Mercurial > repos > bgruening > infernal

comparison cmbuild.xml @ 9:1d74ed49cf41 draft default tip

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 09c1d4ab75f5cd057ed57bf694217f0e355f785e
author bgruening
date Mon, 11 Nov 2024 10:27:19 +0000
parents c9e29ac5d099
children
comparison
equal deleted inserted replaced
8:c9e29ac5d099 9:1d74ed49cf41
2 <description>Build covariance models from sequence alignments</description> 2 <description>Build covariance models from sequence alignments</description>
3 <macros> 3 <macros>
4 <import>macros.xml</import> 4 <import>macros.xml</import>
5 </macros> 5 </macros>
6 <!--parallelism method="multi" split_inputs="alignment_infile" split_mode="to_size" split_size="10" merge_outputs="cmfile_outfile"></parallelism--> 6 <!--parallelism method="multi" split_inputs="alignment_infile" split_mode="to_size" split_size="10" merge_outputs="cmfile_outfile"></parallelism-->
7 <expand macro="xrefs"/>
7 <expand macro="requirements" /> 8 <expand macro="requirements" />
8 <expand macro="stdio" /> 9 <expand macro="stdio" />
9 <expand macro="xrefs"/>
10 <command> 10 <command>
11 <![CDATA[ 11 <![CDATA[
12 cmbuild 12 cmbuild
13 -F 13 -F
14 #if $is_summery_output: 14 #if $is_summery_output:
194 <param name="cyk" type="select" label="Options for refining the input alignment" help=""> 194 <param name="cyk" type="select" label="Options for refining the input alignment" help="">
195 <option value="" selected="true">optimal accuracy algorithm</option> 195 <option value="" selected="true">optimal accuracy algorithm</option>
196 <option value="--cyk">align with the CYK algorithm</option> 196 <option value="--cyk">align with the CYK algorithm</option>
197 </param> 197 </param>
198 198
199 <param name="refine_output" truevalue="" falsevalue="" checked="False" type="boolean" 199 <param name="refine_output" truevalue="--refine" falsevalue="" checked="False" type="boolean"
200 label="Output the refined alignment file as it is used to build the covariance model" help=""/> 200 label="Output the refined alignment file as it is used to build the covariance model" help=""/>
201 201
202 </when> 202 </when>
203 </conditional> 203 </conditional>
204 204
205 <param name="is_summery_output" truevalue="" falsevalue="" checked="False" type="boolean" 205 <param name="is_summery_output" truevalue="-o" falsevalue="" checked="False" type="boolean"
206 label="Output a summery file?" help=""/> 206 label="Output a summery file?" help=""/>
207 207
208 <!-- calibrate options --> 208 <!-- calibrate options -->
209 <conditional name="Calibrate"> 209 <conditional name="Calibrate">
210 <param name="selector" type="boolean" checked="true" label="Calibrate the covariance model" 210 <param name="selector" type="select" label="Calibrate the covariance model"
211 help="A CM file must be calibrated with cmcalibrate before it can be used in cmsearch or cmscan. cmcalibrate is very slow. It takes a couple of hours to calibrate a single average sized CM on a single CPU"/> 211 help="A CM file must be calibrated with cmcalibrate before it can be used in cmsearch or cmscan. cmcalibrate is very slow. It takes a couple of hours to calibrate a single average sized CM on a single CPU">
212 <option value="true">Yes</option>
213 <option value="false">No</option>
214 </param>
212 <when value="false"/> 215 <when value="false"/>
213 <when value="true"> 216 <when value="true">
214 <param argument="-L" type="float" value="1.6" min="0.01" max="160" label="Total length of random sequences to search" help="Set random seq length to search in Mb (megabases)"/> 217 <param argument="-L" type="float" value="1.6" min="0.01" max="160" label="Total length of random sequences to search" help="Set random seq length to search in Mb (megabases)"/>
215 <conditional name="cont_exp_tails_fits" > 218 <conditional name="cont_exp_tails_fits" >
216 <param name="selector" type="select" label="Options controlling exponential tail fits"> 219 <param name="selector" type="select" label="Options controlling exponential tail fits">
323 </data> 326 </data>
324 327
325 </outputs> 328 </outputs>
326 329
327 <tests> 330 <tests>
328 <test> 331 <test expect_num_outputs="1">
329 <param name="alignment_infile" value="cmbuild_input_tRNA5.sto"/> 332 <param name="alignment_infile" value="cmbuild_input_tRNA5.sto"/>
330 <conditional name="Calibrate"> 333 <conditional name="Calibrate">
331 <param name="selector" value="true"/> 334 <param name="selector" value="true"/>
332 <param name="L" value="0.1"/> 335 <param name="L" value="0.1"/>
333 </conditional> 336 </conditional>
336 <has_text text="S 0 -1 0 1 4 0 1 89 109 -7.220 -8.465 -0.063 -4.919"/> 339 <has_text text="S 0 -1 0 1 4 0 1 89 109 -7.220 -8.465 -0.063 -4.919"/>
337 </assert_contents> 340 </assert_contents>
338 </output> 341 </output>
339 </test> 342 </test>
340 <!-- Test emax seq parameter --> 343 <!-- Test emax seq parameter -->
341 <test> 344 <test expect_num_outputs="1">
342 <param name="alignment_infile" value="cmbuild_input_tRNA5.sto"/> 345 <param name="alignment_infile" value="cmbuild_input_tRNA5.sto"/>
343 <conditional name="Calibrate"> 346 <conditional name="Calibrate">
344 <param name="selector" value="true"/> 347 <param name="selector" value="true"/>
345 <param name="L" value="0.1"/> 348 <param name="L" value="0.1"/>
346 </conditional> 349 </conditional>
420 **Options controlling relative weights** 423 **Options controlling relative weights**
421 424
422 425
423 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. 426 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.
424 427
425 - *--wgb*: Use the Henikoff position-based sequence weighting scheme [Henikoff 428 - *--wgb*: Use the Henikoff position-based sequence weighting scheme [Henikoff and Henikoff, J. Mol. Biol. 243:574, 1994]. This is the default.
426 and Henikoff, J. Mol. Biol. 243:574, 1994]. This is the default.
427 - *--wgsc*: Use the Gerstein/Sonnhammer/Chothia weighting algorithm [Gerstein et al, J. Mol. Biol. 235:1067, 1994]. 429 - *--wgsc*: Use the Gerstein/Sonnhammer/Chothia weighting algorithm [Gerstein et al, J. Mol. Biol. 235:1067, 1994].
428 - *--wnone*: Turn sequence weighting off; e.g. explicitly set all sequence weights to 1.0. 430 - *--wnone*: Turn sequence weighting off; e.g. explicitly set all sequence weights to 1.0.
429 - *--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. 431 - *--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.
430 - *--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. 432 - *--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.
431 433