diff --git a/ClustalParser.cabal b/ClustalParser.cabal --- a/ClustalParser.cabal +++ b/ClustalParser.cabal @@ -5,7 +5,7 @@ -- PVP summary: +-+------- breaking API changes -- | | +----- non-breaking API additions -- | | | +--- code changes with no API change -version: 1.1.4 +version: 1.2.0 synopsis: Libary for parsing Clustal tools output description: Currently contains parsers and datatypes for: clustalw2, clustalo, mlocarna, cmalign . @@ -36,8 +36,8 @@ source-repository this type: git - location: https://github.com/eggzilla/ClustalParser/tree/1.1.4 - tag: 1.1.4 + location: https://github.com/eggzilla/ClustalParser/tree/1.2.0 + tag: 1.2.0 library -- Modules exported by the library. @@ -45,7 +45,7 @@ other-modules: Bio.ClustalData -- Other library packages from which modules are imported. - build-depends: base >=4.5 && <5, parsec>=3.1.9, vector + build-depends: base >=4.5 && <5, parsec>=3.1.9, vector, text -- compiler options ghc-options: -Wall -O2 -fno-warn-unused-do-bind -- Directories containing source files. diff --git a/changelog b/changelog --- a/changelog +++ b/changelog @@ -1,4 +1,6 @@ -*-change-log-*- +1.2.0 Florian Eggenhofer 07. January 2017 + * Changed datastructures for sequence identifers and sequences to Data.Text 1.1.4 Florian Eggenhofer 30. May 2016 * Fixed a bug in output of clustal alignments with sequence length of 60 1.1.3 Florian Eggenhofer 4. July 2015 diff --git a/src/Bio/ClustalData.hs b/src/Bio/ClustalData.hs --- a/src/Bio/ClustalData.hs +++ b/src/Bio/ClustalData.hs @@ -3,26 +3,27 @@ module Bio.ClustalData where import qualified Data.Vector as V - +import qualified Data.Text as T + -- | Data type for clustal summary, containing information about the alignment process, usually printed to STDOUT data ClustalSummary = ClustalSummary { - clustalw2version :: String, - sequenceFormat :: String, + clustalw2version :: T.Text, + sequenceFormat :: T.Text, parametersOfInputSequences :: [SequenceParameters], pairwiseAlignmentSummaries :: [PairwiseAlignmentSummary], - guideTreeFileName :: String, + guideTreeFileName :: T.Text, groupNumber :: Int, groupSummaries :: [GroupSummary], alignmentScore :: Int, - alignmentFileName :: String + alignmentFileName :: T.Text } deriving (Show, Eq) data SequenceParameters = SequenceParameters { inputSequenceIndex :: Int, - inputSequenceIdentifier :: String, + inputSequenceIdentifier :: T.Text, inputSequenceLength :: Int } deriving (Show, Eq) @@ -47,7 +48,7 @@ data ClustalAlignment = ClustalAlignment { alignmentEntries :: [ClustalAlignmentEntry], - conservationTrack :: String + conservationTrack :: T.Text } deriving (Eq) @@ -56,30 +57,30 @@ | 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)) + longestSequenceIdLength = (maximum (map T.length (map entrySequenceIdentifier _alignmentEntries))) + 1 + totalSequenceLength = T.length (entryAlignedSequence (head _alignmentEntries)) alignmentString = showAlignment totalSequenceLength longestSequenceIdLength 0 _alignmentEntries _conservationTrack -showAlignment :: Int -> Int -> Int -> [ClustalAlignmentEntry] -> String -> String +showAlignment :: Int -> Int -> Int -> [ClustalAlignmentEntry] -> T.Text -> String showAlignment totalSequenceLength longestSequenceIdLength currentWindowPosition _alignmentEntries _conservationTrack | totalSequenceLength == 0 = [] | currentWindowPosition < totalSequenceLength = showAlignmentBlock longestSequenceIdLength currentWindowPosition _alignmentEntries _conservationTrack ++ (showAlignment totalSequenceLength longestSequenceIdLength (currentWindowPosition + 60) _alignmentEntries _conservationTrack) | currentWindowPosition == totalSequenceLength = [] | otherwise = "" -showAlignmentBlock :: Int -> Int -> [ClustalAlignmentEntry] -> String -> String +showAlignmentBlock :: Int -> Int -> [ClustalAlignmentEntry] -> T.Text -> 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" + extraTrack = concat (replicate longestSequenceIdLength " ") ++ V.toList (V.slice currentWindowPosition 60 (V.fromList (T.unpack _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" +showAlignmentLine longestSequenceIdLength currentWindowPosition _alignmentEntry = T.unpack (entrySequenceIdentifier _alignmentEntry) ++ concat (replicate (longestSequenceIdLength - T.length (entrySequenceIdentifier _alignmentEntry)) " ") ++ V.toList (V.slice currentWindowPosition 60 (V.fromList (T.unpack (entryAlignedSequence _alignmentEntry)))) ++ "\n" data ClustalAlignmentEntry = ClustalAlignmentEntry { - entrySequenceIdentifier :: String, - entryAlignedSequence :: String + entrySequenceIdentifier :: T.Text, + entryAlignedSequence :: T.Text } deriving (Show, Eq) @@ -102,7 +103,7 @@ data StructuralClustalAlignment = StructuralClustalAlignment { structuralAlignmentEntries :: [ClustalAlignmentEntry], - secondaryStructureTrack :: String, + secondaryStructureTrack :: T.Text, energy :: Double } deriving (Eq) @@ -112,8 +113,8 @@ | 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)) + longestSequenceIdLength = (maximum (map T.length (map entrySequenceIdentifier _alignmentEntries))) + 1 + totalSequenceLength = T.