|
0
|
1 <!--
|
|
|
2 # =====================================================
|
|
|
3 # $Id: ExtractModificationSiteSequenceContext.xml 90 2011-01-19 13:20:31Z pieter.neerincx@gmail.com $
|
|
|
4 # $URL: https://trac.nbic.nl/svn/galaxytools/trunk/tools/general/FastaTools/ExtractModificationSiteSequenceContext.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="ExtractPeptideSequenceContext4" version="2.1" name="Extract Modification Site Context">
|
|
|
11 <description>by mapping modified amino acids in peptides back to proteins and fetching the sequence surrounding the modified sites.</description>
|
|
|
12 <command interpreter="perl">ExtractPeptideSequenceContext.pl --db $db --dbf FASTA --f $fragments --icol $icol --pcol $pcol --s --modo $modo --ma '$ma' --n $n --c $c --pc '$pc' --ll ERROR</command>
|
|
|
13 <inputs>
|
|
|
14 <param name="fragments" type="data" format="tabular" label="Peptide sequences and their protein's identifiers"
|
|
|
15 help="(in tab delimited format)"/>
|
|
|
16 <param name="icol" type="data_column" value="1" data_ref="fragments" label="Protein identifier column"/>
|
|
|
17 <param name="pcol" type="data_column" value="2" data_ref="fragments" label="Peptide sequence column"/>
|
|
|
18 <!--
|
|
|
19 <param name="icol" type="integer" value="1" label="Protein identifier column"/>
|
|
|
20 <param name="pcol" type="integer" value="2" label="Peptide sequence column"/>
|
|
|
21 -->
|
|
|
22 <param name="db" type="data" format="fasta" label="Protein sequences"
|
|
|
23 help="(in FASTA format)"/>
|
|
|
24 <param name="n" type="integer" value="5" label="N-terminal sequence context length"/>
|
|
|
25 <param name="c" type="integer" value="5" label="C-terminal sequence context length"/>
|
|
|
26 <param name="pc" type="select" help="to fill positions in the sequence context when the protein was too short for a full length context.">
|
|
|
27 <label>Padding character</label>
|
|
|
28 <option value="-">dash</option>
|
|
|
29 <option value=" ">space</option>
|
|
|
30 <option value="">none</option>
|
|
|
31 </param>
|
|
|
32 <param name="ma" type="text" label="Modified amino acid"/>
|
|
|
33 </inputs>
|
|
|
34 <outputs>
|
|
|
35 <data name="modo" format="tabular" label="Modification site sequence contexts for ${fragments.name}"/>
|
|
|
36 </outputs>
|
|
|
37 <!--
|
|
|
38 <tests>
|
|
|
39 <test>
|
|
|
40 <param name="input" value="*.fasta"/>
|
|
|
41 <param name="identifiers" value="*.txt"/>
|
|
|
42 <output name="output" file="*.fasta"/>
|
|
|
43 </test>
|
|
|
44 </tests>
|
|
|
45 -->
|
|
|
46 <help>
|
|
|
47
|
|
|
48 .. role:: raw-html(raw)
|
|
|
49 :format: html
|
|
|
50
|
|
|
51 .. class:: infomark
|
|
|
52
|
|
|
53 **What it does**
|
|
|
54
|
|
|
55 Map peptide sequences back to proteins and extract sequence contexts for modification sites.
|
|
|
56
|
|
|
57 :raw-html:`<object data="static/images/nbic_gmr/ExtractModificationSiteSequenceContext.svg" type="image/svg+xml" width="100%"/>`
|
|
|
58
|
|
|
59
|
|
|
60 ===================================================
|
|
|
61 *Peptide sequences and their protein's identifiers*
|
|
|
62 ===================================================
|
|
|
63
|
|
|
64 This file must contain at least peptides and accession numbers or IDs of the proteins the peptides were derived from. \
