<?xml version='1.0' encoding='utf-8'?>
<tool id="antismash" name="Antismash" version="4.1" profile="17.01">
    <description>allows the genome-wide identification, annotation and analysis of secondary metabolite biosynthesis gene clusters</description>
    <requirements>
        <requirement type="package" version="4.1">antismash</requirement>
    </requirements>
    <version_command>antismash --version</version_command>
    <command detect_errors="aggressive">
<![CDATA[
        #import os, glob
        #set $htmloutputfolder = $html.files_path
        #if str($infile.ext) == 'genbank':
            #set $file_extension = 'gb'
        #else:
            #set $file_extension = $infile.ext
        #end if

        ln -s '$infile' input_tempfile.$file_extension &&

        ## create html folder
        mkdir -p $htmloutputfolder &&

        antismash
            --cpus "\${GALAXY_SLOTS:-12}"
            --taxon '${taxon}'
            --input-type '${input_type}'

            ${clusterblast}
            ${subclusterblast}
            ${smcogs}
            ${inclusive}
            ${borderpredict}
            ${tta}
            ${asf}
            ${full_hmmer}

            input_tempfile.$file_extension &&

        ## copy all content to html folder
        cp input_tempfile/index.html '${html}' 2> /dev/null &&
        cp -r input_tempfile/* '${htmloutputfolder}'

]]>
    </command>
    <inputs>
        <param name="infile" type="data" format="genbank,fasta,embl" label="Sequence file in GenBank,EMBL or FASTA format"/>

        <param argument="--taxon" type="select" label="Origin of DNA">
            <option value="bacteria" selected="True">Bacteria</option>
            <option value="fungi">Fungi</option>
        </param>

        <param argument="--input_type" type="select" label="Origin of DNA">
            <option value="nucl" selected="True">Nucleotide</option>
            <option value="prot">Amino-acid</option>
        </param>

        <param argument="--clusterblast" type="boolean" truevalue="--clusterblast" falsevalue="" checked="False"
               label="BLAST identified clusters against known clusters"
               help="Compare identified clusters against a database of antiSMASH-predicted clusters." />
        <param argument="--subclusterblast" type="boolean" truevalue="--subclusterblast" falsevalue="" checked="True"
               label="Subcluster BLAST analysis"
               help="Compare identified clusters against known subclusters responsible for synthesising precursors." />
        <param argument="--knownclusterblast" type="boolean" truevalue="--knownclusterblast" falsevalue="" checked="True"
               label="KnowCluster BLAST analysis"
               help="Compare identified clusters against known gene clusters from the MIBiG database."/>
        <param argument="--smcogs" type="boolean" checked="True" truevalue="--smcogs" falsevalue=""
               label="Analysis of secondary metabolism gene families (smCOGs)"
               help="Look for sec. met. clusters of orthologous groups."/>
        <param argument="--inclusive" type="boolean" truevalue="--inclusive" falsevalue="" checked="False"
               label="Inclusive ClusterFinder algorithm"
               help="Use inclusive ClusterFinder algorithm for additional cluster detection."/>
        <param argument="--borderpredict" type="boolean" truevalue="--borderpredict" falsevalue="" checked="False"
               label="Predict gene cluster borders with ClusterFinder"
               help="Use ClusterFinder algorithm to predict gene cluster borders."/>
        <param argument="--asf" type="boolean" truevalue="--asf" falsevalue="" checked="True"
               label="Run active site finder module" />
        <param argument="--tta" type="boolean" truevalue="--tta" falsevalue="" checked="False"
               label="Run TTA codon detection module" />
        <param argument="--full_hmmer" type="boolean" truevalue="--full-hmmer" falsevalue="" checked="False"
               label="Run a whole-genome Pfam analysis" />

        <param name="outputs" type="select" multiple="true" label="Outputs">
            <option value="html" selected="True">HTML file</option>
            <option value="all">All results</option>
            <option value="embl">EMBL files</option>
            <option value="gb">GenBank files</option>
            <option value="genecluster_tabular">Gene clusters</option>
        </param>

