|
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
|
|
85
|
24 --min_coverage $target_gene_family_assembly_cond.min_coverage
|
|
70
|
25 #end if
|
|
|
26 #if str($options_type.strand_specific) == 'yes':
|
|
72
|
27 --strand_specific true
|
|
70
|
28 #end if
|
|
|
29 #if str($options_type.dereplicate) == 'yes':
|
|
72
|
30 --dereplicate true
|
|
70
|
31 #end if
|
|
|
32 --min_length $options_type.min_length
|
|
|
33 #end if
|
|
|
34 --num_threads \${GALAXY_SLOTS:-4}
|
|
87
|
35 2>&1
|
|
86
|
36 && mv $output_dir/transcripts.cds '$output_cds'
|
|
|
37 && mv $output_dir/transcripts.pep '$output_pep'
|
|
|
38 && mv $output_dir/transcripts.cleaned.cds '$output_cleaned_cds'
|
|
|
39 && mv $output_dir/transcripts.cleaned.pep '$output_cleaned_pep'
|
|
|
40 #if str($options_type.options_type_selector) == 'advanced':
|
|
|
41 #if str($target_gene_family_assembly_cond.target_gene_family_assembly) == 'yes':
|
|
|
42 && mv $output_dir/targeted_gene_family_assemblies.stats '$output_targeted_gene_families_stats'
|
|
|
43 #end if
|
|
|
44 #if str($options_type.dereplicate) == 'yes':
|
|
|
45 && mv $output_dir/transcripts.cleaned.nr.cds '$output_cleaned_nr_cds'
|
|
|
46 && mv $output_dir/transcripts.cleaned.nr.pep '$output_cleaned_nr_pep'
|
|
|
47 #end if
|
|
|
48 #end if
|
|
70
|
49 ]]></command>
|
|
0
|
50 <inputs>
|
|
28
|
51 <param name="input" format="fasta" type="data" label="Transcriptome assembly fasta file"/>
|
|
0
|
52 <conditional name="prediction_method_cond">
|
|
28
|
53 <param name="prediction_method" type="select" label="Coding regions prediction method">
|
|
0
|
54 <option value="transdecoder" selected="true">TransDecoder</option>
|
|
|
55 <option value="estscan">ESTScan</option>
|
|
|
56 </param>
|
|
|
57 <when value="transdecoder" />
|
|
|
58 <when value="estscan">
|
|
|
59 <param name="score_matrices" format="smat" type="data" label="Scores matrices"/>
|
|
|
60 </when>
|
|
|
61 </conditional>
|
|
|
62 <conditional name="options_type">
|
|
28
|
63 <param name="options_type_selector" type="select" label="Options configuration">
|
|
0
|
64 <option value="basic" selected="true">Basic</option>
|
|
|
65 <option value="advanced">Advanced</option>
|
|
|
66 </param>
|
|
|
67 <when value="basic" />
|
|
|
68 <when value="advanced">
|
|
|
69 <conditional name="target_gene_family_assembly_cond">
|
|
28
|
70 <param name="target_gene_family_assembly" type="select" label="Perform targeted gene assembly?">
|
|
0
|
71 <option value="no" selected="true">No</option>
|
|
|
72 <option value="yes">Yes</option>
|
|
|
73 </param>
|
|
|
74 <when value="no" />
|
|
|
75 <when value="yes">
|
|
28
|
76 <param name="orthogroups" format="tabular" type="data" label="Targeted gene families"/>
|
|
33
|
77 <param name="scaffold" type="select" label="Gene family scaffold">
|
|
0
|
78 <options from_data_table="plant_tribes_scaffolds" />
|
|
10
|
79 <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
|
80 </param>
|
|
|
81 <param name="method" type="select" label="Protein clustering method">
|
|
|
82 <option value="gfam" selected="true">GFam</option>
|
|
|
83 <option value="orthofinder">OrthoFinder</option>
|
|
|
84 <option value="orthomcl">OrthoMCL</option>
|
|
|
