view seqkit_split2.xml @ 1:911de3a36b31 draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/seqkit commit 66b393a7118c81d86d0fd80780d2bd551c18f3f0

<tool id="seqkit_split2" name="Seqkit Split2" version="@TOOL_VERSION@+galaxy1" profile="@PROFILE@">
    <description>Split sequences into files by part size, number of parts, or length</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="bio_tools"/>
    <expand macro="requirements"/>
    <command detect_errors="exit_code"><![CDATA[
    #import re
    mkdir -p out &&

    ## The preprocessing steps below are adapted from the cutadapt.xml tool wrapper.
    ## Set things up for handling inputs and outputs in single- vs paired-end modes   
    #set input_type = str($input_file_type.type)
    #if $input_type == 'single':
        #set paired = False
    #else:
        #set paired = True
    #end if
  
    #if $input_type == 'paired_collection'
        #set input_1 = $input_file_type.input_1.forward
        #set input_2 = $input_file_type.input_1.reverse
        #set read1 = re.sub('[^\w\-\s]', '_', str($input_file_type.input_1.name)) + "_1"
        #set read2 = re.sub('[^\w\-\s]', '_', str($input_file_type.input_1.name)) + "_2"
    #else
        #set input_1 = $input_file_type.input_1
        #set read1 = re.sub('[^\w\-\s]', '_', str($input_file_type.input_1.element_identifier))
    #end if

    #if $input_1.is_of_type("fastq", "fastq.gz"):
        #set ext = ".fastqsanger"
    #else
        #set ext = ".fasta"
    #end if
    #if $input_1.ext.endswith(".gz"):
        #set ext=ext+".gz"
    #end if

    #set read1 = $read1 + $ext

    #if $paired:
        #if $input_2.is_of_type("fastq", "fastq.gz"):
            #set ext2 = ".fastqsanger"
        #else
            #set ext2 = ".fasta"
        #end if
        #if $input_2.ext.endswith(".gz"):
            #set ext2=ext2+".gz"
        #end if
        #set read2 = $read2 + $ext2
    #end if
    
    ## Link in the input files
    ln -fs '$input_1' '$read1' &&
    #if $paired:
        ln -fs '$input_2' '$read2' &&
    #end if

