Mercurial > repos > iuc > rgrnastar

comparison rg_rnaStar.xml @ 10:d82339e37e8e 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 686574b0392e554b75035a9b79bc919dfda9ab97"
author iuc
date Thu, 15 Aug 2019 01:54:13 -0400
parents 0a563fd2f22e
children 41929aa1e7f3
comparison
equal deleted inserted replaced
9:0a563fd2f22e 10:d82339e37e8e
1 <tool id="rna_star" name="RNA STAR" version="2.6.0b-2" profile="17.01"> 1 <tool id="rna_star" name="RNA STAR" version="@VERSION@" profile="17.01">
2 <description>Gapped-read mapper for RNA-seq data</description> 2 <description>Gapped-read mapper for RNA-seq data</description>
3 <macros> 3 <macros>
4 <import>macros.xml</import> 4 <import>macros.xml</import>
5 </macros> 5 </macros>
6 <expand macro="requirements"/> 6 <expand macro="requirements"/>
7 7 <expand macro="stdio" />
8 <stdio>
9 <regex match="FATAL error" source="both" level="fatal"/>
10 <regex match="EXITING: FATAL INPUT ERROR:" source="both" level="fatal"/>
11 <regex match="EXITING: fatal error trying to allocate genome arrays, exception thrown: std::bad_alloc" source="both" level="fatal"/>
12 <regex match="\[sam_read1\] missing header\? Abort!" source="both" level="fatal"/>
13 </stdio>
14 8
15 <!-- 9 <!--
16 important quote (https://groups.google.com/forum/#!topic/rna-star/q4zGzlPgwXY): 10 important quote (https://groups.google.com/forum/#!topic/rna-star/q4zGzlPgwXY):
17 Hi Gary, 11 Hi Gary,
18 12
21 15
22 Cheers 16 Cheers
23 Alex 17 Alex
24 --> 18 -->
25 <command><![CDATA[ 19 <command><![CDATA[
26 ## Create temporary index for custom reference 20 @TEMPINDEX@
27 #if str($refGenomeSource.geneSource) == 'history':
28 mkdir -p tempstargenomedir &&
29 STAR
30 --runMode genomeGenerate
31 --genomeDir 'tempstargenomedir'
32 --genomeFastaFiles '$refGenomeSource.genomeFastaFiles'
33 #if $refGenomeSource.sjdbGTFfile:
34 --sjdbGTFfile '$refGenomeSource.sjdbGTFfile'
35 --sjdbOverhang '$refGenomeSource.sjdbOverhang'
36 #end if
37 --runThreadN \${GALAXY_SLOTS:-4}
38 &&
39 #end if
40
41 STAR 21 STAR
42 --runThreadN \${GALAXY_SLOTS:-4} 22 @REFGENOMEHANDLING@
43 --genomeLoad NoSharedMemory
44 --genomeDir
45 #if str($refGenomeSource.geneSource) == 'history':
46 'tempstargenomedir'
47 #if $refGenomeSource.sjdbGTFfile:
48 --sjdbGTFfile '$refGenomeSource.sjdbGTFfile'
49 --sjdbOverhang '$refGenomeSource.sjdbOverhang'
50 #end if
51 #else
52 '${refGenomeSource.GTFconditional.genomeDir.fields.path}'
53 #end if
54 23
55 --readFilesIn 24 --readFilesIn
56 #if str($singlePaired.sPaired) == "paired_collection" 25 #if str($singlePaired.sPaired) == 'paired_collection':
57 '$singlePaired.input.forward' '$singlePaired.input.reverse' 26 '$singlePaired.input.forward' '$singlePaired.input.reverse'
58 27
59 #if $singlePaired.input.forward.is_of_type("fastq.gz", "fastqsanger.gz"): 28 #if $singlePaired.input.forward.is_of_type('fastq.gz', 'fastqsanger.gz'):
60 @FASTQ_GZ_OPTION@ 29 @FASTQ_GZ_OPTION@
61 #end if 30 #end if
62 #else 31 #else
63 '$singlePaired.input1' 32 '$singlePaired.input1'
64 #if str($singlePaired.sPaired) == "paired" 33 #if str($singlePaired.sPaired) == 'paired':
65 '$singlePaired.input2' 34 '$singlePaired.input2'
66 #end if 35 #end if
67 36
68 #if $singlePaired.input1.is_of_type("fastq.gz", "fastqsanger.gz"): 37 #if $singlePaired.input1.is_of_type('fastq.gz', 'fastqsanger.gz'):
69 @FASTQ_GZ_OPTION@ 38 @FASTQ_GZ_OPTION@
70 #end if 39 #end if
71 #end if 40 #end if
72 41
73 --outSAMtype BAM SortedByCoordinate 42 --outSAMtype BAM SortedByCoordinate
74 43
75 ## Handle difference between indices with/without annotations 44 ## Two pass mode
76 #if str($refGenomeSource.geneSource) == 'indexed': 45 --twopassMode ${twopass.twopassMode} ${twopass.twopass_read_subset}
77 #if str($refGenomeSource.GTFconditional.GTFselect) == 'without-gtf': 46 #for $sj_input in $twopass.sj_precalculated:
78 #if $refGenomeSource.GTFconditional.sjdbGTFfile: 47 '$sj_input'
79 --sjdbOverhang '$refGenomeSource.GTFconditional.sjdbOverhang' 48 #end for
80 --sjdbGTFfile '${refGenomeSource.GTFconditional.sjdbGTFfile}' 49 #if str($twopass.twopassMode) != 'None':
81 #if str($refGenomeSource.GTFconditional.sjdbGTFfile.ext) == 'gff3': 50 #if str($refGenomeSource.GTFconditional.GTFselect) == 'with-gtf':
82 --sjdbGTFtagExonParentTranscript Parent 51 #if not $refGenomeSource.GTFconditional.sjdbGTFfile:
83 #end if 52 ## case of cached index without built-in gene model,
53 ## when user does not supply the optional gtf, but
54 ## specifies the splice junction overhang
55 --sjdbOverhang $refGenomeSource.GTFconditional.sjdbOverhang
84 #end if 56 #end if
85 #end if 57 #end if
86 #end if 58 #end if
87 59
88 #if $quantMode: 60 --quantMode ${quantmode_output.quantMode}
89 --quantMode GeneCounts 61 #if 'TranscriptomeSAM' in str($quantmode_output.quantMode):
90 #end if 62 --quantTranscriptomeBan ${quantmode_output.quantTranscriptomeBan}
91 63 #end if
92 ## Output parameters 64
93 #if str( $output_params.output_select ) == "yes": 65 ## Output format parameters
94 --outSAMattributes $output_params.outSAMattributes 66
95 #if str( $params.settingsType ) != "star_fusion": 67 ## Read tags
96 --outSAMstrandField $output_params.outSAMstrandField 68 #set read_tags = str($oformat.outSAMattributes).split(',')
69 #if 'XS' in str($oformat.outSAMattributes):
70 ## STAR writes XS tag when --outSAMstrandField intronMotif is used
71 $read_tags.remove('XS')
72 --outSAMstrandField intronMotif
73 #end if
74 #if 'HI' in str($oformat.outSAMattributes):
75 --outSAMattrIHstart ${oformat.HI_offset}
76 #end if
77 #set $tag_names = ' '.join($read_tags)
78 --outSAMattributes $tag_names
79
80 ## Read FLAG
81 --outSAMprimaryFlag ${oformat.outSAMprimaryFlag}
82
83 ## Read MAPQ
84 --outSAMmapqUnique ${oformat.outSAMmapqUnique}
85
86 ## Output filter parameters
87
88 ## Basic Filters
89 #if str($filter.basic_filters) != 'None':
90 #set $filter_options = str($filter.basic_filters).split(',')
91 #else:
92 #set filter_options = []
93 #end if
94 #if 'exclude_unmapped' in $filter_options:
95 $filter_options.remove('exclude_unmapped')
96 --outSAMunmapped None
97 #else:
98 --outSAMunmapped Within
99 #end if
100 #if '--outFilterIntronMotifs RemoveNoncanonical' in $filter_options:
101 ## RemoveNoncanonical excludes a superset of the reads excluded
102 ## with RemoveNoncanonicalUnannotated
103 #if '--outFilterIntronMotifs RemoveNoncanonicalUnannotated' in $filter_options:
104 $filter_options.remove('--outFilterIntronMotifs RemoveNoncanonicalUnannotated')
97 #end if 105 #end if
98 --outFilterIntronMotifs $output_params.outFilterIntronMotifs 106 #end if
99 --outFilterIntronStrands $output_params.outFilterIntronStrands 107 #echo ' '.join($filter_options)
100 #if str( $output_params.output_params2.output_select2 ) == "yes": 108
101 --outSAMunmapped $output_params.output_params2.outSAMunmapped 109 ## Other Filters
102 --outSAMprimaryFlag $output_params.output_params2.outSAMprimaryFlag 110 #if str( $filter.output_params2.output_select2 ) == 'yes':
103 --outSAMmapqUnique "$output_params.output_params2.outSAMmapqUnique" 111 --outFilterType $filter.output_params2.outFilterType
104 --outFilterType $output_params.output_params2.outFilterType 112 --outFilterMultimapScoreRange $filter.output_params2.outFilterMultimapScoreRange
105 --outFilterMultimapScoreRange "$output_params.output_params2.outFilterMultimapScoreRange" 113 --outFilterMultimapNmax $filter.output_params2.outFilterMultimapNmax
106 --outFilterMultimapNmax "$output_params.output_params2.outFilterMultimapNmax" 114 --outFilterMismatchNmax $filter.output_params2.outFilterMismatchNmax
107 --outFilterMismatchNmax "$output_params.output_params2.outFilterMismatchNmax" 115 --outFilterMismatchNoverLmax $filter.output_params2.outFilterMismatchNoverLmax
108 --outFilterMismatchNoverLmax "$output_params.output_params2.outFilterMismatchNoverLmax" 116 --outFilterMismatchNoverReadLmax $filter.output_params2.outFilterMismatchNoverReadLmax
109 --outFilterMismatchNoverReadLmax "$output_params.output_params2.outFilterMismatchNoverReadLmax" 117 --outFilterScoreMin $filter.output_params2.outFilterScoreMin
