Mercurial > repos > iuc > rna_starsolo
changeset 5:c23da6257d6a draft
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/rgrnastar commit 2082c018009fa73c4afee8313febab13bb807ea8"
| author | iuc |
|---|---|
| date | Wed, 16 Oct 2019 05:24:45 -0400 |
| parents | 58b278def57e |
| children | 178bdbdb6d24 |
| files | rg_rnaStarSolo.xml |
| diffstat | 1 files changed, 147 insertions(+), 30 deletions(-) [+] |
line wrap: on
line diff
--- a/rg_rnaStarSolo.xml Fri Sep 06 11:10:22 2019 -0400 +++ b/rg_rnaStarSolo.xml Wed Oct 16 05:24:45 2019 -0400 @@ -2,7 +2,7 @@ <description>mapping, demultiplexing and gene quantification for single cell RNA-seq</description> <macros> <import>macros.xml</import> - <token name="@WRAPPER@"></token> + <token name="@WRAPPER@">1</token> </macros> <expand macro="requirements"/> <expand macro="stdio" > @@ -14,13 +14,52 @@ STAR @REFGENOMEHANDLING@ - ## cDNA sequence always goes first, then barcode + ## Check that the input pairs are of the same type + ## otherwise STARsolo will run for a long time and then error out. + ## We consume either repeats of two inputs R1 + R2 + ## or a collection of paired reads. + + #try + #set $last = None + #for $x in $input_types.input_repeats: + #if str($input_types.use) == "repeat": + #set $r1 = $x.input1 + #set $r2 = $x.input2 + #elif str($input_types.use) == "list_paired": + #set $r1 = $x.forward + #set $r2 = $x.reverse + #else + Wrong Type + #stop + #end if + + #assert $r1.datatype == $r2.datatype + + ## Test that all pairs are of the same type + #if $last: + #assert $last.datatype == $r1.datatype + #end if + #set $last = $r1 + #end for + #except AssertionError + Input types are not the same! + #stop + #end try + + ## cDNA sequence(s) [R2] always go first, then barcode(s) [R1] + ## see: Section 3.1 of STAR manual for multiple inputs, and Section 13 for STARsolo inputs + #if str($input_types.use) == "repeat": + #set $reads2 = ','.join([ '%s' % $x.input2 for $i,$x in enumerate($input_types.input_repeats)]) + #set $reads1 = ','.join([ '%s' % $x.input1 for $i,$x in enumerate($input_types.input_repeats)]) + #else if str($input_types.use) == "list_paired" + #set $reads2 = ','.join([ '%s' % $x.reverse for $i,$x in enumerate($input_types.input_repeats)]) + #set $reads1 = ','.join([ '%s' % $x.forward for $i,$x in enumerate($input_types.input_repeats)]) + #end if + --readFilesIn - #set $reads2 = ','.join([ '%s' % $x.input2 for $i,$x in enumerate($input_repeats)]) - #set $reads1 = ','.join([ '%s' % $x.input1 for $i,$x in enumerate($input_repeats)]) $reads2 $reads1 - #if $input_repeats[0].input1.is_of_type('fastq.gz', 'fastqsanger.gz'): + #if $last.is_of_type('fastq.gz', 'fastqsanger.gz'): @FASTQ_GZ_OPTION@ #end if @@ -29,8 +68,8 @@ ## 1 - check length of barcode, 0 - do not check ## Good for checking custom chemistries - --soloBarcodeReadLength 1 --soloCBwhitelist '$soloCBwhitelist' + --soloBarcodeReadLength '$solo.soloBarcodeReadLength' #if str($solo.params.chemistry) == "CR2": --soloCBstart 1 @@ -54,10 +93,21 @@ --soloUMIdedup '$solo.soloUMIdedup' ]]></command> <inputs> - <repeat name="input_repeats" title="Input Pairs" min="1" > - <param format="fastq,fasta,fastq.gz,fastqsanger.gz" name="input1" type="data" label="RNA-Seq FASTQ/FASTA file, Barcode reads"/> - <param