comparison rg_rnaStarSolo.xml @ 17:5ef7ec16b04f draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/rgrnastar commit 65fa34f035934b4e9c1fbeb5dffe00b12e6a0f32

16:13022c3d3076

                    <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>
    </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:

17:5ef7ec16b04f

                    <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 13
            If the splice feature set is not set correctly,
            "Fatal INPUT FILE error, no exon lines in the GTF file" is expected -->
            <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" />
                <param name="sjdbGTFfile" value="fakexon.Homo_sapiens.GRCh38.100.chr21.gtf" ftype="gtf"/>
                <param name="sjdbGTFfeatureExon" value="fakexon"/>
            </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 Velocyto" />
                <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="ENSG00000279493\s+FP565260\.4\s+Gene\s+Expression" />
                    <has_line_matching expression="ENSG00000279064\s+FP236315\.1\s+Gene\s+Expression" />
                    <has_n_lines n="14" />
                </assert_contents>
            </output>
            <output name="output_stats" >
                <assert_contents>
                    <has_line_matching expression="\s+noUnmapped\s+0" />
                    <has_line_matching expression="\s+yesUMIs\s+36" />
                </assert_contents>
            </output>
            <output name="output_BAM" value="filtered3.bam" compare="sim_size" delta="600" />
            <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>
    </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: