|
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 "SEQUENCEFILEUTIL 1"
|
|
|
127 .TH SEQUENCEFILEUTIL 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 SequenceFileUtil
|
|
|
134 .SH "SYNOPSIS"
|
|
|
135 .IX Header "SYNOPSIS"
|
|
|
136 use SequenceFileUtil ;
|
|
|
137 .PP
|
|
|
138 use SequenceFileUtil qw(:all);
|
|
|
139 .SH "DESCRIPTION"
|
|
|
140 .IX Header "DESCRIPTION"
|
|
|
141 \&\fBSequenceFileUtil\fR module provides the following functions:
|
|
|
142 .PP
|
|
|
143 AreSequenceLengthsIdentical, CalcuatePercentSequenceIdentity,
|
|
|
144 CalculatePercentSequenceIdentityMatrix, GetLongestSequence, GetSequenceLength,
|
|
|
145 GetShortestSequence, IsClustalWSequenceFile, IsGapResidue, IsMSFSequenceFile,
|
|
|
146 IsPIRFastaSequenceFile, IsPearsonFastaSequenceFile, IsSupportedSequenceFile,
|
|
|
147 ReadClustalWSequenceFile, ReadMSFSequenceFile, ReadPIRFastaSequenceFile,
|
|
|
148 ReadPearsonFastaSequenceFile, ReadSequenceFile, RemoveSequenceAlignmentGapColumns,
|
|
|
149 RemoveSequenceGaps, WritePearsonFastaSequenceFile
|
|
|
150 SequenceFileUtil module provides various methods to process sequence
|
|
|
151 files and retreive appropriate information.
|
|
|
152 .SH "FUNCTIONS"
|
|
|
153 .IX Header "FUNCTIONS"
|
|
|
154 .IP "\fBAreSequenceLengthsIdentical\fR" 4
|
|
|
155 .IX Item "AreSequenceLengthsIdentical"
|
|
|
156 .Vb 1
|
|
|
157 \& $Status = AreSequenceLengthsIdentical($SequencesDataRef);
|
|
|
158 .Ve
|
|
|
159 .Sp
|
|
|
160 Checks the lengths of all the sequences available in \fISequencesDataRef\fR and returns 1
|
|
|
161 or 0 based whether lengths of all the sequence is same.
|
|
|
162 .IP "\fBCalcuatePercentSequenceIdentity\fR" 4
|
|
|
163 .IX Item "CalcuatePercentSequenceIdentity"
|
|
|
164 .Vb 3
|
|
|
165 \& $PercentIdentity =
|
|
|
166 \& AreSequenceLengthsIdenticalAreSequenceLengthsIdentical(
|
|
|
167 \& $Sequence1, $Sequence2, [$IgnoreGaps, $Precision]);
|
|
|
168 .Ve
|
|
|
169 .Sp
|
|
|
170 Returns percent identity between \fISequence1\fR and \fISequence2\fR. Optional arguments
|
|
|
171 \&\fIIgnoreGaps\fR and \fIPrecision\fR control handling of gaps in sequences and precision of the
|
|
|
172 returned value. By default, gaps are ignored and precision is set up to 1 decimal.
|
|
|
173 .IP "\fBCalculatePercentSequenceIdentityMatrix\fR" 4
|
|
|
174 .IX Item "CalculatePercentSequenceIdentityMatrix"
|
|
|
175 .Vb 3
|
|
|
176 \& $IdentityMatrixDataRef = CalculatePercentSequenceIdentityMatrix(
|
|
|
177 \& $SequencesDataRef, [$IgnoreGaps,
|
|
|
178 \& $Precision]);
|
|
|
179 .Ve
|
|
|
180 .Sp
|
|
|
181 Calculate pairwise percent identity between all the sequences available in \fISequencesDataRef\fR
|
|
|
182 and returns a reference to identity matrix hash. Optional arguments \fIIgnoreGaps\fR and
|
|
|
183 \&\fIPrecision\fR control handling of gaps in sequences and precision of the returned value. By default, gaps
|
|
|
184 are ignored and precision is set up to 1 decimal.