110 --outFilterScoreMin "$output_params.output_params2.outFilterScoreMin" 118 --outFilterScoreMinOverLread $filter.output_params2.outFilterScoreMinOverLread
111 --outFilterScoreMinOverLread "$output_params.output_params2.outFilterScoreMinOverLread" 119 --outFilterMatchNmin $filter.output_params2.outFilterMatchNmin
112 --outFilterMatchNmin "$output_params.output_params2.outFilterMatchNmin" 120 --outFilterMatchNminOverLread $filter.output_params2.outFilterMatchNminOverLread
113 --outFilterMatchNminOverLread "$output_params.output_params2.outFilterMatchNminOverLread" 121 --outSAMmultNmax $filter.output_params2.outSAMmultNmax
114 --outSAMmultNmax "$output_params.output_params2.outSAMmultNmax" 122 --outSAMtlen $filter.output_params2.outSAMtlen
115 --outSAMtlen "$output_params.output_params2.outSAMtlen"
116 --outBAMsortingBinsN "$output_params.output_params2.outBAMsortingBinsN"
117 #end if
118 #end if 123 #end if
119 124
120 ## Other parameters 125 ## Other parameters
121 #if str( $params.settingsType ) == "star_fusion": 126 #if str( $algo.params.settingsType ) == 'star_fusion':
122 ## Preset parameters for STAR-Fusion 127 ## Preset parameters for STAR-Fusion
123 --outReadsUnmapped None
124 --chimSegmentMin 12 128 --chimSegmentMin 12
125 --chimJunctionOverhangMin 12 129 --chimJunctionOverhangMin 12
126 --alignSJDBoverhangMin 10 130 --alignSJDBoverhangMin 10
127 --alignMatesGapMax 200000 131 --alignMatesGapMax 100000
128 --alignIntronMax 200000 132 --alignIntronMax 100000
129 --twopassMode Basic
130 --twopass1readsN -1
131 --chimSegmentReadGapMax 3 133 --chimSegmentReadGapMax 3
132 --alignSJstitchMismatchNmax 5 -1 5 5 134 --alignSJstitchMismatchNmax 5 -1 5 5
133 --outSAMstrandField intronMotif 135 --peOverlapNbasesMin 12
134 136 --peOverlapMMp 0.1
135 #elif str( $params.settingsType ) == "full": 137 --chimMultimapScoreRange 10
138 --chimMultimapNmax 10
139 --chimNonchimScoreDropMin 10
140
141 #elif str( $algo.params.settingsType ) == 'full':
136 ## Extended parameter options 142 ## Extended parameter options
137 143
138 ## Seed parameter options 144 ## Seed parameter options
139 --seedSearchStartLmax "$params.seed.seedSearchStartLmax" 145 --seedSearchStartLmax ${algo.params.seed.seedSearchStartLmax}
140 --seedSearchStartLmaxOverLread "$params.seed.seedSearchStartLmaxOverLread" 146 --seedSearchStartLmaxOverLread ${algo.params.seed.seedSearchStartLmaxOverLread}
141 --seedSearchLmax "$params.seed.seedSearchLmax" 147 --seedSearchLmax ${algo.params.seed.seedSearchLmax}
142 --seedMultimapNmax "$params.seed.seedMultimapNmax" 148 --seedMultimapNmax ${algo.params.seed.seedMultimapNmax}
143 --seedPerReadNmax "$params.seed.seedPerReadNmax" 149 --seedPerReadNmax ${algo.params.seed.seedPerReadNmax}
144 --seedPerWindowNmax "$params.seed.seedPerWindowNmax" 150 --seedPerWindowNmax ${algo.params.seed.seedPerWindowNmax}
145 --seedNoneLociPerWindow "$params.seed.seedNoneLociPerWindow" 151 --seedNoneLociPerWindow ${algo.params.seed.seedNoneLociPerWindow}
146 152
147 ## Alignment parameter options 153 ## Alignment parameter options
148 --alignIntronMin "$params.align.alignIntronMin" 154 --alignIntronMin ${algo.params.align.alignIntronMin}
149 --alignIntronMax "$params.align.alignIntronMax" 155 --alignIntronMax ${algo.params.align.alignIntronMax}
150 --alignMatesGapMax "$params.align.alignMatesGapMax" 156 --alignMatesGapMax ${algo.params.align.alignMatesGapMax}
151 --alignSJoverhangMin "$params.align.alignSJoverhangMin" 157 --alignSJoverhangMin ${algo.params.align.alignSJoverhangMin}
152 --alignSJDBoverhangMin "$params.align.alignSJDBoverhangMin" 158 --alignSJDBoverhangMin ${algo.params.align.alignSJDBoverhangMin}
153 --alignSplicedMateMapLmin "$params.align.alignSplicedMateMapLmin" 159 --alignSplicedMateMapLmin ${algo.params.align.alignSplicedMateMapLmin}
154 --alignSplicedMateMapLminOverLmate "$params.align.alignSplicedMateMapLminOverLmate" 160 --alignSplicedMateMapLminOverLmate ${algo.params.align.alignSplicedMateMapLminOverLmate}
155 --alignWindowsPerReadNmax "$params.align.alignWindowsPerReadNmax" 161 --alignWindowsPerReadNmax ${algo.params.align.alignWindowsPerReadNmax}
156 --alignTranscriptsPerWindowNmax "$params.align.alignTranscriptsPerWindowNmax" 162 --alignTranscriptsPerWindowNmax ${algo.params.align.alignTranscriptsPerWindowNmax}
157 --alignTranscriptsPerReadNmax "$params.align.alignTranscriptsPerReadNmax" 163 --alignTranscriptsPerReadNmax ${algo.params.align.alignTranscriptsPerReadNmax}
158 --alignEndsType $params.align.alignEndsType 164 --alignEndsType ${algo.params.align.alignEndsType}
159 165 --peOverlapNbasesMin ${algo.params.align.peOverlapNbasesMin}
160 ## Two pass mode 166 --peOverlapMMp ${algo.params.align.peOverlapMMp}
161 --twopassMode "$params.twopass.twopassMode" 167 ## Chimeric alignment parameter options
162 #if str( $params.twopass.twopassMode ) == "Basic": 168 #if str($chimOutType):
163 --twopass1readsN "$params.twopass.twopass1readsN" 169 --chimSegmentMin ${algo.params.chim_settings.chimSegmentMin}
164 #if not $refGenomeSource.sjdbGTFfile: 170 --chimScoreMin ${algo.params.chim_settings.chimScoreMin}
165 --sjdbOverhang '$refGenomeSource.sjdbOverhang' 171 --chimScoreDropMax $algo.params.chim_settings.chimScoreDropMax
172 --chimScoreSeparation $algo.params.chim_settings.chimScoreSeparation
173 --chimScoreJunctionNonGTAG $algo.params.chim_settings.chimScoreJunctionNonGTAG
174 --chimSegmentReadGapMax $algo.params.chim_settings.chimSegmentReadGapMax
175 --chimFilter $algo.params.chim_settings.chimFilter
176 --chimJunctionOverhangMin $algo.params.chim_settings.chimJunctionOverhangMin
177 --chimMainSegmentMultNmax $algo.params.chim_settings.chimMainSegmentMultNmax
178 #if str($chimOutType) == 'Junctions':
179 --chimMultimapNmax $algo.params.chim_settings.chimMultimapNmax
180 #else:
181 --chimMultimapNmax 0
182 #end if
183 --chimMultimapScoreRange $algo.params.chim_settings.chimMultimapScoreRange
184 #end if
185
186 ## Limits
187 --limitOutSJoneRead $algo.params.limits.limitOutSJoneRead
188 --limitOutSJcollapsed $algo.params.limits.limitOutSJcollapsed
189 --limitSjdbInsertNsj $algo.params.limits.limitSjdbInsertNsj
190 #else:
191 ## Go with STAR's default algorithmic settings,
192 ## but we need to provide a reasonable default
193 ## (taken from STAR-Fusion)
194 ## for --chimSegmentMin in case the user enabled chimeric
195 ## alignments (the STAR default is 0, which disables chimeric
196 ## alignments). For consistency, also set
197 ## --chimMultimapNmax to 1 when chimeric alignments are reported
198 ## in Junctions format only.
199 #if str($chimOutType):
200 --chimSegmentMin 12
201 #if str($chimOutType) == 'Junctions':
202 --chimMultimapNmax 1
166 #end if 203 #end if
167 #end if 204 #end if
168 205 #end if
169 ## Chimeric alignment parameter options 206
170 #if str( $params.chim.chim_select ) == "yes": 207 --outBAMsortingThreadN \${GALAXY_SLOTS:-4}
171 --chimOutType Junctions SeparateSAMold 208 --outBAMsortingBinsN $perf.outBAMsortingBinsN
172 --chimSegmentMin "$params.chim.chimSegmentMin" 209 --limitBAMsortRAM \$((\${GALAXY_MEMORY_MB:-0}*1000000))
173 --chimScoreMin "$params.chim.chimScoreMin" 210
174 --chimScoreDropMax "$params.chim.chimScoreDropMax" 211 ## Handle chimeric options and output
175 --chimScoreSeparation "$params.chim.chimScoreSeparation" 212 #if str($chimOutType):
176 --chimScoreJunctionNonGTAG "$params.chim.chimScoreJunctionNonGTAG" 213 --chimOutType $chimOutType
177 --chimJunctionOverhangMin "$params.chim.chimJunctionOverhangMin" 214 #if 'Junctions' in str($chimOutType):
178 --chimMainSegmentMultNmax "$params.chim.chimMainSegmentMultNmax" 215 --chimOutJunctionFormat 1
179 --chimMultimapNmax "$params.chim.chimMultimapNmax"
180 --chimMultimapScoreRange "$params.chim.chimMultimapScoreRange"
181 #end if 216 #end if
182 217 #end if
183 ## Limits
184 --limitBAMsortRAM "$params.limits.limitBAMsortRAM"
185 --limitOutSJoneRead "$params.limits.limitOutSJoneRead"
186 --limitOutSJcollapsed "$params.limits.limitOutSJcollapsed"
187 --limitSjdbInsertNsj "$params.limits.limitSjdbInsertNsj"
188
189 #end if
190
191 ## Convert chimeric reads.
