|
70
|
1 <tool id="plant_tribes_phylogenomics_analysis" name="PhylogenomicsAnalysis" version="0.6.0">
|
|
|
2 <description>builds gene family multiple sequence alignments and their corresponding phylogenies</description>
|
|
0
|
3 <requirements>
|
|
65
|
4 <requirement type="package" version="0.6">plant_tribes_phylogenomics_analysis</requirement>
|
|
0
|
5 </requirements>
|
|
|
6 <stdio>
|
|
|
7 <!-- Anything other than zero is an error -->
|
|
|
8 <exit_code range="1:" />
|
|
40
|
9 <exit_code range=":-1" />
|
|
|
10 <!-- In case the return code has not been set propery check stderr too -->
|
|
0
|
11 <regex match="Error:" />
|
|
|
12 <regex match="Exception:" />
|
|
|
13 </stdio>
|
|
|
14 <command>
|
|
|
15 <![CDATA[
|
|
42
|
16 #if str($options_type.options_type_selector) == 'advanced':
|
|
|
17 #set multiple_sequence_alignments_cond = $options_type.multiple_sequence_alignments_cond
|
|
|
18 #set multiple_sequence_alignments = $multiple_sequence_alignments_cond.multiple_sequence_alignments
|
|
|
19 #if str($multiple_sequence_alignments) == 'yes':
|
|
|
20 #set multiple_sequence_alignments_option_cond = $options_type.multiple_sequence_alignments_cond.multiple_sequence_alignments_option_cond
|
|
|
21 #set multiple_sequence_alignments_option = $multiple_sequence_alignments_option_cond.multiple_sequence_alignments_option
|
|
|
22 #set generate_output_aln = True
|
|
|
23 #else:
|
|
|
24 #set generate_output_aln = False
|
|
|
25 #end if
|
|
67
|
26 #if str($options_type.phylogenetic_trees_cond.phylogenetic_trees) == 'yes':
|
|
|
27 #set generate_output_tree = True
|
|
|
28 #else:
|
|
|
29 #set generate_output_tree = False
|
|
|
30 #end if
|
|
48
|
31 #else:
|
|
|
32 #set generate_output_aln = False
|
|
14
|
33 #set generate_output_tree = False
|
|
|
34 #end if
|
|
|
35
|
|
65
|
36 python $__tool_directory__/phylogenomics_analysis.py
|
|
44
|
37 --num_threads \${GALAXY_SLOTS:-4}
|
|
67
|
38 #set input_format = $input_format_cond.input_format
|
|
51
|
39 #if str($input_format) == 'ptortho':
|
|
|
40 --orthogroup_faa '$input_format_cond.input_ptortho.extra_files_path'
|
|
47
|
41 #else:
|
|
51
|
42 --orthogroup_faa '$input_format_cond.input_ptorthocs.extra_files_path'
|
|
65
|
43 --orthogroup_fna 'true'
|
|
67
|
44 #set multiple_codon_alignments_cond = $input_format_cond.multiple_codon_alignments_cond
|
|
|
45 #set multiple_codon_alignments = $multiple_codon_alignments_cond.multiple_codon_alignments
|
|
|
46 #if str($multiple_codon_alignments) == 'yes':
|
|
|
47 --sequence_type $multiple_codon_alignments_cond.sequence_type
|
|
|
48 #end if
|
|
47
|
49 #end if
|
|
60
|
50 --config_dir '$scaffold.fields.path'
|
|
58
|
51 --scaffold '$scaffold.fields.path'
|
|
0
|
52 --method $method
|
|
14
|
53
|
|
0
|
54 #if str($options_type.options_type_selector) == 'advanced':
|
|
42
|
55 #if str($multiple_sequence_alignments) == 'yes':
|
|
65
|
56 --alignments_method $multiple_sequence_alignments_option
|
|
66
|
57 #if str($multiple_sequence_alignments_option) == 'pasta_alignments':
|
|
40
|
58 --pasta_script_path '$__tool_directory__/run_pasta.py'
|
|
0
|
59 --pasta_iter_limit $multiple_sequence_alignments_option_cond.pasta_iter_limit
|
|
|
60 #end if
|
|
|
61 #end if
|
|
14
|
62
|
|
0
|
