src/objects/mmdb1/mmdb1.asn
Go to the SVN repository for this file
Go to list of all specification files
--$Revision: 32084 $
--**********************************************************************
--
-- Biological Macromolecule 3-D Structure Data Types for MMDB,
-- A Molecular Modeling Database
--
-- Definitions for a biomolecular assembly and the MMDB database
--
-- By Hitomi Ohkawa, Jim Ostell, Chris Hogue, and Steve Bryant
--
-- National Center for Biotechnology Information
-- National Institutes of Health
-- Bethesda, MD 20894 USA
--
-- July 1995
--
--**********************************************************************
-- Contents of the MMDB database are currently based on files distributed by
-- the Protein Data Bank, PDB. These data are changed in form, as described
-- in this specification. To some extent they are also changed in content, in
-- that many data items implicit in PDB are made explicit, and others are
-- corrected or omitted as a consequence of validation checks. The semantics
-- of MMDB data items are indicated by comments within the specification below.
-- These comments explain in detail the manner in which data items from PDB
-- have been mapped into MMDB.
MMDB DEFINITIONS ::=
BEGIN
EXPORTS Biostruc, Biostruc-id, Biostruc-set, Biostruc-annot-set,
Biostruc-residue-graph-set;
IMPORTS Biostruc-graph, Biomol-descr, Residue-graph FROM MMDB-Chemical-graph
Biostruc-model FROM MMDB-Structural-model
Biostruc-feature-set FROM MMDB-Features
Pub FROM NCBI-Pub
Date, Object-id, Dbtag FROM NCBI-General;
-- A structure report or "biostruc" describes the components of a biomolecular
-- assembly in terms of their names and descriptions, and a chemical graph
-- giving atomic formula, connectivity and chirality. It also gives one or more
-- three-dimensional model structures, literally a mapping of the atoms,
-- residues and/or molecules of each component into a measured three-
-- dimensional space. Structure may also be described by named features, which
-- associate nodes in the chemical graph, or regions in space, with text or
-- numeric descriptors.
-- Note that a biostruc may also contain cross references to other databases,
-- including citations to relevant scientific literature. These cross
-- references use object types from other NCBI data specifications, which are
-- "imported" into MMDB, and not repeated in this specification.
Biostruc ::= SEQUENCE {
id SEQUENCE OF Biostruc-id,
descr SEQUENCE OF Biostruc-descr OPTIONAL,
chemical-graph Biostruc-graph,
features SEQUENCE OF Biostruc-feature-set OPTIONAL,
model SEQUENCE OF Biostruc-model OPTIONAL }
-- A Biostruc-id is a collection identifiers for the molecular assembly.
-- Mmdb-id's are NCBI-assigned, and are intended to be unique and stable
-- identifiers. Other-id's are synonyms.
Biostruc-id ::= CHOICE {
mmdb-id Mmdb-id,
other-database Dbtag,
local-id Object-id }
Mmdb-id ::= INTEGER
-- The description of a biostruc refers to both the reported chemical and
-- spatial structure of a biomolecular assembly. PDB-derived descriptors
-- which refer specifically to the chemical components or spatial structure
-- are not provided here, but instead as descriptors of the biostruc-graph or
-- biostruc-model. For PDB-derived structures the biostruc name is the PDB
-- id-code. PDB-derived citations appear as publications within the biostruc
-- description, and include a data-submission citation derived from PDB AUTHOR
-- records. Citations are described using the NCBI Pub specification.
Biostruc-descr ::= CHOICE {
name VisibleString,
pdb-comment VisibleString,
other-comment VisibleString,
history Biostruc-history,
attribution Pub }
-- The history of a biostruc indicates it's origin and it's update history
-- within MMDB, the NCBI-maintained molecular structure database.
Biostruc-history ::= SEQUENCE {
replaces Biostruc-replace OPTIONAL,
replaced-by Biostruc-replace OPTIONAL,
data-source Biostruc-source OPTIONAL }
Biostruc-replace ::= SEQUENCE {
id Biostruc-id,
date Date }
-- The origin of a biostruc is a reference to another database. PDB release
-- date and PDB-assigned id codes are recorded here, as are the PDB-assigned
-- entry date and replacement history.
Biostruc-source ::= SEQUENCE {
name-of-database VisibleString,
version-of-database CHOICE {
release-date Date,
release-code VisibleString } OPTIONAL,
database-entry-id Biostruc-id,
database-entry-date Date,
database-entry-history SEQUENCE OF VisibleString OPTIONAL}
-- A biostruc set is a means to collect ASN.1 data for many biostrucs in
-- one file, as convenient for application programs. The object type is not
-- inteded to imply similarity of the biostrucs grouped together.
