75 lines
2.8 KiB
Groff
75 lines
2.8 KiB
Groff
--$Id: blastdb.asn 311249 2011-07-11 14:12:16Z camacho $
|
|
--
|
|
-- Notes:
|
|
--
|
|
-- taxonomy: an integer is proposed, which would require some sort of
|
|
-- table (or network connection) to do the conversions from integer
|
|
-- to various names. This could save quite a bit of space for databases
|
|
-- that are predominantly of one organism (e.g., human in htgs).
|
|
-- I've proposed here that table contain scientific-, common-, and
|
|
-- blast-names at the advice of Scott Federhen. Scott also was in
|
|
-- favor of having the complete lineage in the file, but it seems like
|
|
-- this would be seldom used and we could have a view with a link back
|
|
-- to the taxonomy page for anyone needing it. Since one file would
|
|
-- suffice for all blast databases, it seems like this should be a new file.
|
|
--
|
|
-- memberships: a sequence of integers is proposed. Each bit of an integer
|
|
-- would indicate membership in some (virtual) blast database (e.g., pdb,
|
|
-- swissprot) or some classification (e.g., mRNA, genomic).
|
|
--
|
|
-- links: a sequence of integers is proposed. Each bit of an integer would
|
|
-- indicate a link that could be established based upon the gi of the
|
|
-- database sequence.
|
|
--
|
|
|
|
NCBI-BlastDL DEFINITIONS ::=
|
|
BEGIN
|
|
|
|
EXPORTS Blast-def-line-set, Blast-def-line;
|
|
|
|
IMPORTS Seq-id, Seq-loc FROM NCBI-Seqloc;
|
|
|
|
Blast-def-line-set ::= SEQUENCE OF Blast-def-line -- all deflines for an entry
|
|
|
|
Blast-def-line ::= SEQUENCE {
|
|
title VisibleString OPTIONAL, -- simple title
|
|
seqid SEQUENCE OF Seq-id, -- Regular NCBI Seq-Id
|
|
taxid INTEGER OPTIONAL, -- taxonomy id
|
|
memberships SEQUENCE OF INTEGER OPTIONAL, -- bit arrays
|
|
links SEQUENCE OF INTEGER OPTIONAL, -- DEPRECATED, replaced by LinkoutDB
|
|
other-info SEQUENCE OF INTEGER OPTIONAL -- for future use (probably genomic sequences)
|
|
}
|
|
|
|
-- This defines the possible sequence filtering algorithms to be used in a
|
|
-- BLAST database
|
|
Blast-filter-program ::= INTEGER {
|
|
not-set (0),
|
|
dust (10),
|
|
seg (20),
|
|
windowmasker (30),
|
|
repeat (40),
|
|
other (100),
|
|
max (255)
|
|
}
|
|
|
|
Blast-mask-list ::= SEQUENCE {
|
|
-- masks for a single sequence should be grouped in a Packed-seqint
|
|
masks SEQUENCE OF Seq-loc,
|
|
-- as of 01/21/2010, this field is set to false always, indicating that the
|
|
-- entire object (set of Seq-loc) is contained in this object
|
|
more BOOLEAN
|
|
}
|
|
|
|
-- Defines the masking information for a set of sequences
|
|
Blast-db-mask-info ::= SEQUENCE {
|
|
algo-id INTEGER,
|
|
algo-program Blast-filter-program,
|
|
algo-options VisibleString,
|
|
-- This object was originally created to allow pagination of the sequence
|
|
-- masks, but this feature was discontinued in 01/21/2010
|
|
masks Blast-mask-list
|
|
}
|
|
|
|
END
|
|
|