|
0
|
1 <tool name="CEAS: Enrichment on chromosome and annotation" id="ceas_ceas" version="0.1.0">
|
|
|
2 <description>Annotate the given intervals and scores with genome features such as gene body</description>
|
|
|
3 <macros>
|
|
|
4 <import>ceas_macros.xml</import>
|
|
|
5 </macros>
|
|
|
6 <expand macro="requirements_bx" />
|
|
|
7 <command>
|
|
|
8 #import os.path
|
|
|
9 #if $genegroup.enable == "yes"
|
|
|
10 #set $gngroups = str($genegroup.genelist)
|
|
|
11 #set $gnlabels = str($genegroup.label)
|
|
|
12 #for $m in $genegroup.more
|
|
|
13 #set $gngroups = $gngroups+","+str($m.genelist)
|
|
|
14 #set $gnlabels = $gnlabels+","+str($m.label)
|
|
|
15 #end for
|
|
|
16 #set $gngroupspara = "--gn-groups="+$gngroups
|
|
|
17 #set $gnlabelspara = "--gn-group-names='"+$gnlabels+"'"+str($genegroup.idtype.value)
|
|
|
18 #else
|
|
|
19 #set $gngroupspara = ""
|
|
|
20 #set $gnlabelspara = ""
|
|
|
21 #end if
|
|
|
22 #set $sizes = str($lowersize) + "," + str($middlesize) + "," + str($uppersize)
|
|
|
23 #set $bisizes = str($lowerbisize) + "," + str($upperbisize)
|
|
|
24 #if $wfile:
|
|
|
25 #if $wfile.extension == "bigwig"
|
|
|
26 ceasBW -w $wfile
|
|
|
27 #set dbkey = $wfile.metadata.dbkey
|
|
|
28 #set $length_file = os.path.join( os.path.abspath($__app__.config.len_file_path), $dbkey+".len" )
|
|
|
29 -l $length_file
|
|
|
30 #else
|
|
|
31 ceas -w $wfile
|
|
|
32 #end if
|
|
|
33 #else
|
|
|
34 ceas
|
|
|
35 #end if
|
|
|
36 #if $bfile:
|
|
|
37 -b $bfile
|
|
|
38 #end if
|
|
|
39 #include source=$gtpath_ceasdb_ref#
|
|
|
40 --span=$span --pf-res=$pfres --sizes=$sizes --bisizes=$bisizes
|
|
|
41 --rel-dist=$reldist $gngroupspara $gnlabelspara --name=$name &> $log &&
|
|
|
42 Rscript ceas_out.R &&
|
|
|
43 #if $imagetype.__str__ == "PNG":
|
|
|
44 convert ceas_out.pdf ceas_out.png && convert ceas_out-*.png -append ceas_out_joint.png &&
|
|
|
45 cp ceas_out_joint.png $output
|
|
|
46 #else
|
|
|
47 cp ceas_out.pdf $output
|
|
|
48 #end if
|
|
|
49 </command>
|
|
|
50 <inputs>
|
|
|
51 <expand macro="ceasdb_ref" />
|
|
|
52 <param name="name" type="hidden" value="ceas_out"/>
|
|
|
53 <param format="wig,bigwig" name="wfile" type="data" label="wig / bigwig file" optional="true">
|
|
|
54 <validator type="unspecified_build" />
|
|
|
55 </param>
|
|
|
56 <param format="bed" name="bfile" type="data" label="BED file(maximum 100000 lines)" optional="true">
|
|
|
57 <validator type="unspecified_build" />
|
|
|
58 </param>
|
|
|
59 <param name="span" type="integer" label="Span" value="3000">
|
|
|
60 <validator type="in_range" max="1000000" min="100" message="The Span is out of range, the parameter has to be between 100 to 1000000" />
|
|
|
61 </param>
|
|
|
62 <param name="pfres" type="integer" label="Profiling resolution" value="50">
|
|
|
63 <validator type="in_range" max="1000" min="10" message="The Profiling Resolution is out of range, the parameter has to be between 10 to 1000" />
|
|
|
64 </param>
|
|
|
65 <param name="lowersize" type="text" label="Promoter/downstream lower-interval" value="1000" >
|
|
|
66 <validator type="in_range" max="10000" min="100" message="The lower-interval is out of range, the parameter has to be between 100 to 10000" />
|
|
|
67 </param>
|
|
|
68 <param name="middlesize" type="text" label="Promoter/downstream middle-interval" value="2000" >
|
|
|
69 <validator type="in_range" max="10000" min="100" message="The middle-interval is out of range, the parameter has to be between 100 to 10000" />
|
|
|
70 </param>
|
|
|
