|
0
|
1 <tool id="fls_modencode_peakcalling_macs2.1" name="MACS2.1.0" version="2">
|
|
|
2 <requirements>
|
|
|
3 <requirement type="package" version="2.7">python</requirement>
|
|
|
4 <requirement type="package" version="1.8.1">numpy</requirement>
|
|
|
5 <requirement type="package" version="2.1.0.20140616">macs2</requirement>
|
|
|
6 </requirements>
|
|
|
7 <description>Model-based Analysis of ChIP-Seq [golem]</description>
|
|
|
8 <command interpreter="python">macs21_wrapper.py $options_file $outputs_file</command>
|
|
|
9 <inputs>
|
|
|
10 <!--experiment name and option of selecting paired or single end will always be present-->
|
|
|
11 <param name="experiment_name" type="text" value="MACS2.1.0 in Galaxy" size="50"
|
|
|
12 label="Experiment Name"/>
|
|
|
13 <!--select one of the 7 major commands offered by macs2-->
|
|
|
14 <conditional name="major_command">
|
|
|
15 <param name="major_command_selector" type="select" label="Select action to be performed">
|
|
|
16 <option value="callpeak">Peak Calling</option>
|
|
|
17 <!--<option value="filterdup">filterdup</option>
|
|
|
18 <option value="randsample">randsample</option>-->
|
|
|
19 <option value="bdgcmp">Compare .bdg Files</option>
|
|
|
20 <!--<option value="bdgdiff">bdgdiff</option>
|
|
|
21 <option value="bdgpeakcall">bdgpeakcall</option>
|
|
|
22 <option value="bdgbroadcall">bdgbroadcall</option>-->
|
|
|
23 </param>
|
|
|
24 <!--callpeak option of macs2-->
|
|
|
25 <when value="callpeak">
|
|
|
26 <!--choose 'broad' or 'narrow' regions-->
|
|
|
27 <conditional name="broad_options">
|
|
|
28 <param name="broad_regions" type="select" label="Type of region to call"
|
|
|
29 help="Broad regions are formed by linking nearby enriched regions">
|
|
|
30 <option value="" selected="true">Narrow regions</option>
|
|
|
31 <option value="broad">Broad regions</option>
|
|
|
32 </param>
|
|
|
33 <when value="broad">
|
|
|
34 <param name="broad_cutoff" type="float"
|
|
|
35 label="Cutoff for broad regions"
|
|
|
36 value="0.1" help="default: 0.1 (--broad-cutoff)"/>
|
|
|
37 </when>
|
|
|
38 </conditional>
|
|
|
39 <!--may need to add a few more formats at later time-->
|
|
|
40 <param name="input_chipseq_file1" type="data" format="bed,sam,bam"
|
|
|
41 label="ChIP-seq read file" />
|
|
|
42 <param name="input_control_file1" type="data" format="bed,sam,bam" optional="True"
|
|
|
43 label="ChIP-seq control read file" />
|
|
|
44 <conditional name="genome_size">
|
|
|
45 <param name="gsize" type="select" label="Effective genome size"
|
|
|
46 help="Either pre-defined (for common organisms), or user-defined (--gsize)">
|
|
|
47 <option value="hs" selected="true">Human (2.7e9)</option>
|
|
|
48 <option value="mm">Mouse (1.87e9)</option>
|
|
|
49 <option value="ce">C. elegans (9e7)</option>
|
|
|
50 <option value="dm">Fruitfly (1.2e8)</option>
|
|
|
51 <option value="">User-defined</option>
|
|
|
52 </param>
|
|
|
53 <when value="">
|
|
|
54 <!-- User-defined effective genome size -->
|
|
|
55 <param name="user_defined_gsize" type="float" value=""
|
|
|
56 label="Enter effective genome size (number of bases)"
|
|
|
57 help="e.g. '1.0e+9' or '1000000000'" />
|
|
|
58 </when>
|
|
|
59 </conditional>
|
|
|
60 <param name="bw" type="integer" label="Band width" value="300" help="(--bw)"/>
|
|
|
61 <param name="xls_to_interval" label="Include XLS file from MACS"
