46
|
1 <tool id="plant_tribes_gene_family_phylogeny_builder" name="GeneFamilyPhylogenyBuilder" version="@WRAPPER_VERSION@.3.0">
|
6
|
2 <description>builds phylogenetic trees of aligned orthologous gene family clusters</description>
|
0
|
3 <macros>
|
|
4 <import>macros.xml</import>
|
|
5 </macros>
|
|
6 <expand macro="requirements_gene_family_phylogeny_builder" />
|
38
|
7 <command detect_errors="exit_code"><![CDATA[
|
46
|
8 #set input_dir = 'input_dir'
|
38
|
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
|
46
|
18 mkdir $input_dir &&
|
47
|
19 #for $i in $input:
|
|
20 #set filename = $i.filename
|
46
|
21 ln -s $filename $input_dir
|
|
22 #end for
|
43
|
23 GeneFamilyPhylogenyBuilder
|
46
|
24 --orthogroup_aln '$input_dir'
|
38
|
25 --scaffold '$scaffold.fields.path'
|
|
26 --config_dir '$scaffold.fields.path'
|
|
27 --method $method
|
|
28 --tree_inference $tree_inference
|
|
29 #if str($tree_inference) == 'raxml':
|
|
30 #if str($rooting_order_file) == 'yes':
|
|
31 --rooting_order '$rooting_order'
|
|
32 ## No else block needed here because the default rooting_order
|
|
33 ## configuration will be used if the --rooting_order flag is missing.
|
|
34 #end if
|
|
35 --bootstrap_replicates $bootstrap_replicates
|
|
36 #end if
|
|
37 --min_orthogroup_size $min_orthogroup_size
|
|
38 --max_orthogroup_size $max_orthogroup_size
|
|
39 --num_threads \${GALAXY_SLOTS:-4}
|
|
40 ]]></command>
|
0
|
41 <inputs>
|
46
|
42 <param name="input" format="fasta" type="data_collection" collection_type="list" label="Proteins orthogroup alignments" />
|
0
|
43 <expand macro="param_scaffold" />
|
|
44 <expand macro="param_method" />
|
|
45 <conditional name="tree_inference_cond">
|
6
|
46 <param name="tree_inference" type="select" label="Phylogenetic inference method">
|
0
|
47 <option value="raxml" selected="true">RAxML</option>
|
|
48 <option value="fasttree">FastTree</option>
|
|
49 </param>
|
|
50 <when value="raxml">
|
|
51 <conditional name="rooting_order_file_cond">
|
7
|
52 <param name="rooting_order_file" type="select" label="Rooting order configuration">
|
0
|
53 <option value="no" selected="true">No</option>
|
|
54 <option value="yes">Yes</option>
|
|
55 </param>
|
|
56 <when value="no" />
|
|
57 <when value="yes">
|
11
|
58 <param name="rooting_order" format="txt" type="data" label="Rooting order configuration" />
|
0
|
59 </when>
|
|
60 </conditional>
|
6
|
61 <param name="bootstrap_replicates" type="integer" value="100" min="0" label="Bootstrap replicates" />
|
0
|
62 </when>
|
|
63 <when value="fasttree" />
|
|
64 </conditional>
|
27
|
65 <param name="max_orthogroup_size" type="integer" value="100" min="4" label="Maximum orthogroup size" />
|
|
66 <param name="min_orthogroup_size" type="integer" value="4" min="4" label="Minimum orthogroup size" />
|
0
|
67 </inputs>
|
|
68 <outputs>
|
43
|
69 <collection name="tree" type="list" label="${tool.name} (phylogenetic trees) on ${on_string}">
|
29
|
70 <discover_datasets pattern="__name__" directory="geneFamilyPhylogenies_dir/orthogroups_tree" format="nhx" />
|
|
71 </collection>
|
43
|
72 <collection name="phylip" type="list" label="${tool.name} (orthogroup phylip multiple sequence alignments) on ${on_string}">
|
25
|
73 <filter>tree_inference_cond['tree_inference'] == 'raxml'</filter>
|
43
|
74 <discover_datasets pattern="__name__" directory="geneFamilyPhylogenies_dir/phylip_aln" format="phylip" />
|
|
75 </collection>
|
0
|
76 </outputs>
|
|
77 <tests>
|
|
78 <test>
|
|
79 </test>
|
|
80 </tests>
|
|
81 <help>
|
6
|
82 This tool is one of the PlantTribes collection of automated modular analysis pipelines for comparative and evolutionary
|
|
83 analyses of genome-scale gene families and transcriptomes. This tool performs gene family phylogenetic inference of
|
|
84 multiple sequence alignments produced by the GeneFamilyAligner tool.
|
0
|
85
|
|
86 -----
|
|
87
|
|
88 **Required options**
|
|
89
|
6
|
90 * **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.
