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

Uploaded
author m-zytnicki
date Tue, 30 Apr 2013 15:02:29 -0400
parents
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
36
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
1 <tool id="CompareOverlappingSmallQuery" name="compare Overlapping Small Query">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
2 <description>Provide the queries that overlap with a reference, when the query data set is small.</description>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
3 <command interpreter="python">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
4 ../Java/Python/CompareOverlappingSmallQuery.py -i $formatType.inputFileName1
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
5 #if $formatType.FormatInputFileName1 == 'bed':
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
6 -f bed
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
7 #elif $formatType.FormatInputFileName1 == 'gff':
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
8 -f gff
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
9 #elif $formatType.FormatInputFileName1 == 'gff2':
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
10 -f gff2
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
11 #elif $formatType.FormatInputFileName1 == 'gff3':
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
12 -f gff3
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
13 #elif $formatType.FormatInputFileName1 == 'sam':
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
14 -f sam
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
15 #elif $formatType.FormatInputFileName1 == 'gtf':
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
16 -f gtf
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
17 #end if
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
18 -j $formatType2.inputFileName2
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
19 #if $formatType2.FormatInputFileName2 == 'bed':
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
20 -g bed
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
21 #elif $formatType2.FormatInputFileName2 == 'gff':
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
22 -g gff
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
23 #elif $formatType2.FormatInputFileName2 == 'gff2':
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
24 -g gff2
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
25 #elif $formatType2.FormatInputFileName2 == 'gff3':
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
26 -g gff3
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
27 #elif $formatType2.FormatInputFileName2 == 'sam':
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
28 -g sam
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
29 #elif $formatType2.FormatInputFileName2 == 'gtf':
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
30 -g gtf
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
31 #end if
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
32 -o $outputFileGff
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
33 #if $OptionDistance.Dist == 'Yes':
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
34 -d $OptionDistance.distance
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
35 #end if
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
36 #if $OptionMinOverlap.present == 'Yes':
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
37 -m $OptionMinOverlap.minOverlap
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
38 #end if
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
39 #if $OptionPcOverlapQuery.present == 'Yes':
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
40 -p $OptionPcOverlapQuery.minOverlap
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
41 #end if
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
42 #if $OptionPcOverlapRef.present == 'Yes':
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
43 -P $OptionPcOverlapRef.minOverlap
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
44 #end if
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
45 #if $OptionCollinearOrAntiSens.OptionCA == 'Collinear':
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
46 -c
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
47 #elif $OptionCollinearOrAntiSens.OptionCA == 'AntiSens':
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
48 -a
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
49 #end if
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
50 $InvertMatch
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
51 $NotOverlapping
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
52 $OptionInclusionQuery
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
53 $OptionInclusionRef
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
54 </command>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
55
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
56 <inputs>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
57 <conditional name="formatType">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
58 <param name="FormatInputFileName1" type="select" label="Input Query File Format">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
59 <option value="bed">bed</option>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
60 <option value="gff">gff</option>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
61 <option value="gff2">gff2</option>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
62 <option value="gff3">gff3</option>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
63 <option value="sam">sam</option>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
64 <option value="gtf">gtf</option>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
65 </param>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
66 <when value="bed">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
67 <param name="inputFileName1" format="bed" type="data" label="Input File 1"/>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
68 </when>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
69 <when value="gff">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
70 <param name="inputFileName1" format="gff" type="data" label="Input File 1"/>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
71 </when>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
72 <when value="gff2">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
73 <param name="inputFileName1" format="gff2" type="data" label="Input File 1"/>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
74 </when>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
75 <when value="gff3">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
76 <param name="inputFileName1" format="gff3" type="data" label="Input File 1"/>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
77 </when>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
78 <when value="sam">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
79 <param name="inputFileName1" format="sam" type="data" label="Input File 1"/>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
80 </when>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
81 <when value="gtf">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
82 <param name="inputFileName1" format="gtf" type="data" label="Input File 1"/>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
83 </when>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
84 </conditional>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
85
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
86 <conditional name="formatType2">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
87 <param name="FormatInputFileName2" type="select" label="Input Reference File Format">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
88 <option value="bed">bed</option>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
89 <option value="gff">gff</option>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
90 <option value="gff2">gff2</option>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
91 <option value="gff3">gff3</option>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
92 <option value="sam">sam</option>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
93 <option value="gtf">gtf</option>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
94 </param>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
95 <when value="bed">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
96 <param name="inputFileName2" format="bed" type="data" label="Input File 2"/>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
97 </when>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
98 <when value="gff">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
99 <param name="inputFileName2" format="gff" type="data" label="Input File 2"/>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
