0
|
1 <!--
|
|
2 # =====================================================
|
|
3 # $Id: GenerateDegenerateFasta.xml 90 2011-01-19 13:20:31Z pieter.neerincx@gmail.com $
|
|
4 # $URL: https://trac.nbic.nl/svn/galaxytools/trunk/tools/general/FastaTools/GenerateDegenerateFasta.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="GenerateDegenerateFasta1" name="GenerateDegenerateFasta" version="2.1">
|
|
11 <description>Creates a FASTA file with all possible sequences for degenerate sequences.</description>
|
|
12 <command interpreter="perl">
|
|
13 #if $sequence_features.acid_type=="aa" #GenerateDegenerateFasta.pl -i $input -p $pcol -s $scol -t aa -o $output -x $sequence_features.xexpansion -l WARN
|
|
14 #elif $sequence_features.acid_type=="dna" #GenerateDegenerateFasta.pl -i $input -p $pcol -s $scol -t dna -o $output -l WARN
|
|
15 #elif $sequence_features.acid_type=="rna" #GenerateDegenerateFasta.pl -i $input -p $pcol -s $scol -t rna -o $output -l WARN
|
|
16 #end if
|
|
17 </command>
|
|
18 <inputs>
|
|
19 <param format="tabular" name="input" type="data" label="Degenerate sequences"
|
|
20 help="(in tab delimited format)"/>
|
|
21 <param name="pcol" type="data_column" value="1" data_ref="input" label="Prefix column"
|
|
22 help="Prefixes will be used as the first part of unique identifiers for the generated sequences."/>
|
|
23 <param name="scol" type="data_column" value="2" data_ref="input" label="Sequence column"/>
|
|
24 <conditional name='sequence_features'>
|
|
25 <param name="acid_type" type="select" accept_default="true" mmultiple="false" label="The degenerate sequences represent">
|
|
26 <label>The degenerate sequences represent</label>
|
|
27 <option value="aa">Proteins</option>
|
|
28 <option value="dna">DNA</option>
|
|
29 <option value="rna">RNA</option>
|
|
30 </param>
|
|
31 <when value="aa">
|
|
32 <param name="xexpansion" type="select" accept_default="true" mmultiple="false" label="The degenerate amino acid X represents">
|
|
33 <label>The degenerate amino acid X represents</label>
|
|
34 <option value="20">The 20 most common amino acids</option>
|
|
35 <option value="22">All 22 amino acids</option>
|
|
36 </param>
|
|
37 </when>
|
|
38 <when value="dna">
|
|
39 </when>
|
|
40 <when value="rna">
|
|
41 </when>
|
|
42 </conditional>
|
|
43 </inputs>
|
|
44 <outputs>
|
|
45 <data format="fasta" name="output" label="FASTA sequences for ${input.name}"/>
|
|
46 </outputs>
|
|
47 <!--
|
|
48 <tests>
|
|
49 <test>
|
|
50 <param name="input" value="GenerateDegenerateFasta_example_input.txt"/>
|
|
51 <output name="output" file="GenerateDegenerateFasta_example_output.fasta" ftype="fasta"/>
|
|
52 </test>
|
|
53 </tests>
|
|
54 -->
|
|
55 <help>
|
|
56
|
|
57 .. class:: infomark
|
|
58
|
|
59 **What it does**
|
|
60
|
|
61 This tool creates a multi-sequence FASTA file with all possible sequences based on degenerate input sequences.
|
|
62 The input must be a tab delimited file containing at least 2 columns.
|
|
63 One with the degenerate sequences and the other with a prefix that will be used to give each of generated sequences a unique identifier.
