comparison stringtie.xml @ 23:8eb8750070d4 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/stringtie commit 252f4cccd66513c985b3df9480d73c8b9f994520

22:ae618321f34a

<tool id="stringtie" name="StringTie" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="21.05">
    <description>transcript assembly and quantification</description>
    <xrefs>
        <xref type="bio.tools">stringtie</xref>
    </xrefs>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <expand macro="stdio" />
    <expand macro="version_command" />
    <command><![CDATA[
#import re

            <when value="short_reads">
                <param name="input_bam" type="data" format="sam,bam,cram" label="Input short mapped reads" help="Input BAM/SAM/CRAM file containing the short reads you want to assemble into transcripts"/>
            </when>
            <when value="long_reads">
                <param name="input_bam" type="data" format="sam,bam,cram" label="Input long mapped reads" help="Input BAM/SAM/CRAM file containing the long reads you want to assemble into transcripts"/>
                <param name="error_splice" argument="-E" type="integer" min="0" max="50" value="25" label="Window around possibly erroneous splice sites" help="This option allows to define window around possibly erroneous splice sites from long reads to look out for correct splice sites. Default: 25" />
            </when>
            <when value="mixed_reads">
                <param name="input_bam_short" type="data" format="sam,bam,cram" label="Input short mapped reads" help="Input BAM/SAM/CRAM file containing the short reads you want to assemble into transcripts"/>
                <param name="input_bam_long" type="data" format="sam,bam,cram" label="Input long mapped reads" help="Input BAM/SAM/CRAM file containing the long reads you want to assemble into transcripts"/>
                <param name="error_splice" argument="-E" type="integer" min="0" max="50" value="25" label="Window around possibly erroneous splice sites" help="This option allows to define window around possibly erroneous splice sites from long reads to look out for correct splice sites. Default: 25" />
            </when>
        </conditional>
        <param name="rna_strandness" type="select" label="Specify strand information"
            help="Select 'Forward (FR)' if your reads are from a forward-stranded library, 'Reverse (RF)' if your reads are from a reverse-stranded library, or 'Unstranded' if your reads are not from a stranded library. See Help section below for more information. Default: Unstranded">
                <option value="" selected="true">Unstranded</option>

                        <option value="history">Use a file from history</option>
                    </param>
                    <when value="cached">
                        <param name="ref_builtin" type="select" label="Use 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_hist" type="data" format="gtf,gff3" label="GTF/GFF3 dataset to guide assembly" />
                    </when>
                </conditional>
                <param name="input_estimation" argument="-e" type="boolean" truevalue="-e" falsevalue="" checked="false" label="Use Reference transcripts only?" help="Limit the processing of read alignments to only estimate and output the assembled transcripts matching the reference transcripts given with the -G option. With this option, read bundles with no reference transcripts (novel transcripts) will be entirely skipped, which may provide a considerable speed boost when the given set of reference transcripts is limited to a set of target genes, for example. Default: No"/>
                <conditional name="special_outputs">
                    <param name="special_outputs_select" type="select" label="Output files for differential expression?" help="Select to output additional files that can be used with Ballgown or DESeq2/edgeR. See Help section below for more information">

                        <option value="deseq2">DESeq2/edgeR/limma-voom</option>
                        <option value="no" selected="true">No additional output</option>
                    </param>
                    <when value="ballgown" />
                    <when value="deseq2">
                        <param name="read_length" argument="--length" type="integer" min="0" value="75" label="Specify the average read length" help="Default: 75" />
                        <param name="clustering" argument="--cluster" type="boolean" truevalue="--cluster" falsevalue="" checked="false" label="Cluster overlapping genes" help="Choose whether to cluster genes with different gene IDs that overlap. Transcripts containing the geneID prefix will be ignored. Default: No" />
                        <param argument="--string" type="text" label="Prefix used for transcripts" help="If a different prefix was used for geneIDs assigned by StringTie than the default, specify it here. Only letters and numbers will be retained in this field. Default: MSTRG" >
                            <sanitizer>
                                <valid initial="string.letters,string.digits"></valid>
                            </sanitizer>
                        </param>
                        <param argument="--key" type="text" label="Prefix for clustering" help="If clustering, what prefix to use for geneIDs assigned by this script. Only letters and numbers will be retained in this field. Default: prepG">

