comparison SMART/galaxy/CompareOverlappingSmallQuery.xml @ 15:440ceca58672

Uploaded
author m-zytnicki
date Mon, 22 Apr 2013 11:08:07 -0400
parents 03045debed6e
children 94ab73e8a190
comparison
equal deleted inserted replaced
14:c79b9ae3f65f 15:440ceca58672
1 <tool id="CompareOverlappingSmallQuery" name="Compare Overlapping Small Query"> 1 <tool id="CompareOverlappingSmallQuery" name="compare Overlapping Small Query">
2 <description>Provide the queries that overlap with a reference, when the query is small.</description> 2 <description>Provide the queries that overlap with a reference, when the query data set is small.</description>
3 <command interpreter="python"> 3 <command interpreter="python">
4 ../Java/Python/CompareOverlappingSmallQuery.py -i $formatType.inputFileName1 4 ../Java/Python/CompareOverlappingSmallQuery.py -i $formatType.inputFileName1
5 #if $formatType.FormatInputFileName1 == 'bed': 5 #if $formatType.FormatInputFileName1 == 'bed':
6 -f bed 6 -f bed
7 #elif $formatType.FormatInputFileName1 == 'gff': 7 #elif $formatType.FormatInputFileName1 == 'gff':
34 -d $OptionDistance.distance 34 -d $OptionDistance.distance
35 #end if 35 #end if
36 #if $OptionMinOverlap.present == 'Yes': 36 #if $OptionMinOverlap.present == 'Yes':
37 -m $OptionMinOverlap.minOverlap 37 -m $OptionMinOverlap.minOverlap
38 #end if 38 #end if
39 #if $OptionPcOverlapQuery.present == 'Yes':
40 -p $OptionPcOverlapQuery.minOverlap
41 #end if
42 #if $OptionPcOverlapRef.present == 'Yes':
43 -P $OptionPcOverlapRef.minOverlap
44 #end if
39 #if $OptionCollinearOrAntiSens.OptionCA == 'Collinear': 45 #if $OptionCollinearOrAntiSens.OptionCA == 'Collinear':
40 -c 46 -c
41 #elif $OptionCollinearOrAntiSens.OptionCA == 'Antisense': 47 #elif $OptionCollinearOrAntiSens.OptionCA == 'AntiSens':
42 -a 48 -a
43 #end if 49 #end if
44 $InvertMatch 50 $InvertMatch
45 $NotOverlapping 51 $NotOverlapping
52 $OptionInclusionQuery
53 $OptionInclusionRef
46 </command> 54 </command>
47 55
48 <inputs> 56 <inputs>
49 <conditional name="formatType"> 57 <conditional name="formatType">
50 <param name="FormatInputFileName1" type="select" label="Input Query File Format"> 58 <param name="FormatInputFileName1" type="select" label="Input Query File Format">
102 <when value="gtf"> 110 <when value="gtf">
103 <param name="inputFileName2" format="gtf" type="data" label="Input File 2"/> 111 <param name="inputFileName2" format="gtf" type="data" label="Input File 2"/>
104 </when> 112 </when>
105 </conditional> 113 </conditional>
106 <conditional name="OptionDistance"> 114 <conditional name="OptionDistance">
107 <param name="Dist" type="select" label="Maximum Distance between two regions"> 115 <param name="Dist" type="select" label="Maximum Distance between two reads">
108 <option value="Yes">Yes</option> 116 <option value="Yes">Yes</option>
109 <option value="No" selected="true">No</option> 117 <option value="No" selected="true">No</option>
110 </param> 118 </param>
111 <when value="Yes"> 119 <when value="Yes">
112 <param name="distance" type="integer" value="0"/> 120 <param name="distance" type="integer" value="0"/>
123 <param name="minOverlap" type="integer" value="0"/> 131 <param name="minOverlap" type="integer" value="0"/>
124 </when> 132 </when>
125 <when value="No"> 133 <when value="No">
126 </when> 134 </when>
127 </conditional> 135 </conditional>
136 <conditional name="OptionPcOverlapQuery">
137 <param name="present" type="select" label="N% of the query must overlap">
138 <option value="Yes">Yes</option>
139 <option value="No" selected="true">No</option>
140 </param>
141 <when value="Yes">
142 <param name="minOverlap" type="integer" value="0"/>
143 </when>
144 <when value="No">
145 </when>
146 </conditional>
147 <conditional name="OptionPcOverlapRef">
148 <param name="present" type="select" label="N% of the reference must overlap">
149 <option value="Yes">Yes</option>
150 <option value="No" selected="true">No</option>
151 </param>
152 <when value="Yes">
153 <param name="minOverlap" type="integer" value="0"/>
154 </when>
155 <when value="No">
156 </when>
157 </conditional>
158 <param name="OptionInclusionQuery" type="boolean" truevalue="-k" falsevalue="" checked="false" label="The query must be nested in a query"/>
159 <param name="OptionInclusionRef" type="boolean" truevalue="-K" falsevalue="" checked="false" label="The reference must be nested in a query"/>
128 <conditional name="OptionCollinearOrAntiSens"> 160 <conditional name="OptionCollinearOrAntiSens">
129 <param name="OptionCA" type="select" label="Collinear or Antisense"> 161 <param name="OptionCA" type="select" label="Collinear or anti-sens">
130 <option value="Collinear">Collinear</option> 162 <option value="Collinear">Collinear</option>
131 <option value="Antisense">Antisense</option> 163 <option value="AntiSens">AntiSens</option>
132 <option value="NONE" selected="true">NONE</option> 164 <option value="NONE" selected="true">NONE</option>
133 </param> 165 </param>
134 <when value="Collinear"> 166 <when value="Collinear">
135 </when> 167 </when>
136 <when value="Antisense"> 168 <when value="AntiSens">
137 </when> 169 </when>
138 <when value="NONE"> 170 <when value="NONE">
139 </when> 171 </when>
140 </conditional> 172 </conditional>
141 <param name="InvertMatch" type="boolean" truevalue="-x" falsevalue="" checked="false" label="Invert match"/> 173 <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"/>
142 <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 default."/> 174 <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."/>
143 </inputs> 175 </inputs>
144 176
145 <outputs> 177 <outputs>
146 <data name="outputFileGff" format="gff3"/> 178 <data name="outputFileGff" format="gff3"/>
147 </outputs> 179 </outputs>
180
181 <help>
182 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).
183
184 It is vital to understand that it will output the elements of the first file which overlap with the elements of the second one.
185
186 Various modifiers are also available:
187
188 -Invert selection (report those which do not overlap).
189
190 -Restrict to colinear / anti-sense overlapping data.
191
192 -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.
193
194 -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.
195
196 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.
197
198 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.
199 </help>
148 </tool> 200 </tool>