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