63 #if str($options_type.phylogenetic_trees_cond.phylogenetic_trees) == 'yes':
|
|
|
64 #set tree_inference_cond = $options_type.phylogenetic_trees_cond.tree_inference_cond
|
|
|
65 #set tree_inference_method = $tree_inference_cond.tree_inference
|
|
|
66 --tree_inference $tree_inference_method
|
|
|
67 #if str($tree_inference_method) == 'raxml':
|
|
14
|
68 #set rooting_order_file_cond = $tree_inference_cond.rooting_order_file_cond
|
|
|
69 #set rooting_order_file = $rooting_order_file_cond.rooting_order_file
|
|
|
70 #if str($rooting_order_file) == 'yes':
|
|
49
|
71 --rooting_order '$rooting_order_file_cond.rooting_order'
|
|
65
|
72 # No else block needed here because the default rooting_order
|
|
|
73 # configuration will be used if the --rooting_order flag is missing.
|
|
14
|
74 #end if
|
|
0
|
75 --bootstrap_replicates $tree_inference_cond.bootstrap_replicates
|
|
|
76 #end if
|
|
|
77 --max_orthogroup_size $options_type.phylogenetic_trees_cond.max_orthogroup_size
|
|
|
78 --min_orthogroup_size $options_type.phylogenetic_trees_cond.min_orthogroup_size
|
|
|
79 #end if
|
|
14
|
80
|
|
0
|
81 #if str($options_type.msa_quality_control_options_cond.msa_quality_control_options) == 'yes':
|
|
|
82 #set msa_quality_control_options_cond = $options_type.msa_quality_control_options_cond
|
|
|
83 #set remove_gappy_sequences_cond = $msa_quality_control_options_cond.remove_gappy_sequences_cond
|
|
|
84 #if str($remove_gappy_sequences_cond) == 'yes':
|
|
|
85 #set trim_type_cond = $remove_gappy_sequences_cond.trim_type_cond
|
|
|
86 --remove_sequences $remove_gappy_sequences_cond.remove_sequences
|
|
65
|
87 --trim_type $trim_type_cond.trim_type
|
|
|
88 #if str($trim_type_cond.trim_type) == 'gap_trimming':
|
|
0
|
89 --gap_trimming $trim_type_cond.gap_trimming
|
|
|
90 #end if
|
|
|
91 #end if
|
|
|
92 #end if
|
|
|
93 #end if
|
|
14
|
94
|
|
51
|
95 #if str($input_format) == 'ptortho':
|
|
65
|
96 --output_ptortho '$output_ptortho'
|
|
|
97 --output_ptortho_dir '$output_ptortho.files_path'
|
|
42
|
98 #else:
|
|
65
|
99 --output_ptorthocs '$output_ptorthocs'
|
|
|
100 --output_ptorthocs_dir '$output_ptorthocs.files_path'
|
|
42
|
101 #end if
|
|
14
|
102
|
|
|
103 #if $generate_output_aln:
|
|
65
|
104 --output_aln '$output_aln'
|
|
|
105 --output_aln_dir '$output_aln.files_path'
|
|
14
|
106 #end if
|
|
|
107
|
|
|
108 #if $generate_output_tree:
|
|
65
|
109 --output_tree '$output_tree'
|
|
|
110 --output_tree_dir '$output_tree.files_path'
|
|
14
|
111 #end if
|
|
0
|
112 ]]>
|
|
|
113 </command>
|
|
|
114 <inputs>
|
|
42
|
115 <conditional name="input_format_cond">
|
|
|
116 <param name="input_format" type="select" label="Select type of data to sub sample">
|
|
53
|
117 <option value="ptortho">Precomputed orthologous gene family clusters</option>
|
|
|
118 <option value="ptorthocs">Precomputed orthologous gene family clusters with corresponding coding sequences</option>
|
|
42
|
119 </param>
|
|
51
|
120 <when value="ptortho">
|
|
|
121 <param name="input_ptortho" format="ptortho" type="data" label="Precomputed orthologous gene family clusters" />
|
|
42
|
122 </when>
|
|
51
|
123 <when value="ptorthocs">
|
|
|
124 <param name="input_ptorthocs" format="ptorthocs" type="data" label="Precomputed orthologous gene family clusters with corresponding coding sequences" />
