comparison SMART/galaxy/compareOverlapping.xml @ 31:0ab839023fe4

Uploaded
author m-zytnicki
date Tue, 30 Apr 2013 14:33:21 -0400
parents 94ab73e8a190
children
comparison
equal deleted inserted replaced
30:5677346472b5 31:0ab839023fe4
1 <tool id="CompareOverlapping" name="compare overlapping"> 1 <tool id="CompareOverlapping" name="Compare Overlapping">
2 <description>Print all the transcripts from a first file which overlap with the transcripts from a second file.</description> 2 <description>Print all the transcripts from a first file which overlap with the transcripts from a second file.</description>
3 <requirements>
4 <requirement type="set_environment">PYTHONPATH</requirement>
5 </requirements>
6 <command interpreter="python"> 3 <command interpreter="python">
7 ../Java/Python/CompareOverlapping.py -i $formatType.inputFileName1 4 ../Java/Python/CompareOverlapping.py -i $formatType.inputFileName1
8 #if $formatType.FormatInputFileName1 == 'bed': 5 #if $formatType.FormatInputFileName1 == 'bed':
9 -f bed 6 -f bed
10 #elif $formatType.FormatInputFileName1 == 'gff': 7 #elif $formatType.FormatInputFileName1 == 'gff':
108 <when value="sam"> 105 <when value="sam">
109 <param name="inputFileName1" format="sam" type="data" label="Input File 1"/> 106 <param name="inputFileName1" format="sam" type="data" label="Input File 1"/>
110 </when> 107 </when>
111 <when value="gtf"> 108 <when value="gtf">
112 <param name="inputFileName1" format="gtf" type="data" label="Input File 1"/> 109 <param name="inputFileName1" format="gtf" type="data" label="Input File 1"/>
113 </when> 110 </when>
114 </conditional> 111 </conditional>
115 112
116 <conditional name="formatType2"> 113 <conditional name="formatType2">
117 <param name="FormatInputFileName2" type="select" label="Input File Format 2"> 114 <param name="FormatInputFileName2" type="select" label="Input File Format 2">
118 <option value="bed">bed</option> 115 <option value="bed">bed</option>
140 <when value="gtf"> 137 <when value="gtf">
141 <param name="inputFileName2" format="gtf" type="data" label="Input File 2"/> 138 <param name="inputFileName2" format="gtf" type="data" label="Input File 2"/>
142 </when> 139 </when>
143 </conditional> 140 </conditional>
144 141
142
143
145 <conditional name="optionNFirstFile1"> 144 <conditional name="optionNFirstFile1">
146 <param name="NFirstForFile1" type="select" label="Shrink the queries to their first N nt."> 145 <param name="NFirstForFile1" type="select" label="NFirst for file 1" help="only consider the n first nucleotides of the transcripts in file 1">
147 <option value="Yes">Yes</option> 146 <option value="Yes">Yes</option>
148 <option value="No" selected="true">No</option> 147 <option value="No" selected="true">No</option>
149 </param> 148 </param>
150 <when value="Yes"> 149 <when value="Yes">
151 <param name="firstNtFile1" type="integer" value="1" label="size" /> 150 <param name="firstNtFile1" type="integer" value="1" label="n first nucleotides for input file 1" />
152 </when> 151 </when>
153 <when value="No"> 152 <when value="No">
154 </when> 153 </when>
155 </conditional> 154 </conditional>
156 <conditional name="optionNFirstFile2"> 155 <conditional name="optionNFirstFile2">
157 <param name="NFirstForFile2" type="select" label="Shrink the references to their first N nt."> 156 <param name="NFirstForFile2" type="select" label="NFirst for file 2" help="only consider the n first nucleotides of the transcripts in file 2">
158 <option value="Yes">Yes</option> 157 <option value="Yes">Yes</option>
159 <option value="No" selected="true">No</option> 158 <option value="No" selected="true">No</option>
160 </param> 159 </param>
161 <when value="Yes"> 160 <when value="Yes">
162 <param name="firstNtFile2" type="integer" value="1" label="size" /> 161 <param name="firstNtFile2" type="integer" value="1" label="n first nucleotides for input file 1" />
163 </when> 162 </when>
164 <when value="No"> 163 <when value="No">
165 </when> 164 </when>
166 </conditional> 165 </conditional>
167 166
168 <conditional name="optionNLastFile1"> 167 <conditional name="optionNLastFile1">
169 <param name="NLastForFile1" type="select" label="Shrink the queries to their last N nt."> 168 <param name="NLastForFile1" type="select" label="NLast for file 1">
170 <option value="Yes">Yes</option> 169 <option value="Yes">Yes</option>
