<tool id="sistr_cmd" name="sistr_cmd" version="0.3.4">
  <description>
    Salmonella In Silico Typing Resource commandline tool for serovar prediction
  </description>
  <requirements>
    <requirement type="package" version="0.3.4">sistr_cmd</requirement>
  </requirements>
  <stdio>
    <exit_code range="1:" />
  </stdio>
  <command><![CDATA[
  sistr 
    #for $fasta in $input_fastas
      -i '$fasta' '${$fasta.name.replace("." + $fasta.ext, "")}'
    #end for
    -f $output_format
    #if $output_format == "tab"
      -o sistr-report.tab
    #elif $output_format == "csv"
      -o sistr-report.csv
    #elif $output_format == "json"
      -o sistr-report.json
    #end if
    -p $cgmlst_profiles
    -n $novel_alleles
    -a $alleles_output
    $use_full_cgmlst_db
    $no_cgmlst
    $run_mash
    $qc
    --threads "\${GALAXY_SLOTS:-1}"
    -T "\${TMPDIR:-/tmp}"
    $keep_tmp
    $verbosity
  ]]></command>
  <inputs>
    <param 
      name="input_fastas" 
      type="data" 
      label="Input Genome(s)" 
      optional="false" 
      multiple="true"
      format="fasta"
      />
    <param 
      name="output_format" 
      type="select" 
      label="Results output format"
      multiple="false">
      <option value="tab" selected="true">
        Tabular (tab-delimited values)
      </option>
      <option value="csv">
        CSV (Comma Separated Values)
      </option>
      <option value="json">
        JSON (JavaScript Object Notation)
      </option>
    </param>
    <param 
      name="use_full_cgmlst_db"
      type="boolean"
      checked="false"
      truevalue="--use-full-cgmlst-db"
      falsevalue=""
      label="Use full cgMLST database for serovar prediction. About 10X slower with equivalent results to reduced centroid allele database."
      />
    <param 
      name="run_mash"
      type="boolean"
      checked="true"
      truevalue="--run-mash"
      falsevalue=""
      label="Run Mash MinHash-based serovar prediction"
      />
    <param 
      name="no_cgmlst"
      type="boolean"
      checked="false"
      truevalue="--no-cgmlst"
      falsevalue=""
      label="Skip running cgMLST-based serovar prediction"
      />
    <param 
      name="qc"
      type="boolean"
      checked="true"
      truevalue="--qc"
      falsevalue=""
      label="Basic QC of results"
      />
    <param 
      name="keep_tmp"
      type="boolean"
      checked="false"
      falsevalue=""
      truevalue="--keep-tmp"
      label="Keep temporary analysis directory"
      />
    <param 
      name="verbosity"
      type="select" 
      label="Logging verbosity">
      <option value="">
        Error messages only
      </option>
      <option value="-v">
        Show warning messages
      </option>
      <option value="-vv" selected="true">
        Show info messages
      </option>
      <option value="-vvv">
        Show debug messages
      </option>
    </param>
  </inputs>
  <outputs>
    <data 
      name="output_prediction_csv" 
      format="csv" 
      label="SISTR Results"
      from_work_dir="sistr-report.csv">
      <filter>output_format == "csv"</filter>
    </data>
    <data 
      name="output_prediction_json" 
      format="json" 
      label="SISTR Results"
      from_work_dir="sistr-report.json">
      <filter>output_format == "json"</filter>
    </data>
    <data 
      name="output_prediction_tab" 
      format="tabular" 
      label="SISTR Results"
      from_work_dir="sistr-report.tab">
      <filter>output_format == "tab"</filter>
    </data>
    <data 
      name="cgmlst_profiles" 
      format="csv" 
      label="cgMLST results" />
    <data
      name="novel_alleles"
      format="fasta" 
      label="Novel cgMLST alleles" />
    <data 
      name="alleles_output"
      format="json"
      label="cgMLST allele match results" />
  </outputs>
  <tests>
    <test>
      <param name="input_fastas" value="AE014613-699860.fasta"/>
      <param name="output_format" value="tab"/>
