<tool id="ampligone" name="AmpliGone" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="23.2">
    <description>Find and remove primers from NGS amplicon reads</description>
    <macros>
        <token name="@TOOL_VERSION@">2.0.1</token>
        <token name="@VERSION_SUFFIX@">0</token>
    </macros>
    <requirements>
        <requirement type="package" version="@TOOL_VERSION@">AmpliGone</requirement>
    </requirements>
    <version_command>ampligone --version</version_command>
    <command detect_errors="exit_code"><![CDATA[
 #import re

 #set $inputs_map = {
  'input': 'reads',
  'reference': 'reference',
  'primers': 'primers'
 }

 #for $key, $short in $inputs_map.items()
  #set $ds = $inputs[$key]
  #set $ext = re.sub("sanger", "", $ds.ext)
  #set $is_gz = str($ds.ext).endswith('.gz') and $ext != 'bam'
  #set $filename = $short + '.' + $ext

  ln -sf '$ds' '$filename' &&
  #silent $inputs_map[$key] = $filename

  #if $key == 'input'
    #set $output_name = 'output.fastq' + ('.gz' if $is_gz else '')
    touch '$cleaned' &&
    ln -sf '$cleaned' $output_name &&
  #end if
 #end for

 #if $inputs.primers.ext == 'fasta' and  $inputs.export_primers == 'yes'
  #set $primer_filename = 'primers.bed'
  touch '$exp_prim' &&
  ln -sf '$exp_prim' $primer_filename &&
 #end if

 ## --- Run the tool using clean and predictable filenames ---
 ampligone 
 ##add input files
  --input '$inputs_map['input']' 
  --reference '$inputs_map['reference']' 
  --primers '$inputs_map['primers']'

 ## Compute options
  --threads "\${GALAXY_SLOTS:-2}"

 ##optional arguments

  #if $opt_args.ampli_type.amplicon_type
    --amplicon-type $opt_args.ampli_type.amplicon_type
  #end if
  #if $opt_args.ampli_type.amplicon_type == 'fragmented'
    --fragment-lookaround-size $opt_args.ampli_type.fragment_lookaround_size 
  #end if
  #if $opt_args.error_rate
    --error-rate $opt_args.error_rate
  #end if

 ##output options
  #if $inputs.primers.ext == 'fasta' and $inputs.export_primers == 'yes'
    --export-primers '$primer_filename'
  #end if

  --output '$output_name'

    ]]></command>
    <inputs>
        <section name="inputs" title="Inputs" expanded="true">
            <param argument="--input" type="data" format="fastqsanger,fastqsanger.gz,bam" label="Input file" help="Input file with reads in FASTQ format."/>
            <param argument="--reference" type="data" format="fasta" label="Reference genome" help="Input Reference genome in FASTA format." />
            <param argument="--primers" type="data" format="fasta,bed" label="Used primer sequences" help="Used primer sequences in FASTA or BED format." />
            <param argument="--export-primers" type="boolean" checked="false" truevalue="yes" falsevalue="no" optional="true" label="Output cut primers coordinates" help="Output BED file with found primer coordinates if they are actually cut from the reads."/>
        </section>

        <section name="opt_args" title="Optional Arguments" expanded="false">
            <conditional name="ampli_type">
                <param argument="--amplicon-type" type="select" label="Define the amplicon-type" help="Define the amplicon-type, either being 'end-to-end', 'end-to-mid', or 'fragmented'. See the docs for more info.">
                    <option value="end-to-end" selected="true">end-to-end</option>
                    <option value="end-to-mid">end-to-mid</option>
                    <option value="fragmented">fragmented</option>
                </param>
                <when value="fragmented">
                    <param argument="--fragment-lookaround-size" type="integer" value="10" optional="true" label="Fragment lookaround size" help="The number of bases to look around a primer-site to consider it part of a fragment." />
                </when>
                <when value="end-to-end"/>
                <when value="end-to-mid"/>
            </conditional>
            <param argument="--error-rate" type="float" min="0" max="1" value="0.1" label="Error rate" help="The maximum allowed error rate for the primer search. Use 0 for exact primer matches." />
        </section>
    </inputs>

