annotate seqsero2.xml @ 0:93ef4c70ce5f draft default tip

"planemo upload for repository https://github.com/quadram-institute-bioscience/galaxy-tools/tree/master/tools/seqsero2 commit 8b41cf1161ac0f0836f5597167911596b0cfa27e-dirty"

<tool id="seqsero2" name="SeqSero2" version="@VERSION@+galaxy0">
    <description> Salmonella serotype prediction</description>
    <macros>
        <token name="@VERSION@">1.2.1</token>
    </macros>
    <requirements>
        <requirement type="package" version="@VERSION@">seqsero2</requirement>
    </requirements>
    <version_command>SeqSero2_package.py -v</version_command>
    <command detect_errors="exit_code"><![CDATA[
    #import re
    #set $seqsero_input = ''
    #set $seqsero_t_value = ''
    #if $inputs.input_type == 'paired':
        #if $inputs.R1.is_of_type('fastqsanger', 'fastq'):
            #set $ext = 'fastq'
        #elif $inputs.R1.is_of_type('fastqsanger.gz'):
            #set $ext = 'fastq.gz'
        #elif $inputs.R1.is_of_type('fastq'):
            #set $ext = 'fastq'
        #elif $inputs.R1.is_of_type('fastq.gz'):
            #set $ext = 'fastq.gz'
        #elif $inputs.R1.is_of_type('fasta.gz'):
            #set $ext = 'fasta.gz'
        #elif $inputs.R1.is_of_type('fasta'):
            #set $ext = 'fasta'
        #end if
        #set $safename_R1 = re.sub('[^\w\-_\.]', '_', $inputs.R1.element_identifier)
        #set $safename_R2 = re.sub('[^\w\-_\.]', '_', $inputs.R2.element_identifier)
        ln -fs '$inputs.R1' $safename_R1.$ext &&
        ln -fs '$inputs.R2' $safename_R2.$ext &&
        #set $seqsero_input = $safename_R1 + '.' + $ext + ' ' + $safename_R2 + '.' + $ext
        #set $seqsero_t_value = '2'
    #elif $inputs.input_type == 'collection':
        #for $input in $inputs.input_collection
            #if $input.forward.is_of_type('fastqsanger', 'fastq'):
                #set $ext = 'fastq'
            #elif $input.forward.is_of_type('fastqsanger.gz'):
                #set $ext = 'fastq.gz'
            #elif $input.forward.is_of_type('fastq'):
                #set $ext = 'fastq'
            #elif $input.forward.is_of_type('fastq.gz'):
                #set $ext = 'fastq.gz'
            #elif $input.forward.is_of_type('fasta.gz'):
                #set $ext = 'fasta.gz'
            #elif $input.forward.is_of_type('fasta'):
                #set $ext = 'fasta'
            #end if
            #set $safename_fwd = re.sub('[^\w\-_\.]', '_', $input.forward.element_identifier)
            ln -fs '$input.forward' $safename_fwd.$ext &&
            #set $safename_rvs = re.sub('[^\w\-_\.]', '_', $input.reverse.element_identifier)
            ln -fs '$input.reverse' $safename_rvs.$ext &&
            #set $seqsero_input = $safename_fwd+ '.' + $ext + ' ' + $safename_rvs + '.' + $ext
            #set $seqsero_t_value = '2'
        #end for
    #elif $inputs.input_type == 'assembly':
        #if $inputs.contigs.is_of_type('fasta.gz'):
            #set $ext = 'fasta.gz'
        #elif $inputs.contigs.is_of_type('fasta'):
            #set $ext = 'fasta'
        #end if
        #set $safename_seq = re.sub('[^\w\-_\.]', '_', $contigs.element_identifier)
        ln -fs '$contigs' $safename_seq.$ext &&
        #set $seqsero_input = $safename_seq + '.' + $ext
        #set $seqsero_t_value = '4'
    #elif $inputs.input_type == 'single':
        #if $inputs.single.is_of_type('fastqsanger', 'fastq'):
            #set $ext = 'fastq'
        #elif $inputs.single.is_of_type('fastqsanger.gz'):
            #set $ext = 'fastq.gz'
        #elif $inputs.single.is_of_type('fastq'):
            #set $ext = 'fastq'
        #elif $inputs.single.is_of_type('fastq.gz'):
            #set $ext = 'fastq.gz'
        #elif $inputs.single.is_of_type('fasta.gz'):
            #set $ext = 'fasta.gz'
        #elif $inputs.single.is_of_type('fasta'):
            #set $ext = 'fasta'
        #end if
        #set $safename_seq = re.sub('[^\w\-_\.]', '_', $single.element_identifier)
        ln -fs '$single' $safename_seq.$ext &&
        #set $seqsero_input = $safename_seq + '.' + $ext
        #set $seqsero_t_value = '3'
    #elif $inputs.input_type == 'nanopore':
        #if $inputs.nanopore.is_of_type('fastqsanger', 'fastq'):
            #set $ext = 'fastq'
        #elif $inputs.nanopore.is_of_type('fastqsanger.gz'):
            #set $ext = 'fastq.gz'
        #elif $inputs.nanopore.is_of_type('fastq'):
            #set $ext = 'fastq'
        #elif $inputs.nanopore.is_of_type('fastq.gz'):
            #set $ext = 'fastq.gz'
        #elif $inputs.nanopore.is_of_type('fasta.gz'):
            #set $ext = 'fasta.gz'
        #elif $inputs.nanopore.is_of_type('fasta'):
            #set $ext = 'fasta'
        #end if
        #set $safename_seq = re.sub('[^\w\-_\.]', '_', $nanopore.element_identifier)
        ln -fs '$nanopore' $safename_seq.$ext &&
        #set $seqsero_input = $safename_seq + '.' + $ext
        #set $seqsero_t_value = '5'
    #end if
    