85 </param>
|
|
39
|
86 <param name="gap_trimming" type="float" value="0.1" min="0" max="1.0" label="Trim alignments"/>
|
|
85
|
87 <param name="min_coverage" type="float" value="0.5" min="0.3" max="1.0" label="Minimum alignment coverage"/>
|
|
0
|
88 </when>
|
|
|
89 </conditional>
|
|
28
|
90 <param name="strand_specific" type="select" label="Strand-specific assembly?">
|
|
0
|
91 <option value="no" selected="true">No</option>
|
|
|
92 <option value="yes">Yes</option>
|
|
|
93 </param>
|
|
28
|
94 <param name="dereplicate" type="select" label="Remove duplicate sequences?">
|
|
0
|
95 <option value="no" selected="true">No</option>
|
|
|
96 <option value="yes">Yes</option>
|
|
|
97 </param>
|
|
28
|
98 <param name="min_length" type="integer" value="200" label="Minimum sequence length"/>
|
|
0
|
99 </when>
|
|
|
100 </conditional>
|
|
|
101 </inputs>
|
|
|
102 <outputs>
|
|
84
|
103 <data name="output_targeted_gene_families_stats" format="tabular" label="Targeted gene families statistics: ${tool.name} on ${on_string}">
|
|
|
104 <filter>options_type['options_type_selector'] == 'advanced' and options_type['target_gene_family_assembly_cond']['target_gene_family_assembly'] == 'yes'</filter>
|
|
|
105 </data>
|
|
80
|
106 <collection name="output_targeted_gene_families" type="list" label="Targeted gene families: ${tool.name} on ${on_string}">
|
|
82
|
107 <discover_datasets pattern="__name__" directory="assemblyPostProcessing_dir/targeted_gene_family_assemblies" format="fasta" />
|
|
62
|
108 <filter>options_type['options_type_selector'] == 'advanced' and options_type['target_gene_family_assembly_cond']['target_gene_family_assembly'] == 'yes'</filter>
|
|
80
|
109 </collection>
|
|
68
|
110 <data name="output_pep" format="fasta" label="transcripts.pep: ${tool.name} on ${on_string}"/>
|
|
|
111 <data name="output_cleaned_pep" format="fasta" label="transcripts.cleaned.pep: ${tool.name} on ${on_string}"/>
|
|
|
112 <data name="output_cleaned_nr_pep" format="fasta" label="transcripts.cleaned.nr.pep: ${tool.name} on ${on_string}">
|
|
66
|
113 <filter>options_type['options_type_selector'] == 'advanced' and options_type['dereplicate'] == 'yes'</filter>
|
|
|
114 </data>
|
|
68
|
115 <data name="output_cleaned_nr_cds" format="fasta" label="transcripts.cleaned.nr.cds: ${tool.name} on ${on_string}">
|
|
66
|
116 <filter>options_type['options_type_selector'] == 'advanced' and options_type['dereplicate'] == 'yes'</filter>
|
|
|
117 </data>
|
|
68
|
118 <data name="output_cleaned_cds" format="fasta" label="transcripts.cleaned.cds: ${tool.name} on ${on_string}"/>
|
|
|
119 <data name="output_cds" format="fasta" label="transcripts.cds: ${tool.name} on ${on_string}"/>
|
|
0
|
120 </outputs>
|
|
|
121 <tests>
|
|
|
122 <test>
|
|
66
|
123 <param name="input" value="assembly.fasta" ftype="fasta"/>
|
|
|
124 <param name="prediction_method" value="transdecoder"/>
|
|
|
125 <output name="output_cds" file="transcripts.cds" ftype="fasta"/>
|
|
|
126 <output name="output_cleaned_cds" file="transcripts.cleaned.cds" ftype="fasta"/>
|
|
69
|
127 <output name="output_cleaned_pep" file="transcripts.cleaned.pep" ftype="fasta"/>
|
|
66
|