    <outputs>
        <data name="cleaned" format="fastqsanger" label="${tool.name} on ${inputs.input.name} ($on_string): Cleaned reads"/>
        <data name="exp_prim" format="bed" label="${tool.name} on ${on_string}: Detected primer coordinates">
            <filter>inputs['primers'].ext == 'fasta' and inputs['export_primers'] is True</filter>
        </data> 
    </outputs>
    <tests>
        <test expect_num_outputs="1">
            <section name="inputs">
                <param name="input" value="sars-cov-2.fastq"/>
                <param name="reference" value="SARS-CoV-2-reference.fasta"/>
                <param name="primers" value="SARS-CoV-2-ARTIC-V5.3.2.scheme.bed" />
            </section>
            <output name="cleaned">
                <assert_contents>
                    <has_text text="@SRR30635841.1"/>
                    <has_text text="@SRR30635841.2"/>
                    <has_text text="@SRR30635841.3"/>
                    <has_text text="@SRR30635841.4"/>
                    <has_text text="@SRR30635841.5"/>
                </assert_contents>  
            </output> 
        </test>
        <test expect_num_outputs="2">
            <section name="inputs">
                <param name="input" value="sars-cov-2.fastq"/>
                <param name="reference" value="SARS-CoV-2-reference.fasta"/>
                <param name="primers" value="ARTIC-V5.3.2.fasta" />
                <param name="export_primers" value="yes"/>
            </section>
            <output name="cleaned">
                <assert_contents>
                    <has_text text="@SRR30635841.1"/>
                    <has_text text="@SRR30635841.2"/>
                    <has_text text="@SRR30635841.3"/>
                    <has_text text="@SRR30635841.4"/>
                    <has_text text="@SRR30635841.5"/>
                </assert_contents>  
            </output> 
            <output name="exp_prim">
                <assert_contents>
                    <has_text text="MN908947.3:6204-6237_LEFT"/>
                    <has_text text="MN908947.3:25744-25777_RIGHT"/>
                </assert_contents>  
            </output>
        </test>
        <test expect_num_outputs="1">
            <section name="inputs">
                <param name="input" value="synthetic.bam"/>
                <param name="reference" value="synthetic.fasta"/>
                <param name="primers" value="synthetic.bed" />
            </section>
            <output name="cleaned">
                <assert_contents>
                    <has_text text="read_number_2_last_120_of_ref"/>
                    <has_text text="read_number_1_first_120_of_ref"/>
                </assert_contents>  
            </output> 
        </test>
    </tests>
    <help><![CDATA[
**AmpliGone**

In contrast to a lot of other primer-removal tools, AmpliGone does not actively look for primer sequences within the NGS reads. When providing BED input, reads are trimmed based on primer sequence coordinates in relation to a given reference sequence. Additionally, AmpliGone is able to compensate for, and therefore properly clean, reads that start or end outside of a primer-region as this is a common occurrence in amplicon-based sequencing data.
AmpliGone works with both reads in FASTQ format, as well as aligned data in BAM-format. However, when data is presented in the BAM-format then only read-data (sequence and quality scores) will be used. Other data present in the BAM-format will not be used in this version of AmpliGone.

Currently, AmpliGone supports Nanopore data and Illumina data. The Illumina platform (NextSeq/MiSeq/HiSeq/other) does not matter.

It is however important that you know the read-length in relation to the amplicon length. AmpliGone expects this information in the form of an 'amplicon-type'.

AmpliGone is build and tested with Nanopore and Illumina data (fastq) in mind and supports 'end-to-end', 'end-to-mid' and 'fragmented' amplicons to be cleaned.


**More Information**  

- **Official Repository**: https://github.com/RIVM-bioinformatics/AmpliGone
- **Extended User Guide**: https://rivm-bioinformatics.github.io/AmpliGone/@TOOL_VERSION@/
  
    ]]></help>
    <citations>
        <citation type="doi">10.5281/zenodo.7684307</citation>
    </citations>
</tool>