    SeqSero2_package.py 
    -m $workflow
    -t $seqsero_t_value
    -i $seqsero_input
    -p \${GALAXY_SLOTS:-4}
    -d output
    ]]>    </command>
    <inputs>
        <conditional name="inputs">
            <param name="input_type" type="select" label="Input type" help="Select 'paired end' reads or 'sequence' for genomes/contigs">
                <option value="paired">Paired End</option>
                <option value="collection">Collection</option>
                <option value="assembly">Contigs</option>
                <option value="single">Interleaved</option>
                <option value="nanopore">Nanopore reads</option>
            </param>
            <when value="paired">
                <param name="R1" type="data" format="fastqsanger,fastqsanger.gz" label="Forward reads (R1)" help="The file of forward reads in FASTQ format"/>
                <param name="R2" type="data" format="fastqsanger,fastqsanger.gz" label="Reverse reads (R2)" help="The file of reverse reads in FASTQ format"/>
            </when>
            <when value="collection">
                <param name="input_collection" format="fastqsanger" type="data_collection" collection_type="list:paired" label="Paired collection"/>
            </when>
            <when value="single">
                <param name="single" type="data" format="fastqsanger,fastqsanger.gz" multiple="false" label="Interleaved" />
            </when>
            <when value="nanopore">
                <param name="nanopore" type="data" format="fastqsanger,fastqsanger.gz" multiple="false" label="Nanopore reads" />
            </when>
            <when value="assembly">
                <param name="contigs" type="data" format="fasta" multiple="false" label="Contigs/genomes" />
            </when>
        </conditional>
        <param label="Workflow" type="select" name="workflow">
            <option value="a">allele</option>
            <option value="k" selected="true">k-mer</option>
        </param>
    </inputs>
    <outputs>
        <data name="results" format="tabular" label="${tool.name} on ${on_string} Results" from_work_dir="output/SeqSero_result.tsv"/>
        <data name="log" format="txt" label="${tool.name} on ${on_string} Log" from_work_dir="output/SeqSero_log.txt"/>

    </outputs>
    <tests>
        <test>
            <param name="input_type" value="assembly" />
            <param name="contigs" value="CP009102.1.fasta" ftype="fasta" />
            <output name="results">
                <assert_contents>
                    <has_text text="Salmonella enterica subspecies enterica (subspecies I)" />
                    <has_text text="Typhimurium" />
                </assert_contents>
            </output>
        </test>
        <!-- TODO: Test for fastq files -->
     </tests>
    <help><![CDATA[
        
**Usage: SeqSero2_package.py**

-m <string> (which workflow to apply, 'a'(raw reads allele micro-assembly), 'k'(raw reads and genome assembly k-mer), default=a)

-t <string> (input data type, '1' for interleaved paired-end reads, '2' for separated paired-end reads, '3' for single reads, '4' for genome assembly, '5' for nanopore reads (fasta/fastq))

-i <file> (/path/to/input/file)

-p <int> (number of threads for allele mode, if p >4, only 4 threads will be used for assembly since the amount of extracted reads is small, default=1) 

-b <string> (algorithms for bwa mapping for allele mode; 'mem' for mem, 'sam' for samse/sampe; default=mem; optional; for now we only optimized for default "mem" mode)

-d <string> (output directory name)

-c <flag> (if '-c' was flagged, SeqSero2 will only output serotype prediction without the directory containing log files)

-n <string> (optional, to specify a sample name in the report output)

-s <flag> (if '-s' was flagged, SeqSero2 will not output header in `SeqSero_result.tsv`)
        
--check <flag> (use '--check' flag to check the required dependencies)

-v, --version (show program's version number and exit)

-----

_`Document`:  https://github.com/denglab/SeqSero2

    ]]></help>
    <citations>
        <citation type="bibtex">
        @misc{zhang_yin_jones_zhang_deathrage_dinsmore_fitzgeral_fields_deng_2015, title={Salmonella serotype determination utilizing high-throughput genome sequencing data.}, journal={J Clin Microbiol}, publisher={ASM}, author={Zhang S, Yin Y, Jones MB, Zhang Z, Deatherage Kaiser BL, Dinsmore BA, Fitzgerald C, Fields PI, Deng X.}, year={2015}, month={Max}, url={http://http://jcm.asm.org/content/early/2015/03/05/JCM.00323-15}},
       }</citation>
        <citation type="bibtex">
        @misc{cfsan_biostatistics_group_2017, title={CFSAN Biostatistics Group fork of SeqSero2}, url={https://github.com/CFSAN-Biostatistics/SeqSero2.git}},
        </citation>
    </citations>

</tool>