<tool id="csp2-snp" name="CSP2 (SNP Pipeline Mode)" version="0.9.7_Dev21">
        <description>Run SNP Pipeline analysis on isolates using one or more references.</description>
        <requirements>
                <requirement type="package" version="24.10.1">nextflow</requirement>
                <requirement type="package" version="1.5.8">micromamba</requirement>
        </requirements>
        <version_command>nextflow -version</version_command>
        <command detect_errors="aggressive"><![CDATA[
mkdir -p queries references
#set readext=""
#for $reads in $query.coll
#if $hasattr($reads, "is_of_type") and $reads.is_of_type("fasta")
         && ln -sf '${reads}' 'queries/${reads.element_identifier}.fasta'
#else if $reads.forward.is_of_type("fastq.gz","fastqsanger.gz")
         #set readext="fastq.gz"
         && ln -sf '${reads.forward}' 'queries/${reads.forward.element_identifier}_1.fastq.gz'
         && ln -sf '${reads.reverse}' 'queries/${reads.reverse.element_identifier}_2.fastq.gz'
#else if $reads.forward.is_of_type("fastq.bz2", "fastqsanger.bz2")
         #set readext="fastq.bz2"
         && ln -sf '${reads.forward}' 'queries/${reads.forward.element_identifier}_1.fastq.bz2'
         && ln -sf '${reads.reverse}' 'queries/${reads.reverse.element_identifier}_2.fastq.bz2'
#else 
         #set readext="fastq"
         && ln -sf '${reads.forward}' 'queries/${reads.forward.element_identifier}_1.fastq'
         && ln -sf '${reads.reverse}' 'queries/${reads.reverse.element_identifier}_2.fastq'
#end if
#end for
        && echo "*** Files in queries directory: ***"
        && ln -sf '$source.reference' 'references/${source.reference.element_identifier}.fasta'
        && nextflow run 
        ${__tool_directory__}/CSP2/CSP2.nf -profile csp2_galaxy 
        --runmode snp 
        #if $query.query_select == 'reads'
        --reads queries
        --readext $readext 
        --forward "_1.${readext}"
        --reverse "_2.${readext}"
        #else
        --fasta queries
        #end if
        --ref_fasta 'references/${source.reference.element_identifier}.fasta'
        --min_cov $opt.min_cov 
        --min_iden $opt.min_iden 
        --min_len $opt.min_len 
        --ref_edge $opt.ref_edge 
        --query_edge $opt.query_edge 
        --dwin $opt.dwin 
        --wsnps $opt.wsnps 
        --out CSP2_SNP_Output
        && echo "*** Files in output directory: ***"
        && ls -lah CSP2_SNP_Output
        && echo "*** Nextflow log follows: ***"
        && cat .nextflow.log
]]>
        </command>
        <inputs>
                <conditional name="source">
                        <param name="source_select" type="select" label="Use a curated GalaxyTrakr reference or a reference from your history">
                                <option value="curated">Use a GalaxyTrakr reference</option>
                                <option value="history">Use a reference from your history</option>
                        </param>
                        <when value="curated">
                                <param name="reference" type="select" label="Select reference fasta">
                                        <options from_data_table="all_fasta">
                                                <filter type="sort_by" column="2"/>
                                                <validator type="no_options" message="No assemblies are available for the selected input dataset"/>
                                        </options>
                                </param>
                        </when>
                        <when value="history">
                                <param type="data" name="reference" format="fasta" label="Select reference FASTA"/>
                        </when>
                </conditional>
                <conditional name="query">
                        <param name="query_select" type="select" label="Screen a list of paired-reads or a list of assemblies">
                                <option value="reads">Screen a list of paired reads</option>
                                <option value="assemblies">Screen a list of assemblies</option>
                        </param>
                        <when value="reads">
                                <param label="Paired reads" name="coll" type="data_collection" format="fastq,fastqsanger,fastq.gz,fastqsanger.gz,fastq.bz2,fastqsanger.bz2" collection_type="list:paired" />
                        </when>
                        <when value="assemblies">
                                <param label="Assemblies" name="coll" type="data_collection" format="fasta" collection_type="list" />
                        </when>
                </conditional>
                <section name="opt" title="Advanced options...">
                        <param name="min_cov" type="float" value="85" label="Minimum reference genome coverage to proceed with distance estimation" optional="true" />
                        <param name="min_iden" type="float" value="99" label="Minimum alignment percent identity to detect SNPs" optional="true" />
                        <param name="min_len" type="integer" value="500" label="Minimum alignment length to detect SNPs" optional="true" />
                        <param name="ref_edge" type="integer" value="150" label="Prune SNPs within this many bases of reference contig edge" optional="true" />
                        <param name="query_edge" type="integer" value="150" label="Prune SNPs within this many bases of query contig edge" optional="true" />
                        <param name="dwin" type="text" value="1000,125,15" label="Comma-separated set of window sizes for SNP density filtration (Set to 0 to disable density filtration)" optional="true" />
