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