BiobaseTypes 0.1.4.0 → 0.2.0.0

raw patch · 16 files changed

+467/−319 lines, 16 filesdep ~PrimitiveArraydep ~SciBaseTypesPVP ok

version bump matches the API change (PVP)

Dependency ranges changed: PrimitiveArray, SciBaseTypes

API changes (from Hackage documentation)

Files

• Biobase/Types/AminoAcidSequence.hs +0/−59
• Biobase/Types/BioSequence.hs +311/−0
• Biobase/Types/Bitscore.hs +11/−0
• Biobase/Types/Codon.hs +20/−0
• Biobase/Types/Energy.hs +3/−2
• Biobase/Types/Evalue.hs +2/−0
• Biobase/Types/Index.hs +7/−13
• Biobase/Types/Index/Type.hs +7/−5
• Biobase/Types/NucleotideSequence.hs +0/−217
• Biobase/Types/ReadingFrame.hs +29/−11
• Biobase/Types/Strand.hs +8/−1
• BiobaseTypes.cabal +11/−7
• DP/Backtraced/BioSequence.hs +3/−0
• DP/Backtraced/Codon.hs +46/−0
• changelog.md +5/−0
• tests/properties.hs +4/−4

@@ -1,59 +0,0 @@---- | Encode the allowed amino acids in a better way.--module Biobase.Types.AminoAcidSequence where--import           Control.DeepSeq-import           Control.Lens-import           Data.ByteString (ByteString)-import           Data.Char (ord,chr,toUpper)-import           Data.Data (Data)-import           Data.Typeable (Typeable)-import           GHC.Exts (IsString(..))-import           GHC.Generics (Generic)-import qualified Data.ByteString.Char8 as BS-import qualified Data.ByteString.UTF8 as BSU-import           Test.QuickCheck (Arbitrary(..))-import qualified Test.QuickCheck as TQ------ | A short amino acid suquence.------ It is an instance of 'Ixed' to allow @RNAseq (BS.pack "cag") ^? ix 2 == Just 'g'@.--newtype AAseq = AAseq { _aaseq ∷ ByteString }-  deriving (Data, Typeable, Generic, Eq, Ord, Read, Show)-makeLenses ''AAseq--instance NFData AAseq--type instance Index AAseq = Int--type instance IxValue AAseq = Char--instance Ixed AAseq where-  ix k = aaseq . ix k . iso (chr . fromIntegral) (fromIntegral . ord)-  {-# Inline ix #-}--deriving instance Reversing AAseq--mkAAseq ∷ ByteString → AAseq-mkAAseq = AAseq . BS.map go . BS.map toUpper-  where go x | x `elem` aas = x-             | otherwise    = 'X'-        aas ∷ String-        aas = "ARNDCEQGHILKMFPSTWYVUO"--instance IsString AAseq where-  fromString = mkAAseq . BS.pack--instance Arbitrary AAseq where-  arbitrary = do-    k ← TQ.choose (0,100)-    xs ← TQ.vectorOf k $ TQ.elements "ARNDCEQGHILKMFPSTWYVUO"-    return . AAseq $ BS.pack xs-  shrink = view (to shrink)---

