-- Hoogle documentation, generated by Haddock
-- See Hoogle, http://www.haskell.org/hoogle/
-- | Handle molecular sequences
--
-- Examine, modify, and simulate molecular sequences in a reproducible
-- way. Please see the README on GitHub at
-- https://github.com/dschrempf/elynx.
@package elynx-seq
@version 0.3.2
-- | Creation date: Fri Oct 12 16:24:02 2018.
--
-- See header of Alphabet.
module ELynx.Data.Character.Character
-- | A set of characters forms an Alphabet. At the moment,
-- Word8 is used, since none of the alphabets has more than 255
-- characters.
class (Show a, Read a, Eq a, Ord a, Enum a, Bounded a, Unbox a) => Character a
-- | Write characters.
toWord :: Character a => a -> Word8
-- | Read characters.
fromWord :: Character a => Word8 -> a
-- | Conversion from Char.
fromChar :: Character a => Char -> a
-- | Conversion to Char.
toChar :: Character a => a -> Char
-- | Conversion from String.
fromString :: Character a => String -> [a]
-- | Conversion to String.
toString :: Character a => [a] -> String
-- | An extended character type with gaps and unknowns.
class Character a => CharacterX a
gap :: CharacterX a => a
-- | Is the character a gap or unknown?
isGap :: CharacterX a => a -> Bool
-- | IUPAC characters with a mapping to extended characters.
class CharacterX a => CharacterI a
unknown :: CharacterI a => a
iupac :: CharacterI a => [a]
toStandard :: CharacterI a => a -> [a]
-- | Check if a IUPAC CharacterI is unknown (e.g., N for
-- nucleotides).
isUnknown :: CharacterI a => a -> Bool
-- | Is the given character a IUPAC character?
isIUPAC :: CharacterI a => a -> Bool
-- | Is the given character a standard character?
isStandard :: CharacterI a => a -> Bool
-- | Convert between character classes. May throw error.
convert :: (Character a, Character b) => a -> b
-- | Creation date: Thu Oct 4 18:26:35 2018.
--
-- See header of Alphabet.
--
-- Extended amino acid with gaps. See also
-- https://www.bioinformatics.org/sms/iupac.html or
-- https://en.wikipedia.org/wiki/International_Union_of_Pure_and_Applied_Chemistry.
--
--
-- Amino Acid Code: Three letter Code: Amino Acid:
-- ---------------- ------------------ -----------
-- A Ala Alanine
-- C Cys Cysteine
-- D Asp Aspartic Acid
-- E Glu Glutamic Acid
-- F Phe Phenylalanine
-- G Gly Glycine
-- H His Histidine
-- I Ile Isoleucine
-- K Lys Lysine
-- L Leu Leucine
-- M Met Methionine
-- N Asn Asparagine
-- P Pro Proline
-- Q Gln Glutamine
-- R Arg Arginine
-- S Ser Serine
-- T Thr Threonine
-- V Val Valine
-- W Trp Tryptophan
-- Y Tyr Tyrosine
-- ---------------- ------------------ -----------
-- - Gap No amino acid
-- . Gap No amino acid
--
module ELynx.Data.Character.AminoAcidX
-- | Amino acids.
data AminoAcidX
A :: AminoAcidX
C :: AminoAcidX
D :: AminoAcidX
E :: AminoAcidX
F :: AminoAcidX
G :: AminoAcidX
H :: AminoAcidX
I :: AminoAcidX
K :: AminoAcidX
L :: AminoAcidX
M :: AminoAcidX
N :: AminoAcidX
P :: AminoAcidX
Q :: AminoAcidX
R :: AminoAcidX
S :: AminoAcidX
T :: AminoAcidX
V :: AminoAcidX
W :: AminoAcidX
Y :: AminoAcidX
Gap :: AminoAcidX
instance Data.Vector.Unboxed.Base.Unbox ELynx.Data.Character.AminoAcidX.AminoAcidX
instance Data.Vector.Generic.Mutable.Base.MVector Data.Vector.Unboxed.Base.MVector ELynx.Data.Character.AminoAcidX.AminoAcidX
instance Data.Vector.Generic.Base.Vector Data.Vector.Unboxed.Base.Vector ELynx.Data.Character.AminoAcidX.AminoAcidX
instance ELynx.Data.Character.Character.Character ELynx.Data.Character.AminoAcidX.AminoAcidX
instance ELynx.Data.Character.Character.CharacterX ELynx.Data.Character.AminoAcidX.AminoAcidX
instance GHC.Enum.Bounded ELynx.Data.Character.AminoAcidX.AminoAcidX
instance GHC.Enum.Enum ELynx.Data.Character.AminoAcidX.AminoAcidX
instance GHC.Classes.Ord ELynx.Data.Character.AminoAcidX.AminoAcidX
instance GHC.Classes.Eq ELynx.Data.Character.AminoAcidX.AminoAcidX
instance GHC.Read.Read ELynx.Data.Character.AminoAcidX.AminoAcidX
instance GHC.Show.Show ELynx.Data.Character.AminoAcidX.AminoAcidX
-- | Creation date: Thu Oct 4 18:26:35 2018.
