Mercurial > repos > nml > hivtrace

comparison hivtrace.xml @ 0:b81f1de20067 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/phac-nml/galaxy_tools/tree/tools/hivtrace commit e2554dc878f6abf1c02ed9e6e4f4440ed32b02aa
author nml
date Thu, 07 Jul 2016 09:58:57 -0400
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:b81f1de20067
1 <?xml version="1.0"?>
2 <tool id="hivtrace" name="HIV-Trace" version="1.0.0">
3 <description>with options and commands</description>
4 <requirements>
5 <requirement type="package" version="0.1.4">hivtrace</requirement>
6 </requirements>
7 <stdio>
8 <exit_code range="1:" />
9 </stdio>
10 <command><![CDATA[
11 hivtrace
12
13 --input $inputfasta
14 --ambiguities $runtype.ambiguities
15
16 #if $runtype.ambiguities == "RESOLVE":
17 --fraction $runtype.fraction
18 #else
19 --fraction 0.05
20 #end if
21
22 #if $reftype.reference == "Custom":
23 --reference $reftype.customreference
24 #else
25 --reference $reftype.reference
26 #end if
27
28 --threshold $threshold
29
30 --minoverlap $minoverlap
31
32 --curate $curate
33
34 --filter $filter
35
36 #if $reftype.strip_drams:
37 --strip_drams $reftype.strip_drams
38 #end if
39
40 #if $compare:
41 --compare
42 #end if
43
44 #if $inputtype.typefasta == "aligned":
45 --skip-alignment
46 #end if
47
48 --log $logfile
49
50 > $outfile
51 ]]></command>
52 <inputs>
53 <param name="inputfasta" type="data" format="fasta" label="Sequence file"/>
54
55 <conditional name="inputtype">
56 <param name="typefasta" type="select" label="Type of FASTA">
57 <option value="unaligned">Unaligned</option>
58 <option value="aligned">Aligned</option>
59 </param>
60 <when value="unaligned"/>
61 <when value="aligned"/>
62 </conditional>
63
64 <conditional name="reftype">
65 <param name="reference" type="select" label="Reference">
66 <sanitizer sanitize="False" />
67 <option value="HXB2_prrt"> HXB2_prrt</option>
68 <option value="HXB2_pol"> HXB2_pol</option>
69 <option value="NL4-3_prrt"> NL4-3_prrt</option>
70 <option value="HXB2_tat"> HXB2_tat</option>
71 <option value="HXB2_int"> HXB2_int</option>
72 <option value="HXB2_pr"> HXB2_pr</option>
73 <option value="HXB2_vif"> HXB2_vif</option>
74 <option value="HXB2_nef"> HXB2_nef</option>
75 <option value="HXB2_vpu"> HXB2_vpu</option>
76 <option value="HXB2_rev"> HXB2_rev</option>
77 <option value="HXB2_vpr"> HXB2_vpr</option>
78 <option value="HXB2_env"> HXB2_env</option>
79 <option value="HXB2_gag"> HXB2_gag</option>
80 <option value="HXB2_rt"> HXB2_rt</option>
81 <option value="Custom"> Custom</option>
82 <help>The sequence that will be used to align everything else to.</help>
83 </param>
84 <when value="HXB2_pol">
85 <param name="strip_drams" type="select" label="Remove DRAMS">
86 <sanitizer sanitize="False" />
87 <option value="no"> No</option>
88 <option value="lewis"> Mask (with ---) the list of codon sites defined in Lewis et al</option>
89 <option value="wheeler"> Mask (with ---) the list of codon sites defined in Wheeler et al</option>
90 <help>How to handle analyses of proteins (HIV-1 pr and/or RT only) which include drug resistance associated positions</help>
91 </param>
92 </when>
93 <when value="NL4-3_prrt"/>
94 <when value="HXB2_tat"/>
95 <when value="HXB2_int"/>
96 <when value="HXB2_prrt">
97 <param name="strip_drams" type="select" label="Remove DRAMS">
98 <sanitizer sanitize="False" />
99 <option value="no"> No</option>
100 <option value="lewis"> Mask (with ---) the list of codon sites defined in Lewis et al</option>
101 <option value="wheeler"> Mask (with ---) the list of codon sites defined in Wheeler et al</option>
102 <help>How to handle analyses of proteins (HIV-1 pr and/or RT only) which include drug resistance associated positions</help>
103 </param>
104 </when>
105 <when value="HXB2_pr">
106 <param name="strip_drams" type="select" label="Remove DRAMS">
107 <sanitizer sanitize="False" />
108 <option value="no"> No</option>
109 <option value="lewis"> Mask (with ---) the list of codon sites defined in Lewis et al</option>
110 <option value="wheeler"> Mask (with ---) the list of codon sites defined in Wheeler et al</option>
