|
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 "INFOSEQUENCEFILES 1"
|
|
|
127 .TH INFOSEQUENCEFILES 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 InfoSequenceFiles.pl \- List information about sequence and alignment files
|
|
|
134 .SH "SYNOPSIS"
|
|
|
135 .IX Header "SYNOPSIS"
|
|
|
136 InfoSequenceFiles.pl SequenceFile(s) AlignmentFile(s)...
|
|
|
137 .PP
|
|
|
138 InfoSequenceFiles.pl [\fB\-a, \-\-all\fR] [\fB\-c, \-\-count\fR] [\fB\-d, \-\-detail\fR infolevel]
|
|
|
139 [\fB\-f, \-\-frequency\fR] [\fB\-\-FrequencyBins\fR number | \*(L"number, number, [number,...]\*(R"]
|
|
|
140 [\fB\-h, \-\-help\fR] [\fB\-i, \-\-IgnoreGaps\fR yes | no] [\fB\-l, \-\-longest\fR] [\fB\-s, \-\-shortest\fR]
|
|
|
141 [\fB\-\-SequenceLengths\fR] [\fB\-w, \-\-workingdir\fR dirname] SequenceFile(s)...
|
|
|
142 .SH "DESCRIPTION"
|
|
|
143 .IX Header "DESCRIPTION"
|
|
|
144 List information about contents of \fISequenceFile(s) and AlignmentFile(s)\fR: number of sequences,
|
|
|
145 shortest and longest sequences, distribution of sequence lengths and so on. The file names are
|
|
|
146 separated by spaces. All the sequence files in a current directory can be specified by \fI*.aln\fR,
|
|
|
147 \&\fI*.msf\fR, \fI*.fasta\fR, \fI*.fta\fR, \fI*.pir\fR or any other supported formats; additionally, \fIDirName\fR
|
|
|
148 corresponds to all the sequence files in the current directory with any of the supported file
|
|
|
149 extension: \fI.aln, .msf, .fasta, .fta, and .pir\fR.
|
|
|
150 .PP
|
|
|
151 Supported sequence formats are: \fIALN/CLustalW\fR, \fI\s-1GCG/MSF\s0\fR, \fI\s-1PILEUP/MSF\s0\fR, \fIPearson/FASTA\fR,
|
|
|
152 and \fI\s-1NBRF/PIR\s0\fR. Instead of using file extensions, file formats are detected by parsing the contents
|
|
|
153 of \fISequenceFile(s) and AlignmentFile(s)\fR.
|
|
|
154 .SH "OPTIONS"
|
|
|
155 .IX Header "OPTIONS"
|
|
|
156 .IP "\fB\-a, \-\-all\fR" 4
|
|
|
157 .IX Item "-a, --all"
|
|
|
158 List all the available information.
|
|
|
159 .IP "\fB\-c, \-\-count\fR" 4
|
|
|
160 .IX Item "-c, --count"
|
|
|
161 List number of of sequences. This is \fBdefault behavior\fR.
|
|
|
162 .IP "\fB\-d, \-\-detail\fR \fIInfoLevel\fR" 4
|
|
|
163 .IX Item "-d, --detail InfoLevel"
|
|
|
164 Level of information to print about sequences during various options. Default: \fI1\fR.
|
|
|
165 Possible values: \fI1, 2 or 3\fR.
|
|
|
166 .IP "\fB\-f, \-\-frequency\fR" 4
|
|
|
167 .IX Item "-f, --frequency"
|
|
|
168 List distribution of sequence lengths using the specified number of bins or bin range specified
|
|
|
169 using \fBFrequencyBins\fR option.
|
|
|
170 .Sp
|
|
|
171 This option is ignored for input files containing only single sequence.
|
|
|
172 .ie n .IP "\fB\-\-FrequencyBins\fR \fInumber | ""number,number,[number,...]""\fR" 4
|
|
|
173 .el .IP "\fB\-\-FrequencyBins\fR \fInumber | ``number,number,[number,...]''\fR" 4
|
|
|
174 .IX Item "--FrequencyBins number | number,number,[number,...]"
|
|
|
175 This value is used with \fB\-f, \-\-frequency\fR option to list distribution of sequence lengths using
|
|
|
176 the specified number of bins or bin range. Default value: \fI10\fR.
|
|
|
177 .Sp
|
|
|
178 The bin range list is used to group sequence lengths into different groups; It must contain
|
|
|
179 values in ascending order. Examples:
|
|
|
180 .Sp
|
|
|
181 .Vb 2
|
|
|
182 \& 100,200,300,400,500,600
|
|
|
183 \& 200,400,600,800,1000
|
|
|
184 .Ve
|
|
|
185 .Sp
|
|
|
186 The frequency value calculated for a specific bin corresponds to all the sequence lengths
|
|
|
187 which are greater than the previous bin value and less than or equal to the current bin value.
|
|
|
188 .IP "\fB\-h, \-\-help\fR" 4
|
|
|
189 .IX Item "-h, --help"
|
|
|
190 Print this help message.
|
|
|
191 .IP "\fB\-i, \-\-IgnoreGaps\fR \fIyes | no\fR" 4
|
|
|
192 .IX Item "-i, --IgnoreGaps yes | no"
|
|
|
193 Ignore gaps during calculation of sequence lengths. Possible values: \fIyes or
|
|
|
194 no\fR. Default value: \fIno\fR.
