Mercurial > repos > galaxyp > nbic_fasta

comparison ConvertFastaHeaders.xml @ 0:163892325845 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Initial commit.
author galaxyp
date Fri, 10 May 2013 17:15:08 -0400
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:163892325845
1 <!--
2 # =====================================================
3 # $Id: ConvertFastaHeaders.xml 90 2011-01-19 13:20:31Z pieter.neerincx@gmail.com $
4 # $URL: https://trac.nbic.nl/svn/galaxytools/trunk/tools/general/FastaTools/ConvertFastaHeaders.xml $
5 # $LastChangedDate: 2011-01-19 07:20:31 -0600 (Wed, 19 Jan 2011) $
6 # $LastChangedRevision: 90 $
7 # $LastChangedBy: pieter.neerincx@gmail.com $
8 # =====================================================
9 -->
10 <tool id="ConvertFastaHeaders1" name="ConvertFastaHeaders" version="2.0">
11 <description>Converts sequence headers of FASTA files</description>
12 <command interpreter="perl">
13 #if $mode.action == "add" #ConvertFastaHeaders.pl -i $input -o $output -p $mode.pos.position -a $mode.action -f "$mode.pos.xfixes" -l ERROR
14 #elif $mode.action == "strip" #ConvertFastaHeaders.pl -i $input -o $output -p $mode.pos.position -a $mode.action -f "$mode.pos.xfixes" -l ERROR
15 #elif $mode.action == "replace" #ConvertFastaHeaders.pl -i $input -o $output -p $mode.pos.position -a $mode.action -f "$mode.pos.xfixes" -n $mode.pos.newfix -l ERROR
16 #elif $mode.action == "delete" #ConvertFastaHeaders.pl -i $input -o $output -p $mode.position -a $mode.action -l ERROR
17 #elif $mode.action == "shuffle" #ConvertFastaHeaders.pl -i $input -o $output -p $mode.position -a $mode.action -l ERROR
18 #end if
19 </command>
20 <inputs>
21 <param format="fasta" name="input" type="data" label="FASTA sequences"/>
22 <conditional name ="mode">
23 <param name="action" type="select">
24 <label>Action to perform on sequence identifiers</label>
25 <option value="add">Add Labels</option>
26 <option value="strip">Remove Labels</option>
27 <option value="replace">Replace Labels</option>
28 <option value="delete">Delete</option>
29 <option value="shuffle">Shuffle order</option>
30 </param>
31 <when value="add">
32 <conditional name="pos">
33 <param name="position" type="select" accept_default="true">
34 <label> Label position </label>
35 <option value="prefix">Prepend Prefixes</option>
36 <option value="suffix">Append Suffixes</option>
37 </param>
38 <when value="prefix">
39 <param name="xfixes" type="text" label="Space separated list of prefixes, which will be added"/>
40 </when>
41 <when value="suffix">
42 <param name="xfixes" type="text" label="Space separated list of suffixes, which will be added"/>
43 </when>
44 </conditional>
45 </when>
46 <when value="strip">
47 <conditional name="pos">
48 <param name="position" type="select" accept_default="true">
49 <label> Label position </label>
50 <option value="prefix">Strip Prefixes</option>
51 <option value="suffix">Strip Suffixes</option>
52 </param>
53 <when value="prefix">
54 <param name="xfixes" type="text" label="Space separated list of prefixes, which will be removed"/>
55 </when>
56 <when value="suffix">
57 <param name="xfixes" type="text" label="Space separated list of suffixes, which will be removed"/>
58 </when>
59 </conditional>
60 </when>
61 <when value="replace">
62 <conditional name="pos">
63 <param name="position" type="select" accept_default="true">
64 <label> Label position </label>
65 <option value="prefix">Replace prefixes with another prefix</option>