|
|
|
62 type="boolean" truevalue="True" falsevalue="False" checked="True"
|
|
|
63 help="MACS2 XLS file will be output to the history in 'interval' format (suitable for subsequent analysis in Galaxy). Note that start positions are 1-based."/>
|
|
|
64
|
|
|
65 <conditional name="bdg_options">
|
|
|
66 <param name="bdg"
|
|
|
67 label="Save fragment pileup, control lambda, -log10pvalue/qvalue in bedGraph"
|
|
|
68 type="boolean" truevalue="-B" falsevalue="" checked="False" />
|
|
|
69 <when value="-B">
|
|
|
70 <param name="spmr"
|
|
|
71 type="boolean" truevalue="--SPMR" falsevalue="" checked="False"
|
|
|
72 label="Save signal per million reads for fragment pileup profiles"
|
|
|
73 help="(--SPMR)" />
|
|
|
74 </when>
|
|
|
75 <when value="">
|
|
|
76 <!-- Display nothing -->
|
|
|
77 </when>
|
|
|
78 </conditional>
|
|
|
79
|
|
|
80 <conditional name="pq_options">
|
|
|
81 <param name="pq_options_selector" type="select"
|
|
|
82 label="Select p-value or q-value" help="default uses q-value">
|
|
|
83 <option value="qvalue">q-value</option>
|
|
|
84 <option value="pvalue">p-value</option>
|
|
|
85 </param>
|
|
|
86 <when value="pvalue">
|
|
|
87 <param name="pvalue" type="float"
|
|
|
88 label="p-value cutoff for binding region detection"
|
|
|
89 value="1e-2" help="default: 1e-2 (--pvalue)"/>
|
|
|
90 </when>
|
|
|
91 <when value="qvalue">
|
|
|
92 <param name="qvalue" type="float"
|
|
|
93 label="q-value cutoff for binding region detection"
|
|
|
94 value="0.01" help="default: 0.01 (--qvalue)"/>
|
|
|
95 </when>
|
|
|
96 </conditional>
|
|
|
97 <conditional name="advanced_options">
|
|
|
98 <param name="advanced_options_selector" type="select"
|
|
|
99 label="Display advanced options">
|
|
|
100 <option value="off">Hide</option>
|
|
|
101 <option value="on">Display</option>
|
|
|
102 </param>
|
|
|
103 <when value="on">
|
|
|
104 <param name="mfoldlo" type="integer"
|
|
|
105 label="Select the regions with MFOLD high-confidence enrichment ratio against background to build model (lower-limit)"
|
|
|
106 value="10" help="(--mfold)"/>
|
|
|
107 <param name="mfoldhi" type="integer"
|
|
|
108 label="Select the regions with MFOLD high-confidence enrichment ratio against background to build model (upper-limit)"
|
|
|
109 value="30" help="(--mfold)"/>
|
|
|
110 <param name="nolambda"
|
|
|
111 label="Use fixed background lambda as local lambda for every binding region"
|
|
|
112 type="boolean" truevalue="--nolambda" falsevalue="" checked="False"
|
|
|
113 help="(--nolambda)"/>
|
|
|
114 <param name="call_summits"
|
|
|
115 label="Detect subpeaks within binding region"
|
|
|
116 type="boolean" truevalue="--call-summits" falsevalue="" checked="False"
|
|
|
117 help="(--call-summits)"/>
|
|
|
118 <conditional name="keep_duplicates">
|
|
|
119 <param name="keep_dup" type="select"
|
|
|
120 label="Use of duplicate reads">
|
|
|
121 <option value="auto">Automatically calculate maximum number of duplicates to keep (auto)</option>
|
|
|
122 <option value="all">Use all duplicates (all)</option>
|
|
|
123 <option value="" selected="true">Manually specify maxium number of duplicates</option>
|
|
|
124 </param>
|
|
|
125 <when value="">
|
|
|
126 <param name="maximum_tags" type="integer" value="1"
|
|
|
127 label="Maxium number of duplicated tags to keep at each location"/>
|
|
|
128 </when>
|
|
|
129 </conditional>
