67 lines
2.7 KiB
Groff
67 lines
2.7 KiB
Groff
--$Revision: 6.0 $
|
|
-- *********************************************************************
|
|
--
|
|
-- These are code and conversion tables for NCBI sequence codes
|
|
-- ASN.1 for the sequences themselves are define in seq.asn
|
|
--
|
|
-- Seq-map-table and Seq-code-table REQUIRE that codes start with 0
|
|
-- and increase continuously. So IUPAC codes, which are upper case
|
|
-- letters will always have 65 0 cells before the codes begin. This
|
|
-- allows all codes to do indexed lookups for things
|
|
--
|
|
-- Valid names for code tables are:
|
|
-- IUPACna
|
|
-- IUPACaa
|
|
-- IUPACeaa
|
|
-- IUPACaa3 3 letter amino acid codes : parallels IUPACeaa
|
|
-- display only, not a data exchange type
|
|
-- NCBI2na
|
|
-- NCBI4na
|
|
-- NCBI8na
|
|
-- NCBI8aa
|
|
-- NCBIstdaa
|
|
-- probability types map to IUPAC types for display as characters
|
|
|
|
NCBI-SeqCode DEFINITIONS ::=
|
|
BEGIN
|
|
|
|
EXPORTS Seq-code-table, Seq-map-table, Seq-code-set;
|
|
|
|
Seq-code-type ::= ENUMERATED { -- sequence representations
|
|
iupacna (1) , -- IUPAC 1 letter nuc acid code
|
|
iupacaa (2) , -- IUPAC 1 letter amino acid code
|
|
ncbi2na (3) , -- 2 bit nucleic acid code
|
|
ncbi4na (4) , -- 4 bit nucleic acid code
|
|
ncbi8na (5) , -- 8 bit extended nucleic acid code
|
|
ncbipna (6) , -- nucleic acid probabilities
|
|
ncbi8aa (7) , -- 8 bit extended amino acid codes
|
|
ncbieaa (8) , -- extended ASCII 1 letter aa codes
|
|
ncbipaa (9) , -- amino acid probabilities
|
|
iupacaa3 (10) , -- 3 letter code only for display
|
|
ncbistdaa (11) } -- consecutive codes for std aas, 0-25
|
|
|
|
Seq-map-table ::= SEQUENCE { -- for tables of sequence mappings
|
|
from Seq-code-type , -- code to map from
|
|
to Seq-code-type , -- code to map to
|
|
num INTEGER , -- number of rows in table
|
|
start-at INTEGER DEFAULT 0 , -- index offset of first element
|
|
table SEQUENCE OF INTEGER } -- table of values, in from-to order
|
|
|
|
Seq-code-table ::= SEQUENCE { -- for names of coded values
|
|
code Seq-code-type , -- name of code
|
|
num INTEGER , -- number of rows in table
|
|
one-letter BOOLEAN , -- symbol is ALWAYS 1 letter?
|
|
start-at INTEGER DEFAULT 0 , -- index offset of first element
|
|
table SEQUENCE OF
|
|
SEQUENCE {
|
|
symbol VisibleString , -- the printed symbol or letter
|
|
name VisibleString } , -- an explanatory name or string
|
|
comps SEQUENCE OF INTEGER OPTIONAL } -- pointers to complement nuc acid
|
|
|
|
Seq-code-set ::= SEQUENCE { -- for distribution
|
|
codes SET OF Seq-code-table OPTIONAL ,
|
|
maps SET OF Seq-map-table OPTIONAL }
|
|
|
|
END
|
|
|