Mercurial > repos > iuc > rna_starsolo

comparison rg_rnaStarSolo.xml @ 2:3a1253ee137b draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/rgrnastar commit ce3f681beac515bc20661e790c2b326077f853ba"
author iuc
date Tue, 27 Aug 2019 05:58:14 -0400
parents e3c94e2933c9
children 61cb2042581a
comparison
equal deleted inserted replaced
1:e613048778d9 2:3a1253ee137b
1 <tool id="rna_starsolo" name="RNA STARSolo" version="@VERSION@@WRAPPER@" profile="17.01"> 1 <tool id="rna_starsolo" name="RNA STARSolo" version="@VERSION@@WRAPPER@" profile="17.01">
2 <description>mapping, demultiplexing and gene quantification for single cell RNA-seq</description> 2 <description>mapping, demultiplexing and gene quantification for single cell RNA-seq</description>
3 <macros> 3 <macros>
4 <import>macros.xml</import> 4 <import>macros.xml</import>
5 <token name="@WRAPPER@"></token> 5 <token name="@WRAPPER@">1</token>
6 </macros> 6 </macros>
7 <expand macro="requirements"/> 7 <expand macro="requirements"/>
8 <expand macro="stdio" /> 8 <expand macro="stdio" >
9 <regex match="Segmentation fault" source="both" level="fatal" />
10 </expand>
9 11
10 <command><![CDATA[ 12 <command><![CDATA[
11 @TEMPINDEX@ 13 @TEMPINDEX@
12 STAR 14 STAR
13 @REFGENOMEHANDLING@ 15 @REFGENOMEHANDLING@
14 16
15 ## cDNA sequence always goes first, then barcode 17 ## cDNA sequence always goes first, then barcode
16 --readFilesIn 18 --readFilesIn
17 '$input2' '$input1' 19 #set $reads2 = ','.join([ '%s' % $x.input2 for $i,$x in enumerate($input_repeats)])
18 #if $input1.is_of_type('fastq.gz', 'fastqsanger.gz'): 20 #set $reads1 = ','.join([ '%s' % $x.input1 for $i,$x in enumerate($input_repeats)])
21 $reads2 $reads1
22
23 #if $input_repeats[0].input1.is_of_type('fastq.gz', 'fastqsanger.gz'):
19 @FASTQ_GZ_OPTION@ 24 @FASTQ_GZ_OPTION@
20 #end if 25 #end if
21 26
22 ## Droplet is the only mode available for now 27 ## Droplet is the only mode available for now
23 --soloType Droplet 28 --soloType Droplet
47 --soloStrand '$solo.soloStrand' 52 --soloStrand '$solo.soloStrand'
48 --soloFeatures '$solo.soloFeatures' 53 --soloFeatures '$solo.soloFeatures'
49 --soloUMIdedup '$solo.soloUMIdedup' 54 --soloUMIdedup '$solo.soloUMIdedup'
50 ]]></command> 55 ]]></command>
51 <inputs> 56 <inputs>
52 <param format="fastq,fasta,fastq.gz,fastqsanger.gz" name="input1" type="data" label="RNA-Seq FASTQ/FASTA file, cDNA reads"/> 57 <repeat name="input_repeats" title="Input Pairs" min="1" >
53 <param format="fastq,fasta,fastq.gz,fastqsanger.gz" name="input2" type="data" label="RNA-Seq FASTQ/FASTA file, Barcode reads"/> 58 <param format="fastq,fasta,fastq.gz,fastqsanger.gz" name="input1" type="data" label="RNA-Seq FASTQ/FASTA file, Barcode reads"/>
59 <param format="fastq,fasta,fastq.gz,fastqsanger.gz" name="input2" type="data" label="RNA-Seq FASTQ/FASTA file, cDNA reads"/>
60 </repeat>
54 <param format="txt,tsv" argument="--soloCBwhitelist" type="data" label="RNA-Seq Cell Barcode Whitelist" /> 61 <param format="txt,tsv" argument="--soloCBwhitelist" type="data" label="RNA-Seq Cell Barcode Whitelist" />
55
56 <expand macro="refgenomehandling" /> 62 <expand macro="refgenomehandling" />
57 <section name="solo" title="Advanced Settings" expanded="true"> 63 <section name="solo" title="Advanced Settings" expanded="true">