@@ -0,0 +1,311 @@++-- | Abstraction over bio sequences encoded as one-ascii character as one+-- symbol. We phantom-type the exact bio-sequence type and provide type classes+-- that act on known types.+--+-- Unknown bio sequences should be tagged with @Void@.++module Biobase.Types.BioSequence where++import           Control.DeepSeq+import           Control.Lens+import           Data.ByteString.Char8 (ByteString)+import           Data.Char (ord,chr,toUpper)+import           Data.Data (Data)+import           Data.Typeable (Typeable)+import           Data.Void+import           GHC.Exts (IsString(..))+import           GHC.Generics (Generic)+import qualified Data.ByteString.Char8 as BS+import qualified Test.QuickCheck as TQ+import           Test.QuickCheck (Arbitrary(..))+import qualified Data.ByteString.UTF8 as BSU++import           Biobase.Types.Strand+import qualified Biobase.Types.Index as BTI++++-- * Sequence identifiers++newtype SequenceIdentifier (which ∷ k) = SequenceIdentifier { _sequenceIdentifier ∷ ByteString }+  deriving (Data, Typeable, Generic, Eq, Ord, Read, Show)+makeWrapped ''SequenceIdentifier+makePrisms ''SequenceIdentifier++instance NFData (SequenceIdentifier w)++instance IsString (SequenceIdentifier w) where+  fromString = SequenceIdentifier . BSU.fromString++++-- * Bio-Sequences++data RNA++data DNA++data XNA++data AA++++newtype BioSequence (which ∷ k) = BioSequence {_bioSequence ∷ ByteString}+  deriving (Data, Typeable, Generic, Eq, Ord, Read, Show, Semigroup)+makeWrapped ''BioSequence+makePrisms ''BioSequence++instance NFData (BioSequence w)++type instance Index (BioSequence w) = Int++type instance IxValue (BioSequence w) = Char++instance Ixed (BioSequence w) where+  ix k = _BioSequence . ix k . iso (chr . fromIntegral) (fromIntegral . ord)+  {-# Inline ix #-}++deriving instance Reversing (BioSequence w)++instance IsString (BioSequence Void) where+  fromString = BioSequence . BS.pack++++-- * RNA++mkRNAseq ∷ ByteString → BioSequence RNA+mkRNAseq = BioSequence . BS.map go . BS.map toUpper+  where go x | x `elem` acgu = x+             | otherwise     = 'N'+        acgu ∷ String+        acgu = "ACGU"++instance IsString (BioSequence RNA) where+  fromString = mkRNAseq . BS.pack++instance Arbitrary (BioSequence RNA) where+  arbitrary = do+    k ← TQ.choose (0,100)+    xs ← TQ.vectorOf k $ TQ.elements "ACGU"+    return . BioSequence $ BS.pack xs+  shrink = view (to shrink)++++-- * DNA++mkDNAseq ∷ ByteString → (BioSequence DNA)+mkDNAseq = BioSequence . BS.map go . BS.map toUpper+  where go x | x `elem` acgt = x+             | otherwise     = 'N'+        acgt ∷ String+        acgt = "ACGT"++instance IsString (BioSequence DNA) where+  fromString = mkDNAseq . BS.pack++instance Arbitrary (BioSequence DNA) where+  arbitrary = do+    k ← TQ.choose (0,100)+    xs ← TQ.vectorOf k $ TQ.elements "ACGT"+    return . BioSequence $ BS.pack xs+  shrink = view (to shrink)++++-- * XNA++mkXNAseq ∷ ByteString → (BioSequence XNA)+mkXNAseq = BioSequence . BS.map go . BS.map toUpper+  where go x | x `elem` acgtu = x+             | otherwise      = 'N'+        acgtu ∷ String+        acgtu = "ACGTU"++instance IsString (BioSequence XNA) where+  fromString = mkXNAseq . BS.pack++instance Arbitrary (BioSequence XNA) where+  arbitrary = do+    k ← TQ.choose (0,100)+    xs ← TQ.vectorOf k $ TQ.elements "ACGTU"+    return . BioSequence $ BS.pack xs+  shrink = view (to shrink)++++-- * Amino acid sequences++mkAAseq ∷ ByteString → (BioSequence AA)+mkAAseq = BioSequence . BS.map go . BS.map toUpper+  where go x | x `elem` aas = x+             | otherwise    = 'X'+        aas ∷ String+        aas = "ARNDCEQGHILKMFPSTWYVUO"++instance IsString (BioSequence AA) where+  fromString = mkAAseq . BS.pack++instance Arbitrary (BioSequence AA) where+  arbitrary = do+    k ← TQ.choose (0,100)+    xs ← TQ.vectorOf k $ TQ.elements "ARNDCEQGHILKMFPSTWYVUO"+    return . BioSequence $ BS.pack xs+  shrink = view (to shrink)++++-- * A window into a longer sequence with prefix/suffix information.++-- | Phantom-typed over two types, the type @w@ of the identifier, which can be+-- descriptive ("FirstInput") and the second type, identifying what kind of+-- sequence types we are dealing with. Finally, the third type fixes the index+-- type of the infix.