71 <param name="uppersize" type="text" label="Promoter/downstream upper-interval" value="3000">
|
|
|
72 <validator type="in_range" max="10000" min="100" message="The upper-interval is out of range, the parameter has to be between 100 to 10000" />
|
|
|
73 </param>
|
|
|
74 <param name="lowerbisize" type="text" label="Bi-Promoter lower range" value="2500">
|
|
|
75 <validator type="in_range" max="10000" min="100" message="The lower-range is out of range, the parameter has to be between 100 to 10000" />
|
|
|
76 </param>
|
|
|
77 <param name="upperbisize" type="text" label="Bi-Promoter upper range" value="5000">
|
|
|
78 <validator type="in_range" max="10000" min="100" message="The upper-range is out of range, the parameter has to be between 100 to 10000" />
|
|
|
79 </param>
|
|
|
80 <param name="reldist" type="integer" label="Relative distance" value="3000">
|
|
|
81 <validator type="in_range" max="10000" min="100" message="The Relative distance is out of range, the parameter has to be between 100 to 10000" />
|
|
|
82 </param>
|
|
|
83 <param type="select" name="imagetype" display="radio" label="Image Type">
|
|
|
84 <option value="PNG">PNG format</option>
|
|
|
85 <option value="PDF">PDF format</option>
|
|
|
86 </param>
|
|
|
87
|
|
|
88 <conditional name="genegroup">
|
|
|
89 <param name="enable" type="select" label="Specify gene list in the signal profiling" force_select="true">
|
|
|
90 <option value="no">No</option>
|
|
|
91 <option value="yes">Yes</option>
|
|
|
92 </param>
|
|
|
93
|
|
|
94 <when value="no">
|
|
|
95 </when>
|
|
|
96
|
|
|
97 <when value="yes">
|
|
|
98 <param format="text" name="genelist" type="data" label="Gene List" optional="false"/>
|
|
|
99 <param name="label" type="text" label="Gene List Label" optional="false" />
|
|
|
100 <repeat name="more" title="Gene Lists">
|
|
|
101 <param format="text" name="genelist" type="data" label="Gene List" optional="false"/>
|
|
|
102 <param name="label" type="text" label="Gene List Label" optional="false" />
|
|
|
103 </repeat>
|
|
|
104 <param name="idtype" type="select" label="Are they ...">
|
|
|
105 <option value="">refseq</option>
|
|
|
106 <option value=" --gname2">genesymbol</option>
|
|
|
107 </param>
|
|
|
108 </when>
|
|
|
109 </conditional>
|
|
|
110
|
|
|
111 </inputs>
|
|
|
112
|
|
|
113 <outputs>
|
|
|
114 <data format="png" name="output">
|
|
|
115 <change_format>
|
|
|
116 <when input="imagetype" value="PDF" format="pdf" />
|
|
|
117 </change_format>
|
|
|
118 </data>
|
|
|
119 <data format="txt" name="log" label="ceas job log" />
|
|
|
120 </outputs>
|
|
|
121 <expand macro="stdio" />
|
|
|
122 <tests>
|
|
|
123 <test>
|
|
|
124 <param name="wfile" value="treatment.wig" />
|
|
|
125 <param name="bfile" value="peaks.bed" />
|
|
|
126 <param name="span" value="3000" />
|
|
|
127 <param name="pfres" value="50" />
|
|
|
128 <param name="lowersize" value="1000" />
|
|
|
129 <param name="middlesize" value="2000" />
|
|
|
130 <param name="uppersize" value="3000" />
|
|
|
131 <param name="lowerbisize" value="2500" />
|
|
|
132 <param name="upperbisize" value="5000" />
|
|
|
133 <param name="reldist" value="3000" />
|
|
|
134 <param name="refsrc" value="history"/>
|
|
|
135 <param name="gdb" ftype="ceasdb" value="mm9.refGene.ceasdb"/>
|
|
|
136 <param name="imagetype" value="PDF" />
|
|
|
137 <param name="enable" value="no" />
|
|
|
138 <output name="log">
|
|
|
139 <assert_contents>
|
|
|
140 <has_text_matching expression="See ceas_out.pdf for the graphical results of CEAS" />
|
|
|
141 </assert_contents>
|
|
|
142 </output>
|
|
|