171 <option value="No" selected="true">No</option> 170 <option value="No" selected="true">No</option>
172 </param> 171 </param>
173 <when value="Yes"> 172 <when value="Yes">
174 <param name="lastNtFile1" type="integer" value="1" label="size"/> 173 <param name="lastNtFile1" type="integer" value="1" label="n last nucleotides for input file 1" help="only consider the n last nucleotides of the transcripts in file 1"/>
175 </when> 174 </when>
176 <when value="No"> 175 <when value="No">
177 </when> 176 </when>
178 </conditional> 177 </conditional>
179 <conditional name="optionNLastFile2"> 178 <conditional name="optionNLastFile2">
180 <param name="NLastForFile2" type="select" label="Shrink the references to their last N nt."> 179 <param name="NLastForFile2" type="select" label="NLast for file 2">
181 <option value="Yes">Yes</option> 180 <option value="Yes">Yes</option>
182 <option value="No" selected="true">No</option> 181 <option value="No" selected="true">No</option>
183 </param> 182 </param>
184 <when value="Yes"> 183 <when value="Yes">
185 <param name="lastNtFile2" type="integer" value="1" label="size"/> 184 <param name="lastNtFile2" type="integer" value="1" label="n last nucleotides for input file 2" help="only consider the n last nucleotides of the transcripts in file 2"/>
186 </when> 185 </when>
187 <when value="No"> 186 <when value="No">
188 </when> 187 </when>
189 </conditional> 188 </conditional>
189
190
190 191
191 <conditional name="optionExtentionCinqFile1"> 192 <conditional name="optionExtentionCinqFile1">
192 <param name="extentionFile1" type="select" label="Extend the query features towards the 5' end"> 193 <param name="extentionFile1" type="select" label="Extension towards 5 for file 1">
193 <option value="Yes">Yes</option> 194 <option value="Yes">Yes</option>
194 <option value="No" selected="true">No</option> 195 <option value="No" selected="true">No</option>
195 </param> 196 </param>
196 <when value="Yes"> 197 <when value="Yes">
197 <param name="extention51" type="integer" value="1" label="in file 1" /> 198 <param name="extention51" type="integer" value="1" label="in file 1" />
198 </when> 199 </when>
199 <when value="No"> 200 <when value="No">
200 </when> 201 </when>
201 </conditional> 202 </conditional>
202 203
204
203 <conditional name="optionExtentionCinqFile2"> 205 <conditional name="optionExtentionCinqFile2">
204 <param name="extentionFile2" type="select" label="Extend the reference features towards 5' end"> 206 <param name="extentionFile2" type="select" label="Extension towards 5 for file 2">
205 <option value="Yes">Yes</option> 207 <option value="Yes">Yes</option>
206 <option value="No" selected="true">No</option> 208 <option value="No" selected="true">No</option>
207 </param> 209 </param>
208 <when value="Yes"> 210 <when value="Yes">
209 <param name="extention52" type="integer" value="1" label="in file 2"/> 211 <param name="extention52" type="integer" value="1" label="in file 2"/>
211 <when value="No"> 213 <when value="No">
212 </when> 214 </when>
213 </conditional> 215 </conditional>
214 216
215 <conditional name="optionExtentionTroisFile1"> 217 <conditional name="optionExtentionTroisFile1">
216 <param name="extentionFile1" type="select" label="Extend the query features towards 3' end"> 218 <param name="extentionFile1" type="select" label="Extension towards 3 for file 1">
217 <option value="Yes">Yes</option> 219 <option value="Yes">Yes</option>
218 <option value="No" selected="true">No</option> 220 <option value="No" selected="true">No</option>
219 </param> 221 </param>
220 <when value="Yes"> 222 <when value="Yes">
221 <param name="extention31" type="integer" value="1" label="in file 1" /> 223 <param name="extention31" type="integer" value="1" label="in file 1" />
223 <when value="No"> 225 <when value="No">
224 </when> 226 </when>
225 </conditional> 227 </conditional>
226 228
227 <conditional name="optionExtentionTroisFile2"> 229 <conditional name="optionExtentionTroisFile2">
228 <param name="extentionFile2" type="select" label="Extend the reference features towards 3' end"> 230 <param name="extentionFile2" type="select" label="Extension towards 3 for file 2">
229 <option value="Yes">Yes</option> 231 <option value="Yes">Yes</option>
230 <option value="No" selected="true">No</option> 232 <option value="No" selected="true">No</option>
231 </param> 233 </param>
232 <when value="Yes"> 234 <when value="Yes">
