/*===========================================================================
*
* 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.
*
* ===========================================================================
*
*/
/*==========================================================================
* General read table which will be inherited by others
*/
version 1;
include 'vdb/vdb.vschema';
include 'insdc/insdc.vschema';
include 'csra2/stats.vschema';
/*--------------------------------------------------------------------------
* tables
*/
table NCBI:csra2:tbl:read #1.0 = NCBI:csra2:tbl:read_stats #1
{
/* CHUNK_SZ
* describes the maximum number of bases in any row
*
* if present, allows a single sequence to be broken into multiple rows
* where this value gives the limit on the number of bases in any row.
*
* the sequence will be split across some number of rows, depending upon
* the value of CHUNK_SZ. if length ( seq ) > CHUNK_SZ, then there will
* be multiple rows, where all but the last will have a length of CHUNK_SZ.
* the last ( or only ) row will have a length of length(seq)%CHUNK_SIZE.
*/
extern column INSDC:coord:len CHUNK_SZ;
/* READ
* base calls
*/
// textual 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
extern column INSDC:4na:bin READ
= out_4na_bin
;
/* QUALITY
* phred-score quality values
*/
extern default column INSDC:quality:phred QUALITY
= out_qual_phred
;
extern column INSDC:quality:text:phred_33 QUALITY
= ( INSDC:quality:text:phred_33 ) < B8 > sum < 33 > ( out_qual_phred )
;
extern column INSDC:quality:text:phred_64 QUALITY
= ( INSDC:quality:text:phred_64 ) < B8 > sum < 64 > ( out_qual_phred )
;
/* ---------------------------- optional columns ---------------------------- */
/* RD_ID
* RD_GROUP
* reports group and id of current row
*/
extern column I64 RD_ID;
extern column ascii RD_GROUP;
/* RD_FILTER
* records filter value if used
*/
extern column INSDC:SRA:read_filter RD_FILTER;
/* ---------------------------- input rules ---------------------------- */
// input text
INSDC:dna:text in_dna_text
= < INSDC:dna:text, INSDC:dna:text > map < '.acmgrsvtwyhkdbn','NACMGRSVTWYHKDBN' > ( READ )
;
// input 4na bin
INSDC:4na:bin in_4na_bin
= < INSDC:4na:bin > range_validate < 0, 15 > ( READ )
| < INSDC:dna:text, INSDC:4na:bin > map < INSDC:4na:map:CHARSET, INSDC:4na:map:BINSET > ( in_dna_text )
;
// input 2na bin
INSDC:2na:bin in_2na_bin
= INSDC:SEQ:rand_4na_2na ( in_4na_bin )
;
// input 4na alt-read ( ambiguities )
INSDC:4na:bin in_alt_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_4na_bin )
;
// feed the statistics
INSDC:4na:bin in_stats_seq = in_4na_bin;
// quality
INSDC:quality:text:phred_33 in_qual_text_phred_33 = QUALITY;
INSDC:quality:text:phred_64 in_qual_text_phred_64 = QUALITY;
INSDC:quality:phred in_qual_phred
= QUALITY
| ( INSDC:quality:phred ) < B8 > diff < 33 > ( in_qual_text_phred_33 )
| ( INSDC:quality:phred ) < B8 > diff < 64 > ( in_qual_text_phred_64 )
;
// feed the statistics
INSDC:quality:phred in_stats_qual_phred = in_qual_phred;
ascii in_stats_read_group
= in_stats_spot_group
| RD_GROUP
;
/* ---------------------------- physical columns ---------------------------- */
physical column INSDC:2na:packed .READ
= ( INSDC:2na:packed ) pack ( in_2na_bin )
;
physical column < INSDC:4na:bin > zip_encoding .ALTREAD
= < INSDC:4na:bin > trim < 0, 0 > ( in_alt_4na_bin )
;
physical column < INSDC:quality:phred > delta_average_zip_encoding .QUALITY
= in_qual_phred
;
/* ---------------------------- output rules ---------------------------- */
// output 2na packed
INSDC:2na:packed out_2na_packed
= .READ
;
// output 2na bin
INSDC:2na:bin out_2na_bin
= ( INSDC:2na:bin ) unpack ( out_2na_packed )
;
// output 2na->4na bin
INSDC:4na:bin out_2na_4na_bin
= < INSDC:2na:bin, INSDC:4na:bin > map < INSDC:2na:map:BINSET, [ 1, 2, 4, 8 ] > ( out_2na_bin )
;
// output 4na bin
INSDC:4na:bin out_4na_bin
= < INSDC:4na:bin > bit_or < ALIGN_RIGHT > ( out_2na_4na_bin, .ALTREAD )
| out_2na_4na_bin
;
// output text
INSDC:dna:text out_dna_text
= < INSDC:4na:bin, INSDC:dna:text > map < INSDC:4na:map:BINSET, INSDC:4na:map:CHARSET > ( out_4na_bin )
;
// output quality
INSDC:quality:phred out_qual_phred
= .QUALITY
| < INSDC:quality:phred > echo < 30 > ( out_4na_bin )
;
}
/*--------------------------------------------------------------------------
* views
*/
table NCBI:csra2:view:read #1.0 =
NCBI:csra2:tbl:read #1.0
{
/* CHUNK_SIZE
* describes the maximum number of bases in any row
*
* if present, allows a single sequence to be broken into multiple rows
* where this value gives the limit on the number of bases in any row.
*
* the sequence will be split across some number of rows, depending upon
* the value of CHUNK_SIZE. if length ( seq ) > CHUNK_SIZE, then there will
* be multiple rows, where all but the last will have a length of CHUNK_SIZE.
* the last ( or only ) row will have a length of length(seq)%CHUNK_SIZE.
*/
readonly column INSDC:coord:len CHUNK_SIZE
= .CHUNK_SZ
| < INSDC:coord:len > echo < 0xFFFFFFFF > ()
;
/* READ
* generate remaining 4 types
*/
readonly column INSDC:4na:packed READ
= ( INSDC:4na:packed ) pack ( out_4na_bin )
;
readonly column INSDC:x2na:bin READ
= < 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 READ
= out_2na_bin
;
readonly column INSDC:2na:packed READ
= out_2na_packed
;
/* READ_ID
* READ_GROUP
* reports group and id of current row
*/
readonly column I64 READ_ID
= .RD_ID
| row_id ()
;
readonly column ascii READ_GROUP
= .RD_GROUP
| < ascii > echo < '' > ()
;
/* READ_FILTER
* records filter value if used
*/
readonly column INSDC:SRA:read_filter READ_FILTER
= .RD_FILTER
| < INSDC:SRA:read_filter > echo < SRA_READ_FILTER_PASS > ()
;
}