58 <conditional name="params"> 64 <conditional name="params">
59 <param name="chemistry" type="select" label="Configure Chemistry Options"> 65 <param name="chemistry" type="select" label="Configure Chemistry Options">
60 <option value="CR2" selected="true">Cell Ranger v2</option> 66 <option value="CR2" selected="true">Cell Ranger v2</option>
104 </data> 110 </data>
105 <data format="txt" name="output_stats" label="${tool.name} on ${on_string}: Feature Statistic Summaries" from_work_dir="Solo.out/Gene.stats" /> 111 <data format="txt" name="output_stats" label="${tool.name} on ${on_string}: Feature Statistic Summaries" from_work_dir="Solo.out/Gene.stats" />
106 </outputs> 112 </outputs>
107 <tests> 113 <tests>
108 <test expect_num_outputs="5"> 114 <test expect_num_outputs="5">
109 <param name="input1" value="41737_R1.fastq.sub240k.gz" ftype="fastqsanger.gz" /> 115 <repeat name="input_repeats" >
110 <param name="input2" value="41737_R2.fastq.sub240k.gz" ftype="fastqsanger.gz" /> 116 <param name="input1" value="41737_R1_sub240k.fastq.gz" ftype="fastqsanger.gz" />
117 <param name="input2" value="41737_R2_sub240k.fastq.gz" ftype="fastqsanger.gz" />
118 </repeat>
111 <param name="soloCBwhitelist" value="737K-august-2016.small.txt.gz" /> 119 <param name="soloCBwhitelist" value="737K-august-2016.small.txt.gz" />
112 <conditional name="refGenomeSource"> 120 <conditional name="refGenomeSource">
113 <param name="geneSource" value="history" /> 121 <param name="geneSource" value="history" />
114 <param name="genomeFastaFiles" value="SNORD83B.22.fa" /> 122 <param name="genomeFastaFiles" value="SNORD83B.22.fa" />
115 <param name="genomeSAindexNbases" value="5" /> 123 <param name="genomeSAindexNbases" value="4" />
116 <conditional name="GTFconditional"> 124 <conditional name="GTFconditional">
117 <param name="GTFselect" value="with-gtf" /> 125 <param name="GTFselect" value="with-gtf" />
118 <param name="sjdbOverhang" value="75"/> 126 <param name="sjdbOverhang" value="75"/>
119 <param name="sjdbGTFfile" value="SNORD83B.22.gtf" ftype="gtf"/> 127 <param name="sjdbGTFfile" value="SNORD83B.22.gtf" ftype="gtf"/>
120 </conditional> 128 </conditional>
143 <has_line_matching expression="\s+nUMIs\s+0" /> 151 <has_line_matching expression="\s+nUMIs\s+0" />
144 </assert_contents> 152 </assert_contents>
145 </output> 153 </output>
146 </test> 154 </test>
147 <test expect_num_outputs="5"> 155 <test expect_num_outputs="5">
148 <param name="input1" value="41737_R1.fastq.sub240k.gz" ftype="fastqsanger.gz" /> 156 <repeat name="input_repeats" >
149 <param name="input2" value="41737_R2.fastq.sub240k.gz" ftype="fastqsanger.gz" /> 157 <param name="input1" value="41737_R1_sub240k.fastq.gz" ftype="fastqsanger.gz" />
158 <param name="input2" value="41737_R2_sub240k.fastq.gz" ftype="fastqsanger.gz" />
159 </repeat>
150 <param name="soloCBwhitelist" value="737K-august-2016.small.txt.gz" /> 160 <param name="soloCBwhitelist" value="737K-august-2016.small.txt.gz" />
151 <conditional name="refGenomeSource"> 161 <conditional name="refGenomeSource">
152 <param name="geneSource" value="history" /> 162 <param name="geneSource" value="history" />
153 <param name="genomeFastaFiles" value="SNORD83B.22.fa" /> 163 <param name="genomeFastaFiles" value="SNORD83B.22.fa" />
