annotate SsuisSerotyping_pipeline.xml @ 1:b4f2c9e7300b draft

Uploaded python script

<tool id="SsuisSerotyping_pipeline" name="Use SsuisSerotyping_pipeline." version="0.1.2">
    <requirements>
        <requirement type="package">perl-bioperl</requirement>
        <requirement type="package">scipy</requirement>
        <requirement type="package" version="2.7">python</requirement>
        <requirement type="package">srst2</requirement>
    </requirements>
    <stdio>
        <exit_code range="1:" />
    </stdio>
    <command><![CDATA[
        python $__tool_directory__/Prepare_Ssuis_serotypingPipeline.py 
            --fastq_file $input1  
            --scoreName '$output1'
            --output2 '$output2'
            --output3 '$output3'
            --output4 '$output4'
            --output5 '$output5'
            --output6 '$output6'
            --output7 '$output7'
            --output8 '$output8'
            #if $optionalfiles.analysis_selector == "specific":
                            --serotype_db '$options.serotype_db' 
                            --serotype_definitions '$options.serotype_definitions' 
                            --cps2K '$options.cps2K' 
                            --Virulence_db '$options.Virulence_db' 
                            --recN_db '$options.recN_db' 
                            --MLST_definitions '$options.MLST_definitions' 
                            --MLST_db '$options.MLST_db'
            #end if
            #if $typeofdata.pors == "paired":
                            --ends pe
                            --forward '$typeofdata.forward'
                            --reverse '$typeofdata.reverse'
            #else:
                            --ends se 
            #end if

    ]]></command>
    <inputs>
        <param type="data" name="input1" format="fastq" />
        <conditional name="optionalfiles">
           <param name="analysis_selector" type="select" label="Use specific or default configuration?">
               <option value="default" selected="True">Use default configuration.</option>
               <option value="specific">Use specific file</option>
           </param>
           <when value="default" />
           <when value="specific">
               <param type="data" name="serotype_db" format="fasta" label="Serotype database in fasta format." />
               <param type="data" name="serotype_definitions" format="txt" label="Definition of the serotype database" />
               <param type="data" name="cps2K" format="fasta" label="Multifasta with cpsH confirmation database" />
               <param type="data" name="Virulence_db" format="fasta" label="Virulence genes" />
               <param type="data" name="recN_db" format="fasta" label="recN species specfic gene" />
               <param type="data" name="MLST_definitions" format="txt" label="Definitions of MLST database file" />
               <param type="data" name="MLST_db" format="fasta" label="MLST database" />
           </when>
        </conditional>
        <conditional name="typeofdata">
           <param name="pors" type="select" label="Read option">
               <option value="single" selected="True">Single-end</option>
               <option value="paired">Paired-end</option>
           </param>
           <when value="single" />
           <when value="paired">
               <param type="text" name="reverse" value="_R1" />
               <param type="text" name="forward" value="_R2" />
           </when>
        </conditional>
    </inputs>
    <outputs>
        <data name="output1" format="txt" label="${tool.name} on ${on_string}: Results_FinalResults.txt" from_work_dir="Results_FinalResults.txt"/>
        <data name="output2" format="txt" label="${tool.name} on ${on_string}: Results_MLSTResults.txt" from_work_dir="Results_MLSTResults.txt"/>
        <data name="output3" format="txt" label="${tool.name} on ${on_string}: Results_recN__fullgenes__recN_full__results.txt" from_work_dir="Results_recN__fullgenes__recN_full__results.txt" />
        <data name="output4" format="txt" label="${tool.name} on ${on_string}: Results_speciesConfirmation.txt" from_work_dir="Results_speciesConfirmation.txt" />
        <data name="output5" format="txt" label="${tool.name} on ${on_string}: Results_FinalSerotypingResults.txt" from_work_dir="Results_FinalSerotypingResults.txt" />
        <data name="output6" format="txt" label="${tool.name} on ${on_string}: Results_InitialCapsuleResults.txt" from_work_dir="Results_InitialCapsuleResults.txt" />
        <data name="output7" format="txt" label="${tool.name} on ${on_string}: Results_VirulenceFactors__fullgenes__Virulence__results.txt" from_work_dir="Results_VirulenceFactors__fullgenes__Virulence__results.txt" />
        <data name="output8" format="txt" label="${tool.name} on ${on_string}: Results_VirulenceFactorResults.txt" from_work_dir="Results_VirulenceFactorResults.txt" />
    </outputs>
    <tests>
        <test>
            <param name="input1" value="/home/plucas/TEST/SsuisSerotyping_pipeline/input_fastq/SS1218_IonXpress_008_R_2016_02_23.soft_clean.trimmomatic_trimmed.fastq"/>
            <output name="output1" file="/home/plucas/TEST/SsuisSerotyping_pipeline/results/Results_FinalResults.txt"/>
        </test>
    </tests>
    <help><![CDATA[
Implementation of the S. suis serotyping pipeline:

