Mercurial > repos > bgruening > infernal

comparison cmbuild.xml @ 6:ee4be6eadd34 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/infernal commit ca2d37289d712b69ac15611bbf4961d083991bba
author bgruening
date Fri, 10 Nov 2017 13:04:44 -0500
parents 6e18e0b098cd
children c9e29ac5d099
comparison
equal deleted inserted replaced
5:6e18e0b098cd 6:ee4be6eadd34
63 '$alignment_infile' 63 '$alignment_infile'
64 64
65 65
66 #if $Calibrate.selector=="true" 66 #if $Calibrate.selector=="true"
67 && cmcalibrate 67 && cmcalibrate
68 -L$Calibrate.L 68 -L $Calibrate.L
69 #if $Calibrate.output_options_cond.selector == "extra" 69 #if $Calibrate.output_options_cond.selector == "extra"
70 #if str($Calibrate.output_options_cond.output_options) != 'None' 70 #if str($Calibrate.output_options_cond.output_options) != 'None'
71 #for j in $Calibrate.output_options_cond.output_options.value: 71 #for j in $Calibrate.output_options_cond.output_options.value:
72 --$j $getVar($j) 72 --$j $getVar($j)
73 #end for 73 #end for
92 #end if 92 #end if
93 93
94 ]]> 94 ]]>
95 </command> 95 </command>
96 <inputs> 96 <inputs>
97 <!-- Stockholm or SELEX 97 <param name="alignment_infile" type="data" format="stockholm" label="Sequence database"/>
98 SELEX is defined in EMBOSS datatypes
99 -->
100 <param name="alignment_infile" type="data" format="stockholm,selex" label="Sequence database"/>
101 98
102 <conditional name="model_construction_opts"> 99 <conditional name="model_construction_opts">
103 <param name="model_construction_opts_selector" type="select" label="These options control how consensus columns are defined in an alignment" help=""> 100 <param name="model_construction_opts_selector" type="select" label="These options control how consensus columns are defined in an alignment" help="">
104 <option value="--fast" selected="true">automatic (--fast)</option> 101 <option value="--fast" selected="true">automatic (--fast)</option>
105 <option value="--hand">user defined (--hand)</option> 102 <option value="--hand">user defined (--hand)</option>
246 label="Turn off QDB during E-value calibration" help="This will slow down calibration"/> 243 label="Turn off QDB during E-value calibration" help="This will slow down calibration"/>
247 <param argument="--nonull3" truevalue="--nonull3" falsevalue="" checked="false" type="boolean" 244 <param argument="--nonull3" truevalue="--nonull3" falsevalue="" checked="false" type="boolean"
248 label="Turn off the null3 post hoc additional null model" help="This is not recommended unless you plan on using the same option to cmsearch and/or cmscan"/> 245 label="Turn off the null3 post hoc additional null model" help="This is not recommended unless you plan on using the same option to cmsearch and/or cmscan"/>
249 <param argument="--random" truevalue="--random" falsevalue="" checked="false" type="boolean" 246 <param argument="--random" truevalue="--random" falsevalue="" checked="false" type="boolean"
250 label="use GC content of random null background model of CM" help="Use the background null model of the CM to generate the random sequences, instead of the more realistic HMM. Unless the CM was built using the --null option to cmbuild, the background null model will be 25% each A, C, G and U"/> 247 label="use GC content of random null background model of CM" help="Use the background null model of the CM to generate the random sequences, instead of the more realistic HMM. Unless the CM was built using the --null option to cmbuild, the background null model will be 25% each A, C, G and U"/>
251 <param argument="--gc" type="data" format="*" optional="true" label="Use GC content distribution from file" help="Generate the random sequences using the nucleotide distribution from the sequence file"/> 248 <param argument="--gc" type="data" format="txt" optional="true" label="Use GC content distribution from file" help="Generate the random sequences using the nucleotide distribution from the sequence file"/>
252 </section> 249 </section>
253 </when> 250 </when>
254 </conditional> 251 </conditional>
255 252
256 253
323 <tests> 320 <tests>
324 <test> 321 <test>
325 <param name="alignment_infile" value="cmbuild_input_tRNA5.sto"/> 322 <param name="alignment_infile" value="cmbuild_input_tRNA5.sto"/>
326 <conditional name="Calibrate"> 323 <conditional name="Calibrate">
327 <param name="selector" value="true"/> 324 <param name="selector" value="true"/>
325 <param name="L" value="0.1"/>
328 </conditional> 326 </conditional>
329 <output name="outfile"> 327 <output name="outfile">
330 <assert_contents> 328 <assert_contents>
331 <has_text text="S 0 -1 0 1 4 0 1 88 108 -7.713 -8.959 -0.044 -5.412"/> 329 <has_text text="S 0 -1 0 1 4 0 1 89 109 -7.220 -8.465 -0.063 -4.919"/>
332 </assert_contents> 330 </assert_contents>
333 </output> 331 </output>
334 </test> 332 </test>
335 </tests> 333 </tests>
336 <help> 334 <help>
342 340
343 cm build builds a covariance model of an RNA multiple alignment. cmbuild uses the consensus structure to determine the architecture of the CM. 341 cm build builds a covariance model of an RNA multiple alignment. cmbuild uses the consensus structure to determine the architecture of the CM.