|
|
64 In addition to the prefix, the generated identifiers will contain an underscore followed by an incremented number.
|
|
65
|
|
66 ===================================================
|
|
67 *Degenerate (wild card) amino acids*
|
|
68 ===================================================
|
|
69
|
|
70 ===================== =========================================== ====================================================================
|
|
71 Amino Acid Expands to Comment
|
|
72 ===================== =========================================== ====================================================================
|
|
73 B D,N
|
|
74 J I,L
|
|
75 X A,C,D,E,F,G,H,I,K,L,M,N,P,Q,R,S,T,V,W,Y The 20 most common amino acids (default) or
|
|
76 X A,C,D,E,F,G,H,I,K,L,M,N,O,P,Q,R,S,T,U,V,W,Y All 22 amino acids including the rare Selenocysteine and Pyrrolysine
|
|
77 Z E,Q
|
|
78 ===================== =========================================== ====================================================================
|
|
79
|
|
80 ===================================================
|
|
81 *Degenerate (wild card) deoxyribonucleic acids*
|
|
82 ===================================================
|
|
83
|
|
84 ===================== ================================ ===============================================================================
|
|
85 Deoxyribonucleic Acid Expands to Comment
|
|
86 ===================== ================================ ===============================================================================
|
|
87 B C,G,T Not A; B follows A alphabetically
|
|
88 D A,G,T Not C; D follows C alphabetically
|
|
89 H A,C,T Not G; H follows G alphabetically
|
|
90 K G,T Keto
|
|
91 M A,C aMino
|
|
92 N A,C,G,T aNy
|
|
93 R A,G puRine
|
|
94 S C,G Strong interaction (3 H-bonds)
|
|
95 V A,C,G Not T (and not U); V follows U alphabetically
|
|
96 W A,T Weak interaction (2 H-bonds)
|
|
97 Y C,T pYrimidine
|
|
98 ===================== ================================ ===============================================================================
|
|
99
|
|
100 ===================================================
|
|
101 *Degenerate (wild card) ribonucleic acids*
|
|
102 ===================================================
|
|
103
|
|
104 ===================== ================================ ===============================================================================
|
|
105 Ribonucleic Acid Expands to Comment
|
|
106 ===================== ================================ ===============================================================================
|
|
107 B C,G,U Not A; B follows A alphabetically
|
|
108 D A,G,U Not C; D follows C alphabetically
|
|
109 H A,C,U Not G; H follows G alphabetically
|
|
110 K G,U Keto
|
|
111 M A,C aMino
|
|
112 N A,C,G,U aNy
|
|
113 R A,G puRine
|
|
114 S C,G Strong interaction (3 H-bonds)
|
|
115 V A,C,G Not U; V follows U alphabetically
|
|
116 W A,U Weak interaction (2 H-bonds)
|
|
117 Y C,U pYrimidine
|
|
118 ===================== ================================ ===============================================================================
|
|
119
|
|
120 -----
|
|
121
|
|
122 **Example**
|
|
123
|
|
124 If the degenerate input contains these two peptides::
|
|
125
|
|
126 Seq1 AXY
|
|
127 Seq2 SJT
|
|
128
|
|
129 The generated FASTA sequences will be this::
|
|
130
|
|
131 >Seq1_1
|
|
132 AAY
|
|
133 >Seq1_2
|
|
134 ACY
|
|
135 >Seq1_3
|
|
136 ADY
|
|
137 >Seq1_4
|
|
138 AEY
|
|
139 >Seq1_5
|
|
140 AFY
|
|
141 >Seq1_6
|
|
142 AGY
|
|
143 >Seq1_7
|
|
144 AHY
|
|
145 >Seq1_8
|
|
146 AIY
|
|
147 >Seq1_9
|
|
148 AKY
|
|
149 >Seq1_10
|
|
150 ALY
|
|
151 >Seq1_11
|
|
152 AMY
|
|
153 >Seq1_12
|
|
154 ANY
|
|
155 >Seq1_13
|
|
156 APY
|
|
157 >Seq1_14
|
|
158 AQY
|
|
159 >Seq1_15
|
|
160 ARY
|
|
161 >Seq1_16
|
|
162 ASY
|
|
163 >Seq1_17
|
|
164 ATY
|
|
165 >Seq1_18
|
|
166 AVY
|
|
167 >Seq1_19
|
|
168 AWY
|
|
169 >Seq1_20
|
|
170 AYY
|
|
171 >Seq2_1
|
|
172 SIT
|
|
173 >Seq2_2
|
|
174 SLT
|
|
175
|
|
176 </help>
|
|
177 </tool>
|