192 #if str($params.settingsType) == "full" and str($params.chim.chim_select) == "yes" and int($params.chim.chimSegmentMin) > 0:
193 && 218 &&
194 samtools sort -@ \${GALAXY_SLOTS:-4} -o ChimericSorted.bam -O BAM Chimeric.out.sam 219 ## recompress BAM output for smaller file size
195 #end if 220 samtools view -b -o '$mapped_reads' Aligned.sortedByCoord.out.bam
221 #if 'TranscriptomeSAM' in str($quantmode_output.quantMode):
222 ## same recompression for optional transcriptome BM
223 &&
224 samtools view -b -o '$transcriptome_mapped_reads' Aligned.toTranscriptome.out.bam
225 #end if
196 ]]></command> 226 ]]></command>
197 227
198 <inputs> 228 <inputs>
199 <!-- FASTQ input(s) and options specifically for paired-end data. --> 229 <!-- FASTQ input(s) and options specifically for paired-end data. -->
200 <conditional name="singlePaired"> 230 <conditional name="singlePaired">
214 <param format="fastq,fasta,fastq.gz,fastqsanger.gz" name="input" type="data_collection" collection_type="paired" label="RNA-Seq FASTQ/FASTA paired reads"/> 244 <param format="fastq,fasta,fastq.gz,fastqsanger.gz" name="input" type="data_collection" collection_type="paired" label="RNA-Seq FASTQ/FASTA paired reads"/>
215 </when> 245 </when>
216 </conditional> 246 </conditional>
217 247
218 <!-- Genome source. --> 248 <!-- Genome source. -->
219 <conditional name="refGenomeSource"> 249 <expand macro="refgenomehandling" />
220 <param name="geneSource" type="select" label="Custom or built-in reference genome" help="Built-ins were indexed using default options"> 250
221 <option value="indexed" selected="True">Use a built-in index</option> 251 <conditional name="twopass">
222 <option value="history">Use reference genome from history and create temporary index</option> 252 <param argument="--twopassMode" type="select"
253 label="Use 2-pass mapping for more sensitive novel splice junction discovery"
254 help="For a study with multiple samples, multisample 2-pass mapping is the most sensitive approach. It involves two separate runs of STAR for each sample, where, in the second run of each sample, the splice junctions found in any sample in the first runs are treated as additional known junctions. If you plan to use the mapping results as input for STAR-Fusion it is recommended that you use at least single-sample 2-pass mapping of all reads.">
255 <option value="None">No</option>
256 <option value="Basic">Yes, perform single-sample 2-pass mapping of all reads</option>
257 <option value="Basic --twopass1readsN">Yes, but base novel splice junction detection in the first pass on a subset of all reads (faster, but less sensitive than single-sample 2-pass mode)</option>
258 <option value="None --sjdbFileChrStartEnd">Yes, I want to use multi-sample 2-pass mapping and I have obtained splice junctions datasets of all samples through previous 1-pass runs of STAR.</option>
223 </param> 259 </param>
224 <when value="indexed"> 260 <when value="None">
225 <conditional name="GTFconditional"> 261 <param name="twopass_read_subset" type="hidden" value="" />
226 <param name="GTFselect" type="select" label="Reference genome with or without an annotation" help="Must the index have been created WITH a GTF file (if not you can specify one afterward)."> 262 <param name="sj_precalculated" type="hidden" value="" />
227 <option value="without-gtf">use genome reference without builtin gene-model</option>
228 <option value="with-gtf">use genome reference with builtin gene-model</option>
229 </param>
230 <when value="with-gtf">
231 <param name="genomeDir" argument="--genomeDir" type="select" label="Select reference genome" help="If your genome of interest is not listed, contact the Galaxy team">
232 <options from_data_table="rnastar_index2">
233 <filter type="static_value" column="4" value="1"/>
234 <filter type="sort_by" column="2" />
235 <validator type="no_options" message="No indexes are available for the selected input dataset"/>
236 </options>
237 </param>
238 </when>
239 <when value="without-gtf">
240 <param argument="--genomeDir" type="select" label="Select reference genome" help="If your genome of interest is not listed, contact the Galaxy team">
241 <options from_data_table="rnastar_index2">
242 <filter type="static_value" column="4" value="0"/>
243 <filter type="sort_by" column="2" />
244 <validator type="no_options" message="No indexes are available for the selected input dataset"/>
245 </options>
246 </param>
247
248 <expand macro="@SJDBOPTIONS@" />
249 </when>
250 </conditional>
251 </when> 263 </when>
252 <when value="history"> 264 <when value="Basic">
253 <param argument="--genomeFastaFiles" type="data" format="fasta" label="Select a reference genome" /> 265 <param name="twopass_read_subset" type="hidden" value="" />
254 <expand macro="@SJDBOPTIONS@" /> 266 <param name="sj_precalculated" type="hidden" value="" />
267 </when>
268 <when value="Basic --twopass1readsN">
269 <param name="sj_precalculated" type="hidden" value="" />
270 <param argument="--twopass1readsN" name="twopass_read_subset" type="integer" min="1" value="50000" label="Number of reads to map in the first pass"/>
271 </when>
272 <when value="None --sjdbFileChrStartEnd">
273 <param name="twopass_read_subset" type="hidden" value="" />
274 <param name="sj_precalculated" type="data" multiple="true" format="interval"
275 label="Pregenerated splice junctions datasets of your samples" />
255 </when> 276 </when>
256 </conditional> 277 </conditional>
257 <param argument="--quantMode" type="boolean" label="Count number of reads per gene" help="column 1: gene ID, column 2: counts for unstranded RNA-seq, column 3: counts for the 1st read strand aligned with RNA , column 4: counts for the 2nd read strand aligned with RNA. This requires either (A) an index that was built with an annotation (GTF or GFF3 file) or (B) having specified an annotation (GTF or GFF3 file above)."/> 278 <conditional name="quantmode_output">
258 279 <param argument="--quantMode" type="select"
259 <!-- Output parameter settings. --> 280 label="Per gene/transcript output"
260 <conditional name="output_params"> 281 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!">
261 <param name="output_select" type="select" label="Would you like to set output parameters (formatting and filtering)?"> 282 <option value="-">No per gene or transcript output</option>
262 <option value="no" selected="true">No</option> 283 <option value="GeneCounts">Per gene read counts (GeneCounts)</option>
263 <option value="yes">Yes</option> 284 <option value="TranscriptomeSAM">Transcript-based BAM output (TranscriptomeSAM)</option>
285 <option value="TranscriptomeSAM GeneCounts">Both per gene read counts and transcript-based BAM output (TranscriptomeSAM GeneCounts)</option>
264 </param> 286 </param>
265 <when value="yes"> 287 <when value="-" />
266 <param argument="--outSAMattributes" type="select" label="Extra SAM attributes to include" help="See &quot;Extra SAM attributes&quot; below"> 288 <when value="GeneCounts" />
267 <option value="Standard" selected="true">Standard</option> 289 <when value="TranscriptomeSAM">
268 <option value="All">All</option> 290 <param argument="--quantTranscriptomeBan" type="boolean" truevalue="IndelSoftclipSingleend" falsevalue="Singleend"
269 <option value="None">None</option> 291 label="Exclude alignments with indels or soft clipping from the transcriptome BAM output?"
270 </param> 292 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." />
271 <param argument="--outSAMstrandField" type="select" label="Include strand field flag XS" help="For Cufflinks compatibility with unstranded RNA-seq data, this option is required"> 293 </when>
272 <option value="None" selected="true">No</option> 294 <when value="TranscriptomeSAM GeneCounts">
273 <option value="intronMotif">Yes -- and reads with inconsistent and/or non-canonical introns are filtered out</option> 295 <param argument="--quantTranscriptomeBan" type="boolean" truevalue="IndelSoftclipSingleend" falsevalue="Singleend"
274 </param> 296 label="Exclude alignments with indels or soft clipping from the transcriptome BAM output?"
