|
28
|
1 <tool id="plant_tribes_assembly_post_processor" name="AssemblyPostProcessor" version="0.4.0">
|
|
|
2 <description>post-processes de novo transcriptome assembly</description>
|
|
0
|
3 <requirements>
|
|
14
|
4 <requirement type="package" version="0.4">plant_tribes_assembly_post_processor</requirement>
|
|
0
|
5 </requirements>
|
|
|
6 <stdio>
|
|
|
7 <!-- Anything other than zero is an error -->
|
|
|
8 <exit_code range="1:" />
|
|
6
|
9 <exit_code range=":-1" />
|
|
|
10 <!-- In case the return code has not been set propery check stderr too -->
|
|
0
|
11 <regex match="Error:" />
|
|
|
12 <regex match="Exception:" />
|
|
|
13 </stdio>
|
|
|
14 <command>
|
|
|
15 <![CDATA[
|
|
|
16 AssemblyPostProcesser
|
|
15
|
17 --transcripts '$input'
|
|
0
|
18 --prediction_method $prediction_method_cond.prediction_method
|
|
|
19 #if str($prediction_method_cond.prediction_method) == 'estscan':
|
|
15
|
20 --score_matrices '$score_matrices'
|
|
0
|
21 #end if
|
|
|
22 #if str($options_type.options_type_selector) == 'advanced':
|
|
|
23 #if str($options_type.target_gene_family_assembly_cond.target_gene_family_assembly) == 'yes':
|
|
15
|
24 --gene_family_search '$options_type.target_gene_family_assembly_cond.orthogroups'
|
|
21
|
25 --scaffold '$options_type.target_gene_family_assembly_cond.scaffold.fields.path'
|
|
15
|
26 --method '$options_type.target_gene_family_assembly_cond.method'
|
|
0
|
27 #end if
|
|
|
28 --gap_trimming $options_type.gap_trimming
|
|
|
29 #if str($options_type.strand_specific) == 'yes':
|
|
|
30 --strand_specific
|
|
|
31 #end if
|
|
|
32 #if str($options_type.dereplicate) == 'yes':
|
|
|
33 --dereplicate
|
|
|
34 #end if
|
|
|
35 --min_length $options_type.min_length
|
|
|
36 #end if
|
|
|
37 --num_threads \${GALAXY_SLOTS:-4}
|
|
25
|
38 >/dev/null
|
|
0
|
39 ]]>
|
|
|
40 </command>
|
|
|
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"/>
|
|
0
|
68 <param name="scaffold" type="select" label="Orthogroups or gene families proteins scaffold">
|
|
|
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>
|
|
|
77 </when>
|
|
|
78 </conditional>
|
|
28
|
79 <param name="gap_trimming" type="float" value="0.1" min="0" max="1.0" label="Trim alignments"/>
|
|
|
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>
|
|
|
93 <collection name="transcripts" type="list">
|
|
1
|
94 <discover_datasets pattern="__name__" directory="assemblyPostProcessing_dir" visible="true" ext="fasta" />
|
|
0
|
95 </collection>
|
|
|
96 </outputs>
|
|
|
97 <tests>
|
|
|
98 <test>
|
|
|
99 <param name="input" value="assembly.fasta" ftype="fasta" />
|
|
|
100 <param name="prediction_method" value="transdecoder" />
|
|
6
|
101 <output_collection name="transcripts" type="list">
|
|
15
|
102 <element name="transcripts.cds" file="transcripts.cds" ftype="fasta"/>
|
|
|
103 <element name="transcripts.cleaned.cds" file="transcripts.cleaned.cds" ftype="fasta"/>
|
|
16
|
104 <element name="transcripts.cleaned.pep" file="transcripts.cleaned.pep" ftype="fasta"/>
|
|
15
|
105 <element name="transcripts.pep" file="transcripts.pep" ftype="fasta"/>
|
|
6
|
106 </output_collection>
|
|
|
107 </test>
|
|
|
108 <test>
|
|
|
109 <param name="input" value="assembly.fasta" ftype="fasta" />
|
|
|
110 <param name="prediction_method" value="transdecoder" />
|
|
0
|
111 <param name="options_type_selector" value="advanced" />
|
|
7
|
112 <param name="gap_trimming" value="0.1" />
|
|
0
|
113 <param name="dereplicate" value="yes" />
|
|
7
|
114 <param name="min_length" value="200" />
|
|
0
|
115 <output_collection name="transcripts" type="list">
|
|
16
|
116 <element name="transcripts.cds" file="transcripts.cds" ftype="fasta"/>
|
|
|
117 <element name="transcripts.cleaned.cds" file="transcripts.cleaned.cds" ftype="fasta"/>
|
|
|
118 <element name="transcripts.cleaned.nr.cds" file="transcripts.cleaned.nr.cds" ftype="fasta"/>
|
|
|
119 <element name="transcripts.cleaned.nr.pep" file="transcripts.cleaned.nr.pep" ftype="fasta"/>
|
|
|
120 <element name="transcripts.cleaned.pep" file="transcripts.cleaned.pep" ftype="fasta"/>
|
|
|
121 <element name="transcripts.pep" file="transcripts.pep" ftype="fasta"/>
|
|
0
|
122 </output_collection>
|
|
|
123 </test>
|
|
|
124 </tests>
|
|
|
125 <help>
|
|
28
|
126 This tool is one of the PlantTribes' collection of automated modular analysis pipelines for comparative and
|
|
|
127 evolutionary analyses of genome-scale gene families and transcriptomes. This tool post-processes de novo
|
|
|
128 assembled transcripts into putative coding sequences and their corresponding amino acid translations and
|
|
|
129 optionally assigns transcripts to circumscribed gene families ("orthogroups")[2]. After transcripts have been
|
|
|
130 assigned to gene families, overlapping contigs can be identified and merged to reduce fragmentation in the
|
|
|
131 de novo assembly.
