|
0
|
1 .\" Automatically generated by Pod::Man 2.25 (Pod::Simple 3.22)
|
|
|
2 .\"
|
|
|
3 .\" Standard preamble:
|
|
|
4 .\" ========================================================================
|
|
|
5 .de Sp \" Vertical space (when we can't use .PP)
|
|
|
6 .if t .sp .5v
|
|
|
7 .if n .sp
|
|
|
8 ..
|
|
|
9 .de Vb \" Begin verbatim text
|
|
|
10 .ft CW
|
|
|
11 .nf
|
|
|
12 .ne \\$1
|
|
|
13 ..
|
|
|
14 .de Ve \" End verbatim text
|
|
|
15 .ft R
|
|
|
16 .fi
|
|
|
17 ..
|
|
|
18 .\" Set up some character translations and predefined strings. \*(-- will
|
|
|
19 .\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left
|
|
|
20 .\" double quote, and \*(R" will give a right double quote. \*(C+ will
|
|
|
21 .\" give a nicer C++. Capital omega is used to do unbreakable dashes and
|
|
|
22 .\" therefore won't be available. \*(C` and \*(C' expand to `' in nroff,
|
|
|
23 .\" nothing in troff, for use with C<>.
|
|
|
24 .tr \(*W-
|
|
|
25 .ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p'
|
|
|
26 .ie n \{\
|
|
|
27 . ds -- \(*W-
|
|
|
28 . ds PI pi
|
|
|
29 . if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch
|
|
|
30 . if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\" diablo 12 pitch
|
|
|
31 . ds L" ""
|
|
|
32 . ds R" ""
|
|
|
33 . ds C` ""
|
|
|
34 . ds C' ""
|
|
|
35 'br\}
|
|
|
36 .el\{\
|
|
|
37 . ds -- \|\(em\|
|
|
|
38 . ds PI \(*p
|
|
|
39 . ds L" ``
|
|
|
40 . ds R" ''
|
|
|
41 'br\}
|
|
|
42 .\"
|
|
|
43 .\" Escape single quotes in literal strings from groff's Unicode transform.
|
|
|
44 .ie \n(.g .ds Aq \(aq
|
|
|
45 .el .ds Aq '
|
|
|
46 .\"
|
|
|
47 .\" If the F register is turned on, we'll generate index entries on stderr for
|
|
|
48 .\" titles (.TH), headers (.SH), subsections (.SS), items (.Ip), and index
|
|
|
49 .\" entries marked with X<> in POD. Of course, you'll have to process the
|
|
|
50 .\" output yourself in some meaningful fashion.
|
|
|
51 .ie \nF \{\
|
|
|
52 . de IX
|
|
|
53 . tm Index:\\$1\t\\n%\t"\\$2"
|
|
|
54 ..
|
|
|
55 . nr % 0
|
|
|
56 . rr F
|
|
|
57 .\}
|
|
|
58 .el \{\
|
|
|
59 . de IX
|
|
|
60 ..
|
|
|
61 .\}
|
|
|
62 .\"
|
|
|
63 .\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2).
|
|
|
64 .\" Fear. Run. Save yourself. No user-serviceable parts.