Biostruc-set ::= SEQUENCE {
id SEQUENCE OF Biostruc-id OPTIONAL,
descr SEQUENCE OF Biostruc-descr OPTIONAL,
biostrucs SEQUENCE OF Biostruc }
-- A biostruc annotation set is a means to collect ASN.1 data for biostruc
-- features into one file. The object type is intended as a means to store
-- feature annotation of similar type, such as "core" definitions for a
-- threading program, or structure-structure alignments for a structure-
-- similarity browser.
Biostruc-annot-set ::= SEQUENCE {
id SEQUENCE OF Biostruc-id OPTIONAL,
descr SEQUENCE OF Biostruc-descr OPTIONAL,
features SEQUENCE OF Biostruc-feature-set }
-- A biostruc residue graph set is a collection of residue graphs. The object
-- type is intended as a means to record dictionaries containing the chemical
-- subgraphs of "standard" residue types, which are used as a means to
-- simplify discription of the covalent structure of a biomolecular assembly.
-- The standard residue graph dictionary supplied with the MMDB database
-- contains 20 standard L amino acids and 8 standard ribonucleotide groups.
-- These graphs are complete, including explicit hydrogen atoms and separate
-- instances for the terminal polypeptide and polynucleotide residues.
Biostruc-residue-graph-set ::= SEQUENCE {
id SEQUENCE OF Biostruc-id OPTIONAL,
descr SEQUENCE OF Biomol-descr OPTIONAL,
residue-graphs SEQUENCE OF Residue-graph }
END
--**********************************************************************
--
-- Biological Macromolecule 3-D Structure Data Types for MMDB,
-- A Molecular Modeling Database
--
-- Definitions for a chemical graph
--
-- By Hitomi Ohkawa, Jim Ostell, Chris Hogue and Steve Bryant
--
-- National Center for Biotechnology Information
-- National Institutes of Health
-- Bethesda, MD 20894 USA
--
-- July, 1995
--
--**********************************************************************
MMDB-Chemical-graph DEFINITIONS ::=
BEGIN
EXPORTS Biostruc-graph, Biomol-descr, Residue-graph,
Molecule-id, PCSubstance-id, Residue-id, Atom-id;
IMPORTS Pub FROM NCBI-Pub
BioSource FROM NCBI-BioSource
Seq-id FROM NCBI-Seqloc
Biostruc-id FROM MMDB;
-- A biostruc graph contains the complete chemical graph of the biomolecular
-- assembly. The assembly graph is defined hierarchically, in terms of
-- subgraphs graphs of component molecules. For PDB-derived biostrucs,
-- the molecules forming the assembly are the individual biopolymer chains and
-- any non-polymer or "heterogen" groups which are present.
-- The PDB-derived "compound name" field appears as the name within the
-- biostruc-graph description. PDB "class" and "source" fields appear as
-- explicit attributes. PDB-derived structures are assigned an assembly type
-- of "other" unless they have been further classified as the "physiological
-- form" or "crystallographic cell" contents. If they have, the source of the
-- type classification appears as a citation within the assembly description.
-- Note that the biostruc-graph also includes as literals the subgraphs of
-- any nonstandard residues present within it. For PDB-derived biostrucs these
-- subgraphs are constructed automatically, with validation as described below.
Biostruc-graph ::= SEQUENCE {
descr SEQUENCE OF Biomol-descr OPTIONAL,
molecule-graphs SEQUENCE OF Molecule-graph,
inter-molecule-bonds SEQUENCE OF Inter-residue-bond OPTIONAL,
residue-graphs SEQUENCE OF Residue-graph OPTIONAL }
-- A biomolecule description refers to the chemical structure of a molecule or
-- component substructures. This descriptor type is used at the level of
-- assemblies, molecules and residues, and also for residue-graph dictionaries.
-- The BioSource object type is drawn from NCBI taxonomy data specifications,
-- and is not repeated here.
Biomol-descr ::= CHOICE {
name VisibleString,
pdb-class VisibleString,
pdb-source VisibleString,
pdb-comment VisibleString,
other-comment VisibleString,
organism BioSource,
attribution Pub,
assembly-type INTEGER { physiological-form(1),
crystallographic-cell(2),
other(255) },
molecule-type INTEGER { dna(1),
rna(2),
protein(3),
other-biopolymer(4),
solvent(5),
other-nonpolymer(6),
other(255) } }
-- A molecule chemical graph is defined by a sequence of residues. Nonpolymers
-- are described in the same way, but may contain only a single residue.
-- Biopolymer molecules are identified within PDB entries according to their
-- appearance on SEQRES records, which formally define a biopolymer as such.