--
-- See header of Alphabet.
--
-- Amino acids with gaps and translation stops.
--
--
-- Amino Acid Code: Three letter Code: Amino Acid:
-- ---------------- ------------------ -----------
-- A Ala Alanine
-- C Cys Cysteine
-- D Asp Aspartic Acid
-- E Glu Glutamic Acid
-- F Phe Phenylalanine
-- G Gly Glycine
-- H His Histidine
-- I Ile Isoleucine
-- K Lys Lysine
-- L Leu Leucine
-- M Met Methionine
-- N Asn Asparagine
-- P Pro Proline
-- Q Gln Glutamine
-- R Arg Arginine
-- S Ser Serine
-- T Thr Threonine
-- V Val Valine
-- W Trp Tryptophan
-- Y Tyr Tyrosine
-- ---------------- ------------------ -----------
-- * Stp No amino acid
-- ---------------- ------------------ -----------
-- - Gap No amino acid (preferred)
-- . Gap No amino acid
--
module ELynx.Data.Character.AminoAcidS
-- | Amino acids.
data AminoAcidS
A :: AminoAcidS
C :: AminoAcidS
D :: AminoAcidS
E :: AminoAcidS
F :: AminoAcidS
G :: AminoAcidS
H :: AminoAcidS
I :: AminoAcidS
K :: AminoAcidS
L :: AminoAcidS
M :: AminoAcidS
N :: AminoAcidS
P :: AminoAcidS
Q :: AminoAcidS
R :: AminoAcidS
S :: AminoAcidS
T :: AminoAcidS
V :: AminoAcidS
W :: AminoAcidS
Y :: AminoAcidS
Stop :: AminoAcidS
Gap :: AminoAcidS
instance Data.Vector.Unboxed.Base.Unbox ELynx.Data.Character.AminoAcidS.AminoAcidS
instance Data.Vector.Generic.Mutable.Base.MVector Data.Vector.Unboxed.Base.MVector ELynx.Data.Character.AminoAcidS.AminoAcidS
instance Data.Vector.Generic.Base.Vector Data.Vector.Unboxed.Base.Vector ELynx.Data.Character.AminoAcidS.AminoAcidS
instance ELynx.Data.Character.Character.Character ELynx.Data.Character.AminoAcidS.AminoAcidS
instance ELynx.Data.Character.Character.CharacterX ELynx.Data.Character.AminoAcidS.AminoAcidS
instance GHC.Enum.Bounded ELynx.Data.Character.AminoAcidS.AminoAcidS
instance GHC.Enum.Enum ELynx.Data.Character.AminoAcidS.AminoAcidS
instance GHC.Classes.Ord ELynx.Data.Character.AminoAcidS.AminoAcidS
instance GHC.Classes.Eq ELynx.Data.Character.AminoAcidS.AminoAcidS
instance GHC.Read.Read ELynx.Data.Character.AminoAcidS.AminoAcidS
instance GHC.Show.Show ELynx.Data.Character.AminoAcidS.AminoAcidS
-- | Creation date: Thu Oct 4 18:26:35 2018.
--
-- See header of Alphabet.
--
-- Amino acid IUPAC code. See also
-- https://www.bioinformatics.org/sms/iupac.html or
-- https://en.wikipedia.org/wiki/International_Union_of_Pure_and_Applied_Chemistry.
--
-- Remarks:
--
--
-- - Question marks (?) are interpreted as unknowns (same as
-- X). However, when a sequence is printed/exported, Xs
-- will be used.