|
|
0
|
132
|
|
|
133 -----
|
|
|
134
|
|
28
|
135 **Required options**
|
|
|
136
|
|
|
137 * **Transcriptome assembly fasta file** - either de novo or reference-guided transcriptome assembly fasta file selected from your history.
|
|
|
138 * **Coding regions prediction method** - method for finding coding recions within transcripts. Available methods are TransDecoder[3] and ESTScan[4].
|
|
|
139 * **Scores matrices** - Scores matrices, based on a related species, are required when ESTScan is ued 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.
|
|
|
140
|
|
|
141 **Other options**
|
|
0
|
142
|
|
28
|
143 * **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].
|
|
|
144 * **Targeted gene families** - A selected history item containing a list of targeted orthogroup identifiers corresponding to the gene family classification from a specified scaffold. Gene 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.
|
|
|
145 * **Gene family scaffold** - one of the PlantTribes gene family scaffolds (installed into Galaxy by the PlantTribes Scaffolds Download Data Manager tool) whose orthogroups(s) are targeted for the localized assembly.
|
|
|
146 * **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.
|
|
|
147 * **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 backbones gene models. The default setting of 0.1 removes sites tha thave gaps in 90% of the sequences in the multiple sequence alignment. This option is restricted to the range 0.0 - 1.0.
|
|
|
148 * **Strand-specific assembly?** - select 'Yes' if transcriptome library sequences were strand-specific. If 'Yes" is selected, transcripts from the minority strand (antisense) are removed.
|
|
|
149 * **Remove duplicate sequences?** - select 'Yes' to remove duplicated and exact subsequences[12].
|
|
|
150 * **Minimum sequence length** - set the minimum sequence length of predicted coding regions. The default is 200 bp.
|
|
0
|
151
|
|
|
152 </help>
|
|
|
153 <citations>
|
|
24
|
154 <citation type="bibtex">
|
|
|
155 @unpublished{None,
|
|
28
|
156 key = {1},
|
|
24
|
157 author = {Eric Wafula},
|
|
28
|
158 title = {Manuscript in preparation},
|
|
24
|
159 year = {None},
|
|
|
160 url = {https://github.com/dePamphilis/PlantTribes}
|
|
28
|
161 }
|
|
|
162 </citation>
|
|
|
163 <citation type="bibtex">
|
|
|
164 @published{PloS one,
|
|
|
165 key = {2},
|
|
|
166 author = {Honaas, L.A., Wafula, E.K., Wickett, N.J., Der, J.P., Zhang, Y., Edger, P.P., Altman, N.S., Pires, J.C. and Leebens-Mack, J.H.},
|
|
|
167 title = {Selecting superior de novo transcriptome assemblies: lessons learned by leveraging the best plant genome},
|
|
|
168 year = {2016},
|
|
|
169 volume = {11},
|
|
|
170 number = {1},
|
|
|
171 pages = {e0146062}
|
|
|
172 }
|
|
|
173 </citation>
|
|
24
|
174 <citation type="bibtex">
|
|
28
|
175 @published{Nature protocols,
|
|
|
176 key = {3},
|
|
|
177 author = {Haas, B.J., Papanicolaou, A., Yassour, M., Grabherr, M., Blood, P.D., Bowden, J., Couger, M.B., Eccles, D., Li, B., Lieber, M. and MacManes, M.D.},
|
|
|
178 title = {De novo transcript sequence reconstruction from RNA-seq using the Trinity platform for reference generation and analysis},
|
|
|
179 year = {2013},
|
|
|
180 volume = {8},
|
|
|
181 number = {8},
|
|
|
182 pages = {1494-1512}
|
|
|
183 }
|
|
|
184 </citation>
|
|
|
185 <citation type="bibtex">
|
|
|
186 @published{ISMB,
|
|
|
187 key = {4},
|
|
24
|
188 author = {Iseli C, Jongeneel CV, Bucher P.},
