|
2
|
1 <tool id="multigps" name="MultiGPS" version="0.74.0">
|
|
0
|
2 <description>analyzes collections of multi-condition ChIP-seq data</description>
|
|
|
3 <macros>
|
|
|
4 <import>macros.xml</import>
|
|
|
5 </macros>
|
|
|
6 <requirements>
|
|
2
|
7 <requirement type="package" version="0.74">multigps</requirement>
|
|
0
|
8 </requirements>
|
|
|
9 <command detect_errors="aggressive">
|
|
|
10 <![CDATA[
|
|
5
|
11 #set output_dir = $output_html.files_path
|
|
|
12 mkdir -p $output_dir &&
|
|
6
|
13 python '$design_file_script' '$inputs' &&
|
|
5
|
14 multigps
|
|
0
|
15 ## General options
|
|
2
|
16 #set single_or_multi_expt = $single_or_multi_expt_cond.single_or_multi_expt
|
|
|
17 #if str($single_or_multi_expt) == 'multi':
|
|
|
18 #for $i in $single_or_multi_expt_cond['input_items']:
|
|
|
19 #set label_cond = $i['label_cond']
|
|
4
|
20 #set experiment_file_name = $label_cond.input
|
|
2
|
21 #set label = $label_cond.label
|
|
3
|
22 #set file_format = $label_cond.input.ext
|
|
4
|
23 #set control_file_name = $label_cond.control
|
|
3
|
24 #set condition_name = $label_cond.condition_name
|
|
2
|
25 #set replicate_name = 'None'
|
|
3
|
26 #set experiment_type = $label_cond.experiment_type
|
|
|
27 #set fixed_read_count = $label_cond.fixedreadcount
|
|
2
|
28 #if str($label) == 'Signal':
|
|
3
|
29 #set replicate_name = $label_cond.replicate_name
|
|
2
|
30 #else if str($label) == 'Control':
|
|
3
|
31 #set rncond = $label_cond.replicate_name_cond
|
|
|
32 #if str($rncond.specify_replicate_name) == 'yes':
|
|
|
33 #set replicate_name = $rncond.replicate_name
|
|
2
|
34 #end if
|
|
|
35 #end if
|
|
4
|
36 --input_item '$experiment_file_name' '$control_file_name' '$label' '$file_format' '$condition_name' '$replicate_name' '$experiment_type' '$fixed_read_count'
|
|
2
|
37 #end for
|
|
|
38 #else:
|
|
|
39 #set expt = $single_or_multi_expt_cond.expt
|
|
|
40 #set control = $single_or_multi_expt_cond.control
|
|
|
41 --expt '$expt'
|
|
|
42 --format $expt.ext
|
|
|
43 #if str($control) != 'None':
|
|
|
44 --control '$control'
|
|
|
45 #end if
|
|
|
46 #end if
|
|
0
|
47 ## Append .txt extensions to events hrefs
|
|
|
48 ## in output dataset so files will render
|
|
|
49 ## in the browser.
|
|
5
|
50 --eventsaretxt
|
|
2
|
51 ## Do not run the parallel version of meme.
|
|
5
|
52 --meme1proc
|
|
0
|
53 --threads \${GALAXY_SLOTS:-4}
|
|
5
|
54 --geninfo '$chromInfo'
|
|
0
|
55 ## Advanced options
|
|
|
56 #set aoc = $advanced_options_cond
|
|
|
57 #if str($aoc.advanced_options) == 'display':
|
|
|
58 #set bmsc = $aoc.binding_model_smoothing_cond
|
|
|
59 #set gmsc = $aoc.gauss_model_smoothing_cond
|
|
|
60 #set rbec = $aoc.report_binding_events_cond
|
|
|
61 #set rloc = $aoc.reads_limits_options_cond
|
|
|
62 #set sdc = $aoc.scale_data_cond
|
|
|
63 #set umc = $aoc.use_motif_cond
|
|
|
64 #if str($umc.use_motif) == 'yes':
|
|
|
65 #set rgc = $umc.reference_genome_cond
|
|
|
66 --seq
|
|
|
67 #if str($rgc.reference_genome_source) == 'cached':
|
|
2
|
68 '${rgc.reference_genome.fields.path}'
|
|
0
|
69 #else:
|
|
2
|
70 '${rgc.reference_genome}'
|
|
0
|
71 #end if
|
|
|
72 #end if
|
|
|
73 ## Limits on how many reads
|
|
|
74 #if str($rloc.reads_limits) == 'yes':
|
|
|
75 --fixedpb $rloc.fixedpb
|
|
|
76 --poissongausspb $rloc.poissongausspb
|
|
|
77 #if str($rloc.nonunique) == 'yes':
|
|
5
|
78 --nonunique
|
|
0
|
79 #end if
|
|
|
80 --mappability $rloc.mappability
|
|
|
81 #if str($rloc.nocache) == 'yes':
|
|
5
|
82 --nocache
|
|
0
|
83 #end if
|
|
|
84 #end if
|
|
|
85 ## Scaling data
|
|
|
86 #if str($sdc.scale_data) == 'yes':
|
|
|
87 #if str($sdc.scaling) == 'no':
|
|
|
88 --noscaling $sdc.scaling
|
|
|
89 #end if
|
|
|
90 #if str($sdc.medianscale) == 'yes':
|
|
|
91 --medianscale $sdc.medianscale
|
|
