|
10
|
1 <tool id="modencode_peakcalling_macs2" name="MACS2" version="2.0.10.2">
|
|
|
2 <requirements>
|
|
|
3 <requirement type="python-module">macs2</requirement>
|
|
|
4 <requirement type="package" version="2.0.10.2">macs2</requirement>
|
|
|
5 <!--<requirement type="set_environment">SCRIPT_PATH</requirement>-->
|
|
|
6 </requirements>
|
|
|
7 <description>Model-based Analysis of ChIP-Seq</description>
|
|
|
8 <command interpreter="python">macs2_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 in Galaxy" size="50" label="Experiment Name"/>
|
|
|
12
|
|
|
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 <!--may need to add a few more formats at later time-->
|
|
|
27 <param name="input_chipseq_file1" type="data" format="bam" label="ChIP-Seq Tag File" />
|
|
|
28 <param name="input_control_file1" type="data" format="bam" optional="True" label="ChIP-Seq Control File" />
|
|
|
29 <param name="gsize" type="float" label="Effective genome size" value="2.7e+9" help="Human: 3.3e+9, Mouse: 3.0e+9, Fly: 1.9e+8, Worm: 1.3e+8 (--gsize)"/>
|
|
|
30 <param name="bw" type="integer" label="Band width" value="300" help="(--bw)"/>
|
|
|
31 <param name="xls_to_interval" label="Parse xls files into into distinct interval files" type="boolean" truevalue="True" falsevalue="False" checked="False"/>
|
|
|
32 <param name="bdg" label="Save fragment pileup, control lambda, -log10pvalue/qvalue in bedGraph" type="boolean" truevalue="-B" falsevalue="" checked="False" help="files located in html report"/>
|
|
|
33
|
|
|
34 <conditional name="pq_options">
|
|
|
35 <param name="pq_options_selector" type="select" label="Select p-value or q-value" help="default uses q-value">
|
|
|
36 <option value="qvalue">q-value</option>
|
|
|
37 <option value="pvalue">p-value</option>
|
|
|
38 </param>
|
|
|
39 <when value="pvalue">
|
|
|
40 <param name="pvalue" type="float" label="p-value cutoff for peak detection" value="1e-2" help="default: 1e-2 (--pvalue)"/>
|
|
|
41 </when>
|
|
|
42 <when value="qvalue">
|
|
|
43 <param name="qvalue" type="float" label="q-value cutoff for peak detection" value="5e-2" help="default: 5e-2 (--qvalue)"/>
|
|
|
44 </when>
|
|
|
45 </conditional>
|
|
|
46 <conditional name="advanced_options">
|
|
|
47 <param name="advanced_options_selector" type="select" label="Display advanced options">
|
|
|
48 <option value="off">Hide</option>
|
|
|
49 <option value="on">Display</option>
|
|
|
50 </param>
|
|
|
51 <when value="on">
|
|
|
52 <param name="mfoldlo" type="integer" label="Select the regions with MFOLD high-confidence enrichment ratio against background to build model (lower-limit)" value="10" help="(--mfold)"/>
|
|
|
53 <param name="mfoldhi" type="integer" label="Select the regions with MFOLD high-confidence enrichment ratio against background to build model (upper-limit)" value="30" help="(--mfold)"/>
|
|
|
54 <param name="nolambda" label="Use fixed background lambda as local lambda for every peak region" type="boolean" truevalue="--nolambda" falsevalue="" checked="False" help="up to 9X more time consuming (--nolambda)"/>
|
|
|
55 </when>
|
|
|
56 <when value="off">
|
|
|
57 <!--display nothing-->
|
|
|
58 </when>
|
|
|
59 </conditional>
|
|
|
60 <conditional name="nomodel_type">
|
|
|
61 <param name="nomodel_type_selector" type="select" label="Build Model">
|
|
|
62 <option value="nomodel">Do not build the shifting model (--nomodel enabled)</option>
|
|
|
63 <option value="create_model" selected="true">Build the shifting model (--nomodel disabled)</option>
|
|
|
64 </param>
|
|
|
65 <when value="nomodel">
|
|
|
66 <param name="shiftsize" type="integer" label="Arbitrary shift size in bp" value="100" help="(--shiftsize)"/>
|
|
|
67 </when>
|
|
|
68 </conditional>
|
|
|
69 </when>
|
|
|
70
|
|
|
71 <!--callpeak option of macs2-->
|
|
|
72 <when value="bdgcmp">
|
|
|
73 <param name="input_chipseq_file1" type="data" format="bam" label="ChIP-Seq Tag File" />
|
|
|
74 <param name="input_control_file1" type="data" format="bam" optional="True" label="ChIP-Seq Control File" />
|
|
|
75 <param name="pseudocount" type="float" label="Set pseudocount" value="0.00001" help="default: 0.00001 (-p)"/>
|
|
|
76
|
|
|
77 <conditional name="bdgcmp_options">
|
|
|