233 <param name="extention32" type="integer" value="1" label="in file 2" /> 235 <param name="extention32" type="integer" value="1" label="in file 2" />
235 <when value="No"> 237 <when value="No">
236 </when> 238 </when>
237 </conditional> 239 </conditional>
238 240
239 <conditional name="OptionColinearOrAntiSens"> 241 <conditional name="OptionColinearOrAntiSens">
240 <param name="OptionCA" type="select" label="Report queries which are collinear/antisens w.r.t. a reference"> 242 <param name="OptionCA" type="select" label="Colinear or anti-sens">
241 <option value="Colinear">Colinear</option> 243 <option value="Colinear">Colinear</option>
242 <option value="AntiSens">AntiSens</option> 244 <option value="AntiSens">AntiSens</option>
243 <option value="NONE" selected="true">NONE</option> 245 <option value="NONE" selected="true">NONE</option>
244 </param> 246 </param>
245 <when value="Colinear"> 247 <when value="Colinear">
271 <param name="minOverlap" type="integer" value="1"/> 273 <param name="minOverlap" type="integer" value="1"/>
272 </when> 274 </when>
273 <when value="No"> 275 <when value="No">
274 </when> 276 </when>
275 </conditional> 277 </conditional>
276 <param name="ReportIntron" type="boolean" truevalue="-t" falsevalue="" checked="false" label="Also report queries which overlap with the introns of references, or queries such that a reference is in one of its intron"/> 278 <param name="InvertMatch" type="boolean" truevalue="-x" falsevalue="" checked="false" label="Invert match"/>
277 <param name="InvertMatch" type="boolean" truevalue="-x" falsevalue="" checked="false" label="Invert match: the output file will contain all query elements which do NOT overlap"/> 279 <param name="ReportIntron" type="boolean" truevalue="-t" falsevalue="" checked="false" label="Report intron"/>
278 <param name="NotOverlapping" type="boolean" truevalue="-O" falsevalue="" checked="false" label="Also report the query data which do not overlap, with the nbOverlaps tag set to 0."/> 280 <param name="NotOverlapping" type="boolean" truevalue="-O" falsevalue="" checked="false" label="When there is no overlapping, the number of Overlapping will be set to 0 by defalt."/>
281
279 </inputs> 282 </inputs>
280 283
281 <outputs> 284 <outputs>
282 <data name="outputFileGff" format="gff3"/> 285 <data name="outputFileGff" format="gff3"/>
283 </outputs> 286 </outputs>
284 287
285 <help>
286 This script may be the most important one. It basically compares two sets of transcripts and keeps those from the first set which overlap with the second one. The first set is considered as the query set (basically, your data) and the second one is the reference set (RefSeq data, for example).
287
288 It is vital to understand that it will output the elements of the first file which overlap with the elements of the second one.
289
290 Various modifiers are also available:
291
292 -Restrict query / reference set to the first nucleotide. Useful to check if the TSS of one set overlap with the other one.
293
294 -Extend query / reference set on the 5' / 3' direction. Useful to check if one set is located upstream / downstream the other one.
295
296 -Include introns in the comparison.
297
298 -Invert selection (report those which do not overlap).
299
300 -Restrict to colinear / anti-sense overlapping data.
301
302 -Keep the query data even if they do not strictly overlap with the reference data, but are located not further away than *n* nucleotide from some reference data.
303
304 -Keep the query data with are strictly included into reference data, meaning that a query transcript such that at least 1 nucleotide does not overlap with reference data will not be presented as a solution.
305
306 The mechanism of shrinking and extending is also useful to make a fine grain comparison. For example, if you want to keep those such that the TSS is overlapping the reference set, you just shrink the query set to 1 nucleotide. Now, if you want to keep those which are overlapping you data or located 2kb downstream of it, just extend the query data in the downstream direction, and you will have what you want. You can also extend in the opposite direction to get the possible transcript factor sites which are upstream.
307
308 Some option reverses the selection. Put in other words, it performs the comparison as usual, and outputs all those query data which do not overlap.
309 </help>
310 </tool> 288 </tool>