Mercurial > repos > iuc > stringtie

comparison stringtie.xml @ 16:eba36e001f45 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/stringtie commit 7dbb0fbe5446140f40fed36e45f42ec8d34bbc78
author iuc
date Fri, 03 May 2019 11:05:13 -0400
parents dd4df992d93d
children 1ebd14235b92
comparison
equal deleted inserted replaced
15:dd4df992d93d 16:eba36e001f45
110 ]]></command> 110 ]]></command>
111 <inputs> 111 <inputs>
112 <param name="input_bam" type="data" format="sam,bam" label="Input mapped reads" help="Input BAM/SAM file containing reads you want to assemble into transcripts"/> 112 <param name="input_bam" type="data" format="sam,bam" label="Input mapped reads" help="Input BAM/SAM file containing reads you want to assemble into transcripts"/>
113 <param name="rna_strandness" type="select" label="Specify strand information" 113 <param name="rna_strandness" type="select" label="Specify strand information"
114 help="Select 'Forward (FR)' if your reads are from a forward-stranded library, 'Reverse (RF)' if your reads are from a reverse-stranded library, or 'Unstranded' if your reads are not from a stranded library. See Help section below for more information. Default: Unstranded"> 114 help="Select 'Forward (FR)' if your reads are from a forward-stranded library, 'Reverse (RF)' if your reads are from a reverse-stranded library, or 'Unstranded' if your reads are not from a stranded library. See Help section below for more information. Default: Unstranded">
115 <option value="" selected="True">Unstranded</option> 115 <option value="" selected="true">Unstranded</option>
116 <option value="--fr">Forward (FR)</option> 116 <option value="--fr">Forward (FR)</option>
117 <option value="--rf">Reverse (RF)</option> 117 <option value="--rf">Reverse (RF)</option>
118 </param> 118 </param>
119 <conditional name="guide"> 119 <conditional name="guide">
120 <param name="use_guide" argument="-G" type="select" label="Use a reference file to guide assembly?" help="Use the reference annotation file (in GTF or GFF3 format) to guide the assembly process. The output will include expressed reference transcripts as well as any novel transcripts that are assembled. This option is required by option -e (Use Reference transcripts only), see below."> 120 <param name="use_guide" argument="-G" type="select" label="Use a reference file to guide assembly?" help="Use the reference annotation file (in GTF or GFF3 format) to guide the assembly process. The output will include expressed reference transcripts as well as any novel transcripts that are assembled. This option is required by option -e (Use Reference transcripts only), see below.">
121 <option value="yes">Use reference GTF/GFF3</option> 121 <option value="yes">Use reference GTF/GFF3</option>
122 <option value="no" selected="True" >Do not use reference GTF/GFF3</option> 122 <option value="no" selected="true" >Do not use reference GTF/GFF3</option>
123 </param> 123 </param>
124 <when value="no" /> 124 <when value="no" />
125 <when value="yes"> 125 <when value="yes">
126 <conditional name="guide_source"> 126 <conditional name="guide_source">
127 <param name="guide_gff_select" type="select" label="Reference file"> 127 <param name="guide_gff_select" type="select" label="Reference file">
138 </when> 138 </when>
139 <when value="history"> 139 <when value="history">
140 <param name="ref_hist" type="data" format="gtf,gff3" label="GTF/GFF3 dataset to guide assembly" /> 140 <param name="ref_hist" type="data" format="gtf,gff3" label="GTF/GFF3 dataset to guide assembly" />
141 </when> 141 </when>
142 </conditional> 142 </conditional>
143 <param name="input_estimation" argument="-e" type="boolean" truevalue="-e" falsevalue="" checked="False" label="Use Reference transcripts only?" help="Limit the processing of read alignments to only estimate and output the assembled transcripts matching the reference transcripts given with the -G option. With this option, read bundles with no reference transcripts (novel transcripts) will be entirely skipped, which may provide a considerable speed boost when the given set of reference transcripts is limited to a set of target genes, for example. Default: No"/> 143 <param name="input_estimation" argument="-e" type="boolean" truevalue="-e" falsevalue="" checked="false" label="Use Reference transcripts only?" help="Limit the processing of read alignments to only estimate and output the assembled transcripts matching the reference transcripts given with the -G option. With this option, read bundles with no reference transcripts (novel transcripts) will be entirely skipped, which may provide a considerable speed boost when the given set of reference transcripts is limited to a set of target genes, for example. Default: No"/>