-- - Full stops (.) are interpreted as gaps (same as
-- -). However, when a sequence is printed/exported, -s
-- will be used
--
--
--
-- Amino Acid Code: Three letter Code: Amino Acid:
-- ---------------- ------------------ -----------
-- A Ala Alanine
-- C Cys Cysteine
-- D Asp Aspartic Acid
-- E Glu Glutamic Acid
-- F Phe Phenylalanine
-- G Gly Glycine
-- H His Histidine
-- I Ile Isoleucine
-- K Lys Lysine
-- L Leu Leucine
-- M Met Methionine
-- N Asn Asparagine
-- P Pro Proline
-- Q Gln Glutamine
-- R Arg Arginine
-- S Ser Serine
-- T Thr Threonine
-- V Val Valine
-- W Trp Tryptophan
-- Y Tyr Tyrosine
-- ---------------- ------------------ -----------
-- J Leucine or Isoleucine
-- B Asx Aspartic acid or Asparagine
-- Z Glx Glutamine or Glutamic acid
-- ---------------- ------------------ -----------
-- X Xaa Any amino acid (preferred; used for printing)
-- ? Xaa Any amino acid
-- ---------------- ------------------ -----------
-- * Stp No amino acid
-- ---------------- ------------------ -----------
-- - Gap No amino acid (preferred; used for printing)
-- . Gap No amino acid
--
module ELynx.Data.Character.AminoAcidI
-- | Amino acids.
data AminoAcidI
A :: AminoAcidI
C :: AminoAcidI
D :: AminoAcidI
E :: AminoAcidI
F :: AminoAcidI
G :: AminoAcidI
H :: AminoAcidI
I :: AminoAcidI
K :: AminoAcidI
L :: AminoAcidI
M :: AminoAcidI
N :: AminoAcidI
P :: AminoAcidI
Q :: AminoAcidI
R :: AminoAcidI
S :: AminoAcidI
T :: AminoAcidI
V :: AminoAcidI
W :: AminoAcidI
Y :: AminoAcidI
J :: AminoAcidI
B :: AminoAcidI
Z :: AminoAcidI
X :: AminoAcidI
Stop :: AminoAcidI
Gap :: AminoAcidI
instance Data.Vector.Unboxed.Base.Unbox ELynx.Data.Character.AminoAcidI.AminoAcidI
instance Data.Vector.Generic.Mutable.Base.MVector Data.Vector.Unboxed.Base.MVector ELynx.Data.Character.AminoAcidI.AminoAcidI
instance Data.Vector.Generic.Base.Vector Data.Vector.Unboxed.Base.Vector ELynx.Data.Character.AminoAcidI.AminoAcidI
instance ELynx.Data.Character.Character.Character ELynx.Data.Character.AminoAcidI.AminoAcidI
instance ELynx.Data.Character.Character.CharacterX ELynx.Data.Character.AminoAcidI.AminoAcidI
instance ELynx.Data.Character.Character.CharacterI ELynx.Data.Character.AminoAcidI.AminoAcidI
instance GHC.Enum.Bounded ELynx.Data.Character.AminoAcidI.AminoAcidI
instance GHC.Enum.Enum ELynx.Data.Character.AminoAcidI.AminoAcidI
instance GHC.Classes.Ord ELynx.Data.Character.AminoAcidI.AminoAcidI
instance GHC.Classes.Eq ELynx.Data.Character.AminoAcidI.AminoAcidI
instance GHC.Read.Read ELynx.Data.Character.AminoAcidI.AminoAcidI
instance GHC.Show.Show ELynx.Data.Character.AminoAcidI.AminoAcidI
-- | Creation date: Thu Oct 4 18:26:35 2018.
--
-- See header of Alphabet.
--
-- Amino acids in alphabetical order.
--
--
-- Amino Acid Code: Three letter Code: Amino Acid:
-- ---------------- ------------------ -----------
-- A Ala Alanine
-- C Cys Cysteine
-- D Asp Aspartic Acid
-- E Glu Glutamic Acid
-- F Phe Phenylalanine
-- G Gly Glycine
-- H His Histidine
-- I Ile Isoleucine
-- K Lys Lysine
-- L Leu Leucine
-- M Met Methionine
-- N Asn Asparagine
-- P Pro Proline
-- Q Gln Glutamine
-- R Arg Arginine
-- S Ser Serine
-- T Thr Threonine
-- V Val Valine
-- W Trp Tryptophan
-- Y Tyr Tyrosine
--
module ELynx.Data.Character.AminoAcid
-- | Amino acids.