    seqkit split2
    #if $paired:
        -1 '$read1'
        -2 '$read2'
    #else:
        '$read1'
    #end if
    #if str($split_type.split_selector) == 'by_part':
        -p $split_type.by_part
        #if $paired:
            --by-part-prefix "seqkit_split2_R{read}_"
        #end if
    #else if str($split_type.split_selector) == 'by_size':
        -s $split_type.by_size
        #if $paired:
            --by-size-prefix string "seqkit_split2_R{read}_"
        #end if
    #else if str($split_type.split_selector) == 'by_length':
        -l $split_type.by_length
    #end if
    -o seqkit_split2
    -O out
    -j "\${GALAXY_SLOTS:-4}" 
    #if $paired:
        && (find out/ -type f -name "seqkit_split2_*.*" | while read -r file; do mv "\$file" "\$(echo \$file | sed -E 's/(seqkit_split2)_(R1|R2)_([0-9]+)(\..+)/\1_\3_\2\4/' | sed -E 's/_R1/_forward/; s/_R2/_reverse/')"; done)
    #end if
    ]]></command>
    <inputs>
        <conditional name="input_file_type">
            <param name="type" type="select" label="Single-end or Paired-end reads?">
                <option value="single">Single-end</option>
                <option value="paired_collection">Paired-end Collection</option>
            </param>
            <when value="single">
                <param name="input_1" type="data" format="@FASTQ_TYPES@" label="Input FASTQ/A file" help="Select a single FASTA or FASTQ file (gzipped or uncompressed)"/>
            </when>
            <when value="paired_collection">
                <param name="input_1" format="@FASTQ_TYPES@" type="data_collection" collection_type="paired" label="Paired Collection" help="Should be of datatype &quot;fastq.gz&quot; or &quot;fasta&quot;" />
            </when>
        </conditional>
        <conditional name="split_type">
            <param name="split_selector" type="select" label="Split sequences by">
                <option value="by_part" selected="true">Number of parts</option>
                <option value="by_size">Number of sequences per part</option>
                <option value="by_length">Length of sequences</option>
            </param>
            <when value="by_part">
                <param name="by_part" type="integer" value="" min="1" label="Number of parts" help="Split sequences into N parts using round-robin distribution." />
            </when>
            <when value="by_size">
                <param name="by_size" type="integer" value="" min="1" label="Number of sequences per part" help="Split sequences into parts with N sequences each." />
            </when>
            <when value="by_length">
                <param name="by_length" type="text" value="" label="Chunk size" help="Split sequences into chunks of >=N bases. Supports K/M/G suffix (e.g., 10K, 1M)">
                    <validator type="regex" message="Invalid characters in field">^[0-9KMG]+$</validator>
                </param>
            </when>
        </conditional>
    </inputs>
    <outputs>
        <collection name="outputs_files" type="list" label="${tool.name} on ${on_string}: Splitted files">
            <discover_datasets pattern="(?P&lt;designation&gt;seqkit_split2\.part_\d+)\.(?P&lt;ext&gt;.+)" directory="out"/>
            <filter>input_file_type['type'] == 'single' </filter>
        </collection>
        <collection name="outputs_paired_files" type="list:paired" label="${tool.name} on ${on_string}: Paired-End Splitted files">
            <filter>input_file_type['type'] == 'paired_collection' </filter>
                <discover_datasets pattern="(?P&lt;identifier_0&gt;.+)_(?P&lt;identifier_1&gt;forward|reverse)\.(?P&lt;ext&gt;.+)" directory="out"/>
        </collection>
    </outputs>
    <tests>
        <!-- Test 01: for Seqkit Split with Single End FASTQ file; splitting by parts -->
        <test expect_num_outputs="1">
            <conditional name="input_file_type">
                <param name="type" value="single"/>
                <param name="input_1" value="reads_1.fq.gz"/>
            </conditional>
            <conditional name="split_type">
                <param name="split_selector" value="by_part"/>
                <param name="by_part" value="2"/>
            </conditional>
            <output_collection name="outputs_files" type="list" count="2">
                <element name="seqkit_split2.part_001" ftype="fastqsanger.gz">
                    <assert_contents>
                        <has_n_lines n="4958"/>
                    </assert_contents>
                </element>
                <element name="seqkit_split2.part_002" ftype="fastqsanger.gz">
                    <assert_contents>
                        <has_n_lines n="4949"/>
                    </assert_contents>
                </element>
            </output_collection>
        </test>
        
        <!-- Test 02: for Seqkit Split with Paired FASTQ Collection; splitting by parts -->
        <test expect_num_outputs="1">
            <conditional name="input_file_type">
                <param name="type" value="paired_collection"/>
                <param name="input_1">
                    <collection type="paired">
                        <element name="forward" ftype="fastq.gz" value="reads_1.fq.gz"/>
                        <element name="reverse" ftype="fastq.gz" value="reads_2.fq.gz"/>
                    </collection>
                </param>
            </conditional>
            <conditional name="split_type">
                <param name="split_selector" value="by_part"/>
                <param name="by_part" value="2"/>
            </conditional>
            <output_collection name="outputs_paired_files" type="list:paired" count="2">
                <element name="seqkit_split2_001">
                    <element name="forward" ftype="fastqsanger.gz">
                        <assert_contents>
                            <has_n_lines n="4958"/>
                        </assert_contents>
                    </element>
                    <element name="reverse" ftype="fastqsanger.gz">
                        <assert_contents>
                            <has_n_lines n="3792"/>
                        </assert_contents>
                    </element>    
                </element>
                <element name="seqkit_split2_002">
                    <element name="forward" ftype="fastqsanger.gz">
                        <assert_contents>
                            <has_n_lines n="4949"/>
                        </assert_contents>
                    </element>
                    <element name="reverse" ftype="fastqsanger.gz">
                        <assert_contents>
                            <has_n_lines n="3657"/>
                        </assert_contents>  
                    </element>
                </element>
            </output_collection>
        </test>

