comparison sistr_cmd.xml @ 6:cf767360ede1 draft default tip

planemo upload for repository https://github.com/phac-nml/sistr_cmd commit 4a9d0e766264aab4b92d8971b70112f84e28e8cd

5:24a7a95867b0

<tool id="sistr_cmd" name="sistr_cmd" version="@VERSION@+galaxy1">
  <description>
    Salmonella In Silico Typing Resource commandline tool for serovar prediction 
  </description>
  <macros>
     <token name="@VERSION@">1.1.1</token>
  </macros>
  <requirements>
    <requirement type="package" version="@VERSION@">sistr_cmd</requirement>
  </requirements>
  <stdio>
    <exit_code range="1:" />
  </stdio>
  <command><![CDATA[
  sistr 
    #for $fasta in $input_fastas
      -i '$fasta' '${$fasta.element_identifier.replace("." + $fasta.ext, "")}'
    #end for
    -f $output_format

    -a $alleles_output
    $use_full_cgmlst_db
    $no_cgmlst
    $run_mash
    $qc
    --threads "\${GALAXY_SLOTS:-1}"
    -T "\${TMPDIR:-/tmp}"
    $keep_tmp
    $more_output
    $verbosity

      type="boolean"
      checked="true"
      truevalue="--qc"
      falsevalue=""
      label="Basic QC of results"
      />
    <param 
      name="more_output"
      type="select" 
      label="Results verbosity">
      <option value="" selected="true">

  </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" ftype="fasta"/>
      <param name="output_format" value="tab"/>
      <output 
        name="cgmlst_profiles" 
        value="cgmlst-profiles.csv"
        ftype="csv"
        compare="diff">
      </output>
      <output name="output_prediction_tab" 
        ftype="tabular"
        value="sistr-results.tabular"
        compare="sim_size">
        <assert_contents>
          <has_text text="AE014613-699860" />
          <has_text text="Typhi" />
          <has_text text="enterica" />
          <has_text_matching expression="FAIL\t-\t-:-:-\t-:-:-"/>
          <has_text text="2014-LET-0419"/>
          <has_n_columns n="22" />
        </assert_contents>
      </output>
      <output 
        name="alleles_output" 
        value="alleles-output.json"
        ftype="json"
        compare="sim_size">
        <assert_contents>
          <has_text text="NZ_AOXE01000059.1"/>
          <has_text text="Salmonella enterica subsp. enterica serovar Typhi Ty2"/>
          <has_text text="NZ_AOXE01000033.1"/>
          <has_text text="NZ_AOXE01000052.1"/>  
        </assert_contents> 
      </output>
    </test>
    <test>
      <param name="input_fastas" value="13-1101-Paratyphi_B.fasta" ftype="fasta"/>
      <param name="output_format" value="tab"/>
      <output 
        name="novel_alleles" 
        value="novel-alleles-13-1101.fasta"
        ftype="fasta"

        <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_n_columns n="22"/>
        </assert_contents>
      </output>
      <output 
        name="alleles_output" 
        value="alleles-output-13-1101.json"

    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:

                            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
]]>
  

6:cf767360ede1

<tool id="sistr_cmd" name="sistr_cmd" version="@VERSION@+galaxy0">
  <description>
    Salmonella In Silico Typing Resource command-line tool for serovar prediction 
  </description>
  <macros>
     <token name="@VERSION@">1.1.3</token>
  </macros>
  <xrefs>
      <xref type="bio.tools">SISTR</xref>
  </xrefs>
  <requirements>
    <requirement type="package" version="@VERSION@">sistr_cmd</requirement>
  </requirements>
  <stdio>
    <exit_code range="1:" />
  </stdio>
  <command><![CDATA[

  sistr 
    #for $fasta in $input_fastas
      -i '$fasta' '${$fasta.element_identifier.replace("." + $fasta.ext, "")}'
    #end for
    -f $output_format