data AminoAcid
A :: AminoAcid
C :: AminoAcid
D :: AminoAcid
E :: AminoAcid
F :: AminoAcid
G :: AminoAcid
H :: AminoAcid
I :: AminoAcid
K :: AminoAcid
L :: AminoAcid
M :: AminoAcid
N :: AminoAcid
P :: AminoAcid
Q :: AminoAcid
R :: AminoAcid
S :: AminoAcid
T :: AminoAcid
V :: AminoAcid
W :: AminoAcid
Y :: AminoAcid
instance Data.Vector.Unboxed.Base.Unbox ELynx.Data.Character.AminoAcid.AminoAcid
instance Data.Vector.Generic.Mutable.Base.MVector Data.Vector.Unboxed.Base.MVector ELynx.Data.Character.AminoAcid.AminoAcid
instance Data.Vector.Generic.Base.Vector Data.Vector.Unboxed.Base.Vector ELynx.Data.Character.AminoAcid.AminoAcid
instance ELynx.Data.Character.Character.Character ELynx.Data.Character.AminoAcid.AminoAcid
instance GHC.Enum.Bounded ELynx.Data.Character.AminoAcid.AminoAcid
instance GHC.Enum.Enum ELynx.Data.Character.AminoAcid.AminoAcid
instance GHC.Classes.Ord ELynx.Data.Character.AminoAcid.AminoAcid
instance GHC.Classes.Eq ELynx.Data.Character.AminoAcid.AminoAcid
instance GHC.Read.Read ELynx.Data.Character.AminoAcid.AminoAcid
instance GHC.Show.Show ELynx.Data.Character.AminoAcid.AminoAcid
-- | Creation date: Sun May 19 21:06:38 2019.
module ELynx.Data.Alphabet.Character
-- | Alphabet characters; abstracted so that representation can be changed
-- at some point.
data Character
-- | Conversion of Characters.
toWord :: Character -> Word8
-- | Conversion of Characters.
fromWord :: Word8 -> Character
-- | Conversion of Characters.
toChar :: Character -> Char
-- | Conversion of Characters.
fromChar :: Char -> Character
-- | Conversion of Characters.
toString :: [Character] -> String
-- | Conversion of Characters.
fromString :: String -> [Character]
-- | Conversion of Characters.
toCVec :: Character a => Vector Character -> Vector a
-- | Conversion of Characters.
fromCVec :: Character a => Vector a -> Vector Character
instance Data.Vector.Unboxed.Base.Unbox ELynx.Data.Alphabet.Character.Character
instance Data.Vector.Generic.Mutable.Base.MVector Data.Vector.Unboxed.Base.MVector ELynx.Data.Alphabet.Character.Character
instance Data.Vector.Generic.Base.Vector Data.Vector.Unboxed.Base.Vector ELynx.Data.Alphabet.Character.Character
instance GHC.Enum.Bounded ELynx.Data.Alphabet.Character.Character
instance GHC.Classes.Ord ELynx.Data.Alphabet.Character.Character
instance GHC.Classes.Eq ELynx.Data.Alphabet.Character.Character
instance GHC.Show.Show ELynx.Data.Alphabet.Character.Character
instance GHC.Read.Read ELynx.Data.Alphabet.Character.Character
-- | 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.
module ELynx.Data.Alphabet.Alphabet
-- | Available alphabets; for details see alphabetSpec.
data Alphabet
DNA :: Alphabet
DNAX :: Alphabet
DNAI :: Alphabet
Protein :: Alphabet
ProteinX :: Alphabet
ProteinS :: Alphabet
ProteinI :: Alphabet
-- | Alphabet specification. Set is used because it provides fast
-- lookups.
data AlphabetSpec
AlphabetSpec :: !Set Character -> !Set Character -> !Set Character -> !Set Character -> !Set Character -> (Character -> [Character]) -> AlphabetSpec
-- | Standard characters.
[std] :: AlphabetSpec -> !Set Character
-- | Gap characters.
[gap] :: AlphabetSpec -> !Set Character
-- | Unknown characters.
[unknown] :: AlphabetSpec -> !Set Character
-- | Other IUPAC codes.
[iupac] :: AlphabetSpec -> !Set Character
-- | All characters in the alphabet.
[all] :: AlphabetSpec -> !Set Character
-- | Convert from IUPAC to the corresponding standard characters.
[toStd] :: AlphabetSpec -> Character -> [Character]
-- | Get the alphabet specification for a given alphabet.
alphabetSpec :: Alphabet -> AlphabetSpec
-- | Verbose alphabet name.
alphabetDescription :: Alphabet -> String
-- | Test if standard character.
isStd :: Alphabet -> Character -> Bool
-- | Test if gap.
isGap :: Alphabet -> Character -> Bool
-- | Test if unknown.
isUnknown :: Alphabet -> Character -> Bool
-- | Test if extended IUPAC character (excluding gaps and unknowns).
isIUPAC :: Alphabet -> Character -> Bool
-- | Test if member of alphabet.