78 <param name="bdgcmp_options_selector" type="select" label="Select action to be performed">
|
|
|
79 <option value="ppois">ppois</option>
|
|
|
80 <option value="qpois">qpois</option>
|
|
|
81 <option value="subtract">subtract</option>
|
|
|
82 <option value="logFE">logFE</option>
|
|
|
83 <option value="FE">FE</option>
|
|
|
84 <option value="logLR">logLR</option>
|
|
|
85 </param>
|
|
|
86 </conditional>
|
|
|
87 </when>
|
|
|
88 </conditional>
|
|
|
89 </inputs>
|
|
|
90
|
|
|
91 <outputs>
|
|
|
92 <!--callpeaks output-->
|
|
|
93 <data name="output_bed_file" format="bed" label="${tool.name}: callpeak on ${on_string} (peaks: bed)">
|
|
|
94 <filter>major_command['major_command_selector'] == 'callpeak'</filter>
|
|
|
95 </data>
|
|
|
96 <data name="output_extra_files" format="html" label="${tool.name}: callpeak on ${on_string} (html report)">
|
|
|
97 <filter>major_command['major_command_selector'] == 'callpeak'</filter>
|
|
|
98 </data>
|
|
|
99 <data name="output_peaks_file" format="xls" label="${tool.name}: callpeak on ${on_string} (peaks: xls)">
|
|
|
100 <filter>major_command['major_command_selector'] == 'callpeak'</filter>
|
|
|
101 </data>
|
|
|
102 <data name="output_narrowpeaks_file" format="txt" label="${tool.name}: callpeak on ${on_string} (peaks: encodePeak)">
|
|
|
103 <filter>major_command['major_command_selector'] == 'callpeak'</filter>
|
|
|
104 </data>
|
|
|
105 <data name="output_xls_to_interval_peaks_file" format="interval" label="${tool.name}: callpeak on ${on_string} (peaks: interval)">
|
|
|
106 <filter>major_command['xls_to_interval'] is True</filter>
|
|
|
107 <filter>major_command['major_command_selector'] == 'callpeak'</filter>
|
|
|
108 </data>
|
|
|
109 <data name="output_xls_to_interval_negative_peaks_file" format="interval" label="${tool.name}: callpeak on ${on_string} (negative peaks: interval)">
|
|
|
110 <filter>major_command['xls_to_interval'] is True</filter>
|
|
|
111 <filter>major_command['input_control_file1'] is not None</filter>
|
|
|
112 <filter>major_command['major_command_selector'] == 'callpeak'</filter>
|
|
|
113 </data>
|
|
|
114 <!--bdgcmp output-->
|
|
|
115 <data name="output_bdgcmp_file" format="bdg" label="${tool.name}: bdgcmp on ${on_string} (bdg)">
|
|
|
116 <filter>major_command['major_command_selector'] == 'bdgcmp'</filter>
|
|
|
117 </data>
|
|
|
118 </outputs>
|
|
|
119 <configfiles>
|
|
|
120
|
|
|
121 <configfile name="outputs_file"><%
|
|
|
122 import simplejson
|
|
|
123 %>
|
|
|
124 ##=======================================================================================
|
|
|
125 #set $__outputs = { 'command':str( $major_command.major_command_selector ) }
|
|
|
126 #if str( $major_command.major_command_selector ) == 'callpeak':
|
|
|
127 #set $__outputs['output_bed_file'] = str( $output_bed_file )
|
|
|
128 #set $__outputs['output_extra_file'] = str( $output_extra_files )
|
|
|
129 #set $__outputs['output_extra_file_path'] = str( $output_extra_files.files_path )
|
|
|
130 #set $__outputs['output_peaks_file'] = str( $output_peaks_file )
|
|
|
131 #set $__outputs['output_narrowpeaks_file'] = str( $output_narrowpeaks_file )
|
|
|
132 #set $__outputs['output_xls_to_interval_peaks_file'] = str( $output_xls_to_interval_peaks_file )
|
|
|
133 #set $__outputs['output_xls_to_interval_negative_peaks_file'] = str( $output_xls_to_interval_negative_peaks_file )
|
|
|
134 #end if
|
|
|
135 ##=======================================================================================
|
|
|
136 #if str( $major_command.major_command_selector ) == 'bdgcmp':
|
|
|
137 #set $__outputs['output_bdgcmp_file'] = str( $output_bdgcmp_file )
|
|
|
138 #end if
|
|
|
139
|
|
|
140 ${ simplejson.dumps( __outputs ) }
|
|
|
141 </configfile>
|
|
|
142 <configfile name="options_file"><%
|
|
|
143 import simplejson
|
|
|
144 %>
|
|
|
145 ##=======================================================================================
|
|
|
146 #set $__options = { 'experiment_name':str( $experiment_name ) }
|
|
|
147 ##treatment/tag input files and format
|
|
|
148 #set $__options['input_chipseq'] = [ str( $major_command.input_chipseq_file1 ) ]
|
|
|
149 #set $__options['format'] = $major_command.input_chipseq_file1.extension.upper()
|
|
|
150
|
|
|