++data BioSequenceWindow w ty k = BioSequenceWindow+  { _bswIdentifier ∷ !(SequenceIdentifier w)+    -- ^ Identifier for this window. Typically some fasta identifier+  , _bswPrefix     ∷ !(BioSequence ty)+    -- ^ Any prefix for this sequence+  , _bswSequence   ∷ !(BioSequence ty)+    -- ^ The actual sequence, the infix+  , _bswSuffix     ∷ !(BioSequence ty)+    -- ^ any suffix+  , _bswStrand     ∷ !Strand+    -- ^ strand information. Probably '+' but arbitrary+  , _bswIndex ∷ !(BTI.Index k)+    -- ^ Provide the index for the left-most character of the @bswSequence@ on+    -- '+' on '-' as well, but to be interpreted on the '+' strand.+    -- TODO this actually needs a more complicated encoding...!+  }+  deriving (Data, Typeable, Generic, Eq, Ord, Read, Show)+makeLenses ''BioSequenceWindow++instance Reversing (BioSequenceWindow w ty k) where+  {-# Inlinable reversing #-}+  reversing bsw = bsw+                & bswPrefix .~ (bsw^.bswSuffix.reversed)+                & bswSuffix .~ (bsw^.bswPrefix.reversed)+                & bswSequence .~ (bsw^.bswSequence.reversed)+                & bswStrand .~ (bsw^.bswStrand.reversed)++-- | A lens into the full sequence information of a sequence window. One should+-- *NOT* modify the length of the individual sequences.++bswFullSequence ∷ Lens' (BioSequenceWindow w ty k) (BioSequence ty)+{-# Inlinable bswFullSequence #-}+bswFullSequence = lens f t+  where f bsw = bsw^.bswPrefix <> bsw^.bswSequence <> bsw^.bswSuffix+        t bsw (BioSequence s) =+          let (pfx,ifxsfx) = BS.splitAt (bsw^.bswPrefix._BioSequence.to BS.length) s+              (ifx,sfx) = BS.splitAt (bsw^.bswSequence._BioSequence.to BS.length) ifxsfx+          in  bsw & bswPrefix._BioSequence .~ pfx+                  & bswSequence._BioSequence .~ ifx+                  & bswSuffix._BioSequence .~ sfx++++-- * DNA/RNA++-- | Simple case translation from @U@ to @T@. with upper and lower-case+-- awareness.++rna2dna ∷ Char → Char+rna2dna = \case+  'U' → 'T'+  'u' → 't'+  x   → x+{-# Inline rna2dna #-}++-- | Single character RNA complement.++rnaComplement ∷ Char → Char+rnaComplement = \case+  'A' → 'U'+  'a' → 'u'+  'C' → 'G'+  'c' → 'g'+  'G' → 'C'+  'g' → 'c'+  'U' → 'A'+  'u' → 'a'+  x   → x+{-# Inline rnaComplement #-}++-- | Simple case translation from @T@ to @U@ with upper- and lower-case+-- awareness.++dna2rna ∷ Char → Char+dna2rna = \case+  'T' → 'U'+  't' → 'u'+  x   → x+{-# Inline dna2rna #-}++-- | Single character DNA complement.++dnaComplement ∷ Char → Char+dnaComplement = \case+  'A' → 'T'+  'a' → 't'+  'C' → 'G'+  'c' → 'g'+  'G' → 'C'+  'g' → 'c'+  'T' → 'A'+  't' → 'a'+  x   → x+{-# Inline dnaComplement #-}++++-- | Transcribes a DNA sequence into an RNA sequence. Note that 'transcribe' is+-- actually very generic. We just define its semantics to be that of+-- biomolecular transcription.+--+-- 'transcribe' makes the assumption that, given @DNA -> RNA@, we transcribe+-- the coding strand.+-- <http://hyperphysics.phy-astr.gsu.edu/hbase/Organic/transcription.html>+--+-- @@ DNAseq "ACGT" ^. transcribe == RNAseq "ACGU" RNAseq "ACGU" ^. transcribe+-- == DNAseq "ACGT" RNAseq "ACGU" ^. from transcribe :: DNAseq == DNAseq "ACGT"+-- @@++class Transcribe f where+  type TranscribeTo f ∷ *+  transcribe ∷ Iso' f (TranscribeTo f)++-- | Transcribe a DNA sequence into an RNA sequence. This does not @reverse@+-- the sequence!++instance Transcribe (BioSequence DNA) where+  type TranscribeTo (BioSequence DNA) = (BioSequence RNA)+  transcribe = iso (over _BioSequence (BS.map dna2rna)) (over _BioSequence (BS.map rna2dna))+  {-# Inline transcribe #-}++-- | Transcribe a RNA sequence into an DNA sequence. This does not @reverse@+-- the sequence!++instance Transcribe (BioSequence RNA) where+  type TranscribeTo (BioSequence RNA) = (BioSequence DNA)+  transcribe = from transcribe+  {-# Inline transcribe #-}++++-- | The complement of a biosequence.++class Complement f where+  complement ∷ Iso' f f++instance Complement (BioSequence DNA) where+  complement = iso (over _BioSequence (BS.map dnaComplement)) (over _BioSequence (BS.map dnaComplement))+  {-# Inline complement #-}++instance Complement (BioSequence RNA) where+  complement = iso (over _BioSequence (BS.map rnaComplement)) (over _BioSequence (BS.map rnaComplement))+  {-# Inline complement #-}+