isMember :: Alphabet -> Character -> Bool
instance GHC.Generics.Generic ELynx.Data.Alphabet.Alphabet.Alphabet
instance GHC.Enum.Bounded ELynx.Data.Alphabet.Alphabet.Alphabet
instance GHC.Enum.Enum ELynx.Data.Alphabet.Alphabet.Alphabet
instance GHC.Classes.Ord ELynx.Data.Alphabet.Alphabet.Alphabet
instance GHC.Classes.Eq ELynx.Data.Alphabet.Alphabet.Alphabet
instance GHC.Read.Read ELynx.Data.Alphabet.Alphabet.Alphabet
instance GHC.Show.Show ELynx.Data.Alphabet.Alphabet.Alphabet
instance Data.Aeson.Types.FromJSON.FromJSON ELynx.Data.Alphabet.Alphabet.Alphabet
instance Data.Aeson.Types.ToJSON.ToJSON ELynx.Data.Alphabet.Alphabet.Alphabet
-- | Creation date: Mon Feb 25 13:32:56 2019.
module ELynx.Data.Alphabet.DistributionDiversity
-- | Entropy of vector.
entropy :: Vector v Double => v Double -> Double
-- | Effective number of used characters measured using entropy. The
-- result only makes sense when the sum of the array is 1.0.
kEffEntropy :: Vector v Double => v Double -> Double
-- | Probability of homoplasy of vector. The result is the probability of
-- binomially sampling the same character twice and only makes sense when
-- the sum of the array is 1.0.
homoplasy :: Vector v Double => v Double -> Double
-- | Effective number of used characters measured using homoplasy.
-- The result only makes sense when the sum of the array is 1.0.
kEffHomoplasy :: Vector v Double => v Double -> Double
-- | For a given code vector of characters, calculate frequency of
-- characters. The input vector has arbitrary length (most often the
-- number of sequences in an alignment), the length of the output vector
-- is the number of characters in the alphabet.
frequencyCharacters :: (Vector v Character, Vector v Int, Vector v Double) => AlphabetSpec -> v Character -> v Double
-- | Creation date: Thu Oct 4 18:26:35 2018.
--
-- See header of Alphabet.
--
--
-- Symbol Description Bases represented Complement
-- ------ ----------- ----------------- ----------
-- A Adenine A T
-- C Cytosine C G
-- G Guanine G C
-- T Thymine T A
--
module ELynx.Data.Character.Nucleotide
-- | Nucleotides.
data Nucleotide
A :: Nucleotide
C :: Nucleotide
G :: Nucleotide
T :: Nucleotide
instance Data.Vector.Unboxed.Base.Unbox ELynx.Data.Character.Nucleotide.Nucleotide
instance Data.Vector.Generic.Mutable.Base.MVector Data.Vector.Unboxed.Base.MVector ELynx.Data.Character.Nucleotide.Nucleotide
instance Data.Vector.Generic.Base.Vector Data.Vector.Unboxed.Base.Vector ELynx.Data.Character.Nucleotide.Nucleotide
instance ELynx.Data.Character.Character.Character ELynx.Data.Character.Nucleotide.Nucleotide
instance GHC.Enum.Bounded ELynx.Data.Character.Nucleotide.Nucleotide
instance GHC.Enum.Enum ELynx.Data.Character.Nucleotide.Nucleotide
instance GHC.Classes.Ord ELynx.Data.Character.Nucleotide.Nucleotide
instance GHC.Classes.Eq ELynx.Data.Character.Nucleotide.Nucleotide
instance GHC.Read.Read ELynx.Data.Character.Nucleotide.Nucleotide
instance GHC.Show.Show ELynx.Data.Character.Nucleotide.Nucleotide
-- | Creation date: Thu Oct 4 18:26:35 2018.
--
-- See header of Alphabet.
--
-- Nucleotide IUPAC code. See also
-- https://www.bioinformatics.org/sms/iupac.html or
-- https://en.wikipedia.org/wiki/International_Union_of_Pure_and_Applied_Chemistry.
--
-- Remarks:
--
--
-- - Question marks (?) are interpreted as unknowns (same as
-- N). However, when a sequence is printed/exported, Ns
-- will be used.
