Mercurial > repos > iuc > data_manager_star_index_builder

comparison data_manager/macros.xml @ 12:71c994a11f71 draft default tip

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/data_managers/data_manager_star_index_builder commit 57d05675396f0b44265fb4dbc8f9f891c6073219
author iuc
date Thu, 05 Dec 2024 06:49:40 +0000
parents d63c1442407f
children
comparison
equal deleted inserted replaced
11:d63c1442407f 12:71c994a11f71
2 <!-- REMEMBER to bump the version of @IDX_VERSION_SUFFIX@ 2 <!-- REMEMBER to bump the version of @IDX_VERSION_SUFFIX@
3 whenever you make changes to the @TOOL_VERSION@ token! 3 whenever you make changes to the @TOOL_VERSION@ token!
4 The data manager uses a symlink to this macro file to keep the STAR and 4 The data manager uses a symlink to this macro file to keep the STAR and
5 the index versions in sync, but you should manually update @IDX_VERSION_SUFFIX@ --> 5 the index versions in sync, but you should manually update @IDX_VERSION_SUFFIX@ -->
6 <!-- STAR version to be used --> 6 <!-- STAR version to be used -->
7 <token name="@TOOL_VERSION@">2.7.10b</token> 7 <token name="@TOOL_VERSION@">2.7.11a</token>
8 <token name="@VERSION_SUFFIX@">3</token> 8 <token name="@VERSION_SUFFIX@">1</token>
9 <token name="@PROFILE@">21.01</token> 9 <token name="@PROFILE@">21.01</token>
10 <!-- STAR index version compatible with this version of STAR 10 <!-- STAR index version compatible with this version of STAR
11 This is the STAR version that introduced the index structure expected 11 This is the STAR version that introduced the index structure expected
12 by the current version. 12 by the current version.
13 It can be found for any specific version of STAR with: 13 It can be found for any specific version of STAR with:
14 STAR -h | grep versionGenome 14 STAR -h | grep versionGenome
15 or by looking for the versionGenome parameter in source/parametersDefault 15 or by looking for the versionGenome parameter in source/parametersDefault
16 of STAR's source code --> 16 of STAR's source code -->
17 <token name="@IDX_VERSION@">2.7.4a</token> 17 <token name="@IDX_VERSION@">2.7.4a</token>
18 <token name="@IDX_VERSION_SUFFIX@">1</token> 18 <token name="@IDX_VERSION_SUFFIX@">3</token>
19 <token name="@IDX_DATA_TABLE@">rnastar_index2x_versioned</token> 19 <token name="@IDX_DATA_TABLE@">rnastar_index2x_versioned</token>
20
21 <xml name="requirements"> 20 <xml name="requirements">
22 <requirements> 21 <requirements>
23 <requirement type="package" version="@TOOL_VERSION@">star</requirement> 22 <requirement type="package" version="@TOOL_VERSION@">star</requirement>
24 <requirement type="package" version="1.16.1">samtools</requirement> 23 <requirement type="package" version="1.18">samtools</requirement>
25 <requirement type="package" version="1.12">gzip</requirement> 24 <requirement type="package" version="1.13">gzip</requirement>
26 <yield /> 25 <yield/>
27 </requirements> 26 </requirements>
28 </xml> 27 </xml>
29
30 <xml name="edam"> 28 <xml name="edam">
31 <edam_topics> 29 <edam_topics>
32 <edam_topic>topic_3170</edam_topic> 30 <edam_topic>topic_3170</edam_topic>
33 <edam_topic>topic_3308</edam_topic> 31 <edam_topic>topic_3308</edam_topic>
34 </edam_topics> 32 </edam_topics>
35 <edam_operations> 33 <edam_operations>
36 <edam_operation>operation_0292</edam_operation> 34 <edam_operation>operation_0292</edam_operation>
37 </edam_operations> 35 </edam_operations>
38 </xml> 36 </xml>
39
40 <xml name="index_selection" token_with_gene_model="0"> 37 <xml name="index_selection" token_with_gene_model="0">
41 <param argument="--genomeDir" type="select" 38 <param argument="--genomeDir" type="select" label="Select reference genome" help="If your genome of interest is not listed, contact the Galaxy team">
42 label="Select reference genome"
43 help="If your genome of interest is not listed, contact the Galaxy team">