@@ -26,6 +26,7 @@ import qualified Data.Vector.Generic.Mutable as VGM import qualified Data.Vector.Unboxed as VU +import           Algebra.Structure.Semiring import           Numeric.Limits  @@ -40,6 +41,16 @@  newtype Bitscore = Bitscore { getBitscore :: Double }   deriving (Eq,Ord,Read,Show,Num,Fractional,Generic)++instance Semiring Bitscore where+  plus = (+)+  times = (*)+  zero = 0+  one = 1+  {-# Inline plus  #-}+  {-# Inline times #-}+  {-# Inline zero  #-}+  {-# Inline one   #-}  instance Binary    Bitscore instance FromJSON  Bitscore

@@ -0,0 +1,20 @@++module Biobase.Types.Codon where++import Control.Lens+import GHC.Generics (Generic)++++-- | A single codon.+--+-- TODO needs to go into its own place++data Codon c = Codon !c !c !c+  deriving (Eq,Ord,Read,Show,Generic,Functor,Foldable,Traversable)++instance Field1 (Codon c) (Codon c) c c+instance Field2 (Codon c) (Codon c) c c+instance Field3 (Codon c) (Codon c) c c+instance Each (Codon c) (Codon c') c c'+

@@ -13,6 +13,7 @@ import Data.Data import Data.Default import Data.Hashable+import GHC.Real import Data.Serialize (Serialize) import Data.Vector.Unboxed.Deriving import GHC.Generics@@ -56,8 +57,8 @@  -- | Discretized @DG@. -newtype DDG = DDG { dDG ∷ Discretized 1 100 }-  deriving (Eq,Ord,Num,Read,Show,Generic,Integral,Real,Enum)+newtype DDG = DDG { dDG ∷ Discretized (1 :% 100) }+  deriving (Eq,Ord,Num,Read,Show,Generic,Real,Enum)  derivingUnbox "DDG"   [t| DDG → Int |]  [| getDiscretized . dDG |]  [| DDG . Discretized |]

@@ -8,6 +8,7 @@ module Biobase.Types.Evalue where  import           Control.DeepSeq+import           Control.Lens import           Data.Aeson import           Data.Binary import           Data.Default@@ -29,6 +30,7 @@  newtype Evalue = Evalue { getEvalue :: Double }   deriving (Eq,Ord,Read,Show,Num,Generic)+makeWrapped ''Evalue  instance Binary    Evalue instance FromJSON  Evalue

@@ -53,30 +53,24 @@ (+.) i n = checkIndex $ unsafePlus i n {-# Inline (+.) #-} --- | Unsafe plus.--unsafePlus :: forall t . KnownNat t => Index t -> Int -> Index t-unsafePlus i n = Index $ IT.getIndex i + n-{-# Inline unsafePlus #-}- -- | Helper function that allows @subtraction@ of an 'Index' and an 'Int', -- with the 'Int' on the right.  (-.) :: forall t . KnownNat t => Index t -> Int -> Index t-(-.) i n = checkIndex $ unsafeMinus i n+(-.) i n = checkIndex $ unsafePlus i n {-# Inline (-.) #-} +-- | Unsafe plus.++unsafePlus :: forall t . KnownNat t => Index t -> Int -> Index t+unsafePlus i n = Index $ IT.getIndex i + n+{-# Inline unsafePlus #-}+ -- | Delta between two 'Index' points.  delta :: forall t . KnownNat t => Index t -> Index t -> Int delta i j = abs . IT.getIndex $ i - j {-# Inline delta #-}---- | Unsafe minus.--unsafeMinus :: forall t . KnownNat t => Index t -> Int -> Index t-unsafeMinus i n = Index $ IT.getIndex i - n-{-# Inline unsafeMinus #-}  toInt ∷ forall t . KnownNat t ⇒ Index t → Int {-# Inline toInt #-}

