Mercurial > repos > vimalkumarvelayudhan > viga

comparison wrapper.xml @ 0:231e4c669675 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Initial commit - v0.10.3 git commit deeded0
author vimalkumarvelayudhan
date Tue, 27 Feb 2018 14:16:54 -0500
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:231e4c669675
1 <tool id="viga" name="viga" version="0.10.3">
2 <description>de novo VIral Genome Annotator</description>
3 <requirements>
4 <container type="docker">vimalkvn/viga</container>
5 </requirements>
6 <stdio>
7 <exit_code range="1:" />
8 </stdio>
9 <command><![CDATA[
10 python $__tool_directory__/VIGA.py
11 --input $input
12 --rfamdb $rfamdb.fields.path
13 --modifiers $modifiers
14 --threads \${GALAXY_SLOTS:-5}
15 --typedata $typedata_select
16 --gcode $gcode_select
17 --out "default"
18 --minrepeat $minrepeat
19 --maxrepeat $maxrepeat
20 --minspacer $minspacer
21 --maxspacer $maxspacer
22
23 #if $readlength
24 --readlength $readlength
25 #end if
26 #if $windowsize
27 --windowsize $windowsize
28 #end if
29 #if $slidingsize
30 --slidingsize $slidingsize
31 #end if
32 #if $locus
33 --locus $locus
34 #end if
35 #if $gffprint
36 --gff
37 #end if
38 #if str($blastevalue)
39 --blastevalue $blastevalue
40 #end if
41 #if str($mincontigsize)
42 --mincontigsize $mincontigsize
43 #end if
44 #if str($idthr)
45 --idthr $idthr
46 #end if
47 #if str($coverthr)
48 --coverthr $coverthr
49 #end if
50 #if str($diffid)
51 --diffid $diffid
52 #end if
53 #if $blastexh
54 --blastexh
55 #end if
56 #if str($homologysearch.use_diamond) == "yes":
57 --noblast
58 --diamonddb $homologysearch.diamonddb.fields.path
59 #else
60 --blastdb $homologysearch.blastdb.fields.path
61 #end if
62 #if str($hmmsearch.use_phmmer) == "yes":
63 --hmmdb $hmmsearch.hmmdb.fields.path
64 --hmmerevalue $hmmsearch.hmmerevalue
65 #else
66 --nohmmer
67 #end if
68 ]]></command>
69 <inputs>
70 <param name="input" type="data" format="fasta" label="(Viral) contigs to annotate" help="Input file as a FASTA file. It can contain multiple sequences (e.g. metagenomic contigs)" />
71 <param name="rfamdb" type="select" label="RFAM database used for ribosomal RNA prediction">
72 <options from_data_table="viga_rfamdb">
73 <filter type="sort_by" column="2"/>
74 <validator type="no_options" message="No indexes are available for the selected input dataset"/>
75 </options>
76 </param>
77 <param name="modifiers" type="data" format="txt" label="Metadata of the contigs" help="Modifiers per every FASTA header according to SeqIn (https://www.ncbi.nlm.nih.gov/Sequin/modifiers.html)" />
78 <param name="typedata_select" type="select" label="GenBank division (--typedata)">
79 <option value="CON" selected="true">Contig</option>
80 <option value="PHG">Phages</option>
81 <option value="VRL">Eukaryotic/Archaea virus</option>
82 <option value="BCT">Prokaryotic chromosome</option>
83 </param>
84 <param name="gcode_select" type="select" label="Number of GenBank translation table (--gcode)">
85 <option value="1">Standard genetic code [Eukaryotic]</option>
86 <option value="2">Vertebrate mitochondrial code</option>
87 <option value="3">Yeast mitochondrial code</option>
88 <option value="4">Mycoplasma/Spiroplasma and Protozoan/mold/coelenterate mitochondrial code</option>
89 <option value="5">Invertebrate mitochondrial code</option>
90 <option value="6">Ciliate, dasycladacean and hexamita nuclear code</option>
91 <option value="9">Echinoderm/flatworm mitochondrial code</option>
92 <option value="10">Euplotid nuclear code</option>
93 <option value="11" selected="true">Bacteria/Archaea/Phages/Plant plastid</option>
94 <option value="12">Alternative yeast nuclear code</option>
95 <option value="13">Ascidian mitochondrial code</option>
96 <option value="14">Alternative flatworm mitochondrial code</option>
97 <option value="16">Chlorophycean mitochondrial code</option>
98 <option value="21">Trematode mitochondrial code</option>
99 <option value="22">Scedenesmus obliquus mitochondrial code</option>
100 <option value="23">Thraustochytrium mitochondrial code</option>
101 <option value="24">Pterobranquia mitochondrial code</option>
102 <option value="25">Gracilibacteria and Candidate division SR1</option>
103 <option value="26">Pachysolen tannophilus nuclear code</option>
104 <option value="27">Karyorelict nuclear code</option>
105 <option value="28">Condylostoma nuclear code</option>
106 <option value="29">Mesodinium nuclear code</option>
107 <option value="30">Peritrich nuclear code</option>
108 <option value="31">Blastocrithidia nuclear code</option>
109 </param>
110 <param name="readlength" type="integer" value="101" min="1" optional="true" label="Read length (--readlength)" help="Read length for the circularity prediction"/>
111 <param name="windowsize" type="integer" value="100" min="2" optional="true" label="Window size (--windowsize)" help="Window size used to determine the origin of replication in circular contigs according to the cumulative GC skew"/>
112 <param name="slidingsize" type="integer" value="10" min="1" optional="true" label="sliding window size (--slidingsize)" help="Sliding window size for the origin of replication prediction"/>
113 <param name="locus" type="text" value="LOC" optional="true" label="Locus tag prefix (--locustag)" help="Name of the sequences. If the input is a multifasta file, please put a general name"/>