      <output 
        name="novel_alleles" 
        value="novel-alleles.fasta"
        ftype="fasta"
        compare="sim_size"/>
      <output 
        name="cgmlst_profiles" 
        value="cgmlst-profiles.csv"
        ftype="csv"
        lines_diff="2">
        <assert_contents>
          <has_text text=",,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,3969539340,2545200385,225275747,2955003506,2353669245,2666669453,1672513023,3779563470,1301843222,2161147266,607954140,3680021500,2914087704,1062106200,3673111880,1314942441,1367997025,3293595301,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,1528212814,2110459436,4160823845,1648892875,2084418558,1638162324,469721942,1317894045,1973458150,926214622,2197498164,398274060,,,,,,,,,,1123870984,278162969,490843778,3950769715,,,,,,4203409135,3569491948,,,,,,,1052128508,,,1510445340,,,4065472468,,,,,,1495737522,,,,,,,,3076491138,712233770,3105746335,625241463,3016847250,1928860657,2229984332,1341416065,2978539204,1175502179,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,1328452594,2372254687,2640609716,3051501604,3258707132,,,,,,,,,,,,1007978530,,2019769394,1109678443,,,,,,,,,"/>
        </assert_contents>
      </output>
      <output 
        name="output_prediction_tab" 
        value="sistr-results.tab"
        ftype="tabular"
        lines_diff="2">
        <assert_contents>
          <has_text text="AE014613-699860" />
          <has_text text="Typhi" />
          <has_text text="enterica" />
          <has_text text="-:-:-" />
          <has_n_columns n="19" />
        </assert_contents>
      </output>
      <output 
        name="alleles_output" 
        value="alleles-output.json"
        ftype="json"
        compare="sim_size"/>
    </test>
    <test>
      <param name="input_fastas" value="13-1101-Paratyphi_B.fasta"/>
      <param name="output_format" value="tab"/>
      <output 
        name="novel_alleles" 
        value="novel-alleles-13-1101.fasta"
        ftype="fasta"
        compare="sim_size"/>
      <output 
        name="cgmlst_profiles" 
        value="cgmlst-profiles-13-1101.csv"
        ftype="csv"
        lines_diff="2">
      </output>
      <output 
        name="output_prediction_tab" 
        value="sistr-results-13-1101.tab"
        ftype="tabular"
        lines_diff="2">
        <assert_contents>
          <has_text text="13-1101-Paratyphi_B" />
          <has_text text="Paratyphi B var. Java" />
          <has_text text="enterica" />
          <has_text text="1,4,[5],12" />
          <has_text text="PASS" />
          <has_text text="2375035975"/>
          <has_n_columns n="21" />
        </assert_contents>
      </output>
      <output 
        name="alleles_output" 
        value="alleles-output-13-1101.json"
        ftype="json"
        compare="sim_size"/>
    </test>
    <test>
      <param name="input_fastas" value="13-1101 Paratyphi_B.fasta"/>
      <param name="output_format" value="tab"/>
      <output 
        name="novel_alleles" 
        value="novel-alleles-13-1101.fasta"
        ftype="fasta"
        compare="sim_size"/>
      <output 
        name="cgmlst_profiles" 
        value="cgmlst-profiles-13-1101.csv"
        ftype="csv"
        lines_diff="2">
      </output>
      <output 
        name="output_prediction_tab" 
        value="sistr-results-13-1101.tab"
        ftype="tabular"
        lines_diff="2">
        <assert_contents>
          <has_text text="13-1101 Paratyphi_B" />
          <has_text text="Paratyphi B var. Java" />
          <has_text text="enterica" />
          <has_text text="1,4,[5],12" />
          <has_text text="PASS" />
          <has_text text="2375035975"/>
          <has_n_columns n="21" />
        </assert_contents>
      </output>
      <output 
        name="alleles_output" 
        value="alleles-output-13-1101.json"
        ftype="json"
        compare="sim_size"/>
    </test>
  </tests>
  <help>
  <![CDATA[

