BiobaseENA 0.0.0.1 → 0.0.0.2

raw patch · 7 files changed

+74/−55 lines, 7 filesdep ~BiobaseTypesPVP: major bump suggested

API removals or changes: PVP suggests a major version bump

Dependency ranges changed: BiobaseTypes

API changes (from Hackage documentation)

Files

• Biobase/GeneticCodes.hs +19/−19
• Biobase/GeneticCodes/Embedded.hs +3/−3
• Biobase/GeneticCodes/Import.hs +12/−12
• Biobase/GeneticCodes/Translation.hs +23/−4
• Biobase/GeneticCodes/Types.hs +12/−12
• BiobaseENA.cabal +4/−4
• README.md +1/−1

@@ -25,22 +25,22 @@   codeByTableID-  ∷ (MonadError String m)-  ⇒ [TranslationTable c a]-  → Int-  → m (TranslationTable c a)+  :: (MonadError String m)+  => [TranslationTable c a]+  -> Int+  -> m (TranslationTable c a) codeByTableID ts i   = maybe (throwError $ printf "No TranslationTable with ID %d found!" i) return-  $ find (\t → t^.tableID == i) ts+  $ find (\t -> t^.tableID == i) ts  codeByTableNameInfix-  ∷ (MonadError String m)-  ⇒ [TranslationTable c a]-  → Text-  → m (TranslationTable c a)+  :: (MonadError String m)+  => [TranslationTable c a]+  -> Text+  -> m (TranslationTable c a) codeByTableNameInfix ts n   = maybe (throwError $ printf "No TranslationTable with Name infix %s found!" $ unpack n) return-  $ find (\t → n `isInfixOf` (t^.tableName)) ts+  $ find (\t -> n `isInfixOf` (t^.tableName)) ts  -- | If the given filepath exists, then we try to load the genetic table from -- the file. This will fail if there is not exactly one genetic table there. If@@ -54,17 +54,17 @@ -- is returned.  fromFileOrCached-  ∷ (MonadIO m, MonadError String m)-  ⇒ FilePath-  → m (TranslationTable Char Char)+  :: (MonadIO m, MonadError String m)+  => FilePath+  -> m (TranslationTable Char Char) fromFileOrCached fp = do   dfe ← liftIO $ doesFileExist fp-  if | fp == "list" → do+  if | fp == "list" -> do           mapM_ (liftIO . uncurry (printf "%3d %s\n")) [ (t^.tableID,t^.tableName) | t ← geneticCodes ]           liftIO exitSuccess-     | dfe → fromFile fp >>= \case-         [x] → return x-         xs  → throwError $ fp ++ " should contain exactly one translation table!"-     | [(k,"")] ← reads fp → codeByTableID geneticCodes k-     | otherwise → codeByTableNameInfix geneticCodes $ pack fp+     | dfe -> fromFile fp >>= \case+         [x] -> return x+         xs  -> throwError $ fp ++ " should contain exactly one translation table!"+     | [(k,"")] <- reads fp -> codeByTableID geneticCodes k+     | otherwise -> codeByTableNameInfix geneticCodes $ pack fp 

@@ -8,9 +8,9 @@ import Biobase.GeneticCodes.Import import Biobase.GeneticCodes.Types -geneticCodesFile ∷ ByteString-geneticCodesFile = $(embedFile "sources/translation-tables")+geneticCodesFile :: ByteString+geneticCodesFile = $(makeRelativeToProject "sources/translation-tables" >>= embedFile) -geneticCodes ∷ [TranslationTable Char Char]+geneticCodes :: [TranslationTable Char Char] geneticCodes = either error id . runExcept $ fromByteString geneticCodesFile 

@@ -30,25 +30,25 @@ -- the error and exit with a failure.  fromFile-  ∷ (MonadIO m, MonadError String m)-  ⇒ FilePath-  → m [TranslationTable Char Char]+  :: (MonadIO m, MonadError String m)+  => FilePath+  -> m [TranslationTable Char Char] fromFile fp = (liftIO $ BS.readFile fp) >>= fromByteString  -- | Parse a ByteString with translation tables.  fromByteString-  ∷ (MonadError String m)-  ⇒ ByteString-  → m [TranslationTable Char Char]+  :: (MonadError String m)+  => ByteString+  -> m [TranslationTable Char Char] fromByteString bs = case runParser (some parseTranslationTable) "" (decodeUtf8 bs) of-    -- Left err → throwError $ parseErrorPretty err -- megaparsec 6.x-    Left err → throwError $ errorBundlePretty err   -- megaparsec 7.x-    Right rs → return rs+    -- Left err -> throwError $ parseErrorPretty err -- megaparsec 6.x+    Left err -> throwError $ errorBundlePretty err   -- megaparsec 7.x+    Right rs -> return rs  -- | Parses a single translation table. -parseTranslationTable ∷ TTParser (TranslationTable Char Char)+parseTranslationTable :: TTParser (TranslationTable Char Char) parseTranslationTable = do   (i,hdr) ← parseHeader   aas     ← parseData "amino acids"@@ -63,14 +63,14 @@  -- | Parse the header, returning the Identifier and the name of the table. -parseHeader ∷ TTParser (Int,Text)+parseHeader :: TTParser (Int,Text) parseHeader   = (,) <$> (fromIntegral <$> lexeme MC.space decimal)   <* char ':' <* MC.space   <*> takeWhileP Nothing (/= '\n')   <* MC.space -parseData ∷ Text → TTParser String+parseData :: Text -> TTParser String parseData t   = string' t <* MC.space   *> (unpack <$> takeP Nothing 64)