44 <options from_data_table="@IDX_DATA_TABLE@"> 39 <options from_data_table="@IDX_DATA_TABLE@">
45 <filter type="static_value" column="4" value="@WITH_GENE_MODEL@" /> 40 <filter type="static_value" column="4" value="@WITH_GENE_MODEL@"/>
46 <filter type="static_value" column="5" value="@IDX_VERSION@" /> 41 <filter type="static_value" column="5" value="@IDX_VERSION@"/>
47 <filter type="sort_by" column="2" /> 42 <filter type="sort_by" column="2"/>
48 <validator type="no_options" message="No indexes are available for the selected input dataset" /> 43 <validator type="no_options" message="No indexes are available for the selected input dataset"/>
49 </options> 44 </options>
50 </param> 45 </param>
51 </xml> 46 </xml>
52
53 <token name="@FASTQ_GZ_OPTION@"> 47 <token name="@FASTQ_GZ_OPTION@">
54 --readFilesCommand zcat 48 --readFilesCommand zcat
55 </token> 49 </token>
56 <xml name="citations"> 50 <xml name="citations">
57 <citations> 51 <citations>
58 <citation type="doi">10.1093/bioinformatics/bts635</citation> 52 <citation type="doi">10.1093/bioinformatics/bts635</citation>
59 </citations> 53 </citations>
60 </xml> 54 </xml>
61 <xml name="SJDBOPTIONS"> 55 <xml name="SJDBOPTIONS">
62 <param argument="--sjdbGTFfile" type="data" format="gff3,gtf" label="Gene model (gff3,gtf) file for splice junctions" optional="false" help="Exon junction information for mapping splices"/> 56 <param argument="--sjdbGTFfile" type="data" format="gff3,gtf" label="Gene model (gff3,gtf) file for splice junctions" optional="false" help="Exon junction information for mapping splices"/>
63 <param argument="--sjdbOverhang" type="integer" min="1" value="100" label="Length of the genomic sequence around annotated junctions" help="Used in constructing the splice junctions database. Ideal value is ReadLength-1"/> 57 <param argument="--sjdbGTFfeatureExon" type="text" value="exon" label="Elements to use from the gene model to use for splice junctions" help="By default and for almost all cases: 'exon', referring to finding junctions at the RNA splice sites. This can optionally be changed to allow splicing at other levels, such as 'gene', 'transcript', 'CDS'."/>
58 <param argument="--sjdbOverhang" type="integer" min="1" value="100" label="Length of the genomic sequence around annotated junctions" help="Used in constructing the splice junctions database. Ideal value is ReadLength-1"/>
64 </xml> 59 </xml>
65 <xml name="dbKeyActions"> 60 <xml name="dbKeyActions">
66 <actions> 61 <actions>
67 <expand macro="dbKeyAction"/> 62 <expand macro="dbKeyAction"/>
68 </actions> 63 </actions>
77 </option> 72 </option>
78 </action> 73 </action>
79 </when> 74 </when>
80 <when value="history"> 75 <when value="history">
81 <action type="metadata" name="dbkey"> 76 <action type="metadata" name="dbkey">
82 <option type="from_param" name="refGenomeSource.genomeFastaFiles" param_attribute="dbkey" /> 77 <option type="from_param" name="refGenomeSource.genomeFastaFiles" param_attribute="dbkey"/>
83 </action> 78 </action>
84 </when> 79 </when>
85 </conditional> 80 </conditional>
86 </xml> 81 </xml>
87 <token name="@TEMPINDEX@"><![CDATA[ 82 <token name="@TEMPINDEX@"><![CDATA[
101 #if 'GTFconditional' in $refGenomeSource: 96 #if 'GTFconditional' in $refGenomeSource:
102 ## GTFconditional exists only in STAR, but not STARsolo 97 ## GTFconditional exists only in STAR, but not STARsolo
103 #if str($refGenomeSource.GTFconditional.GTFselect) == 'with-gtf': 98 #if str($refGenomeSource.GTFconditional.GTFselect) == 'with-gtf':
104 --sjdbOverhang '${refGenomeSource.GTFconditional.sjdbOverhang}' 99 --sjdbOverhang '${refGenomeSource.GTFconditional.sjdbOverhang}'
105 --sjdbGTFfile '${refGenomeSource.GTFconditional.sjdbGTFfile}' 100 --sjdbGTFfile '${refGenomeSource.GTFconditional.sjdbGTFfile}'
101 --sjdbGTFfeatureExon '${refGenomeSource.GTFconditional.sjdbGTFfeatureExon}'