                <param name="coverage_file" argument="-C" type="boolean" truevalue="-C" falsevalue="" checked="false" label="Output coverage file?" help="If StringTie is run with this option (requires -G), it returns a file with all the transcripts in the reference annotation that are fully covered, end to end, by reads. The output format is a GTF file as described below. Each line of the GTF corresponds to a gene or transcript in the reference annotation."/>
            </when>
        </conditional>
        <section name="adv" title="Advanced Options">
            <param name="abundance_estimation" argument="-A" type="boolean" truevalue="-A" falsevalue="" checked="false" label="Output gene abundance estimation file?" help="If selected, gene abundances will be reported in a tab-delimited file, see below for more information"/>
            <param name="omit_sequences" argument="-x" type="text" value="" label="Do not assemble any transcripts on these reference sequence(s)" help="Ignore all read alignments (and thus do not attempt to perform transcript assembly) on the specified reference sequences. This parameter can be a single reference sequence name (e.g. chrM) or a comma-delimited list of sequence names (e.g. chrM,chrX,chrY). This can speed up StringTie especially in the case of excluding the mitochondrial genome, whose genes may have very high coverage in some cases, even though they may be of no interest for a particular RNA-Seq analysis. The reference sequence names are case sensitive, they must match identically the names of chromosomes/contigs of the target genome against which the RNA-Seq reads were aligned in the first place." />
            <param name="name_prefix" argument="-l" type="text" label="Name prefix for output transcripts" help="This prefix will be added to the name of the transcripts that are output. Only letters and numbers will be retained in this field. Default: STRG">
                <sanitizer>
                    <valid initial="string.letters,string.digits"></valid>
                </sanitizer>
            </param>
            <param name="fraction" argument="-f" type="float" min="0.0" max="1.0" value="0.01" label="Minimum isoform fraction" help="Sets the minimum isoform abundance of the predicted transcripts as a fraction of the most abundant transcript assembled at a given locus. Lower abundance transcripts are often artifacts of incompletely spliced precursors of processed transcripts. Default: 0.05"/>
            <param name="min_tlen" argument="-m" type="integer" min="0" value="200" label="Minimum assembled transcript length" help="Sets the minimum length allowed for the predicted transcripts. Default: 200"/>
            <param name="min_anchor_len" argument="-a" type="integer" min="0" value="10" label="Minimum anchor length for junctions" help="Junctions that don't have spliced reads that align across them with at least this amount of bases on both sides are filtered out. Default: 10" />
            <param name="min_anchor_cov" argument="-j" type="integer" min="0" value="1" label="Minimum junction coverage" help="There should be at least this many spliced reads that align across a junction (i.e. junction coverage). This number can be fractional, since some reads align in more than one place. A read that aligns in n places will contribute 1/n to the junction coverage. Default: 1" />
            <param name="min_bundle_cov" argument="-c" type="integer" min="0" value="1" label="Minimum bundle reads per bp coverage to consider for assembly" help="Sets the minimum read coverage allowed for the predicted transcripts. A transcript with a lower coverage than this value is not shown in the output. Default: 2"/>
            <param name="bdist" argument="-g" type="integer" min="0" value="50" label="Gap between read mappings triggering a new bundle" help="Minimum locus gap separation value. Reads that are mapped closer than this distance are merged together in the same processing bundle. Default: 50 (bp)"/>
            <param name="bundle_fraction" argument="-M" type="float" min="0.0" max="1.0" value="1" label="Fraction of bundle allowed to be covered by multi-hit reads"  help="Sets the maximum fraction of muliple-location-mapped reads that are allowed to be present at a given locus. Default: 0.95"/>
            <param name="disable_trimming" argument="-t" type="boolean" truevalue="-t" falsevalue="" checked="false" label="Disable trimming of predicted transcripts based on coverage" help="This parameter disables trimming at the ends of the assembled transcripts. By default StringTie adjusts the predicted transcript's start and/or stop coordinates based on sudden drops in coverage of the assembled transcript. Default: No" />
            <param name="multi_mapping" argument="-u" type="boolean" truevalue="-u" falsevalue="" checked="false" label="Disable multi-mapping correction" help="Default: No"/>
            <param name="point_features" type="data" format="tabular" optional="true" label="Input point-features dataset" help="Loads a list of point-features from a text feature file to guide the transcriptome assembly. Accepted point features are transcription start sites (TSS) and polyadenylation sites (CPAS). There are four tab-delimited columns in the feature file. The first three define the location of the point feature on the cromosome (sequence name, coordinate and strand), and the last is the type of the feature (TSS or CPAS)."/>
        </section>
    </inputs>
    <outputs>
        <data name="output_gtf" format="gtf" label="${tool.name} on ${on_string}: Assembled transcripts" />
        <data name="gene_abundance_estimation" format="tabular" label="${tool.name} on ${on_string}: Gene abundance estimates">
            <filter>adv['abundance_estimation']</filter>
        </data>
        <data name="coverage" format="gtf" label="${tool.name} on ${on_string}: Coverage">
            <filter>guide['use_guide'] == 'yes' and guide['coverage_file'] is True </filter>