|
|
|
130 </when>
|
|
|
131 <when value="off">
|
|
|
132 <!--display nothing-->
|
|
|
133 </when>
|
|
|
134 </conditional>
|
|
|
135 <conditional name="nomodel_type">
|
|
|
136 <param name="nomodel_type_selector" type="select" label="Build Model">
|
|
|
137 <option value="nomodel">Do not build the shifting model (--nomodel enabled)</option>
|
|
|
138 <option value="create_model" selected="true">Build the shifting model (--nomodel disabled)</option>
|
|
|
139 </param>
|
|
|
140 <when value="nomodel">
|
|
|
141 <param name="extsize" type="integer" label="Arbitrary extension size in bp" value="200" help="Used as fragment size to extend each read towards 3' end (--extsize)"/>
|
|
|
142 </when>
|
|
|
143 </conditional>
|
|
|
144 </when>
|
|
|
145
|
|
|
146 <!--callpeak option of macs2-->
|
|
|
147 <when value="bdgcmp">
|
|
|
148 <param name="input_chipseq_file1" type="data" format="bed,sam,bam"
|
|
|
149 label="ChIP-seq read file" />
|
|
|
150 <param name="input_control_file1" type="data" format="bed,sam,bam" optional="True"
|
|
|
151 label="ChIP-seq control read file" />
|
|
|
152 <param name="pseudocount" type="float" label="Set pseudocount" value="0.00001"
|
|
|
153 help="default: 0.00001 (-p)"/>
|
|
|
154 <conditional name="bdgcmp_options">
|
|
|
155 <param name="bdgcmp_options_selector" type="select"
|
|
|
156 label="Select action to be performed">
|
|
|
157 <option value="ppois">ppois</option>
|
|
|
158 <option value="qpois">qpois</option>
|
|
|
159 <option value="subtract">subtract</option>
|
|
|
160 <option value="logFE">logFE</option>
|
|
|
161 <option value="FE">FE</option>
|
|
|
162 <option value="logLR">logLR</option>
|
|
|
163 </param>
|
|
|
164 </conditional>
|
|
|
165 </when>
|
|
|
166 </conditional>
|
|
|
167 </inputs>
|
|
|
168
|
|
|
169 <outputs>
|
|
|
170 <!--callpeaks output-->
|
|
|
171 <data name="output_extra_files" format="html"
|
|
|
172 label="${tool.name}: callpeak on ${on_string} (html report)">
|
|
|
173 <filter>major_command['major_command_selector'] == 'callpeak'</filter>
|
|
|
174 </data>
|
|
|
175 <data name="output_summits_bed_file" format="bed"
|
|
|
176 label="${tool.name}: callpeak on ${on_string} (summits: bed)">
|
|
|
177 <filter>major_command['major_command_selector'] == 'callpeak'</filter>
|
|
|
178 </data>
|
|
|
179 <data name="output_peaks_file" format="xls"
|
|
|
180 label="${tool.name}: callpeak on ${on_string} (peaks: xls)">
|
|
|
181 <filter>major_command['major_command_selector'] == 'callpeak'</filter>
|
|
|
182 <filter>major_command['xls_to_interval'] is False</filter>
|
|
|
183 </data>
|
|
|
184 <data name="output_narrowpeaks_file" format="interval"
|
|
|
185 label="${tool.name}: callpeak on ${on_string} (peaks: narrowPeak)">
|
|
|
186 <filter>major_command['major_command_selector'] == 'callpeak'</filter>
|
|
|
187 <filter>major_command['broad_options']['broad_regions'] == ''</filter>
|
|
|
188 </data>
|
|
|
189 <data name="output_broadpeaks_file" format="interval"
|
|
|
190 label="${tool.name}: callpeak on ${on_string} (peaks: broadPeak)">
|
|
|
191 <filter>major_command['major_command_selector'] == 'callpeak'</filter>
|
|
|
192 <filter>major_command['broad_options']['broad_regions'] == 'broad'</filter>
|
|
|
193 </data>
|
|
|
194 <data name="output_gappedpeaks_file" format="interval"
|
|
|
195 label="${tool.name}: callpeak on ${on_string} (peaks: gappedPeak)">
