SelectSequencesFromMSA 1.0.2 → 1.0.3

raw patch · 3 files changed

+25/−14 lines, 3 filesPVP: major bump suggested

API removals or changes: PVP suggests a major version bump

API changes (from Hackage documentation)

Files

• SelectSequencesFromMSA.cabal +3/−3
• src/Bio/SelectSequences.hs +5/−3
• src/Bio/SelectSequencesLibrary.hs +17/−8

@@ -1,5 +1,5 @@ name:                SelectSequencesFromMSA-version:             1.0.2+version:             1.0.3 synopsis:            SelectSequences is a tool for selection of a represenative subset of sequences from a multiple sequence alignment in clustal format. description:         SelectSequences is a tool for selection of a represenative subset of sequences from a multiple sequence alignment in clustal format.                      .@@ -25,8 +25,8 @@  source-repository this   type:     git-  location: https://github.com/eggzilla/SelectSequencesFromMSA/tree/1.0.2-  tag:      1.0.2+  location: https://github.com/eggzilla/SelectSequencesFromMSA/tree/1.0.3+  tag:      1.0.3                       executable SelectSequencesFromMSA   Hs-Source-Dirs:      ./src/Bio/

@@ -18,7 +18,8 @@     optimalIdentity :: Double,     maximalIdenity :: Double,     referenceSequence :: Bool,-    distanceMatrixPath :: String+    distanceMatrixPath :: String,+    reformatIdOption :: String   } deriving (Show,Data,Typeable)  options :: Options@@ -30,7 +31,8 @@     optimalIdentity = (80 :: Double) &= name "i" &= help "Optimize for this percentage of mean pairwise identity (Default: 80)",     maximalIdenity = (95 :: Double) &= name "m" &= help "Sequences with a higher percentage of pairwise Identity will be removed. (Default: 95)",     referenceSequence = True &= name "x" &= help "The first sequence (=reference sequence) is always present in the output alignment per default. Default: True",-    distanceMatrixPath = "" &= name "d" &= help "Path to distance matrix output file, only internal for interal sequence selection, e.g. /home/user/distmat (Default: )"+    distanceMatrixPath = "" &= name "d" &= help "Path to distance matrix output file, only internal for interal sequence selection, e.g. /home/user/distmat (Default: )",+    reformatIdOption = "RNAcode" &= name "r" &= help "Defines how sequence id is reformated, e.g. fitting for RNAcode or not (Default: RNAcode)"   } &= summary "SelectSequences" &= help "Florian Eggenhofer 2016" &= verbosity  main :: IO ()@@ -48,7 +50,7 @@           Control.Monad.unless (null distanceMatrixPath) (writeFile distanceMatrixPath idMatrix)         else print ("A problem occured selecting sequences: " ++ fromLeft resultStatus)     else do-      resultStatus <- preprocessClustalForRNAz inputClustalPath (selectedOutputPath ++ "/") seqenceNumber optimalIdentity maximalIdenity referenceSequence+      resultStatus <- preprocessClustalForRNAz inputClustalPath (selectedOutputPath ++ "/") seqenceNumber optimalIdentity maximalIdenity referenceSequence reformatIdOption       if isRight resultStatus         then do           let (_,resultAln) = fromRight resultStatus

