Mercurial > repos > gandres > fastme

comparison fastme.xml @ 4:aea74cec21e0 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author dcorreia
date Fri, 22 Apr 2016 08:04:53 -0400
parents df98a0425c8d
children
comparison
equal deleted inserted replaced
3:df98a0425c8d 4:aea74cec21e0
1 <tool id="sniplay_fastme" name="Fastme" version="1.1.0"> 1 <tool id="fastme" name="FastME" version="2.1.4.2">
2 2 <description>Distance-based inference of phylogenetic trees</description>
3 <!-- [REQUIRED] Tool description displayed after the tool name -->
4 <description> Calculate distance tree for an alignment file</description>
5
6 <!-- [OPTIONAL] 3rd party tools, binaries, modules... required for the tool to work -->
7 <requirements> 3 <requirements>
8 <requirement type="binary">perl</requirement> 4 <requirement type="package" version="2.1.4">fastme</requirement>
9 <requirement type="package" version="2.1.4">fastme</requirement>
10 </requirements> 5 </requirements>
11 6 <version_command>
12 <!-- [STRONGLY RECOMMANDED] Exit code rules --> 7 <![CDATA[ fastme --version ]]>
8 </version_command>
13 <stdio> 9 <stdio>
14 <!-- [HELP] If no exit code rule is defined, the tool will stop if anything is written to STDERR -->
15 <exit_code range="1:" level="fatal" /> 10 <exit_code range="1:" level="fatal" />
16 </stdio> 11 </stdio>
17 12 <command>fastme --input_data=$input
18 13 --output_tree=$outputTree
19 <!-- [REQUIRED] The command to execute --> 14 --output_matrix=$outputMatrix
20 <command> 15 --output_info=$outputLog
21 fastme --input_data=$input_data --dna=$model --output_tree=$fileout 16 --nb_threads=\${GALAXY_SLOTS:-1}
22 #if str( $distance ) == "SPR": 17
23 --spr 18 #if $typeChoice.datatype =="d"
24 #elif str( $distance )[:3] == "NNI" : 19 --dna=$typeChoice.modeldna
25 #if str( $distance ) == "NNI_B" : 20
26 --nni=B 21 #else if $typeChoice.datatype =="p"
27 #else : 22 --protein=$typeChoice.modelprot
28 --nni=O 23
29 #end if 24 #else if $typeChoice.datatype =="cfg":
30 25 ## Read information of sequence type
31 #else : 26 ## read an info file to choose which option set and set a model by default
32 --method=$distance 27 #set $info = open( str($input_info) ).read()
33 #end if 28 #if 'dna' in $info:
34 > $fileout_log 29 --dna=T
30 #else if 'protein' in $info:
31 --protein=L
32 #end if
33 #end if
34
35 #if $gammaChoice.gamma == "true"
36 --gamma=$gammaChoice.rate
37 #end if
38
39 $distance
40 $equilibrium
41 $removeGap
42 $treeRefinement
43
44 #if $bootChoice.boot == "true"
45 --output_boot=$outputBoostrap
46 --bootstrap=$bootChoice.replicates
47 #end if
48
49 >> tmp_stdout;
50 cat tmp_stdout > $outputLog;
51
35 </command> 52 </command>
36
37
38
39 <!-- [REQUIRED] Input files and tool parameters -->
40 <inputs> 53 <inputs>
41 <param name="input_data" type="data" format="txt" optional="false" label="Phylip input" /> 54 <param name="input" type="data" format="phylip, phy" label="Fastme input" help="Phylip Alignment or Matrix file"/>
42 <param name="fileout_label" type="text" value="Newick tree" label="Output name" help="Output name for files" /> 55 <param name="fileout_label" type="text" value="Newick tree" label="Output name" help="Output name for files" />
43 <param name="model" type="select" label="Evolutionary model" > 56 <conditional name="typeChoice">
44 <option value="p">p-distance</option> 57 <param name="datatype" type="select" display="radio" label="Data type" >
45 <option value="Y">RY symetric</option> 58 <option value="d">DNA</option>
46 <option value="R">RY</option> 59 <option value="p">Protein</option>
47 <option value="J">JC69</option> 60 <option value="m">Matrix</option>
48 <option value="K">K2P</option> 61 <option value="cfg">Config file</option>
49 <option value="1">F81</option> 62 </param>
50 <option value="4" selected="true">F84</option> 63 <when value="d">
51 <option value="T">TN93</option> 64 <param name="modeldna" type="select" label="Evolutionary model">
52 <option value="L">LogDet</option> 65 <option value="4">F84</option>
66 <option value="R">RY</option>
67 <option value="1">F81</option>
68 <option value="J">JC69</option>
