docsum.asn

ncbi源码

-- $Id: docsum.asn,v 1000.1 2004/06/01 19:31:58 gouriano Exp $

NSE DEFINITIONS ::=
BEGIN

EXPORTS NSE-BaseURLSet, NSE-SubmitterList, NSE-AssayList, NSE-PopList, NSE-ExchangeSet;


NSE-BaseURLSet ::= SEQUENCE {
	version VisibleString,			-- version number of docsum.asn/docsum.dtd specification
	dbSNP-build-number INTEGER,		-- build number of database for this export
	generated NSE-Date OPTIONAL ,		-- Date set-list generated
	query VisibleString OPTIONAL ,		-- Query terms or search constraints
	set-type INTEGER {
       		full-dump (1),			-- Complete set of records in dbSNP
        	from-query (2),			-- Set that satisfies query
        	single     (3) } ,		-- A single record
	url-set SET OF NSE-BaseURL    		-- Set of URLs for resource integration
}

NSE-BaseURL ::= SEQUENCE {			-- list of base URLs for queries to other integrated resources
	resource-id INTEGER,			-- integer pointer to base URL 					BaseURLList.url_id
	resource VisibleString OPTIONAL,	-- name of the resource 					BaseURLList.resource
	field-id VisibleString OPTIONAL,	-- name of the data object used to link 			BaseURLList.resource_id
	base-url VisibleString OPTIONAL 	-- Base URL to which identifier is appended to form full URL 	BaseURLList.base_url
}


NSE-SubmitterList ::= SEQUENCE {		-- set of contact information for all handles defined in dbSNP
	version VisibleString,			-- version number of docsum.asn/docsum.dtd specification
	dbSNP-build-number INTEGER,		-- build number of database for this export
	generated NSE-Date OPTIONAL ,		-- Date set-list generated
	query VisibleString OPTIONAL ,		-- Query terms or search constraints
	set-type INTEGER {
       		full-dump (1),			-- Complete set of records in dbSNP
        	from-query (2),			-- Set that satisfies query
        	single     (3) } ,		-- A single record
	submitter-list SET OF NSE-Submitter 
}

NSE-Submitter ::= SEQUENCE {
	handle VisibleString,			-- Short name, or handle as supplied by NCBI
	name VisibleString,			-- Name of Principal Investigator for lab or submitting group
	fax VisibleString OPTIONAL,		-- FAX number for submitter
	tel VisibleString OPTIONAL,		-- telephone number for submitter
	email VisibleString OPTIONAL,		-- email for submitter
	lab VisibleString OPTIONAL,		-- Laboratory providing SNP
	inst VisibleString OPTIONAL,		-- Institution Name
	addr SEQUENCE OF VisibleString OPTIONAL	-- Address strings
}

NSE-AssayList ::= SEQUENCE {			-- Table of batch characteristics for all SNP batches in dbSNP
	version VisibleString,			-- version number of docsum.asn/docsum.dtd specification
	dbSNP-build-number INTEGER,		-- build number of database for this export
	generated NSE-Date OPTIONAL ,		-- Date set-list generated
	query VisibleString OPTIONAL ,		-- Query terms or search constraints
	set-type INTEGER {
       		full-dump (1),			-- Complete set of records in dbSNP
        	from-query (2),			-- Set that satisfies query
        	single     (3) } ,		-- A single record
	assay-list SET OF NSE-Assay 
}

NSE-Assay ::= SEQUENCE {
	handle VisibleString,
	batch VisibleString,			-- Submitter (local) batch id
	batch-id INTEGER,			-- dbSNP batch_id. Use to join assay to subsnp and validation data (NSE-ss, NSE-ss, below).
	batch-type ENUMERATED {			-- distinguishes submission batches from follow-up confirmation of refSNPs. 
									-- Join to appropriate object by batch-id.
		snpassay (1),				-- detailed assay conditions for NSE-ss.
		validation (2),				-- refSNPs confirmed by subsequent experimental data. Data for NSE-rs.validated-in-other-pop
		doublehit (3) },			-- refSNPs with both alleles seen twice. Data for NSE-rs.validated-by-2hit-2allele
	moltype ENUMERATED {
		genomic (1),
		cDNA (2),
		mito (3),
		chloro (4)
	},
	method VisibleString,						-- local method id
	method-ex SEQUENCE OF VisibleString OPTIONAL,			-- description of deviation from/addition to given method
	samplesize INTEGER OPTIONAL,					-- number of chromosomes examined during ascertainment
	organism VisibleString OPTIONAL,				-- Scientific Name
	taxid INTEGER OPTIONAL,							-- taxonomy ID for organism from NCBI taxonomy database
	population VisibleString OPTIONAL,				-- Population surveyed for variation
	strains SEQUENCE OF VisibleString OPTIONAL,			-- Strains used in survey for variation
	citation SEQUENCE OF VisibleString OPTIONAL,
	linkout-url VisibleString OPTIONAL,
	comment SEQUENCE OF VisibleString OPTIONAL
}