    <tests>
         <!--Ensure default GTF output works -->
        <test expect_num_outputs="1">
            <conditional name="input_options">
                <param name="input_mode" value="short_reads"/>
                <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />
            </conditional>
            <output name="output_gtf" file="stringtie_out1_re.gtf" ftype="gtf" compare="re_match" sort="true"/>
        </test>
        <!--Ensure fraction option works -->
        <test expect_num_outputs="1">
            <conditional name="input_options">
                <param name="input_mode" value="short_reads"/>
                <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />
            </conditional>            
            <param name="fraction" value="0.17" />
            <output name="output_gtf" file="stringtie_out2_re.gtf" ftype="gtf" compare="re_match" sort="true"/>
        </test>
        <!--Ensure guide option works -->
        <test expect_num_outputs="1">
            <conditional name="input_options">
                <param name="input_mode" value="short_reads"/>
                <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />
            </conditional>            
            <param name="use_guide" value="yes" />
            <param name="guide_gff_select" value="history" />
            <param name="ref_hist" ftype="gtf" value="stringtie_in.gtf" />
            <output name="output_gtf" file="stringtie_out3_re.gtf" ftype="gtf" compare="re_match" sort="true"/>
        </test>
        <!--Ensure guide with fraction works -->
        <test expect_num_outputs="1">
            <conditional name="input_options">
                <param name="input_mode" value="short_reads"/>
                <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />
            </conditional>            
            <param name="use_guide" value="yes" />
            <param name="guide_gff_select" value="history" />
            <param name="ref_hist" ftype="gtf" value="stringtie_in.gtf" />
            <param name="fraction" value="0.17" />
            <output name="output_gtf" file="stringtie_out4_re.gtf" ftype="gtf" compare="re_match" sort="true"/>
        </test>
        <!--Ensure coverage and output for Ballgown works -->
        <test expect_num_outputs="7">
            <conditional name="input_options">
                <param name="input_mode" value="short_reads"/>
                <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />
            </conditional>            
            <param name="use_guide" value="yes" />
            <param name="guide_gff_select" value="history" />
            <param name="ref_hist" ftype="gtf" value="stringtie_in.gtf" />
            <param name="special_outputs_select" value="ballgown" />
            <param name="coverage_file" value="true" />
            <output name="exon_expression" file="./ballgown/e_data.ctab" ftype="tabular" />
            <output name="intron_expression" file="./ballgown/i_data.ctab" ftype="tabular" />
            <output name="transcript_expression" file="./ballgown/t_data.ctab" ftype="tabular" />
            <output name="exon_transcript_mapping" file="./ballgown/e2t.ctab" ftype="tabular" />
            <output name="intron_transcript_mapping" file="./ballgown/i2t.ctab" ftype="tabular" />
            <output name="output_gtf" file="stringtie_out5.gtf" ftype="gtf" compare="re_match" sort="true"/>
            <output name="coverage" file="stringtie_out_coverage.gtf" ftype="gtf" compare="re_match" sort="true"/>
        </test>
        <!--Ensure output for edgeR works -->
        <test expect_num_outputs="5">
            <conditional name="input_options">
                <param name="input_mode" value="short_reads"/>
                <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />
            </conditional>            
            <param name="use_guide" value="yes" />
            <param name="special_outputs_select" value="deseq2" />
            <param name="input_estimation" value="true" />
            <param name="guide_gff_select" value="history" />
            <param name="ref_hist" ftype="gtf" value="stringtie_in.gtf" />
            <param name="coverage_file" value="true" />
            <param name="clustering" value="true" />
            <output name="gene_counts" file="gene_counts_edger.tsv" ftype="tabular" />
