Mercurial > repos > iuc > rgrnastar
changeset 24:4df95e2d7f61 draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/rgrnastar commit 904cd12820a09a8e7ce7d01c64fa22f1ed93ed17
author | iuc |
---|---|
date | Wed, 22 Feb 2023 18:00:57 +0000 |
parents | a2b0feda6933 |
children | c7c55b694974 |
files | macros.xml rg_rnaStar.xml |
diffstat | 2 files changed, 39 insertions(+), 31 deletions(-) [+] |
line wrap: on
line diff
--- a/macros.xml Fri Feb 17 20:03:27 2023 +0000 +++ b/macros.xml Wed Feb 22 18:00:57 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@">0</token> + <token name="@VERSION_SUFFIX@">1</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 @@ -64,23 +64,26 @@ </xml> <xml name="dbKeyActions"> <actions> - <conditional name="refGenomeSource.geneSource"> - <when value="indexed"> - <action type="metadata" name="dbkey"> - <option type="from_data_table" name="@IDX_DATA_TABLE@" column="1" offset="0"> - <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/> - <filter type="param_value" ref="refGenomeSource.GTFconditional.genomeDir" column="0"/> - </option> - </action> - </when> - <when value="history"> - <action type="metadata" name="dbkey"> - <option type="from_param" name="refGenomeSource.genomeFastaFiles" param_attribute="dbkey" /> - </action> - </when> - </conditional> + <expand macro="dbKeyAction"/> </actions> </xml> + <xml name="dbKeyAction"> + <conditional name="refGenomeSource.geneSource"> + <when value="indexed"> + <action type="metadata" name="dbkey"> + <option type="from_data_table" name="@IDX_DATA_TABLE@" column="1" offset="0"> + <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/> + <filter type="param_value" ref="refGenomeSource.GTFconditional.genomeDir" column="0"/> + </option> + </action> + </when> + <when value="history"> + <action type="metadata" name="dbkey"> + <option type="from_param" name="refGenomeSource.genomeFastaFiles" param_attribute="dbkey" /> + </action> + </when> + </conditional> + </xml> <token name="@TEMPINDEX@"><![CDATA[ ## Create temporary index for custom reference #if str($refGenomeSource.geneSource) == 'history': @@ -219,7 +222,7 @@ </conditional> </xml> <xml name="umidedup_options"> - <option value="1MM_All" selected="true">Collapse all UMIs with 1 mismatch distance to each other</option> + <option value="1MM_All" selected="true">Collapse all UMIs with 1 mismatch distance to each other (1MM_All)</option> <option value="1MM_Directional_UMItools" >Directional method from the UMI-tool</option> <option value="1MM_Directional" >Directional with stringent UMI deduplication</option> </xml> @@ -231,12 +234,12 @@ </xml> <xml name="cb_match_wl_common"> <option value="Exact" >Exact</option> - <option value="1MM" >Single match</option> + <option value="1MM" >Single match (1MM)</option> </xml> <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> + <option value="1MM_multi" selected="true" >Multiple matches (CellRanger 2, 1MM_multi)</option> + <option value="1MM_multi_pseudocounts" >Multiple matches (CellRanger 3, 1MM_multi_pseudocounts)</option> + <option value="1MM_multi_Nbase_pseudocounts" >Multimatching to WL is allowed for CBs with N-bases (CellRanger 3, 1MM_multi_Nbase_pseudocounts)</option> </xml> <xml name="solo_adapter_params"> <param argument="--soloAdapterSequence" type="text" value="-" label="Adapter sequence to anchor barcodes." > @@ -278,6 +281,7 @@ <xml name="outCountActions"> <actions> <action name="column_names" type="metadata" default="GeneID,Counts_unstrand,Counts_firstStrand,Counts_secondStrand" /> + <expand macro="dbKeyAction"/> </actions> </xml> <xml name="outWig"> @@ -397,4 +401,13 @@ <when value="-" /> </conditional> </xml> + <xml name="outSAMmapqUnique"> + <!-- MAPQ 255 is the default in STAR (coming from tophat behaviour and compatibility for Cufflinks) but it is a problematic value + - according to SAM/BAM specs it means "undefined". + - Using 255 as the max mapq causes problem with modern downstream tools like mutect2: https://sites.duke.edu/workblog/2021/08/18/star-rnaseq-gatk-mutect2/ and 60 has become an inofficial replacement for 255. --> + <param argument="--outSAMmapqUnique" type="integer" value="60" min="0" max="255" + label="MAPQ value for unique mappers" + help="STAR bases the mapping quality scores of alignment records in its BAM output on the number of alternative mappings for the read. If a read maps to multiple locations on the reference genome, the following MAPQ scoring scheme is +used: >=5 mappings => MAPQ=0; 3-4 mappings => MAPQ=1; 2 mappings => MAPQ=3. This setting lets you control the MAPQ used for reads mapped to a single location. Set to 255 for compatibility with Cufflink (default in STAR) but keep to 60 for modern downstream tools like mutect2." /> + </xml> </macros>