100 </when>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
101 <when value="gff2">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
102 <param name="inputFileName2" format="gff2" type="data" label="Input File 2"/>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
103 </when>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
104 <when value="gff3">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
105 <param name="inputFileName2" format="gff3" type="data" label="Input File 2"/>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
106 </when>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
107 <when value="sam">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
108 <param name="inputFileName2" format="sam" type="data" label="Input File 2"/>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
109 </when>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
110 <when value="gtf">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
111 <param name="inputFileName2" format="gtf" type="data" label="Input File 2"/>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
112 </when>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
113 </conditional>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
114 <conditional name="OptionDistance">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
115 <param name="Dist" type="select" label="Maximum Distance between two reads">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
116 <option value="Yes">Yes</option>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
117 <option value="No" selected="true">No</option>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
118 </param>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
119 <when value="Yes">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
120 <param name="distance" type="integer" value="0"/>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
121 </when>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
122 <when value="No">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
123 </when>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
124 </conditional>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
125 <conditional name="OptionMinOverlap">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
126 <param name="present" type="select" label="Minimum number of common nucleotides to declare an overlap">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
127 <option value="Yes">Yes</option>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
128 <option value="No" selected="true">No</option>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
129 </param>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
130 <when value="Yes">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
131 <param name="minOverlap" type="integer" value="0"/>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
132 </when>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
133 <when value="No">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
134 </when>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
135 </conditional>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
136 <conditional name="OptionPcOverlapQuery">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
137 <param name="present" type="select" label="N% of the query must overlap">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
138 <option value="Yes">Yes</option>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
139 <option value="No" selected="true">No</option>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
140 </param>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
141 <when value="Yes">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
142 <param name="minOverlap" type="integer" value="0"/>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
143 </when>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
144 <when value="No">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
145 </when>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
146 </conditional>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
147 <conditional name="OptionPcOverlapRef">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
148 <param name="present" type="select" label="N% of the reference must overlap">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
149 <option value="Yes">Yes</option>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
150 <option value="No" selected="true">No</option>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
151 </param>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
152 <when value="Yes">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
153 <param name="minOverlap" type="integer" value="0"/>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
154 </when>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
155 <when value="No">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
156 </when>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
157 </conditional>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
158 <param name="OptionInclusionQuery" type="boolean" truevalue="-k" falsevalue="" checked="false" label="The query must be nested in a query"/>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
159 <param name="OptionInclusionRef" type="boolean" truevalue="-K" falsevalue="" checked="false" label="The reference must be nested in a query"/>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
160 <conditional name="OptionCollinearOrAntiSens">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
161 <param name="OptionCA" type="select" label="Collinear or anti-sens">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
162 <option value="Collinear">Collinear</option>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
163 <option value="AntiSens">AntiSens</option>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
164 <option value="NONE" selected="true">NONE</option>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
165 </param>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
166 <when value="Collinear">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
167 </when>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
168 <when value="AntiSens">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
169 </when>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
170 <when value="NONE">
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
171 </when>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
172 </conditional>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
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"/>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
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."/>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
175 </inputs>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
176
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
177 <outputs>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
178 <data name="outputFileGff" format="gff3"/>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
179 </outputs>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
180
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
181 <help>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
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).
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
183
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
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.
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
185
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
186 Various modifiers are also available:
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
187
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
188 -Invert selection (report those which do not overlap).
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
189
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
190 -Restrict to colinear / anti-sense overlapping data.
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
191
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
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.
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
193
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
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.
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
195
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
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.
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
197
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
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.
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
199 </help>
44d5973c188c Uploaded
m-zytnicki
parents:
diff changeset
200 </tool>