            <output name="transcript_counts" file="transcript_counts_edger.tsv" ftype="tabular" />
            <output name="legend" file="legend.tsv" ftype="tabular" />
            <output name="output_gtf" file="stringtie_out6.gtf" ftype="gtf" compare="re_match" sort="true"/>
            <output name="coverage" file="stringtie_out_coverage.gtf" ftype="gtf" compare="re_match" sort="true"/>
        </test>
        <!--Ensure gene abundances output works -->
        <test expect_num_outputs="2">
            <conditional name="input_options">
                <param name="input_mode" value="short_reads"/>
                <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />
            </conditional>            
            <param name="use_guide" value="yes" />
            <param name="guide_gff_select" value="history" />
            <param name="ref_hist" ftype="gtf" value="stringtie_in.gtf" />
            <param name="fraction" value="0.17" />
            <param name="abundance_estimation" value="true" />
            <output name="output_gtf" file="stringtie_out4_re.gtf" ftype="gtf" compare="re_match" sort="true"/>
            <output name="gene_abundance_estimation" file="stringtie_out7.tsv" ftype="tabular" lines_diff="2" />
        </test>
        <!--Ensure another fraction value works -->
        <test expect_num_outputs="1">
            <conditional name="input_options">
                <param name="input_mode" value="short_reads"/>
                <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />
            </conditional>            
            <param name="use_guide" value="yes" />
            <param name="guide_gff_select" value="history" />
            <param name="ref_hist" ftype="gtf" value="stringtie_in.gtf" />
            <param name="fraction" value="0.15" />
            <output name="output_gtf" file="stringtie_out8.gtf" ftype="gtf" compare="re_match" sort="true"/>
        </test>
        <!--Ensure built-in GTFs work -->
        <test expect_num_outputs="1">
            <conditional name="input_options">
                <param name="input_mode" value="short_reads"/>
                <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />
            </conditional>            
            <param name="use_guide" value="yes" />
            <param name="guide_gff_select" value="cached" />
            <param name="fraction" value="0.15" />
            <output name="output_gtf" file="stringtie_out9.gtf" ftype="gtf" compare="re_match" sort="true"/>
        </test>
        <!-- Test long reads input -->
        <test expect_num_outputs="1">
            <conditional name="input_options">
                <param name="input_mode" value="long_reads"/>
                <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />
            </conditional>            
            <param name="use_guide" value="yes" />
            <param name="guide_gff_select" value="cached" />
            <param name="fraction" value="0.15" />
            <output name="output_gtf" file="stringtie_out10.gtf" ftype="gtf" compare="re_match" sort="true"/>
        </test>
        <!-- Test error splice option -->
        <test expect_num_outputs="1">
            <conditional name="input_options">
                <param name="input_mode" value="long_reads"/>
                <param name="input_bam" ftype="bam" value="long_reads.bam" />
                <param name="error_splice" value="30" />
            </conditional>            
            <param name="use_guide" value="yes" />
            <param name="guide_gff_select" value="cached" />
            <param name="fraction" value="0.15" />
            <output name="output_gtf" file="stringtie_out11.gtf" ftype="gtf" compare="re_match" sort="true"/>
        </test>
        <!-- Test mixed reads input -->
        <test expect_num_outputs="1">
            <conditional name="input_options">
                <param name="input_mode" value="mixed_reads"/>
                <param name="input_bam_short" ftype="bam" value="short_reads.bam" />
                <param name="input_bam_long" ftype="bam" value="long_reads.bam" />
            </conditional>            
            <output name="output_gtf" ftype="gtf">
                <assert_contents>
                    <has_text text="5.043160"/>
                    <has_text text="StringTie version @TOOL_VERSION@"/>

