| Previous changeset 9:ec9cbd6b9a49 (2021-01-15) Next changeset 11:eec9494fdafa (2021-09-10) |
|
Commit message:
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/rgrnastar commit d0c9fa48df667ffad1abd71164e6bb1d9cb16bd9" |
|
modified:
macros.xml rg_rnaStarSolo.xml |
|
added:
test-data/rnastar_test_genomeSAindexNbases.bed test-data/rnastar_test_genomeSAindexNbases.log test-data/rnastar_test_genomeSAindexNbases_02.bed test-data/rnastar_test_genomeSAindexNbases_02.log test-data/rnastar_test_mapped_reads_genomeSAindexNbases.bam test-data/rnastar_test_mapped_reads_genomeSAindexNbases_02.bam |
| b |
| diff -r ec9cbd6b9a49 -r a6fba3d92531 macros.xml --- a/macros.xml Fri Jan 15 17:39:11 2021 +0000 +++ b/macros.xml Mon Mar 15 13:46:45 2021 +0000 |
| b |
| @@ -5,7 +5,7 @@ the index versions in sync, but you should manually adjust the +galaxy version number. --> <!-- STAR version to be used --> - <token name="@VERSION@">2.7.7a</token> + <token name="@VERSION@">2.7.8a</token> <!-- STAR index version compatible with this version of STAR This is the STAR version that introduced the index structure expected by the current version. @@ -163,10 +163,7 @@ ]]></token> <xml name="ref_selection"> <param argument="--genomeFastaFiles" type="data" format="fasta" label="Select a reference genome" /> - <!-- Currently, this parameter is not exposed in the wrapper, - but used only in the tests to avoid excessive index sizes for - the tiny test genomes. --> - <param name="genomeSAindexNbases" type="hidden" value="" /> + <param argument="--genomeSAindexNbases" type="integer" min="2" max="16" value="14" label="Length of the SA pre-indexing string" help="Typically between 10 and 15. Longer strings will use much more memory, but allow faster searches. For small genomes, the parameter --genomeSAindexNbases must be scaled down to min(14, log2(GenomeLength)/2 - 1)"/> </xml> <xml name="stdio" > <stdio> @@ -209,8 +206,9 @@ </conditional> </xml> <xml name="umidedup_options"> - <option value="1MM_All" selected="true">All</option> - <option value="1MM_Directional" >Directional</option> + <option value="1MM_All" selected="true">Collapse all UMIs with 1 mismatch distance to each other</option> + <option value="1MM_Directional_UMItools" >Directional method from the UMI-tool</option> + <option value="1MM_Directional" >Directional with stringent UMI deduplication</option> </xml> <xml name="anchor_types"> <option value="0">Read start</option> @@ -225,5 +223,26 @@ <xml name="cb_match_wl_cellranger"> <option value="1MM_multi" selected="true" >Multiple matches (CellRanger 2)</option> <option value="1MM_multi_pseudocounts" >Multiple matches (CellRanger 3)</option> + <option value="1MM_multi_Nbase_pseudocounts" >Multimatching to WL is allowed for CBs with N-bases (CellRanger 3)</option> + </xml> + <xml name="solo_adapter_params"> + <param argument="--soloAdapterSequence" type="text" value="-" label="Adapter sequence to anchor barcodes." > + <sanitizer> + <valid initial="string.digits"> + <add value="-"/> + <add value="A"/> + <add value="T"/> + <add value="C"/> + <add value="G"/> + <add value="N"/> + </valid> + </sanitizer> + </param> + <param argument="--soloAdapterMismatchesNmax" type="integer" min="1" value="1" label="Maximum number of mismatches allowed in adapter sequence" /> + <param argument="--clipAdapterType" type="select" > + <option value="Hamming" selected="true" >Adapter clipping based on Hamming distance</option> + <option value="CellRanger4" >5p and 3p adapter clipping similar to CellRanger4</option> + <option value="None" >No adapter clipping</option> + </param> </xml> </macros> |
