Mercurial > repos > s-kaufmann > synteny_mapper

comparison synteny_mapper-005d0bab5d01/synteny-mapper.xml @ 0:b06710963b32 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author s-kaufmann
date Mon, 10 Feb 2014 09:00:25 -0500
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:b06710963b32
1 <tool id="SyntenyMapper1" name="SyntenyMapper" version="1.0.0">
2 <description>Maps maximum stretches of orthologous genes with conserved order within large synteny regions</description>
3
4 <requirements>
5 <requirement type="set_environment">JAR_PATH</requirement>
6 </requirements>
7
8 <command>
9 #if $source.source_select == "ensembl" #java -cp \$JAR_PATH/syntenyMapper.jar de/tum/wzw/mapping/SyntenyMapper $source.ensembl_version $inputSyntenyRegions $inputHomologousGenes $out_file1 $out_file2 $source.species.species1 $source.species.species2 $source.filter
10 #else #java -cp \$JAR_PATH/syntenyMapper.jar de/tum/wzw/mapping/SyntenyMapper $inputSyntenyRegions $inputHomologousGenes $out_file1 $out_file2 $source.species1 $source.species2
11 #end if
12
13 </command>
14
15 <inputs>
16
17
18
19 <conditional name="source">
20 <param name="source_select" type="select" label="Data source">
21 <option value="ensembl">ENSEMBL download</option>
22 <option value="upload">Own data upload</option>
23 </param>
24 <when value="ensembl">
25 <param name="ensembl_version" type="integer" value="73" label="ENSEMBL Compara version"/>
26 <conditional name="species">
27 <param name="species1" type="select" label="Species1">
28 <option value="felis_catus">Felis catus</option>
29 <option value="rattus_norvegicus">Rattus norvegicus</option>
30 <option value="meleagris_gallopavo">Meleagris gallopavo</option>
31 <option value="monodelphis_domestica">Monodelphis domestica</option>
32 <option value="mus_musculus">Mus musculus</option>
33 <option value="canis_familiaris">Canis familiaris</option>
34 <option value="oryctolagus_cuniculus">Oryctolagus cuniculus</option>
35 <option value="equus_caballus">Equus caballus</option>
36 <option value="gallus_gallus">Gallus gallus</option>
37 <option value="macaca_mulatta">Macaca mulatta</option>
38 <option value="pongo_abelii">Pongo abelii</option>
39 <option value="sus_scrofa">Sus scrofa</option>
40 <option value="gorilla_gorilla">Gorilla gorilla</option>
41 <option value="callithrix_jacchus">Callithrix jacchus</option>
42 <option value="ornithorhynchus_anatinus">Ornithorhynchus anatinus</option>
43 <option value="homo_sapiens">Homo sapiens</option>
44 <option value="anolis_carolinensis">Anolis carolinensis</option>
45 <option value="pan_troglodytes">Pan troglodytes</option>
46 <option value="bos_taurus">Bos taurus</option>
47 <filter type="sort_by"/>
48 </param>
49 <when value="felis_catus">
50 <param name="species2" type="select" label="Species2">
51 <option value="homo_sapiens">Homo sapiens</option>
52 <filter type="sort_by"/>
53 </param>
54 </when>
55 <when value="rattus_norvegicus">
56 <param name="species2" type="select" label="Species2">
57 <option value="mus_musculus">Mus musculus</option>
58 <option value="homo_sapiens">Homo sapiens</option>
59 <filter type="sort_by"/>
60 </param>
61 </when>
62 <when value="meleagris_gallopavo">
63 <param name="species2" type="select" label="Species2">
64 <option value="gallus_gallus">Gallus gallus</option>
65 <filter type="sort_by"/>
66 </param>
67 </when>
68 <when value="monodelphis_domestica">
69 <param name="species2" type="select" label="Species2">
70 <option value="homo_sapiens">Homo sapiens</option>
71 <filter type="sort_by"/>
72 </param>
73 </when>
74 <when value="mus_musculus">
75 <param name="species2" type="select" label="Species2">
76 <option value="sus_scrofa">Sus scrofa</option>
