diff --git a/Biobase/AAseq.hs b/Biobase/AAseq.hs new file mode 100644 --- /dev/null +++ b/Biobase/AAseq.hs @@ -0,0 +1,253 @@ +{-# LANGUAGE FlexibleInstances #-} +{-# LANGUAGE TypeOperators #-} +{-# LANGUAGE MultiParamTypeClasses #-} +{-# LANGUAGE GeneralizedNewtypeDeriving #-} +{-# LANGUAGE StandaloneDeriving #-} +{-# LANGUAGE PatternGuards #-} +{-# LANGUAGE ViewPatterns #-} + +-- | This module has the translation tables for the genetic code. + +module Biobase.AAseq where + +import Control.Arrow ((***)) +import Data.Ix (Ix(..)) +import Data.Primitive.Types +import Data.Tuple (swap) +import GHC.Base (remInt,quotInt) +import qualified Data.ByteString.Char8 as BS +import qualified Data.ByteString.Lazy.Char8 as BSL +import qualified Data.Map.Strict as M +import qualified Data.Text as T +import qualified Data.Vector.Generic as VG +import qualified Data.Vector.Generic.Mutable as VGM +import qualified Data.Vector.Unboxed as VU + +import Data.Array.Repa.ExtShape +import Data.Array.Repa.Index +import Data.Array.Repa.Shape + +import Biobase.Primary + + + +-- | The amino acid newtype. + +newtype AA = AA { unAA :: Int } + deriving (Eq,Ord,Ix) + + + +-- * Creating functions and aa data. + +(aStop:aA:aB:aC:aD:aE:aF:aG:aH:aI:aK:aL:aM:aN:aP:aQ:aR:aS:aT:aV:aW:aX:aY:aZ:aUndefined:_) = map AA [0..] + +aaRange = [aStop .. pred aUndefined] + +-- | Translate 'Char' amino acid representation into efficient 'AA' newtype. + +toAA :: Char -> AA +toAA ((`lookup` charAAList) -> Just aa) = aa +toAA c = error $ "unknown AA: " ++ show c + +-- | 'Char' representation of an 'AA'. + +fromAA :: AA -> Char +fromAA ((`lookup` aACharList) -> Just c) = c +fromAA (AA aa) = error $ "unknown AA: " ++ (show aa) + +-- | Create amino acid sequences from different data sources. + +class MkAAseq x where + mkAAseq :: x -> VU.Vector AA + +type AAseq = VU.Vector AA + +-- | Using the codon table, create an 'AAseq' from the 'Primary' sequence. + +primaryToAAseq :: Primary -> AAseq +primaryToAAseq = mkAAseq . go where + go (VU.length -> 0) = [] + go (VU.splitAt 3 -> (VU.toList -> hs,ts)) = case M.lookup hs nucCodonTable of + Just aa -> aa : go ts + _ -> error $ "primaryToAAseq: " ++ show (hs,ts) + + + +-- * lookup tables + +charAAList = + [ ('/',aStop) + , ('A',aA) + , ('B',aB) + , ('C',aC) + , ('D',aD) + , ('E',aE) + , ('F',aF) + , ('G',aG) + , ('H',aH) + , ('I',aI) + , ('K',aK) + , ('L',aL) + , ('M',aM) + , ('N',aN) + , ('P',aP) + , ('Q',aQ) + , ('R',aR) + , ('S',aS) + , ('T',aT) + , ('V',aV) + , ('W',aW) + , ('X',aX) + , ('Y',aY) + , ('Z',aZ) + ] + +aACharList = map swap charAAList + +codonTable = M.fromList + [ ("aaa",'K') + , ("aac",'N') + , ("aag",'K') + , ("aat",'N') + , ("aca",'T') + , ("acc",'T') + , ("acg",'T') + , ("act",'T') + , ("aga",'R') + , ("agc",'S') + , ("agg",'R') + , ("agt",'S') + , ("ata",'I') + , ("atc",'I') + , ("atg",'M') + , ("att",'I') + , ("caa",'Q') + , ("cac",'H') + , ("cag",'Q') + , ("cat",'H') + , ("cca",'P') + , ("ccc",'P') + , ("ccg",'P') + , ("cct",'P') + , ("cga",'R') + , ("cgc",'R') + , ("cgg",'R') + , ("cgt",'R') + , ("cta",'L') + , ("ctc",'L') + , ("ctg",'L') + , ("ctt",'L') + , ("gaa",'E') + , ("gac",'D') + , ("gag",'E') + , ("gat",'D') + , ("gca",'A') + , ("gcc",'A') + , ("gcg",'A') + , ("gct",'A') + , ("gga",'G') + , ("ggc",'G') + , ("ggg",'G') + , ("ggt",'G') + , ("gta",'V') + , ("gtc",'V') + , ("gtg",'V') + , ("gtt",'V') + , ("taa",'/') + , ("tac",'Y') + , ("tag",'/') + , ("tat",'Y') + , ("tca",'S') + , ("tcc",'S') + , ("tcg",'S') + , ("tct",'S') + , ("tga",'/') + , ("tgc",'C') + , ("tgg",'W') + , ("tgt",'C') + , ("tta",'L') + , ("ttc",'F') + , ("ttg",'L') + , ("ttt",'F') + ] + +nucCodonTable = M.fromList . map (map mkNuc *** toAA) . M.assocs $ codonTable + + + +-- * instances + +instance Show AA where + show n = [fromAA n] + +instance Read AA where + readsPrec p [] = [] + readsPrec p (x:xs) + | x==' ' = readsPrec p xs + | Just aa <- x `lookup` charAAList = [(aa,xs)] + | otherwise = [] + +deriving instance Prim AA +deriving instance VGM.MVector VU.MVector AA +deriving instance VG.Vector VU.Vector AA +deriving instance VU.Unbox AA + +instance (Shape sh,Show sh) => Shape (sh :. AA) where + rank (sh:._) = rank sh + 1 + zeroDim = zeroDim:.AA 0 + unitDim = unitDim:.AA 1 -- TODO does this one make sense? + intersectDim (sh1:.n1) (sh2:.n2) = intersectDim sh1 sh2 :. min n1 n2 + addDim (sh1:.AA n1) (sh2:.AA n2) = addDim sh1 sh2 :. AA (n1+n2) -- TODO will not necessarily yield a valid Nuc + size (sh1:.AA n) = size sh1 * n + sizeIsValid (sh1:.AA n) = sizeIsValid (sh1:.n) + toIndex (sh1:.AA sh2) (sh1':.AA sh2') = toIndex (sh1:.sh2) (sh1':.sh2') + fromIndex (ds:.AA d) n = fromIndex ds (n `quotInt` d) :. AA r where + r | rank ds == 0 = n + | otherwise = n `remInt` d + inShapeRange (sh1:.n1) (sh2:.n2) (idx:.i) = i>=n1 && i error "empty list in shapeOfList/Primary" + x:xs -> shapeOfList xs :. AA x + deepSeq (sh:.n) x = deepSeq sh (n `seq` x) + {-# INLINE rank #-} + {-# INLINE zeroDim #-} + {-# INLINE unitDim #-} + {-# INLINE intersectDim #-} + {-# INLINE addDim #-} + {-# INLINE size #-} + {-# INLINE sizeIsValid #-} + {-# INLINE toIndex #-} + {-# INLINE fromIndex #-} + {-# INLINE inShapeRange #-} + {-# INLINE listOfShape #-} + {-# INLINE shapeOfList #-} + {-# INLINE deepSeq #-} + +instance (Shape sh, Show sh, ExtShape sh) => ExtShape (sh :. AA) where + subDim (sh1:.AA n1) (sh2:.AA n2) = subDim sh1 sh2 :. AA (n1-n2) + rangeList (sh1:.AA n1) (sh2:.AA n2) = [ sh:.AA n | sh <- rangeList sh1 sh2, n <- [n1 .. (n1+n2)]] + +instance Enum AA where + toEnum = AA + fromEnum = unAA + +instance MkAAseq [Char] where + mkAAseq = VU.fromList . map toAA + +instance MkAAseq [AA] where + mkAAseq = VU.fromList + +instance MkAAseq (VU.Vector Char) where + mkAAseq = VU.map toAA + +instance MkAAseq BS.ByteString