|
|
|
195 .IP "\fB\-l, \-\-longest\fR" 4
|
|
|
196 .IX Item "-l, --longest"
|
|
|
197 List information about longest sequence: \s-1ID\s0, sequence and sequence length. This option
|
|
|
198 is ignored for input files containing only single sequence.
|
|
|
199 .IP "\fB\-s, \-\-shortest\fR" 4
|
|
|
200 .IX Item "-s, --shortest"
|
|
|
201 List information about shortest sequence: \s-1ID\s0, sequence and sequence length. This option
|
|
|
202 is ignored for input files containing only single sequence.
|
|
|
203 .IP "\fB\-\-SequenceLengths\fR" 4
|
|
|
204 .IX Item "--SequenceLengths"
|
|
|
205 List information about sequence lengths.
|
|
|
206 .IP "\fB\-w, \-\-WorkingDir\fR \fIdirname\fR" 4
|
|
|
207 .IX Item "-w, --WorkingDir dirname"
|
|
|
208 Location of working directory. Default: current directory.
|
|
|
209 .SH "EXAMPLES"
|
|
|
210 .IX Header "EXAMPLES"
|
|
|
211 To count number of sequences in sequence files, type:
|
|
|
212 .PP
|
|
|
213 .Vb 3
|
|
|
214 \& % InfoSequenceFiles.pl Sample1.fasta
|
|
|
215 \& % InfoSequenceFiles.pl Sample1.msf Sample1.aln Sample1.pir
|
|
|
216 \& % InfoSequenceFiles.pl *.fasta *.fta *.msf *.pir *.aln
|
|
|
217 .Ve
|
|
|
218 .PP
|
|
|
219 To list all available information with maximum level of available detail for a sequence
|
|
|
220 alignment file Sample1.msf, type:
|
|
|
221 .PP
|
|
|
222 .Vb 1
|
|
|
223 \& % InfoSequenceFiles.pl \-a \-d 3 Sample1.msf
|
|
|
224 .Ve
|
|
|
225 .PP
|
|
|
226 To list sequence length information after ignoring sequence gaps in Sample1.aln file, type:
|
|
|
227 .PP
|
|
|
228 .Vb 2
|
|
|
229 \& % InfoSequenceFiles.pl \-\-SequenceLengths \-\-IgnoreGaps Yes
|
|
|
230 \& Sample1.aln
|
|
|
231 .Ve
|
|
|
232 .PP
|
|
|
233 To list shortest and longest sequence length information after ignoring sequence
|
|
|
234 gaps in Sample1.aln file, type:
|
|
|
235 .PP
|
|
|
236 .Vb 2
|
|
|
237 \& % InfoSequenceFiles.pl \-\-longest \-\-shortest \-\-IgnoreGaps Yes
|
|
|
238 \& Sample1.aln
|
|
|
239 .Ve
|
|
|
240 .PP
|
|
|
241 To list distribution of sequence lengths after ignoring sequence gaps in Sample1.aln file and
|
|
|
242 report the frequency distribution into 10 bins, type:
|
|
|
243 .PP
|
|
|
244 .Vb 2
|
|
|
245 \& % InfoSequenceFiles.pl \-\-frequency \-\-FrequencyBins 10
|
|
|
246 \& \-\-IgnoreGaps Yes Sample1.aln
|
|
|
247 .Ve
|
|
|
248 .PP
|
|
|
249 To list distribution of sequence lengths after ignoring sequence gaps in Sample1.aln file and
|
|
|
250 report the frequency distribution into specified bin range, type:
|
|
|
251 .PP
|
|
|
252 .Vb 2
|
|
|
253 \& % InfoSequenceFiles.pl \-\-frequency \-\-FrequencyBins
|
|
|
254 \& "150,200,250,300,350" \-\-IgnoreGaps Yes Sample1.aln
|
|
|
255 .Ve
|
|
|
256 .SH "AUTHOR"
|
|
|
257 .IX Header "AUTHOR"
|
|
|
258 Manish Sud <msud@san.rr.com>
|
|
|
259 .SH "SEE ALSO"
|
|
|
260 .IX Header "SEE ALSO"
|
|
|
261 AnalyzeSequenceFilesData.pl, ExtractFromSequenceFiles.pl, InfoAminoAcids.pl, InfoNucleicAcids.pl
|
|
|
262 .SH "COPYRIGHT"
|
|
|
263 .IX Header "COPYRIGHT"
|
|
|
264 Copyright (C) 2015 Manish Sud. All rights reserved.
|
|
|
265 .PP
|
|
|
266 This file is part of MayaChemTools.
|
|
|
267 .PP
|
|
|
268 MayaChemTools is free software; you can redistribute it and/or modify it under
|
|
|
269 the terms of the \s-1GNU\s0 Lesser General Public License as published by the Free
|
|
|
270 Software Foundation; either version 3 of the License, or (at your option)
|
|
|
271 any later version.
|
