4
|
1 <tool id="plant_tribes_assembly_post_processor" name="AssemblyPostProcessor" version="@WRAPPER_VERSION@.3.0">
|
0
|
2 <description>post-processes de novo transcriptome assembly</description>
|
|
3 <macros>
|
|
4 <import>macros.xml</import>
|
|
5 </macros>
|
4
|
6 <requirements>
|
|
7 <requirement type="package" version="1.0.3">plant_tribes_assembly_post_processor</requirement>
|
|
8 </requirements>
|
0
|
9 <command detect_errors="exit_code"><![CDATA[
|
4
|
10 #set output_dir = 'assemblyPostProcessing_dir'
|
|
11 AssemblyPostProcessor
|
0
|
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 $target_gene_family_assembly_cond.gap_trimming
|
4
|
24 #if str($target_gene_family_assembly_cond.min_coverage) != '0.0':
|
|
25 --min_coverage $target_gene_family_assembly_cond.min_coverage
|
|
26 #end if
|
0
|
27 #end if
|
|
28 #if str($options_type.strand_specific) == 'yes':
|
4
|
29 --strand_specific
|
0
|
30 #end if
|
|
31 #if str($options_type.dereplicate) == 'yes':
|
4
|
32 --dereplicate
|
0
|
33 #end if
|
|
34 --min_length $options_type.min_length
|
|
35 #end if
|
|
36 --num_threads \${GALAXY_SLOTS:-4}
|
4
|
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'
|
|
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
|
0
|
51 ]]></command>
|
|
52 <inputs>
|
|
53 <param name="input" format="fasta" type="data" label="Transcriptome assembly fasta file"/>
|
|
54 <conditional name="prediction_method_cond">
|
|
55 <param name="prediction_method" type="select" label="Coding regions prediction method">
|
|
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">
|
|
65 <param name="options_type_selector" type="select" label="Options configuration">
|
|
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">
|
|
72 <param name="target_gene_family_assembly" type="select" label="Perform targeted gene assembly?">
|
|
73 <option value="no" selected="true">No</option>
|
|
74 <option value="yes">Yes</option>
|
|
75 </param>
|
|
76 <when value="no" />
|
|
77 <when value="yes">
|
|
78 <param name="orthogroups" format="tabular" type="data" label="Targeted gene families"/>
|
|
79 <param name="scaffold" type="select" label="Gene family scaffold">
|
|
80 <options from_data_table="plant_tribes_scaffolds" />
|
|
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."/>
|
|
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>
|
|
88 <param name="gap_trimming" type="float" value="0.1" min="0" max="1.0" label="Trim alignments"/>
|
4
|
89 <param name="min_coverage" type="float" value="0" min="0" max="1.0" label="Minimum alignment coverage"/>
|
0
|
90 </when>
|
|
91 </conditional>
|
|
92 <param name="strand_specific" type="select" label="Strand-specific assembly?">
|
|
93 <option value="no" selected="true">No</option>
|
|
94 <option value="yes">Yes</option>
|
|
95 </param>
|
|
96 <param name="dereplicate" type="select" label="Remove duplicate sequences?">
|
|
97 <option value="no" selected="true">No</option>
|
|
98 <option value="yes">Yes</option>
|
|
99 </param>
|
|
100 <param name="min_length" type="integer" value="200" label="Minimum sequence length"/>
|
|
101 </when>
|
|
102 </conditional>
|
|
103 </inputs>
|
|
104 <outputs>
|
4
|
105 <data name="output_targeted_gene_families_stats" format="tabular" label="Targeted gene families statistics: ${tool.name} on ${on_string}">
|
0
|
106 <filter>options_type['options_type_selector'] == 'advanced' and options_type['target_gene_family_assembly_cond']['target_gene_family_assembly'] == 'yes'</filter>
|
|
107 </data>
|
4
|
108 <collection name="output_targeted_gene_families" type="list" label="Targeted gene families: ${tool.name} on ${on_string}">
|
|
109 <discover_datasets pattern="__name__" directory="assemblyPostProcessing_dir/targeted_gene_family_assemblies" format="fasta" />
|
|
110 <filter>options_type['options_type_selector'] == 'advanced' and options_type['target_gene_family_assembly_cond']['target_gene_family_assembly'] == 'yes'</filter>
