1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
|
.\" Automatically generated by Pod::Man 2.23 (Pod::Simple 3.14)
.\"
.\" Standard preamble:
.\" ========================================================================
.de Sp \" Vertical space (when we can't use .PP)
.if t .sp .5v
.if n .sp
..
.de Vb \" Begin verbatim text
.ft CW
.nf
.ne \\$1
..
.de Ve \" End verbatim text
.ft R
.fi
..
.\" Set up some character translations and predefined strings. \*(-- will
.\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left
.\" double quote, and \*(R" will give a right double quote. \*(C+ will
.\" give a nicer C++. Capital omega is used to do unbreakable dashes and
.\" therefore won't be available. \*(C` and \*(C' expand to `' in nroff,
.\" nothing in troff, for use with C<>.
.tr \(*W-
.ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p'
.ie n \{\
. ds -- \(*W-
. ds PI pi
. if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch
. if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\" diablo 12 pitch
. ds L" ""
. ds R" ""
. ds C` ""
. ds C' ""
'br\}
.el\{\
. ds -- \|\(em\|
. ds PI \(*p
. ds L" ``
. ds R" ''
'br\}
.\"
.\" Escape single quotes in literal strings from groff's Unicode transform.
.ie \n(.g .ds Aq \(aq
.el .ds Aq '
.\"
.\" If the F register is turned on, we'll generate index entries on stderr for
.\" titles (.TH), headers (.SH), subsections (.SS), items (.Ip), and index
.\" entries marked with X<> in POD. Of course, you'll have to process the
.\" output yourself in some meaningful fashion.
.ie \nF \{\
. de IX
. tm Index:\\$1\t\\n%\t"\\$2"
..
. nr % 0
. rr F
.\}
.el \{\
. de IX
..
.\}
.\"
.\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2).
.\" Fear. Run. Save yourself. No user-serviceable parts.
. \" fudge factors for nroff and troff
.if n \{\
. ds #H 0
. ds #V .8m
. ds #F .3m
. ds #[ \f1
. ds #] \fP
.\}
.if t \{\
. ds #H ((1u-(\\\\n(.fu%2u))*.13m)
. ds #V .6m
. ds #F 0
. ds #[ \&
. ds #] \&
.\}
. \" simple accents for nroff and troff
.if n \{\
. ds ' \&
. ds ` \&
. ds ^ \&
. ds , \&
. ds ~ ~
. ds /
.\}
.if t \{\
. ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u"
. ds ` \\k:\h'-(\\n(.wu*8/10-\*(#H)'\`\h'|\\n:u'
. ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'^\h'|\\n:u'
. ds , \\k:\h'-(\\n(.wu*8/10)',\h'|\\n:u'
. ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'|\\n:u'
. ds / \\k:\h'-(\\n(.wu*8/10-\*(#H)'\z\(sl\h'|\\n:u'
.\}
. \" troff and (daisy-wheel) nroff accents
.ds : \\k:\h'-(\\n(.wu*8/10-\*(#H+.1m+\*(#F)'\v'-\*(#V'\z.\h'.2m+\*(#F'.\h'|\\n:u'\v'\*(#V'
.ds 8 \h'\*(#H'\(*b\h'-\*(#H'
.ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\*(#H)/2u'\v'-.3n'\*(#[\z\(de\v'.3n'\h'|\\n:u'\*(#]
.ds d- \h'\*(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\*(#H'
.ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'|\\n:u'
.ds th \*(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u*2/3)'\s-1o\s+1\*(#]
.ds Th \*(#[\s+2I\s-2\h'-\w'I'u*3/5'\v'-.3m'o\v'.3m'\*(#]
.ds ae a\h'-(\w'a'u*4/10)'e
.ds Ae A\h'-(\w'A'u*4/10)'E
. \" corrections for vroff
.if v .ds ~ \\k:\h'-(\\n(.wu*9/10-\*(#H)'\s-2\u~\d\s+2\h'|\\n:u'
.if v .ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'\v'-.4m'^\v'.4m'\h'|\\n:u'
. \" for low resolution devices (crt and lpr)
.if \n(.H>23 .if \n(.V>19 \
\{\
. ds : e
. ds 8 ss
. ds o a
. ds d- d\h'-1'\(ga
. ds D- D\h'-1'\(hy
. ds th \o'bp'
. ds Th \o'LP'
. ds ae ae
. ds Ae AE
.\}
.rm #[ #] #H #V #F C
.\" ========================================================================
.\"
.IX Title "TFBS::Word::Consensus 3"
.TH TFBS::Word::Consensus 3 "2005-01-04" "perl v5.12.4" "User Contributed Perl Documentation"
.\" For nroff, turn off justification. Always turn off hyphenation; it makes
.\" way too many mistakes in technical documents.