154 <param name="genomeSAindexNbases" value="5" /> 164 <param name="genomeSAindexNbases" value="4" />
155 <conditional name="GTFconditional"> 165 <conditional name="GTFconditional">
156 <param name="GTFselect" value="with-gtf" /> 166 <param name="GTFselect" value="with-gtf" />
157 <param name="sjdbOverhang" value="75" /> 167 <param name="sjdbOverhang" value="75" />
158 <param name="sjdbGTFfile" value="SNORD83B.22.gtf" ftype="gtf"/> 168 <param name="sjdbGTFfile" value="SNORD83B.22.gtf" ftype="gtf"/>
159 </conditional> 169 </conditional>
175 <has_line line="TTTGTCATCTTAGAGC" /> 185 <has_line line="TTTGTCATCTTAGAGC" />
176 <has_line line="TTTGTCATCTTTCCTC" /> 186 <has_line line="TTTGTCATCTTTCCTC" />
177 </assert_contents> 187 </assert_contents>
178 </output> 188 </output>
179 </test> 189 </test>
190 <test expect_num_outputs="5">
191 <repeat name="input_repeats" >
192 <param name="input1" value="41737_R1_sub240k.fastq.gz" ftype="fastqsanger.gz" />
193 <param name="input2" value="41737_R2_sub240k.fastq.gz" ftype="fastqsanger.gz" />
194 </repeat>
195 <repeat name="input_repeats" >
196 <param name="input1" value="41737_R1_sub240k.fastq.gz" ftype="fastqsanger.gz" />
197 <param name="input2" value="41737_R2_sub240k.fastq.gz" ftype="fastqsanger.gz" />
198 </repeat>
199 <repeat name="input_repeats" >
200 <param name="input1" value="41737_R1_sub240k.fastq.gz" ftype="fastqsanger.gz" />
201 <param name="input2" value="41737_R2_sub240k.fastq.gz" ftype="fastqsanger.gz" />
202 </repeat>
203 <param name="soloCBwhitelist" value="737K-august-2016.small.txt.gz" />
204 <conditional name="refGenomeSource">
205 <param name="geneSource" value="history" />
206 <param name="genomeFastaFiles" value="SNORD83B.22.fa" />
207 <param name="genomeSAindexNbases" value="4" />
208 <conditional name="GTFconditional">
209 <param name="GTFselect" value="with-gtf" />
210 <param name="sjdbOverhang" value="75" />
211 <param name="sjdbGTFfile" value="SNORD83B.22.gtf" ftype="gtf"/>
212 </conditional>
213 </conditional>
214 <section name="solo" >
215 <conditional name="params">
216 <param name="chemistry" value="custom" />
217 <param name="soloCBstart" value="1" />
218 <param name="soloCBlen" value="16" />
219 <param name="soloUMIstart" value="17" />
220 <param name="soloUMIlen" value="10" />
221 </conditional>
222 <param name="soloStrand" value="Forward" />
223 <param name="soloFeatures" value="GeneFull" />
224 <param name="soloUMIdedup" value="1MM_Directional" />
225 </section>
226 <output name="output_barcodes" >
227 <assert_contents>
228 <has_line line="TTTGTCATCTTAGAGC" />
229 <has_line line="TTTGTCATCTTTCCTC" />
230 </assert_contents>
231 </output>
232 </test>
180 </tests> 233 </tests>
181 <help><![CDATA[ 234 <help><![CDATA[
182 **What it does** 235 **What it does**
183 236
184 **STARSolo** is a turnkey solution for analyzing droplet single cell RNA sequencing data (e.g. 10X Genomics Chromium System) built directly into STAR code. STARsolo inputs the raw FASTQ reads files, and performs the following operations: 237 **STARSolo** is a turnkey solution for analyzing droplet single cell RNA sequencing data (e.g. 10X Genomics Chromium System) built directly into STAR code. STARsolo inputs the raw FASTQ reads files, and performs the following operations: