|
5
|
1 <tool id="plant_tribes_gene_family_phylogeny_builder" name="GeneFamilyPhylogenyBuilder" version="@WRAPPER_VERSION@.2.1">
|
|
0
|
2 <description>builds phylogenetic trees of aligned orthologous gene family clusters</description>
|
|
|
3 <macros>
|
|
|
4 <import>macros.xml</import>
|
|
|
5 </macros>
|
|
|
6 <expand macro="requirements_gene_family_phylogeny_builder" />
|
|
|
7 <command detect_errors="exit_code"><![CDATA[
|
|
|
8 #set input_format = $input_format_cond.input_format
|
|
|
9 #set tree_inference = $tree_inference_cond.tree_inference
|
|
|
10 #if str($tree_inference) == 'raxml':
|
|
|
11 #set rooting_order_file_cond = $tree_inference_cond.rooting_order_file_cond
|
|
|
12 #set rooting_order_file = $rooting_order_file_cond.rooting_order_file
|
|
|
13 #if str($rooting_order_file) == 'yes':
|
|
|
14 #set rooting_order = $rooting_order_file_cond.rooting_order
|
|
|
15 #end if
|
|
|
16 #set bootstrap_replicates = $tree_inference_cond.bootstrap_replicates
|
|
|
17 #end if
|
|
|
18
|
|
5
|
19 GeneFamilyPhylogenyBuilder
|
|
0
|
20 #if str($input_format) == 'ptalign':
|
|
|
21 --orthogroup_aln '$input_format_cond.input_ptalign.extra_files_path'
|
|
1
|
22 --alignment_type aln
|
|
|
23 --sequence_type protein
|
|
0
|
24 #else if str($input_format) == 'ptalignca':
|
|
|
25 --orthogroup_aln '$input_format_cond.input_ptalignca.extra_files_path'
|
|
1
|
26 --alignment_type aln
|
|
0
|
27 --sequence_type $input_format_cond.sequence_type
|
|
|
28 #else if str($input_format) == 'ptalignfiltered':
|
|
|
29 --orthogroup_aln '$input_format_cond.input_ptalignfiltered.extra_files_path'
|
|
1
|
30 --alignment_type filter
|
|
|
31 --sequence_type protein
|
|
0
|
32 #else if str($input_format) == 'ptalignfilteredca':
|
|
|
33 --orthogroup_aln '$input_format_cond.input_ptalignfilteredca.extra_files_path'
|
|
1
|
34 --alignment_type filter
|
|
0
|
35 --sequence_type $input_format_cond.sequence_type
|
|
|
36 #else if str($input_format) == 'ptaligntrimmed':
|
|
|
37 --orthogroup_aln '$input_format_cond.input_ptaligntrimmed.extra_files_path'
|
|
1
|
38 --alignment_type trim
|
|
|
39 --sequence_type protein
|
|
0
|
40 #else if str($input_format) == 'ptaligntrimmedca':
|
|
|
41 --orthogroup_aln '$input_format_cond.input_ptaligntrimmedca.extra_files_path'
|
|
1
|
42 --alignment_type trim
|
|
0
|
43 --sequence_type $input_format_cond.sequence_type
|
|
|
44 #end if
|
|
|
45 --scaffold '$scaffold.fields.path'
|
|
|
46 --config_dir '$scaffold.fields.path'
|
|
|
47 --method $method
|
|
|
48 --tree_inference $tree_inference
|
|
|
49 #if str($tree_inference) == 'raxml':
|
|
|
50 #if str($rooting_order_file) == 'yes':
|
|
|
51 --rooting_order '$rooting_order'
|
|
|
52 ## No else block needed here because the default rooting_order
|
|
|
53 ## configuration will be used if the --rooting_order flag is missing.
|
|
|
54 #end if
|
|
|
55 --bootstrap_replicates $bootstrap_replicates
|
|
|
56 #end if
|
|
|
57 --min_orthogroup_size $min_orthogroup_size
|
|
|
58 --max_orthogroup_size $max_orthogroup_size
|
|
|
59 --num_threads \${GALAXY_SLOTS:-4}
|
|
|
60 ]]></command>
|
|
|
61 <inputs>
|
|
|
62 <conditional name="input_format_cond">
|
|
|
63 <param name="input_format" type="select" label="Orthogroup alignments">
|
|
|
64 <option value="ptalign">Proteins orthogroup alignments</option>
|
|
|
65 <option value="ptalignca">Protein and coding sequences orthogroup alignments</option>
|
|
|
66 <option value="ptalignfiltered">Filtered proteins orthogroup alignments</option>
|
|
|
67 <option value="ptalignfilteredca">Filtered protein and coding sequences orthogroup alignments</option>
|
|
|
68 <option value="ptaligntrimmed">Trimmed proteins orthogroup alignments</option>
|
|
|
69 <option value="ptaligntrimmedca">Trimmed protein and coding sequences orthogroup alignments</option>
|
|
|
70 </param>
|
|
|
71 <when value="ptalign">
|
|
|
72 <param name="input_ptalign" format="ptalign" type="data" label="Proteins orthogroup alignments">
|
|
|
73 <validator type="empty_extra_files_path" />
|
|
|
74 </param>
|
|
|
75 </when>
|
|
|
76 <when value="ptalignca">
|
|
|
77 <param name="input_ptalignca" format="ptalignca" type="data" label="Protein and coding sequences orthogroup alignments">
|
|
|
78 <validator type="empty_extra_files_path" />
|
|
|
79 </param>
|
|
|
80 <expand macro="param_sequence_type" />
|
|
|
81 </when>
|
|
|
82 <when value="ptalignfiltered">
|
|
|
83 <param name="input_ptalignfiltered" format="ptalignfiltered" type="data" label="Filtered proteins orthogroup alignments">
|
|
|
84 <validator type="empty_extra_files_path" />
|
|
|
85 </param>
|
|
|
86 </when>
|
|
|
87 <when value="ptalignfilteredca">
|
|
|
88 <param name="input_ptalignfilteredca" format="ptalignfilteredca" type="data" label="Filtered protein and coding sequences orthogroup alignments">
|
|
|
89 <validator type="empty_extra_files_path" />
|
|
|
90 </param>
|
|
|
91 <expand macro="param_sequence_type" />
|
|
|
92 </when>
|
|
|
93 <when value="ptaligntrimmed">
|
|
|
94 <param name="input_ptaligntrimmed" format="ptaligntrimmed" type="data" label="Trimmed proteins orthogroup alignments">
|
|
|
95 <validator type="empty_extra_files_path" />
|
|
|
96 </param>
|
|
|
97 </when>
|
|
|
98 <when value="ptaligntrimmedca">
|
|
|
99 <param name="input_ptaligntrimmedca" format="ptaligntrimmedca" type="data" label="Trimmed protein and coding sequences orthogroup alignments">
|
|
|
100 <validator type="empty_extra_files_path" />
|
|
|
101 </param>
|
|
|
102 <expand macro="param_sequence_type" />
|
|
|
103 </when>
|
|
|
104 </conditional>
|
|
|
105 <expand macro="param_scaffold" />
|
|
|
106 <expand macro="param_method" />
|
|
|
107 <conditional name="tree_inference_cond">
|
|
|
108 <param name="tree_inference" type="select" label="Phylogenetic inference method">
|
|
|
109 <option value="raxml" selected="true">RAxML</option>
|
|
|
110 <option value="fasttree">FastTree</option>
|
|
|
111 </param>
|
|
|
112 <when value="raxml">
|
|
|
113 <conditional name="rooting_order_file_cond">
|
|
|
114 <param name="rooting_order_file" type="select" label="Rooting order configuration">
|
|
|
115 <option value="no" selected="true">No</option>
|
|
|
116 <option value="yes">Yes</option>
|
|
|
117 </param>
|
|
|
118 <when value="no" />
|
|
|
119 <when value="yes">
|
|
|
120 <param name="rooting_order" format="txt" type="data" label="Rooting order configuration" />
|
|
|
121 </when>
|
|
|
122 </conditional>
|
|
|
123 <param name="bootstrap_replicates" type="integer" value="100" min="0" label="Bootstrap replicates" />
|
|
|
124 </when>
|
|
|
125 <when value="fasttree" />
|
|
|
126 </conditional>
|
|
|
127 <param name="max_orthogroup_size" type="integer" value="100" min="4" label="Maximum orthogroup size" />
|
|
|
128 <param name="min_orthogroup_size" type="integer" value="4" min="4" label="Minimum orthogroup size" />
|
|
|
129 </inputs>
|
|
|
130 <outputs>
|
|
5
|
131 <collection name="tree" type="list" label="${tool.name} (phylogenetic trees) on ${on_string}">
|
|
0
|
132 <discover_datasets pattern="__name__" directory="geneFamilyPhylogenies_dir/orthogroups_tree" format="nhx" />
|
|
|
133 </collection>
|
|
5
|
134 <collection name="phylip" type="list" label="${tool.name} (orthogroup phylip multiple sequence alignments) on ${on_string}">
|
|
0
|
135 <filter>tree_inference_cond['tree_inference'] == 'raxml'</filter>
|
|
5
|
136 <discover_datasets pattern="__name__" directory="geneFamilyPhylogenies_dir/phylip_aln" format="phylip" />
|
|
|
137 </collection>
|
|
0
|
138 </outputs>
|
|
|
139 <tests>
|
|
|
140 <!-- Test framework does not currently support inputs whose associated extra_files_path contains files to be analyzed.
|
|
|
141 <test>
|
|
|
142 </test>
|
|
|
143 -->
|
|
|
144 </tests>
|
|
|
145 <help>
|
|
|
146 This tool is one of the PlantTribes collection of automated modular analysis pipelines for comparative and evolutionary
|
|
|
147 analyses of genome-scale gene families and transcriptomes. This tool performs gene family phylogenetic inference of
|
|
|
148 multiple sequence alignments produced by the GeneFamilyAligner tool.
|
|
|
149
|
|
|
150 -----
|
|
|
151
|
|
|
152 **Required options**
|
|
|
153
|
|
|
154 * **Orthogroup alignments** - orthogroup alignment fasta files produced by the GeneFamilyAligner tool selected from your history. Depending on how the GeneFamilyAligner tool was executed, these could either be pre-processed alignments, trimmed alignments or both trimmed and filtered alignments.
|
|
|
155 * **Gene family scaffold** - one of the PlantTribes gene family scaffolds installed into Galaxy by the PlantTribes Scaffold Download Data Manager tool.
|
|
|
156 * **Protein clustering method** - gene family scaffold protein clustering method as described in the AssemblyPostProcessor tool.
|
|
|
157 * **Phylogenetic inference method** - method for estimating orthogroup maximum likelihood (ML) phylogenetic trees. PlantTribes estimates ML phylogenetic trees using either RAxML or FastTree algorithms.
|
|
|
158
|
|
|
159 **Other options**
|
|
|
160
|
|
|
161 * **Rooting order configuration** - select 'Yes' to enable selection of a rooting order configuration file for RAxML. Scaffold configuration templates (.rootingOrder.config) of how to customize the RAxML ML tree rooting order can be found in the scaffold data installed into Galaxy via the PlantTribes Scaffolds Download Data Manager tool, and is also available at the PlantTribes GitHub `repository`_. Phylogenetic tree rooting order settings shown in these templates are used as defaults if 'No' is selected.
|
|
|
162 * **Bootstrap replicates** - number of bootstrap replicates for RAxML to conduct a rapid bootstrap analysis and search for the best-scoring ML tree (default = 100).
|
|
|
163 * **Maximum orthogroup size** - maximum number of sequences allowed in orthogroup alignments (default = 100).
|
|
|
164 * **Minimum orthogroup size** - minimum number of sequences allowed in orthogroup alignments (default = 4).
|
|
|
165 * **Output additional directory of phylogenetic tree files** - selecting 'Yes' will produce an additional output that has an associated directory of files that are copies of the elements of the phylogenetic trees output dataset collection (this output will be used for future downstream tools).
