docsum.asn

ncbi源码

	link-data SET OF NSE-rslink OPTIONAL, 	-- link data for external resources
	ss-list SET OF NSE-ss,			-- set of all subsnp id's in the refSNP cluster	
	contig-mapset SET OF NSE-rsContigHit OPTIONAL, -- list of hits to genome in NT_ contig coordinates and functional relationships
						-- between variations and genes as annotated on contig sequence
						-- data from SNPContigLoc & ContigInfo tables
	sequence-mapset SET OF  NSE-rsSeqHit OPTIONAL, -- list of hits to genome in sequence component coordinates from MapLink and MapLinkArchive
	gene-info SET OF NSE-rsLocusID OPTIONAL, -- set of gene information inferred by blast similarity of variation and GenBank sequences.
						-- analysis is independent of annotation of genome sequence (contig-mapset, above) and
						-- includes variations mapped to mRNAs or genomic sequences that do not yet have a reference contig.
	sts-info SET OF INTEGER OPTIONAL,	-- set of STS ids from SnpInSts
	unigene-info SET OF NSE-rsUnigene OPTIONAL, -- Unigene info from UnigeneSnp
 	structure-data SET OF NSE-rsStruct OPTIONAL -- set of snp to protein structure data based on map coordinates 
                                                -- and protein structure neighbors

}



NSE-rslink ::= SEQUENCE {			-- link data for anther resource
	resource-id INTEGER,			-- BaseURLList.url_id
	link-value VisibleString 		-- value to append to NSE-ResourceURL.base-url for complete link
}


NSE-ss ::= SEQUENCE {				-- data for an individual submission to dbSNP. All submssions (subsnps, ss#) are
						-- grouped into reference SNP clusters (rs) above.

						-- #######################################################
						-- ######
						-- ######   Data defined in both NSE-rs.brief-sets and full-sets   
						-- ######
						-- #######################################################
	handle VisibleString,			-- Tag for the submitting laboratory
	batch-id INTEGER,			-- dbSNP number for batch submission
	subsnp-id INTEGER,			-- dbSNP accession number for submission (ss#)
	loc-snp-id VisibleString OPTIONAL,	-- submitter (local) subsnp ID
	subsnp-class ENUMERATED {		-- SubSNP classification by type of variation			SubSNP.subsnp_class
		snp         (1),		--   true single nucleotide polymorphism
		in-del      (2),		--   insertion deletion polymorophism, deletions represented by '-' in allele string
		het         (3),		--   variation has unknown sequence composition, but is observed to be heterozygous
		microsat    (4),		--   microsatellite / simple sequence repeat
		named       (5),		--   allele sequences defined by name tag instead of raw sequence, e.g. (Alu)/- 
		no-variation (6), 		--   submission reports invariant region in surveyed sequence
		mnp         (8)},		--   multiple nucleotide polymorphism (all alleles same length where length>1)
	orient ENUMERATED {			-- orientation of refsnp cluster members to refsnp cluster sequence
		forward	    (1),		-- ss flanking sequence is in same orientation as seq-ss-exemplar (above) 
		reversed    (2) },		-- flanking sequence and alleles are reverse complement of refSNP as defined
								-- by seq-ss-exemplar. 
	strand ENUMERATED {			-- strand is defined as TOP/BOTTOM by nature of flanking nucleotide sequence itself
		top			(1),		-- 
		bottom		(2) } OPTIONAL,
	moltype ENUMERATED {			-- moltype from Batch table
		genomic (1),
		cDNA (2),
		mito (3),
		chloro (4)
	},
	build-id INTEGER,			-- dbSNP build number when ss# was added to a refSNP (rs#) cluster
	method-class ENUMERATED {	-- class of method used to assay for the variation
		dhplc        (1),		-- Denaturing High Pressure Liquid Chromatography used to detect SNP
		hybridize    (2),		-- a hybridization method (e.g. chip) was used to assay for variation
		computed     (3),		-- variation was mined from sequence alignment with software
		sscp         (5),		-- single stranded conformational polymorphism used to detect variation
		other  		 (6), 		-- other method used to detect variation
		unknown		 (7), 		-- unknown method used to detect variation (not reported)
		rflp		 (8),		-- variation in enzyme restriction site used to detect variation
		sequence	 (9)} OPTIONAL,	-- samples were sequenced and resulting alignment used to define variation
    validated ENUMERATED {
        by-submitter (1),       -- subsnp has been experimentally validated by submitter
        by-frequency (2),       -- subsnp has frequency data submitted
        by-cluster   (3),       -- has 2+ submissions, with 1+ submission assayed with a non-computational method.
        no-info      (4)        -- subsnp is not validated
                } OPTIONAL,
		linkout-url VisibleString OPTIONAL, -- append loc-snp-id to this base URL to construct a pointer to submitter data.