106 #if str($refGenomeSource.GTFconditional.sjdbGTFfile.ext) == 'gff3': 102 #if str($refGenomeSource.GTFconditional.sjdbGTFfile.ext) == 'gff3':
107 --sjdbGTFtagExonParentTranscript Parent 103 --sjdbGTFtagExonParentTranscript Parent
108 #end if 104 #end if
109 #end if 105 #end if
110 #else: 106 #else:
111 ## ref genome selection is less complex for STARsolo cause 107 ## ref genome selection is less complex for STARsolo because
112 ## with-gtf is mandatory there 108 ## with-gtf is mandatory there
113 --sjdbOverhang '${refGenomeSource.sjdbOverhang}' 109 --sjdbOverhang '${refGenomeSource.sjdbOverhang}'
114 --sjdbGTFfile '${refGenomeSource.sjdbGTFfile}' 110 --sjdbGTFfile '${refGenomeSource.sjdbGTFfile}'
111 --sjdbGTFfeatureExon '${refGenomeSource.sjdbGTFfeatureExon}'
115 #if str($refGenomeSource.sjdbGTFfile.ext) == 'gff3': 112 #if str($refGenomeSource.sjdbGTFfile.ext) == 'gff3':
116 --sjdbGTFtagExonParentTranscript Parent 113 --sjdbGTFtagExonParentTranscript Parent
117 #end if 114 #end if
118 #end if 115 #end if
119 #if str($refGenomeSource.genomeSAindexNbases): 116 #if str($refGenomeSource.genomeSAindexNbases):
120 --genomeSAindexNbases ${refGenomeSource.genomeSAindexNbases} 117 --genomeSAindexNbases ${refGenomeSource.genomeSAindexNbases}
118 #end if
119 ## Diploid mode
120 #if 'diploidconditional' in $refGenomeSource:
121 #if str($refGenomeSource.diploidconditional.diploid) == 'Yes':
122 --genomeTransformVCF '${refGenomeSource.diploidconditional.genomeTransformVCF}'
123 --genomeTransformType Diploid
124 #end if
121 #end if 125 #end if
122 --runThreadN \${GALAXY_SLOTS:-4} 126 --runThreadN \${GALAXY_SLOTS:-4}
123 ## in bytes 127 ## in bytes
124 --limitGenomeGenerateRAM \$((\${GALAXY_MEMORY_MB:-31000} * 1000000)) 128 --limitGenomeGenerateRAM \$((\${GALAXY_MEMORY_MB:-31000} * 1000000))
125 && 129 &&
126 #end if 130 #end if
127 ]]></token> 131 ]]></token>
128 <token name="@REFGENOMEHANDLING@" ><![CDATA[ 132 <token name="@REFGENOMEHANDLING@"><![CDATA[
129 --runThreadN \${GALAXY_SLOTS:-4} 133 --runThreadN \${GALAXY_SLOTS:-4}
130 --genomeLoad NoSharedMemory 134 --genomeLoad NoSharedMemory
131 --genomeDir 135 --genomeDir
132 #if str($refGenomeSource.geneSource) == 'history': 136 #if str($refGenomeSource.geneSource) == 'history':
133 tempstargenomedir 137 tempstargenomedir
135 '${refGenomeSource.GTFconditional.genomeDir.fields.path}' 139 '${refGenomeSource.GTFconditional.genomeDir.fields.path}'
136 ## Handle difference between indices with/without annotations 140 ## Handle difference between indices with/without annotations
137 #if str($refGenomeSource.GTFconditional.GTFselect) == 'without-gtf-with-gtf': 141 #if str($refGenomeSource.GTFconditional.GTFselect) == 'without-gtf-with-gtf':
138 --sjdbOverhang $refGenomeSource.GTFconditional.sjdbOverhang 142 --sjdbOverhang $refGenomeSource.GTFconditional.sjdbOverhang
139 --sjdbGTFfile '${refGenomeSource.GTFconditional.sjdbGTFfile}' 143 --sjdbGTFfile '${refGenomeSource.GTFconditional.sjdbGTFfile}'
144 --sjdbGTFfeatureExon '${refGenomeSource.GTFconditional.sjdbGTFfeatureExon}'
140 #if str($refGenomeSource.GTFconditional.sjdbGTFfile.ext) == 'gff3': 145 #if str($refGenomeSource.GTFconditional.sjdbGTFfile.ext) == 'gff3':
141 --sjdbGTFtagExonParentTranscript Parent 146 --sjdbGTFtagExonParentTranscript Parent
142 #end if 147 #end if
143 #end if 148 #end if
144 #end if 149 #end if
145 ]]></token> 150 ]]></token>
146 <token name="@READSHANDLING@" ><![CDATA[ 151 <token name="@READSHANDLING@"><![CDATA[
147 ## Check that the input pairs are of the same type 152 ## Check that the input pairs are of the same type
148 ## otherwise STARsolo will run for a long time and then error out. 153 ## otherwise STARsolo will run for a long time and then error out.
149 ## We consume either repeats of two inputs R1 + R2 154 ## We consume either repeats of two inputs R1 + R2
150 ## or a collection of paired reads. 155 ## or a collection of paired reads.
