comparison SMART/galaxy/CompareOverlappingSmallQuery.xml @ 36:44d5973c188c

Uploaded
author m-zytnicki
date Tue, 30 Apr 2013 15:02:29 -0400
parents
children
comparison
equal deleted inserted replaced
35:d94018ca4ada 36:44d5973c188c
1 <tool id="CompareOverlappingSmallQuery" name="compare Overlapping Small Query">
2 <description>Provide the queries that overlap with a reference, when the query data set is small.</description>
3 <command interpreter="python">
4 ../Java/Python/CompareOverlappingSmallQuery.py -i $formatType.inputFileName1
5 #if $formatType.FormatInputFileName1 == 'bed':
6 -f bed
7 #elif $formatType.FormatInputFileName1 == 'gff':
8 -f gff
9 #elif $formatType.FormatInputFileName1 == 'gff2':
10 -f gff2
11 #elif $formatType.FormatInputFileName1 == 'gff3':
12 -f gff3
13 #elif $formatType.FormatInputFileName1 == 'sam':
14 -f sam
15 #elif $formatType.FormatInputFileName1 == 'gtf':
16 -f gtf
17 #end if
18 -j $formatType2.inputFileName2
19 #if $formatType2.FormatInputFileName2 == 'bed':
20 -g bed
21 #elif $formatType2.FormatInputFileName2 == 'gff':
22 -g gff
23 #elif $formatType2.FormatInputFileName2 == 'gff2':
24 -g gff2
25 #elif $formatType2.FormatInputFileName2 == 'gff3':
26 -g gff3
27 #elif $formatType2.FormatInputFileName2 == 'sam':
28 -g sam
29 #elif $formatType2.FormatInputFileName2 == 'gtf':
30 -g gtf
31 #end if
32 -o $outputFileGff
33 #if $OptionDistance.Dist == 'Yes':
34 -d $OptionDistance.distance
35 #end if
36 #if $OptionMinOverlap.present == 'Yes':
37 -m $OptionMinOverlap.minOverlap
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
45 #if $OptionCollinearOrAntiSens.OptionCA == 'Collinear':
46 -c
47 #elif $OptionCollinearOrAntiSens.OptionCA == 'AntiSens':
48 -a
49 #end if
50 $InvertMatch
51 $NotOverlapping
52 $OptionInclusionQuery
53 $OptionInclusionRef
54 </command>
55
56 <inputs>
57 <conditional name="formatType">
58 <param name="FormatInputFileName1" type="select" label="Input Query File Format">
59 <option value="bed">bed</option>
60 <option value="gff">gff</option>
61 <option value="gff2">gff2</option>
62 <option value="gff3">gff3</option>
63 <option value="sam">sam</option>
64 <option value="gtf">gtf</option>
65 </param>
66 <when value="bed">
67 <param name="inputFileName1" format="bed" type="data" label="Input File 1"/>
68 </when>
69 <when value="gff">
70 <param name="inputFileName1" format="gff" type="data" label="Input File 1"/>
71 </when>
72 <when value="gff2">
73 <param name="inputFileName1" format="gff2" type="data" label="Input File 1"/>
74 </when>
75 <when value="gff3">
76 <param name="inputFileName1" format="gff3" type="data" label="Input File 1"/>
77 </when>
78 <when value="sam">
79 <param name="inputFileName1" format="sam" type="data" label="Input File 1"/>
80 </when>
81 <when value="gtf">
82 <param name="inputFileName1" format="gtf" type="data" label="Input File 1"/>
83 </when>
84 </conditional>
85
86 <conditional name="formatType2">
87 <param name="FormatInputFileName2" type="select" label="Input Reference File Format">
88 <option value="bed">bed</option>
89 <option value="gff">gff</option>
90 <option value="gff2">gff2</option>
91 <option value="gff3">gff3</option>
92 <option value="sam">sam</option>
93 <option value="gtf">gtf</option>
94 </param>
95 <when value="bed">
96 <param name="inputFileName2" format="bed" type="data" label="Input File 2"/>
97 </when>
98 <when value="gff">
99 <param name="inputFileName2" format="gff" type="data" label="Input File 2"/>
100 </when>
101 <when value="gff2">
102 <param name="inputFileName2" format="gff2" type="data" label="Input File 2"/>
103 </when>
104 <when value="gff3">
105 <param name="inputFileName2" format="gff3" type="data" label="Input File 2"/>
106 </when>
107 <when value="sam">
108 <param name="inputFileName2" format="sam" type="data" label="Input File 2"/>
109 </when>
110 <when value="gtf">
111 <param name="inputFileName2" format="gtf" type="data" label="Input File 2"/>
112 </when>
113 </conditional>
114 <conditional name="OptionDistance">
115 <param name="Dist" type="select" label="Maximum Distance between two reads">
116 <option value="Yes">Yes</option>
117 <option value="No" selected="true">No</option>
118 </param>
119 <when value="Yes">
120 <param name="distance" type="integer" value="0"/>
121 </when>
122 <when value="No">
123 </when>
124 </conditional>
125 <conditional name="OptionMinOverlap">
126 <param name="present" type="select" label="Minimum number of common nucleotides to declare an overlap">
127 <option value="Yes">Yes</option>
128 <option value="No" selected="true">No</option>
129 </param>
130 <when value="Yes">
131 <param name="minOverlap" type="integer" value="0"/>
132 </when>
133 <when value="No">
134 </when>
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"/>
160 <conditional name="OptionCollinearOrAntiSens">
161 <param name="OptionCA" type="select" label="Collinear or anti-sens">
162 <option value="Collinear">Collinear</option>
163 <option value="AntiSens">AntiSens</option>
164 <option value="NONE" selected="true">NONE</option>
165 </param>
166 <when value="Collinear">
167 </when>
168 <when value="AntiSens">
169 </when>
170 <when value="NONE">
171 </when>
172 </conditional>
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"/>
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."/>
175 </inputs>
176
177 <outputs>
178 <data name="outputFileGff" format="gff3"/>
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>
200 </tool>