|
|
111 </collection>
|
0
|
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}">
|
|
115 <filter>options_type['options_type_selector'] == 'advanced' and options_type['dereplicate'] == 'yes'</filter>
|
|
116 </data>
|
|
117 <data name="output_cleaned_nr_cds" format="fasta" label="transcripts.cleaned.nr.cds: ${tool.name} on ${on_string}">
|
|
118 <filter>options_type['options_type_selector'] == 'advanced' and options_type['dereplicate'] == 'yes'</filter>
|
|
119 </data>
|
|
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}"/>
|
|
122 </outputs>
|
|
123 <tests>
|
|
124 <test>
|
|
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"/>
|
|
129 <output name="output_cleaned_pep" file="transcripts.cleaned.pep" ftype="fasta"/>
|
|
130 <output name="output_pep" file="transcripts.pep" ftype="fasta"/>
|
|
131 </test>
|
|
132 <test>
|
|
133 <param name="input" value="assembly.fasta" ftype="fasta"/>
|
|
134 <param name="prediction_method" value="estscan"/>
|
|
135 <param name="score_matrices" value="arabidopsis_thaliana.smat" ftype="smat"/>
|
|
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"/>
|
4
|
154 <output_collection name="output_targeted_gene_families" type="list">
|
|
155 </output_collection>
|
|
156 <output name="output_targeted_gene_families_stats" file="output_targeted_gene_families_stats.tabular" ftype="tabular"/>
|
0
|
157 <output name="output_cds" file="transcripts_tgf.cds" ftype="fasta"/>
|
|
158 <output name="output_cleaned_cds" file="transcripts.cleaned_tgf.cds" ftype="fasta"/>
|
|
159 <output name="output_cleaned_nr_cds" file="transcripts_tgf.cleaned.nr.cds" ftype="fasta"/>
|
|
160 <output name="output_cleaned_nr_pep" file="transcripts_tgf.cleaned.nr.pep" ftype="fasta"/>
|
|
161 <output name="output_cleaned_pep" file="transcripts.cleaned_tgf.pep" ftype="fasta"/>
|
|
162 <output name="output_pep" file="transcripts_tgf.pep" ftype="fasta"/>
|
|
163 </test>
|
|
164 </tests>
|
|
165 <help>
|
|
166 This tool is one of the PlantTribes collection of automated modular analysis pipelines for comparative and
|
|
167 evolutionary analyses of genome-scale gene families and transcriptomes. This tool post-processes de novo
|
|
168 assembled transcripts into putative coding sequences and their corresponding amino acid translations and
|
|
169 optionally assigns transcripts to circumscribed gene families ("orthogroups")[2]. After transcripts have been
|
|
170 assigned to gene families, overlapping contigs can be identified and merged to reduce fragmentation in the
|
|
171 de novo assembly.
|
|
172
|
|
173 -----
|
|
174
|
|
175 **Required options**
|
|
176
|
|
177 * **Transcriptome assembly fasta file** - either de novo or reference-guided transcriptome assembly fasta file selected from your history.
|
|
178 * **Coding regions prediction method** - method for finding coding regions within transcripts. Available methods are TransDecoder[3] and ESTScan[4].
|
|
179 * **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.
|
|
180
|
|
181 **Other options**
|
|
182
|
|
183 * **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].
|
|
184
|
4
|
185 * **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.
|
0
|
186 * **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.
|
|
187 * **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.
|
|
188 * **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.
|
4
|
189 * **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.
|
0
|
190
|
|
191 * **Strand-specific assembly?** - select 'Yes' if transcriptome library sequences were strand-specific. If 'Yes" is selected, transcripts from the minority strand (antisense) are removed.
|
|
192 * **Remove duplicate sequences?** - select 'Yes' to remove duplicated and exact subsequences[12].
|
|
193 * **Minimum sequence length** - set the minimum sequence length of predicted coding regions. The default is 200 bp.
