scoremat.asn

ncbi源码

--$Id: scoremat.asn,v 1000.1 2004/04/12 17:26:09 gouriano Exp $
-- ===========================================================================
--
--                            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.
--
-- ===========================================================================
--
-- Author:  Christiam Camacho
--
-- File Description:
--      ASN.1 definitions for scoring matrix
--
-- ===========================================================================
-- $Log: scoremat.asn,v $
-- Revision 1000.1  2004/04/12 17:26:09  gouriano
-- PRODUCTION: UPGRADED [CATCHUP_003] Dev-tree R1.7
--
-- Revision 1.7  2004/02/23 15:42:24  camacho
-- 1. Gave default value to Score-matrix::byrow field
-- 2. Updated documentation
--
-- Revision 1.6  2003/08/25 19:03:28  bauer
-- added raw frequencies and weights as optional score-matrix components
--
-- Revision 1.5  2003/06/16 12:19:56  madden
-- Do not use Blast4-ka-block, other changes worked out with structure group
--
-- Revision 1.2  2002/12/03 14:01:45  camacho
-- Data type changes
--
-- Revision 1.1  2002/12/02 22:15:27  camacho
-- Initial revision
--
-- ===========================================================================

NCBI-ScoreMat DEFINITIONS ::= BEGIN

EXPORTS    Score-matrix, Score-matrix-parameters;
    
IMPORTS    Object-id   FROM NCBI-General
           Seq-entry   FROM NCBI-Seqset;

-- a rudimentary block/core-model, to be used with block-based alignment routines 
-- and threading

BlockProperty ::= SEQUENCE {
  type     INTEGER { unassigned  (0),
                     threshold   (1),       -- score threshold for heuristics
		     minscore    (2),       -- observed minimum score in CD
		     maxscore    (3),       -- observed maximum score in CD
		     meanscore   (4),       -- observed mean score in CD
		     variance    (5),       -- observed score variance
		     name       (10),       -- just name the block
		     is-optional(20),       -- block may not have to be used    
                     other     (255) },
  intvalue  INTEGER OPTIONAL,
  textvalue VisibleString OPTIONAL
}

CoreBlock ::= SEQUENCE {
  start          INTEGER,                   -- begin of block on query
  stop           INTEGER,                   -- end of block on query
  minstart       INTEGER OPTIONAL,          -- optional N-terminal extension
  maxstop        INTEGER OPTIONAL,          -- optional C-terminal extension
  property       SEQUENCE OF BlockProperty OPTIONAL
}

LoopConstraint ::= SEQUENCE {
  minlength      INTEGER DEFAULT 0,         -- minimum length of unaligned region
  maxlength      INTEGER DEFAULT 100000     -- maximum length of unaligned region
}

CoreDef ::= SEQUENCE {
  nblocks        INTEGER,                   -- number of core elements/blocks
  blocks         SEQUENCE OF CoreBlock,     -- nblocks locations
  loops          SEQUENCE OF LoopConstraint -- (nblocks+1) constraints 
}

-- Scoring matrix that allows to store symmetric and non-symmetric matrices
-- (PSSMs).
--
-- Column indices on the PSSM refer to the positions corresponding to the
-- query/master sequence, i.e. the number of columns (N) is the same
-- as the length of the query/master sequence. 
-- Row indices refer to individual amino acid types, i.e. the number of 
-- rows (M) is the same as the number of different residues in the 
-- alphabet we use. Consequently, row labels are amino acid identifiers.
--
-- PSSMs are stored as linear arrays of integers. By default, we store
-- them column-by-column, M values for the first column followed by M
-- values for the second column, and so on. In order to provide
-- flexibility for external applications, the boolean field "byrow" is 
-- provided to specify the storage order.

Score-matrix ::= SEQUENCE {
    is-protein   BOOLEAN,	-- Is the matrix for proteins
    identifier   Object-id,	-- name of matrix (e.g., "blosum62") or number
    comments     SEQUENCE OF VisibleString OPTIONAL, -- comments on matrix.

    -- The dimensions of the matrix are returned so the client can
    -- verify that all data was received.  Both dimensions are returned for
    -- non-symmetric matrices (psi-blast uses these).
    nrows        INTEGER,	-- number of rows
    ncolumns     INTEGER,	-- number of columns

    -- row-labels is given to note the order of residue types so that it can
    -- be cross-checked between applications.
    -- If this field is not given, the matrix values are presented in 
    -- order of the alphabet ncbistdaa is used for protein, ncbi4na for nucl.
    -- for proteins the values returned correspond to 
    -- (-,-), (-,A), (-,B), (-,C) ... (A,-), (A,A), (A,B), (A,C) ...
    row-labels   SEQUENCE OF VisibleString OPTIONAL,

    -- values of scoring matrix. Non-symmetric matrices are stored as described
    -- by the byrow field
    scores       SEQUENCE OF INTEGER OPTIONAL, 
    -- are matrices stored row by row?
    byrow        BOOLEAN DEFAULT FALSE, 

    -- pseudocount constant used for PSSM
    pseudocounts INTEGER OPTIONAL,             

    -- PSSM representative sequence (master) 
    query        Seq-entry OPTIONAL,           

    -- frequencies observed in alignment
    rawFreqs     SEQUENCE OF INTEGER OPTIONAL, 

    -- residue frequencies
    posFreqs     SEQUENCE OF INTEGER OPTIONAL, 

    -- sequence weights for individual cells
    weights      SEQUENCE OF INTEGER OPTIONAL, 

    -- frequencies used in pseudocount method
    freq-Ratios  INTEGER { unassigned  (0),
                           blosum62    (1),
                           blosum45    (2),
                           blosum80    (3),
                           blosum50    (4),
                           blosum90    (5),
                           pam30       (6),
                           pam70       (7),
                           pam250      (8),
                           other     (255)
                         } OPTIONAL,           

    -- scaling factor for the scores
    score-scale-factor INTEGER OPTIONAL,       
    -- scaling factor for the frequencies
    posFreqs-scale-factor INTEGER OPTIONAL,    
    -- scaling factor for frequencies
    rawFreqs-scale-factor INTEGER OPTIONAL,    
    -- and their scaling factor
    weights-scale-factor INTEGER OPTIONAL,     

    -- scaled by score-scale-factor (above)
    gapOpen      INTEGER OPTIONAL,             
    -- scaled by score-scale-factor (above)
    gapExtend    INTEGER OPTIONAL
}

-- Envelope containing matrix or pssm, Karlin-Altschul parameters, and block constraints.

Score-matrix-parameters ::= SEQUENCE {
	matrix		Score-matrix,	
        lambda          REAL OPTIONAL,
	kappa           REAL OPTIONAL,
	h               REAL OPTIONAL,
	constraints	CoreDef OPTIONAL
}

END