-- - Full stops (.) are interpreted as gaps (same as
-- -). However, when a sequence is printed/exported, -s
-- will be used
--
--
--
-- Symbol Description Bases represented Complement
-- ------ ----------- ----------------- ----------
-- A Adenine A T
-- C Cytosine C G
-- G Guanine G C
-- T Thymine T A
-- ------ ----------- ----------------- ----------
-- U Uracil U A
-- W Weak A T W
-- S Strong C G S
-- M aMino A C K
-- K Keto G T M
-- R puRine A G Y
-- Y pYrimidine C T R
-- B not A C G T V
-- D not C A G T H
-- H not G A C T D
-- V not T A C G B
-- ------ ----------- ----------------- ----------
-- N any A C G T N (preferred)
-- ? any A C G T N
-- ------ ----------- ----------------- ----------
-- - Gap (Zero) - (preferred)
-- . Gap (Zero) -
--
module ELynx.Data.Character.NucleotideI
-- | NucleotideIs.
data NucleotideI
A :: NucleotideI
C :: NucleotideI
G :: NucleotideI
T :: NucleotideI
U :: NucleotideI
W :: NucleotideI
S :: NucleotideI
M :: NucleotideI
K :: NucleotideI
R :: NucleotideI
Y :: NucleotideI
B :: NucleotideI
D :: NucleotideI
H :: NucleotideI
V :: NucleotideI
N :: NucleotideI
Gap :: NucleotideI
instance Data.Vector.Unboxed.Base.Unbox ELynx.Data.Character.NucleotideI.NucleotideI
instance Data.Vector.Generic.Mutable.Base.MVector Data.Vector.Unboxed.Base.MVector ELynx.Data.Character.NucleotideI.NucleotideI
instance Data.Vector.Generic.Base.Vector Data.Vector.Unboxed.Base.Vector ELynx.Data.Character.NucleotideI.NucleotideI
instance ELynx.Data.Character.Character.Character ELynx.Data.Character.NucleotideI.NucleotideI
instance ELynx.Data.Character.Character.CharacterX ELynx.Data.Character.NucleotideI.NucleotideI
instance ELynx.Data.Character.Character.CharacterI ELynx.Data.Character.NucleotideI.NucleotideI
instance GHC.Enum.Bounded ELynx.Data.Character.NucleotideI.NucleotideI
instance GHC.Enum.Enum ELynx.Data.Character.NucleotideI.NucleotideI
instance GHC.Classes.Ord ELynx.Data.Character.NucleotideI.NucleotideI
instance GHC.Classes.Eq ELynx.Data.Character.NucleotideI.NucleotideI
instance GHC.Read.Read ELynx.Data.Character.NucleotideI.NucleotideI
instance GHC.Show.Show ELynx.Data.Character.NucleotideI.NucleotideI
-- | See header of Alphabet.
--
-- Extended nucleotides with gaps. See also
-- https://www.bioinformatics.org/sms/iupac.html or
-- https://en.wikipedia.org/wiki/International_Union_of_Pure_and_Applied_Chemistry.
--
--
-- Symbol Description Bases represented Complement
-- ------ ----------- ----------------- ----------
-- A Adenine A T
-- C Cytosine C G
-- G Guanine G C
-- T Thymine T A
-- ------ ----------- ----------------- ----------
-- - or . Gap (Zero) -
--
module ELynx.Data.Character.NucleotideX
-- | Extended nucleotides.
data NucleotideX
A :: NucleotideX
C :: NucleotideX
G :: NucleotideX
T :: NucleotideX
Gap :: NucleotideX
instance Data.Vector.Unboxed.Base.Unbox ELynx.Data.Character.NucleotideX.NucleotideX
instance Data.Vector.Generic.Mutable.Base.MVector Data.Vector.Unboxed.Base.MVector ELynx.Data.Character.NucleotideX.NucleotideX
instance Data.Vector.Generic.Base.Vector Data.Vector.Unboxed.Base.Vector ELynx.Data.Character.NucleotideX.NucleotideX
instance ELynx.Data.Character.Character.Character ELynx.Data.Character.NucleotideX.NucleotideX
instance ELynx.Data.Character.Character.CharacterX ELynx.Data.Character.NucleotideX.NucleotideX
instance GHC.Enum.Bounded ELynx.Data.Character.NucleotideX.NucleotideX
instance GHC.Enum.Enum ELynx.Data.Character.NucleotideX.NucleotideX
instance GHC.Classes.Ord ELynx.Data.Character.NucleotideX.NucleotideX
instance GHC.Classes.Eq ELynx.Data.Character.NucleotideX.NucleotideX
instance GHC.Read.Read ELynx.Data.Character.NucleotideX.NucleotideX
instance GHC.Show.Show ELynx.Data.Character.NucleotideX.NucleotideX
-- | Creation date: Thu May 16 07:58:50 2019.