114 <param name="gffprint" type="boolean" checked="false" optional="true" label="Print the output also as GFF3 file" help="Printing the output as GFF3 file (Default: FALSE)" />
115 <param name="blastevalue" type="float" value="1e-5" min="0" optional="true" label="Blast e-value threshold" />
116
117 <conditional name="hmmsearch">
118 <param name="use_phmmer" type="select" label="Use PHMMER to predict protein function using HMM">
119 <option value="yes" selected="True">Yes (slow, more accurate)</option>
120 <option value="no">No (fast, less accurate)</option>
121 </param>
122 <when value="yes">
123 <param name="hmmdb" type="select" label="PHMMER database to use for protein function prediction">
124 <options from_data_table="viga_hmmdb">
125 <filter type="sort_by" column="2"/>
126 <validator type="no_options" message="No indexes are available for the selected input dataset"/>
127 </options>
128 </param>
129 <param name="hmmerevalue" type="float" value="0.001" label="PHMMER e-value threshold"/>
130 </when>
131 </conditional>
132 <conditional name="homologysearch">
133 <param name="use_diamond" type="select" label="Use DIAMOND instead of BLAST to predict protein function">
134 <option value="yes" selected="True">Yes (fast, less accurate)</option>
135 <option value="no">No (slow, more accurate)</option>
136 </param>
137 <when value="yes">
138 <param name="diamonddb" type="select" label="DIAMOND database" help="DIAMOND Protein Database that will be used for the protein function prediction">
139 <options from_data_table="viga_diamonddb">
140 <filter type="sort_by" column="2"/>
141 <validator type="no_options" message="No indexes are available for the selected input dataset"/>
142 </options>
143 </param>
144 </when>
145 <when value="no">
146 <param name="blastdb" type="select" label="BLAST Database" help="BLAST Protein Database that will be used for the protein function prediction">
147 <options from_data_table="viga_blastdb">
148 <filter type="sort_by" column="2"/>
149 <validator type="no_options" message="No indexes are available for the selected input dataset"/>
150 </options>
151 </param>
152 </when>
153 </conditional>
154 <param name="mincontigsize" type="integer" value="200" min="1" optional="true" label="Minimum contig length to be considered in the output" />
155 <param name="idthr" type="float" value="50.0" min="0.01" max="100.00" optional="true" label="ID threshold" />
156 <param name="coverthr" type="float" value="50.0" min="0.01" max="100.00" optional="true" label="Coverage threshold" />
157 <param name="diffid" type="float" value="5.00" min="0.01" max="100.00" optional="true" label="Max allowed difference between the ID percentages of BLAST and HHSEARCH" />
158
159 <param name="minrepeat" type="integer" value="16" min="1" optional="true" label="Minimum repeat length for CRISPR detection (--minrepeat)"/>
160 <param name="maxrepeat" type="integer" value="64" min="1" optional="true" label="Maximum repeat length for CRISPR detection (--maxrepeat)"/>
161 <param name="minspacer" type="integer" value="8" min="1" optional="true" label="Minimum spacer length for CRISPR detection (--minspacer)"/>
162 <param name="maxspacer" type="integer" value="64" min="1" optional="true" label="Maximum spacer length for CRISPR detection (--maxspacer)"/>
163
164 <param name="blastexh" type="boolean" checked="false" optional="true" label="Use exhaustive BLAST (--blastexh)" help="Use of exhaustive BLAST to predict the proteins by homology according to Fozo et al. (2010) Nucleic Acids Res (Default=FALSE)" />
165 </inputs>
166 <outputs>
167 <data name="default_csv" format="csv" label="${tool.name} on ${on_string}: csv" from_work_dir="default.csv" />
168 <data name="default_gff" format="gff" label="${tool.name} on ${on_string}: gff" from_work_dir="default.gff">
169 <filter>gffprint</filter>
170 </data>
171 <data name="default_gbk" format="txt" label="${tool.name} on ${on_string}: gbk" from_work_dir="default.gbk" />
172 <data name="default_fasta" format="fasta" label="${tool.name} on ${on_string}: fasta" from_work_dir="default.fasta" />
173 <data name="default_tbl" format="txt" label="${tool.name} on ${on_string}: tbl" from_work_dir="default.tbl" />
174 </outputs>
175 <tests>
176 <test>
177 <param name="input" ftype="fasta" value="rubella.fasta" />
178 <param name="outputs" value="csv,gbk,fasta,tbl" />
179 <output name="default_csv" file="default.csv" />
180 <output name="default_gbk" file="default.gbk" />
181 <output name="default_fasta" file="default.fasta" />
182 <output name="default_tbl" file="default.tbl" />
183 </test>
184 <test>
185 <param name="input" ftype="fasta" value="mu.fasta" />
186 <param name="outputs" value="csv,gbk,fasta,tbl" />
187 <output name="default_csv" file="default.csv" />
188 <output name="default_gbk" file="default.gbk" />
189 <output name="default_fasta" file="default.fasta" />
190 <output name="default_tbl" file="default.tbl" />
191 </test>
192 </tests>
193 <help><![CDATA[
194 **About VIGA**
195
196 VIGA_ is a script written in Python 2.7 that annotates viral
197 genomes automatically (using a de novo algorithm) and predict the
198 function of their proteins using BLAST and HMMER.