|
92 #end if
|
|
|
93 #if str($sdc.regressionscale) == 'yes':
|
|
|
94 --regressionscale $sdc.regressionscale
|
|
|
95 #end if
|
|
|
96 #if str($sdc.sesscale) == 'yes':
|
|
|
97 --sesscale $sdc.sesscale
|
|
|
98 #end if
|
|
|
99 #if $sdc.fixedscaling > 0:
|
|
|
100 ‒‒fixedscaling $sdc.fixedscaling
|
|
|
101 #end if
|
|
|
102 --scalewin $sdc.scalewin
|
|
|
103 #if str($sdc.plotscaling) == 'yes':
|
|
|
104 --plotscaling $sdc.plotscaling
|
|
|
105 #end if
|
|
|
106 #end if
|
|
|
107 ## Running MultiGPS
|
|
|
108 #if str($aoc.readdistributionfile) != 'None':
|
|
2
|
109 --readdistributionfile '$aoc.readdistributionfile'
|
|
0
|
110 #end if
|
|
2
|
111 --maxtrainingrounds $aoc.maxtrainingrounds
|
|
0
|
112 #if str($aoc.nomodelupdate) == 'no':
|
|
5
|
113 --nomodelupdate
|
|
0
|
114 #end if
|
|
|
115 --minmodelupdateevents $aoc.minmodelupdateevents
|
|
|
116 #if str($bmsc.nomodelsmoothing) == 'no':
|
|
5
|
117 --nomodelsmoothing
|
|
0
|
118 #else:
|
|
|
119 --splinesmoothparam $bmsc.splinesmoothparam
|
|
|
120 #end if
|
|
|
121 #if str($gmsc.gaussmodelsmoothing) == 'yes':
|
|
5
|
122 --gaussmodelsmoothing
|
|
0
|
123 --gausssmoothparam $gmsc.gausssmoothparam
|
|
|
124 #end if
|
|
|
125 #if str($aoc.jointinmodel) == 'yes':
|
|
5
|
126 --jointinmodel
|
|
0
|
127 #end if
|
|
|
128 #if str($aoc.fixedmodelrange) == 'yes':
|
|
5
|
129 --fixedmodelrange
|
|
0
|
130 #end if
|
|
|
131 --prlogconf $aoc.prlogconf
|
|
|
132 #if $aoc.fixedalpha > 0:
|
|
|
133 --fixedalpha $aoc.fixedalpha
|
|
|
134 #end if
|
|
|
135 --alphascale $aoc.alphascale
|
|
|
136 #if str($aoc.mlconfignotshared) == 'no':
|
|
5
|
137 --mlconfignotshared
|
|
0
|
138 #end if
|
|
|
139 #if str($aoc.exclude) != 'None':
|
|
|
140 --exclude '$aoc.exclude'
|
|
|
141 #end if
|
|
|
142 ## MultiGPS priors
|
|
|
143 #if str($umc.use_motif) == 'yes':
|
|
|
144 #set mpc = $umc.multigps_priors_cond
|
|
|
145 #if str($mpc.multigps_priors) == 'yes':
|
|
|
146 #set bmc = $mpc.both_motifs_cond
|
|
|
147 #if str($mpc.noposprior) == 'no':
|
|
5
|
148 --noposprior
|
|
0
|
149 #end if
|
|
|
150 --probshared $mpc.probshared
|
|
|
151 #if str($bmc.nomotifs) == 'yes':
|
|
|
152 --memenmotifs $bmc.memenmotifs
|
|
|
153 --mememinw $bmc.mememinw
|
|
|
154 --mememaxw $bmc.mememaxw
|
|
|
155 #else:
|
|
2
|
156 #set nmpc = $bmc.nomotifprior_cond
|
|
5
|
157 --nomotifs
|
|
2
|
158 #if str($nmpc.nomotifprior) == 'yes':
|
|
5
|
159 --nomotifprior
|
|
2
|
160 --memenmotifs $nmpc.memenmotifs
|
|
|
161 --mememinw $nmpc.mememinw
|
|
|
162 --mememaxw $nmpc.mememaxw
|
|
0
|
163 #end if
|
|
|
164 #end if
|
|
|
165 #end if
|
|
|
166 #end if
|
|
|
167 ## Reporting binding events
|
|
|
168 #if str($rbec.report_binding_events) == 'yes':
|
|
2
|
169 --minqvalue $rbec.minqvalue
|
|
0
|
170 --minfold $rbec.minfold
|
|
|
171 #if str($rbec.nodifftests) == 'no':
|
|
5
|
172 --nodifftests
|
|
0
|
173 #end if
|
|
|
174 --edgerod $rbec.edgerod
|
|
|
175 --diffp $rbec.diffp
|
|
|
176 #end if
|
|
|
177 #end if
|
|
5
|
178 2>&1
|
|
|
179 --out '$output_html.files_path'
|
|
|
180 && mv $output_dir/*.counts '$replicates_counts'
|
|
|
181 && mv $output_dir/*.bed '$output_bed'
|
|
|
182 && mv $output_dir/*.html '$output_html'
|
|
|
183 && mv $output_dir/*.table.txt '$all_events_table'
|
|
0
|
184 ]]>
|
|
|
185 </command>
|
|
6
|
186 <configfiles>
|
|
|
187 <inputs name="inputs"/>
|
|
|
188 <configfile name="design_file_script">
|
|
|
189 <![CDATA[
|
|
|
190 import sys
|
|
|
191 import json
|
|
|
192
|
|
|
193 input_json_path = sys.argv[1]
|
|
|
194 params = json.load(open(input_json_path, "r"))
|
|
|
195
|
|
|
196 if params['single_or_multi_expt_cond']['single_or_multi_expt'] == 'multi':
|
|
|
197 input_items = params['single_or_multi_expt_cond']['input_items']
|
|
|
198 design_file = open('design.tabular', 'w')
