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