@@ -5,15 +5,17 @@ import           Control.DeepSeq import           Data.Aeson import           Data.Binary+import           Data.Data (Data) import           Data.Hashable (Hashable) import           Data.Proxy import           Data.Serialize (Serialize)+import           Data.Typeable (Typeable) import           Data.Vector.Fusion.Stream.Monadic (Step(..), flatten)-import qualified Data.Vector.Fusion.Stream.Monadic as SM import           Data.Vector.Unboxed.Deriving import           GHC.Generics import           GHC.TypeLits import qualified Data.Ix as Ix+import qualified Data.Vector.Fusion.Stream.Monadic as SM import           Test.QuickCheck import           Text.Printf @@ -25,7 +27,7 @@ -- | A linear @Int@-based index type.  newtype Index (t :: Nat) = Index { getIndex :: Int }-  deriving (Show,Read,Eq,Ord,Generic,Ix.Ix)+  deriving (Show,Read,Eq,Ord,Generic,Ix.Ix,Data,Typeable)  -- | Turn an 'Int' into an 'Index' safely. @@ -44,9 +46,9 @@ {-# Inline maybeIndex #-}  instance KnownNat t => Num (Index t) where-  Index a + Index b = error "not implemented, use (+.)" -- index $ a + b-  Index a - Index b = error "not implemented, use (-.)" -- index $ a - b-  Index a * Index b = error "not implemented" -- index $ a * b+  Index a + Index b = error $ show (" Index.(+) not implemented, use (+.)",a,b) -- index $ a + b+  Index a - Index b = error $ show (" Index.(-) not implemented, use (-.)",a,b) -- index $ a - b+  Index a * Index b = error $ show (" Index.(*) not implemented", a,b) -- index $ a * b   negate = error "Indices are natural numbers"   abs = id   signum = index . signum . getIndex