|
|
91 * **Gene family scaffold** - one of the PlantTribes gene family scaffolds installed into Galaxy by the PlantTribes Scaffold Download Data Manager tool.
|
11
|
92 * **Protein clustering method** - gene family scaffold protein clustering method as described in the AssemblyPostProcessor tool.
|
6
|
93 * **Phylogenetic inference method** - method for estimating orthogroup maximum likelihood (ML) phylogenetic trees. PlantTribes estimates ML phylogenetic trees using either RAxML or FastTree algorithms.
|
|
94
|
0
|
95 **Other options**
|
|
96
|
7
|
97 * **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.
|
6
|
98 * **Bootstrap replicates** - number of bootstrap replicates for RAxML to conduct a rapid bootstrap analysis and search for the best-scoring ML tree (default = 100).
|
11
|
99 * **Maximum orthogroup size** - maximum number of sequences allowed in orthogroup alignments (default = 100).
|
|
100 * **Minimum orthogroup size** - minimum number of sequences allowed in orthogroup alignments (default = 4).
|
36
|
101 * **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).
|
6
|
102
|
9
|
103 .. _repository: https://github.com/dePamphilis/PlantTribes/tree/master/config
|
|
104
|
0
|
105 </help>
|
|
106 <citations>
|
|
107 <expand macro="citation1" />
|
6
|
108 <citation type="bibtex">
|
|
109 @article{Wall2008,
|
|
110 journal = {Nucleic Acids Research},
|
|
111 author = {2. Wall PK, Leebens-Mack J, Muller KF, Field D, Altman NS},
|
|
112 title = {PlantTribes: a gene and gene family resource for comparative genomics in plants},
|
|
113 year = {2008},
|
|
114 volume = {36},
|
|
115 number = {suppl 1},
|
|
116 pages = {D970-D976},}
|
|
117 </citation>
|
|
118 <citation type="bibtex">
|
|
119 @article{Sasidharan2012,
|
|
120 journal = {Nucleic Acids Research},
|
|
121 author = {3. Sasidharan R, Nepusz T, Swarbreck D, Huala E, Paccanaro A},
|
|
122 title = {GFam: a platform for automatic annotation of gene families},
|
|
123 year = {2012},
|
|
124 pages = {gks631},}
|
|
125 </citation>
|
|
126 <citation type="bibtex">
|
|
127 @article{Li2003,
|
|
128 journal = {Genome Research}
|
|
129 author = {4. Li L, Stoeckert CJ, Roos DS},
|
|
130 title = {OrthoMCL: identification of ortholog groups for eukaryotic genomes},
|
|
131 year = {2003},
|
|
132 volume = {13},
|
|
133 number = {9},
|
|
134 pages = {2178-2189},}
|
|
135 </citation>
|
|
136 <citation type="bibtex">
|
|
137 @article{Emms2015,
|
|
138 journal = {Genome Biology}
|
|
139 author = {5. Emms DM, Kelly S},
|
|
140 title = {OrthoFinder: solving fundamental biases in whole genome comparisons dramatically improves orthogroup inference accuracy},
|
|
141 year = {2015},
|
|
142 volume = {16},
|
|
143 number = {1},
|
|
144 pages = {157},}
|
|
145 </citation>
|
|
146 <citation type="bibtex">
|
|
147 @article{Stamatakis2014,
|
|
148 journal = {Bioinformatics},
|
|
149 author = {6. Stamatakis A},
|
|
150 title = {RAxML Version 8: A tool for Phylogenetic Analysis and Post-Analysis of Large Phylogenies},
|
|
151 year = {2014},
|
|
152 url = {http://sco.h-its.org/exelixis/web/software/raxml/index.html},}
|
|
153 </citation>
|
|
154 <citation type="bibtex">
|
|
155 @article{Price2010,
|
|
156 journal = {PLoS one},
|
|
157 author = {7. Price MN, Dehal PS, Arkin AP},
|
|
158 title = {FastTree 2-approximately maximim-likelihood trees for large alignments},
|
|
159 year = {2010},
|
|
160 volume = {5},
|
|
161 number = {3},
|
|
162 pages = {e9490},}
|
|
163 </citation>
|
40
|
164 <citation type="bibtex">
|
|
165 @article{Nascimento2016,
|
|
166 journal = {Bioinformatics},
|
|
167 author = {8. Nascimento M, Sousa A, Ramirez M, Francisco AP, CarriƧo JA, Vaz C},
|
|
168 title = {PHYLOViZ 2.0: providing scalable data integration and visualization for multiple phylogenetic inference methods},
|
|
169 year = {2016},
|
|
170 volume = {33},
|
|
171 number = {1},
|
|
172 pages = {128-129},}
|
|
173 </citation>
|
0
|
174 </citations>
|
|
175 </tool>
|