8
|
1 <tool id="plant_tribes_gene_family_phylogeny_builder" name="GeneFamilyPhylogenyBuilder" version="@WRAPPER_VERSION@.3.1">
|
0
|
2 <description>builds phylogenetic trees of aligned orthologous gene family clusters</description>
|
|
3 <macros>
|
|
4 <import>macros.xml</import>
|
|
5 </macros>
|
6
|
6 <requirements>
|
|
7 <requirement type="package" version="1.0.3">plant_tribes_gene_family_phylogeny_builder</requirement>
|
|
8 </requirements>
|
0
|
9 <command detect_errors="exit_code"><![CDATA[
|
6
|
10 #set input_dir = 'input_dir'
|
0
|
11 #set tree_inference = $tree_inference_cond.tree_inference
|
|
12 #if str($tree_inference) == 'raxml':
|
6
|
13 #set scaffold = $tree_inference_cond.scaffold
|
|
14 #set method = $tree_inference_cond.method
|
0
|
15 #set rooting_order_file_cond = $tree_inference_cond.rooting_order_file_cond
|
|
16 #set rooting_order_file = $rooting_order_file_cond.rooting_order_file
|
|
17 #if str($rooting_order_file) == 'yes':
|
|
18 #set rooting_order = $rooting_order_file_cond.rooting_order
|
|
19 #end if
|
|
20 #set bootstrap_replicates = $tree_inference_cond.bootstrap_replicates
|
|
21 #end if
|
6
|
22 mkdir $input_dir &&
|
|
23 #for $i in $input:
|
|
24 #set filename = $i.file_name
|
|
25 #set name = $i.name
|
|
26 ln -s $filename $input_dir/$name &&
|
|
27 #end for
|
5
|
28 GeneFamilyPhylogenyBuilder
|
6
|
29 --orthogroup_aln '$input_dir'
|
0
|
30 --tree_inference $tree_inference
|
|
31 #if str($tree_inference) == 'raxml':
|
6
|
32 --scaffold '$scaffold.fields.path'
|
|
33 --config_dir '$scaffold.fields.path'
|
|
34 --method $method
|
0
|
35 #if str($rooting_order_file) == 'yes':
|
|
36 --rooting_order '$rooting_order'
|
|
37 ## No else block needed here because the default rooting_order
|
|
38 ## configuration will be used if the --rooting_order flag is missing.
|
|
39 #end if
|
|
40 --bootstrap_replicates $bootstrap_replicates
|
|
41 #end if
|
|
42 --min_orthogroup_size $min_orthogroup_size
|
|
43 --max_orthogroup_size $max_orthogroup_size
|
|
44 --num_threads \${GALAXY_SLOTS:-4}
|
7
|
45 &>gene_family_phylogeny_builder_log.txt;
|
|
46 if [[ $? -ne 0 ]]; then
|
|
47 find geneFamilyPhylogenies_dir -type d -maxdepth 1 -exec cp gene_family_phylogeny_builder_log.txt {} \;
|
|
48 exit 1;
|
|
49 fi
|
0
|
50 ]]></command>
|
|
51 <inputs>
|
6
|
52 <param name="input" format="fasta" type="data_collection" collection_type="list" label="Proteins orthogroup alignments" />
|
0
|
53 <conditional name="tree_inference_cond">
|
|
54 <param name="tree_inference" type="select" label="Phylogenetic inference method">
|
|
55 <option value="raxml" selected="true">RAxML</option>
|
|
56 <option value="fasttree">FastTree</option>
|
|
57 </param>
|
|
58 <when value="raxml">
|
6
|
59 <expand macro="param_scaffold" />
|
|
60 <expand macro="param_method" />
|
0
|
61 <conditional name="rooting_order_file_cond">
|
|
62 <param name="rooting_order_file" type="select" label="Rooting order configuration">
|
|
63 <option value="no" selected="true">No</option>
|
|
64 <option value="yes">Yes</option>
|
|
65 </param>
|
|
66 <when value="no" />
|
|
67 <when value="yes">
|
|
68 <param name="rooting_order" format="txt" type="data" label="Rooting order configuration" />
|
|
69 </when>
|
|
70 </conditional>
|
|
71 <param name="bootstrap_replicates" type="integer" value="100" min="0" label="Bootstrap replicates" />
|
|
72 </when>
|
|
73 <when value="fasttree" />
|
|
74 </conditional>
|
|
75 <param name="max_orthogroup_size" type="integer" value="100" min="4" label="Maximum orthogroup size" />
|
|
76 <param name="min_orthogroup_size" type="integer" value="4" min="4" label="Minimum orthogroup size" />
|
|
77 </inputs>
|
|
78 <outputs>
|
5
|
79 <collection name="tree" type="list" label="${tool.name} (phylogenetic trees) on ${on_string}">
|
8
|
80 <discover_datasets pattern="__name__" directory="geneFamilyPhylogenies_dir/orthogroups_tree" format="newick" />
|
0
|
81 </collection>
|
5
|
82 <collection name="phylip" type="list" label="${tool.name} (orthogroup phylip multiple sequence alignments) on ${on_string}">
|
0
|
83 <filter>tree_inference_cond['tree_inference'] == 'raxml'</filter>
|
5
|
84 <discover_datasets pattern="__name__" directory="geneFamilyPhylogenies_dir/phylip_aln" format="phylip" />
|
|
85 </collection>
|
0
|
86 </outputs>
|
|
87 <tests>
|
|
88 <test>
|
6
|
89 <param name="input">
|
|
90 <collection type="list">
|
|
91 <element name="3722.faa.aln" value="3722.faa.aln"/>
|
|
92 </collection>
|
|
93 </param>
|
|
94 <param name="tree_inference" value="fasttree"/>
|
|
95 <output_collection name="tree" type="list">
|
8
|
96 <element name="3722.faa.aln.tree" file="3722.faa.aln.tree" ftype="newick"/>
|
6
|
97 </output_collection>
|
0
|
98 </test>
|
|
99 </tests>
|
|
100 <help>
|
|
101 This tool is one of the PlantTribes collection of automated modular analysis pipelines for comparative and evolutionary
|
|
102 analyses of genome-scale gene families and transcriptomes. This tool performs gene family phylogenetic inference of
|
|
103 multiple sequence alignments produced by the GeneFamilyAligner tool.