where + mkAAseq = VU.fromList . map toAA . BS.unpack + +instance MkAAseq BSL.ByteString where + mkAAseq = VU.fromList . map toAA . BSL.unpack + +instance MkAAseq T.Text where + mkAAseq = VU.fromList . map toAA . T.unpack + diff --git a/Biobase/Codon.hs b/Biobase/Codon.hs deleted file mode 100644 --- a/Biobase/Codon.hs +++ /dev/null @@ -1,73 +0,0 @@ - --- | This module has the translation tables for the genetic code. - -module Biobase.Codon where - -import qualified Data.Map.Strict as M - -codonTable = M.fromList - [ ("aaa",'K') - , ("aac",'N') - , ("aag",'K') - , ("aat",'N') - , ("aca",'T') - , ("acc",'T') - , ("acg",'T') - , ("act",'T') - , ("aga",'R') - , ("agc",'S') - , ("agg",'R') - , ("agt",'S') - , ("ata",'I') - , ("atc",'I') - , ("atg",'M') - , ("att",'I') - , ("caa",'Q') - , ("cac",'H') - , ("cag",'Q') - , ("cat",'H') - , ("cca",'P') - , ("ccc",'P') - , ("ccg",'P') - , ("cct",'P') - , ("cga",'R') - , ("cgc",'R') - , ("cgg",'R') - , ("cgt",'R') - , ("cta",'L') - , ("ctc",'L') - , ("ctg",'L') - , ("ctt",'L') - , ("gaa",'E') - , ("gac",'D') - , ("gag",'E') - , ("gat",'D') - , ("gca",'A') - , ("gcc",'A') - , ("gcg",'A') - , ("gct",'A') - , ("gga",'G') - , ("ggc",'G') - , ("ggg",'G') - , ("ggt",'G') - , ("gta",'V') - , ("gtc",'V') - , ("gtg",'V') - , ("gtt",'V') - , ("taa",'/') - , ("tac",'Y') - , ("tag",'/') - , ("tat",'Y') - , ("tca",'S') - , ("tcc",'S') - , ("tcg",'S') - , ("tct",'S') - , ("tga",'/') - , ("tgc",'C') - , ("tgg",'W') - , ("tgt",'C') - , ("tta",'L') - , ("ttc",'F') - , ("ttg",'L') - , ("ttt",'F') - ] diff --git a/Biobase/Primary.hs b/Biobase/Primary.hs --- a/Biobase/Primary.hs +++ b/Biobase/Primary.hs @@ -164,24 +164,6 @@ subDim (sh1:.Nuc n1) (sh2:.Nuc n2) = subDim sh1 sh2 :. Nuc (n1-n2) rangeList (sh1:.Nuc n1) (sh2:.Nuc n2) = [ sh:.Nuc n | sh <- rangeList sh1 sh2, n <- [n1 .. (n1+n2)]] -{- --- | The bounded instance from GHC proper. Captures all defined symbols. - -instance Bounded Nuc where - minBound = nN - maxBound = nT - --- | Special bounds for energy / score arrays - -instance Bounds Nuc where - minNormal = nA - maxNormal = nT - minExtended = nN - maxExtended = nT - - --} - -- | Enum instance Enum Nuc where diff --git a/Biobase/Primary/IUPAC.hs b/Biobase/Primary/IUPAC.hs new file mode 100644 --- /dev/null +++ b/Biobase/Primary/IUPAC.hs @@ -0,0 +1,50 @@ +{-# LANGUAGE TemplateHaskell #-} + +-- | Degenerate base symbol representation. We use the same conventions as in +-- <> which ignores +-- @U@racil, except if it stands alone. Therefore, any RNA sequence should be +-- converted to DNA (and back afterwards). +-- +-- NOTE that the generic 'Char' instance is not optimized for speed. +-- +-- TODO this should be easier once we have instances for RNA,DNA, etc + +module Biobase.Primary.IUPAC where + +import Data.ByteString.Char8 (ByteString,unpack) +import Data.FileEmbed (embedFile) +import Data.List (nub,sort) +import