77 <option value="rattus_norvegicus">Rattus norvegicus</option>
78 <option value="ornithorhynchus_anatinus">Ornithorhynchus anatinus</option>
79 <option value="homo_sapiens">Homo sapiens</option>
80 <option value="canis_familiaris">Canis familiaris</option>
81 <option value="gallus_gallus">Gallus gallus</option>
82 <option value="bos_taurus">Bos taurus</option>
83 <filter type="sort_by"/>
84 </param>
85 </when>
86 <when value="canis_familiaris">
87 <param name="species2" type="select" label="Species2">
88 <option value="mus_musculus">Mus musculus</option>
89 <option value="homo_sapiens">Homo sapiens</option>
90 <option value="equus_caballus">Equus caballus</option>
91 <filter type="sort_by"/>
92 </param>
93 </when>
94 <when value="oryctolagus_cuniculus">
95 <param name="species2" type="select" label="Species2">
96 <option value="homo_sapiens">Homo sapiens</option>
97 <filter type="sort_by"/>
98 </param>
99 </when>
100 <when value="equus_caballus">
101 <param name="species2" type="select" label="Species2">
102 <option value="canis_familiaris">Canis familiaris</option>
103 <option value="homo_sapiens">Homo sapiens</option>
104 <filter type="sort_by"/>
105 </param>
106 </when>
107 <when value="gallus_gallus">
108 <param name="species2" type="select" label="Species2">
109 <option value="meleagris_gallopavo">Meleagris gallopavo</option>
110 <option value="mus_musculus">Mus musculus</option>
111 <option value="anolis_carolinensis">Anolis carolinensis</option>
112 <option value="homo_sapiens">Homo sapiens</option>
113 <filter type="sort_by"/>
114 </param>
115 </when>
116 <when value="macaca_mulatta">
117 <param name="species2" type="select" label="Species2">
118 <option value="homo_sapiens">Homo sapiens</option>
119 <filter type="sort_by"/>
120 </param>
121 </when>
122 <when value="pongo_abelii">
123 <param name="species2" type="select" label="Species2">
124 <option value="homo_sapiens">Homo sapiens</option>
125 <filter type="sort_by"/>
126 </param>
127 </when>
128 <when value="sus_scrofa">
129 <param name="species2" type="select" label="Species2">
130 <option value="mus_musculus">Mus musculus</option>
131 <option value="homo_sapiens">Homo sapiens</option>
132 <option value="bos_taurus">Bos taurus</option>
133 <filter type="sort_by"/>
134 </param>
135 </when>
136 <when value="gorilla_gorilla">
137 <param name="species2" type="select" label="Species2">
138 <option value="homo_sapiens">Homo sapiens</option>
139 <filter type="sort_by"/>
140 </param>
141 </when>
142 <when value="callithrix_jacchus">
143 <param name="species2" type="select" label="Species2">
144 <option value="homo_sapiens">Homo sapiens</option>
145 <filter type="sort_by"/>
146 </param>
147 </when>
148 <when value="ornithorhynchus_anatinus">
149 <param name="species2" type="select" label="Species2">
150 <option value="mus_musculus">Mus musculus</option>
151 <option value="homo_sapiens">Homo sapiens</option>
152 <filter type="sort_by"/>
153 </param>
154 </when>
155 <when value="homo_sapiens">
156 <param name="species2" type="select" label="Species2">
157 <option value="felis_catus">Felis catus</option>
158 <option value="rattus_norvegicus">Rattus norvegicus</option>
159 <option value="monodelphis_domestica">Monodelphis domestica</option>
160 <option value="mus_musculus">Mus musculus</option>
161 <option value="canis_familiaris">Canis familiaris</option>
162 <option value="oryctolagus_cuniculus">Oryctolagus cuniculus</option>
163 <option value="equus_caballus">Equus caballus</option>
164 <option value="gallus_gallus">Gallus gallus</option>
165 <option value="macaca_mulatta">Macaca mulatta</option>
166 <option value="pongo_abelii">Pongo abelii</option>
167 <option value="sus_scrofa">Sus scrofa</option>
