<tool id="pneumocat" name="PneumoCaT" version="@VERSION@">
    <description> Pneumococcal Capsular Typing of illumina reads</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <command detect_errors="exit_code">
<![CDATA[

#import os
#import re

#def check_ending($name, $forward_read=True)
    ## Pneumocat needs to have name_1.fastq and name_2.fastq to work
    ## Check for correct ending and change ending if needed

    #if re.search(r'(\.|_)\S*(1|2)*$', $name)
        #if $forward_read
            #return re.sub(r'(\.|_)\S*(1|2)*$', '_R1.fastq', $name)
        #else
            #return re.sub(r'(\.|_)\S*(1|2)*$', '_R2.fastq', $name)
        #end if
    
    #else
        #if $forward_read
            #return '{}_R1.fastq'.format($name)
        #else
            #return '{}_R2.fastq'.format($name)
        #end if
    #end if
#end def


#if $input.type == 'paired'
    #set $initial = re.sub('[^\w_]', '_', os.path.splitext($input.forward.name)[0])
    
    #set $for_input = $check_ending($initial)
    #set $rev_input = $check_ending($initial, forward_read=False)

    ln -s  '$input.forward' ./$for_input &&
    ln -s  '$input.reverse' ./$rev_input &&

#elif $input.type == 'paired_collection'
    #set $initial = re.sub('[^\w_]', '_', os.path.splitext($input.fastq_collection.forward.name)[0])
    
    #set $for_input = $check_ending($initial)
    #set $rev_input = $check_ending($initial, forward_read=False)

    ln -s  '$input.fastq_collection.forward' ./$for_input &&
    ln -s  '$input.fastq_collection.reverse' ./$rev_input &&

#end if

PneumoCaT.py -1 '$for_input' -2 '$rev_input' -o outputs --threads '\${GALAXY_SLOTS:-1}' --cleanup
]]>
    </command>
    <inputs>
        <conditional name="input">
            <param name="type" type="select" label="Sequence Data Type">
                <option value="paired">Paired-end reads (FASTQ)</option>
                <option value="paired_collection">Paired-end reads collection (FASTQ)</option>
            </param>
            <when value="paired">
                <param name="forward"
                    type="data" format="fastq,fastqsanger,fastq.gz,fastqsanger.gz"
                    optional="false"
                    multiple="false"
                    label="Forward reads (FASTQ)"
                    help="Must have ASCII encoded quality scores"
                />
                <param name="reverse"
                    type="data" format="fastq,fastqsanger,fastq.gz,fastqsanger.gz"
                    optional="false"
                    label="Reverse reads (FASTQ)"
                    help="File format must match the Forward FASTQ file"
                />
            </when>
            <when value="paired_collection">
                <param name="fastq_collection"
                    type="data_collection" format="fastq,fastqsanger, fastq.gz, fastqsanger.gz"
                    collection_type="paired"
                    optional="false"
                    label="Paired-end reads collection (FASTQ)"
                />
            </when>
        </conditional>
    </inputs>
    <outputs>
        <data format="txt" name="coverage_summary" from_work_dir="outputs/coverage_summary.txt" label="PneumoCaT Coverage Summary.txt"/>
        <data format="xml" name="results" from_work_dir="outputs/*.results.xml" label="PneumoCaT Results.xml"/>
        <data format="xml" name="specific_results" from_work_dir="outputs/SNP_based_serotyping/*.results.xml" label="PneumoCaT Serotype Distinction.xml"/>
        <data format="txt" name="variant_summary" from_work_dir="outputs/SNP_based_serotyping/variant_summary.yml" label="PneumoCaT Variant Summary.yml"/>
    </outputs>
    <tests>
        <test>
            <conditional name="input">
                <param name="type" value="paired" />
                <param name="forward" value="09N_R1.fastq" />
                <param name="reverse" value="09N_R2.fastq" />
            </conditional>
            <output name="coverage_summary" file="coverage_summary.txt" />
            <output name="results" file="results.xml" />
        </test>
        <test>
            <conditional name="input">
                <param name="type" value="paired_collection" />
                <param name="fastq_collection">
                    <collection type="paired">
                        <element name="forward" value="09N_R1.fastq.gz" ftype="fastq.gz" />
                        <element name="reverse" value="09N_R2.fastq.gz" ftype="fastq.gz" />
                    </collection>
                </param>
            </conditional>
            <output name="coverage_summary" file="coverage_summary.txt" />
            <output name="results" file="results.xml" />
        </test>
    </tests>
    <help>
<![CDATA[
    
PneumoCaT
---------

PneumoCaT (Pneumococcal Capsular Typing) uses a two-step step approach to assign capsular type to
S.pneumoniae genomic data (Illumina). More info can be found at the `PneumoCaT github page <https://github.com/phe-bioinformatics/PneumoCaT>`_

Program Steps
#############

- **Step 1:** Reads from each readset are mapped to capsular locus sequences for all known capsular types using bowtie2

    - This step is considered successful if the readset matches > 90% to one or more capsular locus sequences

        - If only a singular capsular locus is matched, PneumoCaT terminates and reports that as the assigned capsular type
    
        - If more than 1 loci are matched then the tool moves to step 2

- **Step 2:** Variant calling with the capsular type variant database

    - Used to distinguish serotypes within a serogroup/genogroup

Please note PneumoCaT applies a quality metric requiring a mean depth of 20 reads across the mapped sequence
and a minimum depth of 5 reads for mapping. The report will retrun "Failed" if these conditions are not met.

Inputs
######

- **Paired-end Illumina reads** with one of the following example formats is prefered:

    - <name>_1.fastq and <name>_2.fastq

    - <name>_R1.fastq and <name>_R2.fastq

    - <name>_R1.fastqsanger.gz and <name>_R2.fastqsanger.gz

- If the reads are not formatted as above, the wrapper will append _R1.fastq and _R2.fastq to allow function

Outputs
#######

Please see `**PneumoCaTs interpreting results document** <https://github.com/phe-bioinformatics/PneumoCaT/blob/master/Documentation/InterpretingResults.pdf>`_
for full up-to-date information on how to interpret PneumoCaT results.

Galaxy will output 4 results running PneumoCaT with 2 of the results only appearing if **Step 2** variant calling is done

**1. Coverage Summary.txt** -- Always output unless fails --

**2. Results.xml** -- Always output unless fails --

**3. Serotype distinction.xml** -- Step 2 Required --

**4. Variant Summary.txt** -- Step 2 Required --


**Note** - Galaxy will always output files 3 and 4 even if step 2 is not done. In these cases, the files will have no data.

]]>
    </help>
    <expand macro="citations" />
</tool>