|
38
|
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>
|
|
|
3 <requirements>
|
|
|
4 <requirement type="set_environment">PYTHONPATH</requirement>
|
|
|
5 </requirements>
|
|
|
6 <command interpreter="python">
|
|
|
7 ../Java/Python/CompareOverlapping.py -i $formatType.inputFileName1
|
|
|
8 #if $formatType.FormatInputFileName1 == 'bed':
|
|
|
9 -f bed
|
|
|
10 #elif $formatType.FormatInputFileName1 == 'gff':
|
|
|
11 -f gff
|
|
|
12 #elif $formatType.FormatInputFileName1 == 'gff2':
|
|
|
13 -f gff2
|
|
|
14 #elif $formatType.FormatInputFileName1 == 'gff3':
|
|
|
15 -f gff3
|
|
|
16 #elif $formatType.FormatInputFileName1 == 'sam':
|
|
|
17 -f sam
|
|
|
18 #elif $formatType.FormatInputFileName1 == 'gtf':
|
|
|
19 -f gtf
|
|
|
20 #end if
|
|
|
21
|
|
|
22 -j $formatType2.inputFileName2
|
|
|
23 #if $formatType2.FormatInputFileName2 == 'bed':
|
|
|
24 -g bed
|
|
|
25 #elif $formatType2.FormatInputFileName2 == 'gff':
|
|
|
26 -g gff
|
|
|
27 #elif $formatType2.FormatInputFileName2 == 'gff2':
|
|
|
28 -g gff2
|
|
|
29 #elif $formatType2.FormatInputFileName2 == 'gff3':
|
|
|
30 -g gff3
|
|
|
31 #elif $formatType2.FormatInputFileName2 == 'sam':
|
|
|
32 -g sam
|
|
|
33 #elif $formatType2.FormatInputFileName2 == 'gtf':
|
|
|
34 -g gtf
|
|
|
35 #end if
|
|
|
36
|
|
|
37 -o $outputFileGff
|
|
|
38
|
|
|
39 #if $optionNFirstFile1.NFirstForFile1 == 'Yes':
|
|
|
40 -S $optionNFirstFile1.firstNtFile1
|
|
|
41 #end if
|
|
|
42 #if $optionNFirstFile2.NFirstForFile2 == 'Yes':
|
|
|
43 -s $optionNFirstFile2.firstNtFile2
|
|
|
44 #end if
|
|
|
45 #if $optionNLastFile1.NLastForFile1 == 'Yes':
|
|
|
46 -U $optionNLastFile1.lastNtFile1
|
|
|
47 #end if
|
|
|
48 #if $optionNLastFile2.NLastForFile2 == 'Yes':
|
|
|
49 -u $optionNLastFile2.lastNtFile2
|
|
|
50 #end if
|
|
|
51
|
|
|
52 #if $optionExtentionCinqFile1.extentionFile1 == 'Yes':
|
|
|
53 -E $optionExtentionCinqFile1.extention51
|
|
|
54 #end if
|
|
|
55 #if $optionExtentionCinqFile2.extentionFile2 == 'Yes':
|
|
|
56 -e $optionExtentionCinqFile2.extention52
|
|
|
57 #end if
|
|
|
58
|
|
|
59 #if $optionExtentionTroisFile1.extentionFile1 == 'Yes':
|
|
|
60 -N $optionExtentionTroisFile1.extention31
|
|
|
61 #end if
|
|
|
62 #if $optionExtentionTroisFile2.extentionFile2 == 'Yes':
|
|
|
63 -n $optionExtentionTroisFile2.extention32
|
|
|
64 #end if
|
|
|
65
|
|
|
66 #if $OptionColinearOrAntiSens.OptionCA == 'Colinear':
|
|
|
67 -c
|
|
|
68 #elif $OptionColinearOrAntiSens.OptionCA == 'AntiSens':
|
|
|
69 -a
|
|
|
70 #end if
|
|
|
71
|
|
|
72 #if $OptionDistance.Dist == 'Yes':
|
|
|
73 -d $OptionDistance.distance
|
|
|
74 #end if
|
|
|
75
|
|
|
76 #if $OptionMinOverlap.MO == 'Yes':
|
|
|
77 -m $OptionMinOverlap.minOverlap
|
|
|
78 #end if
|
|
|
79
|
|
|
80 $InvertMatch
|
|
|
81 $ReportIntron
|
|
|
82 $NotOverlapping
|
|
|
83
|
|
|
84 </command>
|
|
|
85
|
|
|
86 <inputs>
|
|
|
87 <conditional name="formatType">
|
|
|
88 <param name="FormatInputFileName1" type="select" label="Input File Format 1">
|
|
|
89 <option value="bed">bed</option>
|
|
|
90 <option value="gff">gff</option>
|
|
|
91 <option value="gff2">gff2</option>
|
|
|
92 <option value="gff3">gff3</option>
|
|
|
93 <option value="sam">sam</option>
|
|
|
94 <option value="gtf">gtf</option>
|
|
|
95 </param>
|
|
|
96 <when value="bed">
|
|
|
97 <param name="inputFileName1" format="bed" type="data" label="Input File 1"/>
|
|
|
98 </when>
|
|
|
99 <when value="gff">
|
|
|
100 <param name="inputFileName1" format="gff" type="data" label="Input File 1"/>
|
|
|
101 </when>
|
|
|
102 <when value="gff2">
|
|
|
103 <param name="inputFileName1" format="gff2" type="data" label="Input File 1"/>
|
|
|
104 </when>
|
|
|
105 <when value="gff3">
|
|
|
106 <param name="inputFileName1" format="gff3" type="data" label="Input File 1"/>
|
|
|
107 </when>
|
|
|
108 <when value="sam">
|
|
|
109 <param name="inputFileName1" format="sam" type="data" label="Input File 1"/>
|
|
|
110 </when>
|
|
|
111 <when value="gtf">
|
|
|
112 <param name="inputFileName1" format="gtf" type="data" label="Input File 1"/>
|
|
|
113 </when>
|
|
|
114 </conditional>
|
|
|
115
|
|
|
116 <conditional name="formatType2">
|
|
|
117 <param name="FormatInputFileName2" type="select" label="Input File Format 2">
|
|
|
118 <option value="bed">bed</option>
|
|
|
119 <option value="gff">gff</option>
|
|
|
120 <option value="gff2">gff2</option>
|
|
|
121 <option value="gff3">gff3</option>
|
|
|
122 <option value="sam">sam</option>
|
|
|
123 <option value="gtf">gtf</option>
|
|
|
124 </param>
|
|
|
125 <when value="bed">
|
|
|
126 <param name="inputFileName2" format="bed" type="data" label="Input File 2"/>
|
|
|
127 </when>
|
|
|
128 <when value="gff">
|
|
|
129 <param name="inputFileName2" format="gff" type="data" label="Input File 2"/>
|
|
|
130 </when>
|
|
|
131 <when value="gff2">
|
|
|
132 <param name="inputFileName2" format="gff2" type="data" label="Input File 2"/>
|
|
|
133 </when>
|
|
|
134 <when value="gff3">
|
|
|
135 <param name="inputFileName2" format="gff3" type="data" label="Input File 2"/>
|
|
|
136 </when>
|
|
|
137 <when value="sam">
|
|
|
138 <param name="inputFileName2" format="sam" type="data" label="Input File 2"/>
|
|
|
139 </when>
|
|
|
140 <when value="gtf">
|
|
|
141 <param name="inputFileName2" format="gtf" type="data" label="Input File 2"/>
|
|
|
142 </when>
|
|
|
143 </conditional>
|
|
|
144
|
|
|
145 <conditional name="optionNFirstFile1">
|
|
|
146 <param name="NFirstForFile1" type="select" label="Shrink the queries to their first N nt.">
|
|
|
147 <option value="Yes">Yes</option>
|
|
|
148 <option value="No" selected="true">No</option>
|
|
|
149 </param>
|
|
|
150 <when value="Yes">
|
|
|
151 <param name="firstNtFile1" type="integer" value="1" label="size" />
|
|
|
152 </when>
|
|
|
153 <when value="No">
|
|
|
154 </when>
|
|
|
155 </conditional>
|
|
|
156 <conditional name="optionNFirstFile2">
|
|
|
157 <param name="NFirstForFile2" type="select" label="Shrink the references to their first N nt.">
|
|
|
158 <option value="Yes">Yes</option>
|
|
|
159 <option value="No" selected="true">No</option>
|
|
|
160 </param>
|
|
|
161 <when value="Yes">
|
|
|
162 <param name="firstNtFile2" type="integer" value="1" label="size" />
|
|
|
163 </when>
|
|
|
164 <when value="No">
|
|
|
165 </when>
|
|
|
166 </conditional>
|
|
|
167
|
|
|
168 <conditional name="optionNLastFile1">
|
|
|
169 <param name="NLastForFile1" type="select" label="Shrink the queries to their last N nt.">
|
|
|
170 <option value="Yes">Yes</option>
|
|
|
171 <option value="No" selected="true">No</option>
|
|
|
172 </param>
|
|
|
173 <when value="Yes">
|
|
|
174 <param name="lastNtFile1" type="integer" value="1" label="size"/>
|
|
|
175 </when>
|
|
|
176 <when value="No">
|
|
|
177 </when>
|
|
|
178 </conditional>
|
|
|
179 <conditional name="optionNLastFile2">
|
|
|
180 <param name="NLastForFile2" type="select" label="Shrink the references to their last N nt.">
|
|
|
181 <option value="Yes">Yes</option>
|
|
|
182 <option value="No" selected="true">No</option>
|
|
|
183 </param>
|
|
|
184 <when value="Yes">
|
|
|
185 <param name="lastNtFile2" type="integer" value="1" label="size"/>
|
|
|
186 </when>
|
|
|
187 <when value="No">
|
|
|
188 </when>
|
|
|
189 </conditional>
|
|
|
190
|
|
|
191 <conditional name="optionExtentionCinqFile1">
|
|
|