|
|
|
196 <filter>major_command['major_command_selector'] == 'callpeak'</filter>
|
|
|
197 <filter>major_command['broad_options']['broad_regions'] == 'broad'</filter>
|
|
|
198 </data>
|
|
|
199 <data name="output_xls_to_interval_peaks_file" format="interval"
|
|
|
200 label="${tool.name}: callpeak on ${on_string} (peaks: interval)">
|
|
|
201 <filter>major_command['xls_to_interval'] is True</filter>
|
|
|
202 <filter>major_command['major_command_selector'] == 'callpeak'</filter>
|
|
|
203 </data>
|
|
|
204 <data name="output_treat_pileup_file" format="bedgraph"
|
|
|
205 label="${tool.name}: callpeak on ${on_string} (treat pileup: bedGraph)">
|
|
|
206 <filter>major_command['bdg_options']['bdg'] is True</filter>
|
|
|
207 <filter>major_command['major_command_selector'] == 'callpeak'</filter>
|
|
|
208 </data>
|
|
|
209 <data name="output_lambda_bedgraph_file" format="bedgraph"
|
|
|
210 label="${tool.name}: callpeak on ${on_string} (control lambda: bedGraph)">
|
|
|
211 <filter>major_command['bdg_options']['bdg'] is True</filter>
|
|
|
212 <filter>major_command['major_command_selector'] == 'callpeak'</filter>
|
|
|
213 </data>
|
|
|
214 <!--bdgcmp output-->
|
|
|
215 <data name="output_bdgcmp_file" format="bdg"
|
|
|
216 label="${tool.name}: bdgcmp on ${on_string} (bdg)">
|
|
|
217 <filter>major_command['major_command_selector'] == 'bdgcmp'</filter>
|
|
|
218 </data>
|
|
|
219 </outputs>
|
|
|
220 <configfiles>
|
|
|
221 <configfile name="outputs_file"><%
|
|
|
222 import simplejson
|
|
|
223 %>
|
|
|
224 ##=======================================================================================
|
|
|
225 #set $__outputs = { 'command':str( $major_command.major_command_selector ) }
|
|
|
226 #if str( $major_command.major_command_selector ) == 'callpeak':
|
|
|
227 #set $__outputs['output_summits_bed_file'] = str( $output_summits_bed_file )
|
|
|
228 #set $__outputs['output_extra_file'] = str( $output_extra_files )
|
|
|
229 #set $__outputs['output_extra_file_path'] = str( $output_extra_files.files_path )
|
|
|
230 #set $__outputs['output_peaks_file'] = str( $output_peaks_file )
|
|
|
231 #set $__outputs['output_narrowpeaks_file'] = str( $output_narrowpeaks_file )
|
|
|
232 #set $__outputs['output_broadpeaks_file'] = str( $output_broadpeaks_file )
|
|
|
233 #set $__outputs['output_gappedpeaks_file'] = str( $output_gappedpeaks_file )
|
|
|
234 #set $__outputs['output_xls_to_interval_peaks_file'] = str( $output_xls_to_interval_peaks_file )
|
|
|
235 #set $__outputs['output_treat_pileup_file'] = str( $output_treat_pileup_file )
|
|
|
236 #set $__outputs['output_lambda_bedgraph_file'] = str( $output_lambda_bedgraph_file )
|
|
|
237 #end if
|
|
|
238 ##=======================================================================================
|
|
|
239 #if str( $major_command.major_command_selector ) == 'bdgcmp':
|
|
|
240 #set $__outputs['output_bdgcmp_file'] = str( $output_bdgcmp_file )
|
|
|
241 #end if
|
|
|
242
|
|
|
243 ${ simplejson.dumps( __outputs ) }
|
|
|
244 </configfile>
|
|
|
245 <configfile name="options_file"><%
|
|
|
246 import simplejson
|
|
|
247 %>
|
|
|
248 ##=======================================================================================
|
|
|
249 #set $__options = { 'experiment_name':str( $experiment_name ) }
|
|
|
250 ##treatment/tag input files and format
