Mercurial > repos > greg > multigps

comparison multigps.xml @ 51:4c5540844bb3 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author greg
date Wed, 05 Sep 2018 08:54:21 -0400
parents 20687c85887e
children
comparison
equal deleted inserted replaced
50:20687c85887e 51:4c5540844bb3
1 <tool id="multigps" name="MultiGPS" version="0.73.0"> 1 <tool id="multigps" name="MultiGPS" version="0.74.0">
2 <description>analyzes collections of multi-condition ChIP-seq data</description> 2 <description>analyzes collections of multi-condition ChIP-seq data</description>
3 <macros> 3 <macros>
4 <import>macros.xml</import> 4 <import>macros.xml</import>
5 </macros> 5 </macros>
6 <requirements> 6 <requirements>
7 <requirement type="package" version="0.73">multigps</requirement> 7 <requirement type="package" version="0.74">multigps</requirement>
8 </requirements> 8 </requirements>
9 <command detect_errors="aggressive"> 9 <command detect_errors="aggressive">
10 <![CDATA[ 10 <![CDATA[
11 #set output_dir = $output_html.files_path 11 #set output_dir = $output_html.files_path
12 mkdir -p $output_dir && 12 mkdir -p $output_dir &&
13 multigps 13 multigps
14 ## General options 14 ## General options
15 --design '$build_design_file'
15 ## Append .txt extensions to events hrefs 16 ## Append .txt extensions to events hrefs
16 ## in output dataset so files will render 17 ## in output dataset so files will render
17 ## in the browser. 18 ## in the browser.
18 --eventsaretxt 19 --eventsaretxt
19 ## Do not run the parallel version of meme 20 ## Do not run the parallel version of meme.
20 ## since it is not yet available in conda.
21 --meme1proc 21 --meme1proc
22 --expt '$expt' 22 --threads \${GALAXY_SLOTS:-4}
23 --format $expt.ext
24 #if str($ctrl) != 'None':
25 --ctrl '$ctrl'
26 #end if
27 --threads=\${GALAXY_SLOTS:-4}
28 --geninfo '$chromInfo' 23 --geninfo '$chromInfo'
29 ## Advanced options 24 ## Advanced options
30 #set aoc = $advanced_options_cond 25 #set aoc = $advanced_options_cond
31 #if str($aoc.advanced_options) == 'display': 26 #if str($aoc.advanced_options) == 'display':
32 #set bmsc = $aoc.binding_model_smoothing_cond 27 #set bmsc = $aoc.binding_model_smoothing_cond
35 #set rloc = $aoc.reads_limits_options_cond 30 #set rloc = $aoc.reads_limits_options_cond
36 #set sdc = $aoc.scale_data_cond 31 #set sdc = $aoc.scale_data_cond
37 #set umc = $aoc.use_motif_cond 32 #set umc = $aoc.use_motif_cond
38 #if str($umc.use_motif) == 'yes': 33 #if str($umc.use_motif) == 'yes':
39 #set rgc = $umc.reference_genome_cond 34 #set rgc = $umc.reference_genome_cond
35 --seq
40 #if str($rgc.reference_genome_source) == 'cached': 36 #if str($rgc.reference_genome_source) == 'cached':
41 #set seq = $rgc.reference_genome.fields.path 37 '${rgc.reference_genome.fields.path}'
42 #else: 38 #else:
43 #set seq = $rgc.reference_genome 39 '${rgc.reference_genome}'
44 #end if 40 #end if
45 --seq '$seq'
46 #end if 41 #end if
47 ## Limits on how many reads 42 ## Limits on how many reads
48 #if str($rloc.reads_limits) == 'yes': 43 #if str($rloc.reads_limits) == 'yes':
49 --fixedpb $rloc.fixedpb 44 --fixedpb $rloc.fixedpb
50 --poissongausspb $rloc.poissongausspb 45 --poissongausspb $rloc.poissongausspb
78 --plotscaling $sdc.plotscaling 73 --plotscaling $sdc.plotscaling
79 #end if 74 #end if
80 #end if 75 #end if
81 ## Running MultiGPS 76 ## Running MultiGPS
82 #if str($aoc.readdistributionfile) != 'None': 77 #if str($aoc.readdistributionfile) != 'None':
83 --d '$aoc.readdistributionfile' 78 --readdistributionfile '$aoc.readdistributionfile'
84 #end if 79 #end if
85 --r $aoc.maxtrainingrounds 80 --maxtrainingrounds $aoc.maxtrainingrounds
86 #if str($aoc.nomodelupdate) == 'no': 81 #if str($aoc.nomodelupdate) == 'no':
87 --nomodelupdate 82 --nomodelupdate
88 #end if 83 #end if
89 --minmodelupdateevents $aoc.minmodelupdateevents 84 --minmodelupdateevents $aoc.minmodelupdateevents
90 #if str($bmsc.nomodelsmoothing) == 'no': 85 #if str($bmsc.nomodelsmoothing) == 'no':
125 #if str($bmc.nomotifs) == 'yes': 120 #if str($bmc.nomotifs) == 'yes':
126 --memenmotifs $bmc.memenmotifs 121 --memenmotifs $bmc.memenmotifs
127 --mememinw $bmc.mememinw 122 --mememinw $bmc.mememinw