|
|
|
189 title = {ESTScan: a program for detecting, evaluating, and reconstructing potential coding regions in EST sequences.},
|
|
|
190 year = {1999},
|
|
28
|
191 volume = {99},
|
|
|
192 pages = {138-148}
|
|
|
193 url = {http://estscan.sourceforge.net}
|
|
|
194 }
|
|
|
195 </citation>
|
|
|
196 <citation type="bibtex">
|
|
|
197 @published{Genome research,
|
|
|
198 key = {5},
|
|
|
199 author = {Huang X, Madan A},
|
|
|
200 title = {CAP3: A DNA sequence assembly program},
|
|
|
201 year = {1999},
|
|
|
202 volume = {9},
|
|
|
203 number = {9},
|
|
|
204 pages = {868-877}
|
|
|
205 url = {http://seq.cs.iastate.edu/cap3.html}
|
|
|
206 }
|
|
|
207 </citation>
|
|
|
208 <citation type="bibtex">
|
|
|
209 @published{Genome Inform,
|
|
|
210 key = {6},
|
|
|
211 author = {Eddy, S.R.},
|
|
|
212 title = {A new generation of homology search tools based on probabilistic inference},
|
|
|
213 year = {2009},
|
|
|
214 volume = {23},
|
|
|
215 number = {1},
|
|
|
216 pages = {205-211}
|
|
|
217 }
|
|
|
218 </citation>
|
|
|
219 <citation type="bibtex">
|
|
|
220 @published{Nucleic acids research,
|
|
|
221 key = {7},
|
|
|
222 author = {Sasidharan, R., Nepusz, T., Swarbreck, D., Huala, E. and Paccanaro, A.},
|
|
|
223 title = {GFam: a platform for automatic annotation of gene families},
|
|
|
224 year = {2012},
|
|
|
225 pages = {gks631}
|
|
|
226 }
|
|
|
227 </citation>
|
|
|
228 <citation type="bibtex">
|
|
|
229 @published{Genome research,
|
|
|
230 key = {8},
|
|
|
231 author = {Li, L., Stoeckert, C.J. and Roos, D.S.},
|
|
|
232 title = {OrthoMCL: identification of ortholog groups for eukaryotic genomes},
|
|
|
233 year = {2003},
|
|
|
234 volume = {13},
|
|
|
235 number = {9},
|
|
|
236 pages = {2178-2189}
|
|
|
237 }
|
|
|
238 </citation>
|
|
|
239 <citation type="bibtex">
|
|
|
240 @published{Genome biology,
|
|
|
241 key = {9},
|
|
|
242 author = {Emms, D.M. and Kelly, S.},
|
|
|
243 title = {OrthoFinder: solving fundamental biases in whole genome comparisons dramatically improves orthogroup inference accuracy},
|
|
|
244 year = {2015},
|
|
|
245 volume = {16},
|
|
|
246 number = {1},
|
|
|
247 pages = {157}
|
|
|
248 }
|
|
|
249 </citation>
|
|
|
250 <citation type="bibtex">
|
|
|
251 @published{Bioinformatics,
|
|
|
252 key = {10},
|
|
|
253 author = {Capella-Gutiérrez, S., Silla-Martínez, J.M. and Gabaldón, T.},
|
|
|
254 title = {trimAl: a tool for automated alignment trimming in large-scale phylogenetic analyses},
|
|
|
255 year = {2009},
|
|
|
256 volume = {25},
|
|
|
257 number = {15},
|
|
|
258 pages = {1972-1973}
|
|
|
259 }
|
|
|
260 </citation>
|
|
|
261 <citation type="bibtex">
|
|
|
262 @published{IEEE/ACM Transactions on Computational Biology and Bioinformatics,
|
|
|
263 key = {11},
|
|
|
264 author = {Gremme, G., Steinbiss, S. and Kurtz, S.},
|
|
|
265 title = {GenomeTools: a comprehensive software library for efficient processing of structured genome annotations},
|
|
|
266 year = {2013},
|
|
|
267 volume = {10},
|
|
|
268 number = {3},
|
|
|
269 pages = {645-656}
|
|
|
270 }
|
|
|
271 </citation>
|
|
24
|
272 <citation type="bibtex">
|
|
|
273 @unpublished{None,
|
|
28
|
274 key = {12},
|
|
24
|
275 author = {None},
|
|
|
276 title = {HMMER 3.1+ hmmscan search sequence(s) against a profile database},
|
|
|
277 year = {2013},
|
|
|
278 url = {http://hmmer.org/}
|
|
28
|
279 }
|
|
|
280 </citation>
|
|
0
|
281 </citations>
|
|
|
282 </tool>
|