|
|
|
166
|
|
|
167 .. _repository: https://github.com/dePamphilis/PlantTribes/tree/master/config
|
|
|
168
|
|
|
169 </help>
|
|
|
170 <citations>
|
|
|
171 <expand macro="citation1" />
|
|
|
172 <citation type="bibtex">
|
|
|
173 @article{Wall2008,
|
|
|
174 journal = {Nucleic Acids Research},
|
|
|
175 author = {2. Wall PK, Leebens-Mack J, Muller KF, Field D, Altman NS},
|
|
|
176 title = {PlantTribes: a gene and gene family resource for comparative genomics in plants},
|
|
|
177 year = {2008},
|
|
|
178 volume = {36},
|
|
|
179 number = {suppl 1},
|
|
|
180 pages = {D970-D976},}
|
|
|
181 </citation>
|
|
|
182 <citation type="bibtex">
|
|
|
183 @article{Sasidharan2012,
|
|
|
184 journal = {Nucleic Acids Research},
|
|
|
185 author = {3. Sasidharan R, Nepusz T, Swarbreck D, Huala E, Paccanaro A},
|
|
|
186 title = {GFam: a platform for automatic annotation of gene families},
|
|
|
187 year = {2012},
|
|
|
188 pages = {gks631},}
|
|
|
189 </citation>
|
|
|
190 <citation type="bibtex">
|
|
|
191 @article{Li2003,
|
|
|
192 journal = {Genome Research}
|
|
|
193 author = {4. Li L, Stoeckert CJ, Roos DS},
|
|
|
194 title = {OrthoMCL: identification of ortholog groups for eukaryotic genomes},
|
|
|
195 year = {2003},
|
|
|
196 volume = {13},
|
|
|
197 number = {9},
|
|
|
198 pages = {2178-2189},}
|
|
|
199 </citation>
|
|
|
200 <citation type="bibtex">
|
|
|
201 @article{Emms2015,
|
|
|
202 journal = {Genome Biology}
|
|
|
203 author = {5. Emms DM, Kelly S},
|
|
|
204 title = {OrthoFinder: solving fundamental biases in whole genome comparisons dramatically improves orthogroup inference accuracy},
|
|
|
205 year = {2015},
|
|
|
206 volume = {16},
|
|
|
207 number = {1},
|
|
|
208 pages = {157},}
|
|
|
209 </citation>
|
|
|
210 <citation type="bibtex">
|
|
|
211 @article{Stamatakis2014,
|
|
|
212 journal = {Bioinformatics},
|
|
|
213 author = {6. Stamatakis A},
|
|
|
214 title = {RAxML Version 8: A tool for Phylogenetic Analysis and Post-Analysis of Large Phylogenies},
|
|
|
215 year = {2014},
|
|
|
216 url = {http://sco.h-its.org/exelixis/web/software/raxml/index.html},}
|
|
|
217 </citation>
|
|
|
218 <citation type="bibtex">
|
|
|
219 @article{Price2010,
|
|
|
220 journal = {PLoS one},
|
|
|
221 author = {7. Price MN, Dehal PS, Arkin AP},
|
|
|
222 title = {FastTree 2-approximately maximim-likelihood trees for large alignments},
|
|
|
223 year = {2010},
|
|
|
224 volume = {5},
|
|
|
225 number = {3},
|
|
|
226 pages = {e9490},}
|
|
|
227 </citation>
|
|
2
|
228 <citation type="bibtex">
|
|
|
229 @article{Nascimento2016,
|
|
|
230 journal = {Bioinformatics},
|
|
|
231 author = {8. Nascimento M, Sousa A, Ramirez M, Francisco AP, Carriço JA, Vaz C},
|
|
|
232 title = {PHYLOViZ 2.0: providing scalable data integration and visualization for multiple phylogenetic inference methods},
|
|
|
233 year = {2016},
|
|
|
234 volume = {33},
|
|
|
235 number = {1},
|
|
|
236 pages = {128-129},}
|
|
|
237 </citation>
|
|
0
|
238 </citations>
|
|
|
239 </tool>
|