                        <param name="wsnps" type="text" value="3,2,1" label="Comma-separated list of maximum SNP counts per density window" optional="true" />
                </section>
        </inputs>
        <outputs>
                <!-- <data name="nextflow_log" format="txt" label="Nextflow Log" from_work_dir="Nextflow_Log.txt" /> -->
                <data name="isolate_data" format="tabular" label="Isolate Data" from_work_dir="CSP2_SNP_Output/Isolate_Data.tsv" />
                <data name="raw_mummer" format="tabular" label="Raw MUMmer Output" from_work_dir="CSP2_SNP_Output/Raw_MUMmer_Summary.tsv" />
                <!-- <data name="csp2_zip" format="zip" label="Zipped Output" from_work_dir="CSP2_Output.zip" /> -->
                <collection name="reference_results" type="list:list">
                        <discover_datasets pattern="(?P&lt;name&gt;.+)/CSP2_SNP_Pipeline\.log" format="txt" visible="true" directory="./CSP2_SNP_Output/SNP_Analysis" />
                        <discover_datasets pattern="(?P&lt;name&gt;.+)/Reference_Screening\.tsv" format="tabular" visible="true" directory="./CSP2_SNP_Output/SNP_Analysis" />
                        <discover_datasets pattern="(?P&lt;name&gt;.+)/snp_distance_matrix_preserved\.tsv" format="tabular" visible="true" directory="./CSP2_SNP_Output/SNP_Analysis" />
                        <discover_datasets pattern="(?P&lt;name&gt;.+)/snp_distance_pairwise_preserved\.tsv" format="tabular" visible="true" directory="./CSP2_SNP_Output/SNP_Analysis" />
                        <discover_datasets pattern="(?P&lt;name&gt;.+)/snpma_preserved\.fasta" format="fasta" visible="true" directory="./CSP2_SNP_Output/SNP_Analysis" />
                </collection>
        </outputs>
        <tests>
                <test>
                        <param name="source_select" value="history" />
                        <param name="reference" value="assemblies/Sample_A.fasta" />
                        <param name="query_select" value="assemblies" />
                        <param name="coll">
                                <collection type="list">
                                        <!-- <element name="Sample_A" value="assemblies/Sample_A.fasta" /> -->
                                        <element name="Sample_B" value="assemblies/Sample_B.fasta" />
                                        <element name="Sample_C" value="assemblies/Sample_C.fasta" />
                                        <element name="Sample_D" value="assemblies/Sample_D.fasta" />
                                        <element name="Sample_E" value="assemblies/Sample_E.fasta" />
                                        <element name="Sample_F" value="assemblies/Sample_F.fasta" />
                                        <element name="Sample_G" value="assemblies/Sample_G.fasta" />
                                        <element name="Sample_H" value="assemblies/Sample_H.fasta" />
                                        <element name="Sample_I" value="assemblies/Sample_I.fasta" />
                                        <element name="Sample_J" value="assemblies/Sample_J.fasta" />
                                        <element name="Sample_K" value="assemblies/Sample_K.fasta" />
                                        <element name="Sample_L" value="assemblies/Sample_L.fasta" />
                                        <element name="Sample_M" value="assemblies/Sample_M.fasta" />
                                        <element name="Sample_N" value="assemblies/Sample_N.fasta" />
                                        <element name="Sample_O" value="assemblies/Sample_O.fasta" />
                                </collection>
                        </param>

                        <output name="isolate_data" value="Isolate_Data.tsv" />
                </test>
                <test>
                        <param name="source_select" value="history" />
                        <param name="reference" value="assemblies/Sample_A.fasta" ftype="fasta" />
                        <param name="query_select" value="reads" />
                        <param name="coll">
                                <collection type="list:paired">
                                        <element name="Sample_A">
                                                <collection type="paired">
                                                        <element name="forward" value="reads/Week_42_Reads_1.fq.gz" ftype="fastqsanger.gz" />
                                                        <element name="reverse" value="reads/Week_42_Reads_2.fq.gz" ftype="fastqsanger.gz" />
                                                </collection>
                                        </element>
                                </collection>
                        </param>
                        <output name="screening_results" value="Screening_Results.tsv" />
                        <output name="isolate_data" value="Isolate_Data.tsv" />
                </test>
        </tests>
        <help>
        This tool takes query assemblies and reference assemblies and calculates the pairwise distance between each query/reference combination. If no reference is provided, all queries are compared to all other queries.
        </help>
        <citations>
                <citation type="doi">10.XXXX/placeholder.doi</citation>
                <citation type="bibtex">@article{example2024,title={CFSAN SNP Pipeline 2 (CSP2): a pipeline for fast and accurate SNP distance estimation from bacterial genome assemblies.},author={Doe, John and Smith, Jane},journal={Submitted},year={2024}}
                </citation>
        </citations>
</tool>