|  line  | 
 stmt  | 
 bran  | 
 cond  | 
 sub  | 
 pod  | 
 time  | 
 code  | 
| 
1
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 =head1 NAME  | 
| 
2
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
3
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 Bio::Util::AA - Basic Amino Acid utilities  | 
| 
4
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
5
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 =head1 SYNOPSES  | 
| 
6
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
7
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
  use Bio::Util::AA qw(:all)  | 
| 
8
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
9
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 =head1 DESCRIPTION  | 
| 
10
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
11
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 Provides a set of functions and predefined variables which  | 
| 
12
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 are handy when working with Amino Acids.  | 
| 
13
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
14
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 =cut  | 
| 
15
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
16
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 package Bio::Util::AA;  | 
| 
17
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
18
 | 
1
 | 
 
 | 
 
 | 
  
1
  
 | 
 
 | 
23987
 | 
 use strict;  | 
| 
 
 | 
1
 | 
 
 | 
 
 | 
 
 | 
 
 | 
2
 | 
    | 
| 
 
 | 
1
 | 
 
 | 
 
 | 
 
 | 
 
 | 
31
 | 
    | 
| 
19
 | 
1
 | 
 
 | 
 
 | 
  
1
  
 | 
 
 | 
5
 | 
 use warnings;  | 
| 
 
 | 
1
 | 
 
 | 
 
 | 
 
 | 
 
 | 
2
 | 
    | 
| 
 
 | 
1
 | 
 
 | 
 
 | 
 
 | 
 
 | 
28
 | 
    | 
| 
20
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
21
 | 
1
 | 
 
 | 
 
 | 
  
1
  
 | 
 
 | 
859
 | 
 use version; our $VERSION = qv('0.1.6');  | 
| 
 
 | 
1
 | 
 
 | 
 
 | 
 
 | 
 
 | 
2931
 | 
    | 
| 
 
 | 
1
 | 
 
 | 
 
 | 
 
 | 
 
 | 
7
 | 
    | 
| 
22
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
23
 | 
1
 | 
 
