comparison pizzly.xml @ 1:91ef4a171202 draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/pizzly/ commit 0ad49d906b38e290b860310e73b1f8585ac65d09

0:f7556cfa4047

<tool id="pizzly" name="pizzly" version="0.37.3">
    <description>- fast fusion detection using kallisto</description>
    <requirements>
        <requirement type="package" version="0.37.3">pizzly</requirement>
    </requirements>
    <version_command>pizzly --version</version_command>
    <command detect_errors="exit_code"><![CDATA[
        
        ## Get reference FASTA 

        #if $ref_fa.rfasta.rfasta_source == "history":
            ln -s '$ref_fa.rfasta.ref_fa_hist' reference.fa &&
        #else:
            ln -s '$ref_fa.rfasta.ref_fa_builtin.fields.path' reference.fa &&
        #end if

        
        ## Get reference GTF

        #if $ref_gtf.rgtf.rgtf_source == "history":
            ln -s '$ref_gtf.rgtf.ref_gtf_hist' reference.gtf &&
        #else:
            ln -s '$ref_gtf.rgtf.ref_gtf_builtin.fields.path' reference.gtf &&
        #end if

        
        ## Run pizzly
        
        pizzly
        --fasta reference.fa
        --gtf reference.gtf
        --align-score '$adv.align_score'
        --insert-size '$adv.insert_size'
        --k '$adv.kmer_size'
        $adv.ignore_protein 
        --output out
        '$kinput.input'   &&

        
        ## Convert json output to tabular

        pizzly_flatten_json.py out.json > out.fusions.tab

    ]]></command>
    <inputs>
        <section name="kinput" expanded="false" title="Select kallisto fusions file">
            <param name="input" type="data" format="tabular" label="Output from kallisto quant --fusion" />
        </section>
        <section name="ref_fa" expanded="false" title="Select Reference FASTA"> 
            <conditional name="rfasta">
                <param name="rfasta_source" type="select" label="Reference transcriptome FASTA" help="Make sure the FASTA corresponds to the same file used with kallisto quant --fusion">
                    <option value="cached" selected="true">Use a built-in transcriptome</option>
                    <option value="history">Use a FASTA from history</option>
                </param>

                <option value="cached" selected="true">Use a built-in transcriptome</option>
                <option value="history">Use a GTF from history</option>
            </param>
            <when value="cached">
                <param name="ref_gtf_builtin" type="select" label="Select a built-in GTF" help="If the GTF file for your transcriptome of interest is not listed, contact your Galaxy administrator">
                    <options from_data_table="all_gtf">
                        <filter type="sort_by" column="2" />
                        <validator type="no_options" message="No GTF file is available." />
                    </options>
                </param>
            </when>
            <when value="history">
                <param name="ref_gtf_hist" type="data" format="gtf" label="Select a history GTF" /> 
            </when>
        </conditional>
        </section>
        <section name="adv" expanded="false" title="Advanced Options">
            <param name="insert_size" argument="--insert-size" type="integer" value="400" label="Maximum insert size of the paired-end library" help="kallisto will estimate this from the reads, default: 400">
                <validator type="in_range" min="0" />
            </param>  
            <param name="align_score" argument="--align-score" type="integer" value="2" label="Number of mismatches allowed" help="default: 2">
                <validator type="in_range" min="0" />
            </param> 
            <param name="kmer_size" argument="--k" type="integer" value="31" label="K-mer size used to create the kallisto index" help="default: 31">
                <validator type="in_range" min="0" />
            </param> 
            <param name="ignore_protein" argument="--ignore-protein" type="boolean" truevalue="--ignore-protein" falsevalue="" checked="false" label="Ignore protein coding information in annotation" help="Warning: this will probably lead to an increase in the number of false positives reported"/>
       </section> 
    </inputs>
    <outputs>
        <data name="fusions_tab" format="tabular" from_work_dir="out.fusions.tab" label="${tool.name} on ${on_string}: Table"/>
        <data name="fusions_fa" format="fasta" from_work_dir="out.fusions.fasta" label="${tool.name} on ${on_string}: Fasta"/>
    </outputs>
    <tests>
        <test>
            <param name="rfasta_source" value="history" />
            <param name="rgtf_source" value="history" />
            <param name="input" ftype="tabular" value="fusion.txt" />
            <param name="ref_fa_hist" ftype="fasta" value="ref.fasta.gz" />
            <param name="ref_gtf_hist" ftype="gtf" value="ref.gtf.gz" />
            <output name="fusions_tab" file="out.fusions.tab" ftype="tabular" />
            <output name="fusions_fa" file="out.fusions.fasta" ftype="fasta" />
        </test>
    </tests>
    <help><![CDATA[

.. class:: infomark

**What it does**

pizzly_ is a program for detecting gene fusions from RNA-Seq data of cancer samples. 

pizzly introduces a novel approach to fusion detection, it builds on the pseudoalignment idea (that simplifies and accelerates transcript quantification) by inspecting paired reads that cannot be pseudoaligned due to conflicting matches. pizzly filters false positives, assembles new transcripts from the fusion reads, and reports candidate fusions. 

With pizzly, fusion detection from RNA-Seq reads can be performed **in a matter of minutes**.