@@ -70,8 +70,8 @@   selectedClustalText <- readFile selectedClustalpath   return (Right ([],selectedClustalText)) -preprocessClustalForRNAz :: String -> String -> Int -> Double -> Double -> Bool -> IO (Either String (String,String))-preprocessClustalForRNAz clustalFilepath outputPath seqenceNumber optimalIdentity maximalIdenity referenceSequence = do+preprocessClustalForRNAz :: String -> String -> Int -> Double -> Double -> Bool -> String -> IO (Either String (String,String))+preprocessClustalForRNAz clustalFilepath outputPath seqenceNumber optimalIdentity maximalIdenity referenceSequence reformatOption = do   clustalText <- TI.readFile clustalFilepath   let clustalTextLines = T.lines clustalText   parsedClustalInput <- readClustalAlignment clustalFilepath@@ -80,7 +80,7 @@     then       if isRight parsedClustalInput         then do-          let (idMatrix,filteredClustalInput) = rnaCodeSelectSeqs2 (fromRight parsedClustalInput) seqenceNumber optimalIdentity maximalIdenity referenceSequence+          let (idMatrix,filteredClustalInput) = rnaCodeSelectSeqs2 (fromRight parsedClustalInput) seqenceNumber optimalIdentity maximalIdenity referenceSequence reformatOption           writeFile selectedClustalpath (show filteredClustalInput)           let formatedIdMatrix = show (fmap formatIdMatrix idMatrix)           return (Right (formatedIdMatrix,selectedClustalpath))@@ -99,8 +99,8 @@   -- | Sequence preselection for RNAz and RNAcode                   -rnaCodeSelectSeqs2 :: ClustalAlignment -> Int -> Double -> Double -> Bool -> (Matrix (Maybe (Int,Int,Double)),ClustalAlignment)-rnaCodeSelectSeqs2 currentClustalAlignment targetSeqNumber optimalIdentity maximalIdentity referenceSequence = (identityMatrix,newClustalAlignment)+rnaCodeSelectSeqs2 :: ClustalAlignment -> Int -> Double -> Double -> Bool -> String -> (Matrix (Maybe (Int,Int,Double)),ClustalAlignment)+rnaCodeSelectSeqs2 currentClustalAlignment targetSeqNumber optimalIdentity maximalIdentity referenceSequence reformatOption = (identityMatrix,newClustalAlignment)   where entryVector = V.fromList (alignmentEntries currentClustalAlignment)         entrySequences = V.map entryAlignedSequence entryVector         entryReformatedSequences = V.map (T.map reformatRNACodeAln) entrySequences@@ -120,7 +120,9 @@         selectedEntryIndices = selectEntryIndices referenceSequence targetSeqNumber sortedIndices         selectedEntries = map (\ind -> entryVector V.! (ind-1)) selectedEntryIndices         selectedEntryHeader = map entrySequenceIdentifier selectedEntries-        reformatedSelectedEntryHeader =  map (T.map reformatRNACodeId) selectedEntryHeader+        selectedReformatFunction = selectReformatFunction reformatOption+        reformatedSelectedEntryHeader =  map (T.map selectedReformatFunction) selectedEntryHeader+        --reformatedSelectedEntryHeader =  map (T.map reformatRNACodeId) selectedEntryHeader         selectedEntrySequences = map (\ind -> entryReformatedSequences V.! (ind-1)) selectedEntryIndices         --gapfreeEntrySequences = T.transpose (T.filter (\a -> not (T.all isGap a)) (T.transpose selectedEntrySequences))         gapfreeEntrySequences = T.transpose (filter (not . T.all isGap) (T.transpose selectedEntrySequences))@@ -128,13 +130,19 @@         emptyConservationTrack = setEmptyConservationTrack gapfreeEntries (conservationTrack currentClustalAlignment)         newClustalAlignment = currentClustalAlignment {alignmentEntries = gapfreeEntries, conservationTrack = emptyConservationTrack} +selectReformatFunction :: String -> (Char -> Char)+selectReformatFunction reformatOption+  | reformatOption == "RNAcode" = reformatRNACodeId+  | otherwise = id+ selectEntryIndices :: Bool -> Int -> [Int] -> [Int] selectEntryIndices referenceSequence targetSeqNumber sortedIndices-  | referenceSequence = if (1 :: Int) `elem` firstX then firstX else 1:firstXm1+  | referenceSequence = if (1 :: Int) `elem` firstX then firstRefX else 1:firstXm1   | otherwise = firstX     where firstXm1 = take (targetSeqNumber - 1)  sortedIndices           firstX = take targetSeqNumber sortedIndices-+          firstRefX =(1 :: Int):(filter (\i -> i /= (1 :: Int)) firstX)+  setEmptyConservationTrack :: [ClustalAlignmentEntry] -> T.Text -> T.Text setEmptyConservationTrack alnentries currentConservationTrack   | null alnentries = currentConservationTrack@@ -242,3 +250,4 @@   | c == 'c' = 'C'   | c == 'a' = 'A'   | otherwise = c+