This file is indexed.

/usr/lib/ncbi/schema/insdc.vschema is in sra-toolkit 2.1.7a-1ubuntu2.

This file is owned by root:root, with mode 0o644.

The actual contents of the file can be viewed below.

  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
/*===========================================================================
*
*                            PUBLIC DOMAIN NOTICE
*               National Center for Biotechnology Information
*
*  This software/database is a "United States Government Work" under the
*  terms of the United States Copyright Act.  It was written as part of
*  the author's official duties as a United States Government employee and
*  thus cannot be copyrighted.  This software/database is freely available
*  to the public for use. The National Library of Medicine and the U.S.
*  Government have not placed any restriction on its use or reproduction.
*
*  Although all reasonable efforts have been taken to ensure the accuracy
*  and reliability of the software and data, the NLM and the U.S.
*  Government do not and cannot warrant the performance or results that
*  may be obtained by using this software or data. The NLM and the U.S.
*  Government disclaim all warranties, express or implied, including
*  warranties of performance, merchantability or fitness for any particular
*  purpose.
*
*  Please cite the author in any work or product based on this material.
*
* ===========================================================================
*
*/

/*==========================================================================
 * INSDC types, constants
 */
version 1;


/*--------------------------------------------------------------------------
 * dna
 *  represented in IUPAC characters
 */
typedef ascii INSDC:dna:text;


/*--------------------------------------------------------------------------
 * 4na
 *  nucleotide data with all possible ambiguity
 *  does not represent all possible EVENTS
 *
 *  text encodings use the IUPAC character set
 *  legal values: [ACMGRSVTWYHKDBNacmgrsvtwyhkdbn.]
 *  canonical values: [ACMGRSVTWYHKDBN]
 *
 *  binary values are 0..15 = { NACMGRSVTWYHKDBN }
 *
 *  4na values use bits for each letter:
 *
 *       A | C | G | T
 *    =================
 *    N    |   |   |
 *    A  * |   |   |
 *    C    | * |   |
 *    M  * | * |   |
 *    G    |   | * |
 *    R  * |   | * |
 *    S    | * | * |
 *    V  * | * | * |
 *    T    |   |   | *
 *    W  * |   |   | *
 *    Y    | * |   | *
 *    H  * | * |   | *
 *    K    |   | * | *
 *    D  * |   | * | *
 *    B    | * | * | *
 *    N  * | * | * | *
 */
typedef	U8 INSDC:4na:bin;
typedef	B1 INSDC:4na:packed [ 4 ];

const INSDC:4na:bin INSDC:4na:map:BINSET
    = [ 0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15 ];
const INSDC:dna:text INSDC:4na:map:CHARSET
    = ".ACMGRSVTWYHKDBN";
const INSDC:dna:text INSDC:4na:accept:CHARSET
    = ".ACMGRSVTWYHKDBNacmgrsvtwyhkdbn";


/*--------------------------------------------------------------------------
 * 2na  - nucleotide data A,T,G,C
 * x2na - nucleotide data extended with single ambiguity value (N)
 *
 *  text encodings use the IUPAC character set
 *  legal values: [ACGTNacgtn.]
 *  canonical values: [ACGTN]
 *
 *  x2na values are 0..4 = { ACGTN }
 *
 *  2na values exclude N:
 *    A = 0
 *    C = 1
 *    G = 2
 *    T = 3
 */
typedef U8 INSDC:2na:bin;
typedef U8 INSDC:x2na:bin;
typedef B1 INSDC:2na:packed [ 2 ];

const INSDC:2na:bin  INSDC:2na:map:BINSET      = [ 0,1,2,3 ];
const INSDC:dna:text INSDC:2na:map:CHARSET     = "ACGT";
const INSDC:dna:text INSDC:2na:accept:CHARSET  = "ACGTacgt";
const INSDC:x2na:bin INSDC:x2na:map:BINSET     = [ 0,1,2,3,4 ];
const INSDC:dna:text INSDC:x2na:map:CHARSET    = "ACGTN";
const INSDC:dna:text INSDC:x2na:accept:CHARSET = "ACGTNacgtn.";


/*--------------------------------------------------------------------------
 * color - color-space text
 * 2cs   - color-space data 0,1,2,3
 * x2cs  - color-space data extended with single ambiguity value (.)
 *
 *  text encodings use the ASCII numeric character set
 *  values: [0123.]
 *
 *  x2cs values are 0..4 = { 0123. }
 *
 *  2cs values exclude '.':
 *    '0' = 0
 *    '1' = 1
 *    '2' = 2
 *    '3' = 3
 */
typedef ascii INSDC:color:text;
typedef U8 INSDC:2cs:bin;
typedef U8 INSDC:x2cs:bin;
typedef B1 INSDC:2cs:packed [ 2 ];

const INSDC:2cs:bin  INSDC:2cs:map:BINSET        = [ 0,1,2,3 ];
const INSDC:color:text INSDC:2cs:map:CHARSET     = "0123";
const INSDC:color:text INSDC:2cs:accept:CHARSET  = "0123";
const INSDC:x2cs:bin INSDC:x2cs:map:BINSET       = [ 0,1,2,3,4 ];
const INSDC:color:text INSDC:x2cs:map:CHARSET    = "0123.";
const INSDC:color:text INSDC:x2cs:accept:CHARSET = "0123.";

const U8 INSDC:color:default_matrix =
[
    0, 1, 2, 3, 4,
    1, 0, 3, 2, 4,
    2, 3, 0, 1, 4,
    3, 2, 1, 0, 4,
    4, 4, 4, 4, 4
];


/*--------------------------------------------------------------------------
 * protein
 *  represented in IUPAC characters
 */
typedef ascii INSDC:protein:text;


/*--------------------------------------------------------------------------
 * aa
 *  protein data
 *  text encodings use the IUPAC character set
 */
typedef	U8 INSDC:aa:bin;

const INSDC:aa:bin INSDC:aa:map:BINSET
    = [ 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 ];
const INSDC:protein:text INSDC:aa:map:CHARSET
    = "ABCDEFGHIKLMNPQRSTVWXYZU*";
const INSDC:protein:text INSDC:aa:accept:CHARSET
    = "ABCDEFGHIKLMNPQRSTVWXYZU*abcdefghiklmnpqrstvwxyzu";


/*--------------------------------------------------------------------------
 * quality
 *  quality scoring values
 *
 *  phred legal values: 0..63
 */
typedef U8 INSDC:quality:phred;
typedef I8 INSDC:quality:log_odds;

// text-encoding of quality scores
// offsets are 33 = '!' and 64 = '@'
typedef ascii INSDC:quality:text:phred_33;
typedef ascii INSDC:quality:text:phred_64;
typedef ascii INSDC:quality:text:log_odds_64;


/*--------------------------------------------------------------------------
 * coordinate
 *  zero and one based coordinates
 */

// 32 bit coordinates
typedef I32 INSDC:coord:val;
typedef U32 INSDC:coord:len;

// zero or one based coordinate system
typedef INSDC:coord:val INSDC:coord:zero;
typedef INSDC:coord:val INSDC:coord:one;

// POSITION types for relating bases to their location in signal
typedef INSDC:coord:zero INSDC:position:zero;
typedef INSDC:coord:one INSDC:position:one;