.. _pizzly: https://github.com/pmelsted/pizzly

**Outputs**

Two output files are created containing the filtered fusion calls

- a tabular file 
- a FASTA file 

-----

**More Information**

1:91ef4a171202

<tool id="pizzly" name="pizzly" version="0.37.3.1">
    <description>- fast fusion detection using kallisto</description>
    <requirements>
        <requirement type="package" version="0.37.3">pizzly</requirement>
    </requirements>
    <version_command>pizzly --version</version_command>
    <command detect_errors="exit_code"><![CDATA[

## Get reference FASTA

#if $ref_fa.rfasta.rfasta_source == "history":
    ln -s '$ref_fa.rfasta.ref_fa_hist' reference.fa &&
#else:
    ln -s '$ref_fa.rfasta.ref_fa_builtin.fields.path' reference.fa &&
#end if


## Get reference GTF

#if $ref_gtf.rgtf.rgtf_source == "history":
    ln -s '$ref_gtf.rgtf.ref_gtf_hist' reference.gtf &&
#else:
    ln -s '$ref_gtf.rgtf.ref_gtf_builtin.fields.path' reference.gtf &&
#end if


## Run pizzly

pizzly
--fasta reference.fa
--gtf reference.gtf
--align-score '$adv.align_score'
--insert-size '$adv.insert_size'
--k '$adv.kmer_size'
$adv.ignore_protein
--output out
'$kinput.input'   &&


## Convert json output to tabular

pizzly_flatten_json.py out.json > out.fusions.tab

    ]]></command>
    <inputs>
        <section name="kinput" expanded="false" title="Select kallisto fusions file">
            <param name="input" type="data" format="tabular" label="Output from kallisto quant --fusion" />
        </section>
        <section name="ref_fa" expanded="false" title="Select Reference FASTA">
            <conditional name="rfasta">
                <param name="rfasta_source" type="select" label="Reference transcriptome FASTA" help="Make sure the FASTA corresponds to the same file used with kallisto quant --fusion">
                    <option value="cached" selected="true">Use a built-in transcriptome</option>
                    <option value="history">Use a FASTA from history</option>
                </param>

                <option value="cached" selected="true">Use a built-in transcriptome</option>
                <option value="history">Use a GTF from history</option>
            </param>
            <when value="cached">
                <param name="ref_gtf_builtin" type="select" label="Select a built-in GTF" help="If the GTF file for your transcriptome of interest is not listed, contact your Galaxy administrator">
                    <options from_data_table="gene_sets">
                        <filter type="sort_by" column="2" />
                        <validator type="no_options" message="No GTF file is available." />
                    </options>
                </param>
            </when>
            <when value="history">
                <param name="ref_gtf_hist" type="data" format="gtf" label="Select a history GTF" />
            </when>
        </conditional>
        </section>
        <section name="adv" expanded="false" title="Advanced Options">
            <param name="insert_size" argument="--insert-size" type="integer" value="400" min="0" label="Maximum insert size of the paired-end library" help="kallisto will estimate this from the reads, default: 400" />
            <param name="align_score" argument="--align-score" type="integer" value="2" min="0" label="Number of mismatches allowed" help="default: 2" />
            <param name="kmer_size" argument="--k" type="integer" value="31" min="0" label="K-mer size used to create the kallisto index" help="default: 31" />
            <param name="ignore_protein" argument="--ignore-protein" type="boolean" truevalue="--ignore-protein" falsevalue="" checked="false" label="Ignore protein coding information in annotation" help="Warning: this will probably lead to an increase in the number of false positives reported"/>
       </section> 
    </inputs>
    <outputs>
        <data name="fusions_tab" format="tabular" from_work_dir="out.fusions.tab" label="${tool.name} on ${on_string}: Table"/>
        <data name="fusions_fa" format="fasta" from_work_dir="out.fusions.fasta" label="${tool.name} on ${on_string}: Fasta"/>
    </outputs>
    <tests>
        <test><!-- Ensure history fasta and gtf work -->
            <param name="rfasta_source" value="history" />
            <param name="rgtf_source" value="history" />
            <param name="input" ftype="tabular" value="fusion.txt" />
            <param name="ref_fa_hist" ftype="fasta" value="ref.trans.fasta.gz" />
            <param name="ref_gtf_hist" ftype="gtf" value="ref.gtf.gz" />
            <output name="fusions_tab" file="out.fusions.tab" ftype="tabular" />
            <output name="fusions_fa" file="out.fusions.fasta" ftype="fasta" />
        </test>
        <test><!-- Ensure built-in fasta and gtf work -->
            <param name="rfasta_source" value="cached" />
            <param name="rgtf_source" value="cached" />
            <param name="input" ftype="tabular" dbkey="hg38" value="fusion.txt" />
            <output name="fusions_tab" file="out.fusions.tab" ftype="tabular" />
            <output name="fusions_fa" file="out.fusions.fasta" ftype="fasta" />
        </test>
    </tests>
    <help><![CDATA[

.. class:: infomark

**What it does**

pizzly_ is a program for detecting gene fusions from RNA-Seq data of cancer samples.

pizzly introduces a novel approach to fusion detection, it builds on the pseudoalignment idea (that simplifies and accelerates transcript quantification) by inspecting paired reads that cannot be pseudoaligned due to conflicting matches. pizzly filters false positives, assembles new transcripts from the fusion reads, and reports candidate fusions.

With pizzly, fusion detection from RNA-Seq reads can be performed **in a matter of minutes**.

.. _pizzly: https://github.com/pmelsted/pizzly

**Outputs**

Two output files are created containing the filtered fusion calls

- a tabular file
- a FASTA file

-----

**More Information**