepEnrich then return tables of counts merged from both strategies, that can be further
processed in statistical analysis for differential expression. For detailed information
see the `original publication`_.

.. _original publication: https://bmcgenomics.biomedcentral.com/articles/10.1186/1471-2164-15-583

**Inputs**

*Reference genome* : reference genome in fasta format

*Sequencing dataset*: Single-reads or Paired-end sequencing datasets in fastq format.

*RepeatMasker description file*: a txt repeatmasker file which can be downloaded from
https://www.repeatmasker.org/genomicDatasets/RMGenomicDatasets.html

This file looks like:

<![CDATA[

SW  perc perc perc  query      position in query           matching       repeat              position in  repeat

score  div. del. ins.  sequence    begin     end    (left)    repeat         class/family         begin  end (left)   ID

16  20.2  5.9  0.0  chrM         1211    1261   (18263) +  (TTTTA)n       Simple_repeat            1   54    (0)  84486

13  23.9  2.2  2.2  chrM         2014    2059   (17465) +  (TTA)n         Simple_repeat            1   46    (0)  84487

24  18.8  5.3  2.6  chrM         3924    3999   (15525) +  (TAT)n         Simple_repeat            1   78    (0)  84488

18   4.5  0.0  0.0  chrM         5961    5983   (13541) +  (AT)n          Simple_repeat            1   23    (0)  84489

13  25.9  4.0  4.0  chrM         6247    6320   (13204) +  (ATTTAT)n      Simple_repeat            1   74    (0)  84490

11  14.6  7.5  2.4  chrM         8783    8822   (10702) +  (CTAATT)n      Simple_repeat            1   42    (0)  84491

17  19.0  0.0  8.6  chrM         9064    9126   (10398) +  A-rich         Low_complexity           1   58    (0)  84492

13  21.0  5.9  1.9  chrM        11723   11773    (7751) +  (ATA)n         Simple_repeat            1   53    (0)  84493

66  20.4 12.3 12.3  chrM        12823   13001    (6523) C  LSU-rRNA_Cel   rRNA                   (1) 2431   2253  84494

16  16.6  0.0  2.9  chrM        14361   14396    (5128) +  (ATT)n         Simple_repeat            1   35    (0)  84495

44   2.4  0.0  0.0  chrM        15966   16007    (3517) +  (TA)n          Simple_repeat            1   42    (0)  84496

35   5.3  0.0  0.0  chrM        16559   16597    (2927) +  (AT)n          Simple_repeat            1   39    (0)  84497

36   2.9  0.0  0.0  chrM        16922   16956    (2568) +  (AT)n          Simple_repeat            1   35    (0)  84498

37   0.0  0.0  0.0  chrM        17040   17071    (2453) +  (TA)n          Simple_repeat            1   32    (0)  84499

20   4.3  0.0  0.0  chrM        17417   17440    (2084) +  (T)n           Simple_repeat            1   24    (0)  84500

31   6.9  6.3  1.5  chrM        17451   17513    (2011) +  (TA)n          Simple_repeat            1   66    (0)  84501

26  17.0  0.0  0.0  chrM        19469   19514      (10) +  A-rich         Low_complexity           1   46    (0)  84502

]]>

Users may filter this file so that it contains only desired items (for instance only satellites, repeats and transposons)
 
**Outputs**

(1) Fraction counts, (2) Family fraction counts and (3) Class fraction counts are returned
in tabular format for further statistical tests, differential expression analysis or graphics.

**RepEnrich**

.. class:: warningmark

Earlier versions of the RepEnrich.py and RepEnrich_setpup.py scripts of this galaxy wrapper
were directly derived from the `nskvir/RepEnrich GitHub repository`_ which is not maintained
anymore.

Starting from 2024, python codes were extensively rewritten for clarity, maintenance and
optimization and we now refer exclusively to our `GitHub repository`_ for code review.

.. _nskvir/RepEnrich GitHub repository: https://github.com/nskvir/RepEnrich
.. _GitHub repository: https://github.com/ARTbio/tools-artbio/tree/main/tools/repenrich

**Execution time**

.. class:: warningmark

This tool includes time-consuming steps to index the reference genome, index repeat
sequences and to align reads to these indexes.

.. class:: infomark

For more information on the tools, or giving us feedback, please visit our `code repository`_.

.. _code repository: https://github.com/ARTbio/tools-artbio/tree/master/tools/
.. _ARTbio team: http://artbio.fr

    </help>

    <citations>
    <citation type="doi">10.1186/1471-2164-15-583</citation>
  </citations>
</tool>