|
|
42
|
125 <conditional name="multiple_codon_alignments_cond">
|
|
|
126 <param name="multiple_codon_alignments" type="select" label="Construct orthogroup multiple codon alignments?">
|
|
|
127 <option value="no" selected="True">No</option>
|
|
|
128 <option value="yes">Yes</option>
|
|
|
129 </param>
|
|
51
|
130 <when value="no" />
|
|
42
|
131 <when value="yes">
|
|
51
|
132 <param name="sequence_type" type="select" label="Sequence type used in the phylogenetic inference (dna)">
|
|
42
|
133 <option value="protein" selected="true">Amino acid based</option>
|
|
|
134 <option value="dna">Nucleotide based</option>
|
|
|
135 </param>
|
|
|
136 </when>
|
|
|
137 </conditional>
|
|
|
138 </when>
|
|
|
139 </conditional>
|
|
0
|
140 <param name="scaffold" type="select" label="Orthogroups or gene families proteins scaffold">
|
|
|
141 <options from_data_table="plant_tribes_scaffolds" />
|
|
51
|
142 <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
|
143 </param>
|
|
|
144 <param name="method" type="select" label="Protein clustering method">
|
|
|
145 <option value="gfam" selected="true">GFam</option>
|
|
|
146 <option value="orthofinder">OrthoFinder</option>
|
|
|
147 <option value="orthomcl">OrthoMCL</option>
|
|
|
148 </param>
|
|
|
149 <conditional name="options_type">
|
|
|
150 <param name="options_type_selector" type="select" label="Options Configuration">
|
|
|
151 <option value="basic" selected="true">Basic</option>
|
|
|
152 <option value="advanced">Advanced</option>
|
|
|
153 </param>
|
|
|
154 <when value="basic" />
|
|
|
155 <when value="advanced">
|
|
|
156 <conditional name="multiple_sequence_alignments_cond">
|
|
5
|
157 <param name="multiple_sequence_alignments" type="select" label="Set multiple sequence alignments options?">
|
|
0
|
158 <option value="no" selected="true">No</option>
|
|
|
159 <option value="yes">Yes</option>
|
|
|
160 </param>
|
|
|
161 <when value="no" />
|
|
|
162 <when value="yes">
|
|
|
163 <conditional name="multiple_sequence_alignments_option_cond">
|
|
51
|
164 <param name="multiple_sequence_alignments_option" label="Select method for multiple sequence alignments" type="select"
|
|
|
165 force_select="True">
|
|
0
|
166 <option value="create_alignments">Create orthogroup protein multiple sequence alignments including scaffold backbone proteins (MAFFT algorithm)</option>
|
|
|
167 <option value="add_alignments">Add unaligned orthogroup proteins to scaffold backbone multiple sequence alignments (MAFFT algorithm)</option>
|
|
|
168 <option value="pasta_alignments">Create orthogroup protein multiple sequence alignments including scaffold backbone proteins (PASTA algorithm)</option>
|
|
|
169 </param>
|
|
51
|
170 <when value="create_alignments" />
|
|
|
171 <when value="add_alignments" />
|
|
0
|
172 <when value="pasta_alignments">
|
|
65
|
173 <param name="pasta_iter_limit" type="integer" value="3" min="0" label="Maximum number of iteration that the PASTA algorithm will execute" />
|
|
0
|
174 </when>
|
|
|
175 </conditional>
|
|
|
176 </when>
|
|
|
177 </conditional>
|
|
|
178 <conditional name="phylogenetic_trees_cond">
|
|
|
179 <param name="phylogenetic_trees" type="select" label="Set phylogenetic trees options?">