275 <param argument="--outFilterIntronMotifs" type="select" label="Filter alignments containing non-canonical junctions" help="For Cufflinks compatibility, removing alignments with non-canonical junctions is recommended"> 297 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." />
276 <option value="None" selected="true">No</option>
277 <option value="RemoveNoncanonical">Remove alignments with non-canonical junctions</option>
278 <option value="RemoveNoncanonicalUnannotated">Remove alignments with unannotated non-canonical junctions</option>
279 </param>
280 <param argument="--outFilterIntronStrands" type="select" label="Filter alignments containing junctions with inconsistent strands">
281 <option value="RemoveInconsistentStrands" selected="true">Remove alignments that have junctions with inconsistent strands</option>
282 <option value="None">No filtering</option>
283 </param>
284
285 <!-- Additional output parameter settings. -->
286 <conditional name="output_params2">
287 <param name="output_select2" type="select" label="Would you like to set additional output parameters (formatting and filtering)?">
288 <option value="no" selected="true">No</option>
289 <option value="yes">Yes</option>
290 </param>
291 <when value="yes">
292 <param argument="--outSAMunmapped" type="boolean" truevalue="Within" falsevalue="None" checked="false" label="Would you like unmapped reads included in the SAM?"/>
293 <param argument="--outSAMprimaryFlag" type="boolean" truevalue="AllBestScore" falsevalue="OneBestScore" checked="false" label="Would you like all alignments with the best score labeled primary?"/>
294 <param argument="--outSAMmapqUnique" type="integer" value="255" min="0" max="255" label="MAPQ value for unique mappers"/>
295 <param argument="--outFilterType" type="boolean" truevalue="BySJout" falsevalue="Normal" checked="false" label="Would you like to keep only reads that contain junctions that passed filtering?"/>
296 <param argument="--outFilterMultimapScoreRange" type="integer" value="1" min="0" label="Score range below the maximum score for multimapping alignments"/>
297 <param argument="--outFilterMultimapNmax" type="integer" value="10" min="1" label="Maximum number of alignments to output a read's alignment results, plus 1" help="Reads with at least this number of alignments will have no alignments output"/>
298 <param argument="--outFilterMismatchNmax" type="integer" value="10" min="0" label="Maximum number of mismatches to output an alignment, plus 1" help="Alignments with at least this number of mismatches will not be output"/>
299 <param argument="--outFilterMismatchNoverLmax" type="float" value="0.3" min="0" max="1" label="Maximum ratio of mismatches to mapped length" help="Alignments with a mismatch ratio of at least this value will not be output"/>
300 <param argument="--outFilterMismatchNoverReadLmax" type="float" value="1" min="0" max="1" label="Maximum ratio of mismatches to read length" help="Alignments with a mismatch ratio of at least this value will not be output"/>
301 <param argument="--outFilterScoreMin" type="integer" value="0" min="0" label="Minimum alignment score" help="Alignments must have scores higher than this value to be output"/>
302 <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"/>
303 <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"/>
304 <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"/>
305 <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" />
306 <param argument="--outSAMtlen" type="select" label="Calculation method for TLEN">
307 <option value="1" selected="true">leftmost base of the (+)strand mate to rightmost base of the (-)mate. (+)sign for the (+)strand mate</option>
308 <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>
309 </param>
310 <param argument="--outBAMsortingBinsN" type="integer" value="50" min="1" label="Number of genome bins for coordinate-sorting" help="Higher values result in lower RAM requirements during the sorting step. The default value is 50."/>
311 </when>
312 <when value="no"/>
313 </conditional>
314 </when>
315 <when value="no"/>
316 </conditional>
317
318 <!-- Other parameter settings. -->
319 <conditional name="params">
320 <param name="settingsType" type="select" label="Other parameters (seed, alignment, limits and chimeric alignment)">
321 <option value="default" selected="true">Use Defaults</option>
322 <option value="star_fusion">Use parameters suggested for STAR-Fusion</option>
323 <option value="full">Extended parameter list</option>
324 </param>
325 <when value="default"/>
326 <when value="star_fusion"/><!-- Set STAR-fusion parameters automatically -->
327
328 <when value="full">
329 <section name="seed" title="Seed parameters" expanded="False">
330 <param argument="--seedSearchStartLmax" type="integer" min="1" value="50" label="Search start point through the read"/>
331 <param argument="--seedSearchStartLmaxOverLread" type="float" min="0" value="1.0" label="Search start point through the read, normalized to read length"/>
332 <param argument="--seedSearchLmax" type="integer" min="0" value="0" label="Maximum length of seeds" help="Default of 0 indicates no maximum length"/>
333 <param argument="--seedMultimapNmax" type="integer" min="1" value="10000" label="Maximum number of mappings to use a piece in stitching"/>
334 <param argument="--seedPerReadNmax" type="integer" min="1" value="1000" label="Maximum number of seeds per read"/>
335 <param argument="--seedPerWindowNmax" type="integer" min="1" value="50" label="Maximum number of seeds per window"/>
336 <param argument="--seedNoneLociPerWindow" type="integer" min="1" value="10" label="Maximum number of one seed loci per window"/>
337 </section>
338
339 <section name="align" title="Alignment parameters" expanded="False">
340 <param argument="--alignIntronMin" name="alignIntronMin" type="integer" min="0" value="21" label="Minimum intron size"/>
341 <param argument="--alignIntronMax" type="integer" min="0" value="0" label="Maximum intron size"/>
342 <param argument="--alignMatesGapMax" type="integer" min="0" value="0" label="Maximum gap between two mates"/>
343 <param argument="--alignSJoverhangMin" type="integer" min="1" value="5" label="Minimum overhang for spliced alignments"/>
344 <param argument="--alignSJDBoverhangMin" type="integer" min="1" value="3" label="Minimum overhang for annotated spliced alignments"/>
345 <param argument="--alignSplicedMateMapLmin" type="integer" min="0" value="0" label="Minimum mapped length for a read mate that is spliced"/>
346 <param argument="--alignSplicedMateMapLminOverLmate" type="float" min="0" value="0.66" label="Minimum mapped length for a read mate that is spliced, normalized to mate length"/>
347 <param argument="--alignWindowsPerReadNmax" type="integer" min="1" value="10000" label="Maximum number of windows per read"/>
348 <param argument="--alignTranscriptsPerWindowNmax" type="integer" min="1" value="100" label="Maximum number of transcripts per window"/>
349 <param argument="--alignTranscriptsPerReadNmax" type="integer" min="1" value="10000" label="Maximum number of different alignments per read to consider"/>
350 <param argument="--alignEndsType" type="boolean" truevalue="EndToEnd" falsevalue="Local" checked="false" label="Use end-to-end read alignments, with no soft-clipping?"/>
351 </section>
352
353 <section name="twopass" title="Two pass mode" expanded="False">
354 <param argument="--twopassMode" type="boolean" truevalue="Basic" falsevalue="None" checked="false" label="Use two pass mode to better map reads to unknown splice junctions"/>
355 <param argument="--twopass1readsN" type="integer" min="-1" value="-1" label="Number of reads to map in the first pass (-1: all)"/>
356 </section>
357
358 <section name="limits" title="Limits" expanded="False">
359 <param argument="--limitBAMsortRAM" type="integer" min="0" value="0" label="Maximum available RAM (in bytes) for sorting" help="If 0, this will be set to the genome index size. This is typically only changed in cases where an error is produced." />
360 <param argument="--limitOutSJoneRead" type="integer" min="1" value="1000" label="Maximum number of junctions for one read (including all multimappers)" />
361 <param argument="--limitOutSJcollapsed" type="integer" min="1" value="1000000" label="Maximum number of collapsed junctions" />
362 <param argument="--limitSjdbInsertNsj" type="integer" min="0" value="1000000" label="Maximum number of inserts to be inserted into the genome on the fly." />
363 </section>
364
365 <conditional name="chim">
366 <param name="chim_select" type="select" label="Would you like to set chimeric alignment parameters?">
367 <option value="no" selected="true">No</option>
368 <option value="yes">Yes</option>
369 </param>
370 <when value="yes">
371 <param argument="--chimSegmentMin" type="integer" min="0" value="0" label="Minimum length of chimeric segment" help="For small numbers this will cause large number of chimeric alignments. A value of 12 is commonly used. Default of 0 means no chimeric output">
372 <validator type="in_range" min="1" message="To get chimeric reads this value needs to be larger than 0"/>
373 </param>
374 <param argument="--chimScoreMin" type="integer" min="0" value="0" label="Minimum total (summed) score of chimeric segments"/>
375 <param argument="--chimScoreDropMax" type="integer" min="0" value="20" label="Maximum difference of chimeric score from read length"/>
376 <param argument="--chimScoreSeparation" type="integer" min="0" value="10" label="Minimum difference between the best chimeric score and the next one"/>
377 <param argument="--chimScoreJunctionNonGTAG" type="integer" value="-1" label="Penalty for a non-GT/AG chimeric junction"/>
378 <param argument="--chimJunctionOverhangMin" type="integer" min="0" value="20" label="Minimum overhang for a chimeric junction"/>
379 <param argument="--chimMainSegmentMultNmax" type="integer" min="1" value="10" label="Maximum number of multi-alignments for the main chimeric segment." help="A value of 1 prohibits multimapping main segments"/>
380 <param argument="--chimMultimapNmax" type="integer" min="0" value="0" label="Maximum number of chimeric multi-alignments" help="A value of 0 (the default) only considers unique alignments" />
381 <param argument="--chimMultimapScoreRange" type="integer" min="0" value="1" label="Score range for multi-mapping chimeras" help="The threshold below the best chimeric score that a multimapping chimera must have to be output. This is ignored unless --chimMultimapNmax is above 1" />
382 </when>
383 <when value="no"/>
384 </conditional>
385 </when> 298 </when>
386 </conditional> 299 </conditional>
300 <param argument="--chimOutType" type="select"
301 label="Report chimeric alignments?"
302 help="Choose if and how chimeric alignments should be reported. STAR-Fusion users should select the 'Junctions' option and use the resulting tabular dataset as input to STAR-Fusion. Everyone else: note that selecting 'WithinBAM' or 'WithinBAM Junctions' disables the --chimMultimapNmax setting in the algorithmic parameters section below (the tool will only consider uniquely mapped reads in the search for chimeric alignments). If you disable the reporting of chimeric alignments here, then all chimeric alignment settings in the algorithmic parameters section below will be ignored.">
303 <option value="">Don't report chimeric alignments</option>
304 <option value="Junctions">As separate tabular "Junctions" output (Junctions)</option>
305 <option value="WithinBAM">Within the BAM output (together with regular alignments; WithinBAM)</option>
306 <option value="WithinBAM Junctions">In both forms (WithinBAM Junctions)</option>
307 </param>
308
309 <section name="oformat" title="BAM output format specification" expanded="true">
310 <param argument="--outSAMattributes" type="select" display="checkboxes" multiple="true" optional="true"
311 label="Read alignment tags to include in the BAM output"
312 help="Note on using the XS tag: If the XS tag is used, STAR will filter out alignments with undefined strand (i.e., those containing only non-canonical unannotated junctions). Using this tag is recommended if you plan to use the STAR results with STAR-Fusion. In addition, it is required for compatibility
313 with Cufflinks if your sequences come from an unstranded library preparation.">
314 <option value="NH" selected="true">NH (number of reported alignments/hits for the read)</option>
315 <option value="HI" selected="true">HI (query hit index)</option>
316 <option value="AS" selected="true">AS (local alignment score)</option>
317 <option value="nM" selected="true">nM (number of mismatches per (paired) alignment)</option>
318 <option value="XS">XS (strand flag, see parameter help below) </option>
319 <option value="NM">NM (edit distance of the aligned read to the reference)</option>
320 <option value="MD">MD (string for mismatching positions)</option>
321 <option value="MC">MC (CIGAR string for mate/next segment)</option>
322 <option value="jM">jM (intron motifs for all junctions)</option>
323 <option value="jI">jI (1-based start and end of introns for all junctions)</option>
324 <option value="ch" selected="true">ch (used to indicate chimeric alignments)</option>
325 </param>
326 <param argument="--outSAMattrIHstart" name="HI_offset" type="select" display="radio"
327 label="HI tag values should be">
328 <option value="1" selected="true">one-based</option>
329 <option value="0">zero-based</option>
330 </param>
331 <!-- Using - -outSAMprimaryFlag AllBestScore would cause a
332 violation of the SAM/BAM spec, which says:
333 "For each read/contig in a SAM file, it is required that one and
334 only one line associated with the read satisfies
335 ‘FLAG & 0x900 == 0’.