128 --mememaxw $bmc.mememaxw 123 --mememaxw $bmc.mememaxw
129 #else: 124 #else:
130 #set mfoc = $bmc.nomotifprior_cond 125 #set nmpc = $bmc.nomotifprior_cond
131 --nomotifs 126 --nomotifs
132 --nomotifprior $mfoc.nomotifprior 127 #if str($nmpc.nomotifprior) == 'yes':
133 #if str($mfoc.nomotifprior) == 'yes': 128 --nomotifprior
134 --memenmotifs $mfoc.memenmotifs 129 --memenmotifs $nmpc.memenmotifs
135 --mememinw $mfoc.mememinw 130 --mememinw $nmpc.mememinw
136 --mememaxw $mfoc.mememaxw 131 --mememaxw $nmpc.mememaxw
137 #end if 132 #end if
138 #end if 133 #end if
139 #end if 134 #end if
140 #end if 135 #end if
141 ## Reporting binding events 136 ## Reporting binding events
142 #if str($rbec.report_binding_events) == 'yes': 137 #if str($rbec.report_binding_events) == 'yes':
143 --q $rbec.minqvalue 138 --minqvalue $rbec.minqvalue
144 --minfold $rbec.minfold 139 --minfold $rbec.minfold
145 #if str($rbec.nodifftests) == 'no': 140 #if str($rbec.nodifftests) == 'no':
146 --nodifftests 141 --nodifftests
147 #end if 142 #end if
148 --edgerod $rbec.edgerod 143 --edgerod $rbec.edgerod
149 --diffp $rbec.diffp 144 --diffp $rbec.diffp
150 #end if 145 #end if
151 #end if 146 #end if
152 >/dev/null 147 2>&1
153 --out '$output_html.files_path' 148 --out '$output_html.files_path'
154 && cp $output_dir/*.events.txt '$experiment_events' || true 149 #if str($save_design_file) == 'yes':
155 && mv $output_dir/*.html '$output_html' || true 150 && cp '$build_design_file' '$output_design_file'
156 && mv $output_dir/*.table.txt '$all_events_table' || true 151 #end if
157 && mv $output_dir/*.counts '$replicates_counts' || true 152 && mv $output_dir/*.counts '$replicates_counts'
153 && mv $output_dir/*.bed '$output_bed'
154 && mv $output_dir/*.html '$output_html'
155 && mv $output_dir/*.table.txt '$all_events_table'
158 ]]> 156 ]]>
159 </command> 157 </command>
158 <configfiles>
159 <configfile name="build_design_file"><![CDATA[#for $condition_items in $condition_repeat:
160 #for $signal_items in $condition_items.signal_repeat:
161 #if str($signal_items.fixedreadcount_cond.fixedreadcount_select) == 'yes':
162 #set $frc = $signal_items.fixedreadcount_cond.fixedreadcount
163 #else:
164 #set $frc = ''
165 #end if
166 ${signal_items.signal} Signal ${signal_items.signal.ext.upper()} ${condition_items.condition_name} ${signal_items.replicate_name} ${condition_items.experiment_type} ${frc}
167 #end for
168 #for $control_items in $condition_items.control_repeat:
169 #if str($control_items.specify_replicate_name_cond.specify_replicate_name) == 'yes':
170 #set $rn = $control_items.specify_replicate_name_cond.replicate_name
171 #else:
172 #set $rn = ''
173 #end if
174 #if str($control_items.fixedreadcount_cond.fixedreadcount_select) == 'yes':
175 #set $frc = $control_items.fixedreadcount_cond.fixedreadcount
176 #else:
177 #set $frc = ''
178 #end if
179 ${control_items.control} Control ${control_items.control.ext.upper()} ${condition_items.condition_name} ${rn} ${condition_items.experiment_type} ${frc}
180 #end for
181 #end for ]]></configfile>
182 </configfiles>
160 <inputs> 183 <inputs>
161 <param name="expt" type="data" format="bam,bed,scidx" label="Run MultiGPS on"> 184 <repeat name="condition_repeat" title="Condition" min="1">
162 <validator type="unspecified_build" /> 185 <param name="condition_name" type="text" value="cond" label="Condition name">
186 <validator type="empty_field" />
187 </param>
188 <expand macro="param_experiment_type" />
189 <repeat name="signal_repeat" title="Signal" min="1">
190 <param name="signal" type="data" format="bam,bed,scidx" label="Select signal" help="Supported formats are bam, bed and scidx">
191 <validator type="unspecified_build" />
192 </param>
193 <param name="replicate_name" type="text" value="1" label="Replicate name">
194 <validator type="empty_field" />
195 </param>
196 <expand macro="cond_fixedreadcount" />
197 </repeat>
198 <repeat name="control_repeat" title="Control" min="0">
199 <param name="control" type="data" format="bam,bed,scidx" label="Select control" help="Optional, supported formats are bam, bed and scidx">
200 <validator type="unspecified_build" />
201 </param>
202 <conditional name="specify_replicate_name_cond">