        </test>
        <!-- Test cram input -->
        <test expect_num_outputs="1">
            <conditional name="input_options">
                <param name="input_mode" value="mixed_reads"/>
                <param name="input_bam_short" ftype="cram" value="stringtie_in.cram" />
                <param name="input_bam_long" ftype="cram" value="stringtie_in.cram" />
            </conditional>            
            <output name="output_gtf" ftype="gtf">
                <assert_contents>
                    <has_text text="gi|251831106|ref|NC_012920.1|"/>
                    <has_text text="StringTie version @TOOL_VERSION@"/>

23:8eb8750070d4

<tool id="stringtie" name="StringTie" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="22.05">
    <description>transcript assembly and quantification</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <xrefs>
        <xref type="bio.tools">stringtie</xref>
    </xrefs>
    <expand macro="requirements" />
    <expand macro="stdio" />
    <expand macro="version_command" />
    <command><![CDATA[
#import re

            <when value="short_reads">
                <param name="input_bam" type="data" format="sam,bam,cram" label="Input short mapped reads" help="Input BAM/SAM/CRAM file containing the short reads you want to assemble into transcripts"/>
            </when>
            <when value="long_reads">
                <param name="input_bam" type="data" format="sam,bam,cram" label="Input long mapped reads" help="Input BAM/SAM/CRAM file containing the long reads you want to assemble into transcripts"/>
                <param name="error_splice" argument="-E" type="integer" min="0" max="50" value="25" label="Window around possibly erroneous splice sites" help="This option allows to define window around possibly erroneous splice sites from long reads to look out for correct splice sites. Default: 25"/>
            </when>
            <when value="mixed_reads">
                <param name="input_bam_short" type="data" format="sam,bam,cram" label="Input short mapped reads" help="Input BAM/SAM/CRAM file containing the short reads you want to assemble into transcripts"/>
                <param name="input_bam_long" type="data" format="sam,bam,cram" label="Input long mapped reads" help="Input BAM/SAM/CRAM file containing the long reads you want to assemble into transcripts"/>
                <param name="error_splice" argument="-E" type="integer" min="0" max="50" value="25" label="Window around possibly erroneous splice sites" help="This option allows to define window around possibly erroneous splice sites from long reads to look out for correct splice sites. Default: 25"/>
            </when>
        </conditional>
        <param name="rna_strandness" type="select" label="Specify strand information"
            help="Select 'Forward (FR)' if your reads are from a forward-stranded library, 'Reverse (RF)' if your reads are from a reverse-stranded library, or 'Unstranded' if your reads are not from a stranded library. See Help section below for more information. Default: Unstranded">
                <option value="" selected="true">Unstranded</option>

                        <option value="history">Use a file from history</option>
                    </param>
                    <when value="cached">
                        <param name="ref_builtin" type="select" label="Use 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_hist" type="data" format="gtf,gff3" label="GTF/GFF3 dataset to guide assembly"/>
                    </when>
                </conditional>
                <param name="input_estimation" argument="-e" type="boolean" truevalue="-e" falsevalue="" checked="false" label="Use Reference transcripts only?" help="Limit the processing of read alignments to only estimate and output the assembled transcripts matching the reference transcripts given with the -G option. With this option, read bundles with no reference transcripts (novel transcripts) will be entirely skipped, which may provide a considerable speed boost when the given set of reference transcripts is limited to a set of target genes, for example. Default: No"/>
                <conditional name="special_outputs">
                    <param name="special_outputs_select" type="select" label="Output files for differential expression?" help="Select to output additional files that can be used with Ballgown or DESeq2/edgeR. See Help section below for more information">

                        <option value="deseq2">DESeq2/edgeR/limma-voom</option>
                        <option value="no" selected="true">No additional output</option>
                    </param>
                    <when value="ballgown" />
                    <when value="deseq2">
                        <param name="read_length" argument="--length" type="integer" min="0" value="75" label="Specify the average read length" help="Default: 75"/>
                        <param name="clustering" argument="--cluster" type="boolean" truevalue="--cluster" falsevalue="" checked="false" label="Cluster overlapping genes" help="Choose whether to cluster genes with different gene IDs that overlap. Transcripts containing the geneID prefix will be ignored. Default: No"/>
                        <param argument="--string" type="text" label="Prefix used for transcripts" help="If a different prefix was used for geneIDs assigned by StringTie than the default, specify it here. Only letters and numbers will be retained in this field. Default: MSTRG">
                            <sanitizer>
                                <valid initial="string.letters,string.digits"></valid>
                            </sanitizer>
                        </param>
                        <param argument="--key" type="text" label="Prefix for clustering" help="If clustering, what prefix to use for geneIDs assigned by this script. Only letters and numbers will be retained in this field. Default: prepG">

