diff --git a/Biobase/Infernal/VerboseHit.hs b/Biobase/Infernal/VerboseHit.hs --- a/Biobase/Infernal/VerboseHit.hs +++ b/Biobase/Infernal/VerboseHit.hs @@ -1,10 +1,12 @@ {-# LANGUAGE RecordWildCards #-} --- | Provides a datatype for cmsearch verbose output. +-- | Provides a datatype for cmsearch verbose output. The Import/Export system +-- now allows for primitive annotations using "##" as the first two characters. +-- Annotations are only accepted for individual hits. module Biobase.Infernal.VerboseHit where -import qualified Data.ByteString.Char8 as BS +import Data.ByteString.Char8 as BS import Text.Printf @@ -14,17 +16,18 @@ data VerboseHit = VerboseHit { vhTarget :: (Int,Int) -- ^ part of target sequence (start counting at 1) , vhQuery :: (Int,Int) -- ^ which part of the CM/stk do we align to - , vhCM :: BS.ByteString -- ^ the CM for this alignment + , vhCM :: ByteString -- ^ the CM for this alignment , vhStrand :: Strand -- ^ should be either '+' or '-' , vhScore :: Double -- ^ bit score , vhEvalue :: Double -- ^ number of hits we expect to find with 'score' or higher for 'targetSequence' length , vhPvalue :: Double -- ^ ? , vhGC :: Int -- ^ ? - , vhScaffold :: BS.ByteString -- ^ scaffold, chromosome, ... (the name of the sequence, not the sequence data!) - , vhWuss :: BS.ByteString -- ^ fancy secondary structure annotation using wuss notation - , vhConsensus :: BS.ByteString -- ^ query consensus (upper: highly, lower: weak/no) - , vhScoring :: BS.ByteString -- ^ represents where positive and negative scores come from - , vhSequence :: BS.ByteString -- ^ the target sequence which aligns to the model + , vhScaffold :: ByteString -- ^ scaffold, chromosome, ... (the name of the sequence, not the sequence data!) + , vhWuss :: ByteString -- ^ fancy secondary structure annotation using wuss notation + , vhConsensus :: ByteString -- ^ query consensus (upper: highly, lower: weak/no) + , vhScoring :: ByteString -- ^ represents where positive and negative scores come from + , vhSequence :: ByteString -- ^ the target sequence which aligns to the model + , vhAnnotation :: [ByteString] -- ^ any annotations that could be associated (# lines) } deriving (Show,Read) type Strand = Char diff --git a/Biobase/Infernal/VerboseHit/Export.hs b/Biobase/Infernal/VerboseHit/Export.hs --- a/Biobase/Infernal/VerboseHit/Export.hs +++ b/Biobase/Infernal/VerboseHit/Export.hs @@ -27,7 +27,7 @@ -- TOOD How to append the last line "//" to the finished stream, if at least -- one element was printed? -eneeByteString :: Monad m => Enumeratee [VerboseHit] BS.ByteString m a +eneeByteString :: Monad m => Enumeratee [VerboseHit] ByteString m a eneeByteString = eneeByteStrings ><> mapChunks BS.concat -- | This transformer keeps a 1-1 relationship between each 'VerboseHit' and @@ -35,17 +35,19 @@ -- individual 'VerboseHit's are to be annotated. eneeByteStrings :: Monad m => Enumeratee [VerboseHit] [ByteString] m a -eneeByteStrings = unfoldConvStream f (AliGo BS.empty BS.empty '?') where +eneeByteStrings = unfoldConvStream f (AliGo BS.empty BS.empty '?' []) where f acc = do h <- I.head let na = newAcc acc h - return (fst na , return . BS.unlines $ snd na ++ [showVerboseHit h]) + return ( fst na + , return . BS.unlines $ snd na ++ P.map (append "## ") (vhAnnotation h) ++ [showVerboseHit h] + ) -- | Given the current state "a" and verbose hit "h", determine if any state -- switches have to be emitted. newAcc a@(AliGo{..}) h@VerboseHit{..