|
|
104
|
|
105 -----
|
|
106
|
|
107 **Required options**
|
|
108
|
|
109 * **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.
|
|
110 * **Phylogenetic inference method** - method for estimating orthogroup maximum likelihood (ML) phylogenetic trees. PlantTribes estimates ML phylogenetic trees using either RAxML or FastTree algorithms.
|
|
111
|
6
|
112 - **Gene family scaffold** - one of the PlantTribes gene family scaffolds installed into Galaxy by the PlantTribes Scaffold Download Data Manager tool. This is used only if RAxML is selected as the phylogenetic inference method.
|
|
113 - **Protein clustering method** - gene family scaffold protein clustering method as described in the AssemblyPostProcessor tool. This is used only if RAxML is selected as the phylogenetic inference method.
|
|
114
|
0
|
115 **Other options**
|
|
116
|
|
117 * **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.
|
|
118 * **Bootstrap replicates** - number of bootstrap replicates for RAxML to conduct a rapid bootstrap analysis and search for the best-scoring ML tree (default = 100).
|
|
119 * **Maximum orthogroup size** - maximum number of sequences allowed in orthogroup alignments (default = 100).
|
|
120 * **Minimum orthogroup size** - minimum number of sequences allowed in orthogroup alignments (default = 4).
|
|
121
|
|
122 .. _repository: https://github.com/dePamphilis/PlantTribes/tree/master/config
|
|
123
|
|
124 </help>
|
|
125 <citations>
|
|
126 <expand macro="citation1" />
|
|
127 <citation type="bibtex">
|
|
128 @article{Wall2008,
|
|
129 journal = {Nucleic Acids Research},
|
|
130 author = {2. Wall PK, Leebens-Mack J, Muller KF, Field D, Altman NS},
|
|
131 title = {PlantTribes: a gene and gene family resource for comparative genomics in plants},
|
|
132 year = {2008},
|
|
133 volume = {36},
|
|
134 number = {suppl 1},
|
|
135 pages = {D970-D976},}
|
|
136 </citation>
|
|
137 <citation type="bibtex">
|
|
138 @article{Sasidharan2012,
|
|
139 journal = {Nucleic Acids Research},
|
|
140 author = {3. Sasidharan R, Nepusz T, Swarbreck D, Huala E, Paccanaro A},
|
|
141 title = {GFam: a platform for automatic annotation of gene families},
|
|
142 year = {2012},
|
|
143 pages = {gks631},}
|
|
144 </citation>
|
|
145 <citation type="bibtex">
|
|
146 @article{Li2003,
|
|
147 journal = {Genome Research}
|
|
148 author = {4. Li L, Stoeckert CJ, Roos DS},
|
|
149 title = {OrthoMCL: identification of ortholog groups for eukaryotic genomes},
|
|
150 year = {2003},
|
|
151 volume = {13},
|
|
152 number = {9},
|
|
153 pages = {2178-2189},}
|
|
154 </citation>
|
|
155 <citation type="bibtex">
|
|
156 @article{Emms2015,
|
|
157 journal = {Genome Biology}
|
|
158 author = {5. Emms DM, Kelly S},
|
|
159 title = {OrthoFinder: solving fundamental biases in whole genome comparisons dramatically improves orthogroup inference accuracy},
|
|
160 year = {2015},
|
|
161 volume = {16},
|
|
162 number = {1},
|
|
163 pages = {157},}
|
|
164 </citation>
|
|
165 <citation type="bibtex">
|
|
166 @article{Stamatakis2014,
|
|
167 journal = {Bioinformatics},
|
|
168 author = {6. Stamatakis A},
|
|
169 title = {RAxML Version 8: A tool for Phylogenetic Analysis and Post-Analysis of Large Phylogenies},
|
|
170 year = {2014},
|
|
171 url = {http://sco.h-its.org/exelixis/web/software/raxml/index.html},}
|
|
172 </citation>
|
|
173 <citation type="bibtex">
|
|
174 @article{Price2010,
|
|
175 journal = {PLoS one},
|
|
176 author = {7. Price MN, Dehal PS, Arkin AP},
|
|
177 title = {FastTree 2-approximately maximim-likelihood trees for large alignments},
|
|
178 year = {2010},
|
|
179 volume = {5},
|
|
180 number = {3},
|
|
181 pages = {e9490},}
|
|
182 </citation>
|
2
|
183 <citation type="bibtex">
|
|
184 @article{Nascimento2016,
|
|
185 journal = {Bioinformatics},
|
|
186 author = {8. Nascimento M, Sousa A, Ramirez M, Francisco AP, CarriƧo JA, Vaz C},
|
|
187 title = {PHYLOViZ 2.0: providing scalable data integration and visualization for multiple phylogenetic inference methods},
|
|
188 year = {2016},
|
|
189 volume = {33},
|
|
190 number = {1},
|
|
191 pages = {128-129},}
|
|
192 </citation>
|
0
|
193 </citations>
|
|
194 </tool>
|