128 <output name="output_pep" file="transcripts.pep" ftype="fasta"/>
|
|
6
|
129 </test>
|
|
|
130 <test>
|
|
66
|
131 <param name="input" value="assembly.fasta" ftype="fasta"/>
|
|
|
132 <param name="prediction_method" value="estscan"/>
|
|
55
|
133 <param name="score_matrices" value="arabidopsis_thaliana.smat" ftype="smat"/>
|
|
66
|
134 <param name="options_type_selector" value="advanced"/>
|
|
|
135 <param name="dereplicate" value="yes"/>
|
|
|
136 <output name="output_cds" file="transcripts2.cds" ftype="fasta"/>
|
|
|
137 <output name="output_cleaned_cds" file="transcripts.cleaned.nr.cds" ftype="fasta"/>
|
|
|
138 <output name="output_cleaned_nr_cds" file="transcripts.cleaned.nr.cds" ftype="fasta"/>
|
|
|
139 <output name="output_cleaned_nr_pep" file="transcripts.cleaned.nr.pep" ftype="fasta"/>
|
|
|
140 <output name="output_cleaned_pep" file="transcripts.cleaned.nr.pep" ftype="fasta"/>
|
|
|
141 <output name="output_pep" file="transcripts2.pep" ftype="fasta"/>
|
|
|
142 </test>
|
|
|
143 <test>
|
|
|
144 <param name="input" value="assembly_tgf.fasta" ftype="fasta"/>
|
|
|
145 <param name="prediction_method" value="transdecoder"/>
|
|
|
146 <param name="options_type_selector" value="advanced"/>
|
|
|
147 <param name="target_gene_family_assembly" value="yes"/>
|
|
|
148 <param name="orthogroups" value="target_orthos.ids"/>
|
|
|
149 <param name="scaffold" value="22Gv1.1"/>
|
|
|
150 <param name="method" value="orthomcl"/>
|
|
|
151 <param name="dereplicate" value="yes"/>
|
|
87
|
152 <param name="min_coverage" value="0.3"/>
|
|
82
|
153 <output_collection name="output_targeted_gene_families" type="list">
|
|
|
154 <element name="752.faa" file="752.faa" ftype="fasta"/>
|
|
|
155 <element name="752.fasta" file="752.fasta" ftype="fasta"/>
|
|
|
156 <element name="752.fna" file="752.fna" ftype="fasta"/>
|
|
|
157 </output_collection>
|
|
85
|
158 <output name="output_targeted_gene_families_stats" file="output_targeted_gene_families_stats.tabular" ftype="tabular"/>
|
|
66
|
159 <output name="output_cds" file="transcripts_tgf.cds" ftype="fasta"/>
|
|
|
160 <output name="output_cleaned_cds" file="transcripts.cleaned_tgf.cds" ftype="fasta"/>
|
|
|
161 <output name="output_cleaned_nr_cds" file="transcripts_tgf.cleaned.nr.cds" ftype="fasta"/>
|
|
|
162 <output name="output_cleaned_nr_pep" file="transcripts_tgf.cleaned.nr.pep" ftype="fasta"/>
|
|
|
163 <output name="output_cleaned_pep" file="transcripts.cleaned_tgf.pep" ftype="fasta"/>
|
|
|
164 <output name="output_pep" file="transcripts_tgf.pep" ftype="fasta"/>
|
|
0
|
165 </test>
|
|
|
166 </tests>
|
|
|
167 <help>
|
|
33
|
168 This tool is one of the PlantTribes collection of automated modular analysis pipelines for comparative and
|
|
28
|
169 evolutionary analyses of genome-scale gene families and transcriptomes. This tool post-processes de novo
|
|
|
170 assembled transcripts into putative coding sequences and their corresponding amino acid translations and
|
|
|
171 optionally assigns transcripts to circumscribed gene families ("orthogroups")[2]. After transcripts have been
|
|
|
172 assigned to gene families, overlapping contigs can be identified and merged to reduce fragmentation in the
|
|
|
173 de novo assembly.
