diff --git a/ClustalParser.cabal b/ClustalParser.cabal --- a/ClustalParser.cabal +++ b/ClustalParser.cabal @@ -5,9 +5,9 @@ -- PVP summary: +-+------- breaking API changes -- | | +----- non-breaking API additions -- | | | +--- code changes with no API change -version: 1.0.3 +version: 1.1.0 synopsis: Libary for parsing Clustal tools output -description: Currently contains parsers and datatypes for: clustalw2, clustalo +description: Currently contains parsers and datatypes for: clustalw2, clustalo, mlocarna . For more information on clustal Tools refer to . @@ -33,8 +33,8 @@ source-repository this type: git - location: https://github.com/eggzilla/ClustalParser/tree/1.0.3 - tag: 1.0.3 + location: https://github.com/eggzilla/ClustalParser/tree/1.1.0 + tag: 1.1.0 library -- Modules exported by the library. @@ -42,7 +42,7 @@ other-modules: Bio.ClustalData -- Other library packages from which modules are imported. - build-depends: base >=4.5 && <5, parsec + build-depends: base >=4.5 && <5, parsec>=3.1.9, vector -- compiler options ghc-options: -Wall -O2 -fno-warn-unused-do-bind -- Directories containing source files. @@ -50,7 +50,12 @@ executable ClustalParserTest main-is: ClustalParserTest.hs - build-depends: base >= 4 && <= 5, cmdargs, ClustalParser + build-depends: base >= 4 && <= 5, cmdargs, ClustalParser, either-unwrap -- compiler options ghc-options: -Wall -O2 - + +test-suite hspec + build-depends: base, parsec, ClustalParser, hspec >= 1.8 + hs-source-dirs: test-suite + main-is: Spec.hs + type: exitcode-stdio-1.0 diff --git a/ClustalParserTest.hs b/ClustalParserTest.hs --- a/ClustalParserTest.hs +++ b/ClustalParserTest.hs @@ -2,12 +2,15 @@ import System.Environment (getArgs) import Bio.ClustalParser +import Data.Either.Unwrap main :: IO () main = do args <- getArgs let input_file = (head args) -- read Clustal outputfile - parsedinput <- readStructuralClustalAlignment input_file - print parsedinput + parsedinput <- readClustalAlignment input_file + --parsedinput <- readStructuralClustalAlignment input_file + --print (entrySequenceIdentifier (head (structuralAlignmentEntries(fromRight parsedinput)))) + print (fromRight parsedinput) diff --git a/README.md b/README.md --- a/README.md +++ b/README.md @@ -1,12 +1,15 @@ -ClustalParser [![Build Status](https://travis-ci.org/eggzilla/ClustalParser.svg)](https://travis-ci.org/eggzilla/ClustalParser) +ClustalParser [![Hackage](https://img.shields.io/hackage/v/ClustalParser.svg)](https://hackage.haskell.org/package/ClustalParser) [![Build Status](https://travis-ci.org/eggzilla/ClustalParser.svg)](https://travis-ci.org/eggzilla/ClustalParser) ============= -Currently contains parsers and datatypes for: clustalw2, clustalo +Currently contains parsers and datatypes for: clustalw2, clustalo, mlocarna -Clustal tools are multipe sequence aligenment tools for biological sequences +Clustal tools are multiple sequence alignment tools for biological sequences like DNA, RNA and Protein. For more information on clustal Tools refer to . +Mlocarna is a multiple sequence alignment tool for RNA sequences with +secondary structure output. +For more information on molocarna refer to . 4 types of output are parsed @@ -14,7 +17,7 @@ * Parsing with readClustalAlignment from filepath (Bio.ClustalParser) * Parsing with parseClustalAlignment from String (Bio.ClustalParser) -- Alignment file with secondary structure (.aln): + - Alignment file with secondary structure (.aln): * Parsing with readStructuralClustalAlignment from filepath (Bio.ClustalParser) * Parsing with parsStructuralClustalAlignment from String (Bio.ClustalParser) diff --git a/changelog b/changelog --- a/changelog +++ b/changelog @@ -1,4 +1,7 @@ -*-change-log-*- +1.1.0 Florian