@@ -1,217 +0,0 @@---- | Wrappers around biosequences.--module Biobase.Types.NucleotideSequence where--import           Control.DeepSeq-import           Control.Lens-import           Data.ByteString (ByteString)-import           Data.Char (ord,chr,toUpper)-import           Data.Data (Data)-import           Data.Typeable (Typeable)-import           GHC.Exts (IsString(..))-import           GHC.Generics (Generic)-import qualified Data.ByteString.Char8 as BS-import qualified Data.ByteString.UTF8 as BSU-import           Test.QuickCheck (Arbitrary(..))-import qualified Test.QuickCheck as TQ------ | A sequence identifier. Just a newtype wrapped text field. Because we can--- never know what people are up to, this is utf8-encoded.------ TODO Provide @Iso'@ for @Text@, too?------ TODO move into @Biobase.Types.SequenceID@--newtype SequenceID = SequenceID { _sequenceID ∷ ByteString }-  deriving (Data, Typeable, Generic, Eq, Ord, Read, Show, IsString)-makeLenses ''SequenceID--instance NFData SequenceID---- | Convert to a string in a unicode-aware manner.--sequenceIDstring ∷ Iso' SequenceID String-sequenceIDstring = sequenceID . iso BSU.toString BSU.fromString-{-# Inline sequenceIDstring #-}------ | A short RNA sequence.------ It is an instance of 'Ixed' to allow @RNAseq (BS.pack "cag") ^? ix 2 == Just 'g'@.--newtype RNAseq = RNAseq { _rnaseq ∷ ByteString }-  deriving (Data, Typeable, Generic, Eq, Ord, Read, Show)-makeLenses ''RNAseq--instance NFData RNAseq--type instance Index RNAseq = Int--type instance IxValue RNAseq = Char--instance Ixed RNAseq where-  ix k = rnaseq . ix k . iso (chr . fromIntegral) (fromIntegral . ord)-  {-# Inline ix #-}--deriving instance Reversing RNAseq--mkRNAseq ∷ ByteString → RNAseq-mkRNAseq = RNAseq . BS.map go . BS.map toUpper-  where go x | x `elem` acgu = x-             | otherwise     = 'N'-        acgu ∷ String-        acgu = "ACGU"--instance IsString RNAseq where-  fromString = mkRNAseq . BS.pack--instance Arbitrary RNAseq where-  arbitrary = do-    k ← TQ.choose (0,100)-    xs ← TQ.vectorOf k $ TQ.elements "ACGU"-    return . RNAseq $ BS.pack xs-  shrink = view (to shrink)------ | A short DNA sequence.------ Note everything really long should be handled by specialized libraries with--- streaming capabilities.--newtype DNAseq = DNAseq { _dnaseq ∷ ByteString }-  deriving (Data, Typeable, Generic, Eq, Ord, Read, Show)-makeLenses ''DNAseq--instance NFData DNAseq--type instance Index DNAseq = Int--type instance IxValue DNAseq = Char--instance Ixed DNAseq where-  ix k = dnaseq . ix k . iso (chr . fromIntegral) (fromIntegral . ord)-  {-# Inline ix #-}--mkDNAseq ∷ ByteString → DNAseq-mkDNAseq = DNAseq . BS.map go . BS.map toUpper-  where go x | x `elem` acgt = x-             | otherwise     = 'N'-        acgt ∷ String-        acgt = "ACGT"--instance IsString DNAseq where-  fromString = mkDNAseq . BS.pack--deriving instance Reversing DNAseq--instance Arbitrary DNAseq where-  arbitrary = do-    k ← TQ.choose (0,100)-    xs ← TQ.vectorOf k $ TQ.elements "ACGT"-    return . DNAseq $ BS.pack xs-  shrink = view (to shrink)---- | Simple case translation from @U@ to @T@. with upper and lower-case--- awareness.--rna2dna ∷ Char → Char-rna2dna = \case-  'U' → 'T'-  'u' → 't'-  x   → x-{-# Inline rna2dna #-}---- | Single character RNA complement.--rnaComplement ∷ Char → Char-rnaComplement = \case-  'A' → 'U'-  'a' → 'u'-  'C' → 'G'-  'c' → 'g'-  'G' → 'C'-  'g' → 'c'-  'U' → 'A'-  'u' → 'a'-  x   → x-{-# Inline rnaComplement #-}---- | Simple case translation from @T@ to @U@ with upper- and lower-case--- awareness.--dna2rna ∷ Char → Char-dna2rna = \case-  'T' → 'U'-  't' → 'u'-  x   → x-{-# Inline dna2rna #-}---- | Single character DNA complement.--dnaComplement ∷ Char → Char-dnaComplement = \case-  'A' → 'T'-  'a' → 't'-  'C' → 'G'-  'c' → 'g'-  'G' → 'C'-  'g' → 'c'-  'T' → 'A'-  't' → 'a'-  x   → x-{-# Inline dnaComplement #-}------ | Transcribes a DNA sequence into an RNA sequence. Note that 'transcribe' is--- actually very generic. We just define its semantics to be that of--- biomolecular transcription.------ 'transcribe' makes the assumption that, given @DNA -> RNA@, we transcribe--- the coding strand.--- <http://hyperphysics.phy-astr.gsu.edu/hbase/Organic/transcription.html>------ @@ DNAseq "ACGT" ^. transcribe == RNAseq "ACGU" RNAseq "ACGU" ^. transcribe--- == DNAseq "ACGT" RNAseq "ACGU" ^. from transcribe :: DNAseq == DNAseq "ACGT"--- @@--class Transcribe f where-  type TranscribeTo f ∷ *-  transcribe ∷ Iso' f (TranscribeTo f)---- | Transcribe a DNA sequence into an RNA sequence. This does not @reverse@--- the sequence!--instance Transcribe DNAseq where-  type TranscribeTo DNAseq = RNAseq-  transcribe = iso (RNAseq . BS.map dna2rna . _dnaseq) (DNAseq . BS.map rna2dna . _rnaseq)-  {-# Inline transcribe #-}---- | Transcribe a RNA sequence into an DNA sequence. This does not @reverse@--- the sequence!--instance Transcribe RNAseq where-  type TranscribeTo RNAseq = DNAseq-  transcribe = from transcribe-  {-# Inline transcribe #-}------ | The complement of a biosequence.--class Complement f where-  complement ∷ Iso' f f--instance Complement DNAseq where-  complement = iso (DNAseq . BS.map dnaComplement . _dnaseq) (DNAseq . BS.map dnaComplement . _dnaseq)-  {-# Inline complement #-}--instance Complement RNAseq where-  complement = iso (RNAseq . BS.map rnaComplement . _rnaseq) (RNAseq . BS.map rnaComplement . _rnaseq)-  {-# Inline complement #-}-