203 <param name="specify_replicate_name" type="select" label="Specify replicate name?" help="Optional for control. If used, the control will only be used for the corresponding named signal replicate">
204 <option value="no" selected="True">No</option>
205 <option value="yes">Yes</option>
206 </param>
207 <when value="yes">
208 <param name="replicate_name" type="text" optional="true" label="Replicate name"/>
209 </when>
210 <when value="no" />
211 </conditional>
212 <expand macro="cond_fixedreadcount" />
213 </repeat>
214 </repeat>
215 <param name="save_design_file" type="select" display="radio" label="Output design file?">
216 <option value="no" selected="true">No</option>
217 <option value="yes">Yes</option>
163 </param> 218 </param>
164 <param name="ctrl" type="data" format="bam,bed,scidx" optional="True" label="Optional file containing reads from a control experiment" help="Must be same forat as the input above" />
165 <!-- Advanced options --> 219 <!-- Advanced options -->
166 <conditional name="advanced_options_cond"> 220 <conditional name="advanced_options_cond">
167 <param name="advanced_options" type="select" label="Advanced options"> 221 <param name="advanced_options" type="select" label="Advanced options">
168 <option value="hide" selected="true">Hide</option> 222 <option value="hide" selected="true">Hide</option>
169 <option value="display">Display</option> 223 <option value="display">Display</option>
190 </param> 244 </param>
191 </when> 245 </when>
192 </conditional> 246 </conditional>
193 <!-- Scaling data --> 247 <!-- Scaling data -->
194 <conditional name="scale_data_cond"> 248 <conditional name="scale_data_cond">
195 <param name="scale_data" type="select" label="Set data scaling parameters?" help="Default behavior is to scale signal to corresponding controls using regression on the set of signal/control ratios in 10Kbp windows."> 249 <param name="scale_data" type="select" label="Set data scaling parameters?" help="Default behavior is to scale signal to corresponding controls using the Normalization of ChIP-seq (NCIS) method.[2]">
196 <option value="no" selected="True">No</option> 250 <option value="no" selected="True">No</option>
197 <option value="yes">Yes</option> 251 <option value="yes">Yes</option>
198 </param> 252 </param>
199 <when value="yes"> 253 <when value="yes">
200 <param name="scaling" type="select" label="Use signal vs control scaling?"> 254 <param name="scaling" type="select" label="Use signal vs control scaling?">
280 <option value="history">from history</option> 334 <option value="history">from history</option>
281 </param> 335 </param>
282 <when value="cached"> 336 <when value="cached">
283 <param name="reference_genome" type="select" label="Using reference genome"> 337 <param name="reference_genome" type="select" label="Using reference genome">
284 <options from_data_table="all_fasta"> 338 <options from_data_table="all_fasta">
285 <filter type="data_meta" key="dbkey" ref="expt" column="1"/> 339 <!-- <filter type="data_meta" key="dbkey" ref="expt" column="1"/> does not yet work in a repeat...-->
286 </options> 340 </options>
287 <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/> 341 <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/>
288 </param> 342 </param>
289 </when> 343 </when>
290 <when value="history"> 344 <when value="history">
291 <param name="reference_genome" type="data" format="fasta" label="Using reference genome"> 345 <param name="reference_genome" type="data" format="fasta" label="Using reference genome">
292 <options> 346 <options>
293 <filter type="data_meta" key="dbkey" ref="expt"/> 347 <!-- <filter type="data_meta" key="dbkey" ref="expt"/> does not yet work in a repeat...-->
294 </options> 348 </options>
295 <validator type="no_options" message="The current history does not include a fasta dataset with the build associated with the selected input file"/> 349 <validator type="no_options" message="The current history does not include a fasta dataset with the build associated with the selected input file"/>
296 </param> 350 </param>
297 </when> 351 </when>
298 </conditional> 352 </conditional>
356 </when> 410 </when>
