| Previous changeset 16:13022c3d3076 (2023-03-27) Next changeset 18:8dc4a444ec04 (2024-02-11) |
|
Commit message:
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/rgrnastar commit 65fa34f035934b4e9c1fbeb5dffe00b12e6a0f32 |
|
modified:
macros.xml rg_rnaStarSolo.xml |
|
added:
test-data/fakexon.Homo_sapiens.GRCh38.100.chr21.gtf test-data/no_exon.gtf test-data/rnastar_test_mapped_reads_fakexon.bam |
| b |
| diff -r 13022c3d3076 -r 5ef7ec16b04f macros.xml --- a/macros.xml Mon Mar 27 16:38:01 2023 +0000 +++ b/macros.xml Fri Sep 01 13:18:03 2023 +0000 |
| b |
| @@ -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 |
| b |
| diff -r 13022c3d3076 -r 5ef7ec16b04f rg_rnaStarSolo.xml --- 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><![CDATA[ **What it does** |
| b |
| diff -r 13022c3d3076 -r 5ef7ec16b04f test-data/fakexon.Homo_sapiens.GRCh38.100.chr21.gtf --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/fakexon.Homo_sapiens.GRCh38.100.chr21.gtf Fri Sep 01 13:18:03 2023 +0000 |
| b |
| b'@@ -0,0 +1,461 @@\n+#!genome-build GRCh38.p13\n+#!genome-version GRCh38\n+#!genome-date 2013-12\n+#!genome-build-accession NCBI:GCA_000001405.28\n+#!genebuild-last-updated 2019-06\n+21\thavana\tgene\t1000\t6346\t.\t+\t.\tgene_id "ENSG00000279493"; gene_version "1"; gene_name "FP565260.4"; gene_source "havana"; gene_biotype "protein_coding";\n+21\thavana\ttranscript\t1000\t6346\t.\t+\t.\tgene_id "ENSG00000279493"; gene_version "1"; transcript_id "ENST00000624081"; transcript_version "1"; gene_name "FP565260.4"; gene_source "havana"; gene_biotype "protein_coding"; transcript_name "FP565260.4-201"; transcript_source "havana"; transcript_biotype "protein_coding"; tag "cds_start_NF"; tag "mRNA_start_NF"; tag "basic"; transcript_support_level "5";\n+21\thavana\tfakexon\t1000\t1075\t.\t+\t.\tgene_id "ENSG00000279493"; gene_version "1"; transcript_id "ENST00000624081"; transcript_version "1"; exon_number "1"; gene_name "FP565260.4"; gene_source "havana"; gene_biotype "protein_coding"; transcript_name "FP565260.4-201"; transcript_source "havana"; transcript_biotype "protein_coding"; exon_id "ENSE00003760288"; exon_version "1"; tag "cds_start_NF"; tag "mRNA_start_NF"; tag "basic"; transcript_support_level "5";\n+21\thavana\tCDS\t1000\t1075\t.\t+\t0\tgene_id "ENSG00000279493"; gene_version "1"; transcript_id "ENST00000624081"; transcript_version "1"; exon_number "1"; gene_name "FP565260.4"; gene_source "havana"; gene_biotype "protein_coding"; transcript_name "FP565260.4-201"; transcript_source "havana"; transcript_biotype "protein_coding"; protein_id "ENSP00000485664"; protein_version "1"; tag "cds_start_NF"; tag "mRNA_start_NF"; tag "basic"; transcript_support_level "5";\n+21\thavana\tfakexon\t1749\t1888\t.\t+\t.\tgene_id "ENSG00000279493"; gene_version "1"; transcript_id "ENST00000624081"; transcript_version "1"; exon_number "2"; gene_name "FP565260.4"; gene_source "havana"; gene_biotype "protein_coding"; transcript_name "FP565260.4-201"; transcript_source "havana"; transcript_biotype "protein_coding"; exon_id "ENSE00003758404"; exon_version "1"; tag "cds_start_NF"; tag "mRNA_start_NF"; tag "basic"; transcript_support_level "5";\n+21\thavana\tCDS\t1749\t1888\t.