| b |
| diff -r ec9cbd6b9a49 -r a6fba3d92531 rg_rnaStarSolo.xml --- a/rg_rnaStarSolo.xml Fri Jan 15 17:39:11 2021 +0000 +++ b/rg_rnaStarSolo.xml Mon Mar 15 13:46:45 2021 +0000 |
| [ |
| b'@@ -41,6 +41,17 @@\n --soloCBlen $sc.params.soloCBlen\n --soloUMIstart $sc.params.soloUMIstart\n --soloUMIlen $sc.params.soloUMIlen\n+ #if $sc.params.bccdna_mate.bc_location == "same_mate":\n+ --soloBarcodeMate $sc.params.bccdna_mate.soloBarcodeMate\n+ #if $sc.params.bccdna_mate.soloBarcodeMate == "1":\n+ --clip5pNbases $sc.params.bccdna_mate.clip_n_bases 0\n+ #else if $sc.params.bccdna_mate.soloBarcodeMate == "2":\n+ --clip3pNbases 0 $sc.params.bccdna_mate.clip_n_bases\n+ #end if\n+ #end if\n+ --soloAdapterSequence \'$sc.params.soloAdapterSequence\'\n+ --soloAdapterMismatchesNmax $sc.params.soloAdapterMismatchesNmax\n+ --clipAdapterType $sc.params.clipAdapterType\n #end if\n \n #elif str($sc.solo_type) == "CB_UMI_Complex":\n@@ -58,8 +69,9 @@\n --soloCBposition $cb_pos\n #set $umi_pos = \'_\'.join([str($sc.umi_start_anchor), str($sc.umi_start_anchor_pos), str($sc.umi_end_anchor), str($sc.umi_end_anchor_pos)])\n --soloUMIposition $umi_pos\n- --soloAdapterSequence $sc.soloAdapterSequence\n+ --soloAdapterSequence \'$sc.soloAdapterSequence\'\n --soloAdapterMismatchesNmax $sc.soloAdapterMismatchesNmax\n+ --clipAdapterType $sc.clipAdapterType\n \n #elif str($sc.solo_type) == "SmartSeq":\n ## Create a manifest file with fastq files and their corresponding cell-ids\n@@ -87,6 +99,8 @@\n \n #if str($solo.filter.filter_type) == "cellranger2":\n --soloCellFilter CellRanger2.2 $solo.filter.n_expected $solo.filter.max_perc $solo.filter.max_min_ratio\n+ #else if str($solo.filter.filter_type) == "emptydrops":\n+ --soloCellFilter EmptyDrops_CR $solo.filter.nExpectedCells $solo.filter.maxPercentile $solo.filter.maxMinRatio $solo.filter.indMin $solo.filter.indMax $solo.filter.umiMin $solo.filter.umiMinFracMedian $solo.filter.candMaxN $solo.filter.FDR $solo.filter.simN\n #else if str($solo.filter.filter_type) == "topcells":\n --soloCellFilter TopCells $solo.filter.n_cells\n #else if str($solo.filter.filter_type) == "no_filter":\n@@ -187,12 +201,28 @@\n <param argument="--soloCBlen" type="integer" min="1" value="16" label="Cell Barcode Length" />\n <param argument="--soloUMIstart" type="integer" min="1" value="17" label="UMI Start Base" />\n <param argument="--soloUMIlen" type="integer" min="1" value="10" label="UMI Length" />\n+ <conditional name="bccdna_mate" >\n+ <param name="bc_location" type="select" label="Barcode and cDNA on the same mate\\?" >\n+ <option value="other_mate" selected="true">BC and cDNA are on different mates of paired-end read</option>\n+ <option value="same_mate">BC and cDNA are on the same mate of paired-end read</option>\n+ </param>\n+ <when value="other_mate" />\n+ <when value="same_mate" >\n+ <param argument="--soloBarcodeMate" type="select" label="Barcode sequence is a part of">\n+ <option value="1" selected="true">mate 1</option>\n+ <option value="2">mate 2</option>\n+ </param>\n+ <param name="clip_n_bases" type="integer" value="39" label="Number of bases to clip (=CB+UMI+adapter)"/>\n+ </when>\n+ </conditional>\n+ <expand macro="solo_adapter_params" />\n </when>\n </conditional>\n <param argument="--soloBarcodeReadLength" type="boolean" truevalue="1" falsevalue="0" checked="true" label="Barcode Size is same size of the Read" help="Disable this if your R1 barcodes contain poly-T bases after the barcode sequence." />\n <param argument="--soloUMIdedup" type="select"'..b'.dna.chromosome.21.fa.gz" />\n+ <param name="genomeSAindexNbases" value="4" />\n+ <param name="sjdbOverhang" value="100" />\n+ <param name="sjdbGTFfile" value="filtered3.Homo_sapiens.GRCh38.100.chr21.gtf" ftype="gtf"/>\n+ </conditional>\n+ <conditional name="sc" >\n+ <param name="solo_type" value="CB_UMI_Simple" />\n+ <conditional name="input_types">\n+ <param name="use" value="repeat" />\n+ <param name="input1" value="pbmc_1k_v2_L001.R1.10k.fastq.gz" ftype="fastqsanger.gz" />\n+ <param name="input2" value="pbmc_1k_v2_L001.R2.10k.fastq.gz" ftype="fastqsanger.gz" />\n+ </conditional>\n+ <param name="soloCBwhitelist" value="filtered.barcodes.txt" />\n+ <conditional name="params">\n+ <param name="chemistry" value="CR3" />\n+ </conditional>\n+ <param name="soloUMIdedup" value="1MM_All" />\n+ </conditional>\n+ <section name="solo" >\n+ <conditional name="filter">\n+ <param name="filter_type" value="emptydrops" />\n+ <param name="nExpectedCells" value="5" />\n+ <param name="maxPercentile" value="0.99" />\n+ <param name="maxMinRatio" value="10" />\n+ <param name="indMin" value="45000" />\n+ <param name="indMax" value="90000" />\n+ <param name="umiMin" value="500" />\n+ <param name="umiMinFracMedian" value="0.01" />\n+ <param name="candMaxN" value="20000" />\n+ <param name="FDR" value="0.01" />\n+ <param name="simN" value="10000" />\n+ </conditional>\n+ <param name="soloStrand" value="Forward" />\n+ <param name="soloFeatures" value="Gene" />\n+ </section>\n+ <output name="output_barcodes_filtered">\n+ <assert_contents>\n+ <!-- first and last line -->\n+ <has_line line="ACACCGGTCTAACGGT" />\n+ <has_line line="TTCTCAATCCACGTTC" />\n+ </assert_contents>\n+ </output>\n+ <output name="output_genes_filtered">\n+ <assert_contents>\n+ <has_line_matching expression="ENSG00000279493\\s+FP565260\\.4\\s+Gene\\s+Expression" />\n+ <has_line_matching expression="ENSG00000279064\\s+FP236315\\.1\\s+Gene\\s+Expression" />\n+ </assert_contents>\n+ </output>\n+ <output name="output_matrix_filtered" >\n+ <assert_contents>\n+ <has_line_matching expression="14\\s+7\\s+7" />\n+ <has_line_matching expression="4\\s+7\\s+1" />\n+ </assert_contents>\n+ </output>\n+ <output name="output_stats" >\n+ <assert_contents>\n+ <has_line_matching expression="\\s+nUnmapped\\s+5823" />\n+ <has_line_matching expression="\\s+nUMIs\\s+8" />\n+ </assert_contents>\n+ </output>\n+ <output name="output_BAM" value="filtered3.bam" compare="sim_size" delta="600" />\n+ </test>\n+ <test expect_num_outputs="6">\n <!-- Test soloType CB_UMI_Complex -->\n <conditional name="refGenomeSource">\n <param name="geneSource" value="history" />\n@@ -612,6 +721,7 @@\n <param name="umi_end_anchor_pos" value="14" />\n <param name="soloAdapterSequence" value="GAGTGATTGCTTGTGACGCCTT" />\n <param name="soloAdapterMismatchesNmax" value="1" />\n+ <param name="clipAdapterType" value="CellRanger4" />\n <param name="soloUMIdedup" value="1MM_All" />\n <param name="soloCBmatchWLtype" value="1MM" />\n </conditional>\n' |
| b |
| diff -r ec9cbd6b9a49 -r a6fba3d92531 test-data/rnastar_test_genomeSAindexNbases.bed --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/rnastar_test_genomeSAindexNbases.bed Mon Mar 15 13:46:45 2021 +0000 |
| b |
| @@ -0,0 +1,2 @@ +test_chromosome 251 350 1 1 0 27 0 37 +test_chromosome 401 500 1 1 0 25 0 36 |
| b |
| diff -r ec9cbd6b9a49 -r a6fba3d92531 test-data/rnastar_test_genomeSAindexNbases.log --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/rnastar_test_genomeSAindexNbases.log Mon Mar 15 13:46:45 2021 +0000 |
| b |
| @@ -0,0 +1,37 @@ + Started job on | Mar 08 19:43:44 + Started mapping on | Mar 08 19:43:45 + Finished on | Mar 08 19:43:45 + Mapping speed, Million of reads per hour | inf + + Number of input reads | 100 + Average input read length | 75 + UNIQUE READS: + Uniquely mapped reads number | 99 + Uniquely mapped reads % | 99.00% + Average mapped length | 74.65 + Number of splices: Total | 52 + Number of splices: Annotated (sjdb) | 0 + Number of splices: GT/AG | 52 + Number of splices: GC/AG | 0 + Number of splices: AT/AC | 0 + Number of splices: Non-canonical | 0 + Mismatch rate per base, % | 2.00% + Deletion rate per base | 0.00% + Deletion average length | 0.00 + Insertion rate per base | 0.00% + Insertion average length | 0.00 + MULTI-MAPPING READS: + Number of reads mapped to multiple loci | 1 + % of reads mapped to multiple loci | 1.00% + Number of reads mapped to too many loci | 0 + % of reads mapped to too many loci | 0.00% + UNMAPPED READS: + Number of reads unmapped: too many mismatches | 0 + % of reads unmapped: too many mismatches | 0.00% + Number of reads unmapped: too short | 0 + % of reads unmapped: too short | 0.00% + Number of reads unmapped: other | 0 + % of reads unmapped: other | 0.00% + CHIMERIC READS: + Number of chimeric reads | 0 + % of chimeric reads | 0.00% |
| b |
| diff -r ec9cbd6b9a49 -r a6fba3d92531 test-data/rnastar_test_genomeSAindexNbases_02.bed --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/rnastar_test_genomeSAindexNbases_02.bed Mon Mar 15 13:46:45 2021 +0000 |
| b |
| @@ -0,0 +1,2 @@ +test_chromosome 251 350 1 1 0 27 0 37 +test_chromosome 401 500 1 1 0 25 0 36 |
| b |
| diff -r ec9cbd6b9a49 -r a6fba3d92531 test-data/rnastar_test_genomeSAindexNbases_02.log --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/rnastar_test_genomeSAindexNbases_02.log Mon Mar 15 13:46:45 2021 +0000 |
| b |
| @@ -0,0 +1,37 @@ + Started job on | Mar 08 19:43:59 + Started mapping on | Mar 08 19:43:59 + Finished on | Mar 08 19:43:59 + Mapping speed, Million of reads per hour | inf + + Number of input reads | 100 + Average input read length | 75 + UNIQUE READS: + Uniquely mapped reads number | 99 + Uniquely mapped reads % | 99.00% + Average mapped length | 74.65 + Number of splices: Total | 52 + Number of splices: Annotated (sjdb) | 0 + Number of splices: GT/AG | 52 + Number of splices: GC/AG | 0 + Number of splices: AT/AC | 0 + Number of splices: Non-canonical | 0 + Mismatch rate per base, % | 2.00% + Deletion rate per base | 0.00% + Deletion average length | 0.00 + Insertion rate per base | 0.00% + Insertion average length | 0.00 + MULTI-MAPPING READS: + Number of reads mapped to multiple loci | 1 + % of reads mapped to multiple loci | 1.00% + Number of reads mapped to too many loci | 0 + % of reads mapped to too many loci | 0.00% + UNMAPPED READS: + Number of reads unmapped: too many mismatches | 0 + % of reads unmapped: too many mismatches | 0.00% + Number of reads unmapped: too short | 0 + % of reads unmapped: too short | 0.00% + Number of reads unmapped: other | 0 + % of reads unmapped: other | 0.00% + CHIMERIC READS: + Number of chimeric reads | 0 + % of chimeric reads | 0.00% |
| b |
| diff -r ec9cbd6b9a49 -r a6fba3d92531 test-data/rnastar_test_mapped_reads_genomeSAindexNbases.bam |
| b |
| Binary file test-data/rnastar_test_mapped_reads_genomeSAindexNbases.bam has changed |
| b |
| diff -r ec9cbd6b9a49 -r a6fba3d92531 test-data/rnastar_test_mapped_reads_genomeSAindexNbases_02.bam |
| b |
| Binary file test-data/rnastar_test_mapped_reads_genomeSAindexNbases_02.bam has changed |