                <param name="coverage_file" argument="-C" type="boolean" truevalue="-C" falsevalue="" checked="false" label="Output coverage file?" help="If StringTie is run with this option (requires -G), it returns a file with all the transcripts in the reference annotation that are fully covered, end to end, by reads. The output format is a GTF file as described below. Each line of the GTF corresponds to a gene or transcript in the reference annotation."/>
            </when>
        </conditional>
        <section name="adv" title="Advanced Options">
            <param name="abundance_estimation" argument="-A" type="boolean" truevalue="-A" falsevalue="" checked="false" label="Output gene abundance estimation file?" help="If selected, gene abundances will be reported in a tab-delimited file, see below for more information"/>
            <param name="omit_sequences" argument="-x" type="text" value="" label="Do not assemble any transcripts on these reference sequence(s)" help="Ignore all read alignments (and thus do not attempt to perform transcript assembly) on the specified reference sequences. This parameter can be a single reference sequence name (e.g. chrM) or a comma-delimited list of sequence names (e.g. chrM,chrX,chrY). This can speed up StringTie especially in the case of excluding the mitochondrial genome, whose genes may have very high coverage in some cases, even though they may be of no interest for a particular RNA-Seq analysis. The reference sequence names are case sensitive, they must match identically the names of chromosomes/contigs of the target genome against which the RNA-Seq reads were aligned in the first place."/>
            <param name="name_prefix" argument="-l" type="text" label="Name prefix for output transcripts" help="This prefix will be added to the name of the transcripts that are output. Only letters and numbers will be retained in this field. Default: STRG">
                <sanitizer>
                    <valid initial="string.letters,string.digits"></valid>
                </sanitizer>
            </param>
            <param name="fraction" argument="-f" type="float" min="0.0" max="1.0" value="0.01" label="Minimum isoform fraction" help="Sets the minimum isoform abundance of the predicted transcripts as a fraction of the most abundant transcript assembled at a given locus. Lower abundance transcripts are often artifacts of incompletely spliced precursors of processed transcripts. Default: 0.05"/>
            <param name="min_tlen" argument="-m" type="integer" min="0" value="200" label="Minimum assembled transcript length" help="Sets the minimum length allowed for the predicted transcripts. Default: 200"/>
            <param name="min_anchor_len" argument="-a" type="integer" min="0" value="10" label="Minimum anchor length for junctions" help="Junctions that don't have spliced reads that align across them with at least this amount of bases on both sides are filtered out. Default: 10"/>
            <param name="min_anchor_cov" argument="-j" type="integer" min="0" value="1" label="Minimum junction coverage" help="There should be at least this many spliced reads that align across a junction (i.e. junction coverage). This number can be fractional, since some reads align in more than one place. A read that aligns in n places will contribute 1/n to the junction coverage. Default: 1"/>
            <param name="min_bundle_cov" argument="-c" type="integer" min="0" value="1" label="Minimum bundle reads per bp coverage to consider for assembly" help="Sets the minimum read coverage allowed for the predicted transcripts. A transcript with a lower coverage than this value is not shown in the output. Default: 2"/>
            <param name="bdist" argument="-g" type="integer" min="0" value="50" label="Gap between read mappings triggering a new bundle" help="Minimum locus gap separation value. Reads that are mapped closer than this distance are merged together in the same processing bundle. Default: 50 (bp)"/>
            <param name="bundle_fraction" argument="-M" type="float" min="0.0" max="1.0" value="1" label="Fraction of bundle allowed to be covered by multi-hit reads"  help="Sets the maximum fraction of muliple-location-mapped reads that are allowed to be present at a given locus. Default: 0.95"/>
            <param name="disable_trimming" argument="-t" type="boolean" truevalue="-t" falsevalue="" checked="false" label="Disable trimming of predicted transcripts based on coverage" help="This parameter disables trimming at the ends of the assembled transcripts. By default StringTie adjusts the predicted transcript's start and/or stop coordinates based on sudden drops in coverage of the assembled transcript. Default: No"/>
            <param name="multi_mapping" argument="-u" type="boolean" truevalue="-u" falsevalue="" checked="false" label="Disable multi-mapping correction" help="Default: No"/>
            <param name="point_features" type="data" format="tabular" optional="true" label="Input point-features dataset" help="Loads a list of point-features from a text feature file to guide the transcriptome assembly. Accepted point features are transcription start sites (TSS) and polyadenylation sites (CPAS). There are four tab-delimited columns in the feature file. The first three define the location of the point feature on the cromosome (sequence name, coordinate and strand), and the last is the type of the feature (TSS or CPAS)."/>
        </section>
    </inputs>
    <outputs>
        <data name="output_gtf" format="gtf" label="${tool.name} on ${on_string}: Assembled transcripts"/>
        <data name="gene_abundance_estimation" format="tabular" label="${tool.name} on ${on_string}: Gene abundance estimates">
            <filter>adv['abundance_estimation']</filter>
        </data>
        <data name="coverage" format="gtf" label="${tool.name} on ${on_string}: Coverage">
            <filter>guide['use_guide'] == 'yes' and guide['coverage_file'] is True </filter>

