changeset 15:b8f5f6e87f5c draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/rgrnastar commit f6ccf9e6d01368c832110742b6f6534ff3b3b6a9
author iuc
date Thu, 09 Mar 2023 21:12:17 +0000
parents 1cd2511a396e
children 13022c3d3076
files macros.xml rg_rnaStarSolo.xml
diffstat 2 files changed, 70 insertions(+), 5 deletions(-) [+]
line wrap: on
line diff
--- a/macros.xml	Wed Feb 22 18:01:29 2023 +0000
+++ b/macros.xml	Thu Mar 09 21:12:17 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@">1</token>
+    <token name="@VERSION_SUFFIX@">2</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
--- a/rg_rnaStarSolo.xml	Wed Feb 22 18:01:29 2023 +0000
+++ b/rg_rnaStarSolo.xml	Thu Mar 09 21:12:17 2023 +0000
@@ -123,7 +123,7 @@
     --soloOutFormatFeaturesGeneField3 '${solo.soloOutFormatFeaturesGeneField3}'
 
     ## Unmapped
-    '$solo.outSAMunmapped'
+    $solo.outSAMunmapped
     ## Read MAPQ
     --outSAMmapqUnique ${solo.outSAMmapqUnique}
     ## Limits
@@ -132,11 +132,14 @@
     ##outWig:
     @OUTWIG@
     ## Rename the the selected features directory
-    && mv Solo.out/${solo.soloFeatures} Solo.out/soloFeatures
+    #if $solo.soloFeatures == 'Gene Velocyto'
+        && mv Solo.out/Velocyto Solo.out/soloFeatures
+    #else
+        && mv Solo.out/${solo.soloFeatures} Solo.out/soloFeatures
+    #end if
     ## put the barcodes and features stats into a single file
     && cat <(echo "Barcodes:") Solo.out/Barcodes.stats <(echo "Genes:") Solo.out/soloFeatures/Features.stats > '${output_stats}'
 
-
     #if "CB" in $tag_names or "UB" in $tag_names or str($outWig.outWigType) != 'None':
         ## recompress BAM output for smaller file size
         && samtools view -b -o '$output_BAM' Aligned.sortedByCoord.out.bam
@@ -157,7 +160,6 @@
     #end if
     ##outWig:
     @OUTWIGOUTPUTS@
-
     ]]></command>
     <configfiles>
         <configfile name="manifest_file" >
@@ -351,6 +353,7 @@
                 <option value="GeneFull" >Full: Count all reads overlapping genes' exons and introns</option>
                 <option value="GeneFull_ExonOverIntron" >Full: Count all reads overlapping genes' exons and introns: prioritize 100% overlap with exons</option>
                 <option value="GeneFull_Ex50pAS" >Full: Count all reads overlapping genes' exons and introns: prioritize 50% overlap with exons. Do not count reads with 100% exonic overlap in the antisense direction.</option>
+                <option value="Gene Velocyto">Velocyto: calculate spliced, unspliced, and ambiguous counts per cell per gene similar to the velocyto tool</option>
             </param>
             <conditional name="filter" >
                 <param name="filter_type" type="select" label="Cell filtering type and parameters" >
@@ -1241,6 +1244,68 @@
                 </assert_contents>
             </output>
         </test>
+        <test expect_num_outputs="6">
+            <!-- test 12 -->
+            <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="filtered3.Homo_sapiens.GRCh38.100.chr21.gtf" ftype="gtf"/>
+            </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**