336 This line is called the primary line of the read."
337
338 Thus, this parameter has been removed from the tool interface:
339 <param argument="- -outSAMprimaryFlag" type="boolean"
340 truevalue="AllBestScore" falsevalue="OneBestScore" checked="false"
341 label="Would you like all alignments with the best score labeled
342 primary?"/> -->
343 <param name="outSAMprimaryFlag" type="hidden" value="OneBestScore" />
344 <param argument="--outSAMmapqUnique" type="integer" value="60" min="30" max="255"
345 label="MAPQ value for unique mappers"
346 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
347 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 Cufflinks." />
348 </section>
349 <section name="filter" title="Output filter criteria" expanded="true">
350 <param name="basic_filters" type="select" display="checkboxes" multiple="true" optional="true"
351 label="Exclude the following records from the BAM output">
352 <option value="exclude_unmapped">Unmapped reads</option>
353 <option value="--outFilterIntronStrands RemoveInconsistentStrands">Alignments that have junctions with inconsistent strands</option>
354 <option value="--outFilterIntronMotifs RemoveNoncanonicalUnannotated">Alignments across unannotated non-canonical junctions</option>
355 <option value="--outFilterIntronMotifs RemoveNoncanonical">All alignments across non-canonical junctions (recommended for compatibility with Cufflinks)</option>
356 </param>
357 <!-- Additional output parameter settings. -->
358 <conditional name="output_params2">
359 <param name="output_select2" type="select" label="Would you like to set additional output filters?">
360 <option value="no" selected="true">No</option>
361 <option value="yes">Yes</option>
362 </param>
363 <when value="yes">
364 <param argument="--outFilterType" type="boolean" truevalue="BySJout" falsevalue="Normal" checked="false" label="Would you like to keep only reads that contain junctions that passed filtering?"/>
365 <param argument="--outFilterMultimapScoreRange" type="integer" value="1" min="0" label="Score range below the maximum score for multimapping alignments"/>
366 <param argument="--outFilterMultimapNmax" type="integer" value="10" min="1" label="Maximum number of alignments to output a read's alignment results, plus 1" help="Reads with at least this number of alignments will have no alignments output"/>
367 <param argument="--outFilterMismatchNmax" type="integer" value="10" min="0" label="Maximum number of mismatches to output an alignment, plus 1" help="Alignments with at least this number of mismatches will not be output"/>
368 <param argument="--outFilterMismatchNoverLmax" type="float" value="0.3" min="0" max="1" label="Maximum ratio of mismatches to mapped length" help="Alignments with a mismatch ratio of at least this value will not be output"/>
369 <param argument="--outFilterMismatchNoverReadLmax" type="float" value="1" min="0" max="1" label="Maximum ratio of mismatches to read length" help="Alignments with a mismatch ratio of at least this value will not be output"/>
370 <param argument="--outFilterScoreMin" type="integer" value="0" min="0" label="Minimum alignment score" help="Alignments must have scores higher than this value to be output"/>
371 <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"/>
372 <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"/>
373 <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"/>
374 <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" />
375 <param argument="--outSAMtlen" type="select" label="Calculation method for TLEN">
376 <option value="1" selected="true">leftmost base of the (+)strand mate to rightmost base of the (-)mate. (+)sign for the (+)strand mate</option>
377 <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>
378 </param>
379 </when>
380 <when value="no"/>
381 </conditional>
382 </section>
383
384 <!-- Algorithmic settings. -->
385 <section name="algo" title="Algorithmic settings" expanded="true">
386 <conditional name="params">
387 <param name="settingsType" type="select" label="Configure seed, alignment and limits options">
388 <option value="default" selected="true">Use Defaults</option>
389 <option value="star_fusion">Use parameters suggested for STAR-Fusion</option>
390 <option value="full">Extended parameter list</option>
391 </param>
392 <when value="default"/>
393 <!-- Set STAR-fusion parameters in command section -->
394 <when value="star_fusion"/>
395
396 <when value="full">
397 <section name="seed" title="Seed parameters" expanded="false">
398 <param argument="--seedSearchStartLmax" type="integer" min="1" value="50" label="Search start point through the read"/>
399 <param argument="--seedSearchStartLmaxOverLread" type="float" min="0" value="1.0" label="Search start point through the read, normalized to read length"/>
400 <param argument="--seedSearchLmax" type="integer" min="0" value="0" label="Maximum length of seeds" help="Default of 0 indicates no maximum length"/>
401 <param argument="--seedMultimapNmax" type="integer" min="1" value="10000" label="Maximum number of mappings to use a piece in stitching"/>
402 <param argument="--seedPerReadNmax" type="integer" min="1" value="1000" label="Maximum number of seeds per read"/>
403 <param argument="--seedPerWindowNmax" type="integer" min="1" value="50" label="Maximum number of seeds per window"/>
404 <param argument="--seedNoneLociPerWindow" type="integer" min="1" value="10" label="Maximum number of one seed loci per window"/>
405 </section>
406
407 <section name="align" title="Alignment parameters" expanded="false">
408 <param argument="--alignIntronMin" name="alignIntronMin" type="integer" min="0" value="21" label="Minimum intron size"/>
409 <param argument="--alignIntronMax" type="integer" min="0" value="0" label="Maximum intron size"/>
410 <param argument="--alignMatesGapMax" type="integer" min="0" value="0" label="Maximum gap between two mates"/>
411 <param argument="--alignSJoverhangMin" type="integer" min="1" value="5" label="Minimum overhang for spliced alignments"/>
412 <param argument="--alignSJDBoverhangMin" type="integer" min="1" value="3" label="Minimum overhang for annotated spliced alignments"/>
413 <param argument="--alignSplicedMateMapLmin" type="integer" min="0" value="0" label="Minimum mapped length for a read mate that is spliced"/>
414 <param argument="--alignSplicedMateMapLminOverLmate" type="float" min="0" value="0.66" label="Minimum mapped length for a read mate that is spliced, normalized to mate length"/>
415 <param argument="--alignWindowsPerReadNmax" type="integer" min="1" value="10000" label="Maximum number of windows per read"/>
416 <param argument="--alignTranscriptsPerWindowNmax" type="integer" min="1" value="100" label="Maximum number of transcripts per window"/>
417 <param argument="--alignTranscriptsPerReadNmax" type="integer" min="1" value="10000" label="Maximum number of different alignments per read to consider"/>
418 <param argument="--alignEndsType" type="boolean" truevalue="EndToEnd" falsevalue="Local" checked="false" label="Use end-to-end read alignments, with no soft-clipping?"/>
419 <param argument="--peOverlapNbasesMin" type="integer" min="0" value="0"
420 label="minimum number of overlap bases to trigger mates merging and realignment" />
421 <param argument="--peOverlapMMp" type="float" min="0" max="1" value="0.01"
422 label="maximum proportion of mismatched bases in the overlap area" />
423 </section>
424 <section name="chim_settings" title="Chimeric alignment parameters" expanded="false">
425 <param argument="--chimSegmentMin" type="integer" min="1" value="12"
426 label="Minimum length of chimeric segment"
427 help="For small numbers this will cause large number of chimeric alignments. A value of 12 is commonly used." />
428 <param argument="--chimScoreMin" type="integer" min="0" value="0"
429 label="Minimum total (summed) score of chimeric segments"/>
430 <param argument="--chimScoreDropMax" type="integer" min="0" value="20"
431 label="Maximum difference of chimeric score from read length"/>
432 <param argument="--chimScoreSeparation" type="integer" min="0" value="10"
433 label="Minimum difference between the best chimeric score and the next one"/>
434 <param argument="--chimScoreJunctionNonGTAG" type="integer" value="-1"
435 label="Penalty for a non-GT/AG chimeric junction"/>
436 <param argument="--chimJunctionOverhangMin" type="integer" min="0" value="20"
437 label="Minimum overhang for a chimeric junction"/>
438 <param argument="--chimSegmentReadGapMax" type="integer" min="0" value="0"
439 label="Maximum gap in the read sequence between chimeric segments" />
440 <param argument="--chimFilter" type="boolean" truevalue="banGenomicN" falsevalue="None" checked="true"
441 label="Discard chimeric alignments with Ns in the genome sequence around the chimeric junction" />
442 <param argument="--chimMainSegmentMultNmax" type="integer" min="1" value="10"
443 label="Maximum number of multi-alignments for the main chimeric segment."