				

						-- #######################################################
						-- ######
						-- ######   Additional data supplied in full-set
						-- ######
						-- #######################################################

	snp-link VisibleString OPTIONAL,		-- submission includes reference to another ss# (snp-link value) in dbSNP
	accession SEQUENCE OF VisibleString OPTIONAL,	-- GenBank or dbSTS sequence accessions used to define local sequence context
	comment SEQUENCE OF VisibleString OPTIONAL,	-- submitter notes on discovery protocol or measure of evidence for the submission
	meth-failure SEQUENCE OF VisibleString OPTIONAL,-- notes if submitter reports failure to detect or confirm snp with specific methods
	genename VisibleString OPTIONAL,		-- gene snp was associated with by submitter
	locus-id VisibleString OPTIONAL,		-- NCBI LocusLink ID for gene
	flank-5 SEQUENCE OF VisibleString OPTIONAL,	-- flanking sequence not surveyed, but appended for minimum length requirements
	assay-5 SEQUENCE OF VisibleString OPTIONAL,	-- flanking sequence surveyedd in [NSE-Assay.samplesize] chromosomes
	observed VisibleString OPTIONAL,		-- /-delimited string of alleles observed by submitter
	assay-3 SEQUENCE OF VisibleString OPTIONAL,	-- flanking sequence surveyed in [NSE-Assay.samplesize] chromosomes
	flank-3 SEQUENCE OF VisibleString OPTIONAL,	-- flanking sequence not surveyed, but appended for minimum length requirements
							-- n.b. the complete 5' flanking sequence for a submission is constructed as
							--             flank-5 strings in order + assay-5 strings in order 
							--      the complete 3' flanking sequence is constructed as
							--             assay-3 strings in order + flank-3 strings in order
	pop-info SET OF NSE-ss-popinfo OPTIONAL 
}




NSE-rsContigHit ::= SEQUENCE {		-- data from SNPContigLoc, ContigInfo tables, & SNPContigLocusId tables
	contig-id VisibleString,		-- Id of contig when naming files for refSNPs x contig		
	locations SET OF NSE-rsMaploc,		-- set of all valid locations for variation on contig
	accession VisibleString OPTIONAL,	-- Accession number of the contig
	version INTEGER OPTIONAL,		-- version number of the contig	
	chromosome VisibleString OPTIONAL	-- Chromosome number
}
	

NSE-rsMaploc ::= SEQUENCE {		-- Position of a single hit of a variation on a contig
	asn-from INTEGER,		-- beginning of variation as feature on contig			SNPContigLoc.asn_from
	asn-to INTEGER,		-- end of variation as feature on contig			SNPContigLoc.asn_to
	loc-type ENUMERATED {			-- defines the seq-loc symbol if asn_from != asn_to		SNPContigLoc.loc_type
		range (1),			-- asn-from < asn-to  write as "asn-from..asn-to"		
		exact (2),			-- asn-from = asn-to write as "asn-from"
		between (3) },			-- asn-to = asn-from+1 write as "asn-from^asn-to"		
	hit-quality ENUMERATED {
		high (1),			-- if SNPContigLoc.proc_status = 0 (high quality hit)
		loose (2), 			-- if SNPContigLoc.proc_status = 1 (lower quality hit admits dirty flanks)
		dense (3) } OPTIONAL, 		-- if SNPContigLoc.proc_status = 8 (region of high SNP density like HLA)

	orient ENUMERATED {			-- orientation of refSNP sequence to contig sequence
		forward (1),			-- if SNPContigLoc.orientation = 0
		reverse (2) } OPTIONAL,		-- if SNPContigLoc.orientation = 1
	physmap-str  VisibleString OPTIONAL,	-- chromosome position of var as seq-loc in # of bases 		SNPContigLoc.phys_pos
	physmap-int INTEGER OPTIONAL,		-- chromosome position as integer for sorting			SNPContigLoc.phys_pos_from
	fxn-set SET OF NSE-FxnSet OPTIONAL	-- functional relationship of SNP (and possibly alleles) to genes at contig location
										-- fxn-set analysis is only available for NCBI contig-set
}