        <!-- Test 03: for Seqkit Split with Single End FASTA file; splitting by parts -->
        <test expect_num_outputs="1">
            <conditional name="input_file_type">
                <param name="type" value="single"/>
                <param name="input_1" value="hairpin.fa.gz"/>
            </conditional>
            <conditional name="split_type">
                <param name="split_selector" value="by_part"/>
                <param name="by_part" value="2"/>
            </conditional>
            <output_collection name="outputs_files" type="list" count="2">
                <element name="seqkit_split2.part_001" ftype="fasta.gz">
                    <assert_contents>
                        <has_n_lines n="2988"/>
                    </assert_contents>
                </element>
                <element name="seqkit_split2.part_002" ftype="fasta.gz">
                    <assert_contents>
                        <has_n_lines n="2987"/>
                    </assert_contents>
                </element>
            </output_collection>
        </test>

        <!-- Test 04: for Seqkit Split with Single End FASTA file; splitting by size -->
        <test expect_num_outputs="1">
            <conditional name="input_file_type">
                <param name="type" value="single"/>
                <param name="input_1" value="hairpin.fa.gz"/>
            </conditional>
            <conditional name="split_type">
                <param name="split_selector" value="by_size"/>
                <param name="by_size" value="200"/>
            </conditional>
            <output_collection name="outputs_files" type="list" count="25">
                <element name="seqkit_split2.part_001" ftype="fasta.gz">
                    <assert_contents>
                        <has_n_lines n="224"/>
                    </assert_contents>
                </element>
                <element name="seqkit_split2.part_002" ftype="fasta.gz">
                    <assert_contents>
                        <has_n_lines n="281"/>
                    </assert_contents>
                </element>
            </output_collection>
        </test>

        <!-- Test 05: for Seqkit Split with Single End FASTA file; splitting by length -->
        <test expect_num_outputs="1">
            <conditional name="input_file_type">
                <param name="type" value="single"/>
                <param name="input_1" value="hairpin.fa.gz"/>
            </conditional>
            <conditional name="split_type">
                <param name="split_selector" value="by_length"/>
                <param name="by_length" value="50K"/>
            </conditional>
            <output_collection name="outputs_files" type="list" count="10">
                <element name="seqkit_split2.part_001" ftype="fasta.gz">
                    <assert_contents>
                        <has_n_lines n="642"/>
                    </assert_contents>
                </element>
                <element name="seqkit_split2.part_002" ftype="fasta.gz">
                    <assert_contents>
                        <has_n_lines n="589"/>
                    </assert_contents>
                </element>
            </output_collection>
        </test>
    </tests>
    <help><![CDATA[

**Seqkit Split2**

This tool splits FASTA or FASTQ files (single-end or paired-end) into multiple files based on the number of parts, sequences per part, or sequence length. It supports low memory usage and fast processing.

**Input type**: Choose between single-end FASTA/FASTQ or paired-end FASTQ files.

**Split sequences by**:
  - **Number of parts**: Split into N parts using round-robin distribution.
  - **Number of sequences per part**: Split into parts with N sequences each.
  - **Length of sequences**: Split into chunks of >=N bases (supports K/M/G suffix, e.g., 10K, 1M).

**Outputs**

- A collection of split FASTA/FASTQ files

For more details, see the Seqkit Split2 documentation_

.. _documentation: https://bioinf.shenwei.me/seqkit/usage/#split2

    ]]></help>
        <expand macro="citations"/>
        <creator>
            <person givenName="Saim" familyName="Momin" url="https://github.com/SaimMomin12" identifier="https://orcid.org/0009-0003-9935-828X"/>
            <organization name="Galaxy Europe" url="https://galaxyproject.org/eu/"/>
    </creator>
</tool>