444 help="A value of 1 prohibits multimapping main segments"/>
445 <param argument="--chimMultimapNmax" type="integer" min="1" value="1"
446 label="Maximum number of chimeric multi-alignments"
447 help="The default value of 1 only considers unique alignments. If you chose to report chimeric alignments alongside regular ones in the BAM output, this setting is ignored and only uniquely mapping chimeric reads get reported. " />
448 <param argument="--chimMultimapScoreRange" type="integer" min="0" value="1"
449 label="Score range for multi-mapping chimeras"
450 help="The threshold below the best chimeric score that a multimapping chimera must have to be output. This is ignored unless --chimMultimapNmax is above 1" />
451 </section>
452 <section name="limits" title="Limits" expanded="false">
453 <param argument="--limitOutSJoneRead" type="integer" min="1" value="1000" label="Maximum number of junctions for one read (including all multimappers)" />
454 <param argument="--limitOutSJcollapsed" type="integer" min="1" value="1000000" label="Maximum number of collapsed junctions" />
455 <param argument="--limitSjdbInsertNsj" type="integer" min="0" value="1000000" label="Maximum number of inserts to be inserted into the genome on the fly." />
456 </section>
457 </when>
458 </conditional>
459 </section>
460 <section name="perf" title="Performance tweaks / Troubleshooting" expanded="false">
461 <param argument="--outBAMsortingBinsN" type="integer" value="50" min="1" label="Number of genome bins for coordinate-sorting" help="Higher values result in lower RAM requirements during the sorting step. The default value is 50. Tweak this if you are facing memory-related errors." />
462 </section>
387 </inputs> 463 </inputs>
388 464
389 <outputs> 465 <outputs>
390 <data format="txt" name="output_log" label="${tool.name} on ${on_string}: log" from_work_dir="Log.final.out"> 466 <data format="txt" name="output_log" label="${tool.name} on ${on_string}: log" from_work_dir="Log.final.out">
391 <expand macro="dbKeyActions" /> 467 <expand macro="dbKeyActions" />
392 </data> 468 </data>
469
393 <data format="interval" name="chimeric_junctions" label="${tool.name} on ${on_string}: chimeric junctions" from_work_dir="Chimeric.out.junction"> 470 <data format="interval" name="chimeric_junctions" label="${tool.name} on ${on_string}: chimeric junctions" from_work_dir="Chimeric.out.junction">
394 <filter>params['settingsType'] == "star_fusion" or ( params['settingsType'] == "full" and params['chim']['chim_select'] == "yes" and params['chim']['chimSegmentMin'] > 0 )</filter> 471 <filter>('Junctions' in chimOutType)</filter>
395 <expand macro="dbKeyActions" />
396 </data>
397
398 <data format="bam" name="chimeric_reads" label="${tool.name} on ${on_string}: chimeric.bam" from_work_dir="ChimericSorted.bam">
399 <filter>params['settingsType'] == "full" and params['chim']['chim_select'] == "yes" and params['chim']['chimSegmentMin'] > 0</filter>
400 <expand macro="dbKeyActions" /> 472 <expand macro="dbKeyActions" />
401 </data> 473 </data>
402 474
403 <data format="interval" name="splice_junctions" label="${tool.name} on ${on_string}: splice junctions.bed" from_work_dir="SJ.out.tab"> 475 <data format="interval" name="splice_junctions" label="${tool.name} on ${on_string}: splice junctions.bed" from_work_dir="SJ.out.tab">
404 <expand macro="dbKeyActions" /> 476 <expand macro="dbKeyActions" />
405 </data> 477 </data>
406 478
407 <data name="mapped_reads" format="bam" label="${tool.name} on ${on_string}: mapped.bam" from_work_dir="Aligned.sortedByCoord.out.bam"> 479 <data name="mapped_reads" format="bam" label="${tool.name} on ${on_string}: mapped.bam">
408 <expand macro="dbKeyActions" /> 480 <expand macro="dbKeyActions" />
409 </data> 481 </data>
410 482
483 <data name="transcriptome_mapped_reads" format="unsorted.bam" label="${tool.name} on ${on_string}: transcriptome-mapped.bam" >
484 <filter>'TranscriptomeSAM' in quantmode_output['quantMode']</filter>
485 <expand macro="dbKeyActions" />
486 </data>
487
411 <data name="reads_per_gene" format="tabular" label="${tool.name} on ${on_string}: reads per gene" from_work_dir="ReadsPerGene.out.tab"> 488 <data name="reads_per_gene" format="tabular" label="${tool.name} on ${on_string}: reads per gene" from_work_dir="ReadsPerGene.out.tab">
412 <filter>quantMode is True</filter> 489 <filter>'GeneCounts' in quantmode_output['quantMode']</filter>
413 <expand macro="dbKeyActions" /> 490 <expand macro="dbKeyActions" />
414 </data> 491 </data>
415 </outputs> 492 </outputs>
416 493
417 <tests> 494 <tests>
418 <test> 495 <test expect_num_outputs="3">
419 <param name="input1" value="tophat_in2.fastqsanger" ftype="fastqsanger" /> 496 <conditional name="singlePaired">
420 <param name="geneSource" value="history" /> 497 <param name="sPaired" value="single" />
421 <param name="genomeFastaFiles" value="tophat_test.fa" /> 498 <param name="input1" value="tophat_in2.fastqsanger" ftype="fastqsanger" />
422 <param name="sPaired" value="single" /> 499 </conditional>
423 500 <conditional name="refGenomeSource">
424 <param name="output_select" value="yes" /> 501 <param name="geneSource" value="history" />
425 <param name="outSAMattributes" value="All" /> 502 <param name="genomeFastaFiles" value="tophat_test.fa" />
426 <param name="outSAMstrandField" value="intronMotif" /> 503 <param name="genomeSAindexNbases" value="5" />
427 <param name="settingsType" value="default" /> 504 </conditional>
428 505 <section name="oformat">
429 <output name="output_log" file="rnastar_test.log" compare="diff" lines_diff="12"/> 506 <param name="outSAMattributes" value="NH,HI,AS,nM,NM,MD,jM,jI,MC,ch" />
507 <param name="outSAMmapqUnique" value="255" />
508 </section>
509 <section name="algo">
510 <conditional name="params">
511 <param name="settingsType" value="default" />
512 </conditional>
513 </section>
514 <output name="output_log" file="rnastar_test.log" compare="re_match_multiline" />
430 <output name="splice_junctions" file="rnastar_test_splicejunctions.bed"/> 515 <output name="splice_junctions" file="rnastar_test_splicejunctions.bed"/>
431 <output name="mapped_reads" file="rnastar_test_mapped_reads.bam" compare="sim_size" delta="634" /> 516 <output name="mapped_reads" file="rnastar_test_mapped_reads.bam" compare="sim_size" delta="634" />
432 </test> 517 </test>
433 <test><!-- tests gtf file and GeneCounts mode --> 518 <!-- test with cached genome index -->
434 <param name="input1" value="tophat_in2.fastqsanger" ftype="fastqsanger" /> 519 <test expect_num_outputs="3">
435 <param name="geneSource" value="history" /> 520 <conditional name="singlePaired">
436 <param name="genomeFastaFiles" value="tophat_test.fa" /> 521 <param name="sPaired" value="single" />
437 522 <param name="input1" value="tophat_in2.fastqsanger" ftype="fastqsanger" />
438 <param name="sjdbOverhang" value="75"/> 523 </conditional>
439 <param name="sjdbGTFfile" value="test1.gtf" ftype="gtf"/> 524 <conditional name="refGenomeSource">
440 <param name="quantMode" value="True"/> 525 <param name="geneSource" value="indexed" />
441 526 <conditional name="GTFconditional">
442 <param name="sPaired" value="single" /> 527 <param name="GTFselect" value="with-gtf" />
443 <param name="output_select" value="yes" /> 528 <param name="genomeDir" value="000" />
444 <param name="outSAMattributes" value="All" /> 529 </conditional>
445 <param name="outSAMstrandField" value="intronMotif" /> 530 </conditional>
446 <param name="settingsType" value="default" /> 531 <section name="oformat">
447 532 <param name="outSAMattributes" value="NH,HI,AS,nM,NM,MD,jM,jI,MC,ch" />
448 <output name="output_log" file="rnastar_test.log" compare="diff" lines_diff="12"/> 533 <param name="outSAMmapqUnique" value="255" />
534 </section>
535 <section name="algo">
536 <conditional name="params">
537 <param name="settingsType" value="default" />
538 </conditional>
539 </section>
540 <output name="output_log" file="rnastar_test.log" compare="re_match_multiline" />
541 <output name="splice_junctions" file="rnastar_test_splicejunctions.bed"/>
542 <output name="mapped_reads" file="rnastar_test_mapped_reads.bam" compare="sim_size" delta="634" />
543 </test>
544 <!-- test gtf file and GeneCounts mode -->
545 <test expect_num_outputs="4">
546 <conditional name="singlePaired">
547 <param name="sPaired" value="single" />
548 <param name="input1" value="tophat_in2.fastqsanger" ftype="fastqsanger" />
549 </conditional>
550 <conditional name="refGenomeSource">
551 <param name="geneSource" value="history" />
552 <param name="genomeFastaFiles" value="tophat_test.fa" />
553 <param name="genomeSAindexNbases" value="5" />
554 <conditional name="GTFconditional">
555 <param name="GTFselect" value="with-gtf" />
556 <param name="sjdbOverhang" value="75"/>
557 <param name="sjdbGTFfile" value="test1.gtf" ftype="gtf"/>
558 </conditional>
559 </conditional>
560 <conditional name="quantmode_output">
561 <param name="quantMode" value="GeneCounts"/>
562 </conditional>
563 <section name="oformat">
564 <param name="outSAMattributes" value="NH,HI,AS,nM,NM,MD,jM,jI,MC,ch" />
565 <param name="outSAMmapqUnique" value="255" />
566 </section>
567 <section name="algo">
568 <conditional name="params">
569 <param name="settingsType" value="default" />
570 </conditional>
571 </section>
572
573 <output name="output_log" file="rnastar_test.log" compare="re_match_multiline" />
449 <output name="splice_junctions" file="rnastar_test_splicejunctions.bed"/> 574 <output name="splice_junctions" file="rnastar_test_splicejunctions.bed"/>
450 <output name="mapped_reads" file="rnastar_test_mapped_reads.bam" compare="sim_size" delta="634" /> 575 <output name="mapped_reads" file="rnastar_test_mapped_reads.bam" compare="sim_size" delta="634" />
451 <output name="reads_per_gene" file="tophat_test_reads_per_gene.txt" /> 576 <output name="reads_per_gene" file="tophat_test_reads_per_gene.txt" />