151 #if str($sc.input_types.use) == "repeat": 156 #if str($sc.input_types.use) == "repeat":
170 --soloCBmatchWLtype $sc.soloCBmatchWLtype 175 --soloCBmatchWLtype $sc.soloCBmatchWLtype
171 #if $r1.is_of_type('fastq.gz', 'fastqsanger.gz'): 176 #if $r1.is_of_type('fastq.gz', 'fastqsanger.gz'):
172 @FASTQ_GZ_OPTION@ 177 @FASTQ_GZ_OPTION@
173 #end if 178 #end if
174 ]]></token> 179 ]]></token>
175 <token name="@LIMITS@" ><![CDATA[ 180 <token name="@LIMITS@"><![CDATA[
176 --limitOutSJoneRead $getVar('algo.params.junction_limits.limitOutSJoneRead', $getVar('solo.junction_limits.limitOutSJoneRead', 1000)) 181 --limitOutSJoneRead $getVar('algo.params.junction_limits.limitOutSJoneRead', $getVar('solo.junction_limits.limitOutSJoneRead', 1000))
177 --limitOutSJcollapsed $getVar('algo.params.junction_limits.limitOutSJcollapsed', $getVar('solo.junction_limits.limitOutSJcollapsed', 1000000)) 182 --limitOutSJcollapsed $getVar('algo.params.junction_limits.limitOutSJcollapsed', $getVar('solo.junction_limits.limitOutSJcollapsed', 1000000))
178 --limitSjdbInsertNsj $getVar('algo.params.junction_limits.limitSjdbInsertNsj', $getVar('solo.junction_limits.limitSjdbInsertNsj', 1000000)) 183 --limitSjdbInsertNsj $getVar('algo.params.junction_limits.limitSjdbInsertNsj', $getVar('solo.junction_limits.limitSjdbInsertNsj', 1000000))
179 ]]></token> 184 ]]></token>
180 <xml name="ref_selection"> 185 <xml name="ref_selection">
181 <param argument="--genomeFastaFiles" type="data" format="fasta,fasta.gz" label="Select a reference genome" /> 186 <param argument="--genomeFastaFiles" type="data" format="fasta,fasta.gz" label="Select a reference genome"/>
182 <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)"/> 187 <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)"/>
183 </xml> 188 </xml>
184 <xml name="stdio" > 189 <xml name="stdio">
185 <stdio> 190 <stdio>
186 <regex match="FATAL error" source="both" level="fatal"/> 191 <regex match="FATAL error" source="both" level="fatal"/>
187 <regex match="EXITING: FATAL INPUT ERROR:" source="both" level="fatal"/> 192 <regex match="EXITING: FATAL INPUT ERROR:" source="both" level="fatal"/>
188 <regex match="EXITING: fatal error trying to allocate genome arrays, exception thrown: std::bad_alloc" source="both" level="fatal"/> 193 <regex match="EXITING: fatal error trying to allocate genome arrays, exception thrown: std::bad_alloc" source="both" level="fatal"/>
189 <regex match="\[sam_read1\] missing header\? Abort!" source="both" level="fatal"/> 194 <regex match="\[sam_read1\] missing header\? Abort!" source="both" level="fatal"/>
190 <yield /> 195 <yield/>
191 </stdio> 196 </stdio>
192 </xml> 197 </xml>
193 <xml name="input_selection"> 198 <xml name="input_selection">
194 <conditional name="input_types" > 199 <conditional name="input_types">
195 <param name="use" type="select" label="Input Type" > 200 <param name="use" type="select" label="Input Type">
196 <option value="repeat" >Separate barcode and cDNA reads</option> 201 <option value="repeat">Separate barcode and cDNA reads</option>
197 <option value="list_paired" >Paired collection of barcode and cDNA reads</option> 202 <option value="list_paired">Paired collection of barcode and cDNA reads</option>
198 </param> 203 </param>
199 <when value="repeat"> 204 <when value="repeat">
200 <param format="fastq,fasta,fastq.gz,fastqsanger.gz" name="input1" type="data" multiple="true" 205 <param format="fastq,fasta,fastq.gz,fastqsanger.gz" name="input1" type="data" multiple="true" label="RNA-Seq FASTQ/FASTA file, Barcode reads"/>
201 label="RNA-Seq FASTQ/FASTA file, Barcode reads" /> 206 <param format="fastq,fasta,fastq.gz,fastqsanger.gz" name="input2" type="data" multiple="true" label="RNA-Seq FASTQ/FASTA file, cDNA reads"/>
202 <param format="fastq,fasta,fastq.gz,fastqsanger.gz" name="input2" type="data" multiple="true"
203 label="RNA-Seq FASTQ/FASTA file, cDNA reads"/>
204 </when> 207 </when>
205 <when value="list_paired"> 208 <when value="list_paired">
206 <param name="input_collection" collection_type="paired" type="data_collection" format="fastq,fasta,fastq.gz,fastqsanger.gz" label="Collection of Pairs" /> 209 <param name="input_collection" collection_type="paired" type="data_collection" format="fastq,fasta,fastq.gz,fastqsanger.gz" label="Collection of Pairs"/>
207 </when> 210 </when>
208 </conditional> 211 </conditional>
209 </xml> 212 </xml>
210 <xml name="input_selection_smart_seq"> 213 <xml name="input_selection_smart_seq">
211 <conditional name="input_types_smart_seq" > 214 <conditional name="input_types_smart_seq">
212 <param name="use" type="select" label="Input Type" > 215 <param name="use" type="select" label="Input Type">
213 <option value="list_single_end" >Single-end FASTQ collection</option> 216 <option value="list_single_end">Single-end FASTQ collection</option>
