Mercurial > repos > iuc > rgrnastar
changeset 18:c772497b2c32 draft
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/rgrnastar commit d0c9fa48df667ffad1abd71164e6bb1d9cb16bd9"
author | iuc |
---|---|
date | Mon, 15 Mar 2021 13:46:07 +0000 |
parents | 7ed2edc1337f |
children | 44959aa06aeb |
files | macros.xml rg_rnaStar.xml 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 |
diffstat | 8 files changed, 152 insertions(+), 8 deletions(-) [+] |
line wrap: on
line diff
--- a/macros.xml Fri Jan 15 17:38:35 2021 +0000 +++ b/macros.xml Mon Mar 15 13:46:07 2021 +0000 @@ -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>
--- a/rg_rnaStar.xml Fri Jan 15 17:38:35 2021 +0000 +++ b/rg_rnaStar.xml Mon Mar 15 13:46:07 2021 +0000 @@ -867,7 +867,54 @@ <output name="splice_junctions" file="rnastar_test_splicejunctions_twopass.bed"/> <output name="mapped_reads" file="rnastar_test_mapped_reads_twopass.bam" compare="sim_size" delta="634" /> </test> - </tests> + <!-- test "genomeSAindexNbases" parameter --> + <test expect_num_outputs="3"> + <conditional name="singlePaired"> + <param name="sPaired" value="single" /> + <param name="input1" value="tophat_in2.fastqsanger" ftype="fastqsanger" /> + </conditional> + <conditional name="refGenomeSource"> + <param name="geneSource" value="history" /> + <param name="genomeFastaFiles" value="tophat_test.fa" /> + <param name="genomeSAindexNbases" value="14" /> + </conditional> + <section name="oformat"> + <param name="outSAMattributes" value="NH,HI,AS,nM,NM,MD,jM,jI,MC,ch" /> + <param name="outSAMmapqUnique" value="255" /> + </section> + <section name="algo"> + <conditional name="params"> + <param name="settingsType" value="default" /> + </conditional> + </section> + <output name="output_log" file="rnastar_test_genomeSAindexNbases.log" compare="re_match_multiline" /> + <output name="splice_junctions" file="rnastar_test_genomeSAindexNbases.bed"/> + <output name="mapped_reads" file="rnastar_test_mapped_reads_genomeSAindexNbases.bam" compare="sim_size" delta="634" /> + </test> + <test expect_num_outputs="3"> + <conditional name="singlePaired"> + <param name="sPaired" value="single" /> + <param name="input1" value="tophat_in2.fastqsanger" ftype="fastqsanger" /> + </conditional> + <conditional name="refGenomeSource"> + <param name="geneSource" value="history" /> + <param name="genomeFastaFiles" value="tophat_test.fa" /> + <param name="genomeSAindexNbases" value="10" /> + </conditional> + <section name="oformat"> + <param name="outSAMattributes" value="NH,HI,AS,nM,NM,MD,jM,jI,MC,ch" /> + <param name="outSAMmapqUnique" value="255" /> + </section> + <section name="algo"> + <conditional name="params"> + <param name="settingsType" value="default" /> + </conditional> + </section> + <output name="output_log" file="rnastar_test_genomeSAindexNbases_02.log" compare="re_match_multiline" /> + <output name="splice_junctions" file="rnastar_test_genomeSAindexNbases_02.bed"/> + <output name="mapped_reads" file="rnastar_test_mapped_reads_genomeSAindexNbases_02.bam" compare="sim_size" delta="634" /> + </test> + </tests> <help><![CDATA[ **What it does**
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/rnastar_test_genomeSAindexNbases.bed Mon Mar 15 13:46:07 2021 +0000 @@ -0,0 +1,2 @@ +test_chromosome 251 350 1 1 0 27 0 37 +test_chromosome 401 500 1 1 0 25 0 36
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/rnastar_test_genomeSAindexNbases.log Mon Mar 15 13:46:07 2021 +0000 @@ -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%
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/rnastar_test_genomeSAindexNbases_02.bed Mon Mar 15 13:46:07 2021 +0000 @@ -0,0 +1,2 @@ +test_chromosome 251 350 1 1 0 27 0 37 +test_chromosome 401 500 1 1 0 25 0 36
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/rnastar_test_genomeSAindexNbases_02.log Mon Mar 15 13:46:07 2021 +0000 @@ -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%