<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[
export CSP2_DIR=\$PWD;
mkdir -p \$CSP2_DIR/queries \$CSP2_DIR/references;

if [ -n "$query_fasta" ] && [ "$query_fasta" != "None" ]; then
        #for query in $query_fasta:
                        ln -sf ${query} \$CSP2_DIR/queries/${query.element_identifier};
        #end for
        export QUERY_FASTA_ARG="--fasta \$CSP2_DIR/queries";
else
        export QUERY_FASTA_ARG="";
fi;

if [ -n "$query_reads" ] && [ "$query_reads" != "None" ]; then
        #for query in $query_reads:
                ln -sf ${query} \$CSP2_DIR/queries/${query.element_identifier};
        #end for
        export QUERY_READS_ARG="--reads \$CSP2_DIR/queries";
else
        export QUERY_READS_ARG="";
fi;

if [ -n "$ref_fasta" ] && [ "$ref_fasta" != "None" ]; then
        #for ref in $ref_fasta:
                ln -sf ${ref} \$CSP2_DIR/references/${ref.element_identifier};
        #end for
        export REF_FASTA_ARG="--ref_fasta \$CSP2_DIR/references";
else
        export REF_FASTA_ARG="";
fi;

if [ -n "$ref_reads" ] && [ "$ref_reads" != "None" ]; then
        #for ref in $ref_reads:
                ln -sf ${ref} \$CSP2_DIR/references/${ref.element_identifier};
        #end for
        export REF_READS_ARG="--ref_reads \$CSP2_DIR/references";
else
        export REF_READS_ARG="";
fi;

if [ -n "$trim_name" ] && [ "$trim_name" != "None" ]; then
        export TRIM_ARG="--trim_name $trim_name";
else
        export TRIM_ARG="";
fi;

if [ -n "$ref_id" ] && [ "$ref_id" != "None" ]; then
        export REF_ID_ARG="--ref_id $ref_id";
else
        export REF_ID_ARG="";
fi;

if [[ "$rescue" == "true" ]]; then
        export RESCUE_ARG="--rescue";
else
        export RESCUE_ARG="";
fi;

nextflow run ${__tool_directory__}/CSP2/CSP2.nf -profile csp2_galaxy --cores 2 --runmode snp \$QUERY_FASTA_ARG \$REF_FASTA_ARG \$QUERY_READS_ARG \$REF_READS_ARG \$REF_ID_ARG \$TRIM_ARG \$RESCUE_ARG --readext $readext --forward $forward --reverse $reverse --ref_readext $readext --ref_forward $forward --ref_reverse $reverse --min_cov $min_cov --min_iden $min_iden --min_len $min_len --ref_edge $ref_edge --query_edge $query_edge --dwin $dwin --wsnps $wsnps --max_missing $max_missing --n_ref $n_ref --out \$CSP2_DIR/CSP2_SNP_Output > Nextflow_Log.txt 2>&1;
zip -r CSP2_Output.zip CSP2_SNP_Output;
        ]]>
        </command>
        <inputs>
                <param name="query_fasta" type="data" format="fasta" value="" label="Query assemblies" multiple="true" optional="true" />
                <param name="ref_fasta" type="data" format="fasta" value="" label="Reference assemblies" multiple="true" optional="true" />
                <param name="query_reads" type="data" format="fastq,fastq.gz" value="" label="Query reads" multiple="true" optional="true" />
                <param name="ref_reads" type="data" format="fastq,fastq.gz" value="" label="Reference reads" multiple="true" optional="true" />
                <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" />
                <param name="readext" type="text" value="fastq.gz" label="Read extension format (e.g., fastq.gz)" optional="true" />
                <param name="forward" type="text" value="_1.fastq.gz" label="Forward read suffix (e.g. _1.fastq.gz)" optional="true" />
                <param name="reverse" type="text" value="_2.fastq.gz" label="Forward read suffix (e.g. _2.fastq.gz)" optional="true" />
                <param name="trim_name" type="text" value="" label="Text to remove from all file names (e.g., _contigs_skesa)" optional="true" />
                <param name="ref_id" type="text" value="" label="Comma-separated list of desired Reference IDs (e.g., Sample_A,Sample_B)" optional="true" />
                <param name="rescue" type="boolean" value="false" label="Enable SNP edge rescue mode" optional="true" />
                <param name="max_missing" type="float" value="50" label="Maximum percent of isolates allowed to have missing data to retain a SNP" optional="true" />
                <param name="n_ref" type="integer" value="1" label="Number of reference isolates for CSP2 to select" optional="true" />

        </inputs>
        <outputs>
                <data name="raw_mummer" format="tabular" label="Raw MUMmer Output" from_work_dir="CSP2_SNP_Output/Raw_MUMmer_Summary.tsv" />
                <data name="isolate_data" format="tabular" label="Isolate Data" from_work_dir="CSP2_SNP_Output/Isolate_Data.tsv" />
                <data name="nextflow_log" format="txt" label="Nextflow Log" from_work_dir="Nextflow_Log.txt" />
                <data name="csp2_zip" format="zip" label="Zipped Output" from_work_dir="CSP2_Output.zip" />

                <collection name="snp_analysis_results" type="list:dataset" label="SNP Analysis Results by Reference ID">
                        <discover_datasets pattern="CSP2_SNP_Output/SNP_Analysis/*/CSP2_SNP_Pipeline.log" format="txt" />
                        <discover_datasets pattern="CSP2_SNP_Output/SNP_Analysis/*/snplist.txt" format="txt" />
                        <discover_datasets pattern="CSP2_SNP_Output/SNP_Analysis/*/snplist_preserved.txt" format="txt" />
                        <discover_datasets pattern="CSP2_SNP_Output/SNP_Analysis/*/Reference_Screening.tsv" format="tabular" />
                        <discover_datasets pattern="CSP2_SNP_Output/SNP_Analysis/*/Locus_Categories.tsv" format="tabular" />
                        <discover_datasets pattern="CSP2_SNP_Output/SNP_Analysis/*/Query_Coverage.tsv" format="tabular" />
                        <discover_datasets pattern="CSP2_SNP_Output/SNP_Analysis/*/snp_distance_matrix_preserved.tsv" format="tabular" />
                        <discover_datasets pattern="CSP2_SNP_Output/SNP_Analysis/*/snp_distance_matrix.tsv" format="tabular" />
                        <discover_datasets pattern="CSP2_SNP_Output/SNP_Analysis/*/snp_distance_pairwise_preserved.tsv" format="tabular" />
                        <discover_datasets pattern="CSP2_SNP_Output/SNP_Analysis/*/snp_distance_pairwise.tsv" format="tabular" />
                        <discover_datasets pattern="CSP2_SNP_Output/SNP_Analysis/*/snpma_preserved.fasta" format="fasta" />
                        <discover_datasets pattern="CSP2_SNP_Output/SNP_Analysis/*/snpma.fasta" format="fasta" />
                </collection>
        </outputs>
        <tests>
                <test>
                        <param name="query_fasta">
                                <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>
                        <param name="query_reads">
                                <collection type="list">
                                        <element name="Forward" value="reads/Week_42_Reads_1.fq.gz" />
                                        <element name="Reverse" value="reads/Week_42_Reads_2.fq.gz" />
                                </collection>
                        </param>

                        <param name="ref_id" value="Sample_A,Sample_B" />
                        <param name="readext" value="fq.gz" />
                        <param name="forward" value="_1.fq.gz" />
                        <param name="reverse" value="_2.fq.gz" />

                        <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>