168 <option value="gorilla_gorilla">Gorilla gorilla</option>
169 <option value="callithrix_jacchus">Callithrix jacchus</option>
170 <option value="ornithorhynchus_anatinus">Ornithorhynchus anatinus</option>
171 <option value="pan_troglodytes">Pan troglodytes</option>
172 <option value="bos_taurus">Bos taurus</option>
173 <filter type="sort_by"/>
174 </param>
175 </when>
176 <when value="anolis_carolinensis">
177 <param name="species2" type="select" label="Species2">
178 <option value="gallus_gallus">Gallus gallus</option>
179 <filter type="sort_by"/>
180 </param>
181 </when>
182 <when value="pan_troglodytes">
183 <param name="species2" type="select" label="Species2">
184 <option value="homo_sapiens">Homo sapiens</option>
185 <filter type="sort_by"/>
186 </param>
187 </when>
188 <when value="bos_taurus">
189 <param name="species2" type="select" label="Species2">
190 <option value="sus_scrofa">Sus scrofa</option>
191 <option value="mus_musculus">Mus musculus</option>
192 <option value="homo_sapiens">Homo sapiens</option>
193 <filter type="sort_by"/>
194 </param>
195 </when>
196 </conditional>
197 <param name="filter" type="select" label="Gene filter">
198 <option value="false">Use all genes</option>
199 <option value="true">Use only protein-coding genes</option>
200 </param>
201 </when>
202 <when value="upload">
203 <param name="species1" type="text" size="40" label="Species1 (latin name with underline)">
204 <validator type="expression" message="Please replace any white spaces with underlines">value.find(' ')==-1</validator>
205 </param>
206 <param name="species2" type="text" size="40" label="Species2 (latin name with underline)">
207 <validator type="expression" message="Please replace any white spaces with underlines">value.find(' ')==-1</validator>
208 </param>
209 <param format="tabular" name="inputSyntenyRegions" type="data" label="Synteny Regions (e.g. from ENSEMBL)" help="Dataset missing? See TIP below."/>
210 <param format="tabular" name="inputHomologousGenes" type="data" label="Orthologous Genes (e.g. from ENSEMBL)" help="Dataset missing? See TIP below."/>
211 </when>
212 </conditional>
213
214 </inputs>
215 <outputs>
216 <data format="tabular" name="inputSyntenyRegions" label="ENSEMBL synteny regions">
217 <filter>source['source_select'] == "ensembl"</filter>
218 </data>
219 <data format="tabular" name="inputHomologousGenes" label="ENSEMBL orthologous genes">
220 <filter>source['source_select'] == "ensembl"</filter>
221 </data>
222
223 <data format="tabular" name="out_file1" label="Gene mapping"/>
224 <data format="tabular" name="out_file2" label="Refined Synteny regions"/>
225 </outputs>
226 <tests>
227 <test>
228 <param name="inputSyntenyRegions" value="hom_sapi-mus_musc-synteny-v70"/>
229 <param name="inputHomologousGenes" value="hom_sapi-mus_musc-homologs-v70"/>
230 <param name="species1" value="homo_sapiens"/>
231 <param name="species2" value="mus_musculus"/>
232 <param name="filter" value="true"/>
233 <!--<param name="header_lines" value="0"/>-->
234 <output name="out_file1" file="mapping_test1.bed"/>
235 <output name="out_file2" file="regions_test1.bed"/>
236 </test>
237 </tests>
238
239 <help>
240
241 .. class:: warningmark
242
243 If you are not downloading data directly from ENSEMBL, please make sure to bring your data into the correct format (see below).
244
245 .. class:: infomark
246
247 **TIP:** If your data is not TAB delimited, use *Text Manipulation-&gt;Convert*
248
249 .. class:: infomark
250
251 Species names should be given as latin names (e.g. Homo sapiens).
252
253 **TIP:** If you are interested only in the 1-to-1 ortholog mapping, use *Text Manipulation-&gt;Cut* on columns c3,c7 of the output Gene/IR mapping.
