comparison rg_rnaStarSolo.xml @ 14:1cd2511a396e draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/rgrnastar commit 904cd12820a09a8e7ce7d01c64fa22f1ed93ed17

13:9ee34ba73ebf

    #end if
    ## Splice junctions are always under "raw" directory

    --soloOutFormatFeaturesGeneField3 '${solo.soloOutFormatFeaturesGeneField3}'

    ## Limits
    @LIMITS@

    ##outWig:
    @OUTWIG@

            <when value="indexed">
                <conditional name="GTFconditional">
                    <param name="GTFselect" type="select"
                           label="Reference genome with annotation"
                           help="Select the '... with builtin gene-model' option to select from the list of available indexes that were built with splice junction information. Select the '... without builtin gene-model' option to select from the list of available indexes without annotated splice junctions, and provide your own splice junction annonations.">
                        <option value="without-gtf" selected='true'>use genome reference without builtin gene-model</option>
                        <option value="with-gtf">use genome reference with builtin gene-model</option>
                    </param>
                    <when value="with-gtf">
                        <expand macro="index_selection" with_gene_model="1" />
                    </when>
                    <when value="without-gtf">
                        <expand macro="index_selection" with_gene_model="0" />
                        <expand macro="SJDBOPTIONS"/>
                    </when>
                </conditional>
            </when>

                <param name="cell_ids" format="txt,tsv" type="data" label="File containing cell IDs of the samples. One ID per line in order of samples in the above collection."/>
                <conditional name="umidedup">
                    <param argument="--soloUMIdedup" type="select" label="UMI deduplication (collapsing) algorithm" help="All has all UMIs with 1 mismatch distance to each other collapsed, Directional follows the 'directional' method given in UMI-tools, Exact collapses only exactly matching UMIs.">
                        <expand macro="umidedup_options" />
                        <option value="Exact" >Exact</option>
                        <option value="NoDedup" >CellRanger2-4 algorithm</option>
                    </param>
                    <when value="1MM_All"/>
                    <when value="1MM_Directional_UMItools"/>
                    <when value="1MM_Directional"/>
                    <when value="Exact"/>

            <param argument="--outSAMattributes" type="select" display="checkboxes" multiple="true" optional="true"
            label="Read alignment tags to include in the BAM output">
                <expand macro="common_SAM_attributes"/>
                <option value="CR">CR Cellular barcode sequence bases (uncorrected)</option>
                <option value="CY">CY Phred quality of the cellular barcode sequence in the CR tag</option>
                <option value="GX">GX Gene ID</option>
                <option value="GN">GN Gene name</option>
                <option value="CB">CB Cell identifier (corrected)</option>
                <option value="UB">UB UMI (corrected)</option>
            </param>
            <param name="quantModeGene" type="boolean" truevalue="GeneCounts" falsevalue="" checked="false" label="Output global gene count" help="Can be used by MultiQC" />
            <expand macro="limits" />
        </section>
        <expand macro="outWig"/>
    </inputs>
    <outputs>

            <expand macro="dbKeyActions" />
        </data>
        <data format="txt" name="output_stats" label="${tool.name} on ${on_string}: Barcode/Feature Statistic Summaries"/>
        <data name="reads_per_gene" format="tabular" label="${tool.name} on ${on_string}: combined reads per gene" from_work_dir="ReadsPerGene.out.tab">
            <filter>solo['quantModeGene']</filter>
            <expand macro="dbKeyActions" />
            <expand macro="outCountActions" />
        </data>
        <expand macro="outWigOutputs"/>
    </outputs>
    <!-- Generating test data that is big enough for STARsolo to detect and small enough

            <output name="reads_per_gene" >
                <assert_contents>
                    <has_line_matching expression="ENSG00000279493\s+0\s+0\s+0" />
                    <has_line_matching expression="ENSG00000275464\s+38\s+1\s+40" />
                </assert_contents>
            </output>
        </test>
        <test expect_num_outputs="6">
            <!-- test 2 -->
            <!-- same as above, but using custom and no reads_per_gene-->
            <conditional name="refGenomeSource">
                <param name="geneSource" value="history" />
                <param name="genomeFastaFiles" value="filtered3.Homo_sapiens.GRCh38.dna.chromosome.21.fa.gz" />
                <param name="genomeSAindexNbases" value="4" />
                <param name="sjdbOverhang" value="100" />

                </conditional>
            </conditional>
            <section name="solo" >
                <param name="soloStrand" value="Forward" />
                <param name="soloFeatures" value="Gene" />
            </section>
            <output name="output_barcodes_filtered" >
                <assert_contents>
                    <!-- first and last line -->
                    <has_line line="ACACCGGTCTAACGGT" />

                <assert_contents>
                    <has_line_matching expression="\s+noUnmapped\s+5823" />
                    <has_line_matching expression="\s+yesUMIs\s+8" />
                </assert_contents>
            </output>
            <output name="output_BAM" value="filtered3.bam" compare="sim_size" delta="600" />
        </test>
        <test expect_num_outputs="6">
            <!-- test 3 -->
            <!-- Multiple repeats test -->
            <conditional name="refGenomeSource">