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 @@ -14,6 +14,7 @@ import Text.ParserCombinators.Parsec import Control.Monad import Data.List +import qualified Data.Text as T readDouble :: String -> Double readDouble = read @@ -69,7 +70,7 @@ newline newline eof - return $ ClustalSummary version sequenceFormat' sequenceParametersList pairwiseAlignmentSummaryList guideTreeFileName' (readInt numberOfGroups) groupSummaryList (readInt alignmentScore') alignmentFileName' + return $ ClustalSummary (T.pack version) (T.pack sequenceFormat') sequenceParametersList pairwiseAlignmentSummaryList (T.pack guideTreeFileName') (readInt numberOfGroups) groupSummaryList (readInt alignmentScore') (T.pack alignmentFileName') genParserGroupSummary :: GenParser Char st GroupSummary genParserGroupSummary = do @@ -109,7 +110,7 @@ space string "bp" newline - return $ SequenceParameters (readInt sequenceIndexParam) sequenceIdentifierParam (readInt sequenceLengthParam) + return $ SequenceParameters (readInt sequenceIndexParam) (T.pack sequenceIdentifierParam) (readInt sequenceLengthParam) -- | Parse the input as ClustalAlignment datatype genParserClustalAlignment :: GenParser Char st ClustalAlignment @@ -131,10 +132,10 @@ mergedAlignmentEntries = map constructAlignmentEntries (zip sequenceIdentifiers mergedAlignmentSequenceEntries) conservationTrackSlices = map conservationTrackSlice slices mergedConservationTrack = concat conservationTrackSlices - alignment = ClustalAlignment mergedAlignmentEntries mergedConservationTrack + alignment = ClustalAlignment mergedAlignmentEntries (T.pack mergedConservationTrack) constructAlignmentEntries :: (String, String) -> ClustalAlignmentEntry -constructAlignmentEntries (entryIdentifier,entrySequence) = ClustalAlignmentEntry entryIdentifier entrySequence +constructAlignmentEntries (entryIdentifier,entrySequence) = ClustalAlignmentEntry (T.pack entryIdentifier) (T.pack entrySequence) genParserClustalAlignmentSlice :: GenParser Char st ClustalAlignmentSlice genParserClustalAlignmentSlice = do @@ -211,10 +212,10 @@ transposedAlignmentEntriesListbySlice = transpose alignmentEntriesListBySlice mergedAlignmentSequenceEntries = map concat transposedAlignmentEntriesListbySlice mergedAlignmentEntries = map constructStructuralAlignmentEntries (zip sequenceIdentifiers mergedAlignmentSequenceEntries) - alignment = StructuralClustalAlignment mergedAlignmentEntries secondaryStructure energy' + alignment = StructuralClustalAlignment mergedAlignmentEntries (T.pack secondaryStructure) energy' constructStructuralAlignmentEntries :: (String, String) -> ClustalAlignmentEntry -constructStructuralAlignmentEntries (entryIdentifier,entrySequence) = ClustalAlignmentEntry entryIdentifier entrySequence +constructStructuralAlignmentEntries (entryIdentifier,entrySequence) = ClustalAlignmentEntry (T.pack entryIdentifier) (T.pack entrySequence) genParserStructuralClustalAlignmentSlice :: GenParser Char st StructuralClustalAlignmentSlice genParserStructuralClustalAlignmentSlice = do @@ -257,10 +258,10 @@ readClustalSummary = parseFromFile genParserClustalSummary -- | Parse nucleotide sequence. Allowed letters according to IUPAC -parseNucleotideSequence :: GenParser Char st String -parseNucleotideSequence = do - nucleotideSequence <- many1 (oneOf "RYSWKMBDHVNATUGCryswkmbdhvnatugc") - return $ nucleotideSequence +--parseNucleotideSequence :: GenParser Char st String +--parseNucleotideSequence = do +-- nucleotideSequence <- many1 (oneOf "RYSWKMBDHVNATUGCryswkmbdhvnatugc") +-- return $ nucleotideSequence -- | Parse nucleotide alignment entry. Allowed letters according to IUPAC and commonly used gap characters parseNucleotideAlignmentEntry :: GenParser Char st String @@ -269,13 +270,13 @@ return $ entry -- | Parse protein amino acid code sequence. Allowed letters according to IUPAC -parseProteinSequence :: GenParser Char st String -parseProteinSequence = do - proteinSequence <- many1 (oneOf "ABCDEFGHIKLMNPQRSTVWXYZabcdefghiklmnpqrstvwxyz") - return $ proteinSequence +--parseProteinSequence :: GenParser Char st String +--parseProteinSequence = do +-- proteinSequence <- many1 (oneOf "ABCDEFGHIKLMNPQRSTVWXYZabcdefghiklmnpqrstvwxyz") +-- return $ proteinSequence -- | Parse protein amino acid code alignment entry. Allowed letters according to IUPAC and commonly used gap characters -parseProteinAlignmentEntry :: GenParser Char st String -parseProteinAlignmentEntry = do - entry <- many1 (oneOf "~_-.ABCDEFGHIKLMNPQRSTVWXYZabcdefghiklmnpqrstvwxyz") - return $ entry +--parseProteinAlignmentEntry :: GenParser Char st String +--parseProteinAlignmentEntry = do +-- entry <- many1 (oneOf "~_-.ABCDEFGHIKLMNPQRSTVWXYZabcdefghiklmnpqrstvwxyz") +-- return $ entry