    </inputs>
    <outputs>
        <collection type="list" name="genecluster_tabular" label="${tool.name} on ${on_string} (Gene Cluster)">
            <discover_datasets pattern="(?P&lt;designation&gt;.*)\.txt" directory="input_tempfile" ext="txt" visible="false" />
            <filter>'genecluster_tabular' in outputs</filter>
        </collection>
        <collection name="genbank" type="list" label="${tool.name} on ${on_string} (GenBank)">
            <discover_datasets pattern="(?P&lt;designation&gt;.*)\.gbk" directory="input_tempfile" ext="genbank" visible="false" />
            <filter>'gb' in outputs</filter>
        </collection>
        <collection name="embl" type="list" label="${tool.name} on ${on_string} (EMBL)">
            <discover_datasets pattern="(?P&lt;designation&gt;.*)\.gbk" directory="input_tempfile" ext="embl" visible="false" />
            <filter>'embl' in outputs</filter>
        </collection>
        <collection name="archive" type="list" label="${tool.name} on ${on_string} (all files compressed)">
            <discover_datasets pattern="(?P&lt;designation&gt;.*)\.zip" directory="input_tempfile" ext="zip" visible="false" />
            <filter>'all' in outputs</filter>
        </collection>
        <data format="html" name="html" label="${tool.name} on ${on_string} (html report)" />
    </outputs>
    <tests>
        <test>
            <param name="infile" value="sequence.fasta"/>
            <output name="html" file="index.html"/>
        </test>
        <test>
            <param name="infile" value="sequence.gb"/>
            <param name="outputs" value="html,gb"/>
            <output_collection name="genbank" type="list">
                <element name="ARBH01000003.1.cluster001" file="ARBH01000003.1.cluster001" ftype="genbank" compare="sim_size" />
                <element name="ARBH01000003.1.final" file="ARBH01000003.1.final" ftype="genbank"/>
            </output_collection>
            <output name="html" file="index.2.html"/>
        </test>
    </tests>
    <help>
<![CDATA[

**What it does**

AntiSMASH allows the rapid genome-wide identification, annotation and analysis of secondary metabolite biosynthesis gene clusters in bacterial and fungal genomes.
It integrates and cross-links with a large number of in silico secondary metabolite analysis tools that have been published earlier.

antiSMASH is powered by several open source tools: NCBI BLAST+, HMMer 3, Muscle 3, Glimmer 3, FastTree, TreeGraph 2, Indigo-depict, PySVG and JQuery SVG.

**Input**

The ideal input for antiSMASH is an annotated nucleotide file in Genbank format or EMBL format.
You can either upload a GenBank/EMBL file manually, or simply enter the GenBank/RefSeq accession number of your sequence for antiSMASH to upload it.
If no annotation is available, we recommend running your sequence through an annotation pipeline like RAST to obtain GBK/EMBL files with high-quality annotations.

Alternatively, you can provide a FASTA file containing a single sequence. antiSMASH will generate a preliminary annotation using Prodigal, and use that to run the rest of the analysis.
You can also provide gene annotations in GFF3 foramt. Input files should be properly formatted.
If you are creating your GBK/EMBL/FASTA file manually, be sure to do so in a plain text editor like Notepad or Emacs, and saving your files as "All files (.)", ending with the correct extension (for example ".fasta", ".gbk", or ".embl".

There are several optional analyses that may or may not be run on your sequence. Highly recommended is the Gene Cluster Blast Comparative Analysis, which runs BlastP using each amino acid sequence from a detected gene cluster as a query on a large database of predicted protein sequences from secondary metabolite biosynthetic gene clusters, and pools the results to identify the gene clusters that are most homologous to the gene cluster that was detected in your query nucleotide sequence.
This analysis is selected by default

Also available is the analysis of secondary metabolism gene families (smCOGs). This analysis attempts to allocate each gene in the detected gene clusters to a secondary metabolism-specific gene family using profile hidden Markov models specific for the conserved sequence region characteristic of this family.
Additionally, a phylogenetic tree is constructed of each gene together with the (max. 100) sequences of the smCOG seed alignment. This analysis is selected by default

**Ouput**

The output of the antiSMASH analysis pipeline is organized in an interactive HTML page with SVG graphics, and different parts of the analysis are displayed in different panels for every gene cluster

In the upper right, a small list of buttons offers further functionality. The house-shaped button will get you back on the antiSMASH start page.
The question-mark button will get you to this help page. The exclamation-mark button leads to a page explaining about antiSMASH.
The downward-pointing arrow will open a menu offering to download the complete set of results from the antiSMASH run, a summary Excel file and to the summary EMBL/GenBank output file.
The EMBL/GenBank file can be viewed in a genome browser such as Artemis.

]]>
    </help>
    <citations>
        <citation type="doi">10.1093/nar/gkv437</citation>
    </citations>
</tool>