214 <option value="list_paired_end" >Paired FASTQ collection</option> 217 <option value="list_paired_end">Paired FASTQ collection</option>
215 </param> 218 </param>
216 <when value="list_single_end"> 219 <when value="list_single_end">
217 <param name="single_end_collection" collection_type="list" type="data_collection" format="fastq,fasta,fastq.gz,fastqsanger.gz" label="List of single-end FASTQ files" /> 220 <param name="single_end_collection" collection_type="list" type="data_collection" format="fastq,fasta,fastq.gz,fastqsanger.gz" label="List of single-end FASTQ files"/>
218 </when> 221 </when>
219 <when value="list_paired_end"> 222 <when value="list_paired_end">
220 <param name="paired_end_collection" collection_type="list:paired" type="data_collection" format="fastq,fasta,fastq.gz,fastqsanger.gz" label="List of paired-end FASTQ files" /> 223 <param name="paired_end_collection" collection_type="list:paired" type="data_collection" format="fastq,fasta,fastq.gz,fastqsanger.gz" label="List of paired-end FASTQ files"/>
221 </when> 224 </when>
222 </conditional> 225 </conditional>
223 </xml> 226 </xml>
224 <xml name="umidedup_options"> 227 <xml name="umidedup_options">
225 <option value="1MM_All" selected="true">Collapse all UMIs with 1 mismatch distance to each other (1MM_All)</option> 228 <option value="1MM_All" selected="true">Collapse all UMIs with 1 mismatch distance to each other (1MM_All)</option>
226 <option value="1MM_Directional_UMItools" >Directional method from the UMI-tool</option> 229 <option value="1MM_Directional_UMItools">Directional method from the UMI-tool</option>
227 <option value="1MM_Directional" >Directional with stringent UMI deduplication</option> 230 <option value="1MM_Directional">Directional with stringent UMI deduplication</option>
228 </xml> 231 </xml>
229 <xml name="anchor_types"> 232 <xml name="anchor_types">
230 <option value="0">Read start</option> 233 <option value="0">Read start</option>
231 <option value="1">Read end</option> 234 <option value="1">Read end</option>
232 <option value="2">Adapter start</option> 235 <option value="2">Adapter start</option>
233 <option value="3">Adapter end</option> 236 <option value="3">Adapter end</option>
234 </xml> 237 </xml>
235 <xml name="cb_match_wl_common"> 238 <xml name="cb_match_wl_common">
236 <option value="Exact" >Exact</option> 239 <option value="Exact">Exact</option>
237 <option value="1MM" >Single match (1MM)</option> 240 <option value="1MM">Single match (1MM)</option>
238 </xml> 241 </xml>
239 <xml name="cb_match_wl_cellranger"> 242 <xml name="cb_match_wl_cellranger">
240 <option value="1MM_multi" selected="true" >Multiple matches (CellRanger 2, 1MM_multi)</option> 243 <option value="1MM_multi" selected="true">Multiple matches (CellRanger 2, 1MM_multi)</option>
241 <option value="1MM_multi_pseudocounts" >Multiple matches (CellRanger 3, 1MM_multi_pseudocounts)</option> 244 <option value="1MM_multi_pseudocounts">Multiple matches (CellRanger 3, 1MM_multi_pseudocounts)</option>
242 <option value="1MM_multi_Nbase_pseudocounts" >Multimatching to WL is allowed for CBs with N-bases (CellRanger 3, 1MM_multi_Nbase_pseudocounts)</option> 245 <option value="1MM_multi_Nbase_pseudocounts">Multimatching to WL is allowed for CBs with N-bases (CellRanger 3, 1MM_multi_Nbase_pseudocounts)</option>
243 </xml> 246 </xml>
244 <xml name="solo_adapter_params"> 247 <xml name="solo_adapter_params">
245 <param argument="--soloAdapterSequence" type="text" value="-" label="Adapter sequence to anchor barcodes." > 248 <param argument="--soloAdapterSequence" type="text" value="-" label="Adapter sequence to anchor barcodes.">
246 <sanitizer> 249 <sanitizer>
247 <valid initial="string.digits"> 250 <valid initial="string.digits">
248 <add value="-"/> 251 <add value="-"/>
249 <add value="A"/> 252 <add value="A"/>
250 <add value="T"/> 253 <add value="T"/>
252 <add value="G"/> 255 <add value="G"/>
253 <add value="N"/> 256 <add value="N"/>
254 </valid> 257 </valid>
255 </sanitizer> 258 </sanitizer>
256 </param> 259 </param>
257 <param argument="--soloAdapterMismatchesNmax" type="integer" min="1" value="1" label="Maximum number of mismatches allowed in adapter sequence" /> 260 <param argument="--soloAdapterMismatchesNmax" type="integer" min="1" value="1" label="Maximum number of mismatches allowed in adapter sequence"/>
258 <param argument="--clipAdapterType" type="select" > 261 <param argument="--clipAdapterType" type="select">
259 <option value="Hamming" selected="true" >Adapter clipping based on Hamming distance</option> 262 <option value="Hamming" selected="true">Adapter clipping based on Hamming distance</option>
260 <option value="CellRanger4" >5p and 3p adapter clipping similar to CellRanger4</option> 263 <option value="CellRanger4">5p and 3p adapter clipping similar to CellRanger4</option>
