comparison cryptogenotyper.xml @ 0:c64e19bda2a6 draft default tip

planemo upload for repository https://github.com/phac-nml/CryptoGenotyper commit fdca1f95a5d09edf00bddd42286b68fcb20fa981

0:c64e19bda2a6

<tool id="CryptoGenotyper" name = "CryptoGenotyper" version="@VERSION@+galaxy0">
  <description>
    classifies Cryptosporidium species subtypes based on SSU rRNA and gp60 gene markers from Sanger sequencing data.
  </description>
  <macros>
   <token name="@VERSION@">1.5.0</token>
  </macros>
  <requirements>
    <requirement type="package" version ="@VERSION@">cryptogenotyper</requirement>
  </requirements>
  <version_command>cryptogenotyper --version</version_command>
  <command detect_errors="exit_code">
     <![CDATA[

     #set $ref_file=''

     #if $db
        ln -sf '${db}' '${db.name}' &&
        #set $ref_file = $db.name
     #end if

     #if $primers['seqtype'] == 'contig'
        #set $forward_name=$primers.input.forward.name.rsplit('.', 1)[0]
        #set $reverse_name=$primers.input.reverse.name.rsplit('.', 1)[0]
        ln -sf '${$primers.input['forward']}' '${forward_name}_forward.${primers.input.forward.ext}' &&
        ln -sf '${$primers.input['reverse']}' '${reverse_name}_reverse.${primers.input.reverse.ext}' &&
        cryptogenotyper -i '.' -m '$marker' -t '$primers.seqtype' -f 'forward' -r 'reverse'
        #if $db
          --databasefile $ref_file
        #end if
     #else
        #set $filename_no_ext=$primers.input.name.rsplit('.', 1)[0]
        ln -sf '${primers.input}' '${filename_no_ext}.${primers.input.ext}' &&
        cryptogenotyper -i './${primers.input.name}' -m '$marker' -t '$primers.seqtype'
        #if $db
          --databasefile $ref_file
        #end if
     #end if
     $outputheader
     -o 'result'
     ]]>
  </command>
  <inputs>
      <param name="marker" type="select" label="Marker">
          <option value="18S">SSU rRNA (18S)</option>
          <option value="gp60">gp60</option>
      </param>
      <param name="db" type="data" optional="true" format="fasta" label="Reference Database File (optional):"/>
      <conditional name="primers">
        <param name="seqtype" type="select" label="Type of Sequences">
            <option value="forward" selected="true">Forward Only</option>
            <option value="reverse">Reverse Only</option>
            <option value="contig">Contig</option>
        </param>
        <when value="contig">
          <param name="input" type="data_collection" collection_type="paired" format="ab1,fasta" label="Paired Sequencing File(s)"/>
        </when>
        <when value="forward">
          <param name="input" type="data" format="ab1,fasta" label="Forward Sequencing File(s)"/>
        </when>
        <when value="reverse">
          <param name="input" type="data" format="ab1,fasta" label="Reverse Sequencing File(s)"/>
        </when>
     </conditional>
     <param name="show_log" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Output run log?"></param>
     <param name="outputheader" type="boolean" truevalue="" falsevalue="--noheaderline" checked="true" label="Output header line in the report?">
     </param>


  </inputs>
  <outputs>
    <!-- For single files (forward/reverse mode) -->
    <data name="outfile_single" format="fasta" from_work_dir="result_cryptogenotyper_report.fa" 
     label="${tool.name} ${marker} extracted fasta from ${primers.input.name.split('.')[0]}">
     <filter>primers['seqtype'] != 'contig'</filter>
    </data>
    <!-- For collections (contig mode) -->
    <data name="outfile_collection" format="fasta" from_work_dir="result_cryptogenotyper_report.fa" 
          label="${tool.name} ${marker} extracted fastas">
        <filter>primers['seqtype'] == 'contig'</filter>
    </data>

    <!-- For single files (forward/reverse mode) -->
    <data name="outfile_report_single" format="tabular" from_work_dir="result_cryptogenotyper_report.txt" 
          label="${tool.name} ${marker} REPORT on ${primers.input.name.split('.')[0]}">
        <filter>primers['seqtype'] != 'contig'</filter>
    </data>
    <!-- For collections (contig mode) -->
    <data name="outfile_report_collection" format="tabular" from_work_dir="result_cryptogenotyper_report.txt" 
          label="${tool.name} ${marker} REPORTS">
        <filter>primers['seqtype'] == 'contig'</filter>
    </data>