|
|
|
251 #set $__options['input_chipseq'] = [ str( $major_command.input_chipseq_file1 ) ]
|
|
|
252 #set $__options['format'] = $major_command.input_chipseq_file1.extension.upper()
|
|
|
253
|
|
|
254 ##control/input files
|
|
|
255 #set $__options['input_control'] = []
|
|
|
256 #if str( $major_command.input_control_file1 ) != 'None':
|
|
|
257 #set $_hole = __options['input_control'].append( str( $major_command.input_control_file1 ) )
|
|
|
258 #end if
|
|
|
259
|
|
|
260 #if str( $major_command.major_command_selector ) == 'callpeak':
|
|
|
261 #set $__options['command'] = str( "callpeak" )
|
|
|
262 #set $__options['bw'] = str( $major_command.bw )
|
|
|
263 #set $__options['xls_to_interval'] = str( $major_command.xls_to_interval )
|
|
|
264
|
|
|
265 ##bdg options
|
|
|
266 #if $major_command.bdg_options.bdg == True:
|
|
|
267 #set $__options['bdg'] = str( "-B" )
|
|
|
268 #set $__options['spmr'] = str( $major_command.bdg_options.spmr )
|
|
|
269 #else:
|
|
|
270 #set $__options['bdg'] = str( "" )
|
|
|
271 #set $__options['spmr'] = str( "" )
|
|
|
272 #end if
|
|
|
273
|
|
|
274 ##broad_options
|
|
|
275 #if str( $major_command.broad_options.broad_regions ) == 'broad':
|
|
|
276 #set $__options['broad'] = str( $major_command.broad_options.broad_regions )
|
|
|
277 #set $__options['broad_cutoff'] = str( $major_command.broad_options.broad_cutoff )
|
|
|
278 #else:
|
|
|
279 #set $__options['broad'] = str( "" )
|
|
|
280 #set $__options['broad_cutoff'] = str( "" )
|
|
|
281 #end if
|
|
|
282
|
|
|
283 ##genome sizes
|
|
|
284 #if str( $major_command.genome_size.gsize ) == '':
|
|
|
285 #set $__options['gsize'] = int( $major_command.genome_size.user_defined_gsize )
|
|
|
286 #else:
|
|
|
287 #set $__options['gsize'] = str( $major_command.genome_size.gsize )
|
|
|
288 #end if
|
|
|
289
|
|
|
290 ##advanced options
|
|
|
291 #if str( $major_command.advanced_options.advanced_options_selector ) == 'on':
|
|
|
292 #set $__options['mfoldlo'] = int( $major_command.advanced_options.mfoldlo )
|
|
|
293 #set $__options['mfoldhi'] = int( $major_command.advanced_options.mfoldhi )
|
|
|
294 #set $__options['nolambda'] = str( $major_command.advanced_options.nolambda )
|
|
|
295 #set $__options['call_summits'] = str( $major_command.advanced_options.call_summits )
|
|
|
296 #if str( $major_command.advanced_options.keep_duplicates.keep_dup ) == '':
|
|
|
297 #set $__options['keep_dup'] = int( $major_command.advanced_options.keep_duplicates.maximum_tags )
|
|
|
298 #else:
|
|
|
299 #set $__options['keep_dup'] = str( $major_command.advanced_options.keep_duplicates.keep_dup )
|
|
|
300 #end if
|
|
|
301 #else:
|
|
|
302 #set $__options['mfoldlo'] = int( "5" )
|
|
|
303 #set $__options['mfoldhi'] = int( "50" )
|
|
|
304 #set $__options['nolambda'] = str( "" )
|
|
|
305 #set $__options['call_summits'] = str( "" )
|
|
|
306 #set $__options['keep_dup'] = int( "1" )
|
|
|
307 #end if
|
|
|
308
|
|
|
309 ##enable xls file options
|
|
|
310 ##if str( $major_command.xls_to_interval ) == 'create':
|
|
|
311 ##set $__options['xls_to_interval'] = { 'peaks_file': str( $output_xls_to_interval_peaks_file ), 'negative_peaks_file': str( $output_xls_to_interval_negative_peaks_file ) }
|
|
|
312 ##end if
|
|
|
313
|
|
|
314 ##pq value select options
|
|
|
315 #if str( $major_command.pq_options.pq_options_selector ) == 'qvalue':
|
