<tool id="psiclass" name="PsiCLASS" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="21.05">
    <description>reference-based transcriptome assembler</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <xrefs>
        <xref type="bio.tools">psiclass</xref>
    </xrefs>
    <expand macro="requirements" />
    <command detect_errors='exit_code'><![CDATA[
            mkdir -p "annotation_files" &&
            #set $bam_filenames = []
            #for $i,$file in enumerate($bam_files)
                #set $name = 'bam_' + str($i) + '.bam'
                ln -s '${file}' $name &&
                $bam_filenames.append($name)
            #end for
            #set $allFiles = ','.join( [ str( $file ) for $file in $bam_filenames ] )
            psiclass
                -b  $allFiles 
                -p \${GALAXY_SLOTS:-8}
                #if $splice_conditional.selector == 'true'
                    -s '${splice_conditional.splice_file}'
                #end if
                -c $subexonClassifier
                --sa $intronCoverage
                --vd $transcriptCoverage
                #if $stranded
                    --stranded $stranded
                #end if
                --maxDpConstraintSize $maxDpConstraintSize
                $primaryParalog
                --tssTesQuantile $tssTesQuantile
            && mv *sample* "./annotation_files"
            #if $splice_conditional.selector == 'false'
                && cat ./splice/psiclass_bam.trusted_splice > '${splice_sites}'
            #end if
    ]]></command>
    <inputs>
        <param argument="-b" name="bam_files" type="data" format="bam" multiple="true" label="BAM file(s)"
             help="PsiCLASS has been tuned to run on alignments generated with the tools HISAT and STAR" />
        <conditional name="splice_conditional">
            <param name="selector" type="select" label="Provide trusted splice sites coordinates" help="It is possible to supply 
                an set of trusted introns, for instance generated by RNASTAR or extracted from the GENCODE gene annotations">
                <option value="true">Enabled</option>
                <option value="false" selected="true">Disabled</option>
            </param>
            <when value="true">
                <param argument="-s" name="splice_file" type="data" format="interval" optional="true" label="Splice junction sites file" help="High confidence collapsed splice junction file" />
            </when>
            <when value="false"/>
        </conditional>
        <param argument="-c" type="float" name="subexonClassifier" min="0" max="1" value="0.05" label="Subexon classifier score threshold" 
            help="Only use the subexons with classifier score minor or equal than the given number" />
        <param argument="--sa" name="intronCoverage" type="float" min="0" value="0.5" label="Minimum retained intron converage" 
            help="Minimum average number of supported read for retained introns" />
        <param argument="--vd" name="transcriptCoverage" type="float" min="0" value="1" label="Minimum transcript coverage" 
            help="Minimum average coverage depth of a transcript to be reported" />
        <param argument="--stranded" type="select" optional="true" label="Library strand information" help="Stranded data shows advantages over 
            non-stranded RNA-Seq data such as higher assembly and differential expression accuracy">
            <option value="un">unstranded</option>
            <option value="rf">fr-firststrand (rf): first read from the opposite strand.</option>
            <option value="fr">fr-secondstrand (fr): first read from the transcript strand</option>
        </param>
        <param argument="--maxDpConstraintSize" type="integer" min="-1" value="7" label="Constrain cover iN  median exon depth (DP)" help="-1 for infinite"/>
        <param argument="--primaryParalog" type="boolean" truevalue="--primaryParalog" falsevalue="" checked="false" optional="true"
            label="Use primary alignment to retain paralog genes" help="Default: use unique alignments" />
        <param argument="--tssTesQuantile" type="float" min="0" max="1" value="0.5" label="Quantile for transcription start/end sites in subexon graph"/>
    </inputs>
    <outputs>
        <data name="meta_anotation" format="gtf"  from_work_dir="psiclass_vote.gtf" label="${tool.name} on ${on_string}: meta-annotation" />
        <collection name="annotation_collection" type="list" label="${tool.name} on ${on_string}: per-sample annotations">
            <discover_datasets pattern="__designation_and_ext__" format="gtf" directory="annotation_files"/>
        </collection>
        <data name="splice_sites" format="interval" label="${tool.name} on ${on_string}: splice sites">
            <filter>splice_conditional["selector"] == "false"</filter>
        </data>
    </outputs>
    <tests>
        <test expect_num_outputs="2">
            <param name="bam_files" value="reads1.bam,reads2.bam"/>
            <param name="subexonClassifier" value="0.05"/>
            <param name="intronCoverage" value="0.5"/>
            <param name="transcriptCoverage" value="1"/>
            <param name="stranded" value="un"/>
            <param name="maxDpConstraintSize" value="7"/>
            <param name="primaryParalog" value="false"/>
            <param name="tssTesQuantile" value="0.5"/>
            <conditional name="splice_conditional">
                <param name="selector" value="true"/>
                <param name="splice_file" value="splice_sites.interval"/>
            </conditional>
            <output name="meta_anotation" ftype="gtf" file="test01_meta_annotation.gtf" lines_diff="2"/>
            <output_collection name="annotation_collection" type="list" count="2">
                <element name="psiclass_sample_0" ftype="gtf" file="test01_annotation_sample0.gtf" lines_diff="2"/>
                <element name="psiclass_sample_1" ftype="gtf" file="test01_annotation_sample1.gtf" lines_diff="2"/>
            </output_collection>
        </test>
        <test expect_num_outputs="3">
            <param name="bam_files" value="reads1.bam,reads2.bam"/>
            <param name="subexonClassifier" value="0.05"/>
            <param name="intronCoverage" value="0.3"/>
            <param name="transcriptCoverage" value="0.5"/>
            <param name="stranded" value="rf"/>
            <param name="maxDpConstraintSize" value="6"/>
            <param name="primaryParalog" value="true"/>
            <param name="tssTesQuantile" value="0.4"/>
            <conditional name="splice_conditional">
                <param name="selector" value="false"/>
            </conditional>
            <output name="meta_anotation" ftype="gtf" file="test02_meta_annotation.gtf"/>
            <output_collection name="annotation_collection" type="list" count="2">
                <element name="psiclass_sample_0" ftype="gtf" file="test02_annotation_sample0.gtf" lines_diff="2"/>
                <element name="psiclass_sample_1" ftype="gtf" file="test02_annotation_sample1.gtf" lines_diff="2"/>
            </output_collection>
            <output name="splice_sites" ftype="interval" file="test02_splice_sites.txt"/>
        </test>
        <test expect_num_outputs="3">
            <param name="bam_files" value="reads1.bam"/>
            <output name="meta_anotation" ftype="gtf" file="test03_meta_annotation.gtf"/>
            <output_collection name="annotation_collection" type="list" count="1">
                <element name="psiclass_sample_0" ftype="gtf" file="test03_annotation_sample0.gtf" lines_diff="2"/>
            </output_collection>
            <output name="splice_sites" file="test03_splice_sites.txt" ftype="interval"/>
        </test>
    </tests>
    <help><![CDATA[