--
-- The different universal codes. -
-- https://www.ncbi.nlm.nih.gov/Taxonomy/Utils/wprintgc.cgi?mode=c
-- - http://www.bioinformatics.org/sms2/genetic_code.html -
-- https://en.wikipedia.org/wiki/Genetic_code
module ELynx.Data.Character.Codon
-- | Codons are triplets of characters.
newtype Codon a
Codon :: (a, a, a) -> Codon a
-- | Unsafe conversion from vector with at least three elements; only the
-- first three elements are used, the rest is discarded.
unsafeFromVec :: Vector v a => v a -> Codon a
-- | Universal codes.
data UniversalCode
Standard :: UniversalCode
VertebrateMitochondrial :: UniversalCode
-- | Translate a codon to amino acids including translation stops.
translate :: UniversalCode -> Codon Nucleotide -> AminoAcidS
-- | Translate a codon to amino acids including translation stops.
-- Translate codons including gaps to amino acid gaps. Be careful, single
-- or two character gaps can lead to a reading frame shift and hence, the
-- translated sequence may be bogus.
translateX :: UniversalCode -> Codon NucleotideX -> AminoAcidS
-- | Translate a codon to amino acids including translation stops.
-- Translate gap triplets to amino acid gaps, and triplets including
-- unknowns to amino acid unknowns. Be careful, also translates other
-- IUPAC characters to amino acid Xs!
translateI :: UniversalCode -> Codon NucleotideI -> AminoAcidI
instance GHC.Generics.Generic ELynx.Data.Character.Codon.UniversalCode
instance GHC.Enum.Bounded ELynx.Data.Character.Codon.UniversalCode
instance GHC.Enum.Enum ELynx.Data.Character.Codon.UniversalCode
instance GHC.Classes.Ord ELynx.Data.Character.Codon.UniversalCode
instance GHC.Classes.Eq ELynx.Data.Character.Codon.UniversalCode
instance GHC.Read.Read ELynx.Data.Character.Codon.UniversalCode
instance GHC.Show.Show ELynx.Data.Character.Codon.UniversalCode
instance GHC.Classes.Ord a => GHC.Classes.Ord (ELynx.Data.Character.Codon.Codon a)
instance GHC.Classes.Eq a => GHC.Classes.Eq (ELynx.Data.Character.Codon.Codon a)
instance GHC.Read.Read a => GHC.Read.Read (ELynx.Data.Character.Codon.Codon a)
instance GHC.Show.Show a => GHC.Show.Show (ELynx.Data.Character.Codon.Codon a)
instance Data.Aeson.Types.FromJSON.FromJSON ELynx.Data.Character.Codon.UniversalCode
instance Data.Aeson.Types.ToJSON.ToJSON ELynx.Data.Character.Codon.UniversalCode
-- | Creation date: Fri Oct 5 23:00:17 2018.
module ELynx.Data.Sequence.Defaults
-- | Space reserved for sequence names when printing them.
nameWidth :: Int
-- | The length shown when summarizing sequences.
summaryLength :: Int
-- | How many sequences are shown in summary.
summaryNSequences :: Int
-- | Field width for tables.
fieldWidth :: Int
-- | Creation date: Thu Oct 4 18:54:51 2018.
--
-- This module is to be imported qualified.
module ELynx.Data.Sequence.Sequence
-- | For now, Names are just ByteStrings.
type Name = ByteString
-- | The description of a sequence.
type Description = ByteString
-- | The vector of characters of a sequence.
type Characters = Vector Character
-- | Sequences have a name, a possibly empty description, a code and
-- hopefully a lot of data.
data Sequence
Sequence :: Name -> Description -> Alphabet -> Characters -> Sequence
[name] :: Sequence -> Name
[description] :: Sequence -> Description
[alphabet] :: Sequence -> Alphabet
[characters] :: Sequence -> Characters
-- | Convert byte string to sequence characters.
fromByteString :: ByteString -> Characters
-- | Convert sequence characters to byte string.
toByteString :: Characters -> ByteString
-- | A short description of the sequence.
header :: [Sequence] -> ByteString
-- | Trim and show a Sequence.
summarize :: Sequence -> ByteString
-- | Trim and show a list of Sequences.
summarizeSequences :: [Sequence] -> ByteString
-- | Trim and show a list of Sequences.
body :: [Sequence] -> ByteString
-- | Calculate length of Sequence.
length :: Sequence -> Int
-- | Check if all Sequences have equal length.
equalLength :: [Sequence] -> Bool
-- | Find the longest Sequence in a list.
longest :: [Sequence] -> Sequence
-- | Trim to given length.
trim :: Int -> Sequence -> Sequence
-- | Concatenate two sequences. Names have to match.
concat :: Sequence -> Sequence -> Sequence
-- | Concatenate a list of sequences, see concat.
concatSequences :: [[Sequence]] -> [Sequence]
-- | Only take Sequences that are shorter than a given number.
filterShorterThan :: Int -> [Sequence] -> [Sequence]
-- | Only take Sequences that are longer than a given number.
filterLongerThan :: Int -> [Sequence] -> [Sequence]
-- | Only take Sequences that contain at least on non-IUPAC
-- character.
filterStandard :: [Sequence] -> [Sequence]
instance GHC.Classes.Eq ELynx.Data.Sequence.Sequence.Sequence
instance GHC.Show.Show ELynx.Data.Sequence.Sequence.Sequence
-- | Creation date: Thu Oct 4 18:40:18 2018.
