libncbi-vdb2 2.8.2-2+dfsg-1build1 / usr / lib / ncbi-vdb / insdc / seq.vschema

/*===========================================================================
*
*                            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.
*
* ===========================================================================
*
*/

/*==========================================================================
 * Sequence schema
 */
version 1;

include '/usr/lib/ncbi-vdb/vdb/vdb.vschema';
include '/usr/lib/ncbi-vdb/insdc/insdc.vschema';


/*--------------------------------------------------------------------------
 * rand_4na_2na
 *  converts 4na to 2na
 *
 *  substitutes a random base for ambiguities
 *  from the bases allowed in the 4na.
 *
 *       A | C | G | T
 *    =================
 *    N    |   |   |     # any base may be substituted
 *    A  * |   |   |     # always A
 *    C    | * |   |     # always C
 *    M  * | * |   |     # A or C
 *    G    |   | * |     # always G
 *    R  * |   | * |     # A or G
 *    S    | * | * |     # C or G
 *    V  * | * | * |     # A, C or G
 *    T    |   |   | *   # always T
 *    W  * |   |   | *   # A or T
 *    Y    | * |   | *   # C or T
 *    H  * | * |   | *   # A, C or T
 *    K    |   | * | *   # G or T
 *    D  * |   | * | *   # A, G or T
 *    B    | * | * | *   # C, G or T
 *    N  * | * | * | *   # any base may be substituted
 */
extern function
    INSDC:2na:bin INSDC:SEQ:rand_4na_2na #1 ( INSDC:4na:bin rd_bin );


/*--------------------------------------------------------------------------
 * sequence
 *  basic sequence table
 *
 * history:
 *  1.0.1 - introduced text-mode QUALITY columns
 */
table INSDC:tbl:sequence #1.0.1
{
    /* READ
     *  native or converted DNA sequence
     */

    // default is IUPAC character representation
    extern default column INSDC:dna:text READ
    {
        read = out_dna_text;
        validate = < INSDC:dna:text > compare ( in_dna_text, out_dna_text );
    }

    // 4na representation - unpacked and packed
    extern column INSDC:4na:bin READ = out_4na_bin;
    extern column INSDC:4na:packed READ = out_4na_packed;

    // x2na representation - 2na with ambiguity
    extern column INSDC:x2na:bin READ = out_x2na_bin;

    // 2na representation - 2na with no ambiguity - unpacked and packed
    extern column INSDC:2na:bin READ = out_2na_bin;
    extern column INSDC:2na:packed READ = out_2na_packed;



    /* CSREAD
     *  native or converted color-space sequence
     */

    // default is ASCII character representation
    extern default column INSDC:color:text CSREAD
    {
        read = out_color_text;
        validate = < INSDC:color:text > compare ( in_color_text, out_color_text );
    }

    // x2cs representation - 2cs with ambiguity
    extern column INSDC:x2cs:bin CSREAD = out_x2cs_bin;

    // 2cs representation - 2cs with no ambiguity - unpacked and packed
    extern column INSDC:2cs:bin CSREAD = out_2cs_bin;
    extern column INSDC:2cs:packed CSREAD = out_2cs_packed;

    /* CS_NATIVE
     *  is color-space the native sequence space
     */
    readonly column bool CS_NATIVE = cs_native;

    /* CS_KEY
     *  leading call given in base-space
     */
    extern column INSDC:dna:text CS_KEY
    {
        read = out_cs_key;
        validate = < INSDC:dna:text > compare ( in_cs_key, out_cs_key );
    }

    /* COLOR_MATRIX
     *  matrix used for color-space conversions
     */
    extern column U8 COLOR_MATRIX = out_color_matrix;


    /* QUALITY
     *  base or color call qualities
     */

    // PHRED is default
    extern default column INSDC:quality:phred QUALITY = out_qual_phred;

    // textual encodings
    extern column INSDC:quality:text:phred_33 QUALITY
        = out_qual_text_phred_33
        | ( INSDC:quality:text:phred_33 ) < B8 > sum < 33 > ( out_qual_phred );
    extern column INSDC:quality:text:phred_64 QUALITY
        = out_qual_text_phred_64
        | ( INSDC:quality:text:phred_64 ) < B8 > sum < 64 > ( out_qual_phred );


    /* SIGNAL
     *  signal and intensity information is unspecified
     */
    INSDC:coord:len signal_len
        = ( INSDC:coord:len ) row_len ( out_signal )
        | < INSDC:coord:len > echo < 0 > ();
    

	/* VIRTUAL PRODUCTIONS
	 *  cs_native
	 *  in_cs_key
	 *  out_cs_key
	 *  out_signal
	 *  in_dna_text
	 *  out_2cs_bin
	 *  out_2na_bin
	 *  out_4na_bin
	 *  out_dna_text
	 *  out_x2cs_bin
	 *  out_x2na_bin
	 *  in_color_text
	 *  out_2cs_packed
	 *  out_2na_packed
	 *  out_4na_packed
	 *  out_color_text
	 *  out_qual_phred
	 *  out_color_matrix
	 */
};


/*--------------------------------------------------------------------------
 * protein
 *  basic protein sequence table
 */
table INSDC:tbl:protein #1
{
    /* PROTEIN
     *  native or converted protein sequence
     */

    // default is IUPAC character representation
    extern default column INSDC:protein:text PROTEIN
    {
        read = out_protein_text;
        validate = < INSDC:protein:text > compare ( in_protein_text, out_protein_text );
    }

    // aa representation
    extern column INSDC:aa:bin PROTEIN = out_aa_bin;


	/* INSDC:tbl:protein productions
	 *  out_aa_bin
	 *  in_protein_text
	 *  out_protein_text
	 */
};