format="fastq,fasta,fastq.gz,fastqsanger.gz" name="input2" type="data" label="RNA-Seq FASTQ/FASTA file, cDNA reads"/> - </repeat> + <conditional name="input_types" > + <param name="use" type="select" label="Input Type" > + <option value="repeat" >Single files</option> + <option value="list_paired" >List of Pairs</option> + </param> + <when value="repeat"> + <repeat name="input_repeats" title="Input Pairs" min="1" > + <param format="fastq,fasta,fastq.gz,fastqsanger.gz" name="input1" type="data" label="RNA-Seq FASTQ/FASTA file, Barcode reads"/> + <param format="fastq,fasta,fastq.gz,fastqsanger.gz" name="input2" type="data" label="RNA-Seq FASTQ/FASTA file, cDNA reads"/> + </repeat> + </when> + <when value="list_paired"> + <param name="input_repeats" collection_type="paired" type="data_collection" format="fastq,fasta,fastq.gz,fastqsanger.gz" label="Collection of Pairs" /> + </when> + </conditional> <param format="txt,tsv" argument="--soloCBwhitelist" type="data" label="RNA-Seq Cell Barcode Whitelist" /> <expand macro="refgenomehandling" /> <section name="solo" title="Advanced Settings" expanded="true"> @@ -91,6 +141,7 @@ <option value="1MM_Directional" >Directional</option> <option value="1MM_NotCollapsed" >None</option> </param> + <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." /> </section> </inputs> <outputs> @@ -112,10 +163,13 @@ </outputs> <tests> <test expect_num_outputs="5"> - <repeat name="input_repeats" > - <param name="input1" value="41737_R1_sub240k.fastq.gz" ftype="fastqsanger.gz" /> - <param name="input2" value="41737_R2_sub240k.fastq.gz" ftype="fastqsanger.gz" /> - </repeat> + <conditional name="input_types"> + <param name="use" value="repeat" /> + <repeat name="input_repeats" > + <param name="input1" value="41737_R1_sub240k.fastq.gz" ftype="fastqsanger.gz" /> + <param name="input2" value="41737_R2_sub240k.fastq.gz" ftype="fastqsanger.gz" /> + </repeat> + </conditional> <param name="soloCBwhitelist" value="737K-august-2016.small.txt.gz" /> <conditional name="refGenomeSource"> <param name="geneSource" value="history" /> @@ -153,10 +207,13 @@ </output> </test> <test expect_num_outputs="5"> - <repeat name="input_repeats" > - <param name="input1" value="41737_R1_sub240k.fastq.gz" ftype="fastqsanger.gz" /> - <param name="input2" value="41737_R2_sub240k.fastq.gz" ftype="fastqsanger.gz" /> - </repeat> + <conditional name="input_types"> + <param name="use" value="repeat" /> + <repeat name="input_repeats" > + <param name="input1" value="41737_R1_sub240k.fastq.gz" ftype="fastqsanger.gz" /> + <param name="input2" value="41737_R2_sub240k.fastq.gz" ftype="fastqsanger.gz" /> + </repeat> + </conditional> <param name="soloCBwhitelist" value="737K-august-2016.small.txt.gz" /> <conditional name="refGenomeSource"> <param name="geneSource" value="history" /> @@ -188,18 +245,78 @@ </output> </test> <test expect_num_outputs="5"> - <repeat name="input_repeats" > - <param name="input1" value="41737_R1_sub240k.fastq.gz" ftype="fastqsanger.gz" /> - <param name="input2" value="41737_R2_sub240k.fastq.gz" ftype="fastqsanger.gz" /> - </repeat> - <repeat name="input_repeats" > - <param name="input1" value="41737_R1_sub240k.fastq.gz" ftype="fastqsanger.gz" /> - <param name="input2" value="41737_R2_sub240k.fastq.gz" ftype="fastqsanger.gz" /> - </repeat> - <repeat name="input_repeats" > - <param name="input1" value="41737_R1_sub240k.fastq.gz" ftype="fastqsanger.gz" /> - <param name="input2" value="41737_R2_sub240k.fastq.gz" ftype="fastqsanger.gz" /> - </repeat> + <!