|
|
|
180 <option value="no" selected="true">No</option>
|
|
|
181 <option value="yes">Yes</option>
|
|
|
182 </param>
|
|
|
183 <when value="no" />
|
|
|
184 <when value="yes">
|
|
|
185 <conditional name="tree_inference_cond">
|
|
|
186 <param name="tree_inference" type="select" label="Phylogenetic trees inference method">
|
|
|
187 <option value="raxml" selected="true">RAxML</option>
|
|
|
188 <option value="fasttree">FastTree</option>
|
|
|
189 </param>
|
|
|
190 <when value="raxml">
|
|
14
|
191 <conditional name="rooting_order_file_cond">
|
|
61
|
192 <param name="rooting_order_file" type="select" label="Select rooting order configuration for rooting trees?" help="Select No for the default rooting order configuration which uses the most distant taxon present in the orthogroup">
|
|
14
|
193 <option value="no" selected="true">No</option>
|
|
|
194 <option value="yes">Yes</option>
|
|
|
195 </param>
|
|
51
|
196 <when value="no" />
|
|
14
|
197 <when value="yes">
|
|
56
|
198 <param name="rooting_order" format="txt" type="data" label="Rooting order configuration for rooting trees" />
|
|
14
|
199 </when>
|
|
|
200 </conditional>
|
|
51
|
201 <param name="bootstrap_replicates" type="integer" value="100" min="0" label="Number of replicates for rapid bootstrap analysis and search for the best-scoring ML tree" />
|
|
0
|
202 </when>
|
|
51
|
203 <when value="fasttree" />
|
|
0
|
204 </conditional>
|
|
51
|
205 <param name="max_orthogroup_size" type="integer" value="100" min="0" label="Maximum number of sequences in orthogroup alignments" />
|
|
|
206 <param name="min_orthogroup_size" type="integer" value="4" min="0" label="Minimum number of sequences in orthogroup alignments" />
|
|
0
|
207 </when>
|
|
|
208 </conditional>
|
|
|
209 <conditional name="msa_quality_control_options_cond">
|
|
|
210 <param name="msa_quality_control_options" type="select" label="Set MSA quality control options?">
|
|
|
211 <option value="no" selected="true">No</option>
|
|
|
212 <option value="yes">Yes</option>
|
|
|
213 </param>
|
|
|
214 <when value="no" />
|
|
|
215 <when value="yes">
|
|
|
216 <conditional name="remove_gappy_sequences_cond">
|
|
|
217 <param name="remove_gappy_sequences" type="select" label="Remove gappy sequences in alignments?">
|
|
|
218 <option value="no" selected="true">No</option>
|
|
|
219 <option value="yes">Yes</option>
|
|
|
220 </param>
|
|
51
|
221 <when value="no" />
|
|
0
|
222 <when value="yes">
|
|
51
|
223 <param name="remove_sequences" type="float" value="0.5" min="0" max="1" label="Remove sequences with gaps of" help="0.5 removes sequences with 50% gaps" />
|
|
0
|
224 <conditional name="trim_type_cond">
|
|
|
225 <param name="trim_type" type="select" label="Select process used for gap trimming">
|
|
51
|
226 <option value="gap_trimming" selected="true">Nucleotide based </option>
|
|
26
|
227 <option value="automated_trimming">Trim alignments using trimAl's ML heuristic trimming approach</option>
|
|
0
|
228 </param>
|
|
51
|
229 <when value="automated_trimming" />
|
|
0
|
230 <when value="gap_trimming">
|
|
51
|
231 <param name="gap_trimming" type="float" value="0.1" min="0" max="1.0" label="Remove sites in alignments with gaps of" help="0.1 removes sites with 90% gaps" />