perl Ssuis_serotypingPipeline.pl --fastq_directory /path/to/fastq/directory --scoreName Scores_output_name --serotype_db serotype.fasta --serotype_definitions serotype_definitions.txt --cps2K cps2K.fasta

--fastq_directory       Path to directory containing paired-end fastq files.
                        Must be full path to directory, please do not use '.'
                        or '..' to declare path
                        If no path is given, the current working
                        directory is used
--scoreName             Name of SRST2 results file
                        [optional: default name 'Results']
--serotype_db           Multifasta file containing the serotype database
                        (Ssuis_Serotyping.fasta)
                        [If none is provided, Ssuis_Serotyping.fasta is looked
                        for in the directory containing the script]
--serotype_definitions  Text file containing the definitions for the
                        serotype database file
                        (Ssuis_Serotyping_Definitions.txt)
                        [If none is provided, Ssuis_Serotyping_Definitions.txt is looked
                        for in the directory containing the script]
--cps2K         Multifasta file containing the cpsH confirmation database
                        (Ssuis_cps2K.fasta)
                        [If none is provided, Ssuis_cps2K.fasta is looked
                        for in the directory containing the script]
--MLST_db               Multifasta file containing the MLST database
                        (Streptococcus_suis.fasta)
                        [If none is provided, Streptococcus_suis.fasta is looked
                        for in the directory containing the script]
--MLST_definitions      Text file containing the definitions for the
                        MLST database file
                        (ssuis.txt)
                        [If none is provided, ssuis.txt is looked
                        for in the directory containing the script]
--recN_db               Fasta file containing the recN species specfic gene
                        (recN_Full.fasta)
                        [If none is provided, recN_full.fasta is looked
                        for in the directory containing the script]
--Virulence_db          Multifasta file containing the Virulence genes
                        (Virulence.fasta)
                        [If none is provided, Virulence.fasta is looked
                        for in the directory containing the script]
--forward               Indicator delimiting the forward reads file for
                        paired read fastq files

This option is ignored if single-end reads is selected
                        [optional: default '_R1']

--reverse               Indicator delimiting the reverse reads file for
                        paired read fastq files

This option is ignored if single-end reads is selected
                        [optional: default '_R2']

--ends          Indicates whether the reads are paired-end (pe) or single-end (se)
                        [optional: default 'pe']

Note: We recommend using paired end reads of at least 100nt in length
and at least 30X coverage.
We have not tested the efficiency of the pipeline with reads shorter than 80nt.
    ]]></help>
    <citations>
        <citation type="bibtex">
@misc{githubSsuisSerotyping_pipeline,
  author = {LastTODO, FirstTODO},
  year = {TODO},
  title = {SsuisSerotyping_pipeline},
  publisher = {GitHub},
  journal = {GitHub repository},
  url = {https://github.com/streplab/SsuisSerotyping_pipeline},
}</citation>
    </citations>
</tool>