NSE-PopList ::= SEQUENCE {			-- Table of batch characteristics for all allele frequency batches in dbSNP
	version VisibleString,			-- version number of docsum.asn/docsum.dtd specification
	dbSNP-build-number INTEGER,		-- build number of database for this export
	generated NSE-Date OPTIONAL ,		-- Date set-list generated
	query VisibleString OPTIONAL ,		-- Query terms or search constraints
	set-type INTEGER {
       		full-dump (1),			-- Complete set of records in dbSNP
        	from-query (2),			-- Set that satisfies query
        	single     (3) } ,		-- A single record
	pop-list SET OF NSE-Pop
}

NSE-Pop ::= SEQUENCE {
	handle VisibleString,
	batch VisibleString,				-- Submitter (local) batch id
	batch-id INTEGER,				-- dbSNP batch_id. Use to join population allele data to subsnp data
	method VisibleString,				-- local method id
	method-ex SEQUENCE OF VisibleString OPTIONAL,	-- description of deviation from/addition to given method
	citation SEQUENCE OF VisibleString OPTIONAL,
	comment SEQUENCE OF VisibleString OPTIONAL
}

NSE-ExchangeSet ::= SEQUENCE {
	copyright SEQUENCE OF VisibleString OPTIONAL,
	version VisibleString,			-- version number of docsum.asn/docsum.dtd specification
	dbSNP-build-number INTEGER,		-- build number of database for this export
	generated NSE-Date OPTIONAL ,		-- Date set-list generated
	query VisibleString OPTIONAL ,		-- Query terms or search constraints
	source-dbs SET OF VisibleString OPTIONAL ,	-- List of source databases
	set-type INTEGER {
       		full-dump (1),			-- Complete set of records in dbSNP
        	from-query (2),			-- Set that satisfies query
        	single     (3) } ,		-- A single record
	set-depth INTEGER {
		brief-set (1),			-- only summary information included in NSE-rs objects
		full-set (2) } ,		-- all information included in NSE-rs objects (data on subsnps in rs group)
	rs-set SET OF NSE-rs,  			-- Set of Reference SNP docsums and grouped subSNP members
	num-refsnp-ids INTEGER OPTIONAL ,	-- Total number of refsnp-ids
	total-seq-length INTEGER OPTIONAL ,	-- Total length of exemplar flanking sequences
	num-contig-locs INTEGER OPTIONAL ,	-- Total number of contig locations from SNPContigLoc
	num-locus-ids INTEGER OPTIONAL ,	-- Total number of locus ids from SNPContigLocusId
	num-gi-hits INTEGER OPTIONAL ,		-- Total number of gi hits from MapLink
	num-3d-structs INTEGER OPTIONAL ,	-- Total number of 3D structures from SNP3D
	num-allele-freqs INTEGER OPTIONAL ,	-- Total number of allele frequences from SubPopAllele
	num-sts-hits INTEGER OPTIONAL ,		-- Total number of STS hits from SnpInSts
	num-unigene-cids INTEGER OPTIONAL 	-- Total number of unigene cluster ids from UnigeneSnp
}



NSE-rs ::= SEQUENCE {				-- defines the docsum structure for refSNP clusters, where a refSNP cluster (rs) is
						-- a grouping of individual dbSNP submissions that all refer to the same variation.
						-- The refsnp provides a single unified record for annotation of NCBI resources such
						-- as reference genome sequence.
	