 | 
 
 | 
  
1
  
 | 
 
 | 
82
 | 
 use Exporter 'import';  | 
| 
 
 | 
1
 | 
 
 | 
 
 | 
 
 | 
 
 | 
2
 | 
    | 
| 
 
 | 
1
 | 
 
 | 
 
 | 
 
 | 
 
 | 
416
 | 
    | 
| 
24
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
25
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 our @EXPORT_OK = qw(  | 
| 
26
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
   %ambiguous_forward  | 
| 
27
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
   %ambiguous_map  | 
| 
28
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
   %aa_abbrev  | 
| 
29
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
30
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
   $aas  | 
| 
31
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
   $aa_match  | 
| 
32
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
   $aa_fail  | 
| 
33
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
   $strict_aas  | 
| 
34
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
   $strict_match  | 
| 
35
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
   $strict_fail  | 
| 
36
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
   $ambigs  | 
| 
37
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
   $ambig_match  | 
| 
38
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
   $ambig_fail  | 
| 
39
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 );  | 
| 
40
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
41
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 our %EXPORT_TAGS = (  | 
| 
42
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     all   => \@EXPORT_OK,  | 
| 
43
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     funcs => [qw()]  | 
| 
44
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 );  | 
| 
45
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
46
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 =head1 VARIABLES  | 
| 
47
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
48
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 =cut  | 
| 
49
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
50
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 =head2 AMBIGUOUS MAPPINGS  | 
| 
51
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
52
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 Two ambiguous mapping hashes. One maps from the amino acid  | 
| 
53
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 forward to the possible ambiguous amino acid, and one is a  | 
| 
54
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 map of what each ambiguous amino acid means.  | 
| 
55
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
56
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 =cut  | 
| 
57
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
58
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 our %ambiguous_forward = (  | 
| 
59
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     A => 'B',  | 
| 
60
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     B => 'B',  | 
| 
61
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     D => 'B',  | 
| 
62
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     I => 'J',  | 
| 
63
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     J => 'J',  | 
| 
64
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     L => 'J',  | 
| 
65
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     E => 'Z',  | 
| 
66
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     Q => 'Z',  | 
| 
67
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     Z => 'Z'  | 
| 
68
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 );  | 
| 
69
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
70
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 our %ambiguous_map = (  | 
| 
71
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     B => [ 'A', 'D' ],  | 
| 
72
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     J => [ 'I', 'L' ],  | 
| 
73
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     Z => [ 'E', 'Q' ]  | 
| 
74
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 );  | 
| 
75
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
76
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 =head2 %aa_abbrev  | 
| 
77
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
78
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 Hash from one letter code for amino acids to the three  | 
| 
79
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 letter abbreviations. Includes ambiguous amino acids as well  | 
| 
80
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 as selenocysteine and pyrrolysine.  | 
| 
81
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
82
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 =cut  | 
| 
83
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
84
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 our %aa_abbrev = (  | 
| 
85
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     A => 'Ala',  | 
| 
86
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     B => 'Asx',  | 
| 
87
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     C => 'Cys',  | 
| 
88
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     D => 'Asp',  | 
| 
89
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     E => 'Glu',  | 
| 
90
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     F => 'Phe',  | 
| 
91
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     G => 'Gly',  | 
| 
92
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     H => 'His',  | 
| 
93
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     I => 'Ile',  | 
| 
94
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     J => 'Xle',  | 
| 
95
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     K => 'Lys',  | 
| 
96
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     L => 'Leu',  | 
| 
97
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     M => 'Met',  | 
| 
98
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     N => 'Asn',  | 
| 
99
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     O => 'Pyl',  | 
| 
100
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     P => 'Pro',  | 
| 
101
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     Q => 'Gln',  | 
| 
102
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     R => 'Arg',  | 
| 
103
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     S => 'Ser',  | 
| 
104
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     T => 'Thr',  | 
| 
105
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     U => 'Sec',  | 
| 
106
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     V => 'Val',  | 
| 
107
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     W => 'Trp',  | 
| 
108
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     X => 'Xaa',  | 
| 
109
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     Y => 'Tyr',  | 
| 
110
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     Z => 'Glx'  | 
| 
111
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 );  | 
| 
112
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
113
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 =head2 BASIC VARIABLES  | 
| 
114
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
115
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 Basic useful amino acid variables. A list of valid  | 
| 
116
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 characters for amino acids, a stricter list containing just  | 
| 
117
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 the 20 common ones and *, and another list containing the  | 
| 
118
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 ambiguous amino acids. Also associated precompiled  | 
| 
119
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 regular expressions.  | 
| 
120
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
121
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 =cut  | 
| 
122
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
123
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 our $aas     = '*ABCDEFGHIJKLMNOPQRSTUVWXYZ';  | 
| 
124
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 our $aa_match = qr/[$aas]/i;  | 
| 
125
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 our $aa_fail  = qr/[^$aas]/i;  | 
| 
126
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
127
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 our $strict_aas   = '*ACDEFGHIKLMNPQRSTVWXY';  | 
| 
128
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 our $strict_match = qr/[$strict_aas]/i;  | 
| 
129
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 our $strict_fail  = qr/[^$strict_aas]/i;  | 
| 
130
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
131
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 our $ambigs     = 'BJZ';  | 
| 
132
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 our $ambig_match = qr/[$ambigs]/i;  | 
| 
133
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 our $ambig_fail  = qr/[^$ambigs]/i;  | 
| 
134
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
135
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 1;  | 
| 
136
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
137
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 =head1 AUTHOR  | 
| 
138
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
139
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 Kevin Galinsky,   | 
| 
140
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
141
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 =head1 COPYRIGHT AND LICENSE  | 
| 
142
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
143
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 Copyright (c) 2010-2011, Broad Institute.  | 
| 
144
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
145
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 Copyright (c) 2008-2009, J. Craig Venter Institute.  | 
| 
146
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
147
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 This program is free software; you can redistribute it and/or modify it  | 
| 
148
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 under the same terms as Perl itself.  | 
| 
149
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
150
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 =cut  |