344 342
345 **Input** 343 **Input**
346 344
347 Input file is a multiple sequence alignment file in Stockholm or SELEX format, and must contain consensus secondary structure annotation. 345 Input file is a multiple sequence alignment file in Stockholm format, and must contain consensus secondary structure annotation.
348 cmbuild uses the consensus structure to determine the architecture of the CM. 346 cmbuild uses the consensus structure to determine the architecture of the CM.
349 347
350 Example: simple example of a multiple RNA sequence alignment with secondary structure annotation 348 Example: simple example of a multiple RNA sequence alignment with secondary structure annotation
351 349
352 # STOCKHOLM 1.0 350 # STOCKHOLM 1.0
398 **Options controlling relative weights** 396 **Options controlling relative weights**
399 397
400 398
401 cmbuild uses an ad hoc sequence weighting algorithm to downweight closely related sequences and upweight distantly related ones. This has the effect of making models less biased by uneven phylogenetic representation. For example, two identical sequences would typically each receive half the weight that one sequence would. These options control which algorithm gets used. 399 cmbuild uses an ad hoc sequence weighting algorithm to downweight closely related sequences and upweight distantly related ones. This has the effect of making models less biased by uneven phylogenetic representation. For example, two identical sequences would typically each receive half the weight that one sequence would. These options control which algorithm gets used.
402 400
403 - *--wgb*: Use the Henikoff position-based sequence weighting scheme ([Henikoff and Henikoff](http://zhanglab.ccmb.med.umich.edu/literature/henikoff_weight_1994.pdf), J. Mol. Biol. 243:574, 1994). This is the default. 401 - *--wgb*: Use the Henikoff position-based sequence weighting scheme [Henikoff
404 - *--wgsc*: Use the Gerstein/Sonnhammer/Chothia weighting algorithm ([Gerstein et al.](http://ac.els-cdn.com/0022283694900124/1-s2.0-0022283694900124-main.pdf?_tid=6ed29974-3044-11e5-8949-00000aacb35f&acdnat=1437550798_aaa62caa2c812bb81013f967e7b119ee), J. Mol. Biol. 236:1067, 1994). 402 and Henikoff, J. Mol. Biol. 243:574, 1994]. This is the default.
403 - *--wgsc*: Use the Gerstein/Sonnhammer/Chothia weighting algorithm [Gerstein et al, J. Mol. Biol. 235:1067, 1994].
405 - *--wnone*: Turn sequence weighting off; e.g. explicitly set all sequence weights to 1.0. 404 - *--wnone*: Turn sequence weighting off; e.g. explicitly set all sequence weights to 1.0.
406 - *--wgiven*: Use sequence weights as given in annotation in the input alignment file. If no weights were given, assume they are all 1.0. The default is to determine new sequence weights by the Gerstein/Sonnhammer/Chothia algorithm, ignoring any annotated weights. 405 - *--wgiven*: Use sequence weights as given in annotation in the input alignment file. If no weights were given, assume they are all 1.0. The default is to determine new sequence weights by the Gerstein/Sonnhammer/Chothia algorithm, ignoring any annotated weights.
407 - *--wblosum*: Use the BLOSUM filtering algorithm to weight the sequences, instead of the default GSC weighting. Cluster the sequences at a given percentage identity (see --wid); assign each cluster a total weight of 1.0, distributed equally amongst the members of that cluster. 406 - *--wblosum*: Use the BLOSUM filtering algorithm to weight the sequences, instead of the default GSC weighting. Cluster the sequences at a given percentage identity (see --wid); assign each cluster a total weight of 1.0, distributed equally amongst the members of that cluster.
408 407
409 408