357 <when value="hide" /> 411 <when value="hide" />
358 </conditional> 412 </conditional>
359 </inputs> 413 </inputs>
360 <outputs> 414 <outputs>
361 <data name="replicates_counts" format="tabular" label="${tool.name} replicates counts on ${on_string}"/> 415 <data name="output_design_file" format="tabular" label="${tool.name} (design file) on ${on_string}">
362 <data name="all_events_table" format="tabular" label="${tool.name} all events table on ${on_string}"/> 416 <filter>save_design_file == 'yes'</filter>
363 <data name="experiment_events" format="tabular" label="${tool.name} experiment events on ${on_string}"/> 417 </data>
364 <data name="output_html" format="html" label="${tool.name} on ${on_string}"/> 418 <data name="output_bed" format="bed" label="${tool.name} (bed) on ${on_string}"/>
419 <data name="output_html" format="html" label="${tool.name} (html) on ${on_string}"/>
420 <data name="replicates_counts" format="tabular" label="${tool.name} (replicates counts) on ${on_string}"/>
421 <data name="all_events_table" format="tabular" label="${tool.name} (all events table) on ${on_string}"/>
365 </outputs> 422 </outputs>
366 <tests> 423 <tests>
367 <test> 424 <test>
368 <param name="expt" value="expt_hg19.scidx" ftype="scidx" dbkey="hg19" /> 425 <repeat name="condition_repeat">
369 <param name="advanced_options_cond" value="hide" /> 426 <repeat name="signal_repeat">
370 <output name="output_html" file="hg19_output_html1.html" ftype="html" lines_diff="12"/> 427 <param name="signal" value="expt_hg19.scidx" ftype="scidx" dbkey="hg19" />
428 </repeat>
429 </repeat>
430 <param name="advanced_options" value="hide" />
431 <output name="output_html" file="hg19_output_html1.html" ftype="html" compare="contains"/>
432 <output name="output_bed" file="hg19_output_bed1.bed" ftype="bed"/>
371 <output name="all_events_table" file="hg19_all_events_table1.tabular" ftype="tabular"/> 433 <output name="all_events_table" file="hg19_all_events_table1.tabular" ftype="tabular"/>
372 <output name="replicates_counts" file="hg19_replicates_counts1.tabular" ftype="tabular"/> 434 <output name="replicates_counts" file="hg19_replicates_counts1.tabular" ftype="tabular"/>
373 </test> 435 </test>
374 <test> 436 <test>
375 <param name="expt" value="expt_hg19.scidx" ftype="bam" dbkey="hg19" /> 437 <repeat name="condition_repeat">
376 <param name="ctrl" value="cntrl_hg19.scidx" ftype="bam" dbkey="hg19" /> 438 <repeat name="signal_repeat">
377 <param name="advanced_options_cond" value="display" /> 439 <param name="signal" value="expt_hg19.scidx" ftype="scidx" dbkey="hg19" />
378 <output name="output_html" file="hg19_output_html2.html" ftype="html" lines_diff="12"/> 440 </repeat>
441 <repeat name="control_repeat">
442 <param name="control" value="cntrl_hg19.scidx" ftype="scidx" dbkey="hg19" />
443 </repeat>
444 </repeat>
445 <param name="advanced_options" value="display" />
446 <output name="output_html" file="hg19_output_html2.html" ftype="html" compare="contains"/>
447 <output name="output_bed" file="hg19_output_bed2.bed" ftype="bed"/>
379 <output name="all_events_table" file="hg19_all_events_table2.tabular" ftype="tabular"/> 448 <output name="all_events_table" file="hg19_all_events_table2.tabular" ftype="tabular"/>
380 <output name="replicates_counts" file="hg19_replicates_counts2.tabular" ftype="tabular"/> 449 <output name="replicates_counts" file="hg19_replicates_counts2.tabular" ftype="tabular"/>
381 </test> 450 </test>
382 </tests> 451 </tests>
383 <help> 452 <help>
385 **What it does** 454 **What it does**
386 455
387 MultiGPS is a framework for analyzing collections of multi-condition ChIP-seq datasets and characterizing 456 MultiGPS is a framework for analyzing collections of multi-condition ChIP-seq datasets and characterizing
388 differential binding events between conditions. MultiGPS encourages consistency in the reported binding 457 differential binding events between conditions. MultiGPS encourages consistency in the reported binding
389 event locations across conditions and provides accurate estimation of ChIP enrichment levels at each event. 458 event locations across conditions and provides accurate estimation of ChIP enrichment levels at each event.