NSE-FxnSet ::= SEQUENCE {
	locusid INTEGER,			-- locus-id of gene as aligned to contig			SNPContigLocusId.locus_id
	symbol VisibleString OPTIONAL,		-- symbol (official if present in LocusLink) of gene		SNPContigLocusId.locus_symbol
	mrna-acc VisibleString OPTIONAL,	-- mRNA accession if variation in transcript			SNPContigLocusId.mrna_acc
	prot-acc VisibleString OPTIONAL,	-- protein accession if variation in coding region interval	SNPContigLocusId.protein_acc
	fxn-class-contig ENUMERATED {
		locus-region (1),		-- variation in region of gene, but not in transcript		SNPContigLocusId.fxn_class
		coding (2),				-- variation in coding region of gene, assigned if allele-specific class unknown 
		coding-synon (3),		-- no change in peptide for allele with respect to contig seq 	**allele-specific class**
		coding-nonsynon (4),	-- change in peptide with respect to contig sequence 			**allele-specific class**
		mrna-utr (5),			-- variation in transcript, but not in coding region interval
		intron (6),				-- variation in intron, but not in first 2 or last 2 bases of intron
		splice-site (7), 		-- variation in first 2 or last to bases of intron
		reference (8), 			-- allele observed in reference contig sequence 				**allele-specific class**
		exception (9)			-- variation in coding region with exception raised on
								-- alignment. This occurs when protein with gap in sequence
								-- is aligned back to contig sequence. variations 3' of
								-- the gap have undefined functional inference.
	} ,
	reading-frame INTEGER OPTIONAL,		-- position of variation in reading frame of transcript		SNPContigLocusId.reading_Frame
	allele VisibleString OPTIONAL,		-- allele, * denotes allele observed in contig sequence		SNPContigLocusId.allele
	residue VisibleString OPTIONAL,		-- translated amino acid residue for allele			SNPContigLocusId.residue
	aa-position INTEGER OPTIONAL		-- position of the variant residue in peptide sequence	SNPContigLocusId.aa_position
}


NSE-rsSeqHit ::= SEQUENCE {			-- Properties of individual mapping result from finished & draft sequences
	accession VisibleString,		-- Accession of the sequence 
	version INTEGER OPTIONAL,		-- version number of the sequence (reports most recent ver.) 
	loc SET OF NSE-SeqLoc			-- set of all valid locations on accession
}



NSE-SeqLoc ::= SEQUENCE {
	asn-from INTEGER,			-- beginning position of variation on sequence
	asn-to INTEGER OPTIONAL,		-- end position of variation on sequence
	loc-type ENUMERATED {
		range 	(1),			-- asn-from < asn-to: write as "asn-from..asn-to"
		exact	(2),			-- asn-from = asn-to: write as "asn-from"
		between	(3) 			-- asn-from = asn-to - 1: write as "asn-from^asn-to"
	} OPTIONAL,
	source-db ENUMERATED {
		ref-mrna (1),			-- NCBI RefSeq mRNA
		gb-sts (2),			-- GenBank STS division
		gb-mrna (4),			-- Genbank mrna
		ref-genome(5),			-- NCBI RefSeq genomic
		gb-small (6),			-- Genbank genomic < 30kb in length
		hgs-finish (10),		-- genome sequence, finished
		hgs-draft (11),			-- genome sequence, draft
		bes (12) 			-- BAC-end sequence
	} OPTIONAL,
        orient ENUMERATED {
                forward (1),                    -- if MapLink.orientation = 0
                reverse (2) } OPTIONAL          -- if MapLink.orientation = 1
}


NSE-rsLocusID ::= SEQUENCE {
	locus-id INTEGER,
	url-id INTEGER DEFAULT 3,
	symbol VisibleString OPTIONAL,
	fxn-class-mrna ENUMERATED {			-- these values are the same encoding as Fxn-Set.fxn-class (above)
		locus-region	(1),
		coding		(2),
		coding-synon	(3),
		coding-nonsynon	(4),
		mrna-UTR	(5),
		intron		(6),
		splice-site	(7),
		reference	(8),
		exception       (9) 
	} OPTIONAL
}

NSE-rsStruct ::= SEQUENCE {
	prot-acc VisibleString,             -- accession of the protein with variation (SNP3D.protein_acc)