|
|
|
199 for item in input_items:
|
|
|
200 experiment_file_name, control_file_name, label, file_format, condition_name, replicate_name, experiment_type, fixed_read_count = item
|
|
|
201 if control_file_name not in ['None', None, '']:
|
|
|
202 control_file_names.append(control_file_name)
|
|
|
203 file_format = file_format.upper()
|
|
|
204 items = [experiment_file_name, label, file_format, condition_name]
|
|
|
205 if replicate_name not in ['None', None, '']:
|
|
|
206 items.append(replicate_name)
|
|
|
207 if experiment_type not in ['None', None, '']:
|
|
|
208 items.append(experiment_type)
|
|
|
209 if fixed_read_count not in ['None', None, '']:
|
|
|
210 items.append(fixed_read_count)
|
|
|
211 design_file.write('%s\n' % '\t'.join(items))
|
|
|
212 design_file.close()
|
|
|
213 ]]>
|
|
|
214 </configfile>
|
|
|
215 </configfiles>
|
|
0
|
216 <inputs>
|
|
2
|
217 <conditional name="single_or_multi_expt_cond">
|
|
|
218 <param name="single_or_multi_expt" type="select" label="Run MultiGPS on single or multiple inputs?">
|
|
|
219 <option value="multi" selected="True">Multiple inputs</option>
|
|
|
220 <option value="single">Single input</option>
|
|
|
221 </param>
|
|
|
222 <when value="multi">
|
|
|
223 <repeat name="input_items" title="Input files, attributes and options" min="2">
|
|
|
224 <conditional name="label_cond">
|
|
|
225 <param name="label" type="select" label="This experiment is">
|
|
|
226 <option value="Signal" selected="True">Signal</option>
|
|
|
227 <option value="Control">Control</option>
|
|
|
228 </param>
|
|
|
229 <when value="Signal">
|
|
3
|
230 <expand macro="label_cond_params_start" />
|
|
2
|
231 <param name="replicate_name" type="text" label="Replicate name" />
|
|
3
|
232 <expand macro="label_cond_params_end" />
|
|
2
|
233 </when>
|
|
|
234 <when value="Control">
|
|
3
|
235 <expand macro="label_cond_params_start" />
|
|
2
|
236 <conditional name="replicate_name_cond">
|
|
|
237 <param name="specify_replicate_name" type="select" label="Specify replicate name?" help="Optional for control experiments. If used, the control will only be used for the corresponding named signal replicate">
|
|
|
238 <option value="no" selected="True">No</option>
|
|
|
239 <option value="yes">Yes</option>
|
|
|
240 </param>
|
|
|
241 <when value="yes">
|
|
|
242 <param name="replicate_name" type="text" optional="True" label="Replicate name"/>
|
|
|
243 </when>
|
|
|
244 <when value="no" />
|
|
|
245 </conditional>
|
|
3
|
246 <expand macro="label_cond_params_end" />
|
|
2
|
247 </when>
|
|
|
248 </conditional>
|
|
|
249 </repeat>
|
|
|
250 </when>
|
|
|
251 <when value="single">
|
|
|
252 <param name="expt" type="data" format="bam,bed,scidx" label="Run MultiGPS on">
|
|
|
253 <validator type="unspecified_build" />
|
|
|
254 </param>
|
|
|
255 <param name="control" 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" />
|
|
|
256 </when>
|
|
|
257 </conditional>
|
|
0
|
258 <!-- Advanced options -->
|
|
|
259 <conditional name="advanced_options_cond">
|
|
|
260 <param name="advanced_options" type="select" label="Advanced options">
|
|
|
261 <option value="hide" selected="true">Hide</option>
|
|
|
262 <option value="display">Display</option>
|
|
|
263 </param>
|
|
|
264 <when value="display">
|
|
|
265 <!-- Limits on how many reads -->
|
|
|
266 <conditional name="reads_limits_options_cond">
|
|
|
267 <param name="reads_limits" type="select" label="Set limits on how many reads can have their 5′ end at the same position in each replicate?" help="Default behavior is to estimate a global per-base limit from a Poisson distribution parameterized by the number of reads divided by the number of mappable bases in the genome. The per-base limit is set as the count corresponding to the 10^-7 probability level from the Poisson.">