144 <conditional name="special_outputs"> 144 <conditional name="special_outputs">
145 <param name="special_outputs_select" type="select" label="Output files for differential expression?" help="Select to output additional files that can be used with Ballgown or DESeq2/edgeR. See Help section below for more information"> 145 <param name="special_outputs_select" type="select" label="Output files for differential expression?" help="Select to output additional files that can be used with Ballgown or DESeq2/edgeR. See Help section below for more information">
146 <option value="ballgown">Ballgown</option> 146 <option value="ballgown">Ballgown</option>
147 <option value="deseq2">DESeq2/edgeR/limma-voom</option> 147 <option value="deseq2">DESeq2/edgeR/limma-voom</option>
148 <option value="no" selected="True">No additional output</option> 148 <option value="no" selected="true">No additional output</option>
149 </param> 149 </param>
150 <when value="ballgown" /> 150 <when value="ballgown" />
151 <when value="deseq2"> 151 <when value="deseq2">
152 <param name="read_length" argument="--length" type="integer" min="0" value="75" label="Specify the average read length" help="Default: 75" /> 152 <param name="read_length" argument="--length" type="integer" min="0" value="75" label="Specify the average read length" help="Default: 75" />
153 <param name="clustering" argument="--cluster" type="boolean" truevalue="--cluster" falsevalue="" checked="false" label="Cluster overlapping genes" help="Choose whether to cluster genes with different gene IDs that overlap. Transcripts containing the geneID prefix will be ignored. Default: No" /> 153 <param name="clustering" argument="--cluster" type="boolean" truevalue="--cluster" falsevalue="" checked="false" label="Cluster overlapping genes" help="Choose whether to cluster genes with different gene IDs that overlap. Transcripts containing the geneID prefix will be ignored. Default: No" />
162 </sanitizer> 162 </sanitizer>
163 </param> 163 </param>
164 </when> 164 </when>
165 <when value="no" /> 165 <when value="no" />
166 </conditional> 166 </conditional>
167 <param name="coverage_file" argument="-C" type="boolean" truevalue="-C" falsevalue="" checked="False" label="Output coverage file?" help="If StringTie is run with this option (requires -G), it returns a file with all the transcripts in the reference annotation that are fully covered, end to end, by reads. The output format is a GTF file as described below. Each line of the GTF is corresponds to a gene or transcript in the reference annotation. Default: No"/> 167 <param name="coverage_file" argument="-C" type="boolean" truevalue="-C" falsevalue="" checked="false" label="Output coverage file?" help="If StringTie is run with this option (requires -G), it returns a file with all the transcripts in the reference annotation that are fully covered, end to end, by reads. The output format is a GTF file as described below. Each line of the GTF corresponds to a gene or transcript in the reference annotation."/>
168 </when> 168 </when>
169 </conditional> 169 </conditional>
170 <section name="adv" title="Advanced Options"> 170 <section name="adv" title="Advanced Options">
171 <param name="abundance_estimation" argument="-A" type="boolean" truevalue="-A" falsevalue="" checked="False" label="Output gene abundance estimation file?" help="If selected, gene abundances will be reported in a tab-delimited file, see below for more information. Default: No"/> 171 <param name="abundance_estimation" argument="-A" type="boolean" truevalue="-A" falsevalue="" checked="false" label="Output gene abundance estimation file?" help="If selected, gene abundances will be reported in a tab-delimited file, see below for more information"/>
172 <param name="omit_sequences" argument="-x" type="text" value="" label="Do not assemble any transcripts on these reference sequence(s)" help="Ignore all read alignments (and thus do not attempt to perform transcript assembly) on the specified reference sequences. This parameter can be a single reference sequence name (e.g. chrM) or a comma-delimited list of sequence names (e.g. chrM,chrX,chrY). This can speed up StringTie especially in the case of excluding the mitochondrial genome, whose genes may have very high coverage in some cases, even though they may be of no interest for a particular RNA-Seq analysis. The reference sequence names are case sensitive, they must match identically the names of chromosomes/contigs of the target genome against which the RNA-Seq reads were aligned in the first place." /> 172 <param name="omit_sequences" argument="-x" type="text" value="" label="Do not assemble any transcripts on these reference sequence(s)" help="Ignore all read alignments (and thus do not attempt to perform transcript assembly) on the specified reference sequences. This parameter can be a single reference sequence name (e.g. chrM) or a comma-delimited list of sequence names (e.g. chrM,chrX,chrY). This can speed up StringTie especially in the case of excluding the mitochondrial genome, whose genes may have very high coverage in some cases, even though they may be of no interest for a particular RNA-Seq analysis. The reference sequence names are case sensitive, they must match identically the names of chromosomes/contigs of the target genome against which the RNA-Seq reads were aligned in the first place." />
173 <param name="name_prefix" argument="-l" type="text" label="Name prefix for output transcripts" help="This prefix will be added to the name of the transcripts that are output. Only letters and numbers will be retained in this field. Default: STRG"> 173 <param name="name_prefix" argument="-l" type="text" label="Name prefix for output transcripts" help="This prefix will be added to the name of the transcripts that are output. Only letters and numbers will be retained in this field. Default: STRG">
174 <sanitizer> 174 <sanitizer>
175 <valid initial="string.letters,string.digits"></valid> 175 <valid initial="string.letters,string.digits"></valid>
176 </sanitizer> 176 </sanitizer>
180 <param name="min_anchor_len" argument="-a" type="integer" min="0" value="10" label="Minimum anchor length for junctions" help="Junctions that don't have spliced reads that align across them with at least this amount of bases on both sides are filtered out. Default: 10" /> 180 <param name="min_anchor_len" argument="-a" type="integer" min="0" value="10" label="Minimum anchor length for junctions" help="Junctions that don't have spliced reads that align across them with at least this amount of bases on both sides are filtered out. Default: 10" />
181 <param name="min_anchor_cov" argument="-j" type="integer" min="0" value="1" label="Minimum junction coverage" help="There should be at least this many spliced reads that align across a junction (i.e. junction coverage). This number can be fractional, since some reads align in more than one place. A read that aligns in n places will contribute 1/n to the junction coverage. Default: 1" /> 181 <param name="min_anchor_cov" argument="-j" type="integer" min="0" value="1" label="Minimum junction coverage" help="There should be at least this many spliced reads that align across a junction (i.e. junction coverage). This number can be fractional, since some reads align in more than one place. A read that aligns in n places will contribute 1/n to the junction coverage. Default: 1" />
182 <param name="min_bundle_cov" argument="-c" type="integer" min="0" value="2" label="Minimum bundle reads per bp coverage to consider for assembly" help="Sets the minimum read coverage allowed for the predicted transcripts. A transcript with a lower coverage than this value is not shown in the output. Default: 2"/> 182 <param name="min_bundle_cov" argument="-c" type="integer" min="0" value="2" label="Minimum bundle reads per bp coverage to consider for assembly" help="Sets the minimum read coverage allowed for the predicted transcripts. A transcript with a lower coverage than this value is not shown in the output. Default: 2"/>
183 <param name="bdist" argument="-g" type="integer" min="0" value="50" label="Gap between read mappings triggering a new bundle" help="Minimum locus gap separation value. Reads that are mapped closer than this distance are merged together in the same processing bundle. Default: 50 (bp)"/> 183 <param name="bdist" argument="-g" type="integer" min="0" value="50" label="Gap between read mappings triggering a new bundle" help="Minimum locus gap separation value. Reads that are mapped closer than this distance are merged together in the same processing bundle. Default: 50 (bp)"/>
184 <param name="bundle_fraction" argument="-M" type="float" min="0.0" max="1.0" value="0.95" label="Fraction of bundle allowed to be covered by multi-hit reads" help="Sets the maximum fraction of muliple-location-mapped reads that are allowed to be present at a given locus. Default: 0.95"/> 184 <param name="bundle_fraction" argument="-M" type="float" min="0.0" max="1.0" value="0.95" label="Fraction of bundle allowed to be covered by multi-hit reads" help="Sets the maximum fraction of muliple-location-mapped reads that are allowed to be present at a given locus. Default: 0.95"/>
185 <param name="disable_trimming" argument="-t" type="boolean" truevalue="-t" falsevalue="" checked="False" label="Disable trimming of predicted transcripts based on coverage" help="This parameter disables trimming at the ends of the assembled transcripts. By default StringTie adjusts the predicted transcript's start and/or stop coordinates based on sudden drops in coverage of the assembled transcript. Default: No" /> 185 <param name="disable_trimming" argument="-t" type="boolean" truevalue="-t" falsevalue="" checked="false" label="Disable trimming of predicted transcripts based on coverage" help="This parameter disables trimming at the ends of the assembled transcripts. By default StringTie adjusts the predicted transcript's start and/or stop coordinates based on sudden drops in coverage of the assembled transcript. Default: No" />
186 <param name="multi_mapping" argument="-u" type="boolean" truevalue="-u" falsevalue="" checked="False" label="Disable multi-mapping correction" help="Default: No"/> 186 <param name="multi_mapping" argument="-u" type="boolean" truevalue="-u" falsevalue="" checked="false" label="Disable multi-mapping correction" help="Default: No"/>
187 </section> 187 </section>
188 </inputs> 188 </inputs>
189 <outputs> 189 <outputs>
190 <data name="output_gtf" format="gtf" label="${tool.name} on ${on_string}: Assembled transcripts" /> 190 <data name="output_gtf" format="gtf" label="${tool.name} on ${on_string}: Assembled transcripts" />
191 <data name="gene_abundance_estimation" format="gtf" label="${tool.name} on ${on_string}: Gene abundance estimates"> 191 <data name="gene_abundance_estimation" format="tabular" label="${tool.name} on ${on_string}: Gene abundance estimates">
192 <filter>adv['abundance_estimation']</filter> 192 <filter>adv['abundance_estimation']</filter>
193 </data> 193 </data>
194 <data name="coverage" format="gtf" label="${tool.name} on ${on_string}: Coverage"> 194 <data name="coverage" format="gtf" label="${tool.name} on ${on_string}: Coverage">
195 <filter>guide['use_guide'] == 'yes' and guide['coverage_file'] is True </filter> 195 <filter>guide['use_guide'] == 'yes' and guide['coverage_file'] is True </filter>
196 </data> 196 </data>
258 <param name="input_bam" ftype="bam" value="stringtie_in1.bam" /> 258 <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />
259 <param name="use_guide" value="yes" /> 259 <param name="use_guide" value="yes" />
260 <param name="guide_gff_select" value="history" /> 260 <param name="guide_gff_select" value="history" />
261 <param name="ref_hist" ftype="gtf" value="stringtie_in.gtf" /> 261 <param name="ref_hist" ftype="gtf" value="stringtie_in.gtf" />
262 <param name="special_outputs_select" value="ballgown" /> 262 <param name="special_outputs_select" value="ballgown" />
263 <param name="coverage_file" value="True" /> 263 <param name="coverage_file" value="true" />
264 <output name="exon_expression" file="./ballgown/e_data.ctab" ftype="tabular" /> 264 <output name="exon_expression" file="./ballgown/e_data.ctab" ftype="tabular" />
265 <output name="intron_expression" file="./ballgown/i_data.ctab" ftype="tabular" /> 265 <output name="intron_expression" file="./ballgown/i_data.ctab" ftype="tabular" />
266 <output name="transcript_expression" file="./ballgown/t_data.ctab" ftype="tabular" /> 266 <output name="transcript_expression" file="./ballgown/t_data.ctab" ftype="tabular" />
267 <output name="exon_transcript_mapping" file="./ballgown/e2t.ctab" ftype="tabular" /> 267 <output name="exon_transcript_mapping" file="./ballgown/e2t.ctab" ftype="tabular" />
268 <output name="intron_transcript_mapping" file="./ballgown/i2t.ctab" ftype="tabular" /> 268 <output name="intron_transcript_mapping" file="./ballgown/i2t.ctab" ftype="tabular" />
272 <!--Ensure output for edgeR works --> 272 <!--Ensure output for edgeR works -->
273 <test expect_num_outputs="5"> 273 <test expect_num_outputs="5">
274 <param name="input_bam" ftype="bam" value="stringtie_in1.bam" /> 274 <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />
275 <param name="use_guide" value="yes" /> 275 <param name="use_guide" value="yes" />
276 <param name="special_outputs_select" value="deseq2" /> 276 <param name="special_outputs_select" value="deseq2" />
277 <param name="input_estimation" value="True" /> 277 <param name="input_estimation" value="true" />
278 <param name="guide_gff_select" value="history" /> 278 <param name="guide_gff_select" value="history" />
279 <param name="ref_hist" ftype="gtf" value="stringtie_in.gtf" /> 279 <param name="ref_hist" ftype="gtf" value="stringtie_in.gtf" />
280 <param name="coverage_file" value="True" /> 280 <param name="coverage_file" value="true" />
281 <param name="clustering" value="True" /> 281 <param name="clustering" value="true" />
282 <output name="gene_counts" file="gene_counts_edger.tsv" ftype="tabular" /> 282 <output name="gene_counts" file="gene_counts_edger.tsv" ftype="tabular" />
283 <output name="transcript_counts" file="transcript_counts_edger.tsv" ftype="tabular" /> 283 <output name="transcript_counts" file="transcript_counts_edger.tsv" ftype="tabular" />
284 <output name="legend" file="legend.tsv" ftype="tabular" /> 284 <output name="legend" file="legend.tsv" ftype="tabular" />
285 <output name="output_gtf" file="stringtie_out6.gtf" ftype="gtf" lines_diff="4" /> 285 <output name="output_gtf" file="stringtie_out6.gtf" ftype="gtf" lines_diff="4" />
286 <output name="coverage" file="stringtie_out_coverage.gtf" ftype="gtf" /> 286 <output name="coverage" file="stringtie_out_coverage.gtf" ftype="gtf" />
290 <param name="input_bam" ftype="bam" value="stringtie_in1.bam" /> 290 <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />
291 <param name="use_guide" value="yes" /> 291 <param name="use_guide" value="yes" />
292 <param name="guide_gff_select" value="history" /> 292 <param name="guide_gff_select" value="history" />
293 <param name="ref_hist" ftype="gtf" value="stringtie_in.gtf" /> 293 <param name="ref_hist" ftype="gtf" value="stringtie_in.gtf" />
294 <param name="fraction" value="0.17" /> 294 <param name="fraction" value="0.17" />
295 <param name="abundance_estimation" value="True" /> 295 <param name="abundance_estimation" value="true" />
296 <output name="output_gtf" file="stringtie_out4.gtf" ftype="gtf" lines_diff="4" /> 296 <output name="output_gtf" file="stringtie_out4.gtf" ftype="gtf" lines_diff="4" />
297 <output name="gene_abundance_estimation" file="stringtie_out7.gtf" ftype="gtf" lines_diff="2" /> 297 <output name="gene_abundance_estimation" file="stringtie_out7.tsv" ftype="tabular" lines_diff="2" />
298 </test> 298 </test>
299 <!--Ensure another fraction value works --> 299 <!--Ensure another fraction value works -->
300 <test expect_num_outputs="1"> 300 <test expect_num_outputs="1">
301 <param name="input_bam" ftype="bam" value="stringtie_in1.bam" /> 301 <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />
302 <param name="use_guide" value="yes" /> 302 <param name="use_guide" value="yes" />