143 </test>
|
|
|
144 <test>
|
|
|
145 <param name="wfile" value="treatment.bigwig" />
|
|
|
146 <param name="bfile" value="peaks.bed" />
|
|
|
147 <param name="span" value="3000" />
|
|
|
148 <param name="pfres" value="50" />
|
|
|
149 <param name="lowersize" value="1000" />
|
|
|
150 <param name="middlesize" value="2000" />
|
|
|
151 <param name="uppersize" value="3000" />
|
|
|
152 <param name="lowerbisize" value="2500" />
|
|
|
153 <param name="upperbisize" value="5000" />
|
|
|
154 <param name="reldist" value="3000" />
|
|
|
155 <param name="refsrc" value="history"/>
|
|
|
156 <param name="gdb" ftype="ceasdb" value="mm9.refGene.ceasdb"/>
|
|
|
157 <param name="imagetype" value="PDF" />
|
|
|
158 <param name="enable" value="no" />
|
|
|
159 <output name="log">
|
|
|
160 <assert_contents>
|
|
|
161 <has_text_matching expression="See ceas_out.pdf for the graphical results of CEAS" />
|
|
|
162 </assert_contents>
|
|
|
163 </output>
|
|
|
164 </test>
|
|
|
165 </tests>
|
|
|
166 <help>
|
|
|
167 ** CEAS **
|
|
|
168 This tool annotates the given intervals and scores with genome
|
|
|
169 features such as gene body. It's the major module in CEAS package
|
|
|
170 which is written by Hyunjin Gene Shin, published in Bioinformatics
|
|
|
171 (pubmed id:19689956).
|
|
|
172
|
|
|
173 @EXTERNAL_DOCUMENTATION@
|
|
|
174
|
|
|
175 @CITATION_SECTION@
|
|
|
176
|
|
|
177
|
|
|
178 .. class:: warningmark
|
|
|
179
|
|
|
180 **NEED IMPROVEMENT**
|
|
|
181
|
|
|
182 -----
|
|
|
183
|
|
|
184 **Parameters**
|
|
|
185
|
|
|
186 - **WIGGLE file** contains the scores for the experiment in a wiggle
|
|
|
187 format file. Normally, it's produced by the peak calling tool. It's
|
|
|
188 optional.
|
|
|
189 - **BED file** contains the peak locations for the experiment in a BED
|
|
|
190 format file.
|
|
|
191 - **Span** from TSS and TTS in the gene-centered annotation. ChIP
|
|
|
192 regions within this range from TSS and TTS are considered when
|
|
|
193 calculating the coverage rates in promoter and downstream.
|
|
|
194 - **Profiling resolution** is the WIGGLE profiling resolution.
|
|
|
195 - **Promoter/downstream intervals** for ChIP region annotation are
|
|
|
196 comma-separated three values or a single value can be given. If a
|
|
|
197 single value is given, it will be segmented into three equal
|
|
|
198 fractions (ie, 3000 is equivalent to 1000,2000,3000)
|
|
|
199 - **BiPromoter ranges** is for ChIP region annotation. It's
|
|
|
200 comma-separated two values or a single value can be given. If a
|
|
|
201 single value is given, it will be segmented into two equal fractions
|
|
|
202 (ie, 5000 is equivalent to 2500,5000)
|
|
|
203 - **Relative distance** is the relative distance to TSS/TTS in WIGGLE file
|
|
|
204 profiling
|
|
|
205 - **Genome Annotation Version** to specify the annotations according to
|
|
|
206 the data set. The annotations are downloaded from UCSC genome site.
|
|
|
207 - **Image type** specify the output image format, either in PNG or in
|
|
|
208 PDF format.
|
|
|
209 - If **Specify gene list in the signal profiling** is set, you can specify
|
|
|
210 different gene groups for CEAS to put them together in the profile
|
|
|
211 figure. You need to select several **Gene List** files from history which
|
|
|
212 contains the RefSeq ids or Gene Symbols for each row, and
|
|
|
213 **Gene List Label** for each gene list file.
|
|
|
214
|
|
|
215 -----
|
|
|
216
|
|
|
217 **Outputs**
|
|
|
218
|
|
|
219 - **PNG/PDF file** is the result for CEAS analysis, containing 5 pages.