|
|
|
268 <option value="no" selected="True">No</option>
|
|
|
269 <option value="yes">Yes</option>
|
|
|
270 </param>
|
|
|
271 <when value="no" />
|
|
|
272 <when value="yes">
|
|
|
273 <param name="fixedpb" type="integer" value="0" min="0" label="Fixed per-base limit" help="Zero value estimates from background model"/>
|
|
|
274 <param name="poissongausspb" type="integer" value="0" min="0" label="Poisson threshold for filtering per base" help="Filter per base using the specified Poisson threshold parameterized by a local Gaussian sliding window" />
|
|
|
275 <param name="nonunique" type="select" label="Use non-unique reads?">
|
|
|
276 <option value="no" selected="True">No</option>
|
|
|
277 <option value="yes">Yes</option>
|
|
|
278 </param>
|
|
|
279 <param name="mappability" type="float" value="0.0" min="0.8" label="Fraction of the genome that is mappable for these experiments" />
|
|
|
280 <param name="nocache" type="select" label="Turn off caching of the entire set of experiments?" help="Run slower with less memory" >
|
|
|
281 <option value="no" selected="True">No</option>
|
|
|
282 <option value="yes">Yes</option>
|
|
|
283 </param>
|
|
|
284 </when>
|
|
|
285 </conditional>
|
|
|
286 <!-- Scaling data -->
|
|
|
287 <conditional name="scale_data_cond">
|
|
|
288 <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.">
|
|
|
289 <option value="no" selected="True">No</option>
|
|
|
290 <option value="yes">Yes</option>
|
|
|
291 </param>
|
|
|
292 <when value="yes">
|
|
|
293 <param name="scaling" type="select" label="Use signal vs control scaling?">
|
|
|
294 <option value="yes" selected="True">Yes</option>
|
|
|
295 <option value="no">No</option>
|
|
|
296 </param>
|
|
|
297 <param name="medianscale" type="select" label="Use the median signal/control ratio as the scaling factor?">
|
|
|
298 <option value="no" selected="True">No</option>
|
|
|
299 <option value="yes">Yes</option>
|
|
|
300 </param>
|
|
|
301 <param name="regressionscale" type="select" label="Use scaling by regression on binned tag counts?">
|
|
|
302 <option value="no" selected="True">No</option>
|
|
|
303 <option value="yes">Yes</option>
|
|
|
304 </param>
|
|
|
305 <param name="sesscale" type="select" label="Estimate scaling factor by SES?" help="SES: Diaz, et al. Stat Appl Genet Mol Biol. 2012">
|
|
|
306 <option value="no" selected="True">No</option>
|
|
|
307 <option value="yes">Yes</option>
|
|
|
308 </param>
|
|
|
309 <param name="fixedscaling" type="float" value="0.0" min="0.0" label="Multiply control counts by total tag count ratio and then by this factor" help="Set as 0 to skip" />
|
|
|
310 <param name="scalewin" type="integer" min="0" value="500" label="Window size for estimating scaling ratios" help="The value is the number of base pairs. Use something much smaller than the default if scaling via SES (e.g. 200)." />
|
|
|
311 <param name="plotscaling" type="select" label="Plot diagnostic information for the chosen scaling method?">
|
|
|
312 <option value="no" selected="True">No</option>
|
|
|
313 <option value="yes">Yes</option>
|
|
|
314 </param>
|
|
|
315 </when>
|
|
|
316 <when value="no" />
|
|
|
317 </conditional>
|
|
|
318 <!-- Running MultiGPS -->
|
|
|
319 <param name="readdistributionfile" type="data" optional="True" format="tabular" label="Optional binding event read distribution file for initializing models" help="A default initial distribution appropriate for ChIP-seq data is used if this option is not specified." />
|
|
|
320 <param name="maxtrainingrounds" type="integer" value="3" min="0" label="Maximum number of training rounds for updating binding event read distributions" />
|
|
|
321 <param name="nomodelupdate" type="select" label="Perform binding model updates?">
|
|
|