|
|
194
|
|
195 </help>
|
|
196 <citations>
|
|
197 <expand macro="citation1" />
|
|
198 <citation type="bibtex">
|
|
199 @article{Honaas2016,
|
|
200 journal = {PloS one},
|
|
201 author = {2. Honaas LA, Wafula EK, Wickett NJ, Der JP, Zhang Y, Edger PP, Altman NS, Pires JC, Leebens-Mack JH},
|
|
202 title = {Selecting superior de novo transcriptome assemblies: lessons learned by leveraging the best plant genome},
|
|
203 year = {2016},
|
|
204 volume = {11},
|
|
205 number = {1},
|
|
206 pages = {e0146062},}
|
|
207 </citation>
|
|
208 <citation type="bibtex">
|
|
209 @article{Haas2013,
|
|
210 journal = {Nature Protocols},
|
|
211 author = {3. Haas BJ, Papanicolaou A, Yassour M, Grabherr M, Blood PD, Bowden J, Couger MB, Eccles D, Li B, Lieber M, MacManes MD},
|
|
212 title = {De novo transcript sequence reconstruction from RNA-seq using the Trinity platform for reference generation and analysis},
|
|
213 year = {2013},
|
|
214 volume = {8},
|
|
215 number = {8},
|
|
216 pages = {1494-1512},}
|
|
217 </citation>
|
|
218 <citation type="bibtex">
|
|
219 @article{Iseli1999,
|
|
220 journal = {ISMB},
|
|
221 author = {4. Iseli C, Jongeneel CV, Bucher P},
|
|
222 title = {ESTScan: a program for detecting, evaluating, and reconstructing potential coding regions in EST sequences},
|
|
223 year = {1999},
|
|
224 volume = {99},
|
|
225 pages = {138-148},
|
|
226 url = {http://estscan.sourceforge.net},}
|
|
227 </citation>
|
|
228 <citation type="bibtex">
|
|
229 @article{Huang1999,
|
|
230 journal = {Genome Research},
|
|
231 author = {5. Huang X, Madan A},
|
|
232 title = {CAP3: A DNA sequence assembly program},
|
|
233 year = {1999},
|
|
234 volume = {9},
|
|
235 number = {9},
|
|
236 pages = {868-877},
|
|
237 url = {http://seq.cs.iastate.edu/cap3.html},}
|
|
238 </citation>
|
|
239 <citation type="bibtex">
|
|
240 @article{Eddy2009,
|
|
241 journal = {Genome Inform},
|
|
242 author = {6. Eddy SR},
|
|
243 title = {A new generation of homology search tools based on probabilistic inference},
|
|
244 year = {2009},
|
|
245 volume = {23},
|
|
246 number = {1},
|
|
247 pages = {205-211},}
|
|
248 </citation>
|
|
249 <citation type="bibtex">
|
|
250 @article{Katoh2013,
|
|
251 journal = {Molecular biology and evolution},
|
|
252 author = {7. Katoh K, Standley DM},
|
|
253 title = {MAFFT multiple sequence alignment software version 7: improvements in performance and usability},
|
|
254 year = {2013},
|
|
255 volume = {30},
|
|
256 number = {4},
|
|
257 pages = {772-780},}
|
|
258 </citation>
|
|
259 <citation type="bibtex">
|
|
260 @article{Sasidharan2012,
|
|
261 journal = {Nucleic Acids Research},
|
|
262 author = {8. Sasidharan R, Nepusz T, Swarbreck D, Huala E, Paccanaro A},
|
|
263 title = {GFam: a platform for automatic annotation of gene families},
|
|
264 year = {2012},
|
|
265 pages = {gks631},}
|
|
266 </citation>
|
|
267 <citation type="bibtex">
|
|
268 @article{Li2003,
|
|
269 journal = {Genome Research}
|
|
270 author = {9. Li L, Stoeckert CJ, Roos DS},
|
|
271 title = {OrthoMCL: identification of ortholog groups for eukaryotic genomes},
|
|
272 year = {2003},
|
|
273 volume = {13},
|
|
274 number = {9},
|
|
275 pages = {2178-2189},}
|
|
276 </citation>
|
|
277 <citation type="bibtex">
|
|
278 @article{Emms2015,
|
|
279 journal = {Genome Biology}
|
|
280 author = {10. Emms DM, Kelly S},
|
|
281 title = {OrthoFinder: solving fundamental biases in whole genome comparisons dramatically improves orthogroup inference accuracy},
|
|
282 year = {2015},
|
|
283 volume = {16},
|
|
284 number = {1},
|
|
285 pages = {157},}
|
|
286 </citation>
|
|
287 <citation type="bibtex">
|
|
288 @article{Capella-Gutierrez2009,
|
|
289 journal = {Bioinformatics,},
|
|
290 author = {11. Capella-Gutierrez S, Silla-MartÃnez JM, Gabaldón T},
|
|
291 title = {trimAl: a tool for automated alignment trimming in large-scale phylogenetic analyses},
|
|
292 year = {2009},
|
|
293 volume = {25},
|
|
294 number = {15},
|
|
295 pages = {1972-1973},}
|
|
296 </citation>
|
|
297 <citation type="bibtex">
|
|
298 @article{Gremme2013,
|
|
299 journal = {IEEE/ACM Transactions on Computational Biology and Bioinformatics},
|
|
300 author = {12. Gremme G, Steinbiss S, Kurtz S},
|
|
301 title = {GenomeTools: a comprehensive software library for efficient processing of structured genome annotations},
|
|
302 year = {2013},
|
|
303 volume = {10},
|
|
304 number = {3},
|
|
305 pages = {645-656},}
|
|
306 </citation>
|
|
307 </citations>
|
|
308 </tool>
|