sra-toolkit 2.1.7a-1ubuntu2 / usr / lib / ncbi / schema / abi.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.
*
* ===========================================================================
*
*/

/*==========================================================================
 * NCBI ABI Sequence Read Archive schema
 */
version 1;

include 'ncbi/sra.vschema';
include 'ncbi/spotname.vschema';


/*--------------------------------------------------------------------------
 * NCBI:SRA:ABI
 *  ABI SRA Platform
 */

/* tokenize_spot_name
 *  scans name on input
 *  tokenizes into parts
 */
extern function NCBI:SRA:spot_name_token
    NCBI:SRA:ABI:tokenize_spot_name #1 ( ascii name );


/* NCBI:SRA:ABI:common
 *  basic table interface based upon ABI's pipelines
 *
 * history:
 *  1.0.1 - base explicitly upon changes to sra #1.0.1
 *  1.0.2 - base explicitly upon sra #1.0.2
 *  1.0.3 - base explicitly upon sra #1.0.3
 */
table NCBI:SRA:ABI:common #1.0.3 = INSDC:SRA:tbl:sra #1.0.3
{
    // platform name is always 'ABSOLID'
    ascii platform_name
        = < ascii > echo < "ABSOLID" > ();

    /* TRIMMED SEQUENCE
     *  need to find the 0-based trim_start and trim_len
     */
    INSDC:coord:zero bio_start = NCBI:SRA:bio_start ( out_read_start, out_read_type );
    INSDC:coord:zero trim_start = bio_start;
    U32 trim_left = ( U32 ) trim_start;
    INSDC:coord:len trim_len = ( INSDC:coord:len ) < U32 > diff ( spot_len, trim_left );

    /* COORDINATES
     *  in addition to X and Y,
     *  ABI has PANEL
     */
    column INSDC:coord:val PANEL = out_panel_coord;

    // signal
    column NCBI:fsamp4 SIGNAL
        = out_signal;

    NCBI:fsamp4 out_signal = ( NCBI:fsamp4 )
        < NCBI:SRA:swapped_fsamp4 > NCBI:SRA:swap ( out_signal_swapped, out_x2cs_bin );


	/* INSDC:tbl:sequence inherited productions
	 *  cs_native
	 *  in_cs_key
	 *  out_cs_key
	 *  out_signal_swapped
	 *  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
	 */

	/* INSDC:SRA:tbl:spotname inherited productions
	 *  out_x_coord
	 *  out_y_coord
	 *  out_name_fmt
	 *  out_spot_name
	 *  spot_ids_found
	 */

	/* INSDC:SRA:tbl:spotdesc inherited productions
	 *  out_label
	 *  out_nreads
	 *  out_read_len
	 *  out_label_len
	 *  out_rd_filter
	 *  out_read_type
	 *  out_read_start
	 *  out_label_start
	 *  static_fixed_spot_len
	 */

	/* INSDC:SRA:tbl:stats inherited productions
	 *  base_count
	 *  spot_count
	 *  max_spot_id
	 *  min_spot_id
	 *  in_stats_bin
	 *  bio_base_count
	 */

	/* INSDC:SRA:tbl:sra inherited productions
	 *  out_platform
	 */

	/* NCBI:SRA:ABI:common productions
	 *  out_panel_coord
	 */
};


/* NCBI:SRA:ABI:tbl:v2 #1
 *  normalized v2 table
 *
 * history:
 *  1.0.1 - changes to sra #1.0.1
 *  1.0.2 - changes to common #1.0.2
 *  1.0.3 - sra #2.1.2, color_space #2.0.2, common #1.0.3
 *  1.0.4 - updated ancestry
 */
physical NCBI:SRA:swapped_fsamp4 NCBI:SRA:ABI:encoding:SIGNAL #2
{
    decode { return NCBI:SRA:fsamp4:decode #2 ( @ ); }
    encode { return NCBI:SRA:fsamp4:encode #2 < 14, 10 > ( @ ); }
}

table NCBI:SRA:ABI:tbl:v2 #1.0.4
    = NCBI:SRA:tbl:sra #2.1.3
    , NCBI:tbl:color_space #2.1.0
    , NCBI:tbl:phred_quality #2.0.3
    , NCBI:SRA:ABI:common #1.0.3
{
    /* NAME tokenizing and coordinates
     *  most work happens in skeyname table
     *  we still obtain PANEL from name
     */
    INSDC:coord:val out_panel_coord = ( INSDC:coord:val )
        NCBI:SRA:extract_name_coord < NCBI:SRA:name_token:T > ( _out_name, out_spot_name_tok );
    NCBI:SRA:spot_name_token out_spot_name_tok
        = NCBI:SRA:ABI:tokenize_spot_name ( _out_name );

    NCBI:SRA:spot_name_token in_spot_name_tok
        = NCBI:SRA:ABI:tokenize_spot_name ( NAME );


    /* SIGNAL
     *  optional, no longer archived
     */

    // support for individual color inputs
    extern column NCBI:fsamp1 FTC
    {
        read = out_ftc;
        validate = < F32 > no_compare #1 ( in_ftc, out_ftc );
    }
    NCBI:fsamp1 in_ftc = FTC;
    NCBI:fsamp1 out_ftc
        = ( NCBI:fsamp1 ) < F32 > cut < 0 > ( out_signal );

    extern column NCBI:fsamp1 FAM
    {
        read = out_fam;
        validate = < F32 > no_compare #1 ( in_fam, out_fam );
    }
    NCBI:fsamp1 in_fam = FAM;
    NCBI:fsamp1 out_fam
        = ( NCBI:fsamp1 ) < F32 > cut < 0 > ( out_signal );

    extern column NCBI:fsamp1 CY3
    {
        read = out_cy3;
        validate = < F32 > no_compare #1 ( in_cy3, out_cy3 );
    }
    NCBI:fsamp1 in_cy3 = CY3;
    NCBI:fsamp1 out_cy3
        = ( NCBI:fsamp1 ) < F32 > cut < 1 > ( out_signal );

    extern column NCBI:fsamp1 TXR
    {
        read = out_txr;
        validate = < F32 > no_compare #1 ( in_txr, out_txr );
    }
    NCBI:fsamp1 in_txr = TXR;
    NCBI:fsamp1 out_txr
        = ( NCBI:fsamp1 ) < F32 > cut < 2 > ( out_signal );

    extern column NCBI:fsamp1 CY5
    {
        read = out_cy5;
        validate = < F32 > no_compare #1 ( in_cy5, out_cy5 );
    }
    NCBI:fsamp1 in_cy5 = CY5;
    NCBI:fsamp1 out_cy5
        = ( NCBI:fsamp1 ) < F32 > cut < 3 > ( out_signal );

    // intermediate input (writing) production
    NCBI:fsamp4 in_signal
        = SIGNAL
        | ( NCBI:fsamp4 ) < F32 > paste ( in_ftc, in_cy3, in_txr, in_cy5 )
        | ( NCBI:fsamp4 ) < F32 > paste ( in_fam, in_cy3, in_txr, in_cy5 );

    // overridden output production
    NCBI:SRA:swapped_fsamp4 out_signal_swapped = .SIGNAL;

    // rule for writing SIGNAL
    physical column NCBI:SRA:ABI:encoding:SIGNAL #2 .SIGNAL
        = ( NCBI:SRA:swapped_fsamp4 ) < NCBI:fsamp4 > NCBI:SRA:swap ( in_signal, in_x2cs_bin )
        | ( NCBI:SRA:swapped_fsamp4 ) < NCBI:fsamp4 > NCBI:SRA:swap ( in_signal, in_2cs_bin );
};