--- a/rg_rnaStar.xml Fri Feb 17 20:03:27 2023 +0000 +++ b/rg_rnaStar.xml Wed Feb 22 18:00:57 2023 +0000 @@ -386,13 +386,7 @@ label="Would you like all alignments with the best score labeled primary?"/> --> <param name="outSAMprimaryFlag" type="hidden" value="OneBestScore" /> - <!-- MAPQ 255 is the default in STAR (coming from tophat behaviour and compatibility for Cufflinks) but it is a problematic value - - according to SAM/BAM specs it means "undefined". - - Using 255 as the max mapq causes problem with modern downstream tools like mutect2: https://sites.duke.edu/workblog/2021/08/18/star-rnaseq-gatk-mutect2/ and 60 has become an inofficial replacement for 255. --> - <param argument="--outSAMmapqUnique" type="integer" value="60" min="0" max="255" - label="MAPQ value for unique mappers" - help="STAR bases the mapping quality scores of alignment records in its BAM output on the number of alternative mappings for the read. If a read maps to multiple locations on the reference genome, the following MAPQ scoring scheme is -used: >=5 mappings => MAPQ=0; 3-4 mappings => MAPQ=1; 2 mappings => MAPQ=3. This setting lets you control the MAPQ used for reads mapped to a single location. Set to 255 for compatibility with Cufflink (default in STAR) but keep to 60 for modern downstream tools like mutect2." /> + <expand macro="outSAMmapqUnique"/> </section> <section name="filter" title="Output filter criteria" expanded="true"> <param name="basic_filters" type="select" display="checkboxes" multiple="true" optional="true" @@ -419,7 +413,7 @@ <param argument="--outFilterScoreMinOverLread" type="float" value="0.66" min="0" max="1" label="Minimum alignment score, normalized to read length" help="Alignments must have (normalized) scores higher than this value to be output"/> <param argument="--outFilterMatchNmin" type="integer" value="0" min="0" label="Minimum number of matched bases" help="Alignments must have the number of matched bases higher than this value to be output"/> <param argument="--outFilterMatchNminOverLread" type="float" value="0.66" min="0" max="1" label="Minimum number of matched bases, normalized to read length" help="Alignments must have the (normalized) number of matched bases higher than this value to be output"/> - <param argument="--outSAMmultNmax" type="integer" value="-1" min="-1" label="Maximum number of multimapping alignments to output for a read" help="A value of -1 (the default) results in all alignments (up to –-outFilterMultimapNmax) being output" /> + <param argument="--outSAMmultNmax" type="integer" value="-1" min="-1" label="Maximum number of multimapping alignments to output for a read" help="A value of -1 (the default) results in all alignments (up to --outFilterMultimapNmax) being output" /> <param argument="--outSAMtlen" type="select" label="Calculation method for TLEN"> <option value="1" selected="true">leftmost base of the (+)strand mate to rightmost base of the (-)mate. (+)sign for the (+)strand mate</option> <option value="2">leftmost base of any mate to rightmost base of any mate. (+)sign for the mate with the leftmost base. This is different from 1 for overlapping mates with protruding ends</option> @@ -546,7 +540,6 @@ <data name="reads_per_gene" format="tabular" label="${tool.name} on ${on_string}: reads per gene" from_work_dir="ReadsPerGene.out.tab"> <filter>'GeneCounts' in refGenomeSource['GTFconditional']['quantmode_output']['quantMode']</filter> - <expand macro="dbKeyActions" /> <expand macro="outCountActions" /> </data> <expand macro="outWigOutputs"/> @@ -631,7 +624,9 @@ <output name="output_log" file="rnastar_test.log" compare="re_match_multiline" /> <output name="splice_junctions" file="rnastar_test_splicejunctions.bed"/> <output name="mapped_reads" file="rnastar_test_mapped_reads.bam" compare="sim_size" delta="634" /> - <output name="reads_per_gene" file="tophat_test_reads_per_gene.txt" /> + <output name="reads_per_gene" file="tophat_test_reads_per_gene.txt"> + <metadata name="column_names" value="GeneID,Counts_unstrand,Counts_firstStrand,Counts_secondStrand" /> + </output> </test> <!-- test gtf file and TranscriptomeSAM mode --> <test expect_num_outputs="4">