|
|
|
65 The data must be in TAB delimited format and may contain other columns, which will be preserved in the output. \
|
|
|
66 If a sequence context was found, it will be appended in a new column to the right of the existing columns. \
|
|
|
67 When another sequence context was found for the same peptide, it will appended as an extra row in the output.
|
|
|
68 Protein accession numbers / IDs must be in the same format as was used in the FASTA file with protein sequences (database). \
|
|
|
69 The only exception to this rule is that accession numbers / IDs may be optionally suffixed with the peptide\'s position in its protein between brackets. \
|
|
|
70 For example: CLH1_HUMAN[1612-1620] will be matched to CLH1_HUMAN in a FASTA file with protein sequences. \
|
|
|
71 Amino acids in the petide sequences must be in uppercase.
|
|
|
72
|
|
|
73 ===============================================
|
|
|
74 *Protein sequences*
|
|
|
75 ===============================================
|
|
|
76
|
|
|
77 Input file containing all protein sequences in FASTA format. \
|
|
|
78 This tool will look for any type of protein ID in the first part of FASTA sequence headers up until the first white space. \
|
|
|
79 Optionally multiple IDs may be present separated with pipe symbols (|) or semicolons (;). \
|
|
|
80 Optionally IDs may be prefixed with a database namespace and a colon (:). \
|
|
|
81 For example the accession number P32234 as well as the ID 128UP_DROME would be recognized in both this sequence header:
|
|
|
82
|
|
|
83 >UniProtAcc:P32234|UniProtID:128UP_DROME GTP-binding protein 128up - Drosophila melanogaster (Fruit fly)
|
|
|
84
|
|
|
85 and in this one:
|
|
|
86
|
|
|
87 >P32234|128UP_DROME GTP-binding protein 128up - Drosophila melanogaster (Fruit fly)
|
|
|
88
|
|
|
89 ===================================================
|
|
|
90 *N-terminal and C-terminal sequence context length*
|
|
|
91 ===================================================
|
|
|
92
|
|
|
93 Integers specifying the length of the N-terminal and C-terminal sequence context to retrieve starting from the modification site. \
|
|
|
94 Note that the width of a modification site is 1 amino acid. \
|
|
|
95 When defaults are used for both the N-terminal and C-terminal sequence context lengths, \
|
|
|
96 the total sequence context length for a modification site will be:
|
|
|
97 (N-terminal sequence context) + (modified amino acid) + (C-terminal sequence context) = 5 + 1 + 5 = 11.
|
|
|
98
|
|
|
99 ===============================================
|
|
|
100 *Modified amino acid*
|
|
|
101 ===============================================
|
|
|
102
|
|
|
103 The amino acid must be specified in uppercase and the modification in lower case. \
|
|
|
104 The order is not important. \
|
|
|
105 Hence a phophorylated serine in a peptide sequence can be indicated with either pS or Sp, \
|
|
|
106 but you cannot mix both pS and Sp in a single peptide sequence file. \
|
|
|
107 You may provide an asterisk (*) instead of an upper case amino acid to retrieve sequence contexts \
|
|
|
108 for the specified modification no matter what amino acid it was located on. \
|
|
|
109 A modification may be specified with more than one lower case character, \
|
|
|
110 so for example phosphoS or Sphospho can also be used for a phosphorylated serine.
|
|
|
111
|
|
|
112 ===============================================
|
|
|
113 *Padding character*
|
|
|
114 ===============================================
|
|
|
115
|
|
|
116 Optional padding character to fill N-terminal or C-terminal positions in the sequence context, \
|
|
|
117 when the protein was too short to get a complete sequence context. \
|
|
|
118 Defaults to - a.k.a. dash or alignment gap character. \
|
|
|
119
|
|
|
120 -----
|
|
|
121
|
|
|
122 **Getting input data**
|
|
|
123
|
|
|
124 .. _my folder utility: http://mascotinternal.chem.uu.nl/mascot/cgi/uu_myfolder.pl
|
|
|
125
|
|
|
126 This tool requires \
|
|
|
127 peptide sequences in TAB delimited format and \
|
|
|
128 protein sequences from which the peptides were derived in FASTA format. \
|
|
|
129 If your peptide sequences are not in TAB delimited format, you can convert from:
|
|
|
130
|
|
|
131 - FASTA format using *FASTA manipulation* -> *FASTA-to-Tabular*
|
|
|
132 - A format using a different delimiter using *Text Manipulation* -> *Convert*
|
|
|
133
|
|
|
134 When your peptides were derived from a mass spectrometry experiment and identified with a search engine like Mascot, Sequest, etc.,\
|
|
|
135 please make sure you provide the same FASTA database for this tool as the one used for your search.
