comparison libs/sratoolkit.2.8.0-centos_linux64/schema/csra2/reference.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.
*
* ===========================================================================
*
*/

/*==========================================================================
 * VDB Alignment types, functions and tables
 */
version 1;

include 'vdb/vdb.vschema';
include 'csra2/stats.vschema';


/*--------------------------------------------------------------------------
 * tables
 */
table NCBI:csra2:tbl:reference #1.0
    = NCBI:csra2:tbl:read_stats #1
{
    /* CHUNK_SIZE
     *  describes the maximum number of bases in any cell
     */
    extern column INSDC:coord:len CHUNK_SIZE;

    /* CIRCULAR
     *  true if the reference is circular
     */
    extern column bool CIRCULAR;

    /* CANONICAL_NAME
     *  this should be an accessioned proper name
     */
    extern column utf8 CANONICAL_NAME;

    /* COMMON_NAME
     *  this name may be ambiguous or missing entirely
     */
    extern column utf8 COMMON_NAME;

    /* LOCAL_SEQUENCE
     *  supports name overloading by type
     */
    extern default column INSDC:dna:text LOCAL_SEQUENCE
    {
        read = out_local_dna_text;
        validate = < INSDC:dna:text > compare ( in_local_dna_text, out_local_dna_text );
    }
    extern column INSDC:4na:bin LOCAL_SEQUENCE = out_local_4na_bin;

    /* PRIMARY_ALIGNMENT_IDS
     * SECONDARY_ALIGNMENT_IDS
     *  an index to rows in the PRIMARY_ALIGNMENT and
     *  SECONDARY_ALIGNMENT tables having alignments 
     *  STARTING within this chunk
     *
     *  the indicies MUST be sorted in clustered order,
     *  meaning that they are in ascending numeric order
     */
    extern column < I64 > izip_encoding PRIMARY_ALIGNMENT_IDS;
    extern column < I64 > izip_encoding SECONDARY_ALIGNMENT_IDS;

    /* OVERLAP_REF_POS
     *  min ( REF_POS ) for all alignments intersecting this chunk
     *  but starting in a previous chunk, where the stored position
     *  is in reference coordinates.
     *
     *  a value of 0 indicates that no alignments starting to
     *  the left of this chunk also intersect with it.
     */
    extern column < INSDC:coord:zero > izip_encoding OVERLAP_REF_POS;

    /* OVERLAP_REF_LEN
     *  max ( REF_POS + REF_LEN - CHUNK_START ) % CHUNK_SIZE
     *  for all alignments intersecting this chunk but starting
     *  in a previous chunk.
     *
     *  indicates the amount of this chunk that is needed by
     *  alignments not starting within chunk. so if a slice on
     *  this reference were to start at 100 bases into this chunk,
     *  for example, and the OVERLAP_REF_LEN were 100 or less, then
     *  there are no alignments from prior chunks that need to be
     *  considered.
     */
    extern column < INSDC:coord:len > izip_encoding OVERLAP_REF_LEN;

    /* COVERAGE
     *  graphing statistics for the chunk
     */

    // clipped at 255
    extern column < U8 > izip_encoding CGRAPH_HIGH;
    extern column < U8 > izip_encoding CGRAPH_LOW;

    // count of the number of mismatches in the chunk
    extern column < U32 > izip_encoding CGRAPH_MISMATCHES;

    // count of the number of inserts and deletes in the chunk
    extern column < U32 > izip_encoding CGRAPH_INDELS;


    /* writing rules */
    INSDC:dna:text in_local_dna_text
        = < INSDC:dna:text, INSDC:dna:text > map < '.acmgrsvtwyhkdbn','NACMGRSVTWYHKDBN' > ( LOCAL_SEQUENCE );
        ;
    INSDC:4na:bin in_local_4na_bin
        = < INSDC:4na:bin > range_validate < 0, 15 > ( LOCAL_SEQUENCE )
        | < INSDC:dna:text, INSDC:4na:bin > map < INSDC:4na:map:CHARSET, INSDC:4na:map:BINSET > ( in_local_dna_text )
        ;
    INSDC:2na:bin in_local_2na_bin
        = INSDC:SEQ:rand_4na_2na ( in_local_4na_bin )
        ;
    INSDC:4na:bin in_ambig_4na_bin
        = < INSDC:4na:bin, INSDC:4na:bin > map < INSDC:4na:map:BINSET, [ 15,0,0,3,0,5,6,7,0,9,10,11,12,13,14,15 ] > ( in_local_4na_bin );
        ;