322 <option value="yes" selected="True">Yes</option>
|
|
|
323 <option value="no">No</option>
|
|
|
324 </param>
|
|
|
325 <param name="minmodelupdateevents" type="integer" value="500" min="0" label="Minimum number of events to support an update of the read distribution" />
|
|
|
326 <conditional name="binding_model_smoothing_cond">
|
|
|
327 <param name="nomodelsmoothing" type="select" label="Perform binding model smoothing?" help="Smoothing performed with a cubic spline.">
|
|
|
328 <option value="yes" selected="True">Yes</option>
|
|
|
329 <option value="no">No</option>
|
|
|
330 </param>
|
|
|
331 <when value="yes">
|
|
|
332 <param name="splinesmoothparam" type="integer" value="30" min="0" label="Spline smoothing parameter" />
|
|
|
333 </when>
|
|
|
334 <when value="no" />
|
|
|
335 </conditional>
|
|
|
336 <conditional name="gauss_model_smoothing_cond">
|
|
|
337 <param name="gaussmodelsmoothing" type="select" label="Use Gaussian model smoothing?" help="Select No to smooth with a cubic spline.">
|
|
|
338 <option value="no" selected="True">No</option>
|
|
|
339 <option value="yes">Yes</option>
|
|
|
340 </param>
|
|
|
341 <when value="no" />
|
|
|
342 <when value="yes">
|
|
|
343 <param name="gausssmoothparam" type="integer" value="3" min="0" label="Smoothing factor" help="Gaussian smoothing standard deviation." />
|
|
|
344 </when>
|
|
|
345 </conditional>
|
|
|
346 <param name="jointinmodel" type="select" label="Allow joint events in model updates?">
|
|
|
347 <option value="no" selected="True">No</option>
|
|
|
348 <option value="yes">Yes</option>
|
|
|
349 </param>
|
|
|
350 <param name="fixedmodelrange" type="select" label="Keep binding model range fixed to inital size?" help="Select No to vary automatically">
|
|
|
351 <option value="no" selected="True">No</option>
|
|
|
352 <option value="yes">Yes</option>
|
|
|
353 </param>
|
|
|
354 <param name="prlogconf" type="integer" value="-6" label="Poisson log threshold for potential region scanning" />
|
|
|
355 <param name="fixedalpha" type="integer" value="0" min="0" label="Impose this alpha" help="This is a sparse prior on binding events in the MultiGPS model. It can be interpreted as a minimum number of reads that each binding event must be responsible for in the model. A zero value will estimate the alpha automatically." />
|
|
|
356 <param name="alphascale" type="float" value="1.0" min="0" label="Alpha scaling factor" />
|
|
|
357 <param name="mlconfignotshared" type="select" label="Share component configs in the ML step?" help="Mainly affects the quantification of binding levels for binding events that are not shared but are located at nearby locations across experiments.">
|
|
|
358 <option value="yes" selected="True">Yes</option>
|
|
|
359 <option value="no">No</option>
|
|
|
360 </param>
|
|
|
361 <param name="exclude" type="data" optional="True" format="txt" label="Optional file containing a set of regions to ignore during MultiGPS training" help="Ideally exclude the mitochondrial genome and other blacklisted regions that contain artifactual accumulations of reads in both ChIP-seq and control experiments." />
|
|
|
362 <!-- MultiGPS priors -->
|
|
|
363 <conditional name="use_motif_cond">
|
|
|
364 <param name="use_motif" type="select" label="Perform motif-finding or use a motif-prior?">
|
|
|
365 <option value="no" selected="True">No</option>
|
|
|
366 <option value="yes">Yes</option>
|
|
|
367 </param>
|
|
|
368 <when value="yes">
|
|
|
369 <!-- Specifying the genome -->
|
|
|
370 <conditional name="reference_genome_cond">
|
|
|
371 <param name="reference_genome_source" type="select" label="Choose the source for the reference genome">
|
|
|
372 <option value="cached">locally cached</option>
|
|
|
373 <option value="history">from history</option>