66 <option value="suffix">Replace suffixes with another suffix</option>
67 <option value="pre2suf">Replace prefixes with a suffix</option>
68 <option value="suf2pre">Replace suffixes with a prefix</option>
69 </param>
70 <when value="prefix">
71 <param name="xfixes" type="text" label="Space separated list of prefixes, which will be replaced"/>
72 <param name="newfix" type="text" label="New prefix to replace the current prefixes"/>
73 </when>
74 <when value="suffix">
75 <param name="xfixes" type="text" label="Space separated list of suffixes, which will be replaced"/>
76 <param name="newfix" type="text" label="New suffix to replace the current suffixes"/>
77 </when>
78 <when value="pre2suf">
79 <param name="xfixes" type="text" label="Space separated list of prefixes, which will be replaced"/>
80 <param name="newfix" type="text" label="New suffix to replace the current prefixes"/>
81 </when>
82 <when value="suf2pre">
83 <param name="xfixes" type="text" label="Space separated list of suffixes, which will be replaced"/>
84 <param name="newfix" type="text" label="New prefix to replace the current suffixes"/>
85 </when>
86 </conditional>
87 </when>
88 <when value="delete">
89 <param name="position" type="text" size="10" value="" label="Ranks of IDs to delete"
90 help="Comma separated list of numbers. For example 1,3 will delete the first and third ID from the FASTA headers."/>
91 </when>
92 <when value="shuffle">
93 <param name="position" type="text" size="10" value="" label="New order for the IDs"
94 help="Comma separated list of numbers. For example 1,3,2 will shuffle the order from 1,2,3 to 1,3,2."/>
95 </when>
96 </conditional>
97 </inputs>
98 <outputs>
99 <data format="fasta" name="output" label="${input.name} with converted FASTA headers"/>
100 </outputs>
101 <!--
102 <tests>
103 <test> -a add -f "UniProt-Acc: UniProt-ID:"
104 <param name="input" value="ConvertFastaHeaders_example_input_Add.fasta"/>
105 <output name="output" file="ConvertFastaHeaders_example_output_Add.fasta"/>
106 </test>
107 <test> -a strip -p prefix -f 'SP:'
108 <param name="input" value="ExtractPeptideSequenceContext_example_DB.fasta"/>
109 <output name="output" file="ConvertFastaHeaders_example_output_Strip.fasta"/>
110 </test>
111 <test> -a replace -p pre2suf -f 'SP:' -n '_CON'
112 <param name="input" value="ExtractPeptideSequenceContext_example_DB.fasta"/>
113 <output name="output" file="ConvertFastaHeaders_example_output_Replace.fasta"/>
114 </test>
115 <test> -a delete -p '1 3'
116 <param name="input" value="ExtractPeptideSequenceContext_example_DB.fasta"/>
117 <output name="output" file="ConvertFastaHeaders_example_output_Delete.fasta"/>
118 </test>
119 <test> -a shuffle -p '2 3 1'
120 <param name="input" value="ExtractPeptideSequenceContext_example_DB.fasta"/>
121 <output name="output" file="ConvertFastaHeaders_example_output_Shuffle.fasta"/>
122 </test>
123 </tests>
124 -->
125 <help>
126
127 .. class:: infomark
128
129 **What it does**
130
131 This tool converts the sequence headers (the description line starting with &gt;) for a set of FASTA sequences. \
132 Currently supported conversions:
133
134 - Append prefixes like for example database namespace to identifiers / accession numbers.
135 - Append suffixes to identifiers / accession numbers.
136 - Remove prefixes like for example database namespace from identifiers / accession numbers.
137 - Remove suffixes from identifiers / accession numbers.
138 - Replace prefixes with a suffix or vice versa.