69 <option value="K">K2P</option>
70 <option value="T" selected="true">TN93</option>
71 <option value="p">p-distance</option>
72 </param>
73 </when>
74 <when value="p">
75 <param name="modelprot" type="select" label="Evolutionary model">
76 <option value="L">LG</option>
77 <option value="W">WAG</option>
78 <option value="J">JTT</option>
79 <option value="h">Day off</option>
80 <option value="C">CpRev</option>
81 <option value="D">DCMut</option>
82 <option value="b">HIVb</option>
83 <option value="I">HIVw</option>
84 <option value="M">MtREV</option>
85 <option value="R">RtREV</option>
86 <option value="p">p-distance</option>
87 </param>
88 </when>
89 <when value="m"/>
90 <when value="cfg">
91 <param name="input_info" format="txt" type="data" multiple="false" label="Config file" help="Precompute file containning sequence description (dna or protein)"/>
92 </when>
93 </conditional>
94 <param name="equilibrium" type="boolean" label="Equilibrium frequencies" truevalue="--equilibrium" falsevalue="" help="By default, frequencies are globally counted from the nucleotides alignment or defined by the proteic substitution model. By checking the box, frequencies are pairwise estimated by counting the nucleotides or estimated by counting the amino-acids in the alignment."/>
95 <conditional name="gammaChoice">
96 <param name="gamma" type="select" label="Gamma distributed rates across sites">
97 <option value="true">Yes</option>
98 <option value="false">No</option>
99 </param>
100 <when value="true">
101 <param name="rate" type="float" label="Gamma distribution parameter" value="1" min="0"/>
102 </when>
103 <when value="false" />
104 </conditional>
105 <param name="removeGap" type="select" display="radio" label="Remove gap strategy">
106 <option value="">Pairwise deletion of gaps</option>
107 <option value="--remove_gap">Remove all sites with gap</option>
53 </param> 108 </param>
54 <param name="distance" type="select" label="Distance methode" > 109 <param name="distance" type="select" label="Distance algorithm">
55 <option value="B">TaxAdd_BalME</option> 110 <option value="--method=I">BIONJ</option>
56 <option value="O">TaxAdd_OLSME</option> 111 <option value="--method=B --branch_length=B">TaxAdd BalME</option>
57 <option value="I" selected="true">BIONJ</option> 112 <option value="--method=O --branch_length=O">TaxAdd OLSME</option>
58 <option value="N">NJ</option> 113 <option value="--method=N">NJ</option>
59 <option value="U">UNJ</option> 114 <option value="--method=U">UNJ</option>
60 <option value="NNI_B">NNI_BalME</option>
61 <option value="NNI_O">NNI_OLS</option>
62 <option value="SPR">SPR</option>
63 </param> 115 </param>
64 </inputs> 116 <param name="treeRefinement" type="select" display="radio" label="Tree Refinement" help='(NNI) Nearest Neighbor Interchanges,(SPR) Subtree Pruning and Regrafting '>
65 117 <option value="">None</option>
66 <!-- [REQUIRED] Output files --> 118 <option value="--nni=O">OLS NNI</option>
119 <option value="--nni=B">BalME NNI</option>
120 <option value="--spr" selected="true">BalME SPR</option>
121 <option value="--nni=B --spr">BalME NNI + SPR</option>
122 </param>
123 <conditional name="bootChoice">
124 <param name="boot" type="select" label="Bootstrap">
125 <option value="false">No</option>
126 <option value="true">Yes</option>
127 </param>
128 <when value="false"/>
129 <when value="true">
130 <param name="replicates" type="integer" value="1000" label="Number of replicates"/>
131 </when>
132 </conditional>
133 </inputs>
67 <outputs> 134 <outputs>
68 <data name="fileout_log" type="data" format="txt" label="${fileout_label}.log" /> 135 <data name="outputTree" format="nwk" label="${fileout_label}"/>
69 <data name="fileout" type="data" format="txt" label="${fileout_label}" /> 136 <data name="outputLog" format="txt" label="FastME Information"/>
137 <data name="outputBoostrap" format="nwk" label="FastME Bootstrap trees">
138 <filter>bootChoice['boot'] == "true"</filter>
139 </data>
140 <data name="outputMatrix" format="txt" label="FastME Distance matrix"/>
70 </outputs> 141 </outputs>
71