-- Biopolymers are defined by the distinction between ATOM and HETATM
-- coordinate records only in cases where the chemical sequence from SEQRES
-- is in conflict with coordinate data. The PDB-assigned chain code appears as
-- the name within the molecule descriptions of the biopolymers.
-- Nonpolymer molecules from PDB correspond to individual HETEROGEN groups,
-- excluding any HETEROGEN groups which represent modified biopolymer residues.
-- These molecules are named according to the chain, residue type and residue
-- number fields as assigned by PDB. Any description appearing in the PDB HET
-- record appears as a pdb-comment within the molecule description.
-- Molecule types for PDB-derived molecule graphs are assigned by matching
-- residue and atom names against the PDB-documented standard types for protein,
-- DNA and RNA, and against residue codes commonly used to indicate solvent.
-- Classification is by "majority rule". If more than half of the residues in
-- a biopolymer are standard groups of one type, then the molecule is of that
-- type, and otherwise classified as "other". Note that this classification does
-- not preclude the presence of modified residues, but insists they constitute
-- less than half the biopolymer. Non-polymers are classified only as "solvent"
-- or "other".
-- Note that a molecule graph may also contain a set of cross references
-- to biopolymer sequence databases. All biopolymer molecules in MMDB contain
-- appropriate identifiers for the corresponding entry in the NCBI-Sequences
-- database, in particular the NCBI "gi" number, which may be used for sequence
-- retrieval. The Seq-id object type is defined in the NCBI molecular sequence
-- specification, and not repeated here.
Molecule-graph ::= SEQUENCE {
id Molecule-id,
descr SEQUENCE OF Biomol-descr OPTIONAL,
seq-id Seq-id OPTIONAL,
residue-sequence SEQUENCE OF Residue,
inter-residue-bonds SEQUENCE OF Inter-residue-bond OPTIONAL,
sid PCSubstance-id OPTIONAL }
Molecule-id ::= INTEGER
-- Pubchem substance id
PCSubstance-id ::= INTEGER
-- Residues may be assigned a text-string name as well as an id number. PDB
-- assigned residue numbers appear as the residue name.
Residue ::= SEQUENCE {
id Residue-id,
name VisibleString OPTIONAL,
residue-graph Residue-graph-pntr }
Residue-id ::= INTEGER
-- Residue graphs from different sources may be referenced within a molecule
-- graph. The allowed choices are the nonstandard residue graphs included in
-- the present biostruc, residue graphs within other biostrucs, or residue
-- graphs within tables of standard residue definitions.
Residue-graph-pntr ::= CHOICE {
local Residue-graph-id,
biostruc Biostruc-graph-pntr,
standard Biostruc-residue-graph-set-pntr }
Biostruc-graph-pntr ::= SEQUENCE {
biostruc-id Biostruc-id,
residue-graph-id Residue-graph-id }
Biostruc-residue-graph-set-pntr ::= SEQUENCE {
biostruc-residue-graph-set-id Biostruc-id,
residue-graph-id Residue-graph-id }
-- Residue graphs define atomic formulae, connectivity, chirality, and names.
-- For standard residue graphs from the MMDB dictionary the PDB-assigned
-- residue-type code appears as the name within the residue graph description,
-- and the full trivial name of the residue as a comment within that
-- description. For any nonstandard residue graphs provided with an MMDB
-- biostruc the PDB-assigned residue-type code similarly appears as the name
-- within the description, and any information provided on PDB HET records as
-- a pdb-comment within that description.
-- Note that nonstandard residue graphs for a PDB-derived biostruc may be
-- incomplete. Current PDB format cannot represent connectivity for groups
-- which are disordered, and for which no coordinates are given. In these
-- cases the residue graph defined in MMDB represents only the subgraph that
-- could be identified from available ATOM, HETATM and CONECT records.
Residue-graph ::= SEQUENCE {
id Residue-graph-id,
descr SEQUENCE OF Biomol-descr OPTIONAL,
residue-type INTEGER { deoxyribonucleotide(1),
ribonucleotide(2),
amino-acid(3),
other(255) } OPTIONAL,
iupac-code SEQUENCE OF VisibleString OPTIONAL,
atoms SEQUENCE OF Atom,
bonds SEQUENCE OF Intra-residue-bond,
chiral-centers SEQUENCE OF Chiral-center OPTIONAL }
Residue-graph-id ::= INTEGER
-- Atoms in residue graphs are defined by elemental symbols and names. PDB-
-- assigned atom names appear here in the name field, except in cases of known
-- PDB synonyms. In these cases atom names are mapped to the names used in the
-- MMDB standard dictionary. This occurs primarily for hydrogen atoms, where
-- PDB practice allows synonyms for several atom types. For PDB atoms the
-- elemental symbol is obtained by parsing the PDB atom name field, allowing
-- for known special-semantics cases where the atom name does not follow the
-- documented encoding rule. Ionizable protons are identified within standard
-- residue graphs in the MMDB dictionary, but not within automatically-defined
-- nonstandard graphs.
