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