199
200 ----
201
202 **About this Galaxy wrapper**
203
204 **Requirements**
205
206 `Docker <https://www.docker.com>`_ should first be installed and working on the
207 server where this Galaxy instance is setup. The user running Galaxy should be
208 part of the **docker** user group.
209
210 #. Download or clone the VIGA_ Github repository (as a submodule)
211 in to the ``tools`` directory.
212
213 **Configuration**
214
215 **Update database paths in .loc files**
216
217 Edit the following files in the **tool-data** directory and add paths to
218 corresponding databases:
219
220 * viga_blastdb.loc
221 * viga_diamonddb.loc
222 * viga_rfamdb.loc
223 * viga_hmmdb.loc
224
225 **Create or update the Galaxy job configuration file**
226
227 If the file **config/job_conf.xml** does not exist, create it by copying the
228 template **config/job_conf.xml.sample_basic** in the Galaxy directory. Then
229 add a Docker destination for viga. Change ``/data/databases`` under
230 ``docker_volumes`` to the location where your databases are stored. Here is
231 an example::
232
233 <?xml version="1.0"?>
234 <!-- A sample job config that explicitly configures job running the way it is configured by default (if there is no explicit config). -->
235 <job_conf>
236 <plugins>
237 <plugin id="local" type="runner" load="galaxy.jobs.runners.local:LocalJobRunner" workers="4"/>
238 </plugins>
239 <handlers>
240 <handler id="main"/>
241 </handlers>
242 <destinations default="local">
243 <destination id="local" runner="local"/>
244 <destination id="docker" runner="local">
245 <param id="docker_enabled">true</param>
246 <param id="docker_sudo">false</param>
247 <param id="docker_auto_rm">true</param>
248 <param id="docker_volumes">$defaults,/data/databases:ro</param>
249 </destination>
250 </destinations>
251 <tools>
252 <tool id="viga" destination="docker"/>
253 </tools>
254 </job_conf>
255
256
257 **Restart Galaxy**. The tool will now be ready to use.
258
259 ----
260
261 **Output files**
262
263 VIGA creates the following output files:
264
265 * tbl - Table file with all protein information.
266 * gbk - GenBank format file with annotations.
267 * fasta - FASTA format file for GenBank submission
268 * csv - Table file for GenBank submission.
269 * gff - GFF3 format file (if option is selected)
270
271 ----
272
273 **License and citation**
274
275 VIGA_ and this Galaxy wrapper - `GPLv3 <https://www.gnu.org/copyleft/gpl.html>`_.
276
277
278 Galaxy
279
280 - Goecks, J, Nekrutenko, A, Taylor, J and The Galaxy Team. "Galaxy: a
281 comprehensive approach for supporting accessible, reproducible, and
282 transparent computational research in the life sciences."
283 Genome Biol. 2010 Aug 25;11(8):R86.
284
285 - Blankenberg D, Von Kuster G, Coraor N, Ananda G, Lazarus R, Mangan M,
286 Nekrutenko A, Taylor J. "Galaxy: a web-based genome analysis tool for
287 experimentalists". Current Protocols in Molecular Biology.
288 2010 Jan; Chapter 19:Unit 19.10.1-21.
289
290 - Giardine B, Riemer C, Hardison RC, Burhans R, Elnitski L, Shah P, Zhang Y,
291 Blankenberg D, Albert I, Taylor J, Miller W, Kent WJ, Nekrutenko A. "Galaxy:
292 a platform for interactive large-scale genome analysis."
293 Genome Research. 2005 Oct; 15(10):1451-5.
294
295 You can use this tool only if you agree to the license terms of: `VIGA`_.
296
297 .. _VIGA: https://github.com/EGTortuero/viga
298
299 ]]></help>
300 <!-- <citations>
301 <citation type="doi">NOT YET</citation>
302 </citations>
303 -->
304 </tool>