view libs/sratoolkit.2.8.0-centos_linux64/schema/ncbi/seq-graph.vschema @ 3:38ad1130d077 draft

planemo upload commit a4fb57231f274270afbfebd47f67df05babffa4a-dirty

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

/*==========================================================================
 * seq-graph style named annotations
 */
version 1;

include 'vdb/vdb.vschema';


/*--------------------------------------------------------------------------
 * types
 * constants
 */

// example usage of data type:
typedef utf8 NCBI:SeqGraph:sid;
typedef utf8 NCBI:SeqGraph:name;
typedef U32 NCBI:SeqGraph:len;
typedef U32 NCBI:SeqGraph:scale;
typedef I64 NCBI:SeqGraph:value;
typedef NCBI:SeqGraph:value NCBI:SeqGraph:start;
typedef NCBI:SeqGraph:value NCBI:SeqGraph:gr_q0;   // min
typedef NCBI:SeqGraph:value NCBI:SeqGraph:gr_q10;  // 10th quantile
typedef NCBI:SeqGraph:value NCBI:SeqGraph:gr_q50;  // median
typedef NCBI:SeqGraph:value NCBI:SeqGraph:gr_q90;  // 90th quantile
typedef NCBI:SeqGraph:value NCBI:SeqGraph:gr_q100; // max
typedef NCBI:SeqGraph:value NCBI:SeqGraph:gr_zoom_q0;   // min zoomed to 100bp segment
typedef NCBI:SeqGraph:value NCBI:SeqGraph:gr_zoom_q10;  // 10th quantile zoomed to 100bp segment
typedef NCBI:SeqGraph:value NCBI:SeqGraph:gr_zoom_q50;  // median zoomed to 100bp segment
typedef NCBI:SeqGraph:value NCBI:SeqGraph:gr_zoom_q90;  // 90th quantile zoomed to 100bp segment
typedef NCBI:SeqGraph:value NCBI:SeqGraph:gr_zoom_q100; // max zoomed to 100bp segment
typedef NCBI:SeqGraph:value NCBI:SeqGraph:gr_num_switches; // number of value switches in graph


/*-------------------------------------------------------------------------- 
 * tables
 */
table NCBI:SeqGraph:tbl:seqgraph #1.0
{
    /* SID
     * Sequence id (Accession.version).
     * Indexed.
     */
    extern column NCBI:SeqGraph:sid SID
        = ( NCBI:SeqGraph:sid ) idx:text:project #1.0 < 'sid' > ( .SID );
    physical column < NCBI:SeqGraph:sid > zip_encoding .SID
        = ( NCBI:SeqGraph:sid ) idx:text:insert #1.0 < 'sid' > ( SID );

    /* NAME
     * Sequence name (which resolves into SID using assembly information)
     * Indexed.
     */
    extern column NCBI:SeqGraph:name NAME
        = ( NCBI:SeqGraph:name ) idx:text:project #1.0 < 'name' > ( .NAME );
    physical column < NCBI:SeqGraph:name > zip_encoding .NAME
        = ( NCBI:SeqGraph:name ) idx:text:insert #1.0 < 'name' > ( NAME );

    /* START
     * Sequence offset for the segment saved in this row. 
     * In most cases this can be calculated from row id and LEN below.
     */
    extern column < NCBI:SeqGraph:start > izip_encoding START;

    /* LEN
     *  MAX_SEQ_LEN is used in our refseq schema
     *  CHUNK_SIZE might be preferred
     *  Mostly a constant ( = 5000), except for the last row for each sequence.
     */
    extern column < NCBI:SeqGraph:len > izip_encoding LEN;

    /* SCALE
     * Scaling factor for graph values.
     * Mostly needed in order to store values as integers when actual values
     * are real with a certain precision.
     */
    extern column < NCBI:SeqGraph:scale > izip_encoding SCALE;

    /* GRAPH
     * intensity values
     */
    extern column < NCBI:SeqGraph:value > izip_encoding GRAPH;


    /* GR_Q0
     * Minimal value for the row
     */
    extern column < NCBI:SeqGraph:gr_q0 > izip_encoding GR_Q0;


    /* GR_Q10
     * 10th quantile value for the row 
     */
    extern column < NCBI:SeqGraph:gr_q10 > izip_encoding GR_Q10;


    /* GR_Q50
     * Median value for the row 
     */
    extern column < NCBI:SeqGraph:gr_q50 > izip_encoding GR_Q50;


    /* GR_Q90
     * 90th quantile value for the row  
     */
    extern column < NCBI:SeqGraph:gr_q90 > izip_encoding GR_Q90;


    /* GR_Q100
     * Maximal value for the row
     */
    extern column < NCBI:SeqGraph:gr_q100 > izip_encoding GR_Q100;

    /* GR_ZOOM_Q0
     * Minimal values for 100bp segments of the graph chunk
     */
    extern column < NCBI:SeqGraph:gr_zoom_q0 > izip_encoding GR_ZOOM_Q0;


    /* GR_ZOOM_Q10
     * 10th quantile values for 100bp segments of the graph chunk
     */
    extern column < NCBI:SeqGraph:gr_zoom_q10 > izip_encoding GR_ZOOM_Q10;


    /* GR_ZOOM_Q50
     * Median values for 100bp segments of the graph chunk 
     */
    extern column < NCBI:SeqGraph:gr_zoom_q50 > izip_encoding GR_ZOOM_Q50;


    /* GR_ZOOM_Q90
     * 90th quantile values for 100bp segments of the graph chunk 
     */
    extern column < NCBI:SeqGraph:gr_zoom_q90 > izip_encoding GR_ZOOM_Q90;


    /* GR_ZOOM_Q100
     * Maximal values for 100bp segments of the graph chunk 
     */
    extern column < NCBI:SeqGraph:gr_zoom_q100 > izip_encoding GR_ZOOM_Q100;

    /* NUM_SWITCHES
     * Number of value switches within the graph. Helps client make the decision how better to
     * represent the graph in ASN.1 (Seq-graph or Seq-table).
     */
    extern column < NCBI:SeqGraph:gr_num_switches > izip_encoding NUM_SWITCHES;
};


database NCBI:SeqGraph:database:kmergraph #1.0
{
    table NCBI:SeqGraph:tbl:seqgraph #1.0 LEFT;
    table NCBI:SeqGraph:tbl:seqgraph #1.0 RIGHT;
    table NCBI:SeqGraph:tbl:seqgraph #1.0 SUM;
}