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