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