72 <!-- [OPTIONAL] Tests to be run manually by the Galaxy admin -->
73 <tests> 142 <tests>
74 <!-- [HELP] Test files have to be in the ~/test-data directory -->
75
76 <test> 143 <test>
77 <param name="input_data" value="phylip" /> 144 <param name="input" value="phylip" />
78 <param name="model" value="4"/> 145 <param name="modeldna" value="4"/>
79 <param name="distance" value="I"/> 146 <param name="gamma" value="false"/>
80 <output name="fileout" file="newick" /> 147 <param name="treeRefinement" value=""/>
148 <param name="distance" value="--method=I"/>
149 <output name="outputTree" file="newick" />
81 </test> 150 </test>
82
83 <!-- [HELP] Multiple tests can be defined with different parameters -->
84 <!--
85 <test> 151 <test>
152 <param name="input" value="phylip" />
153 <param name="modeldna" value="T"/>
154 <param name="distance" value="--method=I"/>
155 <param name="treeRefinement" value="--nni=B --spr"/>
156 <param name="fileout_label" value="TreeTn93BionjSpr.nwk" />
157 <output name="outputTree" file="TreeTn93BionjSpr.nwk" />
86 </test> 158 </test>
87 -->
88 </tests> 159 </tests>
89
90 <!-- [OPTIONAL] Help displayed in Galaxy -->
91 <help> 160 <help>
92 161
93 .. class:: infomark 162 .. class:: infomark
94 163
95 **Authors** 164
96 165 **FastME version 2.1.4**
97 | Richard Desper and Olivier Gascuel,
98 | Journal of Computational Biology 19(5), 687-705, 2002.
99 | Molecular Biology and Evolution 21(3), 587-598, 2004.
100 | Please cite these papers if you use this software in your publications.
101 166
102 167
103 .. class:: infomark 168 .. class:: infomark
104 169
105 **Galaxy integration** Andres Gwendoline, Institut Français de Bioinformatique. 170
106 171 **Galaxy integration** Andres Gwendoline, Institut Français de Bioinformatique. Correia Damien, CNRS.
107 .. class:: infomark 172 **Support** For any questions about Galaxy integration, please send an e-mail to vincent.lefort@lirmm.fr
108 173
109 **Support** For any questions about Galaxy integration, please send an e-mail to support.abims@sb-roscoff.fr 174
110 175 -----
111 --------------------------------------------------- 176
112 177
113 178 ############
114 ====== 179 FastME 2.0
115 FastMe 180 ############
116 ====== 181
182 Comprehensive, accurate and fast distance-based phylogeny inference program
183
117 184
118 ----------- 185 -----------
119 Description 186 Description
120 ----------- 187 -----------
121 188
122 189 FastME provides distance algorithms to infer phylogenies. It's based on balanced minimum evolution, which is the very principle of NJ.
123 FastME - A distance based phylogeny reconstruction algorithm. 190
124 191 FastME included Nearest Neighbor Interchange (NNI) and also Subtree Pruning and Regrafting (SPR), while remaining as fast as NJ and providing a number of facilities: distance estimation for DNA and proteins with various models and options, bootstrapping, and parallel computations.
125 FastME showed better topological accuracy than NJ,
126 BIONJ, WEIGHBOR and FITCH, in all evolutionary
127 conditions we tested, which include large range
128 deviations from molecular clock and substitution rates.
129
130
131
132 -----------------
133 Workflow position
134 -----------------
135
136 **Upstream tools**
137
138 =========== ========================== =======
139 Name output file(s) format
140 =========== ========================== =======
141 Readseq phylip conversion phylip
142 =========== ========================== =======
143
144
145 **Downstream tools**
146
147 =========== ========================== =======
148 Name output file(s) format
149 =========== ========================== =======
150 Rooting out tree Newick
151 =========== ========================== =======
152
153
154 ----------
155 Input file
156 ----------
157
158 Phylip file
159 Phylip file with sequence alignments
160
161
162 ----------
163 Parameters
164 ----------
165
166 Output name
167 Output base name for the ouput files
168
169 Evolutionary model
170 Indicate the evolutionary [model] which can be choosen from:p-distance, RY symmetric, RY, JC69, K2P, F81, F84 (default), TN93, LogDet.