|
|
|
185 .IP "\fBGetSequenceLength\fR" 4
|
|
|
186 .IX Item "GetSequenceLength"
|
|
|
187 .Vb 1
|
|
|
188 \& $SeqquenceLength = GetSequenceLength($Sequence, [$IgnoreGaps]);
|
|
|
189 .Ve
|
|
|
190 .Sp
|
|
|
191 Returns length of the specified sequence. Optional argument \fIIgnoreGaps\fR controls handling
|
|
|
192 of gaps. By default, gaps are ignored.
|
|
|
193 .IP "\fBGetShortestSequence\fR" 4
|
|
|
194 .IX Item "GetShortestSequence"
|
|
|
195 .Vb 2
|
|
|
196 \& ($ID, $Sequence, $SeqLen, $Description) = GetShortestSequence(
|
|
|
197 \& $SequencesDataRef, [$IgnoreGaps]);
|
|
|
198 .Ve
|
|
|
199 .Sp
|
|
|
200 Checks the lengths of all the sequences available in \f(CW$SequencesDataRef\fR and returns \f(CW$ID\fR,
|
|
|
201 \&\f(CW$Sequence\fR, \f(CW$SeqLen\fR, and \f(CW$Description\fR values for the shortest sequence. Optional arguments \f(CW$IgnoreGaps\fR
|
|
|
202 controls handling of gaps in sequences. By default, gaps are ignored.
|
|
|
203 .IP "\fBGetLongestSequence\fR" 4
|
|
|
204 .IX Item "GetLongestSequence"
|
|
|
205 .Vb 2
|
|
|
206 \& ($ID, $Sequence, $SeqLen, $Description) = GetLongestSequence(
|
|
|
207 \& $SequencesDataRef, [$IgnoreGaps]);
|
|
|
208 .Ve
|
|
|
209 .Sp
|
|
|
210 Checks the lengths of all the sequences available in \fISequencesDataRef\fR and returns \fB\s-1ID\s0\fR,
|
|
|
211 \&\fBSequence\fR, \fBSeqLen\fR, and \fBDescription\fR values for the longest sequence. Optional argument
|
|
|
212 $\fIIgnoreGaps\fR controls handling of gaps in sequences. By default, gaps are ignored.
|
|
|
213 .IP "\fBIsGapResidue\fR" 4
|
|
|
214 .IX Item "IsGapResidue"
|
|
|
215 .Vb 1
|
|
|
216 \& $Status = AreSequenceLengthsIdentical($Residue);
|
|
|
217 .Ve
|
|
|
218 .Sp
|
|
|
219 Returns 1 or 0 based on whether \fIResidue\fR corresponds to a gap. Any character other than A to Z is
|
|
|
220 considered a gap residue.
|
|
|
221 .IP "\fBIsSupportedSequenceFile\fR" 4
|
|
|
222 .IX Item "IsSupportedSequenceFile"
|
|
|
223 .Vb 1
|
|
|
224 \& $Status = IsSupportedSequenceFile($SequenceFile);
|
|
|
225 .Ve
|
|
|
226 .Sp
|
|
|
227 Returns 1 or 0 based on whether \fISequenceFile\fR corresponds to a supported sequence
|
|
|
228 format.
|
|
|
229 .IP "\fBIsClustalWSequenceFile\fR" 4
|
|
|
230 .IX Item "IsClustalWSequenceFile"
|
|
|
231 .Vb 1
|
|
|
232 \& $Status = IsClustalWSequenceFile($SequenceFile);
|
|
|
233 .Ve
|
|
|
234 .Sp
|
|
|
235 Returns 1 or 0 based on whether \fISequenceFile\fR corresponds to Clustal sequence alignment
|
|
|
236 format.