.if n .ad l
.nh
.SH "NAME"
TFBS::Word \- IUPAC DNA consensus word\-based pattern class
=head1 DESCRIPTION
.PP
TFBS::Word is a base class consisting of universal constructor called by
its subclasses (TFBS::Matrix::*), and word pattern manipulation methods that
are independent of the word type. It is not meant to be instantiated itself.
.SH "FEEDBACK"
.IX Header "FEEDBACK"
Please send bug reports and other comments to the author.
.SH "AUTHOR \- Boris Lenhard"
.IX Header "AUTHOR - Boris Lenhard"
Boris Lenhard <Boris.Lenhard@cgb.ki.se>
.SH "APPENDIX"
.IX Header "APPENDIX"
The rest of the documentation details each of the object
methods. Internal methods are preceded with an underscore.
.SS "new"
.IX Subsection "new"
.Vb 8
\& Title : new
\& Usage : my $pwm = TFBS::Matrix::PWM\->new(%args)
\& Function: constructor for the TFBS::Matrix::PWM object
\& Returns : a new TFBS::Matrix::PWM object
\& Args : # you must specify the \-word argument:
\& \-word, # a strig consisting of letters in
\& # IUPAC degenerate DNA alphabet
\& # (any of ACGTSWKMPYBDHVN)
\&
\& #######
\&
\& \-name, # string, OPTIONAL
\& \-ID, # string, OPTIONAL
\& \-class, # string, OPTIONAL
\& \-tags # a hash reference reference, OPTIONAL
.Ve
.SS "search_seq"
.IX Subsection "search_seq"
.Vb 6
\& Title : search_seq
\& Usage : my $siteset = $pwm\->search_seq(%args)
\& Function: scans a nucleotide sequence with the pattern represented
\& by the PWM
\& Returns : a TFBS::SiteSet object
\& Args : # you must specify either one of the following three:
\&
\& \-file, # the name od a fasta file (single sequence)
\& #or
\& \-seqobj # a Bio::Seq object
\& # (more accurately, a Bio::PrimarySeqobject or a
\& # subclass thereof)
\& #or
\& \-seqstring # a string containing the sequence
\&
\& \-max_mismatches, # number of allowed positions in the site that do
\& # not match the consensus
\& # OPTIONAL: default 0
.Ve
.SS "search_aln"
.IX Subsection "search_aln"
.Vb 10
\& Title : search_aln
\& Usage : my $site_pair_set = $pwm\->search_aln(%args)
\& Function: Scans a pairwise alignment of nucleotide sequences
\& with the pattern represented by the word: it reports only
\& those hits that are present in equivalent positions of both
\& sequences and exceed a specified threshold score in both, AND
\& are found in regions of the alignment above the specified
\& conservation cutoff value.
\& Returns : a TFBS::SitePairSet object
\& Args : # you must specify either one of the following three:
\&
\& \-file, # the name of the alignment file in Clustal
\& format
\& #or
\& \-alignobj # a Bio::SimpleAlign object
\& # (more accurately, a Bio::PrimarySeqobject or a
\& # subclass thereof)
\& #or
\& \-alignstring # a multi\-line string containing the alignment
\& # in clustal format
\& #############
\&
\& \-max_mismatches, # number of allowed positions in the site that do
\& # not match the consensus
\& # OPTIONAL: default 0
\&
\& \-window, # size of the sliding window (inn nucleotides)
\& # for calculating local conservation in the
\& # alignment
\& # OPTIONAL: default 50
\&
\& \-cutoff # conservation cutoff (%) for including the
\& # region in the results of the pattern search
\& # OPTIONAL: default "70%"
.Ve
.SS "to_PWM"
.IX Subsection "to_PWM"
.SS "validate_word"
.IX Subsection "validate_word"
.SS "length"
.IX Subsection "length"
|