    INSDC:4na:bin in_stats_seq = in_local_4na_bin;

    /* physical columns for sequence */
    physical column INSDC:2na:packed .LOCAL_SEQUENCE
        = ( INSDC:2na:packed ) pack ( in_local_2na_bin )
        ;
    physical column < INSDC:4na:bin > zip_encoding .LOCAL_AMBIGUITY
        = < INSDC:4na:bin > trim < 0, 0 > ( in_ambig_4na_bin )
        ;

    /* reading rules */
    INSDC:2na:packed out_local_2na_packed
        = .LOCAL_SEQUENCE
        ;
    INSDC:2na:bin out_local_2na_bin
        = ( INSDC:2na:bin ) unpack ( out_local_2na_packed )
        ;
    INSDC:4na:bin out_local_2na_4na_bin
        = < INSDC:2na:bin, INSDC:4na:bin > map < INSDC:2na:map:BINSET, [ 1, 2, 4, 8 ] > ( out_local_2na_bin );
        ;
    INSDC:4na:bin out_local_4na_bin
        = < INSDC:4na:bin > bit_or < ALIGN_RIGHT > ( out_local_2na_4na_bin, .LOCAL_AMBIGUITY )
        ;
    INSDC:dna:text out_local_dna_text
        = < INSDC:4na:bin, INSDC:dna:text > map < INSDC:4na:map:BINSET, INSDC:4na:map:CHARSET > ( out_local_4na_bin )
        ;


    INSDC:coord:len in_local_read_len
        = ( INSDC:coord:len ) row_len ( in_local_2na_bin )
        ;
    INSDC:SRA:xread_type in_local_read_type
        = < INSDC:SRA:xread_type > echo < SRA_READ_TYPE_BIOLOGICAL > ()
        ;
}


/*--------------------------------------------------------------------------
 * "views"
 */
table NCBI:csra2:view:reference #1.0
    = NCBI:csra2:tbl:reference #1.0
{
    /* EXTERNAL
     *  may need to be a function
     *  it can test the CANONICAL_NAME as in cSRA.v1,
     *  but if internal it can also check row_length of bases
     */
    readonly column bool EXTERNAL
        = < bool > exists < false > ( .LOCAL_SEQUENCE )
        | < bool > echo < true > ()
        ;

    /* SEQUENCE
     *  available as text, 4na, x2na, 2na
     */
    default readonly column INSDC:dna:text SEQUENCE
        = out_dna_text
        ;
    readonly column INSDC:4na:bin SEQUENCE
        = out_4na_bin
        ;
    readonly column INSDC:4na:packed SEQUENCE
        = ( INSDC:4na:packed ) pack ( out_4na_bin )
        ;
    readonly column INSDC:x2na:bin SEQUENCE
        = < INSDC:4na:bin, INSDC:x2na:bin > map < INSDC:4na:map:BINSET, [ 4,0,1,4,2,4,4,4,3,4,4,4,4,4,4,4 ] > ( out_4na_bin )
        ;
    readonly column INSDC:2na:bin SEQUENCE
        = out_2na_bin
        ;
    readonly column INSDC:2na:packed SEQUENCE
        = pack ( out_2na_bin )
        ;

    /* QUALITY
     * This is fake column for compatibility
     */
    readonly column INSDC:quality:phred QUALITY
        = out_qual_phred
        ;

    /* column aliases */
    readonly column INSDC:coord:len MAX_SEQ_LEN = .CHUNK_SIZE;
    readonly column ascii SEQ_ID = cast ( .CANONICAL_NAME );

    /* sequence productions */
    INSDC:4na:bin out_4na_bin
        = out_local_4na_bin
    // TODO:  | sub-select from external table
        ;

    INSDC:dna:text out_dna_text
        = < INSDC:4na:bin, INSDC:dna:text > map < INSDC:4na:map:BINSET, INSDC:4na:map:CHARSET > ( out_4na_bin )
        ;

    INSDC:2na:bin out_2na_bin
        = INSDC:SEQ:rand_4na_2na ( out_4na_bin )
        ;

    /* quality productions */
    INSDC:quality:phred out_qual_phred
        = < INSDC:quality:phred > echo < 30 > ( SEQUENCE )
        ;

    INSDC:quality:phred in_stats_qual_phred = out_qual_phred;
}