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