-- Multiple repeats test --> + <conditional name="input_types"> + <param name="use" value="repeat" /> + <repeat name="input_repeats" > + <param name="input1" value="41737_R1_sub240k.fastq.gz" ftype="fastqsanger.gz" /> + <param name="input2" value="41737_R2_sub240k.fastq.gz" ftype="fastqsanger.gz" /> + </repeat> + <repeat name="input_repeats" > + <param name="input1" value="41737_R1_sub240k.fastq.gz" ftype="fastqsanger.gz" /> + <param name="input2" value="41737_R2_sub240k.fastq.gz" ftype="fastqsanger.gz" /> + </repeat> + <repeat name="input_repeats" > + <param name="input1" value="41737_R1_sub240k.fastq.gz" ftype="fastqsanger.gz" /> + <param name="input2" value="41737_R2_sub240k.fastq.gz" ftype="fastqsanger.gz" /> + </repeat> + </conditional> + <param name="soloCBwhitelist" value="737K-august-2016.small.txt.gz" /> + <conditional name="refGenomeSource"> + <param name="geneSource" value="history" /> + <param name="genomeFastaFiles" value="SNORD83B.22.fa" /> + <param name="genomeSAindexNbases" value="4" /> + <conditional name="GTFconditional"> + <param name="GTFselect" value="with-gtf" /> + <param name="sjdbOverhang" value="75" /> + <param name="sjdbGTFfile" value="SNORD83B.22.gtf" ftype="gtf"/> + </conditional> + </conditional> + <section name="solo" > + <conditional name="params"> + <param name="chemistry" value="custom" /> + <param name="soloCBstart" value="1" /> + <param name="soloCBlen" value="16" /> + <param name="soloUMIstart" value="17" /> + <param name="soloUMIlen" value="10" /> + </conditional> + <param name="soloStrand" value="Forward" /> + <param name="soloFeatures" value="GeneFull" /> + <param name="soloUMIdedup" value="1MM_Directional" /> + </section> + <output name="output_barcodes" > + <assert_contents> + <has_line line="TTTGTCATCTTAGAGC" /> + <has_line line="TTTGTCATCTTTCCTC" /> + </assert_contents> + </output> + </test> + <test expect_num_outputs="5"> + <!-- Same as the test before but with a collection of pairs --> + <conditional name="input_types"> + <param name="use" value="list_paired" /> + <param name="input_repeats" > + <collection type="list:paired"> + <element name="Pair1"> + <collection type="paired"> + <element name="forward" value="41737_R1_sub240k.fastq.gz" ftype="fastqsanger.gz" /> + <element name="reverse" value="41737_R2_sub240k.fastq.gz" ftype="fastqsanger.gz" /> + </collection> + </element> + <element name="Pair2"> + <collection type="paired"> + <element name="forward" value="41737_R1_sub240k.fastq.gz" ftype="fastqsanger.gz" /> + <element name="reverse" value="41737_R2_sub240k.fastq.gz" ftype="fastqsanger.gz" /> + </collection> + </element> + <!-- Planemo does not support more than 2 elements in a list of pairs --> + <!-- <element name="Pair3"> --> + <!-- <element name="forward" value="41737_R1_sub240k.fastq.gz" ftype="fastqsanger.gz" /> --> + <!-- <element name="reverse" value="41737_R2_sub240k.fastq.gz" ftype="fastqsanger.gz" /> --> + <!-- </element> --> + </collection> + </param> + </conditional> <param name="soloCBwhitelist" value="737K-august-2016.small.txt.gz" /> <conditional name="refGenomeSource"> <param name="geneSource" value="history" />