Eggenhofer 1. July 2015 + * Added Hspec test-suite for Parsing functions + * Added Show instances for ClustalAlignment and StructuralClustalAlignment 1.0.3 Florian Eggenhofer 19. April 2015 * Added Y (pyrimidine) and R (purine) to sequence characters 1.0.2 Florian Eggenhofer 19. March 2015 diff --git a/src/Bio/ClustalData.hs b/src/Bio/ClustalData.hs --- a/src/Bio/ClustalData.hs +++ b/src/Bio/ClustalData.hs @@ -2,6 +2,7 @@ -- For more information on Clustal tools consult: module Bio.ClustalData where +import qualified Data.Vector as V -- | Data type for clustal summary, containing information about the alignment process, usually printed to STDOUT data ClustalSummary = ClustalSummary @@ -48,8 +49,32 @@ alignmentEntries :: [ClustalAlignmentEntry], conservationTrack :: String } - deriving (Show, Eq) + deriving (Eq) +instance Show ClustalAlignment where + show (ClustalAlignment _alignmentEntries _conservationTrack ) + | not (null _alignmentEntries) = header ++ alignmentString + | otherwise = header + where header = "CLUSTAL W (1.8) multiple sequence alignment\n\n\n" + longestSequenceIdLength = (maximum (map length (map entrySequenceIdentifier _alignmentEntries))) + 1 + totalSequenceLength = length (entryAlignedSequence (head _alignmentEntries)) + alignmentString = showAlignment totalSequenceLength longestSequenceIdLength 0 _alignmentEntries _conservationTrack + +showAlignment :: Int -> Int -> Int -> [ClustalAlignmentEntry] -> String -> String +showAlignment totalSequenceLength longestSequenceIdLength currentWindowPosition _alignmentEntries _conservationTrack + | totalSequenceLength == 0 = [] + | currentWindowPosition <= totalSequenceLength = showAlignmentBlock longestSequenceIdLength currentWindowPosition _alignmentEntries _conservationTrack ++ (showAlignment totalSequenceLength longestSequenceIdLength (currentWindowPosition + 60) _alignmentEntries _conservationTrack) + | otherwise = "" + +showAlignmentBlock :: Int -> Int -> [ClustalAlignmentEntry] -> String -> String +showAlignmentBlock longestSequenceIdLength currentWindowPosition _alignmentEntries _conservationTrack = blockString + where blockString = entries ++ extraTrack ++ "\n" + entries = concatMap (showAlignmentLine longestSequenceIdLength currentWindowPosition) _alignmentEntries + extraTrack = concat (replicate longestSequenceIdLength " ") ++ V.toList (V.slice currentWindowPosition 60 (V.fromList _conservationTrack)) ++ "\n" + +showAlignmentLine :: Int -> Int -> ClustalAlignmentEntry -> String +showAlignmentLine longestSequenceIdLength currentWindowPosition _alignmentEntry = (entrySequenceIdentifier _alignmentEntry) ++ concat (replicate (longestSequenceIdLength - length (entrySequenceIdentifier _alignmentEntry)) " ") ++ V.toList (V.slice currentWindowPosition 60 (V.fromList (entryAlignedSequence _alignmentEntry))) ++ "\n" + data ClustalAlignmentEntry = ClustalAlignmentEntry { entrySequenceIdentifier :: String, @@ -79,7 +104,16 @@ secondaryStructureTrack :: String, energy :: Double } - deriving (Show, Eq) + deriving (Eq) + +instance Show StructuralClustalAlignment where + show (StructuralClustalAlignment _alignmentEntries _secondaryStructureTrack _energy) + | not (null _alignmentEntries) = header ++ alignmentString + | otherwise = header + where header = "CLUSTAL W \n\n" + longestSequenceIdLength = (maximum (map length (map entrySequenceIdentifier _alignmentEntries))) + 1 + totalSequenceLength = length (entryAlignedSequence (head _alignmentEntries)) + alignmentString = showAlignment totalSequenceLength longestSequenceIdLength 0 _alignmentEntries _secondaryStructureTrack data StructuralClustalAlignmentSlice = StructuralClustalAlignmentSlice { diff --git a/src/Bio/ClustalParser.hs b/src/Bio/ClustalParser.hs --- a/src/Bio/ClustalParser.hs +++ b/src/Bio/ClustalParser.hs @@ -118,14 +118,14 @@ newline newline newline - alignmentSlices <- many1 genParserClustalAlignmentSlice + alignmentSlices <- many1 (try genParserClustalAlignmentSlice) eof return (mergealignmentSlices alignmentSlices) mergealignmentSlices :: [ClustalAlignmentSlice] -> ClustalAlignment mergealignmentSlices slices = alignment where entrySlicesList = map entrySlices slices -- list of lists of entry slices - sequenceIdentifiers = map entrySequenceSliceIdentifier (head entrySlicesList) + sequenceIdentifiers = nub (map entrySequenceSliceIdentifier (head entrySlicesList)) alignmentEntriesListBySlice = map (map entryAlignedSliceSequence) entrySlicesList transposedAlignmentEntriesListbySlice = transpose alignmentEntriesListBySlice mergedAlignmentSequenceEntries = map concat transposedAlignmentEntriesListbySlice @@ -152,7 +152,7 @@ genParserClustalEntrySlice = do sliceIdentifier <- many1 (noneOf " ") spacer <- many1 (char ' ') - sliceSequence <- many1 (oneOf "NYRUAGCT-") + sliceSequence <- many1 (oneOf "SNYRUAGCT-") newline return $ ClustalAlignmentEntrySlice sliceIdentifier sliceSequence (length spacer) @@ -189,29 +189,25 @@ genParseMlocarnaHeader :: GenParser Char st String genParseMlocarnaHeader = do - string "mLo" - many1 (noneOf "\n") + string "mLocARNA" + many1 (choice [alphaNum,oneOf "-: ()."]) newline string "Copyright" - many1 (noneOf "\n") + many1 (choice [alphaNum,char ' ']) newline newline - many1 genParseAlignmentProcessStep + string "Compute pair probs ..." newline + string "Perform progressive alignment ..." newline - return "" - -genParseAlignmentProcessStep :: GenParser Char st String -genParseAlignmentProcessStep = do - many1 (noneOf ".\n") - choice [try (string ("... ")), try (string ("..."))] newline + newline return "" mergeStructuralAlignmentSlices :: [StructuralClustalAlignmentSlice] -> String -> Double -> StructuralClustalAlignment mergeStructuralAlignmentSlices slices secondaryStructure energy' = alignment where entrySlicesList = map structuralEntrySlices slices -- list of lists of entry slices - sequenceIdentifiers = map structuralEntrySequenceSliceIdentifier (head entrySlicesList) + sequenceIdentifiers = (map structuralEntrySequenceSliceIdentifier (head entrySlicesList)) alignmentEntriesListBySlice = map (map structuralEntryAlignedSliceSequence) entrySlicesList transposedAlignmentEntriesListbySlice = transpose alignmentEntriesListBySlice mergedAlignmentSequenceEntries = map concat transposedAlignmentEntriesListbySlice @@ -231,7 +227,7 @@ genParserStructuralClustalEntrySlice = do sliceIdentifier <- many1 (noneOf " ") many1 (char ' ') - sliceSequence <- many1 (oneOf "NYRUAGCT-") + sliceSequence <- many1 (oneOf "SNYRUAGCT-") newline return $ StructuralClustalAlignmentEntrySlice (filter (/='\n') sliceIdentifier) sliceSequence @@ -247,7 +243,7 @@ -- | Parse Clustal alignment (.aln) with secondary structure in dot-bracket notation from String (as produced by mlocarna) parseStructuralClustalAlignment :: String -> Either ParseError StructuralClustalAlignment -parseStructuralClustalAlignment = parse genParserStructuralClustalAlignment "genParserClustalAlignment" +parseStructuralClustalAlignment = parse genParserStructuralClustalAlignment "genParserStructuralClustalAlignment" -- | Parse Clustal alignment (.aln) with secondary structure in dot-bracket notation from filehandle (as produced by mlocarna) readStructuralClustalAlignment :: String -> IO (Either ParseError StructuralClustalAlignment) diff --git a/test-suite/Spec.hs b/test-suite/Spec.hs new file mode 100644 --- /dev/null +++ b/test-suite/Spec.hs @@ -0,0 +1,2 @@ +-- test-suite/Spec.hs +{-# OPTIONS_GHC -F -pgmF hspec-discover #-}