Usage::

    usage: sistr_cmd [-h] [-i fasta_path genome_name] [-f OUTPUT_FORMAT]
                     [-o OUTPUT_PREDICTION] [-p CGMLST_PROFILES]
                     [-n NOVEL_ALLELES] [-a ALLELES_OUTPUT] [-T TMP_DIR] [-K]
                     [--use-full-cgmlst-db] [--no-cgmlst] [-m] [--qc] [-t THREADS]
                     [-v] [-V]
                     [F [F ...]]

    SISTR (Salmonella In Silico Typing Resource) Command-line Tool
    ==============================================================
    Serovar predictions from whole-genome sequence assemblies by determination of antigen gene and cgMLST gene alleles using BLAST.

    Note about using the "--use-full-cgmlst-db" flag:
        The "centroid" allele database is ~10% the size of the full set so analysis is much quicker with the "centroid" vs "full" set of alleles. Results between 2 cgMLST allele sets should not differ.

    If you find this program useful in your research, please cite as:

    The Salmonella In Silico Typing Resource (SISTR): an open web-accessible tool for rapidly typing and subtyping draft Salmonella genome assemblies.
    Catherine Yoshida, Peter Kruczkiewicz, Chad R. Laing, Erika J. Lingohr, Victor P.J. Gannon, John H.E. Nash, Eduardo N. Taboada.
    PLoS ONE 11(1): e0147101. doi: 10.1371/journal.pone.0147101

    positional arguments:
      F                     Input genome FASTA file

    optional arguments:
      -h, --help            show this help message and exit
      -i fasta_path genome_name, --input-fasta-genome-name fasta_path genome_name
                            fasta file path to genome name pair
      -f OUTPUT_FORMAT, --output-format OUTPUT_FORMAT
                            Output format (json, csv, pickle)
      -o OUTPUT_PREDICTION, --output-prediction OUTPUT_PREDICTION
                            SISTR serovar prediction output path
      -p CGMLST_PROFILES, --cgmlst-profiles CGMLST_PROFILES
                            Output CSV file destination for cgMLST allelic
                            profiles
      -n NOVEL_ALLELES, --novel-alleles NOVEL_ALLELES
                            Output FASTA file destination of novel cgMLST alleles
                            from input genomes
      -a ALLELES_OUTPUT, --alleles-output ALLELES_OUTPUT
                            Output path of allele sequences and info to JSON
      -T TMP_DIR, --tmp-dir TMP_DIR
                            Base temporary working directory for intermediate
                            analysis files.
      -K, --keep-tmp        Keep temporary analysis files.
      --use-full-cgmlst-db  Use the full set of cgMLST alleles which can include
                            highly similar alleles. By default the smaller
                            "centroid" alleles or representative alleles are used
                            for each marker.
      --no-cgmlst           Do not run cgMLST serovar prediction
      -m, --run-mash        Determine Mash MinHash genomic distances to Salmonella
                            genomes with trusted serovar designations. Mash binary
                            must be in accessible via $PATH (e.g. /usr/bin).
      --qc                  Perform basic QC to provide level of confidence in
                            serovar prediction results.
      -t THREADS, --threads THREADS
                            Number of parallel threads to run sistr_cmd analysis.
      -v, --verbose         Logging verbosity level (-v == show warnings; -vvv ==
                            show debug info)
      -V, --version         show program's version number and exit
]]>
  
  </help>
  <citations>
    <!-- Citation for SISTR PLOS ONE paper -->
    <citation type="doi">10.1371/journal.pone.0147101</citation>
  </citations>
</tool>