111 <help>How to handle analyses of proteins (HIV-1 pr and/or RT only) which include drug resistance associated positions</help>
112 </param>
113 </when>
114 <when value="HXB2_vif"/>
115 <when value="HXB2_nef"/>
116 <when value="HXB2_vpu"/>
117 <when value="HXB2_rev"/>
118 <when value="HXB2_vpr"/>
119 <when value="HXB2_env"/>
120 <when value="HXB2_gag"/>
121 <when value="HXB2_rt">
122 <param name="strip_drams" type="select" label="Remove DRAMS">
123 <sanitizer sanitize="False" />
124 <option value="no"> No</option>
125 <option value="lewis"> Mask (with ---) the list of codon sites defined in Lewis et al</option>
126 <option value="wheeler"> Mask (with ---) the list of codon sites defined in Wheeler et al</option>
127 <help>How to handle analyses of proteins (HIV-1 pr and/or RT only) which include drug resistance associated positions</help>
128 </param>
129 </when>
130 <when value="Custom">
131 <param name="customreference" type="data" format="fasta" label="Custom reference file"/>
132 </when>
133 </conditional>
134
135 <param name="curate" type="select" label="Contaminant screen">
136 <sanitizer sanitize="False" />
137 <option value="remove"> Remove all sequences sharing a cluster with the reference</option>
138 <option value="report"> Flag all sequences sharing a cluster with the reference</option>
139 <option value="no"> Do nothing</option>
140 <help>What should be done if query sequences belong to the same cluster as the reference. If the reference is a database/lab strain (e.g. HXB2),
141 such sequences are likely mislabeled/contaminated.</help>
142 </param>
143
144 <param name="threshold" type="float" label="Distance threshold" value="0.015"
145 help="Two sequences will be connected with a putative link (subject to filtering), if and only if their pairwise distance does not exceed this threshold.">
146 <validator type="in_range" min="0" max="0.02" message="Must be between 0 and 0.02"/>
147 </param>
148
149 <param name="minoverlap" type="float" label="Minimum overlap" value="500"
150 help="Only sequences who overlap by at least this many non-gap characters will be included in distance calculations. Be sure to adjust this based on the length of the input sequences.">
151 <validator type="in_range" min="50" max="5000" message="Must be between 50 and 5000"/>
152 </param>
153
154 <param name="filter" type="select" label="Filter edges">
155 <sanitizer sanitize="False" />
156 <option value="remove"> Remove spurious edges from the inferred network</option>
157 <option value="report"> Annotate spurious edges in the inferred network</option>
158 <option value="no"> Do not perform filtering</option>
159
160 <help>Use a phylogenetic test of conditional independence on each triangle in the network to remove spurious <i>transitive</i> connections which make A→B→C chains look like A-B-C triangles.</help>
161 </param>
162
163 <conditional name="runtype">
164 <param name="ambiguities" type="select" label="Handle Ambiguities">
165 <sanitizer sanitize="False" />
166 <option value="RESOLVE"> Resolve</option>
167 <option value="AVERAGE"> Average</option>
168 <option value="SKIP"> Skip</option>
169 <option value="GAPMM"> GAPMM</option>
170 <help>Procedure for handling IUPAC ambiguities</help>
171 </param>
172 <when value="AVERAGE"/>
173 <when value="SKIP"/>
174 <when value="GAPMM"/>
175 <when value="RESOLVE">
176 <param name="fraction" type="float" label="Ambiguity Fraction" value="0.05"
177 help="Any sequence with no more than the selected proportion [0 - 1] will have its ambiguities resolved (if possible), and ambiguities in
178 sequences with higher fractions of them will be averaged. This mitigates spurious linkages due to highly ambiguous sequences.">
179 <validator type="in_range" min="0" max="1" message="Must be between 0 and 1"/>
180 </param>
181 </when>
182 </conditional>
183
184 <param name="compare" type="boolean" truevalue="--compare" falsevalue="" checked="False" label="Compare to Los Alamos National Laboratory HIV database sequences"
185 help="Compare uploaded sequences to the all of the public sequences, retrieved periodically from (hiv.lanl.gov). Comparing to a public database