    <tests>
         <!--Ensure default GTF output works -->
        <test expect_num_outputs="1">
            <conditional name="input_options">
                <param name="input_mode" value="short_reads"/>
                <param name="input_bam" ftype="bam" value="stringtie_in1.bam"/>
            </conditional>
            <output name="output_gtf" file="stringtie_out1_re.gtf" ftype="gtf" lines_diff="2"/>
        </test>
        <!--Ensure fraction option works -->
        <test expect_num_outputs="1">
            <conditional name="input_options">
                <param name="input_mode" value="short_reads"/>
                <param name="input_bam" ftype="bam" value="stringtie_in1.bam"/>
            </conditional>            
            <param name="fraction" value="0.17"/>
            <output name="output_gtf" file="stringtie_out2_re.gtf" ftype="gtf" lines_diff="2"/>
        </test>
        <!--Ensure guide option works -->
        <test expect_num_outputs="1">
            <conditional name="input_options">
                <param name="input_mode" value="short_reads"/>
                <param name="input_bam" ftype="bam" value="stringtie_in1.bam"/>
            </conditional>            
            <param name="use_guide" value="yes"/>
            <param name="guide_gff_select" value="history"/>
            <param name="ref_hist" ftype="gtf" value="stringtie_in.gtf" />
            <output name="output_gtf" file="stringtie_out3_re.gtf" ftype="gtf" lines_diff="2"/>
        </test>
        <!--Ensure guide with fraction works -->
        <test expect_num_outputs="1">
            <conditional name="input_options">
                <param name="input_mode" value="short_reads"/>
                <param name="input_bam" ftype="bam" value="stringtie_in1.bam"/>
            </conditional>            
            <param name="use_guide" value="yes"/>
            <param name="guide_gff_select" value="history"/>
            <param name="ref_hist" ftype="gtf" value="stringtie_in.gtf"/>
            <param name="fraction" value="0.17"/>
            <output name="output_gtf" file="stringtie_out4_re.gtf" ftype="gtf" lines_diff="2"/>
        </test>
        <!--Ensure coverage and output for Ballgown works -->
        <test expect_num_outputs="7">
            <conditional name="input_options">
                <param name="input_mode" value="short_reads"/>
                <param name="input_bam" ftype="bam" value="stringtie_in1.bam"/>
            </conditional>            
            <param name="use_guide" value="yes"/>
            <param name="guide_gff_select" value="history"/>
            <param name="ref_hist" ftype="gtf" value="stringtie_in.gtf"/>
            <param name="special_outputs_select" value="ballgown"/>
            <param name="coverage_file" value="true"/>
            <output name="exon_expression" file="./ballgown/e_data.ctab" ftype="tabular"/>
            <output name="intron_expression" file="./ballgown/i_data.ctab" ftype="tabular"/>
            <output name="transcript_expression" file="./ballgown/t_data.ctab" ftype="tabular"/>
            <output name="exon_transcript_mapping" file="./ballgown/e2t.ctab" ftype="tabular"/>
            <output name="intron_transcript_mapping" file="./ballgown/i2t.ctab" ftype="tabular"/>
            <output name="output_gtf" file="stringtie_out5.gtf" ftype="gtf" lines_diff="2"/>
            <output name="coverage" file="stringtie_out_coverage.gtf" ftype="gtf" lines_diff="2"/>
        </test>
        <!--Ensure output for edgeR works -->
        <test expect_num_outputs="5">
            <conditional name="input_options">
                <param name="input_mode" value="short_reads"/>
                <param name="input_bam" ftype="bam" value="stringtie_in1.bam"/>
            </conditional>            
            <param name="use_guide" value="yes"/>
            <param name="special_outputs_select" value="deseq2"/>
            <param name="input_estimation" value="true"/>
            <param name="guide_gff_select" value="history" />
            <param name="ref_hist" ftype="gtf" value="stringtie_in.gtf"/>
            <param name="coverage_file" value="true"/>
            <param name="clustering" value="true"/>
            <output name="gene_counts" file="gene_counts_edger.tsv" ftype="tabular"/>
            <output name="transcript_counts" file="transcript_counts_edger.tsv" ftype="tabular"/>
            <output name="legend" file="legend.tsv" ftype="tabular"/>
            <output name="output_gtf" file="stringtie_out6.gtf" ftype="gtf" lines_diff="2"/>