--
-- This module is to be imported qualified.
module ELynx.Data.Sequence.Alignment
-- | A collection of sequences.
data Alignment
Alignment :: [Name] -> [Description] -> Alphabet -> Matrix Character -> Alignment
[names] :: Alignment -> [Name]
[descriptions] :: Alignment -> [Description]
[alphabet] :: Alignment -> Alphabet
[matrix] :: Alignment -> Matrix Character
-- | Number of sites.
length :: Alignment -> Int
-- | Number of sequences.
nSequences :: Alignment -> Int
-- | Create Alignment from a list of Sequences.
fromSequences :: [Sequence] -> Either String Alignment
-- | Conversion to list of Sequences.
toSequences :: Alignment -> [Sequence]
-- | Similar to summarizeSequenceList but with different Header.
summarize :: Alignment -> ByteString
-- | Join two Alignments vertically. That is, add more sequences to
-- an alignment. See also concat.
join :: Alignment -> Alignment -> Alignment
-- | Concatenate two Alignments horizontally. That is, add more
-- sites to an alignment. See also join.
concat :: Alignment -> Alignment -> Alignment
-- | Concatenate a list of Alignments horizontally. See
-- concat.
concatAlignments :: [Alignment] -> Alignment
-- | Only keep columns with standard characters. Alignment columns with
-- IUPAC characters are removed.
filterColsOnlyStd :: Alignment -> Alignment
-- | Filter columns with proportion of standard character larger than given
-- number.
filterColsStd :: Double -> Alignment -> Alignment
-- | Only keep columns without gaps or unknown characters.
filterColsNoGaps :: Alignment -> Alignment
-- | Frequency data; do not store the actual characters, but their
-- frequencies. The matrix is of size N x K, where N is
-- the number of sites, and K is the number of characters.
type FrequencyData = Matrix Double
-- | Calculate the distribution of characters.
distribution :: FrequencyData -> [Double]
-- | Calculcate frequency of characters at each site of a multi sequence
-- alignment.
toFrequencyData :: Alignment -> FrequencyData
-- | Diversity analysis. See kEffEntropy.
kEffEntropy :: FrequencyData -> [Double]
-- | Diversity analysis. See kEffEntropy.
kEffHomoplasy :: FrequencyData -> [Double]
-- | Count the number of standard (i.e., not extended IUPAC) characters in
-- the alignment.
countIUPACChars :: Alignment -> Int
-- | Count the number of gaps in the alignment.
countGaps :: Alignment -> Int
-- | Count the number of unknown characters in the alignment.
countUnknowns :: Alignment -> Int
-- | Sample the given sites from a multi sequence alignment.
subSample :: [Int] -> Alignment -> Alignment
-- | Randomly sample a given number of sites of the multi sequence
-- alignment.
randomSubSample :: PrimMonad m => Int -> Alignment -> Gen (PrimState m) -> m Alignment
instance GHC.Classes.Eq ELynx.Data.Sequence.Alignment.Alignment
instance GHC.Show.Show ELynx.Data.Sequence.Alignment.Alignment
-- | Creation date: Fri May 17 13:49:18 2019.
module ELynx.Data.Sequence.Translate
-- | Translate a sequence from DNA or DNAX to
-- ProteinS.
translateSeq :: UniversalCode -> Int -> Sequence -> Sequence
-- | Write FASTA files.
--
-- NCBI file specifications.
module ELynx.Export.Sequence.Fasta
-- | Convert a Sequence to Fasta format.
sequenceToFasta :: Sequence -> ByteString
-- | Convert a list Sequences to Fasta format. A newline is added
-- between any two Sequences.
sequencesToFasta :: [Sequence] -> ByteString
-- | Parse FASTA files.
--
-- NCBI file specifications.
module ELynx.Import.Sequence.Fasta
-- | Parse a sequence of characters.
fastaSequence :: Alphabet -> Parser Sequence
-- | Parse a Fasta file with given Alphabet.
fasta :: Alphabet -> Parser [Sequence]