<tool id="snp-pipeline" name="CFSAN SNP Pipeline" version="1.0.1">
	<description>Build SNP table in VCF format from fastq collections</description>
    <requirements>
        <requirement type="package">bowtie2</requirement>
        <requirement type="package">smalt</requirement>
        <requirement type="package">samtools</requirement>
        <requirement type="package">picard</requirement>
        <requirement type="package">varscan</requirement>
        <requirement type="package">tabix</requirement>
        <requirement type="package">bgzip</requirement>
        <requirement type="package">fastq-dump</requirement>
        <requirement type="package">biopython</requirement>
        <requirement type="python-module">snp-pipeline</requirement>
    </requirements>
    <command detect_errors="exit_code"><![CDATA[
        cfsan_snp_pipeline $command -i <(
        	$__tool_directory__/snp-wind.py 
        	#for $e in $fastqs
        		-n $e.forward.display_name -f $e.forward.fastq -r $e.reverse.fastq 
        	#end for
        	.
        )
        && cat ./error.log 1>&2
        && source ./snp-unwind.sh
    ]]></command>
    <configfiles>
    	<configfile name="config_file">
    		
    	</configfile>
    </configfiles>
    <inputs>
    	<conditional name="reference">
    		<param name="ref" type="select" label="Use a curated GalaxyTrakr reference, or a reference from your history" help="Choose whether to use one of our references or your own from your history">
    			<option value="curated">Use a GalaxyTraker reference</option>
    			<option value="history">Use a reference from your history</option>
    		</param>
    		<when value="curated">
    			<param name="reference_fasta" 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 name="reference_fasta" type="data" format="fasta" label="Select reference fasta" />
    		</when>
    	</conditional>
<!-- 
    	<param name="fa_vcf" type="select" label="Select FASTA or VCF output for consensus results">
    		<option value="fa">Consensus results in FASTA format</option>
    		<option value="vc">Consensus results in VCF format<option>
    	</param>
 -->
 		<conditional name="input_arrangement">
 			<param name="inp" type="select" label="Input data layout">
 				<option value="manual">Define paired collections of files from your history</option>
 				<option value="collection">Use a paired-end dataset collection</option>
 			</param>
 		</conditional>
    	<repeat name="fastqs" title="FASTQ collections">
    		<param name="forward" type="data" format="fastq,fastqsanger" label="Forward reads" />
    		<param name="reverse" type="data" format="fastq,fastqsanger" label="Reverse reads" />
    	</repeat>
    </inputs>

    <outputs>
    	<data format="txt" label="SNP List" name="snplist" from_work_dir="snplist.txt"/>
<!--     	<conditional name="fasta_vcf"> -->
    		
    		<data format="fasta" label="Consensus base calls" name="confasta" from_work_dir="consensus.fasta"/>
    		<data format="fasta" label="Filtered consensus base calls" name="confastafil" from_work_dir="consensus.fasta"/>
    		<data format="vcf" label="Consensus base calls" name="convcf" from_work_dir="consensus.vcf"/>
    		<data format="vcf" label="Filtered consensus base calls" name="convcffil" from_work_dir="consensus_preserved.vcf"/>
<!--     	</conditional> -->
		<data format="fasta" label="SNP matrix" name="snpma" from_work_dir="snpma.fasta"/>
		<data format="fasta" label="Filtered SNP matrix" name="snpmalfil" from_work_dir="snpma_preserved.fasta"/>
		<data format="vcf" label="SNP matrix" name="snpmav" from_work_dir="snpma.vcf"/>
		<data format="vcf" label="Filtered SNP matrix" name="snpmavfil" from_work_dir="snpma_preserved.vcf"/>
		
		<data format="tsv" label="SNP distance, pairwise" name="snpdi" from_work_dir="snp_distance_pairwise.tsv"/>
		<data format="tsv" label="Filtered SNP distance, pairwise" name="snpdifil" from_work_dir="snp_distance_pairwise_preserved.tsv"/>
		<data format="tsv" label="SNP distance matrix" name="snpdima" from_work_dir="snp_distance_matrix.tsv"/>
		<data format="tsv" label="Filtered SNP distance matrix" name="snpdimafil" from_work_dir="snp_distance_matrix_preserved.tsv"/>
		<data format="fasta" label="Reference SNPs" name="refsnp" from_work_dir="referenceSNP.fasta"/>
		<data format="fasta" label="Filtered reference SNPs" name="refsnpfil" from_work_dir="referenceSNP_preserved.fasta"/>
		<data format="tsv" label="Metrics" name="metrics" from_work_dir="metrics.tsv"/>


    </outputs>
    <help><![CDATA[
<p>
The <b>CFSAN SNP Pipeline</b> is a Python-based system for the production of SNP matrices from sequence data used in the phylogenetic analysis of pathogenic organisms sequenced from samples of interest to food safety.
<p>
The SNP Pipeline was developed by the <b>United States Food and Drug Administration, Center for Food Safety and Applied Nutrition</b>.
<p>
Free software.
Documentation: <a target="_blank" href="http://snp-pipeline.readthedocs.io/en/latest/readme.html">http://snp-pipeline.readthedocs.io/en/latest/readme.html</a>
Source Code: <a target="_blank" href="https://github.com/CFSAN-Biostatistics/snp-pipeline">https://github.com/CFSAN-Biostatistics/snp-pipeline</a>
PyPI Distribution: <a target="_blank" href="https://pypi.python.org/pypi/snp-pipeline">https://pypi.python.org/pypi/snp-pipeline</a>
    ]]></help>
    <citations>
        <citation type="doi">10.7717/peerj-cs.20</citation>
        <citation type="bibtex">
@misc{cfsan-snp-pipeline,
  author = {Steve Davis and James Pettengill and Yan Luo and Justin Payne and Albert Shpuntoff and Rugh Rand and Errol Strain},
  year = {2015},
  title = {CFSAN SNP Pipeline: an automated method for constructing SNP matrices from next-generation sequence data},
  url = {https://doi.org/10.7717/peerj-cs.20},
  journal = {PeerJ Computer Science},
}</citation>
    </citations>
</tool>