|
|
|
220 - **LOG file** for job log. If you see errors, please attached this in
|
|
|
221 the bug report
|
|
|
222
|
|
|
223 -----
|
|
|
224
|
|
|
225 **script parameter list of CEAS 0.9.8**
|
|
|
226
|
|
|
227 Options:
|
|
|
228 --version show program's version number and exit
|
|
|
229 -h, --help Show this help message and exit.
|
|
|
230 -b BED, --bed=BED BED file of ChIP regions.
|
|
|
231 -w WIG, --wig=WIG WIG file for either wig profiling or genome background
|
|
|
232 annotation. WARNING: --bg flag must be set for genome
|
|
|
233 background re-annotation.
|
|
|
234 -e EBED, --ebed=EBED BED file of extra regions of interest (eg, non-coding
|
|
|
235 regions)
|
|
|
236 -g GDB, --gt=GDB Gene annotation table (eg, a refGene table in sqlite3
|
|
|
237 db format provided through the CEAS web,
|
|
|
238 http://liulab.dfci.harvard.edu/CEAS/download.html).
|
|
|
239 --name=NAME Experiment name. This will be used to name the output
|
|
|
240 files. If an experiment name is not given, the stem of
|
|
|
241 the input BED file name will be used instead (eg, if
|
|
|
242 'peaks.bed', 'peaks' will be used as a name.)
|
|
|
243 --sizes=SIZES Promoter (also dowsntream) sizes for ChIP region
|
|
|
244 annotation. Comma-separated three values or a single
|
|
|
245 value can be given. If a single value is given, it
|
|
|
246 will be segmented into three equal fractions (ie, 3000
|
|
|
247 is equivalent to 1000,2000,3000), DEFAULT:
|
|
|
248 1000,2000,3000. WARNING: Values > 10000bp are
|
|
|
249 automatically set to 10000bp.
|
|
|
250 --bisizes=BISIZES Bidirectional-promoter sizes for ChIP region
|
|
|
251 annotation Comma-separated two values or a single
|
|
|
252 value can be given. If a single value is given, it
|
|
|
253 will be segmented into two equal fractions (ie, 5000
|
|
|
254 is equivalent to 2500,5000) DEFAULT: 2500,5000bp.
|
|
|
255 WARNING: Values > 20000bp are automatically set to
|
|
|
256 20000bp.
|
|
|
257 --bg Run genome BG annotation again. WARNING: This flag is
|
|
|
258 effective only if a WIG file is given through -w
|
|
|
259 (--wig). Otherwise, ignored.
|
|
|
260 --span=SPAN Span from TSS and TTS in the gene-centered annotation.
|
|
|
261 ChIP regions within this range from TSS and TTS are
|
|
|
262 considered when calculating the coverage rates in
|
|
|
263 promoter and downstream, DEFAULT=3000bp
|
|
|
264 --pf-res=PF_RES Wig profiling resolution, DEFAULT: 50bp. WARNING:
|
|
|
265 Value smaller than the wig interval (resolution) may
|
|
|
266 cause aliasing error.
|
|
|
267 --rel-dist=REL_DIST Relative distance to TSS/TTS in wig profiling,
|
|
|
268 DEFAULT: 3000bp
|
|
|
269 --gn-groups=GN_GROUPS
|
|
|
270 Gene-groups of particular interest in wig profiling.
|
|
|
271 Each gene group file must have gene names in the 1st
|
|
|
272 column. The file names are separated by commas w/ no
|
|
|
273 space (eg, --gn-groups=top10.txt,bottom10.txt)
|
|
|
274 --gn-group-names=GN_NAMES
|
|
|
275 The names of the gene groups in --gn-groups. The gene
|
|
|
276 group names are separated by commas. (eg, --gn-group-
|
|
|
277 names='top 10%,bottom 10%'). These group names appear
|
|
|
278 in the legends of the wig profiling plots. If no group
|
|
|
279 names given, the groups are represented as 'Group 1,
|
|
|
280 Group2,...Group n'.
|
|
|
281 --gname2 Whether or not use the 'name2' column of the gene
|
|
|
282 annotation table when reading the gene IDs in the
|
|
|
283 files given through --gn-groups. This flag is
|
|
|
284 meaningful only with --gn-groups.
|
|
|
285
|
|
|
286 </help>
|
|
|
287
|
|
|
288 </tool>
|
