Mercurial > repos > iuc > rna_starsolo
changeset 17:5ef7ec16b04f draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/rgrnastar commit 65fa34f035934b4e9c1fbeb5dffe00b12e6a0f32
| author | iuc |
|---|---|
| date | Fri, 01 Sep 2023 13:18:03 +0000 |
| parents | 13022c3d3076 |
| children | 8dc4a444ec04 |
| files | macros.xml rg_rnaStarSolo.xml test-data/fakexon.Homo_sapiens.GRCh38.100.chr21.gtf test-data/no_exon.gtf test-data/rnastar_test_mapped_reads_fakexon.bam |
| diffstat | 5 files changed, 536 insertions(+), 2 deletions(-) [+] |
line wrap: on
line diff
--- a/macros.xml Mon Mar 27 16:38:01 2023 +0000 +++ b/macros.xml Fri Sep 01 13:18:03 2023 +0000 @@ -5,7 +5,7 @@ the index versions in sync, but you should manually update @IDX_VERSION_SUFFIX@ --> <!-- STAR version to be used --> <token name="@TOOL_VERSION@">2.7.10b</token> - <token name="@VERSION_SUFFIX@">3</token> + <token name="@VERSION_SUFFIX@">4</token> <token name="@PROFILE@">21.01</token> <!-- STAR index version compatible with this version of STAR This is the STAR version that introduced the index structure expected @@ -60,6 +60,7 @@ </xml> <xml name="SJDBOPTIONS"> <param argument="--sjdbGTFfile" type="data" format="gff3,gtf" label="Gene model (gff3,gtf) file for splice junctions" optional="false" help="Exon junction information for mapping splices"/> + <param argument="--sjdbGTFfeatureExon" type="text" value="exon" label="Elements to use from the gene model to use for splice junctions" help="By default and for almost all cases: 'exon', referring to finding junctions at the RNA splice sites. This can optionally be changed to allow splicing at other levels, such as 'gene', 'transcript', 'CDS'."/> <param argument="--sjdbOverhang" type="integer" min="1" value="100" label="Length of the genomic sequence around annotated junctions" help="Used in constructing the splice junctions database. Ideal value is ReadLength-1"/> </xml> <xml name="dbKeyActions"> @@ -103,15 +104,17 @@ #if str($refGenomeSource.GTFconditional.GTFselect) == 'with-gtf': --sjdbOverhang '${refGenomeSource.GTFconditional.sjdbOverhang}' --sjdbGTFfile '${refGenomeSource.GTFconditional.sjdbGTFfile}' + --sjdbGTFfeatureExon '${refGenomeSource.GTFconditional.sjdbGTFfeatureExon}' #if str($refGenomeSource.GTFconditional.sjdbGTFfile.ext) == 'gff3': --sjdbGTFtagExonParentTranscript Parent #end if #end if #else: - ## ref genome selection is less complex for STARsolo cause + ## ref genome selection is less complex for STARsolo because ## with-gtf is mandatory there --sjdbOverhang '${refGenomeSource.sjdbOverhang}' --sjdbGTFfile '${refGenomeSource.sjdbGTFfile}' + --sjdbGTFfeatureExon '${refGenomeSource.sjdbGTFfeatureExon}' #if str($refGenomeSource.sjdbGTFfile.ext) == 'gff3': --sjdbGTFtagExonParentTranscript Parent #end if @@ -137,6 +140,7 @@ #if str($refGenomeSource.GTFconditional.GTFselect) == 'without-gtf-with-gtf': --sjdbOverhang $refGenomeSource.GTFconditional.sjdbOverhang --sjdbGTFfile '${refGenomeSource.GTFconditional.sjdbGTFfile}' + --sjdbGTFfeatureExon '${refGenomeSource.GTFconditional.sjdbGTFfeatureExon}' #if str($refGenomeSource.GTFconditional.sjdbGTFfile.ext) == 'gff3': --sjdbGTFtagExonParentTranscript Parent #end if
--- a/rg_rnaStarSolo.xml Mon Mar 27 16:38:01 2023 +0000 +++ b/rg_rnaStarSolo.xml Fri Sep 01 13:18:03 2023 +0000 @@ -1306,6 +1306,71 @@ <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><