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