151 ##control/input files
|
|
|
152 #set $__options['input_control'] = []
|
|
|
153 #if str( $major_command.input_control_file1 ) != 'None':
|
|
|
154 #set $_hole = __options['input_control'].append( str( $major_command.input_control_file1 ) )
|
|
|
155 #end if
|
|
|
156
|
|
|
157 #if str( $major_command.major_command_selector ) == 'callpeak':
|
|
|
158 #set $__options['command'] = str( "callpeak" )
|
|
|
159 #set $__options['gsize'] = int( $major_command.gsize )
|
|
|
160 #set $__options['bw'] = str( $major_command.bw )
|
|
|
161 #set $__options['bdg'] = str( $major_command.bdg )
|
|
|
162 #set $__options['xls_to_interval'] = str( $major_command.xls_to_interval )
|
|
|
163
|
|
|
164 ##advanced options
|
|
|
165 #if str( $major_command.advanced_options.advanced_options_selector ) == 'on':
|
|
|
166 #set $__options['mfoldlo'] = int( $major_command.advanced_options.mfoldlo )
|
|
|
167 #set $__options['mfoldhi'] = int( $major_command.advanced_options.mfoldhi )
|
|
|
168 #set $__options['nolambda'] = str( $major_command.advanced_options.nolambda )
|
|
|
169 #else:
|
|
|
170 #set $__options['mfoldlo'] = int( "10" )
|
|
|
171 #set $__options['mfoldhi'] = int( "30" )
|
|
|
172 #set $__options['nolambda'] = str( "" )
|
|
|
173 #end if
|
|
|
174
|
|
|
175 ##enable xls file options
|
|
|
176 ##if str( $major_command.xls_to_interval ) == 'create':
|
|
|
177 ##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 ) }
|
|
|
178 ##end if
|
|
|
179
|
|
|
180 ##pq value select options
|
|
|
181 #if str( $major_command.pq_options.pq_options_selector ) == 'qvalue':
|
|
|
182 #set $__options['qvalue'] = str( $major_command.pq_options.qvalue )
|
|
|
183 #else:
|
|
|
184 #set $__options['pvalue'] = str( $major_command.pq_options.pvalue )
|
|
|
185 #end if
|
|
|
186
|
|
|
187 ##model options
|
|
|
188 #if str( $major_command.nomodel_type.nomodel_type_selector ) == 'nomodel':
|
|
|
189 #set $__options['nomodel'] = str( $major_command.nomodel_type.shiftsize )
|
|
|
190 #end if
|
|
|
191 #end if
|
|
|
192 ##=======================================================================================
|
|
|
193 #if str( $major_command.major_command_selector ) == 'bdgcmp':
|
|
|
194 #set $__options['command'] = str( "bdgcmp" )
|
|
|
195 #set $__options['pseudocount'] = float( str( $major_command.pseudocount ) )
|
|
|
196 #set $__options['m'] = str( $major_command.bdgcmp_options.bdgcmp_options_selector )
|
|
|
197 #end if
|
|
|
198 ##=======================================================================================
|
|
|
199
|
|
|
200 ${ simplejson.dumps( __options ) }
|
|
|
201 </configfile>
|
|
|
202 </configfiles>
|
|
|
203 <tests>
|
|
|
204 <!--none yet for macs2-->
|
|
|
205 </tests>
|
|
|
206 <help>
|
|
|
207 **What it does**
|
|
|
208
|
|
|
209 With the improvement of sequencing techniques, chromatin immunoprecipitation followed by high throughput sequencing (ChIP-Seq)
|
|
|
210 is getting popular to study genome-wide protein-DNA interactions. To address the lack of powerful ChIP-Seq analysis method, we present a novel algorithm, named Model-based Analysis of ChIP-Seq (MACS), for
|
|
|
211 identifying transcript factor binding sites. MACS captures the influence of genome complexity to evaluate the significance of enriched ChIP regions, and MACS improves the spatial resolution of
|
|
|
212 binding sites through combining the information of both sequencing tag position and orientation. MACS can be easily used for ChIP-Seq data alone, or with control sample with the increase of specificity.
|
|
|
213
|
|
|
214 View the original MACS2 documentation: https://github.com/taoliu/MACS/blob/master/README
|
|
|
215
|
|
|
216 ------
|
|
|
217
|
|
|
218 **Usage**
|
|
|
219
|
|
|
220 **Peak Calling**: Main MACS2 Function to Call peaks from alignment results.
|
|
|
221
|
|
|
222 **Compare .bdg files**: Deduct noise by comparing two signal tracks in bedGraph.
|
|
|
223
|
|
|
224
|
|
|
225 ------
|
|
|
226
|
|
|
227 **Citation**
|
|
|
228
|
|
|
229 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.
|
|
|
230
|
|
|
231 Integration of MACS2 with Galaxy performed by Ziru Zhou ( ziruzhou@gmail.com ). Please send your comments/questions to modENCODE DCC at help@modencode.org.
|
|
|
232 </help>
|
|
|
233 </tool> |