|
|
0
|
232 </when>
|
|
|
233 </conditional>
|
|
|
234 </when>
|
|
|
235 </conditional>
|
|
|
236 </when>
|
|
|
237 </conditional>
|
|
|
238 </when>
|
|
|
239 </conditional>
|
|
|
240 </inputs>
|
|
|
241 <outputs>
|
|
65
|
242 <data name="output_ptortho" format="ptortho">
|
|
51
|
243 <filter>input_format_cond['input_format'] == 'ptortho'</filter>
|
|
41
|
244 </data>
|
|
65
|
245 <data name="output_ptorthocs" format="ptorthocs">
|
|
51
|
246 <filter>input_format_cond['input_format'] == 'ptorthocs'</filter>
|
|
41
|
247 </data>
|
|
54
|
248 <data name="output_aln" format="ptalign" label="Multiple alignments using method ${options_type['multiple_sequence_alignments_cond']['multiple_sequence_alignments_option_cond']['multiple_sequence_alignments_option']} on ${on_string}">
|
|
22
|
249 <filter>options_type['options_type_selector'] == 'advanced' and options_type['multiple_sequence_alignments_cond']['multiple_sequence_alignments'] == 'yes'</filter>
|
|
14
|
250 </data>
|
|
53
|
251 <data name="output_tree" format="pttree" label="Phylogenetic trees on ${on_string}">
|
|
14
|
252 <filter>options_type['options_type_selector'] == 'advanced' and options_type['phylogenetic_trees_cond']['phylogenetic_trees'] == 'yes'</filter>
|
|
|
253 </data>
|
|
0
|
254 </outputs>
|
|
|
255 <tests>
|
|
|
256 <test>
|
|
|
257 </test>
|
|
|
258 </tests>
|
|
|
259 <help>
|
|
71
|
260 This tool is one of the PlantTribes collection of automated modular analysis pipelines that utilize objective classifications of
|
|
59
|
261 complete protein sequences from sequenced plant genomes to perform comparative evolutionary studies. It performs phylogenomic
|
|
|
262 analyses by creating multiple sequence alignments and inferred maximum likelihood phylogenies for orthogroups produced by the
|
|
|
263 **Classify gene sequences into precomputed orthologous gene family clusters** tool.
|
|
0
|
264
|
|
59
|
265 -----
|
|
0
|
266
|
|
59
|
267 **Options**
|
|
0
|
268
|
|
69
|
269 * **Required**
|
|
18
|
270
|
|
59
|
271 - **Select gene family clusters** - Sequences classified into gene family clusters, optionally including corresponding coding sequences.
|
|
|
272 - **Orthogroups or gene families proteins scaffold** - PlantTribes scaffolds data.
|
|
|
273 - **Protein clustering method** - One of GFam (domain architecture based clustering), OrthoFinder (broadly defined clusters) or OrthoMCL (narrowly defined clusters).
|
|
|
274
|
|
69
|
275 * **Multiple sequence alignments**
|
|
14
|
276
|
|
59
|
277 - **Select method for multiple sequence alignments** - Method used for setting multiple sequence alignments.
|
|
|
278 - **Input sequences include corresponding coding sequences?** - Selecting 'Yes' for this option requires that the selected input data format is 'ptorthocs'.
|
|
|
279 - **Construct orthogroup multiple codon alignments?** - Construct orthogroup multiple codon alignments.
|
|
|
280 - **Sequence type used in the phylogenetic inference** - Sequence type (dna or amino acid) used in the phylogenetic inference.
|
|
|
281 - **Use corresponding coding sequences?** - Selecting 'Yes' for this option requires that the selected input data format is 'ptorthocs' or this tool will produce an error.