186 is only available for some of the reference sequences"/>
187 </inputs>
188 <outputs>
189 <data name="outfile" format="txt" label="${tool.name} on ${on_string}: Results"/>
190 <data name="logfile" format="txt" label="${tool.name} on ${on_string}: Log"/>
191 </outputs>
192
193 <tests>
194 <test>
195 <param/>
196 <output/>
197 </test>
198 </tests>
199
200 <help><![CDATA[
201 Options Summary for HIV-Trace
202
203 **Sequence file**
204
205 A FASTA file, with nucleotide sequences to be analyzed. Each sequence will be aligned to the chosen reference sequence prior to network inference. Sequence names may include munged attributes, e.g. ISOLATE_XYZ|2005|SAN DIEGO|MSM
206
207 -----
208
209 **Type of FASTA**
210
211 Select whether your FASTA file is aligned or unaligned
212
213 -----
214
215 **Reference**
216
217 The sequence that will be used to align everything else to. It is assumed that the input sequences are in fact homologous to the reference and do not have too much indel variation
218
219 Please reference the landmarks of the HIV-1 genome if the presets seem foreign to you.
220
221 -----
222
223 **Remove DRAMS**
224
225 .. class:: infomark
226
227 **TIP:** This option is only available for four reference types: HXB2_pol, HXB2_prrt, HXB2_pr, and HXB2_rt
228
229 *Lewis* - mask (with ---) the list of codon sites defined in Lewis et al: http://journals.plos.org/plosmedicine/article?id=10.1371/journal.pmed.0050050
230
231 *Wheeler* - mask (with ---) the list of codon sites defined in Wheeler et al: http://www.ncbi.nlm.nih.gov/pubmed/20395786
232
233 -----
234
235 **Contaminant screen**
236
237 Screen for contaminants by marking or removing sequences that cluster with any of the contaminant IDs
238
239 *Remove* - remove spurious edges from the inferred network
240
241 *Report* - flag all sequences sharing a cluster with the reference
242
243 *None* - do nothing
244
245 -----
246
247 **Distance threshold**
248
249 Two sequences will be connected with a putative link (subject to filtering, see below), if and only if their pairwise distance does not exceed this threshold
250
251 -----
252
253 **Minimum overlap**
254
255 Only sequences who overlap by at least this many non-gap characters will be included in distance calculations. Be sure to adjust this based on the length of the input sequences. You should aim to have at least 2/(distance threshold) aligned characters
256
257 -----
258
259 **Filter edges**
260
261 Use a phylogenetic test of conditional independence on each triangle in the network to remove spurious transitive connections which make A->B->C chains look like A-B-C triangles
262
263 -----
264
265 **Handle ambiguities**
266
267 Handle ambiguious nucleotides using one of the following specified strategies.
268
269 *Resolve* - count any resolutions that match as a perfect match
270
271 *Average* - average all possible resolutions
272
273 *Skip* - skip all positions with ambiguities
274
275 *GAPMM* - count character-gap positions as 4-way mismatches, otherwise same as average
276
277
278 For more details, please see the the MBE paper: http://mbe.oxfordjournals.org/content/22/5/1208.short
279
280 -----
281
282 **Ambiguity fraction**
283
284 .. class:: infomark
285
286 **TIP:** This option is only available when *Handle ambiguities* is set to Resolve
287
288 Affects only the Resolve option for handling ambiguities. Any sequence with no more than the selected proportion [0 - 1] will have its ambiguities resolved (if possible), and ambiguities in sequences with higher fractions of them will be averaged. This mitigates spurious linkages due to highly ambiguous sequences
289
290 -----
291
292 **Compare to Los Alamos National Laboratory HIV database sequences**
293
294 .. class:: infomark
295
296 **TIP:** This option is only available for specific reference types
297
298 Compare uploaded sequences to all public sequences. Retrieved periodically from the Los Alamos HIV Sequence Database: http://hiv.lanl.gov/
299 ]]></help>
300 <citations>
301 <citation/>
302 </citations>
303 </tool>