|
|
|
237 .IP "\fBIsPearsonFastaSequenceFile\fR" 4
|
|
|
238 .IX Item "IsPearsonFastaSequenceFile"
|
|
|
239 .Vb 1
|
|
|
240 \& $Status = IsPearsonFastaSequenceFile($SequenceFile);
|
|
|
241 .Ve
|
|
|
242 .Sp
|
|
|
243 Returns 1 or 0 based on whether \fISequenceFile\fR corresponds to Pearson \s-1FASTA\s0 sequence
|
|
|
244 format.
|
|
|
245 .IP "\fBIsPIRFastaSequenceFile\fR" 4
|
|
|
246 .IX Item "IsPIRFastaSequenceFile"
|
|
|
247 .Vb 1
|
|
|
248 \& $Status = IsPIRFastaSequenceFile($SequenceFile);
|
|
|
249 .Ve
|
|
|
250 .Sp
|
|
|
251 Returns 1 or 0 based on whether \fISequenceFile\fR corresponds to \s-1PIR\s0 \s-1FASTA\s0 sequence
|
|
|
252 format.
|
|
|
253 .IP "\fBIsMSFSequenceFile\fR" 4
|
|
|
254 .IX Item "IsMSFSequenceFile"
|
|
|
255 .Vb 1
|
|
|
256 \& $Status = IsClustalWSequenceFile($SequenceFile);
|
|
|
257 .Ve
|
|
|
258 .Sp
|
|
|
259 Returns 1 or 0 based on whether \fISequenceFile\fR corresponds to \s-1MSF\s0 sequence alignment
|
|
|
260 format.
|
|
|
261 .IP "\fBReadSequenceFile\fR" 4
|
|
|
262 .IX Item "ReadSequenceFile"
|
|
|
263 .Vb 1
|
|
|
264 \& $SequenceDataMapRef = ReadSequenceFile($SequenceFile);
|
|
|
265 .Ve
|
|
|
266 .Sp
|
|
|
267 Reads \fISequenceFile\fR and returns reference to a hash containing following key/value
|
|
|
268 pairs:
|
|
|
269 .Sp
|
|
|
270 .Vb 5
|
|
|
271 \& $SequenceDataMapRef\->{IDs} \- Array of sequence IDs
|
|
|
272 \& $SequenceDataMapRef\->{Count} \- Number of sequences
|
|
|
273 \& $SequenceDataMapRef\->{Description}{$ID} \- Sequence description
|
|
|
274 \& $SequenceDataMapRef\->{Sequence}{$ID} \- Sequence for a specific ID
|
|
|
275 \& $SequenceDataMapRef\->{Sequence}{InputFileType} \- File format
|
|
|
276 .Ve
|
|
|
277 .IP "\fBReadClustalWSequenceFile\fR" 4
|
|
|
278 .IX Item "ReadClustalWSequenceFile"
|
|
|
279 .Vb 1
|
|
|
280 \& $SequenceDataMapRef = ReadClustalWSequenceFile($SequenceFile);
|
|
|
281 .Ve
|
|
|
282 .Sp
|
|
|
283 Reads ClustalW \fISequenceFile\fR and returns reference to a hash containing following key/value
|
|
|
284 pairs as describes in \fBReadSequenceFile\fR method.
|
|
|
285 .IP "\fBReadMSFSequenceFile\fR" 4
|
|
|
286 .IX Item "ReadMSFSequenceFile"
|
|
|
287 .Vb 1
|
|
|
288 \& $SequenceDataMapRef = ReadMSFSequenceFile($SequenceFile);
|
|
|
289 .Ve
|
|
|
290 .Sp
|
|
|
291 Reads \s-1MSF\s0 \fISequenceFile\fR and returns reference to a hash containing following key/value
|
|
|
292 pairs as describes in \fBReadSequenceFile\fR method.
|
|
|
293 .IP "\fBReadPIRFastaSequenceFile\fR" 4
|
|
|
294 .IX Item "ReadPIRFastaSequenceFile"
|
|
|
295 .Vb 1
|
|
|
296 \& $SequenceDataMapRef = ReadPIRFastaSequenceFile($SequenceFile);
|
|
|
297 .Ve
|
|
|
298 .Sp
|
|
|
299 Reads \s-1PIR\s0 \s-1FASTA\s0 \fISequenceFile\fR and returns reference to a hash containing following key/value
|
|
|
300 pairs as describes in \fBReadSequenceFile\fR method.