Data.Tuple (swap) + + + +class Degenerate x where + fromSymbol :: x -> [x] + toSymbol :: [x] -> Maybe x + +instance Degenerate Char where + fromSymbol = maybe [] id . flip lookup iupacList + toSymbol = flip lookup (map swap iupacList) . nub . sort + +-- instance Degenerate RNA where +-- +-- instance Degenerate DNA where +-- +-- instance Degenerate XNA where -- if we want a combined alphabet + + + +-- ** Raw embeddings + +-- | list of characters + +iupacList :: [(Char,String)] +iupacList = map (go . words) . lines . unpack $ iupacNucleotides where + go [[c],cs] = (c,cs) +{-# NOINLINE iupacList #-} + +-- | Raw iupac data, embedded into the library. + +iupacNucleotides :: ByteString +iupacNucleotides = $(embedFile "sources/iupac-nucleotides") + diff --git a/BiobaseXNA.cabal b/BiobaseXNA.cabal --- a/BiobaseXNA.cabal +++ b/BiobaseXNA.cabal @@ -1,5 +1,5 @@ name: BiobaseXNA -version: 0.7.0.2 +version: 0.8.1.0 author: Christian Hoener zu Siederdissen maintainer: choener@tbi.univie.ac.at homepage: http://www.tbi.univie.ac.at/~choener/ @@ -13,21 +13,19 @@ cabal-version: >= 1.6.0 description: This is a base library for bioinformatics with emphasis on RNA - and DNA primary structure. + and DNA primary structure as well as amino acid sequences. . Provided are efficient encodings for short sequences, as required by RNA folding tools. Extended RNA secondary structures can be represented as well. . - . - . Contains data from: . + @ Frequency and isostericity of RNA base pairs - . Jesse Stombaugh, Craig L. Zirbel, Eric Westhof, and Neocles B. Leontis - . Nucl. Acids Res. (2009) + @ . @@ -36,6 +34,7 @@ extra-source-files: sources/isostericity-matrices.csv sources/isostericity-detailed.csv + sources/iupac-nucleotides changelog library @@ -46,17 +45,18 @@ csv >= 0.1.2 , file-embed >= 0.0.4.7 , primitive >= 0.5 , - PrimitiveArray >= 0.5 , + PrimitiveArray >= 0.5.3 , repa >= 3.2 , text >= 0.11 , tuple >= 0.2 , vector >= 0.10 exposed-modules: - Biobase.Codon + Biobase.AAseq Biobase.Primary Biobase.Primary.Bounds Biobase.Primary.Hashed + Biobase.Primary.IUPAC Biobase.Secondary Biobase.Secondary.Constraint Biobase.Secondary.Diagrams diff --git a/changelog b/changelog --- a/changelog +++ b/changelog @@ -1,8 +1,21 @@ +0.8.1.0 +------- + +- Biobase.Primary.IUPAC for degenerate base symbol conversion + +0.8.0.0 +------- + +- Biobase.Codon -> Biobase.AAseq +- and efficient encoding of AAseqs + 0.7 - * updated to PrimitiveArray >= 0.5 +--- - * added Codon table +- updated to PrimitiveArray >= 0.5 +- added Codon table 0.6.2.0 +------- - * Updated to PrimitiveArray >= 0.2.0.0 +- Updated to PrimitiveArray >= 0.2.0.0 diff --git a/sources/iupac-nucleotides b/sources/iupac-nucleotides new file mode 100644 --- /dev/null +++ b/sources/iupac-nucleotides @@ -0,0 +1,16 @@ +A A +C C +G G +T T +U U +W AT +S CG +M AC +K GT +R AG +Y CT +B CGT +D AGT +H ACT +V ACG +N ACGT