452 </test> 577 </test>
453 <test> 578 <!-- test gtf file and TranscriptomeSAM mode -->
454 <param name="input1" value="tophat_in2.fastqsanger" ftype="fastqsanger" /> 579 <test expect_num_outputs="4">
455 <param name="geneSource" value="history" /> 580 <conditional name="singlePaired">
456 <param name="genomeFastaFiles" value="tophat_test.fa" /> 581 <param name="sPaired" value="single" />
457 <param name="sPaired" value="single" /> 582 <param name="input1" value="tophat_in2.fastqsanger" ftype="fastqsanger" />
458 583 </conditional>
459 <param name="output_select" value="yes" /> 584 <conditional name="refGenomeSource">
460 <param name="outSAMattributes" value="All" /> 585 <param name="geneSource" value="history" />
461 <param name="outSAMstrandField" value="intronMotif" /> 586 <param name="genomeFastaFiles" value="tophat_test.fa" />
462 <param name="outFilterIntronMotifs" value="RemoveNoncanonical" /> 587 <param name="genomeSAindexNbases" value="5" />
463 588 <conditional name="GTFconditional">
464 <param name="output_select2" value="yes" /> 589 <param name="GTFselect" value="with-gtf" />
465 <param name="outFilterScoreMinOverLread" value="0.9" /> 590 <param name="sjdbOverhang" value="75"/>
466 <param name="settingsType" value="full" /> 591 <param name="sjdbGTFfile" value="test1.gtf" ftype="gtf"/>
467 <param name="seed_select" value="yes" /> 592 </conditional>
468 <param name="seedSearchStartLmax" value="25" /> 593 </conditional>
469 594 <conditional name="quantmode_output">
470 <output name="output_log" file="rnastar_test2.log" compare="diff" lines_diff="12"/> 595 <param name="quantMode" value="TranscriptomeSAM"/>
596 </conditional>
597 <section name="oformat">
598 <param name="outSAMattributes" value="NH,HI,AS,nM,NM,MD,jM,jI,MC,ch" />
599 <param name="outSAMmapqUnique" value="255" />
600 </section>
601 <section name="algo">
602 <conditional name="params">
603 <param name="settingsType" value="default" />
604 </conditional>
605 </section>
606
607 <output name="output_log" file="rnastar_test.log" compare="re_match_multiline" />
608 <output name="splice_junctions" file="rnastar_test_splicejunctions.bed"/>
609 <output name="mapped_reads" file="rnastar_test_mapped_reads.bam" compare="sim_size" delta="634" />
610 <output name="transcriptome_mapped_reads" file="rnastar_test_transcriptome_mapped_reads.bam" />
611 </test>
612 <test expect_num_outputs="3">
613 <conditional name="singlePaired">
614 <param name="sPaired" value="single" />
615 <param name="input1" value="tophat_in2.fastqsanger" ftype="fastqsanger" />
616 </conditional>
617 <conditional name="refGenomeSource">
618 <param name="geneSource" value="history" />
619 <param name="genomeFastaFiles" value="tophat_test.fa" />
620 <param name="genomeSAindexNbases" value="5" />
621 </conditional>
622 <section name="oformat">
623 <param name="outSAMattributes" value="NH,HI,AS,nM,NM,MD,jM,jI,MC,ch,XS" />
624 <param name="outSAMmapqUnique" value="255" />
625 </section>
626 <section name="filter">
627 <param name="basic_filters" value="exclude_unmapped,--outFilterIntronMotifs RemoveNoncanonical" />
628 <conditional name="output_params2">
629 <param name="output_select2" value="yes" />
630 <param name="outFilterScoreMinOverLread" value="0.9" />
631 </conditional>
632 </section>
633 <section name="algo">
634 <conditional name="params">
635 <param name="settingsType" value="full" />
636 <section name="seed">
637 <param name="seed_select" value="yes" />
638 <param name="seedSearchStartLmax" value="25" />
639 </section>
640 </conditional>
641 </section>
642
643 <output name="output_log" file="rnastar_test2.log" compare="re_match_multiline" />
471 <output name="splice_junctions" file="rnastar_test2_splicejunctions.bed"/> 644 <output name="splice_junctions" file="rnastar_test2_splicejunctions.bed"/>
472 <output name="mapped_reads" file="rnastar_test2_mapped_reads.bam" compare="sim_size" delta="200" /> 645 <output name="mapped_reads" file="rnastar_test2_mapped_reads.bam" compare="sim_size" delta="200" />
473 </test> 646 </test>
474 <test> 647 <test expect_num_outputs="4">
475 <param name="input1" value="test3.fastqsanger" ftype="fastqsanger" /> 648 <conditional name="singlePaired">
476 <param name="geneSource" value="history" /> 649 <param name="sPaired" value="single" />
477 <param name="genomeFastaFiles" value="test3.ref.fa" /> 650 <param name="input1" value="test3.fastqsanger" ftype="fastqsanger" />
478 <param name="sPaired" value="single" /> 651 </conditional>
479 652 <conditional name="refGenomeSource">
480 <param name="output_select" value="yes" /> 653 <param name="geneSource" value="history" />
481 <param name="outSAMattributes" value="All" /> 654 <param name="genomeFastaFiles" value="test3.ref.fa" />
482 <param name="outSAMstrandField" value="intronMotif" /> 655 <param name="genomeSAindexNbases" value="5" />
483 <param name="settingsType" value="star_fusion" /> 656 </conditional>
484 657 <param name="chimOutType" value="Junctions" />
485 <output name="chimeric_junctions" file="test3.chimjunc.tabular"/> 658 <section name="oformat">
486 </test> 659 <param name="outSAMattributes" value="NH,HI,AS,nM,NM,MD,jM,jI,MC,ch,XS" />
487 <test><!-- tests fastqsanger.gz --> 660 <param name="outSAMmapqUnique" value="255" />
488 <param name="input1" value="test3.fastqsanger.gz" ftype="fastqsanger.gz" /> 661 </section>
489 <param name="geneSource" value="history" /> 662 <section name="algo">
490 <param name="genomeFastaFiles" value="test3.ref.fa" /> 663 <conditional name="params">
491 <param name="sPaired" value="single" /> 664 <param name="settingsType" value="star_fusion" />
492 665 </conditional>
493 <param name="output_select" value="yes" /> 666 </section>
494 <param name="outSAMattributes" value="All" /> 667
495 <param name="outSAMstrandField" value="intronMotif" /> 668 <output name="chimeric_junctions" file="test3.chimjunc.tabular" compare="diff" lines_diff="2"/>
496 <param name="settingsType" value="star_fusion" /> 669 </test>
497 670 <test expect_num_outputs="4"><!-- tests fastqsanger.gz -->
498 <output name="chimeric_junctions" file="test3.chimjunc.tabular"/> 671 <conditional name="singlePaired">
499 </test> 672 <param name="sPaired" value="single" />
500 <test> 673 <param name="input1" value="test3.fastqsanger.gz" ftype="fastqsanger.gz" />
501 <param name="input1" value="tophat_in2.fastqsanger" ftype="fastqsanger" /> 674 </conditional>
502 <param name="geneSource" value="history" /> 675 <conditional name="refGenomeSource">
503 <param name="genomeFastaFiles" value="tophat_test.fa" /> 676 <param name="geneSource" value="history" />
504 <param name="sPaired" value="single" /> 677 <param name="genomeFastaFiles" value="test3.ref.fa" />
505 678 <param name="genomeSAindexNbases" value="5" />
506 <param name="output_select" value="yes" /> 679 </conditional>
507 <param name="outSAMattributes" value="All" /> 680 <param name="chimOutType" value="Junctions" />
508 <param name="outSAMstrandField" value="intronMotif" /> 681 <section name="oformat">
509 <param name="outFilterIntronMotifs" value="RemoveNoncanonical" /> 682 <param name="outSAMattributes" value="NH,HI,AS,nM,NM,MD,jM,jI,MC,ch,XS" />
510 683 <param name="outSAMmapqUnique" value="255" />
511 <param name="output_select2" value="yes" /> 684 </section>
512 <param name="settingsType" value="full" /> 685 <section name="algo">
513 <param name="chim_select" value="false" /> 686 <conditional name="params">
514 687 <param name="settingsType" value="star_fusion" />
515 <output name="output_log" file="rnastar_test.log" compare="diff" lines_diff="12"/> 688 </conditional>
689 </section>
690
691 <output name="chimeric_junctions" file="test3.chimjunc.tabular" compare="diff" lines_diff="2"/>
692 </test>
693 <test expect_num_outputs="3">
694 <conditional name="singlePaired">
695 <param name="sPaired" value="single" />
696 <param name="input1" value="tophat_in2.fastqsanger" ftype="fastqsanger" />
697 </conditional>
698 <conditional name="refGenomeSource">
699 <param name="geneSource" value="history" />
700 <param name="genomeFastaFiles" value="tophat_test.fa" />
701 <param name="genomeSAindexNbases" value="5" />
702 </conditional>
703 <section name="oformat">
704 <param name="outSAMattributes" value="NH,HI,AS,nM,NM,MD,jM,jI,MC,ch" />
705 <param name="outSAMmapqUnique" value="255" />
706 </section>
707 <section name="filter">
708 <param name="basic_filters" value="--outFilterIntronMotifs RemoveNoncanonical" />
709 <conditional name="output_params2">
710 <param name="output_select2" value="yes" />
711 </conditional>
712 </section>
713 <section name="algo">
714 <conditional name="params">
715 <param name="settingsType" value="full" />
716 </conditional>
717 </section>
718
719 <output name="output_log" file="rnastar_test.log" compare="re_match_multiline" />
516 <output name="splice_junctions" file="rnastar_test_splicejunctions.bed"/> 720 <output name="splice_junctions" file="rnastar_test_splicejunctions.bed"/>
517 <output name="mapped_reads" file="rnastar_test_mapped_reads.bam" compare="sim_size" delta="634" /> 721 <output name="mapped_reads" file="rnastar_test_mapped_reads.bam" compare="sim_size" delta="634" />
518 </test> 722 </test>
519 <test> 723 <!-- twopass mode tests -->
520 <param name="input1" value="tophat_in2.fastqsanger" ftype="fastqsanger" /> 724 <!-- test Basic twopass -->
521 <param name="geneSource" value="history" /> 725 <test expect_num_outputs="3">
522 <param name="genomeFastaFiles" value="tophat_test.fa" /> 726 <conditional name="singlePaired">
523 <param name="sPaired" value="single" /> 727 <param name="sPaired" value="single" />
524 728 <param name="input1" value="tophat_in2.fastqsanger" ftype="fastqsanger" />
525 <param name="output_select" value="yes" /> 729 </conditional>
526 <param name="outSAMattributes" value="All" /> 730 <conditional name="refGenomeSource">