@@ -25,13 +25,16 @@  class Translation t where   -- | Defines the target type for a given translation input.-  type TargetType t ∷ *+  type TargetType t :: *   -- | Type of the nucleotide characters.-  type CodonType t ∷ *+  type CodonType t :: *   -- | Type of the amino acid characters.-  type AAType t ∷ *+  type AAType t :: *   -- | Translate from a given type of sequence @t@ into the target type.-  translate ∷ TranslationTable (CodonType t) (AAType t) → t → TargetType t+  translate :: TranslationTable (CodonType t) (AAType t) -> t -> TargetType t+  -- | This function works just like @translate@ but with an important difference of creating a+  -- target sequence that contains all possible frames. The index @mod 3@ yields the current frame.+  translateAllFrames :: TranslationTable (CodonType t) (AAType t) -> t -> TargetType t  -- | Very simple translation of individual base triplets. @@ -41,6 +44,8 @@   type AAType      (Codon Char) = Char   translate tbl t = maybe 'X' _aminoAcid $ M.lookup t (tbl^.codonToAminoAcid)   {-# Inline translate #-}+  translateAllFrames = translate+  {-# Inline translateAllFrames #-}  -- | Strings of characters are normally very inconvenient but useful in -- backtracking cases. Fully assumes that the alphabet is DNA. Ignores@@ -55,6 +60,14 @@               | otherwise = []               where (hd,tl) = splitAt 3 xs     in  go+  {-# Inlinable translate #-}+  translateAllFrames tbl = go []+    where go _     []     = []+          -- first two AA are unknown @?@ since the codon has not been established at this point.+          go []    (x:xs) = '?' : go [x] xs+          go [p]   (x:xs) = '?' : go [p,x] xs+          go [p,q] (x:xs) = translate tbl (Codon p q x) : go [q,x] xs+  {-# Inlinable translateAllFrames #-}  -- | Translation of @BioSequence DNA@. The translation tables assume DNA -- triplets anyway. Biologically there should be a transcription step in@@ -67,4 +80,10 @@   translate tbl (BioSequence xs) =     let go k = Just (translate tbl $ Codon (BS.index xs k) (BS.index xs (k+1)) (BS.index xs (k+2)) ,k+3)     in  BioSequence . fst $ BS.unfoldrN (BS.length xs `div` 3) go 0+  {-# Inlinable translate #-}+  translateAllFrames tbl (BioSequence xs) = BioSequence . fst $ BS.unfoldrN (BS.length xs) go 0+    where go 0 = Just ('?', 1)+          go 1 = Just ('?', 2)+          go k = Just (translate tbl $ Codon (BS.index xs (k-2)) (BS.index xs (k-1)) (BS.index xs k), k+1)+  {-# Inlinable translateAllFrames #-} 

@@ -13,31 +13,31 @@   data TranslationElement c a = TranslationElement-  { _baseCodon    ∷ !(Codon c)-  , _isStartCodon ∷ !Bool-  , _aminoAcid    ∷ !a+  { _baseCodon    :: !(Codon c)+  , _isStartCodon :: !Bool+  , _aminoAcid    :: !a   }   deriving (Show) makeLenses ''TranslationElement  data TranslationTable c a = TranslationTable-  { _codonToAminoAcid  ∷ !(Map (Codon c) (TranslationElement c a))-  , _aminoAcidtoCodons ∷ !(Map a [TranslationElement c a])-  , _tableID           ∷ !Int-  , _tableName         ∷ !Text+  { _codonToAminoAcid  :: !(Map (Codon c) (TranslationElement c a))+  , _aminoAcidtoCodons :: !(Map a [TranslationElement c a])+  , _tableID           :: !Int+  , _tableName         :: !Text   }   deriving (Show) makeLenses ''TranslationTable  genTranslationTable-  ∷ (Ord c, Ord a)-  ⇒ Int+  :: (Ord c, Ord a)+  => Int   -- ^ table identifier-  → Text+  -> Text   -- ^ table hdr / table name-  → [TranslationElement c a]+  -> [TranslationElement c a]   -- ^ known translation elements (should be @4^3@ but is not checked)-  → TranslationTable c a+  -> TranslationTable c a   -- ^ finished translation table {-# Inlinable genTranslationTable #-} genTranslationTable i hdr xs = TranslationTable

@@ -1,17 +1,17 @@ Cabal-version:  2.2 Name:           BiobaseENA-Version:        0.0.0.1+Version:        0.0.0.2 License:        BSD-3-Clause License-file:   LICENSE Author:         Christian Hoener zu Siederdissen Maintainer:     choener@bioinf.uni-leipzig.de-Copyright:      Christian Hoener zu Siederdissen, 2019+Copyright:      Christian Hoener zu Siederdissen, 2020-2021 homepage:       https://github.com/choener/BiobaseENA bug-reports:    https://github.com/choener/BiobaseENA/issues Stability:      Experimental Category:       Data Build-type:     Simple-tested-with:    GHC == 8.4.4+tested-with:    GHC == 8.8, GHC == 8.10, GHC == 9.0 Synopsis:       European Nucleotide Archive data Description:                 Provides data (and later API) access to the European Nucleotide Archive.@@ -39,7 +39,7 @@                , vector                   >= 0.10                , vector-th-unbox          >= 0.2                ---               , BiobaseTypes             == 0.2.0.*+               , BiobaseTypes             == 0.2.1.*   ghc-options:     -O2     -funbox-strict-fields

@@ -1,4 +1,4 @@-[![Build Status](https://travis-ci.org/choener/BiobaseENA.svg?branch=master)](https://travis-ci.org/choener/BiobaseENA)+![github action: master](https://github.com/choener/BiobaseENA/actions/workflows/action.yml/badge.svg)  # BiobaseENA