171
172 Distance methode
173 FastME computes a tree using a distance algorithm. You may choose this method/topologie from: TaxAdd_BalME, TaxAdd_OLSME, BIONJ (default), NJ, UNJ, NNI_BalME, NNI_OLS or SPR
174
175 ------------
176 Output files
177 ------------
178
179 Output_name
180 Resulting tree at Newick format
181
182 Output_name.log
183 Log file
184 192
185 ------------ 193 ------------
186 Dependencies 194 Dependencies
187 ------------ 195 ------------
188 FastME 196 FastME
189 http://www.atgc-montpellier.fr/fastme 197 http://www.atgc-montpellier.fr/fastme
190 198
191 199
192 200
193 --------------------------------------------------- 201 ---------------------------------------------------
194 202
195 --------------- 203 ---------------
197 --------------- 205 ---------------
198 206
199 Input files 207 Input files
200 =========== 208 ===========
201 209
202 Philip file 210 **Phylip file**::
203 ----------- 211
204 212
205 :: 213 4 120
206 214 Orangutan CCAAACGACA TTTCATATGC TGTCATTTCT GAAGATATGA GACAAGTGAG CTGTCCGGAA
207 168 5125 215 Gorilla CCAAACAACA TTTCATGTGC TGTCATTTCT GAAGATATGA GACAAGTGAG CTCTCCGAAA
208 IRAT112 GAGAACCGTC CTGTAAGTAC TCTTGCTTTA AGTAATAAAG TAATACTAAT 216 Human CCAAACAACA TTTCATGTGC TGTCATTTCT GAAGATAAGA GACAAGTGAG CTCTCCGAAA
209 KARASUKARA GAGAACCGTC CTGTAAGTAC TCTTGCTTTA AATACGAAAG TAATACTAAT 217 Chimp CCAAACAACA TTTCATGTGC TGTCATTTCT GAAGATATGA GACAAGTGAG CTCTCCGAAA
218
219 CCAACATATC AGACATATGT GAATTTCAAT TATTGTACGG GCATCCTGGG CTCTCAAAGT
220 CCAAGATATC AGACATTTAT GAATTTCAAT TATTGTACGG GCATCCTGGG CTCTCAAAGT
221 CCAAGATACC AGACATTTGT GAATTTCAAT TATTGTACTG GCATCCTGGG CTCTCAAAGT
222 CCAAGATATC AGACATTTAT GAATTTCAAT TATTGTACTG GCATCCTGGG CTCTCAAAGT
223
224
210 225
211 Parameters 226 Parameters
212 ========== 227 ==========
213 228
214 Output name -> Newick tree 229 ::
215 230
216 Evolutionary model -> F84 231 Output name: Newick tree
217 232 Evolutionary model : TN93
218 Distance methode -> BIONJ 233 Distance method : BIONJ
234
219 235
220 Output files 236 Output files
221 ============ 237 ============
222 238
223 Newick tree 239 **Newick tree**::
224 ----------- 240
225 241 ((Gorilla:0.005755,Orangutan:0.020680):0.001063,Human:0.006655,Chimp:0.002132);
226 :: 242
227 243 -----
228 (((((((((((((((((((((((((GOGOLEMPUK:0.001198,GOGOLEMPAK:0.002128):0.030378,TREMBESE:0.013258):0.055246,(((JIMBRUKJOL:0.045219,KETANKONIR:0.035298):0.006267, ... 244
229 245 OPTIONS
246 =======
247
248
249 -i file, --input_data=file
250 The input data file contains sequence alignment(s) or a distance matrix(ces).
251
252 -u input_tree_file, --user_tree=input_tree_file
253 FastME may use an existing topology available in the input user tree file which corresponds to the input dataset.
254
255 -o output_tree_file, --output_tree=output_tree_file
256 FastME will write the infered tree into the output tree file.
257
258 -O output_matrix_file, --output_matrix=output_matrix_file
259 Use output matrix file option if you want FastME to write the distances
260 matrix computed from the input alignment in the output matrix file.
261
262 -I output_information_file, --output_info=output_information_file
263 Use this option if you want FastME to write information
264 about its execution in the output information file.
265
266 -B output_bootstrap_trees_file, --output_boot=output_bootstrap_trees_file
267 Use this option if you want FastME to write bootstrap trees
268 in the bootstrap trees file.
269
270 -a, --append
271 Use this option to append results to existing output files (if any).
272 By default output files will be overwritten.
273
274 -m method, --method=method
275 FastME computes a tree using a distance algorithm.
276 You may choose this method from:
277 TaxAdd_(B)alME, TaxAdd_(O)LSME, B(I)ONJ (default),
278 (N)J or (U)NJ.
279
280 -d model, --dna=model
281 Use this option if your input data file contains DNA sequences alignment(s).
282 You may also indicate the evolutionary [model] which can be choosen from:
283 (p)-distance, R(Y) symmetric, (R)Y, (J)C69, (K)2P, F8(1), F8(4) (default), (T)N93, (L)ogDet.