261 <option value="None" >No adapter clipping</option> 264 <option value="None">No adapter clipping</option>
262 </param> 265 </param>
263 </xml> 266 </xml>
264 <xml name="common_SAM_attributes"> 267 <xml name="common_SAM_attributes">
265 <option value="NH" selected="true">NH (number of reported alignments/hits for the read)</option> 268 <option value="NH" selected="true">NH (number of reported alignments/hits for the read)</option>
266 <option value="HI" selected="true">HI (query hit index)</option> 269 <option value="HI" selected="true">HI (query hit index)</option>
271 <option value="jM">jM (intron motifs for all junctions)</option> 274 <option value="jM">jM (intron motifs for all junctions)</option>
272 <option value="jI">jI (1-based start and end of introns for all junctions)</option> 275 <option value="jI">jI (1-based start and end of introns for all junctions)</option>
273 </xml> 276 </xml>
274 <xml name="limits"> 277 <xml name="limits">
275 <section name="junction_limits" title="Junction Limits" expanded="false"> 278 <section name="junction_limits" title="Junction Limits" expanded="false">
276 <param argument="--limitOutSJoneRead" type="integer" min="1" value="1000" label="Maximum number of junctions for one read (including all multimappers)" /> 279 <param argument="--limitOutSJoneRead" type="integer" min="1" value="1000" label="Maximum number of junctions for one read (including all multimappers)"/>
277 <param argument="--limitOutSJcollapsed" type="integer" min="1" value="1000000" label="Maximum number of collapsed junctions" /> 280 <param argument="--limitOutSJcollapsed" type="integer" min="1" value="1000000" label="Maximum number of collapsed junctions"/>
278 <param argument="--limitSjdbInsertNsj" type="integer" min="0" value="1000000" label="Maximum number of inserts to be inserted into the genome on the fly." /> 281 <param argument="--limitSjdbInsertNsj" type="integer" min="0" value="1000000" label="Maximum number of inserts to be inserted into the genome on the fly."/>
279 </section> 282 </section>
280 </xml> 283 </xml>
281 <xml name="outCountActions"> 284 <xml name="outCountActions">
282 <actions> 285 <actions>
283 <action name="column_names" type="metadata" default="GeneID,Counts_unstrand,Counts_firstStrand,Counts_secondStrand" /> 286 <action name="column_names" type="metadata" default="GeneID,Counts_unstrand,Counts_firstStrand,Counts_secondStrand"/>
284 <expand macro="dbKeyAction"/> 287 <expand macro="dbKeyAction"/>
285 </actions> 288 </actions>
286 </xml> 289 </xml>
287 <xml name="outWig"> 290 <xml name="outWig">
288 <conditional name="outWig"> 291 <conditional name="outWig">
291 <option value="bedGraph">Yes in bedgraph format</option> 294 <option value="bedGraph">Yes in bedgraph format</option>
292 <option value="wiggle">Yes in wiggle format</option> 295 <option value="wiggle">Yes in wiggle format</option>
293 </param> 296 </param>
294 <when value="None"> 297 <when value="None">
295 <!-- This is necessary for the filtering of output --> 298 <!-- This is necessary for the filtering of output -->
296 <param name="outWigStrand" type="hidden" value="false" /> 299 <param name="outWigStrand" type="hidden" value="false"/>
297 </when> 300 </when>
298 <when value="bedGraph"> 301 <when value="bedGraph">
299 <expand macro="outWigParams"/> 302 <expand macro="outWigParams"/>
300 </when> 303 </when>
301 <when value="wiggle"> 304 <when value="wiggle">
339 #end if 342 #end if
340 ]]></token> 343 ]]></token>
341 <xml name="outWigOutputs"> 344 <xml name="outWigOutputs">
342 <data format="bedgraph" name="signal_unique_str1" label="${tool.name} on ${on_string}: Coverage Uniquely mapped strand 1" from_work_dir="Signal.Unique.str1.out"> 345 <data format="bedgraph" name="signal_unique_str1" label="${tool.name} on ${on_string}: Coverage Uniquely mapped strand 1" from_work_dir="Signal.Unique.str1.out">
343 <filter>outWig['outWigType'] != "None"</filter> 346 <filter>outWig['outWigType'] != "None"</filter>
344 <expand macro="dbKeyActions" /> 347 <expand macro="dbKeyActions"/>
345 <change_format> 348 <change_format>
346 <when input="outWig.outWigType" value="wiggle" format="wig" /> 349 <when input="outWig.outWigType" value="wiggle" format="wig"/>
347 </change_format> 350 </change_format>
348 </data> 351 </data>
349 <data format="bedgraph" name="signal_uniquemultiple_str1" label="${tool.name} on ${on_string}: Coverage Uniquely + Multiple mapped strand 1" from_work_dir="Signal.UniqueMultiple.str1.out"> 352 <data format="bedgraph" name="signal_uniquemultiple_str1" label="${tool.name} on ${on_string}: Coverage Uniquely + Multiple mapped strand 1" from_work_dir="Signal.UniqueMultiple.str1.out">
