annotate PhageTerm.xml @ 24:c8f88ae512f3 draft default tip

Uploaded

<tool id="PhageTerm" name="PhageTerm" version="1.0.12">
    <description>Determine Bacteriophage Termini and Packaging Mode using randomly fragmented NGS data.</description>
    <requirements>
        <requirement type="package" version="2.7">python</requirement>
        <requirement type="package" version="1.16.5">numpy</requirement>
        <requirement type="package" version="2.2.5">matplotlib</requirement>
        <requirement type="package" version="0.24.2">pandas</requirement>
        <requirement type="package" version="0.20.4">scikit-learn</requirement>
        <requirement type="package" version="1.2.1">scipy</requirement>
        <requirement type="package" version="0.10.2">statsmodels</requirement>
        <requirement type="package" version="3.5.42">reportlab</requirement>
    </requirements>
    <edam_operations>
        <edam_operation>operation_3198</edam_operation>
    </edam_operations>
    <edam_topics>
        <edam_topic>topic_0781</edam_topic>
    </edam_topics>
    <stdio>
        <!-- Assume anything other than zero is an error -->
        <exit_code range="1:" />
    </stdio>
    <command interpreter="python2.7">PhageTerm.py -c \${GALAXY_SLOTS} -f $fastq -r $reference
#if $phagename
-n $phagename
#end if
#if $paired
-p $paired
#end if
#if $seed
-s $seed
#end if
#if $surrounding
-d $surrounding
#end if
#if $host
-g $host
#end if
#if $coverage
-m $coverage
#end if
    </command>
    <inputs>
        <param format="fastq" name="fastq" type="data" label="Phage Reads (FASTQ)" help="Phage sequencing reads file in fastq format from randomly fragmented NGS data (e.g. Illumina TruSeq) but NOT Nextera."/>
        <param format="fasta" name="reference" type="data" label="Phage Genome (FASTA)" help="Phage reference genome file in fasta format, Multi-fasta NOT accepted."/>
        <param name="phagename" type="text" value="my_phage" size="20" optional="true" label="Prefix" help="Prefix for the output file name."/>
        <param format="fastq" name="paired" type="data" optional="true" label="Phage Paired-End Reads (FASTQ)" help="Phage sequencing paired-end reads file in fastq format."/>
        <param format="fasta" name="host" type="data" optional="true" label="Bacterial Host Genome (FASTA)" help="Host reference genome file in fasta format, Multi-fasta NOT accepted. Warning : increases process time."/>
        <param name="seed" type="integer" optional="true" value="20" label="Seed length" help="Seed length value for alignment of reads."/>
        <param name="surrounding" type="integer" optional="true" value="20" label="Peak surrounding region" help="Length of the surrounding region defining close peaks to be merged in the analysis process."/>
        <param name="coverage" type="integer" optional="true" value="250" label="Limit Coverage" help="Phage upper limit coverage."/>
    </inputs>
    <outputs>
        <data name="Statistics" format="csv" label="${phagename}_statistics.csv" from_work_dir="*_statistics.csv" />
        <data name="CohesiveSequence" format="fasta" label="${phagename}_cohesive-DTR.fasta" from_work_dir="*_cohesive-sequence.fasta"/>
        <data name="PhageSequence" format="fasta" label="${phagename}_sequence.fasta" from_work_dir="*_sequence.fasta"/>
        <data name="ReportPDF" format="pdf" label="${phagename}_PhageTerm_report.pdf" from_work_dir="*_PhageTerm_report.pdf"/>
    </outputs>
    <tests>
        <test>
            <param name="phagename" value="Test-cohesive-5'" />
            <param name="fastq" value="COS-5.fastq" />
            <param name="reference" value="COS-5.fasta" />
        </test>
        <test>
            <param name="phagename" value="Test-cohesive-3'" />
            <param name="fastq" value="COS-3.fastq" />
            <param name="reference" value="COS-3.fasta" />
        </test>
        <test>
            <param name="phagename" value="Test-short-direct-terminal-repeats" />
            <param name="fastq" value="DTR-short.fastq" />
            <param name="reference" value="DTR-short.fasta" />
        </test>
        <test>
            <param name="phagename" value="Test-long-direct-terminal-repeats" />
            <param name="fastq" value="DTR-long.fastq" />
            <param name="reference" value="DTR-long.fasta" />
        </test>
        <test>
            <param name="phagename" value="Test-Headful" />
            <param name="fastq" value="Headful.fastq" />
            <param name="reference" value="Headful.fasta" />
            <param name="surrounding" value="0" />
        </test>
        <test>
            <param name="phagename" value="Test-Mu-like" />
            <param name="fastq" value="Mu-like_R1.fastq" />
            <param name="paired" value="Mu-like_R2.fastq" />
            <param name="reference" value="Mu-like.fasta" />
            <param name="host" value="Mu-like_host.fasta" />
            <param name="surrounding" value="0" />
        </test>
    </tests>
    <help>

**What it does**

PhageTerm software is a tool to determine phage termini and packaging mode from high throughput sequences
that rely on the random fragmentation of DNA (e.g. Illumina TruSeq, but NOT Nextera).

-----

**Methods**

Our methods is based on the detection of biases in the number of reads that start at natural DNA termini compared to elsewhere along the phage genome.
Preprint manuscript: http://biorxiv.org/content/early/2017/02/16/108100
Source Code: https://sourceforge.net/projects/phageterm.

-----

**Inputs**

- Raw reads file in fastq format
- Phage genome in fasta format
- Raw paired-ends reads file in fastq format (optional)
- Host genome in fasta format (optional)

-----

**Options**

Name of the phage being analyzed by the user (Default: my_phage)
Length of the seed used for reads in the mapping process (Default: 20)
Length of the surrounding used to merge close peaks in the analysis process (Default: 20)
Define phage target mean coverage (Default: 250)

-----

**Outputs**

- Report (.pdf)
- Statistical table (.csv)
- Phage Sequence (.fasta)
- Cohesive or DTR sequence (.fasta)


    </help>
    <citations>
        <citation type="doi">10.1038/s41598-017-07910-5</citation>
    </citations>
</tool>