    -a $alleles_output
    $use_full_cgmlst_db
    $no_cgmlst
    $run_mash
    $qc
    #if $serovar_list.selection_mode == "default"
      --list-of-serovars
    #elif  $serovar_list.selection_mode == "custom"
      --list-of-serovars  $serovar_list.custom_list_of_serovars_file
    #end if
    --threads "\${GALAXY_SLOTS:-1}"
    -T "\${TMPDIR:-/tmp}"
    $keep_tmp
    $more_output
    $verbosity

      type="boolean"
      checked="true"
      truevalue="--qc"
      falsevalue=""
      label="Basic QC of results"
    />
    <conditional name="serovar_list">
        <param label="Check predicted SISTR serovar against the list of serovars?" name="selection_mode" type="select">
          <option value="none">Not selected</option>
          <option selected="true" value="default">Use the default list</option>
          <option value="custom">Use a custom list</option>
        </param>
        <when value="none"/>
        <when value="default"/>
        <when value="custom">
          <param name="custom_list_of_serovars_file" type="data" format="text" optional="true" label="Custom list of serovars (optional)" 
        help="if no file selected, the default one is used available at https://raw.githubusercontent.com/phac-nml/sistr_cmd/v1.1.3/sistr/data/serovar-list.txt"
        />
        </when>
    </conditional>
    <param 
      name="more_output"
      type="select" 
      label="Results verbosity">
      <option value="" selected="true">

  </inputs>
  <outputs>
    <data 
      name="output_prediction_csv" 
      format="csv" 
      label="${tool.name} on ${input_fastas[0].element_identifier}: Main Report (csv)"
      from_work_dir="sistr-report.csv">
      <filter>output_format == "csv"</filter>
    </data>
    <data 
      name="output_prediction_json" 
      format="json" 
      label="${tool.name} on ${input_fastas[0].element_identifier}: Main Report (json)"
      from_work_dir="sistr-report.json">
      <filter>output_format == "json"</filter>
    </data>
    <data 
      name="output_prediction_tab" 
      format="tabular" 
      label="${tool.name} on ${input_fastas[0].element_identifier}: Main Report (tab)"
      from_work_dir="sistr-report.tab">
      <filter>output_format == "tab"</filter>
    </data>
    <data 
      name="cgmlst_profiles" 
      format="csv" 
      label="${tool.name} on ${input_fastas[0].element_identifier}: cgMLST allele match results (csv)" />
    <data
      name="novel_alleles"
      format="fasta" 
      label="${tool.name} on ${input_fastas[0].element_identifier}: Novel cgMLST alleles (fasta)" />
    <data 
      name="alleles_output"
      format="json"
      label="${tool.name} on ${input_fastas[0].element_identifier}: cgMLST allele match results (json)" />
  </outputs>
  <tests>
    <test expect_num_outputs="4">
      <param name="input_fastas" value="AE014613-699860.fasta" ftype="fasta"/>
      <param name="output_format" value="tab"/>
      <param name="selection_mode" value="none"/>
      <output 
        name="cgmlst_profiles" 
        value="cgmlst-profiles-AE014613.csv"
        ftype="csv"
        compare="diff">
      </output>
      <output name="output_prediction_tab" 
        ftype="tabular"
        value="sistr-results-AE014613-699860.tabular"
        compare="sim_size"> 
        <assert_contents>
          <has_text text="AE014613-699860" />
          <has_text text="Typhi" />
          <has_text text="enterica" />
          <has_text_matching expression="FAIL\t-\t-:-:-\t-:-:-"/>
          <has_text text="2014-LET-0419"/>
          <has_n_columns n="23" />
        </assert_contents>
      </output>
      <output 
        name="alleles_output" 
        value="alleles-output-AE014613.json"
        ftype="json"
        compare="sim_size">
        <assert_contents>
          <has_text text="NZ_AOXE01000059.1"/>
          <has_text text="Salmonella enterica subsp. enterica serovar Typhi Ty2"/>
          <has_text text="NZ_AOXE01000033.1"/>
          <has_text text="NZ_AOXE01000052.1"/>  
        </assert_contents> 
      </output>
    </test>
    <test expect_num_outputs="4">
      <param name="input_fastas" value="13-1101-Paratyphi_B_varJava.fasta" ftype="fasta"/>
      <param name="output_format" value="tab"/>
      <output 
        name="novel_alleles" 
        value="novel-alleles-13-1101.fasta"
        ftype="fasta"

        <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="1,4,[5],12:b:1,2"/>
          <has_text text="FAIL"/>
          <has_text text="Y"/>
          <has_n_columns n="24"/>
        </assert_contents>
      </output>
      <output 
        name="alleles_output" 
        value="alleles-output-13-1101.json"

    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:

                            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.
      -l [LIST_OF_SEROVARS], --list-of-serovars [LIST_OF_SEROVARS]
                            A path to a single column text file containing list of
                            serovars to check SISTR serovar prediction against.
                            Result reported in the "predicted_serovar_in_list"
                            field as Y (present) or N (absent) value.                      
      -v, --verbose         Logging verbosity level (-v == show warnings; -vvv ==
                            show debug info)
      -V, --version         show program's version number and exit
]]>