            <output name="coverage" file="stringtie_out_coverage.gtf" ftype="gtf" lines_diff="2"/>
        </test>
        <!--Ensure gene abundances output works -->
        <test expect_num_outputs="2">
            <conditional name="input_options">
                <param name="input_mode" value="short_reads"/>
                <param name="input_bam" ftype="bam" value="stringtie_in1.bam"/>
            </conditional>            
            <param name="use_guide" value="yes"/>
            <param name="guide_gff_select" value="history"/>
            <param name="ref_hist" ftype="gtf" value="stringtie_in.gtf"/>
            <param name="fraction" value="0.17"/>
            <param name="abundance_estimation" value="true"/>
            <output name="output_gtf" file="stringtie_out4_re.gtf" ftype="gtf" lines_diff="2"/>
            <output name="gene_abundance_estimation" file="stringtie_out7.tsv" ftype="tabular" lines_diff="2" />
        </test>
        <!--Ensure another fraction value works -->
        <test expect_num_outputs="1">
            <conditional name="input_options">
                <param name="input_mode" value="short_reads"/>
                <param name="input_bam" ftype="bam" value="stringtie_in1.bam"/>
            </conditional>            
            <param name="use_guide" value="yes"/>
            <param name="guide_gff_select" value="history"/>
            <param name="ref_hist" ftype="gtf" value="stringtie_in.gtf"/>
            <param name="fraction" value="0.15"/>
            <output name="output_gtf" file="stringtie_out8.gtf" ftype="gtf" lines_diff="2"/>
        </test>
        <!--Ensure built-in GTFs work -->
        <test expect_num_outputs="1">
            <conditional name="input_options">
                <param name="input_mode" value="short_reads"/>
                <param name="input_bam" ftype="bam" value="stringtie_in1.bam"/>
            </conditional>            
            <param name="use_guide" value="yes"/>
            <param name="guide_gff_select" value="cached"/>
            <param name="fraction" value="0.15"/>
            <output name="output_gtf" file="stringtie_out9.gtf" ftype="gtf" lines_diff="2"/>
        </test>
        <!-- Test long reads input -->
        <test expect_num_outputs="1">
            <conditional name="input_options">
                <param name="input_mode" value="long_reads"/>
                <param name="input_bam" ftype="bam" value="stringtie_in1.bam"/>
            </conditional>            
            <param name="use_guide" value="yes"/>
            <param name="guide_gff_select" value="cached"/>
            <param name="fraction" value="0.15"/>
            <output name="output_gtf" file="stringtie_out10.gtf" ftype="gtf" lines_diff="2"/>
        </test>
        <!-- Test error splice option -->
        <test expect_num_outputs="1">
            <conditional name="input_options">
                <param name="input_mode" value="long_reads"/>
                <param name="input_bam" ftype="bam" value="long_reads.bam"/>
                <param name="error_splice" value="30"/>
            </conditional>            
            <param name="use_guide" value="yes"/>
            <param name="guide_gff_select" value="cached"/>
            <param name="fraction" value="0.15"/>
            <output name="output_gtf" file="stringtie_out11.gtf" ftype="gtf" lines_diff="2"/>
        </test>
        <!-- Test mixed reads input -->
        <test expect_num_outputs="1">
            <conditional name="input_options">
                <param name="input_mode" value="mixed_reads"/>
                <param name="input_bam_short" ftype="bam" value="short_reads.bam"/>
                <param name="input_bam_long" ftype="bam" value="long_reads.bam"/>
            </conditional>            
            <output name="output_gtf" ftype="gtf">
                <assert_contents>
                    <has_text text="5.043160"/>
                    <has_text text="StringTie version @TOOL_VERSION@"/>

        </test>
        <!-- Test cram input -->
        <test expect_num_outputs="1">
            <conditional name="input_options">
                <param name="input_mode" value="mixed_reads"/>
                <param name="input_bam_short" ftype="cram" value="stringtie_in.cram"/>
                <param name="input_bam_long" ftype="cram" value="stringtie_in.cram"/>
            </conditional>            
            <output name="output_gtf" ftype="gtf">
                <assert_contents>
                    <has_text text="gi|251831106|ref|NC_012920.1|"/>
                    <has_text text="StringTie version @TOOL_VERSION@"/>