527 <param name="outSAMstrandField" value="intronMotif" /> 731 <param name="geneSource" value="history" />
528 <param name="outFilterIntronMotifs" value="RemoveNoncanonical" /> 732 <param name="genomeFastaFiles" value="tophat_test.fa" />
529 733 <param name="genomeSAindexNbases" value="5" />
530 <param name="output_select2" value="yes" /> 734 </conditional>
531 <param name="settingsType" value="full" /> 735 <conditional name="twopass">
532 <param name="twopass" value="true" /> 736 <param name="twopassMode" value="Basic" />
533 <param name="twopassMode" value="Basic" /> 737 </conditional>
534 <param name="chim_select" value="false" /> 738 <section name="oformat">
535 739 <param name="outSAMattributes" value="NH,HI,AS,nM,NM,MD,jM,jI,MC,ch" />
536 <output name="output_log" file="rnastar_test_twopass.log" compare="diff" lines_diff="12"/> 740 <param name="outSAMmapqUnique" value="255" />
741 </section>
742 <section name="filter">
743 <param name="basic_filters" value="exclude_unmapped,--outFilterIntronMotifs RemoveNoncanonical" />
744 <conditional name="output_params2">
745 <param name="output_select2" value="yes" />
746 </conditional>
747 </section>
748 <section name="algo">
749 <conditional name="params">
750 <param name="settingsType" value="full" />
751 </conditional>
752 </section>
753
754 <output name="output_log" file="rnastar_test_twopass.log" compare="re_match_multiline" />
537 <output name="splice_junctions" file="rnastar_test_splicejunctions_twopass.bed"/> 755 <output name="splice_junctions" file="rnastar_test_splicejunctions_twopass.bed"/>
538 <output name="mapped_reads" file="rnastar_test_mapped_reads.bam" compare="sim_size" delta="634" /> 756 <output name="mapped_reads" file="rnastar_test_mapped_reads_twopass.bam" compare="sim_size" delta="634" />
757 </test>
758 <!-- test Basic twopass without a gtf file option -->
759 <test expect_num_outputs="3">
760 <conditional name="singlePaired">
761 <param name="sPaired" value="single" />
762 <param name="input1" value="tophat_in2.fastqsanger" ftype="fastqsanger" />
763 </conditional>
764 <conditional name="refGenomeSource">
765 <param name="geneSource" value="indexed" />
766 <conditional name="GTFconditional">
767 <param name="GTFselect" value="without-gtf" />
768 <param name="genomeDir" value="001" />
769 </conditional>
770 </conditional>
771 <conditional name="twopass">
772 <param name="twopassMode" value="Basic" />
773 </conditional>
774 <section name="oformat">
775 <param name="outSAMattributes" value="NH,HI,AS,nM,NM,MD,jM,jI,MC,ch" />
776 <param name="outSAMmapqUnique" value="255" />
777 </section>
778 <section name="filter">
779 <param name="basic_filters" value="exclude_unmapped,--outFilterIntronMotifs RemoveNoncanonical" />
780 <conditional name="output_params2">
781 <param name="output_select2" value="yes" />
782 </conditional>
783 </section>
784 <section name="algo">
785 <conditional name="params">
786 <param name="settingsType" value="full" />
787 </conditional>
788 </section>
789
790 <output name="output_log" file="rnastar_test_twopass.log" compare="re_match_multiline" />
791 <output name="splice_junctions" file="rnastar_test_splicejunctions_twopass.bed"/>
792 <output name="mapped_reads" file="rnastar_test_mapped_reads_twopass.bam" compare="sim_size" delta="634" />
793 </test>
794 <!-- test "multisample" twopass -->
795 <test expect_num_outputs="3">
796 <conditional name="singlePaired">
797 <param name="sPaired" value="single" />
798 <param name="input1" value="tophat_in2.fastqsanger" ftype="fastqsanger" />
799 </conditional>
800 <conditional name="refGenomeSource">
801 <param name="geneSource" value="history" />
802 <param name="genomeFastaFiles" value="tophat_test.fa" />
803 <param name="genomeSAindexNbases" value="5" />
804 </conditional>
805 <conditional name="twopass">
806 <param name="twopassMode" value="None --sjdbFileChrStartEnd" />
807 <param name="sj_precalculated" value="rnastar_test_splicejunctions_twopass.bed" />
808 </conditional>
809 <section name="oformat">
810 <param name="outSAMattributes" value="NH,HI,AS,nM,NM,MD,jM,jI,MC,ch" />
811 <param name="outSAMmapqUnique" value="255" />
812 </section>
813 <section name="filter">
814 <param name="basic_filters" value="exclude_unmapped,--outFilterIntronMotifs RemoveNoncanonicalUnannotated,--outFilterIntronMotifs RemoveNoncanonical" />
815 <conditional name="output_params2">
816 <param name="output_select2" value="yes" />
817 </conditional>
818 </section>
819 <section name="algo">
820 <conditional name="params">
821 <param name="settingsType" value="full" />
822 </conditional>
823 </section>
824
825 <output name="output_log" file="rnastar_test_twopass.log" compare="re_match_multiline" />
826 <output name="splice_junctions" file="rnastar_test_splicejunctions_twopass.bed"/>
827 <output name="mapped_reads" file="rnastar_test_mapped_reads_twopass.bam" compare="sim_size" delta="634" />
539 </test> 828 </test>
540 </tests> 829 </tests>
541 <help> 830 <help><![CDATA[
542 **What it does** 831 **What it does**
543 832
544 STAR is an ultrafast universal RNA-seq aligner. 833 STAR_ is an ultrafast universal RNA-seq aligner.
545 834
546 **Extra SAM attributes** 835 **Compatibility Notes**
547 836
548 The Standard option includes the following four attributes:: 837 STAR has a huge amount of options to filter alignments and to configure the
549 838 exact format of its output.
550 NH: Number of reported alignments that contain the query in the current record. 839
551 HI: Query hit index, indicating the alignment record is the i-th one stored in SAM 840 Some tools you may plan to use in your downstream analysis of the results are known to be sensitive to these settings or combinations of them.
552 AS: Local alignment score (paired for paired-end reads) 841
553 nM: Number of mismatches per (paired) alignment 842 *STAR-Fusion*
554 843
555 The All option includes the Standard attributes, plus the following four:: 844 STAR-Fusion_ can use the chimeric junctions output of STAR as input, but you
556 845 need to enable **chimeric alignment detection** by STAR for that dataset to be
557 NM: Edit distance to the reference, including ambiguous bases but excluding clipping 846 generated. Hence, be sure to select:
558 MD: String for mismatching positions 847
559 jM: Intron motifs for all junctions 848 **Report chimeric alignments?**: `As separate tabular "Junctions" output (Junctions)`.
560 jI: Start and end of introns for all junctions 849
561 850 In addition, for best results it is recommended_ that you
562 **STAR-Fusion** 851
563 852 - use **2-pass mapping** for more sensitive novel splice junction discovery
564 STAR-Fusion_ is used to identify candidate fusion transcripts. The recommended_ parameters for running 853
565 STAR prior to STAR-Fusion can be pre-selected. 854 - under *BAM output format specification*,
566 855 **Read alignment tags to include in the BAM output**: select `XS` as an
567 **Attributions** 856 additional tag to generate (this is the equivalent of using
568 857 `--outSAMstrandField intronMotif` on the command line)
569 rna_star - see the web site at rna_star_ 858
570 859 - under *Algorithmic settings*, **Configure seed, alignment and limits options**:
571 For details, please see the rna_starMS_ 860 `use parameters suggested for STAR-Fusion`.
572 "STAR: ultrafast universal RNA-seq aligner" 861
573 A. Dobin et al, Bioinformatics 2012; doi: 10.1093/bioinformatics/bts635 862 *Cufflinks*
574 863
575 Galaxy_ (that's what you are using right now!) for gluing everything together 864 .. class:: infomark
576 865
577 Most of the work for this wrapper XML is Jeremy Goecks' original STAR wrapper 866 Cufflinks is not considered to be the best tool for use downstream of STAR
578 867 anymore. Consider using *Stringtie* instead, which also should pose no
579 Minor tweaks to output names to suit our downstream purposes, toolshed automated dependencies 868 compatibility issues.
580 and odds and ends of other code and documentation comprising this tool was 869
581 written by Ross Lazarus and that part is licensed_ the same way as other rgenetics artefacts 870 To avoid compatibility issues with Cufflinks you should:
582 871
583 .. _licensed: http://creativecommons.org/licenses/by-nc-nd/3.0/ 872 - select **XS** as a *Read alignment tag to include in the BAM output* if (and
873 only if) your sequenced reads come from an unstranded library prep
874 - *not* select the *jM* and *jI* tags for inclusion
875 - keep the **HI** tag selected and
876 - select *HI tag values should be* **zero-based**
877 - exclude **All alignments across non-canonical junctions** under *Output
878 filter criteria -> Exclude the following records from the BAM output*
879
880 -----
881
882 Attribution
883
884 Minor tweaks to output names to suit downstream purposes, toolshed automated
885 dependencies and odds and ends of other code and documentation comprising
886 this tool were originally written by Ross Lazarus and have been licensed under
887 the creative commons
888 `BY-NC_ND 3.0 license <http://creativecommons.org/licenses/by-nc-nd/3.0/>`__.
889
890 .. _STAR: https://github.com/alexdobin/STAR
584 .. _STAR-Fusion: https://github.com/STAR-Fusion/STAR-Fusion 891 .. _STAR-Fusion: https://github.com/STAR-Fusion/STAR-Fusion
585 .. _recommended: https://github.com/STAR-Fusion/STAR-Fusion/wiki#alternatively-running-star-yourself-and-then-running-star-fusion-using-the-existing-outputs 892 .. _recommended: https://github.com/STAR-Fusion/STAR-Fusion/wiki#alternatively-kickstart-mode-running-star-yourself-and-then-running-star-fusion-using-the-existing-outputs
586 .. _rna_star: https://github.com/alexdobin/STAR 893 ]]></help>
587 .. _rna_starMS: http://bioinformatics.oxfordjournals.org/content/29/1/15.full
588 .. _Galaxy: http://getgalaxy.org
589 </help>
590 <expand macro="citations"/> 894 <expand macro="citations"/>
591 </tool> 895 </tool>