@@ -1,29 +1,47 @@ +-- | Stranded reading frames.+ module Biobase.Types.ReadingFrame where -import GHC.Generics+import Control.Lens hiding (Index)+import GHC.Generics hiding (from)  import Biobase.Types.Index (Index, toInt0)+import Biobase.Types.Strand    -- | The Reading frame. Sequence indexing starts at position 1, which starts -- reading frame 1. Reading frame 2 and 3 start at position 2 and 3 -- respectively.------ The reading frame should be constructed from an @Index 1@ with a smart--- constructor to get the frame calculation right.  newtype ReadingFrame = ReadingFrame { getReadingFrame ∷ Int }-  deriving (Eq,Ord,Generic)+  deriving (Eq,Ord,Generic,Show)+makeWrapped ''ReadingFrame -nextReadingFrame ∷ ReadingFrame → ReadingFrame-{-# Inline nextReadingFrame #-}-nextReadingFrame (ReadingFrame rf) = ReadingFrame $ rf `mod` 3 + 1+-- | Convert between @+1 ... +3@ and @ReadingFrame@. -prevReadingFrame ∷ ReadingFrame → ReadingFrame-{-# Inline prevReadingFrame #-}-prevReadingFrame (ReadingFrame rf) = ReadingFrame $ rf `mod` 3 + 2+rf ∷ Prism' Int ReadingFrame+{-# Inline rf #-}+rf = prism' getReadingFrame $ \k → let ak = abs k in+  if (ak <=  3 && ak >= 1) then Just (ReadingFrame k) else Nothing++-- | A lens for the strand++strandRF ∷ Lens' ReadingFrame Strand+{-# Inline strandRF #-}+strandRF = lens (\(ReadingFrame k) → if k < 0 then MinusStrand else PlusStrand)+                (\(ReadingFrame k) s → ReadingFrame $ if s == PlusStrand then abs k else (negate $ abs k))++-- |+--+-- @pred@ and @succ@ are correct, if the input is a legal 'ReadingFrame'.++instance Enum ReadingFrame where+  {-# Inline toEnum #-}+  toEnum k = case k^?rf of Just rf → rf ; Nothing → error $ show k ++ " is not a legal reading frame"+  {-# Inline fromEnum #-}+  fromEnum = getReadingFrame  -- | --

@@ -8,11 +8,14 @@ module Biobase.Types.Strand where  import Control.DeepSeq+import Control.Lens hiding (Index) import Control.Monad (guard) import Data.Aeson import Data.Binary+import Data.Data (Data) import Data.Hashable (Hashable) import Data.Serialize (Serialize)+import Data.Typeable (Typeable) import Data.Vector.Fusion.Stream.Monadic (Step(..), flatten) import Data.Vector.Unboxed.Deriving import GHC.Generics@@ -27,7 +30,7 @@ -- in, say, the FASTA file. 'MinusStrand' hence is the reverse complement.  newtype Strand = Strand { getStrand :: Int }-  deriving (Eq,Ord,Generic)+  deriving (Eq,Ord,Generic,Data,Typeable)  instance Show Strand where   show PlusStrand  = "PlusStrand"@@ -55,6 +58,10 @@   toEnum i | i>=0 && i<=1 = Strand i   toEnum i                = error $ "toEnum (Strand)" ++ show i   fromEnum = getStrand++instance Reversing Strand where+  reversing PlusStrand = MinusStrand+  reversing MinusStrand = PlusStrand  pattern PlusStrand  = Strand 0 pattern MinusStrand = Strand 1