.. class:: infomark

**What is PsiCLASS?**

PsiCLASS is a reference-based transcriptome assembler for single or multiple RNA-seq samples. 

Unlike conventional methods that analyze each sample separately and then merge the outcomes to create a unified set of meta-annotations, 
PsiCLASS takes a multi-sample approach, simultaneously analyzing all RNA-seq data sets in an experiment. 

PsiCLASS is both a transcript assembler and a meta-assembler, producing separate transcript sets for the individual samples and a unified 
set of meta-annotations. The algorithmic underpinnings of PsiCLASS include using a global subexon splice graph, statistical cross-sample 
feature (intron, subexon) selection methods, and an efficient dynamic programming algorithm to select a subset of transcripts from among 
those encoded in the graph, based on the read support in each sample.

Lastly, the set of meta-annotations is selected from among the transcripts generated for individual samples by voting. While PsiCLASS is 
highly accurate and efficient for medium-to-large collections of RNA-seq data, its accuracy is equally high for small RNA-seq data sets 
(2-10 samples) and is competitive to reference methods for single samples. Additionally, its performance is robust with the aggregation 
method used, including the built-in voting and assembly-based approaches such as StringTie-merge and TACO. Therefore, it can be effectively 
used as a multi-sample and as a single-sample assembler, as well as in conventional assemble-and-merge protocols.

    ]]></help>
    <expand macro="citations" />
</tool>