comparison libs/sratoolkit.2.8.0-centos_linux64/schema/ncbi/pnbrdb.vschema @ 3:38ad1130d077 draft

planemo upload commit a4fb57231f274270afbfebd47f67df05babffa4a-dirty

3:38ad1130d077

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

version 1;
include 'vdb/vdb.vschema';

/* PNBRDB
 *  the original flat-file pnbrdb structure was divided into two forks:
 *   1 - "hsp" containing full blastp hsps
 *   2 - "nbr" containing only pig->pig relationships with max score
 *
 *  each fork was organized into bin directories by "query" ( left-hand ) pig
 *  each bin contained entries for up to 1M query pigs with a numeric
 *  4 digit 1-based name generated as "( ( qpig - 1 ) / 1024 ) / 1024 + 1".
 *  this bin approach served as a primitive index.
 *
 *  within each bin directory, there are 1024 data files, where each data file
 *  represented 1024 query pigs. the file name incorporated a 4 digit 1-based
 *  file id generated as "( ( qpig - 1 ) / 1024 ) % 1024 + 1" making it possible
 *  to locate any entry by query pig within a 1024 entry neighborhood by using
 *  filesystem path alone.
 *
 *  within each data file, a fixed-size 1024-entry header gave the location of
 *  entries ordered according to the most common queries.
 *
 *  all basic data are contained within the "hsp" fork. the "nbr" fork served
 *  as a pre-calculated result of the query selecting all unique pig->pig pairs
 *  with their maximum score value.
 */

/* The vdb representation of the pnbrdb has two tables
 *  1. table with one row per qpig (i.e. qpig = row_id) and two columns:
 *     offset and count. Offset indicates row_id in the second table where the
 *     hsps for the qpig are stored and count indicates the number of these rows.
 *  2. table with these coulmns: spig, max_score and blob. The blob contains all
 *     segments for given (qpig, spig) pair.
 */

table NCBI:pnbr:table:qpig #1
{
    /* OFFSET
     *  start position of hsps for qpig = row_id in the hsp table.
     */
    extern column <U64> izip_encoding OFFSET;

    /* COUNT
     *  number of hsps for qpig = row_id in the hsp table.
     */
    extern column <U64> izip_encoding COUNT;
};

table NCBI:pnbr:table:hsp #1
{
    /* SPIG
     *  the subject pig column
     */
    extern column <U32> izip_encoding SPIG;

    /* MAX_SCORE
     *  max score between given query pig and subject pig
     */
    extern column <I32> izip_encoding MAX_SCORE;

    /* SEGMENTS
     *  blob for storing hsps for given qpig and spig.
     */
    extern column <B8> zip_encoding SEGMENTS;
};

database NCBI:pnbr:db:pnbr #1
{
    table NCBI:pnbr:table:qpig #1 QPIG_REFERENCE;
    table NCBI:pnbr:table:hsp #1 HSP;
};