|
|
14
|
282
|
|
69
|
283 * **Phylogenetic trees**
|
|
15
|
284
|
|
59
|
285 - **Phylogenetic trees inference method** - Phylogenetic trees inference method.
|
|
|
286 - **Select rooting order configuration for rooting trees??** - If 'No' is selected, trees will be rooted using the most distant taxon present in the orthogroup.
|
|
|
287 - **Number of replicates for rapid bootstrap analysis and search for the best-scoring ML tree** - Number of replicates for rapid bootstrap analysis and search for the best-scoring ML tree.
|
|
|
288 - **Maximum number of sequences in orthogroup alignments** - Maximum number of sequences in orthogroup alignments.
|
|
|
289 - **Minimum number of sequences in orthogroup alignments** - Minimum number of sequences in orthogroup alignments.
|
|
14
|
290
|
|
69
|
291 * **MSA quality control**
|
|
14
|
292
|
|
59
|
293 - **Remove sequences with gaps of** - Removes gappy sequences in alignments (i.e., 0.5 removes sequences with 50% gaps).
|
|
|
294 - **Select process used for gap trimming** - Either nucleotide based trimming or alignments are trimed using using trimAl's ML heuristic trimming approach.
|
|
|
295 - **Remove sites in alignments with gaps of** - If the process used for gap trimming is nucleotide based, this is the gap value used when removing gappy sites in alignments (i.e., 0.1 removes sites with 90% gaps).
|
|
14
|
296
|
|
0
|
297 </help>
|
|
|
298 <citations>
|
|
51
|
299 <citation type="bibtex">
|
|
70
|
300 @misc{None,
|
|
|
301 journal = {None},
|
|
|
302 author = {1. Wafula EK},
|
|
|
303 title = {Manuscript in preparation},
|
|
51
|
304 year = {None},
|
|
70
|
305 url = {https://github.com/dePamphilis/PlantTribes},}
|
|
51
|
306 </citation>
|
|
|
307 <citation type="bibtex">
|
|
70
|
308 @article{Mirarab2014,
|
|
|
309 journal = {Research in Computational Molecular Biology (RECOMB)},
|
|
|
310 author = {2. Mirarab S, Nguyen N, Warnow T},
|
|
|
311 title = {PASTA: Ultra-Large Multiple Sequence Alignment. In R. Sharan (Ed.)},
|
|
51
|
312 year = {2014},
|
|
70
|
313 pages = {177–191},
|
|
|
314 url = {https://github.com/smirarab/pasta},}
|
|
51
|
315 </citation>
|
|
|
316 <citation type="bibtex">
|
|
70
|
317 @article{Salvador2009,
|
|
|
318 journal = {Bioinformatics},
|
|
|
319 author = {3. Capella-Gutierrez S, Silla-Martinez JM, Gabaldon T},
|
|
|
320 title = {trimAl: a tool for automated alignment trimming in large-scale phylogenetic analyses},
|
|
51
|
321 year = {2009},
|
|
70
|
322 url = {http://trimal.cgenomics.org},}
|
|
51
|
323 </citation>
|
|
|
324 <citation type="bibtex">
|
|
70
|
325 @article{Stamatakis2014,
|
|
|
326 journal = {Bioinformatics},
|
|
|
327 author = {4. Stamatakis A},
|
|
|
328 title = {RAxML Version 8: A tool for Phylogenetic Analysis and Post-Analysis of Large Phylogenies},
|
|
51
|
329 year = {2014},
|
|
70
|
330 url = {http://sco.h-its.org/exelixis/web/software/raxml/index.html},}
|
|
51
|
331 </citation>
|
|
|
332 <citation type="doi">10.1371/journal.pone.0009490</citation>
|
|
70
|
333 <citation type="doi">10.1093/bioinformatics/btw412</citation>
|
|
0
|
334 </citations>
|
|
|
335 </tool>
|