139
140 -----
141
142 **Examples**
143
144 ========================================================
145 *Appending database namespace prefixes*
146 ========================================================
147
148 Supply a space separated list of prefixes to add to pipe separated identifiers. \
149 The prefixes must contain both the database namespace you want to add and the character used to separate the namespace from the identifier. \
150 The order of the namespaces is important in this case! \
151 For example with action *Add Labels*, label position *Prepend Prefixes* and prefixes *UniProtAcc: UniProtID:*, this header::
152
153 >P32234|128UP_DROME GTP-binding protein 128up - Drosophila melanogaster (Fruit fly)
154
155 will be converted into::
156
157 >UniProtAcc:P32234|UniProtID:128UP_DROME GTP-binding protein 128up - Drosophila melanogaster (Fruit fly)
158
159 ========================================================
160 *Removing database namespace prefixes*
161 ========================================================
162
163 Supply a space separated list of namespaces to remove from pipe separated identifiers. \
164 The prefixes must contain both the database namespace you want to remove and the character used to separate the namespace from the identifier. \
165 The order of the namespaces is not relevant in this case. \
166 For example with action *Remove Labels*, label position *Strip Prefixes* and \
167 with prefixes *UniProtAcc: UniProtID:* or with prefixes *UniProtID: UniProtAcc:*, this header::
168
169 >UniProtAcc:P32234|UniProtID:128UP_DROME GTP-binding protein 128up - Drosophila melanogaster (Fruit fly)
170
171 will be converted into::
172
173 >P32234|128UP_DROME GTP-binding protein 128up - Drosophila melanogaster (Fruit fly)
174
175 ========================================================
176 *Replacing a prefix with a suffix*
177 ========================================================
178
179 Supply the prefix to remove from pipe separated identifiers and a new suffix. \
180 The order of the prefixes is not relevant in this case. \
181 Optionally you can specify more than one prefix to remove by separating them with spaces. \
182 You can specify only one new suffix though, so in case you specified more than one prefix they will all be replaced with the same new suffix. \
183 In the following example we'll replace a *REV_* prefix to indicate a reversed sequence with a *_REV* suffix. \
184 With action *Replace Labels*, label position *Replace prefixes with a suffix*, prefix *REV_* and new suffix *_REV*, this header::
185
186 >REV_P32234|128UP_DROME GTP-binding protein 128up - Drosophila melanogaster (Fruit fly)
187
188 will be converted into::
189
190 >P32234_REV|128UP_DROME GTP-binding protein 128up - Drosophila melanogaster (Fruit fly)
191
192 ========================================================
193 *Other \*fix replacements*
194 ========================================================
195
196 You can also replace a prefix with a new prefix, a suffix with a new suffix or a suffix with a new prefix. \
197 These replacements are all similar to the example above. \
198 Hence you can specify multiple \*-fixes to be replaced and only one new \*-fix to replace the existing ones.
199
200 ========================================================
201 *Deleting sequence identifiers*
202 ========================================================
203
204 Supply a comma separated list of numbers for the ranks of the identifiers / accession numbers you want to remove. \
205 Multiple identifiers must be separated with a pipe symbol. \
206 For example with action *Delete*, and Ranks of IDs to delete set to *1,3*, this header::
207
208 >UniProtID:128UP_DROME|UniProtAcc:P32234|EMBL:AY069810 GTP-binding protein 128up - Drosophila melanogaster (Fruit fly)
209
210 will be converted into::
211
212 >UniProtAcc:P32234 GTP-binding protein 128up - Drosophila melanogaster (Fruit fly)
213
214 ========================================================
215 *Changing the order of sequence identifiers*
216 ========================================================
217
218 Supply a comma separated list of numbers for the new order of all the identifiers / accession numbers in a header. \
219 Multiple identifiers must be separated with a pipe symbol. \
220 Hence if your headers contain 4 pipe separated IDs and you only want to swap the order of the first and the second, \
221 you will still need to specify the new (unchanged) order for number 3 and 4 too.
222
223 For example with action *Shuffle*, and New order for the IDs set to *2,1,3*, this header::
224
225 >UniProtID:128UP_DROME|UniProtAcc:P32234|EMBL:AY069810 GTP-binding protein 128up - Drosophila melanogaster (Fruit fly)
226
227 will be converted into::
228
229 >UniProtAcc:P32234|UniProtID:128UP_DROME|EMBL:AY069810 GTP-binding protein 128up - Drosophila melanogaster (Fruit fly)
230
231 Specifying only *2,1* as the New order for the IDs will not work, because this header contains 3 IDs, \
232 so you'll have to include the (new) position for the third one as well.
233
234 ========================================================
235 *Need another type of conversion?*
236 ========================================================
237
238 Contact your local bioinformaticians to add other conversions...
239
240 </help>
241 </tool>