} - | otherwise = ( AliGo vhCM vhScaffold vhStrand, ls ) + | otherwise = ( AliGo vhCM vhScaffold vhStrand [], ls ) where ls = [ "//" | aliCM /= BS.empty && aliCM /= vhCM ] ++ [ "CM: " `BS.append` vhCM | aliCM /= vhCM ] ++ [ ">" `BS.append` vhScaffold `BS.append` "\n" | aliScaffold /= vhScaffold ] ++ diff --git a/Biobase/Infernal/VerboseHit/Import.hs b/Biobase/Infernal/VerboseHit/Import.hs --- a/Biobase/Infernal/VerboseHit/Import.hs +++ b/Biobase/Infernal/VerboseHit/Import.hs @@ -35,25 +35,26 @@ -- accumulator to keep track of the current CM, scaffold and strand. eneeVerboseHit :: (Functor m, Monad m) => Enumeratee BS.ByteString [VerboseHit] m a -eneeVerboseHit = enumLinesBS ><> I.filter (not . BS.null) ><> unfoldConvStream f (AliGo BS.empty BS.empty '?') where +eneeVerboseHit = enumLinesBS ><> I.filter (not . BS.null) ><> unfoldConvStream f (AliGo BS.empty BS.empty '?' []) where f acc = do h' <- tryHead case h' of Nothing -> return (acc, []) (Just h) - | "CM: " `BS.isInfixOf` h -> return (acc{aliCM = BS.copy $ BS.drop 4 h}, []) - | ">" `BS.isInfixOf` h -> return (acc{aliScaffold = BS.copy $ BS.drop 1 h}, []) - | " Plus" `BS.isInfixOf` h -> return (acc{aliStrand = '+'}, []) - | " Minus" `BS.isInfixOf` h -> return (acc{aliStrand = '-'}, []) - | " Query" `BS.isInfixOf` h -> do - x <- qs h (aliCM acc) (aliScaffold acc) (aliStrand acc) - return (acc,x) + | "##" `isPrefixOf` h -> return (acc{aliAnnotation = aliAnnotation acc ++ [BS.drop 2 h]},[]) + | "CM: " `isInfixOf` h -> return (acc{aliCM = BS.copy $ BS.drop 4 h, aliAnnotation = []}, []) + | ">" `isInfixOf` h -> return (acc{aliScaffold = BS.copy $ BS.drop 1 h, aliAnnotation = []}, []) + | " Plus" `isInfixOf` h -> return (acc{aliStrand = '+', aliAnnotation = []}, []) + | " Minus" `isInfixOf` h -> return (acc{aliStrand = '-', aliAnnotation = []}, []) + | " Query" `isInfixOf` h -> do + x <- qs h (aliCM acc) (aliScaffold acc) (aliStrand acc) (aliAnnotation acc) + return (acc{aliAnnotation = []},x) | otherwise -> return (acc,[]) -- | Parses one CM query result. -qs :: Monad m => BS.ByteString -> BS.ByteString -> BS.ByteString -> Char -> Iteratee [BS.ByteString] m [VerboseHit] -qs query cm scaf pm = do +qs :: Monad m => ByteString -> ByteString -> ByteString -> Char -> [ByteString] -> Iteratee [ByteString] m [VerboseHit] +qs query cm scaf pm anno = do let q = fromRight . parseOnly qt $ query s <- I.head >>= return . fromRight . parseOnly sepg l <- fourLines $ sel4 q @@ -71,6 +72,7 @@ , vhConsensus = cpy $ l!!1 , vhScoring = cpy $ l!!2 , vhSequence = cpy $ l!!3 + , vhAnnotation = anno } where cpy = BS.copy . BS.concat diff --git a/Biobase/Infernal/VerboseHit/Internal.hs b/Biobase/Infernal/VerboseHit/Internal.hs --- a/Biobase/Infernal/VerboseHit/Internal.hs +++ b/Biobase/Infernal/VerboseHit/Internal.hs @@ -3,15 +3,16 @@ module Biobase.Infernal.VerboseHit.Internal where -import qualified Data.ByteString.Char8 as BS +import Data.ByteString.Char8 as BS -- | State for import and export functions data AliGo = AliGo - { aliCM :: BS.ByteString - , aliScaffold :: BS.ByteString + { aliCM :: ByteString + , aliScaffold :: ByteString , aliStrand :: Char + , aliAnnotation :: [ByteString] } deriving (Show) diff --git a/BiobaseInfernal.cabal b/BiobaseInfernal.cabal --- a/BiobaseInfernal.cabal +++ b/BiobaseInfernal.cabal @@ -1,5 +1,5 @@ name: BiobaseInfernal -version: 0.5.3.1 +version: 0.5.4.0 author: Christian Hoener zu Siederdissen maintainer: choener@tbi.univie.ac.at homepage: http://www.tbi.univie.ac.at/~choener/ @@ -15,6 +15,12 @@ Provides import and export facilities for Infernal/Rfam data formats. We include Stockholm, CM, verbose Infernal results, and tabulated Infernal results. Some small tools are included. + . + The VerboseHit format is slightly extended to allow simple + annotations. This extension should be backward-compatible with + standard-compliant parsers. + . + . . With the BioHaskell library split, this package is officially back! And the package is not feature-complete yet, take the