284
285 -p model, --protein=model
286 Use this option if your input data file contains protein sequences alignment(s).
287 You may also indicate the evolutionary [model] which can be choosen from:
288 (p)-distance, (F)81 like, (L)G (default), (W)AG, (J)TT, Day(h)off, (D)CMut, (C)pRev,
289 (M)tREV, (R)tREV, HIV(b), H(I)Vw or FL(U).
290
291 -r, --remove_gap
292 Use this option to completely remove any site which has a gap in
293 any sequence. By default, FastME is doing pairwise deletion of gaps.
294
295 -e, --equilibrium
296 The equilibrium frequencies for DNA are always estimated by counting
297 the occurence of the nucleotides in the input alignment.
298 For amino-acid sequences, the equilibrium frequencies are estimated
299 using the frequencies defined by the substitution model.
300 Use this option if you whish to estimate the amino-acid frequencies
301 by counting their occurence in the input alignment.
302
303 -g alpha, --gamma=alpha
304 Use this option if you wish to have gamma distributed rates across sites.
305 By default, FastME runs with no gamma variation.
306 If running FastME with gamma distributed rates across sites, the [alpha] default value is 1.0.
307 Only helpful when the input data file contains sequences alignment(s).
308
309 -n NNI, --nni=NNI
310 Use this option to do [NNI] tree topology improvement.
311 You may choose the [NNI] type from:
312 NNI_(B)alME (default) or NNI_(O)LS.
313
314 -s, --spr
315 Use this option to do SPR tree topology improvement.
316
317 -w branch, --branch_length=branch
318 Use this option to indicate the branch length to assign to the tree.
319 Only helpful when not improving the tree topology (no NNI nor SPR).
320 You may choose the branch length from:
321 (B)alLS (default), (O)LS or (n)one. (n)one is only available with BIONJ, NJ or UNJ.
322
323 -D datasets, --datasets=datasets
324 Use this option to indicate the number of datasets in your input
325 data file. Default value is 1.
326
327 -b replicates, --bootstrap=replicates
328 Use this option to indicate the number of replicates FastME will
329 do for bootstrapping. Default value is 0.
330 Only helpful when the input data file contains sequences alignment(s).
331
332 -z seed, --seed=seed
333 Use this option to initialize randomization with seed value. Only helpful when bootstrapping.
334
335 -c Use this option if you want FastME only to compute distance matrix.
336 Only helpful when the input data file contains sequences alignment(s).
337
338 -T number_of_threads, --nb_threads=number_of_threads
339 Use this option to set the number of threads to use.
340 Default number of threads is 4.
341
342 -v value, --verbose=value
343 Sets the verbose level to value [0-3]. Default value is 0
344
345 -V, --version
346 Prints the FastME version.
347
348 -h, --help Display this usage.
349
350
351 For further informations, please visite FastME_
352
353 .. _FastME: http://www.atgc-montpellier.fr/fastme/usersguide.php
230 354
231 </help> 355 </help>
232
233 <citations> 356 <citations>
234 <!-- [HELP] As DOI or BibTex entry --> 357 <citation type="doi">10.1093/molbev/msv150</citation>
235 <citation type="bibtex"> 358 <citation type="doi">10.1089/106652702761034136</citation>
236 @article{Lefort30062015,
237 author = {Lefort, Vincent and Desper, Richard and Gascuel, Olivier},
238 title = {FastME 2.0: A Comprehensive, Accurate, and Fast Distance-Based Phylogeny Inference Program},
239 year = {2015},
240 doi = {10.1093/molbev/msv150},
241 abstract ={FastME provides distance algorithms to infer phylogenies. FastME is based on balanced minimum evolution, which is the very principle of Neighbor Joining (NJ). FastME improves over NJ by performing topological moves using fast, sophisticated algorithms. The first version of FastME only included Nearest Neighbor Interchange. The new 2.0 version also includes Subtree Pruning and Regrafting, while remaining as fast as NJ and providing a number of facilities: Distance estimation for DNA and proteins with various models and options, bootstrapping, and parallel computations. FastME is available using several interfaces: Command-line (to be integrated in pipelines), PHYLIP-like, and a Web server (http://www.atgc-montpellier.fr/fastme/).},
242 URL = {http://mbe.oxfordjournals.org/content/early/2015/07/25/molbev.msv150.abstract},
243 eprint = {http://mbe.oxfordjournals.org/content/early/2015/07/25/molbev.msv150.full.pdf+html},
244 journal = {Molecular Biology and Evolution}
245 }
246
247 </citation>
248
249 </citations> 359 </citations>
250
251
252 </tool> 360 </tool>