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