350 <filter>outWig['outWigType'] != "None"</filter> 353 <filter>outWig['outWigType'] != "None"</filter>
351 <expand macro="dbKeyActions" /> 354 <expand macro="dbKeyActions"/>
352 <change_format> 355 <change_format>
353 <when input="outWig.outWigType" value="wiggle" format="wig" /> 356 <when input="outWig.outWigType" value="wiggle" format="wig"/>
354 </change_format> 357 </change_format>
355 </data> 358 </data>
356 <data format="bedgraph" name="signal_unique_str2" label="${tool.name} on ${on_string}: Coverage Uniquely mapped strand 2" from_work_dir="Signal.Unique.str2.out"> 359 <data format="bedgraph" name="signal_unique_str2" label="${tool.name} on ${on_string}: Coverage Uniquely mapped strand 2" from_work_dir="Signal.Unique.str2.out">
357 <filter>outWig['outWigType'] != "None" and outWig['outWigStrand']</filter> 360 <filter>outWig['outWigType'] != "None" and outWig['outWigStrand']</filter>
358 <expand macro="dbKeyActions" /> 361 <expand macro="dbKeyActions"/>
359 <change_format> 362 <change_format>
360 <when input="outWig.outWigType" value="wiggle" format="wig" /> 363 <when input="outWig.outWigType" value="wiggle" format="wig"/>
361 </change_format> 364 </change_format>
362 </data> 365 </data>
363 <data format="bedgraph" name="signal_uniquemultiple_str2" label="${tool.name} on ${on_string}: Coverage Uniquely + Multiple mapped strand 2" from_work_dir="Signal.UniqueMultiple.str2.out"> 366 <data format="bedgraph" name="signal_uniquemultiple_str2" label="${tool.name} on ${on_string}: Coverage Uniquely + Multiple mapped strand 2" from_work_dir="Signal.UniqueMultiple.str2.out">
364 <filter>outWig['outWigType'] != "None" and outWig['outWigStrand']</filter> 367 <filter>outWig['outWigType'] != "None" and outWig['outWigStrand']</filter>
365 <expand macro="dbKeyActions" /> 368 <expand macro="dbKeyActions"/>
366 <change_format> 369 <change_format>
367 <when input="outWig.outWigType" value="wiggle" format="wig" /> 370 <when input="outWig.outWigType" value="wiggle" format="wig"/>
368 </change_format> 371 </change_format>
369 </data> 372 </data>
370 </xml> 373 </xml>
371 <xml name="quantMode"> 374 <xml name="quantMode">
372 <conditional name="quantmode_output"> 375 <conditional name="quantmode_output">
373 <param argument="--quantMode" type="select" 376 <param argument="--quantMode" type="select" label="Per gene/transcript output" help="STAR can provide analysis results not only with respect to the reference genome, but also with respect to genes and transcripts described by a gene model. Note: This functionality requires either the selection above of a cached index with a gene model, or a gene model provided alongside the index/reference genome in GTF or GFF3 format!">
374 label="Per gene/transcript output"
375 help="STAR can provide analysis results not only with respect to the reference genome, but also with respect to genes and transcripts described by a gene model. Note: This functionality requires either the selection above of a cached index with a gene model, or a gene model provided alongside the index/reference genome in GTF or GFF3 format!">
376 <option value="-">No per gene or transcript output</option> 377 <option value="-">No per gene or transcript output</option>
377 <option value="GeneCounts">Per gene read counts (GeneCounts)</option> 378 <option value="GeneCounts">Per gene read counts (GeneCounts)</option>
378 <option value="TranscriptomeSAM">Transcript-based BAM output (TranscriptomeSAM)</option> 379 <option value="TranscriptomeSAM">Transcript-based BAM output (TranscriptomeSAM)</option>
379 <option value="TranscriptomeSAM GeneCounts">Both per gene read counts and transcript-based BAM output (TranscriptomeSAM GeneCounts)</option> 380 <option value="TranscriptomeSAM GeneCounts">Both per gene read counts and transcript-based BAM output (TranscriptomeSAM GeneCounts)</option>
380 </param> 381 </param>
381 <when value="-" /> 382 <when value="-"/>
382 <when value="GeneCounts" /> 383 <when value="GeneCounts"/>
383 <when value="TranscriptomeSAM"> 384 <when value="TranscriptomeSAM">
384 <param argument="--quantTranscriptomeBan" type="boolean" truevalue="IndelSoftclipSingleend" falsevalue="Singleend" 385 <param argument="--quantTranscriptomeBan" type="boolean" truevalue="IndelSoftclipSingleend" falsevalue="Singleend" label="Exclude alignments with indels or soft clipping from the transcriptome BAM output?" help="You will need to exclude alignments with indels and soft-clipped bases from the transcriptome BAM output for compatibility with certain transcript quantification tools, most notably RSEM. If you are using a tool, like eXpress, that can deal with indels and soft-clipped bases, you can achieve better results by leaving this option disabled."/>
385 label="Exclude alignments with indels or soft clipping from the transcriptome BAM output?"