                    <has_line_matching expression="10\s+2\s+1" />
                    <has_n_lines n="107" />
                </assert_contents>
            </output>
        </test>
    </tests>
    <help><![CDATA[
**What it does**

**STARSolo** is a turnkey solution for analyzing droplet single cell RNA sequencing data (e.g. 10X Genomics Chromium System) built directly into STAR_ code. STARsolo takes raw FASTQ reads files as input, and performs the following operations:

14:1cd2511a396e

    #end if
    ## Splice junctions are always under "raw" directory

    --soloOutFormatFeaturesGeneField3 '${solo.soloOutFormatFeaturesGeneField3}'

    ## Unmapped
    '$solo.outSAMunmapped'
    ## Read MAPQ
    --outSAMmapqUnique ${solo.outSAMmapqUnique}
    ## Limits
    @LIMITS@

    ##outWig:
    @OUTWIG@

            <when value="indexed">
                <conditional name="GTFconditional">
                    <param name="GTFselect" type="select"
                           label="Reference genome with annotation"
                           help="Select the '... with builtin gene-model' option to select from the list of available indexes that were built with splice junction information. Select the '... without builtin gene-model' option to select from the list of available indexes without annotated splice junctions, and provide your own splice junction annonations.">
                        <option value="without-gtf-with-gtf" selected='true'>use genome reference without builtin gene-model</option>
                        <option value="with-gtf">use genome reference with builtin gene-model</option>
                    </param>
                    <when value="with-gtf">
                        <expand macro="index_selection" with_gene_model="1" />
                    </when>
                    <when value="without-gtf-with-gtf">
                        <expand macro="index_selection" with_gene_model="0" />
                        <expand macro="SJDBOPTIONS"/>
                    </when>
                </conditional>
            </when>

                <param name="cell_ids" format="txt,tsv" type="data" label="File containing cell IDs of the samples. One ID per line in order of samples in the above collection."/>
                <conditional name="umidedup">
                    <param argument="--soloUMIdedup" type="select" label="UMI deduplication (collapsing) algorithm" help="All has all UMIs with 1 mismatch distance to each other collapsed, Directional follows the 'directional' method given in UMI-tools, Exact collapses only exactly matching UMIs.">
                        <expand macro="umidedup_options" />
                        <option value="Exact" >Exact</option>
                        <option value="NoDedup" >Do not deduplicate UMIs</option>
                    </param>
                    <when value="1MM_All"/>
                    <when value="1MM_Directional_UMItools"/>
                    <when value="1MM_Directional"/>
                    <when value="Exact"/>

            <param argument="--outSAMattributes" type="select" display="checkboxes" multiple="true" optional="true"
            label="Read alignment tags to include in the BAM output">
                <expand macro="common_SAM_attributes"/>
                <option value="CR">CR Cellular barcode sequence bases (uncorrected)</option>
                <option value="CY">CY Phred quality of the cellular barcode sequence in the CR tag</option>
                <option value="UR">UR UMI (uncorrected)</option>
                <option value="UY">UY Phred quality of the UMI</option>
                <option value="GX">GX Gene ID</option>
                <option value="GN">GN Gene name</option>
                <option value="CB">CB Cell identifier (corrected)</option>
                <option value="UB">UB UMI (corrected)</option>
                <option value="sM">sM assessment of CB and UMI</option>
                <option value="sS">sS sequence of the entire barcode (CB,UMI,adapter...)</option>
                <option value="sQ">quality of the entire barcode</option>
            </param>
            <param name="quantModeGene" type="boolean" truevalue="GeneCounts" falsevalue="" checked="false" label="Output global gene count" help="Can be used by MultiQC" />
            <param argument="--outSAMunmapped" type="boolean" truevalue="--outSAMunmapped Within" falsevalue="--outSAMunmapped None" checked="false" label="Output unmapped reads in the BAM" />
            <expand macro="outSAMmapqUnique"/>
            <expand macro="limits" />
        </section>
        <expand macro="outWig"/>
    </inputs>
    <outputs>

            <expand macro="dbKeyActions" />
        </data>
        <data format="txt" name="output_stats" label="${tool.name} on ${on_string}: Barcode/Feature Statistic Summaries"/>
        <data name="reads_per_gene" format="tabular" label="${tool.name} on ${on_string}: combined reads per gene" from_work_dir="ReadsPerGene.out.tab">
            <filter>solo['quantModeGene']</filter>
            <expand macro="outCountActions" />
        </data>
        <expand macro="outWigOutputs"/>
    </outputs>
    <!-- Generating test data that is big enough for STARsolo to detect and small enough