    <!-- For single files (forward/reverse mode) -->
    <data name="outfile_log_single" format="txt" from_work_dir="cryptogenotyper.log" 
     label="${tool.name} Run ${marker} log on ${primers.input.name.split('.')[0]}">
      <filter>show_log and primers['seqtype'] != 'contig'</filter>
    </data>
    <!-- For collections (contig mode) -->
    <data name="outfile_log_collection" format="txt" from_work_dir="cryptogenotyper.log" 
          label="${tool.name} ${marker} logs">
        <filter>show_log and primers['seqtype'] == 'contig'</filter>
    </data>
  </outputs>

  <tests>
    <!--TEST 1-->
    <test expect_num_outputs="2">
      <param name="marker" value="18S"/>
      <conditional name="primers">
            <param name="seqtype" value="forward"/>
            <param name="input" value="P17705_Crypto16-2F-20170927_SSUF_G12_084.ab1"/>
      </conditional>
      <output name="outfile_report_single" ftype="tabular">
          <assert_contents>
              <has_text_matching expression="C.parvum"/>
          </assert_contents>
      </output>
    </test>
    <!--TEST 2 -->
    <test expect_num_outputs="2">
      <param name="marker" value="gp60"/>
      <conditional name="primers">
            <param name="seqtype" value="forward"/>
            <param name="input" value="P17705_gp60-Crypt14-1F-20170927_gp60F_G07_051.ab1"/>
      </conditional>
      <output name="outfile_report_single" ftype="tabular" >
          <assert_contents>
              <has_text_matching expression="C.parvum"/>
          </assert_contents>
      </output>
    </test>
    <!--TEST 3:Paired gp60 contig test -->
    <test expect_num_outputs="2">
      <param name="marker" value="gp60"/>
      <param name="primers|seqtype" value="contig"/>
      <param name="primers|input">
        <collection type="paired">
          <element name="forward" value="P17705_gp60-Crypt14-1F-20170927_gp60F_G07_051.ab1"/>
          <element name="reverse" value="P17705_gp60-Crypt14-1R-20170927_gp60R_H07_049.ab1"/>
        </collection>
      </param>
      <output name="outfile_report_collection" ftype="tabular">
        <assert_contents>
          <has_text_matching expression="C.parvum"/>
          <has_text_matching expression="IIaA15G2R1"/>
        </assert_contents>
      </output>
    </test>
    <!--TEST 4:Paired 18S contig test -->
    <test expect_num_outputs="2">
      <param name="marker" value="18S"/>
      <param name="primers|seqtype" value="contig"/>
      <param name="primers|input">
        <collection type="paired">
          <element name="forward" value="P17705_Crypto16-2F-20170927_SSUF_G12_084.ab1"/>
          <element name="reverse" value="P17705_Crypto16-2R-20170927_SSUR_H12_082.ab1"/>
        </collection>
      </param>
      <output name="outfile_report_collection" ftype="tabular">
        <assert_contents>
          <has_text_matching expression="C.parvum"/>
          <has_text_matching expression="Check for C. parvum TGA paralogs"/>
        </assert_contents>
      </output>
    </test>

 
    <!--TEST 5: 18S multi-fasta forward -->
    <test expect_num_outputs="2">
      <param name="marker" value="18S"/>
      <param name="primers|seqtype" value="forward"/>
      <param name="primers|input" value="test_illumina_18S_F.fasta"/>
      <output name="outfile_report_single" ftype="tabular">
        <assert_contents>
          <has_n_lines n="5"/>
          <has_text_matching expression="C.hominis"/>
          <has_text_matching expression="forward"/>
        </assert_contents>
      </output>
    </test>

    <!--TEST 6: 18S multi-fasta reverse -->
    <test expect_num_outputs="2">
      <param name="marker" value="18S"/>
      <param name="primers|seqtype" value="reverse"/>
      <param name="primers|input" value="test_illumina_18S_R.fasta"/>
      <output name="outfile_report_single" ftype="tabular">
        <assert_contents>
          <has_n_lines n="5"/>
          <has_text_matching expression="C.hominis"/>
          <has_text_matching expression="reverse"/>
        </assert_contents>
      </output>
    </test>

    <!--TEST 7: 18S multi-fasta contig -->
    <test expect_num_outputs="2">
      <param name="marker" value="18S"/>
      <param name="primers|seqtype" value="contig"/>
      <param name="primers|input">
        <collection type="paired">
          <element name="forward" value="test_illumina_18S_F.fasta"/>
          <element name="reverse" value="test_illumina_18S_R.fasta"/>
        </collection>
      </param>
      <output name="outfile_report_collection" ftype="tabular">
        <assert_contents>
          <has_text_matching expression="C.hominis"/>
          <has_text_matching expression="contig"/>
        </assert_contents>
      </output>
    </test>

    <!--TEST 8: gp60 multi-fasta forward -->
    <test expect_num_outputs="2">
      <param name="marker" value="gp60"/>
      <param name="primers|seqtype" value="forward"/>
      <param name="primers|input" value="test_illumina_gp60_F1.fasta"/>
      <output name="outfile_report_single" ftype="tabular">
        <assert_contents>
          <has_n_lines n="3"/>
          <has_text_matching expression="C.parvum"/>
          <has_text_matching expression="forward"/>
          <has_text_matching expression="IIaA16G3R1"/>
          <has_text_matching expression="IIaA15G2R2"/>
          
        </assert_contents>
      </output>
    </test>

    <!--TEST 9: gp60 multi-fasta reverse -->
    <test expect_num_outputs="2">
      <param name="marker" value="gp60"/>
      <param name="primers|seqtype" value="reverse"/>
      <param name="primers|input" value="test_illumina_gp60_R1.fasta"/>
      <output name="outfile_report_single" ftype="tabular">
        <assert_contents>
          <has_n_lines n="3"/>
          <has_text_matching expression="C.parvum"/>
          <has_text_matching expression="reverse"/>
          <has_text_matching expression="IIaA3R1"/>
          <has_text_matching expression="IIaA3R1"/>
        </assert_contents>
      </output>
    </test>



    <!--TEST 10: gp60 multi-fasta reverse -->
     <test expect_num_outputs="3">
      <param name="marker" value="gp60"/>
      <param name="primers|seqtype" value="contig"/>
      <param name="show_log" value="true"/>
      <param name="primers|input">
        <collection type="paired">
          <element name="forward" value="test_illumina_gp60_F1.fasta"/>
          <element name="reverse" value="test_illumina_gp60_R1.fasta"/>
        </collection>
      </param>
      <output name="outfile_report_collection" ftype="tabular">
        <assert_contents>
          <has_text_matching expression="C.parvum"/>
          <has_text_matching expression="contig"/>
          <has_text_matching expression="IIaA16G3R1"/>
          <has_text_matching expression="IIaA15G2R2"/>
        </assert_contents>
      </output>
    </test>



 

  </tests>


  <help>


**Syntax**

CryptoGenotyper is a standalone tool to *in-silico*  determine species and subtype based on SSU rRNA (18S) and gp60 markers.

**❗ Important:** To process **multiple input files** and generate **a single** combined report, please import and use the workflows available `here`_.

.. _here: https://github.com/phac-nml/CryptoGenotyper/tree/main/CryptoGenotyper/GalaxyWorkflows


For a tutorial on how to use CryptoGenotyper, please refer to the `official tutorial`_.

For more information, please visit https://github.com/phac-nml/CryptoGenotyper.

.. _official tutorial: https://github.com/phac-nml/CryptoGenotyper/blob/docs/docs/CryptoGenotyperTutorial-CrownCopyright.pdf

-----

**Input:**

AB1 or FASTA file(s) representing Cryptosporidium's SSU rRNA (18S) or gp60 locus can be provided as single-end reads (either forward or reverse only) or as paired-end reads in contig mode (both a forward and a reverse read for each sample).

Optional: A custom reference database of SSU rRNA or gp60 locus in .fasta file format, to be used during the homology search for *Cryptosporidium* classification.


**Output:**

A tabular report and a FASTA file containing the identification of the *Cryptosporidium* species/subtype and its corresponding sequence for each sample along with other relevant details. 
The gp60 subtyping is based on the `Deciphering a cryptic minefield: a guide to Cryptosporidium gp60 subtyping publication`_.

.. _`Deciphering a cryptic minefield: a guide to Cryptosporidium gp60 subtyping publication`: https://doi.org/10.1016/j.crpvbd.2025.100257

  </help>
  <citations>
    <citation type="bibtex">
  @ARTICLE{githubCryptoGenotyper,
  author = {Yanta, Christine A. and Bessonov, Kyrylo and Robinson, Guy and Troell, Karin and Guy, Rebecca A.},
  title = {CryptoGenotyper: a new bioinformatics tool to enhance Cryptosporidium identification},
  journal = {Food and waterborne parasitology},
  year = {2021},
  volume = {23},
  url = {https://doi.org/10.1016/j.fawpar.2021.e00115}
    }</citation>
  <citation type="bibtex">
  @ARTICLE{RobinsonGp60,
   author = {Robinson, Gillian and Chalmers, Rachel M. and Elwin, Kirsty and Guy, Richard A. and Bessonov, Konstantin and Troell, Kristina and Xiao, Lihua},
   title = {Deciphering a cryptic minefield: A guide to Cryptosporidium gp60 subtyping},
   journal = {Current Research in Parasitology and Vector-Borne Diseases},
   year = {2025},
   volume = {7},
   url = {https://doi.org/10.1016/j.crpvbd.2025.100257}
   }
   }</citation>
  </citations>

</tool>