|
|
|
65 . \" fudge factors for nroff and troff
|
|
|
66 .if n \{\
|
|
|
67 . ds #H 0
|
|
|
68 . ds #V .8m
|
|
|
69 . ds #F .3m
|
|
|
70 . ds #[ \f1
|
|
|
71 . ds #] \fP
|
|
|
72 .\}
|
|
|
73 .if t \{\
|
|
|
74 . ds #H ((1u-(\\\\n(.fu%2u))*.13m)
|
|
|
75 . ds #V .6m
|
|
|
76 . ds #F 0
|
|
|
77 . ds #[ \&
|
|
|
78 . ds #] \&
|
|
|
79 .\}
|
|
|
80 . \" simple accents for nroff and troff
|
|
|
81 .if n \{\
|
|
|
82 . ds ' \&
|
|
|
83 . ds ` \&
|
|
|
84 . ds ^ \&
|
|
|
85 . ds , \&
|
|
|
86 . ds ~ ~
|
|
|
87 . ds /
|
|
|
88 .\}
|
|
|
89 .if t \{\
|
|
|
90 . ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u"
|
|
|
91 . ds ` \\k:\h'-(\\n(.wu*8/10-\*(#H)'\`\h'|\\n:u'
|
|
|
92 . ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'^\h'|\\n:u'
|
|
|
93 . ds , \\k:\h'-(\\n(.wu*8/10)',\h'|\\n:u'
|
|
|
94 . ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'|\\n:u'
|
|
|
95 . ds / \\k:\h'-(\\n(.wu*8/10-\*(#H)'\z\(sl\h'|\\n:u'
|
|
|
96 .\}
|
|
|
97 . \" troff and (daisy-wheel) nroff accents
|
|
|
98 .ds : \\k:\h'-(\\n(.wu*8/10-\*(#H+.1m+\*(#F)'\v'-\*(#V'\z.\h'.2m+\*(#F'.\h'|\\n:u'\v'\*(#V'
|
|
|
99 .ds 8 \h'\*(#H'\(*b\h'-\*(#H'
|
|
|
100 .ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\*(#H)/2u'\v'-.3n'\*(#[\z\(de\v'.3n'\h'|\\n:u'\*(#]
|
|
|
101 .ds d- \h'\*(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\*(#H'
|
|
|
102 .ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'|\\n:u'
|
|
|
103 .ds th \*(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u*2/3)'\s-1o\s+1\*(#]
|
|
|
104 .ds Th \*(#[\s+2I\s-2\h'-\w'I'u*3/5'\v'-.3m'o\v'.3m'\*(#]
|
|
|
105 .ds ae a\h'-(\w'a'u*4/10)'e
|
|
|
106 .ds Ae A\h'-(\w'A'u*4/10)'E
|
|
|
107 . \" corrections for vroff
|
|
|
108 .if v .ds ~ \\k:\h'-(\\n(.wu*9/10-\*(#H)'\s-2\u~\d\s+2\h'|\\n:u'
|
|
|
109 .if v .ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'\v'-.4m'^\v'.4m'\h'|\\n:u'
|
|
|
110 . \" for low resolution devices (crt and lpr)
|
|
|
111 .if \n(.H>23 .if \n(.V>19 \
|
|
|
112 \{\
|
|
|
113 . ds : e
|
|
|
114 . ds 8 ss
|
|
|
115 . ds o a
|
|
|
116 . ds d- d\h'-1'\(ga
|
|
|
117 . ds D- D\h'-1'\(hy
|
|
|
118 . ds th \o'bp'
|
|
|
119 . ds Th \o'LP'
|
|
|
120 . ds ae ae
|
|
|
121 . ds Ae AE
|
|
|
122 .\}
|
|
|
123 .rm #[ #] #H #V #F C
|
|
|
124 .\" ========================================================================
|
|
|
125 .\"
|
|
|
126 .IX Title "EXTRACTFROMSEQUENCEFILES 1"
|
|
|
127 .TH EXTRACTFROMSEQUENCEFILES 1 "2015-03-29" "perl v5.14.2" "MayaChemTools"
|
|
|
128 .\" For nroff, turn off justification. Always turn off hyphenation; it makes
|
|
|
129 .\" way too many mistakes in technical documents.
|
|
|
130 .if n .ad l
|
|
|
131 .nh
|
|
|
132 .SH "NAME"
|
|
|
133 ExtractFromSequenceFiles.pl \- Extract data from sequence and alignment files
|
|
|
134 .SH "SYNOPSIS"
|
|
|
135 .IX Header "SYNOPSIS"
|
|
|
136 ExtractFromSequenceFiles.pl SequenceFile(s) AlignmentFile(s)...
|
|
|
137 .PP
|
|
|
138 ExtractFromSequenceFiles.pl [\fB\-h, \-\-help\fR] [\fB\-i, \-\-IgnoreGaps\fR yes | no]
|
|
|
139 [\fB\-m, \-\-mode\fR SequenceID | SequenceNum | SequenceNumRange] [\fB\-o, \-\-overwrite\fR]
|
|
|
140 [\fB\-r, \-\-root\fR rootname] [\fB\-s, \-\-Sequences\fR \*(L"SequenceID, [SequenceID,...]\*(R" | \*(L"SequenceNum, [SequenceNum,...]\*(R" |
|
|
|
141 \&\*(L"StartingSeqNum, EndingSeqNum\*(R"] [\fB\-\-SequenceIDMatch\fR Exact | Relaxed]
|
|
|
142 [\fB\-w, \-\-WorkingDir\fR dirname] SequenceFile(s) AlignmentFile(s)...
|
|
|
143 .SH "DESCRIPTION"
|
|
|
144 .IX Header "DESCRIPTION"
|
|
|
145 Extract specific data from \fISequenceFile(s) and AlignmentFile(s)\fR and generate
|
|
|
146 \&\s-1FASTA\s0 files. You can extract sequences using sequence IDs or sequence numbers.
|
|
|
147 .PP
|
|
|
148 The file names are separated by spaces. All the sequence files in a current directory can
|
|
|
149 be specified by \fI*.aln\fR, \fI*.msf\fR, \fI*.fasta\fR, \fI*.fta\fR, \fI*.pir\fR or any other supported
|
|
|
150 formats; additionally, \fIDirName\fR corresponds to all the sequence files in the current directory
|
|
|
151 with any of the supported file extension: \fI.aln, .msf, .fasta, .fta, and .pir\fR.
|
|
|
152 .PP
|
|
|
153 Supported sequence formats are: \fIALN/CLustalW\fR, \fI\s-1GCG/MSF\s0\fR, \fI\s-1PILEUP/MSF\s0\fR, \fIPearson/FASTA\fR,
|
|
|
154 and \fI\s-1NBRF/PIR\s0\fR. Instead of using file extensions, file formats are detected by parsing the contents
|
|
|
155 of \fISequenceFile(s) and AlignmentFile(s)\fR.
|
|
|
156 .SH "OPTIONS"
|
|
|
157 .IX Header "OPTIONS"
|
|
|
158 .IP "\fB\-h, \-\-help\fR" 4
|
|
|
159 .IX Item "-h, --help"
|
|
|
160 Print this help message.
|
|
|
161 .IP "\fB\-i, \-\-IgnoreGaps\fR \fIyes | no\fR" 4
|
|
|
162 .IX Item "-i, --IgnoreGaps yes | no"
|
|
|
163 Ignore gaps or gap columns during during generation of new sequence or alignment file(s).
|
|
|
164 Possible values: \fIyes or no\fR. Default value: \fIyes\fR.
|
|
|
165 .Sp
|
|
|
166 In order to remove gap columns, length of all the sequence must be same; otherwise,
|
|
|
167 this option is ignored.
|
|
|
168 .IP "\fB\-m, \-\-mode\fR \fISequenceID | SequenceNum | SequenceNumRange\fR" 4
|
|
|
169 .IX Item "-m, --mode SequenceID | SequenceNum | SequenceNumRange"
|
|
|
170 Specify how to extract data from sequence files: extract sequences using sequence
|
|
|
171 IDs or sequence numbers. Possible values: \fISequenceID | SequenceNum
|
|
|
172 | SequenceNumRange\fR. Default: \fISequenceNum\fR with value of 1.
|
|
|
173 .Sp
|
|
|
174 The sequence numbers correspond to position of sequences starting from 1 for first sequence
|
|
|
175 in \fISequenceFile(s) and AlignmentFile(s)\fR.
|
|
|
176 .IP "\fB\-o, \-\-overwrite\fR" 4
|
|
|
177 .IX Item "-o, --overwrite"
|
|
|
178 Overwrite existing files.
|
|
|
179 .IP "\fB\-r, \-\-root\fR \fIrootname\fR" 4
|
|
|
180 .IX Item "-r, --root rootname"
|
|
|
181 New sequence file name is generated using the root: <Root><Mode>.<Ext>. Default new file:
|
|
|
182 <SequenceFileName><Mode>.<Ext>. This option is ignored for multiple input files.
|
|
|
183 .ie n .IP "\fB\-s, \-\-Sequences\fR \fI""SequenceID,[SequenceID,...]"" | ""SequenceNum,[SequenceNum,...]"" | ""StartingSeqNum,EndingSeqNum""\fR" 4
|
|
|
184 .el .IP "\fB\-s, \-\-Sequences\fR \fI``SequenceID,[SequenceID,...]'' | ``SequenceNum,[SequenceNum,...]'' | ``StartingSeqNum,EndingSeqNum''\fR" 4
|
|
|
185 .IX Item "-s, --Sequences SequenceID,[SequenceID,...] | SequenceNum,[SequenceNum,...] | StartingSeqNum,EndingSeqNum"
|
|
|
186 This value is \fB\-m, \-\-mode\fR specific. In general, it's a comma delimites list of sequence IDs or sequence
|
|
|
187 numbers.
|
|
|
188 .Sp
|
|
|
189 For \fISequenceID\fR value of \fB\-m, \-\-mode\fR option, input value format is: \fISequenceID,...\fR. Examples:
|
|
|
190 .Sp
|
|
|
191 .Vb 2
|
|
|
192 \& ACHE_BOVIN
|
|
|
193 \& ACHE_BOVIN,ACHE_HUMAN
|
|
|
194 .Ve
|
|
|
195 .Sp
|
|
|
196 For \fISequenceNum\fR value of \fB\-m, \-\-mode\fR option, input value format is: \fISequenceNum,...\fR. Examples:
|
|
|
197 .Sp
|
|
|
198 .Vb 2
|
|
|
199 \& 2
|
|
|
200 \& 1,5
|
|
|
201 .Ve
|
|
|
202 .Sp
|
|
|
203 For \fISequenceNum\fR value of \fB\-m, \-\-mode\fR option, input value format is: \fIStaringSeqNum,EndingSeqNum\fR. Examples:
|
|
|
204 .Sp
|
|
|
205 .Vb 1
|
|
|
206 \& 2,4
|
|
|
207 .Ve
|
|
|
208 .IP "\fB\-\-SequenceIDMatch\fR \fIExact | Relaxed\fR" 4
|
|
|
209 .IX Item "--SequenceIDMatch Exact | Relaxed"
|
|
|
210 Sequence IDs matching criterion during \fISequenceID\fR value of \fB\-m, \-\-mode\fR option: match
|
|
|
211 specified sequence \s-1ID\s0 exactly or as sub string against sequence IDs in the files. Possible
|
|
|
212 values: \fIExact | Relaxed\fR. Default: \fIRelaxed\fR. Sequence \s-1ID\s0 match is case insenstitive
|
|
|
213 during both options.
