Copyright	(c) Dominik Schrempf 2019
License	GPL-3
Maintainer	dominik.schrempf@gmail.com
Stability	unstable
Portability	portable
Safe Haskell	None
Language	Haskell2010

ELynx.Data.Alphabet.Alphabet

Description

Creation date: Fri May 10 11:10:32 2019.

Hierarchy:

Character type.
Sets of Characters form Alphabets; each Alphabet has a specification AlphabetSpec.

New alphabets have to be added manually in this module.

This way of handling characters and alphabets IS NOT TYPE SAFE, but much, much faster. A second layer of modules such as Nucleotide depend on a Character type class. Hence, they provide a type safe way of handling alphabets. Conversion is possible, for instance, with fromCVec, and toCVec.

Synopsis

data Alphabet
- = DNA
- | DNAX
- | DNAI
- | Protein
- | ProteinX
- | ProteinS
- | ProteinI
data AlphabetSpec = AlphabetSpec {
- std :: !(Set Character)
- gap :: !(Set Character)
- unknown :: !(Set Character)
- iupac :: !(Set Character)
- all :: !(Set Character)
- toStd :: Character -> [Character]
}
alphabetSpec :: Alphabet -> AlphabetSpec
alphabetNameVerbose :: Alphabet -> String
isStd :: Alphabet -> Character -> Bool
isGap :: Alphabet -> Character -> Bool
isUnknown :: Alphabet -> Character -> Bool
isIUPAC :: Alphabet -> Character -> Bool
isMember :: Alphabet -> Character -> Bool

Documentation

data Alphabet Source #

Available alphabets; for details see alphabetSpec.

Constructors

DNA
DNAX
DNAI
Protein
ProteinX
ProteinS
ProteinI

Instances

Bounded Alphabet Source #
Instance details Defined in ELynx.Data.Alphabet.Alphabet Methods minBound :: Alphabet # maxBound :: Alphabet #
Enum Alphabet Source #
Instance details Defined in ELynx.Data.Alphabet.Alphabet Methods succ :: Alphabet -> Alphabet # pred :: Alphabet -> Alphabet # toEnum :: Int -> Alphabet # fromEnum :: Alphabet -> Int # enumFrom :: Alphabet -> [Alphabet] # enumFromThen :: Alphabet -> Alphabet -> [Alphabet] # enumFromTo :: Alphabet -> Alphabet -> [Alphabet] # enumFromThenTo :: Alphabet -> Alphabet -> Alphabet -> [Alphabet] #
Eq Alphabet Source #
Instance details Defined in ELynx.Data.Alphabet.Alphabet Methods (==) :: Alphabet -> Alphabet -> Bool # (/=) :: Alphabet -> Alphabet -> Bool #
Ord Alphabet Source #
Instance details Defined in ELynx.Data.Alphabet.Alphabet Methods compare :: Alphabet -> Alphabet -> Ordering # (<) :: Alphabet -> Alphabet -> Bool # (<=) :: Alphabet -> Alphabet -> Bool # (>) :: Alphabet -> Alphabet -> Bool # (>=) :: Alphabet -> Alphabet -> Bool # max :: Alphabet -> Alphabet -> Alphabet # min :: Alphabet -> Alphabet -> Alphabet #
Read Alphabet Source #
Instance details Defined in ELynx.Data.Alphabet.Alphabet Methods readsPrec :: Int -> ReadS Alphabet # readList :: ReadS [Alphabet] # readPrec :: ReadPrec Alphabet # readListPrec :: ReadPrec [Alphabet] #
Show Alphabet Source #
Instance details Defined in ELynx.Data.Alphabet.Alphabet Methods showsPrec :: Int -> Alphabet -> ShowS # show :: Alphabet -> String # showList :: [Alphabet] -> ShowS #

data AlphabetSpec Source #

Alphabet specification. Set is used because it provides fast lookups.

Constructors

AlphabetSpec
Fields std :: !(Set Character) Standard characters. gap :: !(Set Character) Gap characters. unknown :: !(Set Character) Unknown characters. iupac :: !(Set Character) Other IUPAC codes. all :: !(Set Character) All characters in the alphabet. toStd :: Character -> [Character] Convert from IUPAC to the corresponding standard characters.

alphabetSpec :: Alphabet -> AlphabetSpec Source #

Get the alphabet specification for a given alphabet.

alphabetNameVerbose :: Alphabet -> String Source #

Verbose alphabet name.

isStd :: Alphabet -> Character -> Bool Source #

Test if standard character.

isGap :: Alphabet -> Character -> Bool Source #

Test if gap.

isUnknown :: Alphabet -> Character -> Bool Source #

Test if unknown.

isIUPAC :: Alphabet -> Character -> Bool Source #

Test if extended IUPAC character (excluding gaps and unknowns).

isMember :: Alphabet -> Character -> Bool Source #

Test if member of alphabet.