\t+\t2\tgene_id "ENSG00000279493"; gene_version "1"; transcript_id "ENST00000624081"; transcript_version "1"; exon_number "2"; gene_name "FP565260.4"; gene_source "havana"; gene_biotype "protein_coding"; transcript_name "FP565260.4-201"; transcript_source "havana"; transcript_biotype "protein_coding"; protein_id "ENSP00000485664"; protein_version "1"; tag "cds_start_NF"; tag "mRNA_start_NF"; tag "basic"; transcript_support_level "5";\n+21\thavana\tfakexon\t3587\t3672\t.\t+\t.\tgene_id "ENSG00000279493"; gene_version "1"; transcript_id "ENST00000624081"; transcript_version "1"; exon_number "3"; gene_name "FP565260.4"; gene_source "havana"; gene_biotype "protein_coding"; transcript_name "FP565260.4-201"; transcript_source "havana"; transcript_biotype "protein_coding"; exon_id "ENSE00003755466"; exon_version "1"; tag "cds_start_NF"; tag "mRNA_start_NF"; tag "basic"; transcript_support_level "5";\n+21\thavana\tCDS\t3587\t3672\t.\t+\t0\tgene_id "ENSG00000279493"; gene_version "1"; transcript_id "ENST00000624081"; transcript_version "1"; exon_number "3"; gene_name "FP565260.4"; gene_source "havana"; gene_biotype "protein_coding"; transcript_name "FP565260.4-201"; transcript_source "havana"; transcript_biotype "protein_coding"; protein_id "ENSP00000485664"; protein_version "1"; tag "cds_start_NF"; tag "mRNA_start_NF"; tag "basic"; transcript_support_level "5";\n+21\thavana\tfakexon\t6136\t6346\t.\t+\t.\tgene_id "ENSG00000279493"; gene_version "1"; transcript_id "ENST00000624081"; transcript_version "1"; exon_number "4"; gene_name "FP565260.4"; gene_source "havana"; gene_biotype "protein_coding"; transcript_name "FP565260.4-201"; transcript_source "havana"; transcript_biotype "protein_coding"; exon_id "ENSE00003755385"; exon_version "1"; tag "cds_start_NF"; tag "mRNA_start_NF"; tag "basic"; transcript_support_level "5";\n+21\thavana\tCDS\t6136\t6298\t.\t+\t1\tgene_id "ENSG0000027'..b'6691\t.\t+\t.\tgene_id "ENSG00000277777"; gene_version "1"; gene_name "CU633967.2"; gene_source "ensembl"; gene_biotype "misc_RNA";\n+21\tensembl\ttranscript\t586591\t586691\t.\t+\t.\tgene_id "ENSG00000277777"; gene_version "1"; transcript_id "ENST00000610788"; transcript_version "1"; gene_name "CU633967.2"; gene_source "ensembl"; gene_biotype "misc_RNA"; transcript_name "CU633967.2-201"; transcript_source "ensembl"; transcript_biotype "misc_RNA"; tag "basic"; transcript_support_level "NA";\n+21\tensembl\tfakexon\t586591\t586691\t.\t+\t.\tgene_id "ENSG00000277777"; gene_version "1"; transcript_id "ENST00000610788"; transcript_version "1"; exon_number "1"; gene_name "CU633967.2"; gene_source "ensembl"; gene_biotype "misc_RNA"; transcript_name "CU633967.2-201"; transcript_source "ensembl"; transcript_biotype "misc_RNA"; exon_id "ENSE00003748388"; exon_version "1"; tag "basic"; transcript_support_level "NA";\n+21\thavana\tgene\t692383\t694838\t.\t-\t.\tgene_id "ENSG00000279186"; gene_version "1"; gene_name "FP236315.2"; gene_source "havana"; gene_biotype "TEC";\n+21\thavana\ttranscript\t692383\t694838\t.\t-\t.\tgene_id "ENSG00000279186"; gene_version "1"; transcript_id "ENST00000624506"; transcript_version "1"; gene_name "FP236315.2"; gene_source "havana"; gene_biotype "TEC"; transcript_name "FP236315.2-201"; transcript_source "havana"; transcript_biotype "TEC"; tag "basic"; transcript_support_level "NA";\n+21\thavana\tfakexon\t692383\t694838\t.\t-\t.