|
|
0
|
174
|
|
|
175 -----
|
|
|
176
|
|
28
|
177 **Required options**
|
|
|
178
|
|
|
179 * **Transcriptome assembly fasta file** - either de novo or reference-guided transcriptome assembly fasta file selected from your history.
|
|
33
|
180 * **Coding regions prediction method** - method for finding coding regions within transcripts. Available methods are TransDecoder[3] and ESTScan[4].
|
|
|
181 * **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
|
182
|
|
|
183 **Other options**
|
|
0
|
184
|
|
29
|
185 * **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
|
186
|
|
84
|
187 * **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
|
188 * **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.
|
|
|
189 * **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
|
190 * **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.
|
|
85
|
191 * **Minimum alignment coverage** - allowable sequence coverage in the orthogroup trimmed protein multiple sequence alignments. The default setting of 0.5 reports assembled targeted gene family transcripts with at least 50% coverage of the conserved regions in the trimmed multiple sequence alignment.
|
|
35
|
192
|
|
28
|
193 * **Strand-specific assembly?** - select 'Yes' if transcriptome library sequences were strand-specific. If 'Yes" is selected, transcripts from the minority strand (antisense) are removed.
|
|
|
194 * **Remove duplicate sequences?** - select 'Yes' to remove duplicated and exact subsequences[12].
|
|
|
195 * **Minimum sequence length** - set the minimum sequence length of predicted coding regions. The default is 200 bp.
|
|
31
|
196
|
|
0
|
197 </help>
|
|
|
198 <citations>
|
|
37
|
199 <expand macro="citation1" />
|
|
28
|
200 <citation type="bibtex">
|
|
29
|
201 @article{Honaas2016,
|
|
|
202 journal = {PloS one},
|
|
|
203 author = {2. Honaas LA, Wafula EK, Wickett NJ, Der JP, Zhang Y, Edger PP, Altman NS, Pires JC, Leebens-Mack JH},
|
|
28
|
204 title = {Selecting superior de novo transcriptome assemblies: lessons learned by leveraging the best plant genome},
|
|
|
205 year = {2016},
|
|
|
206 volume = {11},
|
|
|
207 number = {1},
|
|
29
|
208 pages = {e0146062},}
|
|
28
|
209 </citation>
|
|
24
|
210 <citation type="bibtex">
|
|
29
|
211 @article{Haas2013,
|
|
|
212 journal = {Nature Protocols},
|
|
|
213 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
|
214 title = {De novo transcript sequence reconstruction from RNA-seq using the Trinity platform for reference generation and analysis},
|
|
|
215 year = {2013},
|
|
|
216 volume = {8},
|
|
|
217 number = {8},
|
|
29
|
218 pages = {1494-1512},}
|
|
28
|
219 </citation>
|
|
|
220 <citation type="bibtex">
|
|
29
|
221 @article{Iseli1999,
|
|
|
222 journal = {ISMB},
|
|
|
223 author = {4. Iseli C, Jongeneel CV, Bucher P},
|
|
|
224 title = {ESTScan: a program for detecting, evaluating, and reconstructing potential coding regions in EST sequences},
|
|
24
|
225 year = {1999},
|
|
28
|
226 volume = {99},
|
|
29
|
227 pages = {138-148},
|
|
|
228 url = {http://estscan.sourceforge.net},}
|
|
28
|
229 </citation>
|
|
|
230 <citation type="bibtex">
|
|
29
|
231 @article{Huang1999,
|
|
|
232 journal = {Genome Research},
|
|
|