|
|
|
136 If you used Mascot hosted by the Biomolecular Mass Spectrometry and Proteomics Group @ Utrecht University, \
|
|
|
137 you can use the `my folder utility`_ to download the FASTA databases from the Mascot server.
|
|
|
138
|
|
|
139 -----
|
|
|
140
|
|
|
141 **Examples**
|
|
|
142
|
|
|
143 Example input for peptides identified with a Mascot search, \
|
|
|
144 some with phosphorylated residues indicated by pS, pT or pY \
|
|
|
145 and in TAB delimited format::
|
|
|
146
|
|
|
147 sequence score peptide mr mass delta (abs) mass delta (ppm) all protein matches
|
|
|
148 AGNAARDN 54.24 787.357254 -4.223E-5 -0.05334300253998803 H2A1B_HUMAN[67-74]; H2A1C_HUMAN[67-74]; H2A1D_HUMAN[67-74]
|
|
|
149 KLpSAAVVLI 11.48 912.600784 0.001608 1.7619971713721432 OSGI2_HUMAN[405-413]
|
|
|
150 RAGIKVpTVA 23.01 913.570892 6.283E-5 0.06786555979719196 PARK7_HUMAN[28-36]
|
|
|
151 KGGVVGIKVD 44.61 970.581146 -0.001214 -1.2507970147608864 ALDOA_HUMAN[101-110]
|
|
|
152 KIKELQAF 11.87 975.575287 0.003907 4.004816493470687 MMP20_HUMAN[71-78]
|
|
|
153 KIpSGpTVNIR 57.17 986.587265 -0.002761 -2.798536022051734 SYTC_HUMAN[681-689]
|
|
|
154 KLpYEALKF 17.54 1010.580032 0.004782 4.731935966057164 F105A_HUMAN[238-245]
|
|
|
155 KLDApSEpSLR 31.31 1017.545441 -0.002377 -2.3360136110127785 CLH1_HUMAN[1612-1620]
|
|
|
156
|
|
|
157 ===============================================
|
|
|
158 *Appending modification site sequence contexts*
|
|
|
159 ===============================================
|
|
|
160
|
|
|
161 With these options:
|
|
|
162
|
|
|
163 - p\* as *modified amino acid*
|
|
|
164 - c6 as *Protein identifier column*
|
|
|
165 - c1 as *Peptide sequence column*
|
|
|
166 - a suitable FASTA database with *Protein sequences*
|
|
|
167 - and everything else set to defaults
|
|
|
168
|
|
|
169 the example above will generate a result like this::
|
|
|
170
|
|
|
171 KLpSAAVVLI 11.48 912.600784 0.001608 1.7619971713721432 OSGI2_HUMAN[405-413] KIFKLSAAVVL
|
|
|
172 RAGIKVpTVA 23.01 913.570892 6.283E-5 0.06786555979719196 PARK7_HUMAN[28-36] AGIKVTVAGLA
|
|
|
173 KIpSGpTVNIR 57.17 986.587265 -0.002761 -2.798536022051734 SYTC_HUMAN[681-689] EKEKISGTVNI
|
|
|
174 KIpSGpTVNIR 57.17 986.587265 -0.002761 -2.798536022051734 SYTC_HUMAN[681-689] EKISGTVNIRT
|
|
|
175 KLpYEALKF 17.54 1010.580032 0.004782 4.731935966057164 F105A_HUMAN[238-245] LEYKLYEALKF
|
|
|
176 KLDApSEpSLR 31.31 1017.545441 -0.002377 -2.3360136110127785 CLH1_HUMAN[1612-1620] DKLDASESLRK
|
|
|
177 KLDApSEpSLR 31.31 1017.545441 -0.002377 -2.3360136110127785 CLH1_HUMAN[1612-1620] LDASESLRKEE
|
|
|
178
|
|
|
179 Note the header line was ignored, peptides like AGNAARDN without any modified amino acids are absent from the output \
|
|
|
180 and peptides like KLDApSEpSLR with more than one modified amino acid occur more than once in the output.
|
|
|
181
|
|
|
182 </help>
|
|
|
183 </tool>
|