|
|
|
301 .IP "\fBReadPearsonFastaSequenceFile\fR" 4
|
|
|
302 .IX Item "ReadPearsonFastaSequenceFile"
|
|
|
303 .Vb 1
|
|
|
304 \& $SequenceDataMapRef = ReadPearsonFastaSequenceFile($SequenceFile);
|
|
|
305 .Ve
|
|
|
306 .Sp
|
|
|
307 Reads Pearson \s-1FASTA\s0 \fISequenceFile\fR and returns reference to a hash containing following key/value
|
|
|
308 pairs as describes in \fBReadSequenceFile\fR method.
|
|
|
309 .IP "\fBRemoveSequenceGaps\fR" 4
|
|
|
310 .IX Item "RemoveSequenceGaps"
|
|
|
311 .Vb 1
|
|
|
312 \& $SeqWithoutGaps = RemoveSequenceGaps($Sequence);
|
|
|
313 .Ve
|
|
|
314 .Sp
|
|
|
315 Removes gaps from \fISequence\fR and return a sequence without any gaps.
|
|
|
316 .IP "\fBRemoveSequenceAlignmentGapColumns\fR" 4
|
|
|
317 .IX Item "RemoveSequenceAlignmentGapColumns"
|
|
|
318 .Vb 2
|
|
|
319 \& $NewAlignmentDataMapRef = RemoveSequenceAlignmentGapColumns(
|
|
|
320 \& $AlignmentDataMapRef);
|
|
|
321 .Ve
|
|
|
322 .Sp
|
|
|
323 Using input alignment data map ref containing following keys, generate a new hash with
|
|
|
324 same set of keys after residue columns containg only gaps have been removed:
|
|
|
325 .Sp
|
|
|
326 .Vb 4
|
|
|
327 \& {IDs} : Array of IDs in order as they appear in file
|
|
|
328 \& {Count}: ID count
|
|
|
329 \& {Description}{$ID} : Description data
|
|
|
330 \& {Sequence}{$ID} : Sequence data
|
|
|
331 .Ve
|
|
|
332 .IP "\fBWritePearsonFastaSequenceFile\fR" 4
|
|
|
333 .IX Item "WritePearsonFastaSequenceFile"
|
|
|
334 .Vb 2
|
|
|
335 \& WritePearsonFastaSequenceFile($SequenceFileName, $SequenceDataRef,
|
|
|
336 \& [$MaxLength]);
|
|
|
337 .Ve
|
|
|
338 .Sp
|
|
|
339 Using sequence data specified via \fISequenceDataRef\fR, write out a Pearson \s-1FASTA\s0 sequence
|
|
|
340 file. Optional argument \fIMaxLength\fR controls maximum length sequence in each line; default is
|
|
|
341 80.
|
|
|
342 .SH "AUTHOR"
|
|
|
343 .IX Header "AUTHOR"
|
|
|
344 Manish Sud <msud@san.rr.com>
|
|
|
345 .SH "SEE ALSO"
|
|
|
346 .IX Header "SEE ALSO"
|
|
|
347 PDBFileUtil.pm
|
|
|
348 .SH "COPYRIGHT"
|
|
|
349 .IX Header "COPYRIGHT"
|
|
|
350 Copyright (C) 2015 Manish Sud. All rights reserved.
|
|
|
351 .PP
|
|
|
352 This file is part of MayaChemTools.
|
|
|
353 .PP
|
|
|
354 MayaChemTools is free software; you can redistribute it and/or modify it under
|
|
|
355 the terms of the \s-1GNU\s0 Lesser General Public License as published by the Free
|
|
|
356 Software Foundation; either version 3 of the License, or (at your option)
|
|
|
357 any later version.
|