Atom ::= SEQUENCE {
id Atom-id,
name VisibleString OPTIONAL,
iupac-code SEQUENCE OF VisibleString OPTIONAL,
element ENUMERATED {
h(1), he(2), li(3), be(4), b(5),
c(6), n(7), o(8), f(9), ne(10),
na(11), mg(12), al(13), si(14), p(15),
s(16), cl(17), ar(18), k(19), ca(20),
sc(21), ti(22), v(23), cr(24), mn(25),
fe(26), co(27), ni(28), cu(29), zn(30),
ga(31), ge(32), as(33), se(34), br(35),
kr(36), rb(37), sr(38), y(39), zr(40),
nb(41), mo(42), tc(43), ru(44), rh(45),
pd(46), ag(47), cd(48), in(49), sn(50),
sb(51), te(52), i(53), xe(54), cs(55),
ba(56), la(57), ce(58), pr(59), nd(60),
pm(61), sm(62), eu(63), gd(64), tb(65),
dy(66), ho(67), er(68), tm(69), yb(70),
lu(71), hf(72), ta(73), w(74), re(75),
os(76), ir(77), pt(78), au(79), hg(80),
tl(81), pb(82), bi(83), po(84), at(85),
rn(86), fr(87), ra(88), ac(89), th(90),
pa(91), u(92), np(93), pu(94), am(95),
cm(96), bk(97), cf(98), es(99),
fm(100), md(101), no(102), lr(103),
other(254), unknown(255) },
ionizable-proton ENUMERATED {
true(1),
false(2),
unknown(255) } OPTIONAL }
Atom-id ::= INTEGER
-- Intra-residue-bond specifies connectivity between atoms in Residue-graph.
-- Unlike Inter-residue-bond defined later, its participating atoms are part of
-- a residue subgraph dictionary, not part of a specific biostruc-graph.
-- For residue graphs in the standard MMDB dictionary bonds are defined from
-- the known chemical structures of amino acids and nucleotides. For
-- nonstandard residue graphs bonds are defined from PDB CONECT records, with
-- validation for consistency with coordinate data, and from stereochemical
-- calculation to identify unreported bonds. Validation and bond identification
-- are based on comparison of inter-atomic distances to the sum of covalent
-- radii for the corresponding elements.
Intra-residue-bond ::= SEQUENCE {
atom-id-1 Atom-id,
atom-id-2 Atom-id,
bond-order INTEGER {
single(1),
partial-double(2),
aromatic(3),
double(4),
triple(5),
other(6),
unknown(255)} OPTIONAL }
-- Chiral centers are atoms with tetrahedral geometry. Chirality is defined
-- by a chiral volume involving the chiral center and 3 other atoms bonded to
-- it. For any coordinates assigned to atoms c, n1, n2, and n3, the vector
-- triple product (n1-c) dot ( (n2-c) cross (n3-c) ) must have the indicated
-- sign. The calculation assumes an orthogonal right-handed coordinate system
-- as is used for MMDB model structures.
-- Chirality is defined for standard residues in the MMDB dictionary, but is
-- not assigned automatically for PDB-derived nonstandard residues. If assigned
-- for nonstandard residues, the source of chirality information is described
-- by a citation within the residue description.
Chiral-center ::= SEQUENCE {
c Atom-id,
n1 Atom-id,
n2 Atom-id,
n3 Atom-id,
sign ENUMERATED { positive(1),
negative(2) } }
-- Inter-residue bonds are defined by a reference to two atoms. For PDB-derived
-- structures bonds are identified from biopolymer connectivity according to
-- SEQRES and from other connectivity information on SSBOND and CONECT
-- records. These data are validated and unreported bonds identified by
-- stereochemical calculation, using the same criteria as for intra-residue
-- bonds.
Inter-residue-bond ::= SEQUENCE {
atom-id-1 Atom-pntr,
atom-id-2 Atom-pntr,
bond-order INTEGER {
single(1),
partial-double(2),
aromatic(3),
double(4),
triple(5),
other(6),
unknown(255)} OPTIONAL }
-- Atoms, residues and molecules within the current biostruc are referenced
-- by hierarchical pointers.
Atom-pntr ::= SEQUENCE {
molecule-id Molecule-id,
residue-id Residue-id,
atom-id Atom-id }
Atom-pntr-set ::= SEQUENCE OF Atom-pntr
END