|
|
|
374 </param>
|
|
|
375 <when value="cached">
|
|
|
376 <param name="reference_genome" type="select" label="Using reference genome">
|
|
|
377 <options from_data_table="all_fasta">
|
|
2
|
378 <!-- <filter type="data_meta" key="dbkey" ref="expt" column="1"/> does not yet work in a repeat...-->
|
|
0
|
379 </options>
|
|
|
380 <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/>
|
|
|
381 </param>
|
|
|
382 </when>
|
|
|
383 <when value="history">
|
|
|
384 <param name="reference_genome" type="data" format="fasta" label="Using reference genome">
|
|
|
385 <options>
|
|
2
|
386 <!-- <filter type="data_meta" key="dbkey" ref="expt"/> does not yet work in a repeat...-->
|
|
0
|
387 </options>
|
|
|
388 <validator type="no_options" message="The current history does not include a fasta dataset with the build associated with the selected input file"/>
|
|
|
389 </param>
|
|
|
390 </when>
|
|
|
391 </conditional>
|
|
|
392 <!-- MultiGPS priors options -->
|
|
|
393 <conditional name="multigps_priors_cond">
|
|
|
394 <param name="multigps_priors" type="select" label="Specify MultiGPS priors options?">
|
|
|
395 <option value="no" selected="True">No</option>
|
|
|
396 <option value="yes">Yes</option>
|
|
|
397 </param>
|
|
|
398 <when value="no" />
|
|
|
399 <when value="yes">
|
|
|
400 <param name="noposprior" type="select" label="Perform inter-experiment positional prior?">
|
|
|
401 <option value="yes" selected="True">Yes</option>
|
|
|
402 <option value="no">No</option>
|
|
|
403 </param>
|
|
|
404 <param name="probshared" type="float" value="0.9" min="0.0" label="Probability that events are shared across conditions" />
|
|
|
405 <conditional name="both_motifs_cond">
|
|
|
406 <param name="nomotifs" type="select" label="Perform both motif-finding and motif priors?">
|
|
|
407 <option value="yes" selected="True">Yes</option>
|
|
|
408 <option value="no">No</option>
|
|
|
409 </param>
|
|
|
410 <when value="yes">
|
|
|
411 <expand macro="motif_finding_params" />
|
|
|
412 </when>
|
|
|
413 <when value="no">
|
|
|
414 <conditional name="nomotifprior_cond">
|
|
|
415 <param name="nomotifprior" type="select" label="Perform motif-finding only?" help="Selecting Yes turns off motif priors.">
|
|
|
416 <option value="no" selected="True">No</option>
|
|
|
417 <option value="yes">Yes</option>
|
|
|
418 </param>
|
|
|
419 <when value="no" />
|
|
|
420 <when value="yes">
|
|
|
421 <expand macro="motif_finding_params" />
|
|
|
422 </when>
|
|
|
423 </conditional>
|
|
|
424 </when>
|
|
|
425 </conditional>
|
|
|
426 </when>
|
|
|
427 </conditional>
|
|
|
428 </when>
|
|
|
429 <when value="no" />
|
|
|
430 </conditional>
|
|
|
431 <!-- Reporting binding events -->
|
|
|
432 <conditional name="report_binding_events_cond">
|
|
|
433 <param name="report_binding_events" type="select" label="Report binding events?">
|
|
|
434 <option value="no" selected="True">No</option>
|
|
|
435 <option value="yes">Yes</option>
|
|
|
436 </param>
|
|
|
437 <when value="no" />
|
|
|
438 <when value="yes">
|
|
|
439 <param name="minqvalue" type="float" min="0" value="0.001" label="Minimum Q-value (corrected p-value) of reported binding events" />
|
|
|
440 <param name="minfold" type="float" min="0" value="1.5" label="Minimum event fold-change vs scaled control" />
|
|
|
441 <param name="nodifftests" type="select" label="Run differential enrichment tests?">
|
|
|
442 <option value="yes" selected="True">Yes</option>
|
|
|
443 <option value="no">No</option>
|
|
|
444 </param>
|
|
|
445 <param name="edgerod" type="float" min="0" value="0.15" label="EdgeR over-dispersion parameter value" />
|
|
|
446 <param name="diffp" type="float" min="0" value="0.01" label="Minimum p-value for reporting differential enrichment" />
|
|
|
447 </when>
|
|
|
