diff --git a/ChangeLog.md b/ChangeLog.md --- a/ChangeLog.md +++ b/ChangeLog.md @@ -7,6 +7,11 @@ ## [Unreleased] +## 0.1.1.0 +* Back compability lost for SQ section +* No more DuplicateRecordFields, so it can be built by 7.x +* Includes and Contains sections of DE tested + ## 0.1.0.1 * Small fixes in description fields read * Documentation fixes diff --git a/src/Bio/Uniprot/Parser.hs b/src/Bio/Uniprot/Parser.hs --- a/src/Bio/Uniprot/Parser.hs +++ b/src/Bio/Uniprot/Parser.hs @@ -75,39 +75,40 @@ -- |Parses DE lines of UniProt-KB text file. parseDE :: Parser DE parseDE = do - recName <- optional $ parseNameDE RecName - altNames <- many' (endOfLine *> parseAltDE) - subNames <- many' (endOfLine *> parseNameDE SubName) - includes <- pure [] - contains <- pure [] + recName <- optional $ parseNameDE 0 RecName + altNames <- many' (endOfLine *> parseAltDE 0) + subNames <- many' (endOfLine *> parseNameDE 0 SubName) + includes <- many' (endOfLine *> parseInternal "Includes") + contains <- many' (endOfLine *> parseInternal "Contains") flags <- optional (endOfLine *> parseFlagsDE) pure DE{..} where -- |Parses name section like RecName, AltName or SubName. - parseNameDE :: NameType -> Parser Name - parseNameDE nameType = do - fullName <- parseDELine nameType "Full" - shortName <- many' $ endOfLine *> parseDELine None "Short" - ecNumber <- many' $ endOfLine *> parseDELine None "EC" + parseNameDE :: Int -> NameType -> Parser Name + parseNameDE indent nameType = do + fullName <- parseDELine indent nameType "Full" + shortName <- many' $ endOfLine *> parseDELine indent None "Short" + ecNumber <- many' $ endOfLine *> parseDELine indent None "EC" pure Name{..} -- |Parses flag line of DE section parseFlagsDE :: Parser Flag - parseFlagsDE = read . unpack <$> parseDELine Flags "" + parseFlagsDE = read . unpack <$> parseDELine 0 Flags "" -- |Parses AltName lines of DE section - parseAltDE :: Parser AltName - parseAltDE = - (Simple <$> parseNameDE AltName) <|> - (Allergen <$> parseDELine AltName "Allergen") <|> - (Biotech <$> parseDELine AltName "Biotech") <|> - (CDAntigen <$> parseDELine AltName "CD_antigen") <|> - (INN <$> parseDELine AltName "INN") + parseAltDE :: Int -> Parser AltName + parseAltDE indent = + (Simple <$> parseNameDE indent AltName) <|> + (Allergen <$> parseDELine indent AltName "Allergen") <|> + (Biotech <$> parseDELine indent AltName "Biotech") <|> + (CDAntigen <$> parseDELine indent AltName "CD_antigen") <|> + (INN <$> parseDELine indent AltName "INN") -- |Parses any DE line - parseDELine :: NameType -> Text -> Parser Text - parseDELine nameType tpe = do + parseDELine :: Int -> NameType -> Text -> Parser Text + parseDELine indent nameType tpe = do string "DE " + count indent (char ' ') case nameType of None -> string " " a -> string $ append (pack $ show a) ": " @@ -119,6 +120,15 @@ char ';' pure res + -- |Parses internal DE entities + parseInternal :: Text -> Parser DE + parseInternal name = do + string "DE " >> string name >> char ':' + endOfLine + recName <- optional $ parseNameDE 2 RecName + altNames <- many' (endOfLine *> parseAltDE 2) + pure $ DE recName altNames [] [] [] Nothing + -- |Parses DE lines of UniProt-KB text file. parseGN :: Parser [GN] parseGN = do @@ -334,7 +344,7 @@ parseSQ = do string "SQ SEQUENCE" many1 space - seqLength <- decimal + length <- decimal space >> string "AA;" many1 space molWeight <- decimal diff --git a/src/Bio/Uniprot/Type.hs b/src/Bio/Uniprot/Type.hs --- a/src/Bio/Uniprot/Type.hs +++ b/src/Bio/Uniprot/Type.hs @@ -1,4 +1,3 @@ -{-# LANGUAGE DuplicateRecordFields #-} module Bio.Uniprot.Type where import Data.Text (Text) @@ -230,7 +229,7 @@ -- |SeQuence header - sequence data and a quick summary of its content. data SQ = SQ - { seqLength :: Int -- ^Length of the sequence in amino acids. + { length :: Int -- ^Length of the sequence in amino acids. , molWeight :: Int -- ^Molecular weight rounded to the nearest mass unit (Dalton). , crc64 :: Text -- ^Sequence 64-bit CRC (Cyclic Redundancy Check) value. , sequence :: Text -- ^Sequence of the protein diff --git a/test/Spec.hs b/test/Spec.hs --- a/test/Spec.hs +++ b/test/Spec.hs @@ -33,6 +33,25 @@ DE AltName: CD_antigen=CD279; DE Flags: Precursor;|] +de2Str :: Text +de2Str = [text| +DE RecName: Full=Arginine biosynthesis bifunctional protein argJ; +DE Includes: +DE RecName: Full=Glutamate N-acetyltransferase; +DE EC=2.3.1.35; +DE AltName: Full=Ornithine acetyltransferase; +DE Short=OATase; +DE AltName: Full=Ornithine transacetylase; +DE Includes: +DE RecName: Full=Amino-acid acetyltransferase; +DE EC=2.3.1.1; +DE AltName: Full=N-acetylglutamate synthase; +DE Short=AGS; +DE Contains: +DE RecName: Full=Arginine biosynthesis bifunctional protein argJ alpha chain; +DE Contains: +DE RecName: Full=Arginine biosynthesis bifunctional protein argJ beta chain;|] + gnStr :: Text gnStr = "GN Name=PDCD1; Synonyms=PD1;" @@ -690,6 +709,22 @@ deAns = DE (Just (Name "Programmed cell death protein 1" ["Protein PD-1", "hPD-1"] [])) [CDAntigen "CD279"] [] [] [] (Just Precursor) +de2Ans :: DE +de2Ans = DE (Just (Name "Arginine biosynthesis bifunctional protein argJ" [] [])) [] [] + [DE (Just (Name "Glutamate N-acetyltransferase" [] ["2.3.1.35"])) + [Simple (Name "Ornithine acetyltransferase" ["OATase"] []), + Simple (Name "Ornithine transacetylase" [] [])] + [] [] [] Nothing, + DE (Just (Name "Amino-acid acetyltransferase" [] ["2.3.1.1"])) + [Simple (Name "N-acetylglutamate synthase" ["AGS"] [])] + [] [] [] Nothing + ] + [DE (Just (Name "Arginine biosynthesis bifunctional protein argJ alpha chain" [] [])) + [] [] [] [] Nothing, + DE (Just (Name "Arginine biosynthesis bifunctional protein argJ beta chain" [] [])) + [] [] [] [] Nothing] + Nothing + gnAns :: [GN] gnAns = [GN (Just "PDCD1") ["PD1"] [] []] @@ -903,8 +938,9 @@ parseOnly parseAC acStr `shouldBe` Right acAns it "parses DT lines" $ parseOnly parseDT dtStr `shouldBe` Right dtAns - it "parses DE lines" $ + it "parses DE lines" $ do parseOnly parseDE deStr `shouldBe` Right deAns + parseOnly parseDE de2Str `shouldBe` Right de2Ans it "parses GN lines" $ parseOnly parseGN gnStr `shouldBe` Right gnAns it "parses OS lines" $ diff --git a/uniprot-kb.cabal b/uniprot-kb.cabal --- a/uniprot-kb.cabal +++ b/uniprot-kb.cabal @@ -2,10 +2,10 @@ -- -- see: https://github.com/sol/hpack -- --- hash: 46801dc834178bde36de5bfcd64e4b397b76da7ac4dbe6f22b7275f5a1661110 +-- hash: 3517fcac83f428dec7f91394fc57d66a124e38ba92fb52f33441827f60aa1c9e name: uniprot-kb -version: 0.1.0.1 +version: 0.1.1.0 synopsis: UniProt-KB format parser description: Specification implementation of https://web.expasy.org/docs/userman.html category: Bio