390 MultiGPS loads all data to memory, so you will need a lot of available memory if you are running analysis 459 MultiGPS performs significant EM optimization of binding events along the genome and across experimental
391 over many conditions or large datasets. 460 conditions, and it integrates motif-finding via MEME. The tool loads all data into memory, so the potential
461 exists for time and memory intensive analyses if running over many conditions or large datasets.
392 462
393 ----- 463 -----
394 464
395 **Options** 465 **Options**
396 466
397 * **Loading data:** 467 * **Loading data:**
398 468
399 - **Optional file containing reads from a control experiment** - must be same format as input experiment 469 - **Optional file containing reads from a control experiment** - file containing reads from a control experiment
400 - **Fixed per-base limit** - Fixed per-base limit (default: estimated from background model). 470 - **Fixed per-base limit** - Fixed per-base limit (default: estimated from background model).
401 - **Poisson threshold for filtering per base** - Look at neighboring positions to decide what the per-base limit should be. 471 - **Poisson threshold for filtering per base** - Look at neighboring positions to decide what the per-base limit should be.
402 - **Use non-unique reads** - Use non-unique reads. 472 - **Use non-unique reads** - Use non-unique reads.
403 - **Fraction of the genome that is mappable for these experiments** - Fraction of the genome that is mappable for these experiments 473 - **Fraction of the genome that is mappable for these experiments** - Fraction of the genome that is mappable for these experiments
404 - **Turn off caching of the entire set of experiments?** - Flag to turn off caching of the entire set of experiments (i.e. run slower with less memory). 474 - **Turn off caching of the entire set of experiments?** - Flag to turn off caching of the entire set of experiments (i.e. run slower with less memory).
448 - **EdgeR over-dispersion parameter value** - EdgeR over-dispersion parameter value. 518 - **EdgeR over-dispersion parameter value** - EdgeR over-dispersion parameter value.
449 - **Minimum p-value for reporting differential enrichment** - Minimum p-value for reporting differential enrichment. 519 - **Minimum p-value for reporting differential enrichment** - Minimum p-value for reporting differential enrichment.
450 520
451 </help> 521 </help>
452 <citations> 522 <citations>
453 <citation type="doi">10.1371/journal.pcbi.1003501</citation> 523 <citation type="bibtex">
524 @article{Mahony2014,
525 journal = {PLOS Computational Biology},
526 author = {1. Mahony S, Edwards MD, Mazzoni EO, Sherwood RI, Kakumanu A, Morrison CA, Wichterle H, Gifford DK},
527 title = {An Integrated Model of Multiple-Condition ChIP-Seq Data Reveals Predeterminants of Cdx2 Binding},
528 year = {2014},}
529 volume = {10},
530 number = {3},
531 pages = {e1003501},}
532 </citation>
533 <citation type="bibtex">
534 @article{Liang2012,
535 journal = {BMC Bioinformatics},
536 author = {2. Liang, Ketes},
537 title = {Normalization of ChIP-seq data with control},
538 year = {2012},}
539 </citation>
454 </citations> 540 </citations>
455 </tool> 541 </tool>
542