448 </conditional>
|
|
|
449 </when>
|
|
|
450 <when value="hide" />
|
|
|
451 </conditional>
|
|
|
452 </inputs>
|
|
|
453 <outputs>
|
|
2
|
454 <data name="output_bed" format="bed" label="${tool.name} (bed) on ${on_string}"/>
|
|
|
455 <data name="output_html" format="html" label="${tool.name} (html) on ${on_string}"/>
|
|
|
456 <data name="replicates_counts" format="tabular" label="${tool.name} (replicates counts) on ${on_string}"/>
|
|
|
457 <data name="all_events_table" format="tabular" label="${tool.name} (all events table) on ${on_string}"/>
|
|
0
|
458 </outputs>
|
|
|
459 <tests>
|
|
|
460 <test>
|
|
2
|
461 <param name="single_or_multi_expt" value="single" />
|
|
0
|
462 <param name="expt" value="expt_hg19.scidx" ftype="scidx" dbkey="hg19" />
|
|
2
|
463 <param name="advanced_options" value="hide" />
|
|
0
|
464 <output name="output_html" file="hg19_output_html1.html" ftype="html" compare="contains"/>
|
|
2
|
465 <output name="output_bed" file="hg19_output_bed1.bed" ftype="bed"/>
|
|
0
|
466 <output name="all_events_table" file="hg19_all_events_table1.tabular" ftype="tabular"/>
|
|
|
467 <output name="replicates_counts" file="hg19_replicates_counts1.tabular" ftype="tabular"/>
|
|
|
468 </test>
|
|
|
469 <test>
|
|
2
|
470 <param name="single_or_multi_expt" value="single" />
|
|
0
|
471 <param name="expt" value="expt_hg19.scidx" ftype="scidx" dbkey="hg19" />
|
|
2
|
472 <param name="control" value="cntrl_hg19.scidx" ftype="scidx" dbkey="hg19" />
|
|
|
473 <param name="advanced_options" value="display" />
|
|
0
|
474 <output name="output_html" file="hg19_output_html2.html" ftype="html" compare="contains"/>
|
|
2
|
475 <output name="output_bed" file="hg19_output_bed2.bed" ftype="bed"/>
|
|
0
|
476 <output name="all_events_table" file="hg19_all_events_table2.tabular" ftype="tabular"/>
|
|
|
477 <output name="replicates_counts" file="hg19_replicates_counts2.tabular" ftype="tabular"/>
|
|
|
478 </test>
|
|
|
479 </tests>
|
|
|
480 <help>
|
|
|
481
|
|
|
482 **What it does**
|
|
|
483
|
|
|
484 MultiGPS is a framework for analyzing collections of multi-condition ChIP-seq datasets and characterizing
|
|
|
485 differential binding events between conditions. MultiGPS encourages consistency in the reported binding
|
|
|
486 event locations across conditions and provides accurate estimation of ChIP enrichment levels at each event.
|
|
|
487 MultiGPS performs significant EM optimization of binding events along the genome and across experimental
|
|
|
488 conditions, and it integrates motif-finding via MEME. The tool loads all data into memory, so the potential
|
|
|
489 exists for time and memory intensive analyses if running over many conditions or large datasets.
|
|
|
490
|
|
|
491 -----
|
|
|
492
|
|
|
493 **Options**
|
|
|
494
|
|
|
495 * **Loading data:**
|
|
|
496
|
|
|
497 - **Optional file containing reads from a control experiment** - must be same format as input experiment
|
|
|
498 - **Fixed per-base limit** - Fixed per-base limit (default: estimated from background model).
|
|
|
499 - **Poisson threshold for filtering per base** - Look at neighboring positions to decide what the per-base limit should be.
|
|
|
500 - **Use non-unique reads** - Use non-unique reads.
|
|
|
501 - **Fraction of the genome that is mappable for these experiments** - Fraction of the genome that is mappable for these experiments
|
|
|
502 - **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).
|
|
|
503
|
|
|
504 * **Scaling control vs signal counts:**
|
|
|
505
|
|
|
506 - **Use signal vs control scaling?** - Flag to turn off auto estimation of signal vs control scaling factor
|
|
|
507 - **Use the median signal/control ratio as the scaling factor?** - Flag to use scaling by median ratio (default = scaling by NCIS).