233 author = {5. Huang X, Madan A},
|
|
28
|
234 title = {CAP3: A DNA sequence assembly program},
|
|
|
235 year = {1999},
|
|
|
236 volume = {9},
|
|
|
237 number = {9},
|
|
29
|
238 pages = {868-877},
|
|
|
239 url = {http://seq.cs.iastate.edu/cap3.html},}
|
|
28
|
240 </citation>
|
|
|
241 <citation type="bibtex">
|
|
29
|
242 @article{Eddy2009,
|
|
|
243 journal = {Genome Inform},
|
|
|
244 author = {6. Eddy SR},
|
|
28
|
245 title = {A new generation of homology search tools based on probabilistic inference},
|
|
|
246 year = {2009},
|
|
|
247 volume = {23},
|
|
|
248 number = {1},
|
|
29
|
249 pages = {205-211},}
|
|
28
|
250 </citation>
|
|
|
251 <citation type="bibtex">
|
|
30
|
252 @article{Katoh2013,
|
|
|
253 journal = {Molecular biology and evolution},
|
|
|
254 author = {7. Katoh K, Standley DM},
|
|
|
255 title = {MAFFT multiple sequence alignment software version 7: improvements in performance and usability},
|
|
|
256 year = {2013},
|
|
|
257 volume = {30},
|
|
|
258 number = {4},
|
|
|
259 pages = {772-780},}
|
|
|
260 </citation>
|
|
|
261 <citation type="bibtex">
|
|
29
|
262 @article{Sasidharan2012,
|
|
|
263 journal = {Nucleic Acids Research},
|
|
30
|
264 author = {8. Sasidharan R, Nepusz T, Swarbreck D, Huala E, Paccanaro A},
|
|
28
|
265 title = {GFam: a platform for automatic annotation of gene families},
|
|
|
266 year = {2012},
|
|
29
|
267 pages = {gks631},}
|
|
28
|
268 </citation>
|
|
|
269 <citation type="bibtex">
|
|
29
|
270 @article{Li2003,
|
|
|
271 journal = {Genome Research}
|
|
30
|
272 author = {9. Li L, Stoeckert CJ, Roos DS},
|
|
28
|
273 title = {OrthoMCL: identification of ortholog groups for eukaryotic genomes},
|
|
|
274 year = {2003},
|
|
|
275 volume = {13},
|
|
|
276 number = {9},
|
|
29
|
277 pages = {2178-2189},}
|
|
28
|
278 </citation>
|
|
|
279 <citation type="bibtex">
|
|
29
|
280 @article{Emms2015,
|
|
|
281 journal = {Genome Biology}
|
|
30
|
282 author = {10. Emms DM, Kelly S},
|
|
28
|
283 title = {OrthoFinder: solving fundamental biases in whole genome comparisons dramatically improves orthogroup inference accuracy},
|
|
|
284 year = {2015},
|
|
|
285 volume = {16},
|
|
|
286 number = {1},
|
|
29
|
287 pages = {157},}
|
|
28
|
288 </citation>
|
|
|
289 <citation type="bibtex">
|
|
29
|
290 @article{Capella-Gutierrez2009,
|
|
|
291 journal = {Bioinformatics,},
|
|
30
|
292 author = {11. Capella-Gutierrez S, Silla-MartÃnez JM, Gabaldón T},
|
|
28
|
293 title = {trimAl: a tool for automated alignment trimming in large-scale phylogenetic analyses},
|
|
|
294 year = {2009},
|
|
|
295 volume = {25},
|
|
|
296 number = {15},
|
|
29
|
297 pages = {1972-1973},}
|
|
28
|
298 </citation>
|
|
|
299 <citation type="bibtex">
|
|
29
|
300 @article{Gremme2013,
|
|
|
301 journal = {IEEE/ACM Transactions on Computational Biology and Bioinformatics},
|
|
30
|
302 author = {12. Gremme G, Steinbiss S, Kurtz S},
|
|
28
|
303 title = {GenomeTools: a comprehensive software library for efficient processing of structured genome annotations},
|
|
|
304 year = {2013},
|
|
|
305 volume = {10},
|
|
|
306 number = {3},
|
|
29
|
307 pages = {645-656},}
|
|
28
|
308 </citation>
|
|
0
|
309 </citations>
|
|
|
310 </tool>
|