|
|
316 #set $__options['qvalue'] = str( $major_command.pq_options.qvalue )
|
|
|
317 #else:
|
|
|
318 #set $__options['pvalue'] = str( $major_command.pq_options.pvalue )
|
|
|
319 #end if
|
|
|
320
|
|
|
321 ##model options
|
|
|
322 #if str( $major_command.nomodel_type.nomodel_type_selector ) == 'nomodel':
|
|
|
323 #set $__options['nomodel'] = str( $major_command.nomodel_type.extsize )
|
|
|
324 #end if
|
|
|
325 #end if
|
|
|
326 ##=======================================================================================
|
|
|
327 #if str( $major_command.major_command_selector ) == 'bdgcmp':
|
|
|
328 #set $__options['command'] = str( "bdgcmp" )
|
|
|
329 #set $__options['pseudocount'] = float( str( $major_command.pseudocount ) )
|
|
|
330 #set $__options['m'] = str( $major_command.bdgcmp_options.bdgcmp_options_selector )
|
|
|
331 #end if
|
|
|
332 ##=======================================================================================
|
|
|
333
|
|
|
334 ${ simplejson.dumps( __options ) }
|
|
|
335 </configfile>
|
|
|
336 </configfiles>
|
|
|
337 <tests>
|
|
|
338 <!--none yet for macs2-->
|
|
|
339 </tests>
|
|
|
340 <help>
|
|
|
341
|
|
|
342 .. class:: warningmark
|
|
|
343
|
|
|
344 **This is a modified version of the standard Galaxy toolshed "MACS2" tool,
|
|
|
345 which has been customised for users at the University of Manchester to work
|
|
|
346 with MACS 2.1.0.**
|
|
|
347
|
|
|
348 It is based on the 16:14f378e35191 revision of the tool at
|
|
|
349
|
|
|
350 * http://toolshed.g2.bx.psu.edu/view/modencode-dcc/macs2
|
|
|
351
|
|
|
352 ------
|
|
|
353
|
|
|
354 **What it does**
|
|
|
355
|
|
|
356 With the improvement of sequencing techniques, chromatin immunoprecipitation
|
|
|
357 followed by high throughput sequencing (ChIP-Seq) is getting popular to study
|
|
|
358 genome-wide protein-DNA interactions. To address the lack of powerful ChIP-Seq
|
|
|
359 analysis method, we present a novel algorithm, named Model-based Analysis of
|
|
|
360 ChIP-Seq (MACS), for identifying transcript factor binding sites. MACS captures
|
|
|
361 the influence of genome complexity to evaluate the significance of enriched
|
|
|
362 ChIP regions, and MACS improves the spatial resolution of binding sites through
|
|
|
363 combining the information of both sequencing tag position and orientation. MACS
|
|
|
364 can be easily used for ChIP-Seq data alone, or with control sample with the
|
|
|
365 increase of specificity.
|
|
|
366
|
|
|
367 View the original MACS2 documentation:
|
|
|
368 https://github.com/taoliu/MACS/blob/master/README.rst
|
|
|
369
|
|
|
370 ------
|
|
|
371
|
|
|
372 **Usage**
|
|
|
373
|
|
|
374 **Peak Calling**: Main MACS2 Function to Call peaks from alignment results.
|
|
|
375
|
|
|
376 **Compare .bdg files**: Deduct noise by comparing two signal tracks in bedGraph.
|
|
|
377
|
|
|
378
|
|
|
379 ------
|
|
|
380
|
|
|
381 **Citation**
|
|
|
382
|
|
|
383 For the underlying tool, please cite Zhang Y, Liu T, Meyer CA, Eeckhoute J, Johnson DS, Bernstein BE, Nusbaum C, Myers RM, Brown M, Li W, Liu XS. Model-based analysis of ChIP-Seq (MACS). Genome Biol. 2008;9(9):R137.
|
|
|
384
|
|
|
385 Integration of MACS2 with Galaxy performed by Ziru Zhou ( ziruzhou@gmail.com ). Please send your comments/questions to modENCODE DCC at help@modencode.org.
|
|
|
386 </help>
|
|
|
387 </tool>
|