|
|
|
508 - **Use scaling by regression on binned tag counts?** - Flag to use scaling by regression (default = scaling by NCIS).
|
|
|
509 - **Estimate scaling factor by SES?** - Specify whether to estimate scaling factor by SES.
|
|
|
510 - **Multiply control counts by total tag count ratio and then by this factor** - Multiply control counts by total tag count ratio and then by this factor (default: NCIS).
|
|
|
511 - **Window size for estimating scaling ratios** - Window size in base pairs for estimating scaling ratios
|
|
|
512 - **Plot diagnostic information for the chosen scaling method?** - Flag to plot diagnostic information for the chosen scaling method.
|
|
|
513
|
|
|
514 * **Running MultiGPS:**
|
|
|
515
|
|
|
516 - **Optional binding event read distribution file** - Binding event read distribution file for initializing models. The true distribution of reads around binding events is estimated during MultiGPS training. A default initial distribution appropriate for ChIP-seq data is used if this option is not specified.
|
|
|
517 - **Maximum number of training rounds for updating binding event read distributions** - Maximum number of training rounds for updating binding event read distributions.
|
|
|
518 - **Perform binding model updates?** - Perform binding model updates?
|
|
|
519 - **Minimum number of events to support an update of the read distribution** - Minimum number of events to support an update of the read distribution
|
|
|
520 - **Perform binding model smoothing?** - Smooth with a cubic spline using a specified smoothing factor.
|
|
|
521 - **Spline smoothing parameter** - Smoothing parameter for smoothing cubic spline.
|
|
|
522 - **Perform Gaussian model smoothing?** - Select "Yes" to use Gaussian model smoothing using a specified smoothing factor if binding model smoothing is not performed.
|
|
|
523 - **Allow joint events in model updates?** - Specify whether to allow joint events in model updates.
|
|
|
524 - **Keep binding model range fixed to inital size?** - Flag to keep binding model range fixed to inital size (default: vary automatically)
|
|
|
525 - **Poisson log threshold for potential region scanning** - Poisson log threshold for potential region scanning.
|
|
|
526 - **Alpha scaling factor** - Alpha scaling factor. Increasing this parameter results in stricter binding event calls.
|
|
|
527 - **Impose this alpha** - The alpha parameter is a sparse prior on binding events in the MultiGPS model. It can be interpreted as a minimum number of reads that each binding event must be responsible for in the model. Default: estimate alpha automatically.
|
|
|
528 - **Share component configs in the ML step?** - Flag to not share component configs in the ML step
|
|
|
529 - **Optional file containing a set of regions to ignore during MultiGPS training** - File containing a set of regions to ignore during MultiGPS training. It’s a good idea to exclude the mitochondrial genome and other ‘blacklisted’ regions that contain artifactual accumulations of reads in both ChIP-seq and control experiments. MultiGPS will waste time trying to model binding events in these regions, even though they will not typically appear significantly enriched over the control (and thus will not be reported to the user).
|
|
|
530
|
|
|
531 * **MultiGPS priors:**
|
|
|
532
|
|
|
533 - **Perform inter-experiment positional prior?** - Flag to turn off inter-experiment positional prior (default=on).
|
|
|
534 - **Probability that events are shared across conditions** - Probability that events are shared across conditions.
|
|
|
535 - **Perform both motif-finding and motif priors?** - Flag to turn off motif-finding and motif priors.
|
|
|
536 - **Perform motif-finding only?** - Flag to turn off motif priors only.
|
|
|
537 - **Number of motifs MEME should find for each condition** - Number of motifs MEME should find for each condition.
|
|
|
538 - **Minimum motif width for MEME** - minw arg for MEME.
|
|
|
539 - **Maximum motif width for MEME** - maxw arg for MEME.
|
|
|
540
|
|
|
541 * **Reporting binding events:**
|
|
|
542
|
|
|
543 - **Minimum Q-value (corrected p-value) of reported binding events** - Minimum Q-value (corrected p-value) of reported binding events.
|
|
|
544 - **Minimum event fold-change vs scaled control** - Minimum event fold-change vs scaled control.
|
|
|
545 - **Run differential enrichment tests?** - Choose whether to run differential enrichment tests.
|
|
|
546 - **EdgeR over-dispersion parameter value** - EdgeR over-dispersion parameter value.
|
|
|
547 - **Minimum p-value for reporting differential enrichment** - Minimum p-value for reporting differential enrichment.
|
|
|
548
|
|
|
549 </help>
|
|
|
550 <citations>
|
|
|
551 <citation type="doi">10.1371/journal.pcbi.1003501</citation>
|
|
|
552 </citations>
|
|
|
553 </tool>
|