254
255 ----
256
257 **What it does**
258
259 SyntenyMapper uses two species' predefined macro-rearrangement blocks of common origin (e.g. synteny regions from ENSEMBL) and orthology assignments, both alignment-based, and combines them to create refined synteny regions with microrearrangement blocks and a 1-to-1 ortholog mapping.
260
261 It finds the longest blocks of conserved gene order within each synteny block and eliminates all orthology mappings with different gene neighbourhood. As a result, SyntenyMapper produces a list of segments with identical order of genes in both species, caused by micro-rearrangements. For visualization of this mapping, use SyntenyMapperVisualization. To utilize the mapping for feature track comparison between two species, use TrackMapper.
262
263 -----
264
265 **Syntax**
266
267 The SyntenyMapper allows you to identify long blocks of genes with conserved gene order in two organisms.
268
269 The mapping is based on previously determined long synteny regions and orthology pairs of genes.
270
271 First two comment lines (marked by a leading #) in the synteny file should name #Species1: and #Species2:, respectively. IDs should consist of five digits.
272 The synteny file should have the format (tab-separated):
273
274
275 +-----+-------------------+---------------+-------------+--------------------+---------------+-------------+-------------+
276 |#ID |Chromosome_species1|Start_species1 |End_species1 |Chromosome_species2 |Start_species2 |End_species2 |Dir_species2 |
277 +-----+-------------------+---------------+-------------+--------------------+---------------+-------------+-------------+
278
279
280 The orthologous genes file should have the format (tab-separated):
281
282
283 +---------+------------------+------------------------+-----------+---------+---------+----------+----------+-----------------+
284 |#ID |ENSEMBL_ID |Name |Chromosome |Start |End |Direction | Identity |Species |
285 +---------+------------------+------------------------+-----------+---------+---------+----------+----------+-----------------+
286
287
288 There should be two (or more) entries for each ID, describing pairs of genes that are orthologs.
289
290 -----
291
292 **Example**
293
294 These are sample lines from two example input files. If you are not downloading data directly from ENSEMBL (or reusing downloaded data), please make sure that it adheres to the above defined format.
295
296 The synteny file contains coordinates of large (e.g. whole-genome alignment based) synteny regions in both organisms and specifies the species names.
297
298 *Synteny file:*
299
300 +----------------------------------------------------------------------------------------------+
301 |#Species1: homo_sapiens |
302 +----------------------------------------------------------------------------------------------+
303 |#Species2: mus_musculus |
304 +-----+-----------------+------------+----------+-----------------+------------+----------+----+
305 |#ID |Chromosome_human |Start_human |End_human |Chromosome_mouse |Start_mouse |End_mouse |Dir |
306 +-----+-----------------+------------+----------+-----------------+------------+----------+----+
307 |44723|chr6 |155053083 |160101646 |chr17 |3113738 |7931992 |-1 |
308 +-----+-----------------+------------+----------+-----------------+------------+----------+----+
309
310
311 The orthology file contains coordinates of genes of two species, coupled together by the same identifier to orthology pairs. Chromosomes can be named with "chr" prefix or without in both files.
312
313 *Orthology file:*
314
315 +---------+------------------+------------------------+-----------+---------+---------+----------+----------+-----------------+
316 |#ID |ENSEMBL_ID |Name |Chromosome |Start |End |Direction | Identity |Species |
317 +---------+------------------+------------------------+-----------+---------+---------+----------+----------+-----------------+
318 |33818986 |ENSRNOG00000050189|olfactory receptor Olr89|1 |174585043|174585993|1 |92.0 |rattus_norvegicus|
319 +---------+------------------+------------------------+-----------+---------+---------+----------+----------+-----------------+
320 |33818986 |ENSMUSG00000073952|null |7 |103320401|103321360|1 |93.0 |mus_musculus |
321 +---------+------------------+------------------------+-----------+---------+---------+----------+----------+-----------------+
322
323 </help>
324 </tool>