192 <param name="extentionFile1" type="select" label="Extend the query features towards the 5' end">
|
|
|
193 <option value="Yes">Yes</option>
|
|
|
194 <option value="No" selected="true">No</option>
|
|
|
195 </param>
|
|
|
196 <when value="Yes">
|
|
|
197 <param name="extention51" type="integer" value="1" label="in file 1" />
|
|
|
198 </when>
|
|
|
199 <when value="No">
|
|
|
200 </when>
|
|
|
201 </conditional>
|
|
|
202
|
|
|
203 <conditional name="optionExtentionCinqFile2">
|
|
|
204 <param name="extentionFile2" type="select" label="Extend the reference features towards 5' end">
|
|
|
205 <option value="Yes">Yes</option>
|
|
|
206 <option value="No" selected="true">No</option>
|
|
|
207 </param>
|
|
|
208 <when value="Yes">
|
|
|
209 <param name="extention52" type="integer" value="1" label="in file 2"/>
|
|
|
210 </when>
|
|
|
211 <when value="No">
|
|
|
212 </when>
|
|
|
213 </conditional>
|
|
|
214
|
|
|
215 <conditional name="optionExtentionTroisFile1">
|
|
|
216 <param name="extentionFile1" type="select" label="Extend the query features towards 3' end">
|
|
|
217 <option value="Yes">Yes</option>
|
|
|
218 <option value="No" selected="true">No</option>
|
|
|
219 </param>
|
|
|
220 <when value="Yes">
|
|
|
221 <param name="extention31" type="integer" value="1" label="in file 1" />
|
|
|
222 </when>
|
|
|
223 <when value="No">
|
|
|
224 </when>
|
|
|
225 </conditional>
|
|
|
226
|
|
|
227 <conditional name="optionExtentionTroisFile2">
|
|
|
228 <param name="extentionFile2" type="select" label="Extend the reference features towards 3' end">
|
|
|
229 <option value="Yes">Yes</option>
|
|
|
230 <option value="No" selected="true">No</option>
|
|
|
231 </param>
|
|
|
232 <when value="Yes">
|
|
|
233 <param name="extention32" type="integer" value="1" label="in file 2" />
|
|
|
234 </when>
|
|
|
235 <when value="No">
|
|
|
236 </when>
|
|
|
237 </conditional>
|
|
|
238
|
|
|
239 <conditional name="OptionColinearOrAntiSens">
|
|
|
240 <param name="OptionCA" type="select" label="Report queries which are collinear/antisens w.r.t. a reference">
|
|
|
241 <option value="Colinear">Colinear</option>
|
|
|
242 <option value="AntiSens">AntiSens</option>
|
|
|
243 <option value="NONE" selected="true">NONE</option>
|
|
|
244 </param>
|
|
|
245 <when value="Colinear">
|
|
|
246 </when>
|
|
|
247 <when value="AntiSens">
|
|
|
248 </when>
|
|
|
249 <when value="NONE">
|
|
|
250 </when>
|
|
|
251 </conditional>
|
|
|
252
|
|
|
253 <conditional name="OptionDistance">
|
|
|
254 <param name="Dist" type="select" label="Maximum Distance between two reads">
|
|
|
255 <option value="Yes">Yes</option>
|
|
|
256 <option value="No" selected="true">No</option>
|
|
|
257 </param>
|
|
|
258 <when value="Yes">
|
|
|
259 <param name="distance" type="integer" value="0"/>
|
|
|
260 </when>
|
|
|
261 <when value="No">
|
|
|
262 </when>
|
|
|
263 </conditional>
|
|
|
264
|
|
|
265 <conditional name="OptionMinOverlap">
|
|
|
266 <param name="MO" type="select" label="Minimum number of overlapping between two reads">
|
|
|
267 <option value="Yes">Yes</option>
|
|
|
268 <option value="No" selected="true">No</option>
|
|
|
269 </param>
|
|
|
270 <when value="Yes">
|
|
|
271 <param name="minOverlap" type="integer" value="1"/>
|
|
|
272 </when>
|
|
|
273 <when value="No">
|
|
|
274 </when>
|
|
|
275 </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"/>
|
|
|
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"/>
|
|
|
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."/>
|
|
|
279 </inputs>
|
|
|
280
|
|
|
281 <outputs>
|
|
|
282 <data name="outputFileGff" format="gff3"/>
|
|
|
283 </outputs>
|
|
|
284
|
|
|
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>
|