\tgene_id "ENSG00000279186"; gene_version "1"; transcript_id "ENST00000624506"; transcript_version "1"; exon_number "1"; gene_name "FP236315.2"; gene_source "havana"; gene_biotype "TEC"; transcript_name "FP236315.2-201"; transcript_source "havana"; transcript_biotype "TEC"; exon_id "ENSE00003756739"; exon_version "1"; tag "basic"; transcript_support_level "NA";\n+21\thavana\tgene\t694546\t696361\t.\t+\t.\tgene_id "ENSG00000279784"; gene_version "1"; gene_name "FP236315.3"; gene_source "havana"; gene_biotype "lncRNA";\n+21\thavana\ttranscript\t694546\t696361\t.\t+\t.\tgene_id "ENSG00000279784"; gene_version "1"; transcript_id "ENST00000623587"; transcript_version "1"; gene_name "FP236315.3"; gene_source "havana"; gene_biotype "lncRNA"; transcript_name "FP236315.3-201"; transcript_source "havana"; transcript_biotype "lncRNA"; tag "basic"; transcript_support_level "2";\n+21\thavana\tfakexon\t694546\t694654\t.\t+\t.\tgene_id "ENSG00000279784"; gene_version "1"; transcript_id "ENST00000623587"; transcript_version "1"; exon_number "1"; gene_name "FP236315.3"; gene_source "havana"; gene_biotype "lncRNA"; transcript_name "FP236315.3-201"; transcript_source "havana"; transcript_biotype "lncRNA"; exon_id "ENSE00003758868"; exon_version "1"; tag "basic"; transcript_support_level "2";\n+21\thavana\tfakexon\t696164\t696361\t.\t+\t.\tgene_id "ENSG00000279784"; gene_version "1"; transcript_id "ENST00000623587"; transcript_version "1"; exon_number "2"; gene_name "FP236315.3"; gene_source "havana"; gene_biotype "lncRNA"; transcript_name "FP236315.3-201"; transcript_source "havana"; transcript_biotype "lncRNA"; exon_id "ENSE00003757033"; exon_version "1"; tag "basic"; transcript_support_level "2";\n+21\thavana\tgene\t696205\t698657\t.\t-\t.\tgene_id "ENSG00000279064"; gene_version "1"; gene_name "FP236315.1"; gene_source "havana"; gene_biotype "lncRNA";\n+21\thavana\ttranscript\t696205\t698657\t.\t-\t.\tgene_id "ENSG00000279064"; gene_version "1"; transcript_id "ENST00000623723"; transcript_version "1"; gene_name "FP236315.1"; gene_source "havana"; gene_biotype "lncRNA"; transcript_name "FP236315.1-201"; transcript_source "havana"; transcript_biotype "lncRNA"; tag "basic"; transcript_support_level "2";\n+21\thavana\tfakexon\t696205\t696358\t.\t-\t.\tgene_id "ENSG00000279064"; gene_version "1"; transcript_id "ENST00000623723"; transcript_version "1"; exon_number "2"; gene_name "FP236315.1"; gene_source "havana"; gene_biotype "lncRNA"; transcript_name "FP236315.1-201"; transcript_source "havana"; transcript_biotype "lncRNA"; exon_id "ENSE00003756092"; exon_version "1"; tag "basic"; transcript_support_level "2";\n' |
| b |
| diff -r 13022c3d3076 -r 5ef7ec16b04f test-data/no_exon.gtf --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/no_exon.gtf Fri Sep 01 13:18:03 2023 +0000 |
| b |
| @@ -0,0 +1,4 @@ +test_chromosome test gene 1 650 . + . gene_id "GENE1"; gene_name "GENE1"; transcript_id "GENE1_t1"; +test_chromosome test transcript 1 650 . + . gene_id "GENE1"; gene_name "GENE1"; transcript_id "GENE1_t1"; +test_chromosome test fakexon 1 650 . + . gene_id "GENE1"; transcript_id "GENE1_t1"; exon_number "1"; gene_name "GENE1"; +test_chromosome test CDS 100 550 . + . gene_id "GENE1"; transcript_id "GENE1_t1"; exon_number "1"; gene_name "GENE1"; |
| b |
| diff -r 13022c3d3076 -r 5ef7ec16b04f test-data/rnastar_test_mapped_reads_fakexon.bam |
| b |
| Binary file test-data/rnastar_test_mapped_reads_fakexon.bam has changed |