|
|
|
214 .IP "\fB\-\-SequenceLength\fR \fInumber\fR" 4
|
|
|
215 .IX Item "--SequenceLength number"
|
|
|
216 Maximum sequence length per line in sequence file(s). Default: \fI80\fR.
|
|
|
217 .IP "\fB\-w \-\-WorkingDir\fR \fItext\fR" 4
|
|
|
218 .IX Item "-w --WorkingDir text"
|
|
|
219 Location of working directory. Default: current directory.
|
|
|
220 .SH "EXAMPLES"
|
|
|
221 .IX Header "EXAMPLES"
|
|
|
222 To extract first sequence from Sample1.fasta sequence file and generate Sample1SequenceNum.fasta
|
|
|
223 sequence file, type:
|
|
|
224 .PP
|
|
|
225 .Vb 1
|
|
|
226 \& % ExtractFromSequenceFiles.pl \-o Sample1.fasta
|
|
|
227 .Ve
|
|
|
228 .PP
|
|
|
229 To extract first sequence from Sample1.aln alignment file and generate Sample1SequenceNum.fasta
|
|
|
230 sequence file without any column gaps, type:
|
|
|
231 .PP
|
|
|
232 .Vb 1
|
|
|
233 \& % ExtractFromSequenceFiles.pl \-o Sample1.aln
|
|
|
234 .Ve
|
|
|
235 .PP
|
|
|
236 To extract first sequence from Sample1.aln alignment file and generate Sample1SequenceNum.fasta
|
|
|
237 sequence file with column gaps, type:
|
|
|
238 .PP
|
|
|
239 .Vb 1
|
|
|
240 \& % ExtractFromSequenceFiles.pl \-\-IgnroreGaps No \-o Sample1.aln
|
|
|
241 .Ve
|
|
|
242 .PP
|
|
|
243 To extract sequence number 1 and 4 from Sample1.fasta sequence file and generate
|
|
|
244 Sample1SequenceNum.fasta sequence file, type:
|
|
|
245 .PP
|
|
|
246 .Vb 2
|
|
|
247 \& % ExtractFromSequenceFiles.pl \-o \-m SequenceNum \-\-Sequences 1,4
|
|
|
248 \& \-o Sample1.fasta
|
|
|
249 .Ve
|
|
|
250 .PP
|
|
|
251 To extract sequences from sequence number 1 to 4 from Sample1.fasta sequence file and generate
|
|
|
252 Sample1SequenceNumRange.fasta sequence file, type:
|
|
|
253 .PP
|
|
|
254 .Vb 2
|
|
|
255 \& % ExtractFromSequenceFiles.pl \-o \-m SequenceNumRange \-\-Sequences
|
|
|
256 \& 1,4 \-o Sample1.fasta
|
|
|
257 .Ve
|
|
|
258 .PP
|
|
|
259 To extract sequence \s-1ID\s0 \*(L"Q9P993/104\-387\*(R" from sequence from Sample1.fasta sequence file and generate
|
|
|
260 Sample1SequenceID.fasta sequence file, type:
|
|
|
261 .PP
|
|
|
262 .Vb 2
|
|
|
263 \& % ExtractFromSequenceFiles.pl \-o \-m SequenceID \-\-Sequences
|
|
|
264 \& "Q9P993/104\-387" \-\-SequenceIDMatch Exact \-o Sample1.fasta
|
|
|
265 .Ve
|
|
|
266 .SH "AUTHOR"
|
|
|
267 .IX Header "AUTHOR"
|
|
|
268 Manish Sud <msud@san.rr.com>
|
|
|
269 .SH "SEE ALSO"
|
|
|
270 .IX Header "SEE ALSO"
|
|
|
271 AnalyzeSequenceFilesData.pl, InfoSequenceFiles.pl
|
|
|
272 .SH "COPYRIGHT"
|
|
|
273 .IX Header "COPYRIGHT"
|
|
|
274 Copyright (C) 2015 Manish Sud. All rights reserved.
|
|
|
275 .PP
|
|
|
276 This file is part of MayaChemTools.
|
|
|
277 .PP
|
|
|
278 MayaChemTools is free software; you can redistribute it and/or modify it under
|
|
|
279 the terms of the \s-1GNU\s0 Lesser General Public License as published by the Free
|
|
|
280 Software Foundation; either version 3 of the License, or (at your option)
|
|
|
281 any later version.
|