						-- #######################################################
						-- ######
						-- ######   Data defined for both brief-sets and full-sets   
						-- ######
						-- #######################################################

	refsnp-id INTEGER,			-- refSNP (rs) number
	taxid INTEGER,				-- NCBI Taxonomy Database ID. 9606 for Homo sapiens
	organism VisibleString OPTIONAL,	-- species abbreviation
	snp-class ENUMERATED {		
		snp         (1),		-- single nucleotide variation: alleles of length=1 and from set of {A,T,C,G}
		in-del      (2),		-- insertion / deletion variation: alleles of different length or include '-' character
		het         (3),		-- heterozygous (undetermined) variation: allele contains string '(heterozygous)'
		microsat    (4),		-- microsatellite variation: allele string contains numbers and '(motif)' pattern
		named       (5),		-- insertion/deletion of named object (length unknown)
		no-variation (6),		-- novariation asserted for sequence
		mixed       (7),                -- mixed class
		mnp         (8)},               -- Multiple Nucleotide Polymorphism. All alleles of same length > 1

	snp-type ENUMERATED {			
		notwithdrawn (1),		-- variation is OK, default case
		artifact     (2),		-- variation determined to be experimental artifact
		gene-dup      (3),		-- variation artifact of duplicated gene region
		duplicatesub  (4),		-- variation was duplicate submission
		notspecified  (5),		-- no reason specified for withdrawal	
		ambiguousloc  (6),		-- variation has excessive number of potional locations in genome
		lowmapquality (7)		-- evidence for calling variation deemed insufficient
				},
	moltype ENUMERATED {			-- moltype from exemplar ss
		genomic (1),
		cDNA (2),
		mito (3),
		chloro (4)
	},
	create-date NSE-Date,       -- date the refsnp cluster was instantiated
	update-date NSE-Date OPTIONAL, -- most recent date the cluster was updated (member added or deleted)
	create-build INTEGER,			-- build number when the cluster was created
	update-build INTEGER,			-- latest build number when the cluster was updated
	observed VisibleString,			-- list of all alleles observed in ss-list members, correcting for reverse
						-- complementation of memebers reported in reverse orientation
	seq-5 SEQUENCE OF VisibleString OPTIONAL,	-- 5' sequence that flanks the variation
	seq-3 SEQUENCE OF VisibleString OPTIONAL,	-- 3' sequence that flanks the variation
						-- all sequences are in forward orientation, complete sequence
						-- lower case letters indicate repetetitive or low-complexity sequence by RepeatMasker
						-- flanking sequence is reported in strings of 255 b.p. and multiple strings
						-- should be concatenated in order to reconstruct the complete flanking sequence.
						-- Sequence should be assembled as seq-5 + observed + seq-3
	seq-ss-exemplar INTEGER,		-- dbSNP ss# selected as source of refSNP flanking sequence, ss# part of ss-list below 
	ncbi-build-id INTEGER OPTIONAL,		-- NCBI build number for data on genome mapping to synchronize with NCBI MapViewer
	ncbi-num-chr-hits INTEGER OPTIONAL,		-- total number of distinct chromosomes in contig-mapset
	ncbi-num-ctg-hits INTEGER OPTIONAL,		-- total number of distinct contig-ids in contig-mapset
	ncbi-num-seq-loc INTEGER OPTIONAL,		-- total number of distinct seq-loc's in contig-mapset
	ncbi-mapweight INTEGER OPTIONAL,		-- location quality score for NCBI map display

	het REAL OPTIONAL,			-- average heterozygosity 
	het-SE REAL OPTIONAL,			-- standard error of heterozygosity 
	valid-prob-min INTEGER OPTIONAL,	-- minimum reported success rate of all submissions in cluster
	valid-prob-max INTEGER OPTIONAL,	-- maximum reported success rate of all submissions in cluster
	validated-other-pop BOOLEAN OPTIONAL, -- at least one ss in cluster was validated by independent assay
	val-other-pop-batches SET OF INTEGER OPTIONAL, -- dbSNP batch-id's for independent assay validation data. Use batch-ids to get methods etc.
	validated-by-frequency BOOLEAN OPTIONAL, -- at least one subsnp in cluster has frequency data submitted
	validated-by-cluster   BOOLEAN OPTIONAL, -- cluster has 2+ submissions, with 1+ submissions assayed with a non-computational method
	validated-by-2hit-2allele BOOLEAN OPTIONAL, --all alleles have been observed in 2+ chromosomes
	val-2hit-2allele SET OF INTEGER OPTIONAL, -- dbSNP batch-id's for double-hit snp validation data. Use batch-id to get methods, etc.
	validated-by-hapmap BOOLEAN OPTIONAL,	-- validated by HapMap project
	genotype BOOLEAN OPTIONAL,		-- at least one genotype reported for this refSNP
	linkout BOOLEAN OPTIONAL,		-- YES if linkout to at least one submitter website
	last-action NSE-Date OPTIONAL,		-- Date of update or create