386 help="You will need to exclude alignments with indels and soft-clipped bases from the transcriptome BAM output for compatibility with certain transcript quantification tools, most notably RSEM. If you are using a tool, like eXpress, that can deal with indels and soft-clipped bases, you can achieve better results by leaving this option disabled." />
387 </when> 386 </when>
388 <when value="TranscriptomeSAM GeneCounts"> 387 <when value="TranscriptomeSAM GeneCounts">
389 <param argument="--quantTranscriptomeBan" type="boolean" truevalue="IndelSoftclipSingleend" falsevalue="Singleend" 388 <param argument="--quantTranscriptomeBan" type="boolean" truevalue="IndelSoftclipSingleend" falsevalue="Singleend" label="Exclude alignments with indels or soft clipping from the transcriptome BAM output?" help="You will need to exclude alignments with indels and soft-clipped bases from the transcriptome BAM output for compatibility with certain transcript quantification tools, most notably RSEM. If you are using a tool, like eXpress, that can deal with indels and soft-clipped bases, you can achieve better results by leaving this option disabled."/>
390 label="Exclude alignments with indels or soft clipping from the transcriptome BAM output?"
391 help="You will need to exclude alignments with indels and soft-clipped bases from the transcriptome BAM output for compatibility with certain transcript quantification tools, most notably RSEM. If you are using a tool, like eXpress, that can deal with indels and soft-clipped bases, you can achieve better results by leaving this option disabled." />
392 </when> 389 </when>
393 </conditional> 390 </conditional>
394 </xml> 391 </xml>
395 <xml name="quantModeNoGTF"> 392 <xml name="quantModeNoGTF">
396 <conditional name="quantmode_output"> 393 <conditional name="quantmode_output">
397 <param argument="--quantMode" type="select" 394 <param argument="--quantMode" type="select" label="Per gene/transcript output">
398 label="Per gene/transcript output">
399 <option value="-">No per gene or transcript output as no GTF was provided</option> 395 <option value="-">No per gene or transcript output as no GTF was provided</option>
400 </param> 396 </param>
401 <when value="-" /> 397 <when value="-"/>
402 </conditional> 398 </conditional>
403 </xml> 399 </xml>
404 <xml name="outSAMmapqUnique"> 400 <xml name="outSAMmapqUnique">
405 <!-- MAPQ 255 is the default in STAR (coming from tophat behaviour and compatibility for Cufflinks) but it is a problematic value 401 <!-- MAPQ 255 is the default in STAR (coming from tophat behaviour and compatibility for Cufflinks) but it is a problematic value
406 - according to SAM/BAM specs it means "undefined". 402 - according to SAM/BAM specs it means "undefined".
407 - 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. --> 403 - 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. -->
408 <param argument="--outSAMmapqUnique" type="integer" value="60" min="0" max="255" 404 <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: &gt;=5 mappings =&gt; MAPQ=0; 3-4 mappings =&gt; MAPQ=1; 2 mappings =&gt; 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."/>
409 label="MAPQ value for unique mappers" 405 </xml>
410 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 406 <xml name="wasp">
411 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." /> 407 <!--
408 This is re-implementation of the original WASP algorithm by Bryce van de Geijn, Graham McVicker,
409 Yoav Gilad and Jonathan K Pritchard. Please cite the original WASP paper: Nature Methods 12,
410 1061–1063 (2015) https://www.nature.com/articles/nmeth.3582. WASP filtering is activated
411 with "waspOutputMode SAMtag".
412 -->
413 <conditional name="wasp_conditional">
414 <param argument="--waspOutputMode" type="select" label="Actiavte WASP filtering">
415 <help><![CDATA[This is a reimplementation of the original WASP algorithm by Bryce van de Geijn, Graham McVicker,
416 Yoav Gilad and Jonathan K Pritchard. https://doi.org/10.1038/nmeth.3582. This option will add the vW tag to the SAM output. vW:i:1 means
417 alignment passed WASP filtering, and all other values mean it did not:<br/>
418 - vW:i:2 = multi-mapping read<br/>
419 - vW:i:3 = variant base in the read is N (non-ACGT)<br/>
420 - vW:i:4 = remapped read did not map <br/>
421 - vW:i:5 = remapped read multi-maps <br/>
422 - vW:i:6 = remapped read maps to a different locus <br/>
423 - vW:i:7 = read overlaps too many variants <br/>
424 ]]>
425 </help>
426 <option value="" selected="true">No WASP filtering</option>
427 <option value="wasp_mode">Activate WASP filtering</option>
428 </param>
429 <when value="wasp_mode">
430 <param argument="--varVCFfile" type="data" format="vcf" label="VCF file with personal variants" help="Each variant is expected to have a genotype with two alleles. The VCF file needs to have the 10th column with genotype recorded as 0/1, 1/0, 1/1 (or | instead of /)"/>
431 </when>
432 <when value=""/>
433 </conditional>
412 </xml> 434 </xml>
413 </macros> 435 </macros>