            <output name="reads_per_gene" >
                <assert_contents>
                    <has_line_matching expression="ENSG00000279493\s+0\s+0\s+0" />
                    <has_line_matching expression="ENSG00000275464\s+38\s+1\s+40" />
                </assert_contents>
                <metadata name="column_names" value="GeneID,Counts_unstrand,Counts_firstStrand,Counts_secondStrand" />
            </output>
        </test>
        <test expect_num_outputs="6">
            <!-- test 2 -->
            <!-- same as above, but using custom, no reads_per_gene and include unmapped reads-->
            <conditional name="refGenomeSource">
                <param name="geneSource" value="history" />
                <param name="genomeFastaFiles" value="filtered3.Homo_sapiens.GRCh38.dna.chromosome.21.fa.gz" />
                <param name="genomeSAindexNbases" value="4" />
                <param name="sjdbOverhang" value="100" />

                </conditional>
            </conditional>
            <section name="solo" >
                <param name="soloStrand" value="Forward" />
                <param name="soloFeatures" value="Gene" />
                <param name="outSAMunmapped" value="true" />
            </section>
            <output name="output_barcodes_filtered" >
                <assert_contents>
                    <!-- first and last line -->
                    <has_line line="ACACCGGTCTAACGGT" />

                <assert_contents>
                    <has_line_matching expression="\s+noUnmapped\s+5823" />
                    <has_line_matching expression="\s+yesUMIs\s+8" />
                </assert_contents>
            </output>
            <output name="output_BAM">
                <assert_contents>
                    <has_size value="884669" delta="80000" />
                </assert_contents>
            </output>
        </test>
        <test expect_num_outputs="6">
            <!-- test 3 -->
            <!-- Multiple repeats test -->
            <conditional name="refGenomeSource">

                    <has_line_matching expression="10\s+2\s+1" />
                    <has_n_lines n="107" />
                </assert_contents>
            </output>
        </test>
        <test expect_num_outputs="7">
            <!-- test 11 indexed -->
            <conditional name="refGenomeSource">
                <param name="geneSource" value="indexed" />
                <conditional name="GTFconditional">
                    <param name="GTFselect" value="without-gtf-with-gtf" />
                    <param name="genomeDir" value="000" />
                    <param name="sjdbOverhang" value="75"/>
                    <param name="sjdbGTFfile" value="test1.gtf" ftype="gtf"/>
                </conditional>
            </conditional>
            <conditional name="sc" >
                <param name="solo_type" value="CB_UMI_Simple" />
                <conditional name="input_types">
                    <param name="use" value="repeat" />
                    <param name="input1" value="pbmc_1k_v2_L001.R1.10k.fastq.gz" ftype="fastqsanger.gz" />
                    <param name="input2" value="pbmc_1k_v2_L001.R2.10k.fastq.gz" ftype="fastqsanger.gz" />
                </conditional>
                <param name="soloCBwhitelist" value="filtered.barcodes.txt" />
                <conditional name="params">
                    <param name="chemistry" value="Cv3" />
                </conditional>
                <conditional name="umidedup">
                    <param name="soloUMIdedup" value="1MM_All" />
                </conditional>
            </conditional>
            <section name="solo" >
                <conditional name="filter">
                    <param name="filter_type" value="no_filter" />
                </conditional>
                <param name="soloStrand" value="Forward" />
                <param name="soloFeatures" value="Gene" />
                <param name="quantModeGene" value="true" />
            </section>
            <output name="output_barcodes" >
                <assert_contents>
                    <!-- first and last line -->
                    <has_line line="AAACCTGAGCGCTCCA" />
                    <has_line line="TTTGGTTAGTGGGCTA" />
                    <has_n_lines n="394" />
                </assert_contents>
            </output>
            <output name="output_genes">
                <assert_contents>
                    <has_line_matching expression="GENE1\s+GENE1\s+Gene\s+Expression" />
                    <has_n_lines n="1" />
                </assert_contents>
            </output>
            <output name="output_matrix" >
                <assert_contents>
                    <has_line_matching expression="1\s+394\s+31" />
                    <has_line_matching expression="1\s+2\s+1" />
                    <has_n_lines n="34" />
                </assert_contents>
            </output>
            <output name="output_stats" >
                <assert_contents>
                    <has_line_matching expression="\s+noUnmapped\s+6335" />
                    <has_line_matching expression="\s+yesUMIs\s+33" />
                </assert_contents>
            </output>
            <output name="output_BAM">
                <assert_contents>
                    <has_size value="7133" delta="1000"/>
                </assert_contents>
            </output>
            <output name="reads_per_gene" >
                <assert_contents>
                    <has_line_matching expression="GENE1\s+41\s+41\s+0" />
                </assert_contents>
            </output>
        </test>
    </tests>
    <help><![CDATA[
**What it does**

**STARSolo** is a turnkey solution for analyzing droplet single cell RNA sequencing data (e.g. 10X Genomics Chromium System) built directly into STAR_ code. STARsolo takes raw FASTQ reads files as input, and performs the following operations: