|
74
|
1 <tool id="plant_tribes_assembly_post_processor" name="AssemblyPostProcessor" version="@WRAPPER_VERSION@.3.0">
|
|
28
|
2 <description>post-processes de novo transcriptome assembly</description>
|
|
37
|
3 <macros>
|
|
|
4 <import>macros.xml</import>
|
|
|
5 </macros>
|
|
74
|
6 <requirements>
|
|
|
7 <requirement type="package" version="1.0.3">plant_tribes_assembly_post_processor</requirement>
|
|
|
8 </requirements>
|
|
70
|
9 <command detect_errors="exit_code"><![CDATA[
|
|
86
|
10 #set output_dir = 'assemblyPostProcessing_dir'
|
|
|
11 AssemblyPostProcessor
|
|
70
|
12 --transcripts '$input'
|
|
|
13 --prediction_method $prediction_method_cond.prediction_method
|
|
|
14 #if str($prediction_method_cond.prediction_method) == 'estscan':
|
|
|
15 --score_matrices '$score_matrices'
|
|
|
16 #end if
|
|
|
17 #if str($options_type.options_type_selector) == 'advanced':
|
|
|
18 #set target_gene_family_assembly_cond = $options_type.target_gene_family_assembly_cond
|
|
|
19 #if str($target_gene_family_assembly_cond.target_gene_family_assembly) == 'yes':
|
|
|
20 --gene_family_search '$target_gene_family_assembly_cond.orthogroups'
|
|
|
21 --scaffold '$target_gene_family_assembly_cond.scaffold.fields.path'
|
|
|
22 --method '$target_gene_family_assembly_cond.method'
|
|
|
23 --gap_trimming $target_gene_family_assembly_cond.gap_trimming
|
|
92
|
24 #if str($target_gene_family_assembly_cond.min_coverage) != '0.0':
|
|
91
|
25 --min_coverage $target_gene_family_assembly_cond.min_coverage
|
|
|
26 #end if
|
|
70
|
27 #end if
|
|
|
28 #if str($options_type.strand_specific) == 'yes':
|
|
93
|
29 --strand_specific
|
|
70
|
30 #end if
|
|
|
31 #if str($options_type.dereplicate) == 'yes':
|
|
93
|
32 --dereplicate
|
|
70
|
33 #end if
|
|
|
34 --min_length $options_type.min_length
|
|
|
35 #end if
|
|
|
36 --num_threads \${GALAXY_SLOTS:-4}
|
|
96
|
37 &>proc.log
|
|
|
38 && mv $output_dir/transcripts.cds '$output_cds'
|
|
|
39 && mv $output_dir/transcripts.pep '$output_pep'
|
|
|
40 && mv $output_dir/transcripts.cleaned.cds '$output_cleaned_cds'
|
|
|
41 && mv $output_dir/transcripts.cleaned.pep '$output_cleaned_pep'
|
|
86
|
42 #if str($options_type.options_type_selector) == 'advanced':
|
|
|
43 #if str($target_gene_family_assembly_cond.target_gene_family_assembly) == 'yes':
|
|
96
|
44 && if [ -f $output_dir/targeted_gene_family_assemblies.stats ]; then
|
|
|
45 mv $output_dir/targeted_gene_family_assemblies.stats '$output_targeted_gene_families_stats'
|
|
|
46 fi
|
|
86
|
47 #end if
|
|
|
48 #if str($options_type.dereplicate) == 'yes':
|
|
96
|
49 && if [ -f $output_dir/transcripts.cleaned.nr.cds ]; then
|
|
|
50 mv $output_dir/transcripts.cleaned.nr.cds '$output_cleaned_nr_cds'
|
|
|
51 fi
|
|
|
52 && if [ -f $output_dir/transcripts.cleaned.nr.pep ]; then
|
|
|
53 mv $output_dir/transcripts.cleaned.nr.pep '$output_cleaned_nr_pep'
|
|
|
54 fi
|
|
86
|
55 #end if
|
|
|
56 #end if
|
|
70
|
57 ]]></command>
|
|
0
|
58 <inputs>
|
|
28
|
59 <param name="input" format="fasta" type="data" label="Transcriptome assembly fasta file"/>
|
|
0
|
60 <conditional name="prediction_method_cond">
|
|
28
|
61 <param name="prediction_method" type="select" label="Coding regions prediction method">
|
|
0
|
62 <option value="transdecoder" selected="true">TransDecoder</option>
|
|
|
63 <option value="estscan">ESTScan</option>
|
|
|
64 </param>
|
|
|
65 <when value="transdecoder" />
|
|
|
66 <when value="estscan">
|
|
|
67 <param name="score_matrices" format="smat" type="data" label="Scores matrices"/>
|
|
|
68 </when>
|
|
|
69 </conditional>
|
|
|
70 <conditional name="options_type">
|
|
28
|
71 <param name="options_type_selector" type="select" label="Options configuration">
|
|
0
|
72 <option value="basic" selected="true">Basic</option>
|
|
|
73 <option value="advanced">Advanced</option>
|
|
|
74 </param>
|
|
|
75 <when value="basic" />
|
|
|
76 <when value="advanced">
|
|
|
77 <conditional name="target_gene_family_assembly_cond">
|
|
28
|
78 <param name="target_gene_family_assembly" type="select" label="Perform targeted gene assembly?">
|
|
0
|
79 <option value="no" selected="true">No</option>
|
|
|
80 <option value="yes">Yes</option>
|
|
|
81 </param>
|
|
|
82 <when value="no" />
|
|
|
83 <when value="yes">
|
|
28
|
84 <param name="orthogroups" format="tabular" type="data" label="Targeted gene families"/>
|
|
33
|
85 <param name="scaffold" type="select" label="Gene family scaffold">
|
|
0
|
86 <options from_data_table="plant_tribes_scaffolds" />
|
|
10
|
87 <validator type="no_options" message="No PlantTribes scaffolds are available. Use the PlantTribes Scaffolds Download Data Manager tool in Galaxy to install and populate the PlantTribes scaffolds data table."/>
|
|
0
|
88 </param>
|
|
|
89 <param name="method" type="select" label="Protein clustering method">
|
|
|
90 <option value="gfam" selected="true">GFam</option>
|
|
|
91 <option value="orthofinder">OrthoFinder</option>
|
|
|
92 <option value="orthomcl">OrthoMCL</option>
|
|
|
93 </param>
|
|
39
|
94 <param name="gap_trimming" type="float" value="0.1" min="0" max="1.0" label="Trim alignments"/>
|
|
90
|
95 <param name="min_coverage" type="float" value="0" min="0" max="1.0" label="Minimum alignment coverage"/>
|
|
0
|
96 </when>
|
|
|
97 </conditional>
|
|
28
|
98 <param name="strand_specific" type="select" label="Strand-specific assembly?">
|
|
0
|
99 <option value="no" selected="true">No</option>
|
|
|
100 <option value="yes">Yes</option>
|
|
|
101 </param>
|
|
28
|
102 <param name="dereplicate" type="select" label="Remove duplicate sequences?">
|
|
0
|
103 <option value="no" selected="true">No</option>
|
|
|
104 <option value="yes">Yes</option>
|
|
|
105 </param>
|
|
28
|
106 <param name="min_length" type="integer" value="200" label="Minimum sequence length"/>
|
|
0
|
107 </when>
|
|
|
108 </conditional>
|
|
|
109 </inputs>
|
|
|
110 <outputs>
|
|
84
|
111 <data name="output_targeted_gene_families_stats" format="tabular" label="Targeted gene families statistics: ${tool.name} on ${on_string}">
|
|
|
112 <filter>options_type['options_type_selector'] == 'advanced' and options_type['target_gene_family_assembly_cond']['target_gene_family_assembly'] == 'yes'</filter>
|
|
|
113 </data>
|
|
80
|
114 <collection name="output_targeted_gene_families" type="list" label="Targeted gene families: ${tool.name} on ${on_string}">
|
|
82
|
115 <discover_datasets pattern="__name__" directory="assemblyPostProcessing_dir/targeted_gene_family_assemblies" format="fasta" />
|
|
62
|
116 <filter>options_type['options_type_selector'] == 'advanced' and options_type['target_gene_family_assembly_cond']['target_gene_family_assembly'] == 'yes'</filter>
|
|
80
|
117 </collection>
|
|
68
|
118 <data name="output_pep" format="fasta" label="transcripts.pep: ${tool.name} on ${on_string}"/>
|
|
|
119 <data name="output_cleaned_pep" format="fasta" label="transcripts.cleaned.pep: ${tool.name} on ${on_string}"/>
|
|
|
120 <data name="output_cleaned_nr_pep" format="fasta" label="transcripts.cleaned.nr.pep: ${tool.name} on ${on_string}">
|
|
66
|
121 <filter>options_type['options_type_selector'] == 'advanced' and options_type['dereplicate'] == 'yes'</filter>
|
|
|
122 </data>
|
|
68
|
123 <data name="output_cleaned_nr_cds" format="fasta" label="transcripts.cleaned.nr.cds: ${tool.name} on ${on_string}">
|
|
66
|
124 <filter>options_type['options_type_selector'] == 'advanced' and options_type['dereplicate'] == 'yes'</filter>
|
|
|
125 </data>
|
|
68
|
126 <data name="output_cleaned_cds" format="fasta" label="transcripts.cleaned.cds: ${tool.name} on ${on_string}"/>
|
|
|
127 <data name="output_cds" format="fasta" label="transcripts.cds: ${tool.name} on ${on_string}"/>
|
|
0
|
128 </outputs>
|
|
|
129 <tests>
|
|
|
130 <test>
|
|
66
|
131 <param name="input" value="assembly.fasta" ftype="fasta"/>
|
|
|
132 <param name="prediction_method" value="transdecoder"/>
|
|
|
133 <output name="output_cds" file="transcripts.cds" ftype="fasta"/>
|
|
|
134 <output name="output_cleaned_cds" file="transcripts.cleaned.cds" ftype="fasta"/>
|
|
69
|
135 <output name="output_cleaned_pep" file="transcripts.cleaned.pep" ftype="fasta"/>
|
|
66
|
136 <output name="output_pep" file="transcripts.pep" ftype="fasta"/>
|
|
6
|
137 </test>
|
|
|
138 <test>
|
|
66
|
139 <param name="input" value="assembly.fasta" ftype="fasta"/>
|
|
|
140 <param name="prediction_method" value="estscan"/>
|
|
55
|
141 <param name="score_matrices" value="arabidopsis_thaliana.smat" ftype="smat"/>
|
|
66
|
142 <param name="options_type_selector" value="advanced"/>
|
|
|
143 <param name="dereplicate" value="yes"/>
|
|
|
144 <output name="output_cds" file="transcripts2.cds" ftype="fasta"/>
|
|
|
145 <output name="output_cleaned_cds" file="transcripts.cleaned.nr.cds" ftype="fasta"/>
|
|
|
146 <output name="output_cleaned_nr_cds" file="transcripts.cleaned.nr.cds" ftype="fasta"/>
|
|
|
147 <output name="output_cleaned_nr_pep" file="transcripts.cleaned.nr.pep" ftype="fasta"/>
|
|
|
148 <output name="output_cleaned_pep" file="transcripts.cleaned.nr.pep" ftype="fasta"/>
|
|
|
149 <output name="output_pep" file="transcripts2.pep" ftype="fasta"/>
|
|
|
150 </test>
|
|
|
151 <test>
|
|
|
152 <param name="input" value="assembly_tgf.fasta" ftype="fasta"/>
|
|
|
153 <param name="prediction_method" value="transdecoder"/>
|
|
|
154 <param name="options_type_selector" value="advanced"/>
|
|
|
155 <param name="target_gene_family_assembly" value="yes"/>
|
|
|
156 <param name="orthogroups" value="target_orthos.ids"/>
|
|
|
157 <param name="scaffold" value="22Gv1.1"/>
|
|
|
158 <param name="method" value="orthomcl"/>
|
|
|
159 <param name="dereplicate" value="yes"/>
|
|
82
|
160 <output_collection name="output_targeted_gene_families" type="list">
|
|
|
161 <element name="752.faa" file="752.faa" ftype="fasta"/>
|
|
|
162 <element name="752.fasta" file="752.fasta" ftype="fasta"/>
|
|
|
163 <element name="752.fna" file="752.fna" ftype="fasta"/>
|
|
|
164 </output_collection>
|
|
85
|
165 <output name="output_targeted_gene_families_stats" file="output_targeted_gene_families_stats.tabular" ftype="tabular"/>
|
|
66
|
166 <output name="output_cds" file="transcripts_tgf.cds" ftype="fasta"/>
|
|
|
167 <output name="output_cleaned_cds" file="transcripts.cleaned_tgf.cds" ftype="fasta"/>
|
|
|
168 <output name="output_cleaned_nr_cds" file="transcripts_tgf.cleaned.nr.cds" ftype="fasta"/>
|
|
|
169 <output name="output_cleaned_nr_pep" file="transcripts_tgf.cleaned.nr.pep" ftype="fasta"/>
|
|
|
170 <output name="output_cleaned_pep" file="transcripts.cleaned_tgf.pep" ftype="fasta"/>
|
|
|
171 <output name="output_pep" file="transcripts_tgf.pep" ftype="fasta"/>
|
|
0
|
172 </test>
|
|
|
173 </tests>
|
|
|
174 <help>
|
|
33
|
175 This tool is one of the PlantTribes collection of automated modular analysis pipelines for comparative and
|
|
28
|
176 evolutionary analyses of genome-scale gene families and transcriptomes. This tool post-processes de novo
|
|
|
177 assembled transcripts into putative coding sequences and their corresponding amino acid translations and
|
|
|
178 optionally assigns transcripts to circumscribed gene families ("orthogroups")[2]. After transcripts have been
|
|
|
179 assigned to gene families, overlapping contigs can be identified and merged to reduce fragmentation in the
|
|
|
180 de novo assembly.
|
|
0
|
181
|
|
|
182 -----
|
|
|
183
|
|
28
|
184 **Required options**
|
|
|
185
|
|
|
186 * **Transcriptome assembly fasta file** - either de novo or reference-guided transcriptome assembly fasta file selected from your history.
|
|
33
|
187 * **Coding regions prediction method** - method for finding coding regions within transcripts. Available methods are TransDecoder[3] and ESTScan[4].
|
|
|
188 * **Scores matrices** - scores matrices, based on a related species, are required when ESTScan is used to find coding regions. Details of how to create species-specific scores matrices can be found on the ESTScan website (http://estscan.sourceforge.net). Matrices of some organisms are also available to download.
|
|
28
|
189
|
|
|
190 **Other options**
|
|
0
|
191
|
|
29
|
192 * **Perform targeted gene assembly?** - selecting 'Yes' enables local assembly of one or more targeted gene families in a specific scaffold. Scaffolds are defined in PlantTribes as clusters of paralogous/orthologous sequences from a specified set of proteomes[5-7].
|
|
35
|
193
|
|
84
|
194 * **Targeted gene families** - select a history item containing a list of targeted orthogroup identifiers corresponding to the gene family classification from a specified scaffold. Gene family identifiers can be obtained from the function annotation table ("Orthogroup ID" field of .summary file) of scaffold data installed into Galaxy via the PlantTribes Scaffolds Download Data Manager tool, and are also available in the PlantTribes "annotation" directory of the scaffold data download.
|
|
35
|
195 * **Gene family scaffold** - one of the PlantTribes gene family scaffolds (installed into Galaxy by the PlantTribes Scaffolds Download Data Manager tool) whose orthogroup(s) are targeted for the localized assembly.
|
|
|
196 * **Protein clustering method** - gene family scaffold protein clustering method. Each PlantTribes scaffold data has up to three sets of clusters - GFam[8] (clusters of consensus domain architecture), OrthoFinder[9] (broadly defined clusters) or OrthoMCL[10] (narrowly defined clusters). You can also install your own data scaffold created using a different clustering method as long as it conforms to the PlantTribes scaffold data format.
|
|
39
|
197 * **Trim alignments** - trim gene family multiple sequence alignments that include scaffold backbone genes and locally assembled transcripts to remove non-conserved regions (gappy sites)[11]. The trimmed alignments are used in assigning scores to locally assembled transcripts to determine how well they compare to the backbone gene models. The default setting of 0.1 removes sites that have gaps in 90% or more of the sequences in the multiple sequence alignment. This option is restricted to the range 0.0 - 1.0.
|
|
90
|
198 * **Minimum alignment coverage** - allowable sequence coverage in the orthogroup trimmed protein multiple sequence alignments. Selecting transcripts with coverage of at least the average of the backbone orthogroup gene models is recommended. Details are shown in the targeted gene family assembly statistics history item.
|
|
35
|
199
|
|
28
|
200 * **Strand-specific assembly?** - select 'Yes' if transcriptome library sequences were strand-specific. If 'Yes" is selected, transcripts from the minority strand (antisense) are removed.
|
|
|
201 * **Remove duplicate sequences?** - select 'Yes' to remove duplicated and exact subsequences[12].
|
|
|
202 * **Minimum sequence length** - set the minimum sequence length of predicted coding regions. The default is 200 bp.
|
|
31
|
203
|
|
0
|
204 </help>
|
|
|
205 <citations>
|
|
37
|
206 <expand macro="citation1" />
|
|
28
|
207 <citation type="bibtex">
|
|
29
|
208 @article{Honaas2016,
|
|
|
209 journal = {PloS one},
|
|
|
210 author = {2. Honaas LA, Wafula EK, Wickett NJ, Der JP, Zhang Y, Edger PP, Altman NS, Pires JC, Leebens-Mack JH},
|
|
28
|
211 title = {Selecting superior de novo transcriptome assemblies: lessons learned by leveraging the best plant genome},
|
|
|
212 year = {2016},
|
|
|
213 volume = {11},
|
|
|
214 number = {1},
|
|
29
|
215 pages = {e0146062},}
|
|
28
|
216 </citation>
|
|
24
|
217 <citation type="bibtex">
|
|
29
|
218 @article{Haas2013,
|
|
|
219 journal = {Nature Protocols},
|
|
|
220 author = {3. Haas BJ, Papanicolaou A, Yassour M, Grabherr M, Blood PD, Bowden J, Couger MB, Eccles D, Li B, Lieber M, MacManes MD},
|
|
28
|
221 title = {De novo transcript sequence reconstruction from RNA-seq using the Trinity platform for reference generation and analysis},
|
|
|
222 year = {2013},
|
|
|
223 volume = {8},
|
|
|
224 number = {8},
|
|
29
|
225 pages = {1494-1512},}
|
|
28
|
226 </citation>
|
|
|
227 <citation type="bibtex">
|
|
29
|
228 @article{Iseli1999,
|
|
|
229 journal = {ISMB},
|
|
|
230 author = {4. Iseli C, Jongeneel CV, Bucher P},
|
|
|
231 title = {ESTScan: a program for detecting, evaluating, and reconstructing potential coding regions in EST sequences},
|
|
24
|
232 year = {1999},
|
|
28
|
233 volume = {99},
|
|
29
|
234 pages = {138-148},
|
|
|
235 url = {http://estscan.sourceforge.net},}
|
|
28
|
236 </citation>
|
|
|
237 <citation type="bibtex">
|
|
29
|
238 @article{Huang1999,
|
|
|
239 journal = {Genome Research},
|
|
|
240 author = {5. Huang X, Madan A},
|
|
28
|
241 title = {CAP3: A DNA sequence assembly program},
|
|
|
242 year = {1999},
|
|
|
243 volume = {9},
|
|
|
244 number = {9},
|
|
29
|
245 pages = {868-877},
|
|
|
246 url = {http://seq.cs.iastate.edu/cap3.html},}
|
|
28
|
247 </citation>
|
|
|
248 <citation type="bibtex">
|
|
29
|
249 @article{Eddy2009,
|
|
|
250 journal = {Genome Inform},
|
|
|
251 author = {6. Eddy SR},
|
|
28
|
252 title = {A new generation of homology search tools based on probabilistic inference},
|
|
|
253 year = {2009},
|
|
|
254 volume = {23},
|
|
|
255 number = {1},
|
|
29
|
256 pages = {205-211},}
|
|
28
|
257 </citation>
|
|
|
258 <citation type="bibtex">
|
|
30
|
259 @article{Katoh2013,
|
|
|
260 journal = {Molecular biology and evolution},
|
|
|
261 author = {7. Katoh K, Standley DM},
|
|
|
262 title = {MAFFT multiple sequence alignment software version 7: improvements in performance and usability},
|
|
|
263 year = {2013},
|
|
|
264 volume = {30},
|
|
|
265 number = {4},
|
|
|
266 pages = {772-780},}
|
|
|
267 </citation>
|
|
|
268 <citation type="bibtex">
|
|
29
|
269 @article{Sasidharan2012,
|
|
|
270 journal = {Nucleic Acids Research},
|
|
30
|
271 author = {8. Sasidharan R, Nepusz T, Swarbreck D, Huala E, Paccanaro A},
|
|
28
|
272 title = {GFam: a platform for automatic annotation of gene families},
|
|
|
273 year = {2012},
|
|
29
|
274 pages = {gks631},}
|
|
28
|
275 </citation>
|
|
|
276 <citation type="bibtex">
|
|
29
|
277 @article{Li2003,
|
|
|
278 journal = {Genome Research}
|
|
30
|
279 author = {9. Li L, Stoeckert CJ, Roos DS},
|
|
28
|
280 title = {OrthoMCL: identification of ortholog groups for eukaryotic genomes},
|
|
|
281 year = {2003},
|
|
|
282 volume = {13},
|
|
|
283 number = {9},
|
|
29
|
284 pages = {2178-2189},}
|
|
28
|
285 </citation>
|
|
|
286 <citation type="bibtex">
|
|
29
|
287 @article{Emms2015,
|
|
|
288 journal = {Genome Biology}
|
|
30
|
289 author = {10. Emms DM, Kelly S},
|
|
28
|
290 title = {OrthoFinder: solving fundamental biases in whole genome comparisons dramatically improves orthogroup inference accuracy},
|
|
|
291 year = {2015},
|
|
|
292 volume = {16},
|
|
|
293 number = {1},
|
|
29
|
294 pages = {157},}
|
|
28
|
295 </citation>
|
|
|
296 <citation type="bibtex">
|
|
29
|
297 @article{Capella-Gutierrez2009,
|
|
|
298 journal = {Bioinformatics,},
|
|
30
|
299 author = {11. Capella-Gutierrez S, Silla-MartÃnez JM, Gabaldón T},
|
|
28
|
300 title = {trimAl: a tool for automated alignment trimming in large-scale phylogenetic analyses},
|
|
|
301 year = {2009},
|
|
|
302 volume = {25},
|
|
|
303 number = {15},
|
|
29
|
304 pages = {1972-1973},}
|
|
28
|
305 </citation>
|
|
|
306 <citation type="bibtex">
|
|
29
|
307 @article{Gremme2013,
|
|
|
308 journal = {IEEE/ACM Transactions on Computational Biology and Bioinformatics},
|
|
30
|
309 author = {12. Gremme G, Steinbiss S, Kurtz S},
|
|
28
|
310 title = {GenomeTools: a comprehensive software library for efficient processing of structured genome annotations},
|
|
|
311 year = {2013},
|
|
|
312 volume = {10},
|
|
|
313 number = {3},
|
|
29
|
314 pages = {645-656},}
|
|
28
|
315 </citation>
|
|
0
|
316 </citations>
|
|
|
317 </tool>
|