@@ -1,7 +1,7 @@ name:           BiobaseTypes-version:        0.1.4.0-author:         Christian Hoener zu Siederdissen, 2015 - 2018-copyright:      Christian Hoener zu Siederdissen, 2015 - 2018+version:        0.2.0.0+author:         Christian Hoener zu Siederdissen, 2015 - 2019+copyright:      Christian Hoener zu Siederdissen, 2015 - 2019 homepage:       https://github.com/choener/BiobaseTypes bug-reports:    https://github.com/choener/BiobaseTypes/issues maintainer:     choener@bioinf.uni-leipzig.de@@ -58,30 +58,34 @@                --                , bimaps                   == 0.1.0.*                , ForestStructures         == 0.0.1.*-               , PrimitiveArray           == 0.9.0.*-               , SciBaseTypes             == 0.0.0.*+               , PrimitiveArray           == 0.9.1.*+               , SciBaseTypes             == 0.1.0.*   exposed-modules:     Biobase.Types.Accession-    Biobase.Types.AminoAcidSequence+    Biobase.Types.BioSequence     Biobase.Types.Bitscore+    Biobase.Types.Codon     Biobase.Types.Energy     Biobase.Types.Evalue     Biobase.Types.Index     Biobase.Types.Index.Type     Biobase.Types.Names     Biobase.Types.Names.Internal-    Biobase.Types.NucleotideSequence     Biobase.Types.ReadingFrame     Biobase.Types.Shape     Biobase.Types.Strand     Biobase.Types.Structure     Biobase.Types.Taxonomy+    DP.Backtraced.BioSequence+    DP.Backtraced.Codon   default-language:     Haskell2010   default-extensions: BangPatterns                     , DataKinds                     , DeriveDataTypeable+                    , DeriveFoldable                     , DeriveGeneric+                    , DeriveTraversable                     , FlexibleContexts                     , FlexibleInstances                     , GeneralizedNewtypeDeriving

@@ -0,0 +1,3 @@++module DP.Backtraced.BioSequence where+

@@ -0,0 +1,46 @@++-- | The Backtraced column structure is for codon-based alignments, including+-- special cases.++module DP.Backtraced.Codon where++import Data.ByteString (ByteString)+import Data.Vector (Vector)+import GHC.Generics (Generic)++import Biobase.Types.Codon++++-- | A single 'Backtraced' column. Since such a column will be part of a+-- @Backtraced (Z:.BtCodon c aa:. ...)@ structure, it is always possible to+-- extend even further, by having more entries.++data BtCodon c aa+  -- | A canonical match. A codon and the translated amino acid need to be set.+  = Match+    { _codon  ∷ !(Codon c)+    , _aa     ∷ !aa+    }+  -- | A frameshifting match. The vector of frameshifted nucleotides will have+  -- a number of characters @c@, that encode for a single amino acid.+  | Frameshift+    { _frameshift ∷ !(Vector c)+    , _aa         ∷ !aa+    }+  | Insert+    { _codon  ∷ !(Codon c)+    , _aa     ∷ !aa+    }+  | Shifted+    { _frameshift ∷ !(Vector c)+    , _aa         ∷ !aa+    }+  | Region+    { _region     ∷ !(Vector c)+    , _annotation ∷ !ByteString+    }+  | Delete+    {+    }+

@@ -1,3 +1,8 @@+0.2.0.0+-------++- unified treatment of bio sequences with one phantom-typed newtype.+ 0.1.4.0 ------- 

@@ -10,8 +10,8 @@ import           Test.Tasty.QuickCheck (testProperty) import           Test.Tasty.TH +import           Biobase.Types.BioSequence import           Biobase.Types.Bitscore-import           Biobase.Types.NucleotideSequence import           Biobase.Types.Shape import           Biobase.Types.Structure @@ -29,11 +29,11 @@  -- complement twice -prop_complement_twice_DNA (dna ∷ DNAseq) = dna == dna^.complement.complement+prop_complement_twice_DNA (dna ∷ BioSequence DNA) = dna == dna^.complement.complement -prop_complement_twice_RNA (rna ∷ RNAseq) = rna == rna^.complement.complement+prop_complement_twice_RNA (rna ∷ BioSequence RNA) = rna == rna^.complement.complement -prop_transcribe_twice_DNA (dna ∷ DNAseq) = dna == dna^.transcribe.transcribe+prop_transcribe_twice_DNA (dna ∷ BioSequence DNA) = dna == dna^.transcribe.transcribe  --prop_transcribe_twice_DNA (rna ∷ RNAseq) = rna == rna^.transcribe.transcribe