modify-fasta 0.8.0.3 → 0.8.0.4

raw patch · 8 files changed

+23/−66 lines, 8 filesPVP: major bump suggested

API removals or changes: PVP suggests a major version bump

API changes (from Hackage documentation)

Files

• modify-fasta.cabal +1/−1
• src/Diversity.hs +1/−44
• src/FilterCloneList.hs +1/−1
• src/FilterCloneMap.hs +10/−10
• src/FilterFastaList.hs +3/−3
• src/Print.hs +2/−2
• src/TransformCloneList.hs +2/−2
• src/Utility.hs +3/−3

@@ -2,7 +2,7 @@ -- documentation, see http://haskell.org/cabal/users-guide/  name:                modify-fasta-version:             0.8.0.3+version:             0.8.0.4 synopsis:            Modify fasta (and CLIP) files in several optional ways -- description:          homepage:            https://github.com/GregorySchwartz/modify-fasta

@@ -9,49 +9,6 @@ import Data.List import qualified Data.Text as T --- Takes two strings, returns Hamming distance+-- | Takes two strings, returns Hamming distance hamming :: T.Text -> T.Text -> Int hamming xs ys = length $ filter (not . uncurry (==)) $ T.zip xs ys---- Returns the diversity of a list of things-diversity :: (Ord b) => Double -> [b] -> Double-diversity order sample-    | length sample == 0 = 0-    | order == 1         = exp . h $ speciesList-    | otherwise          = (sum . map ((** order) . p_i) $ speciesList) ** pow-  where-    pow          = 1 / (1 - order)-    h            = negate . sum . map (\x -> (p_i x) * (log (p_i x)))-    p_i x        = ((fromIntegral . length $ x) :: Double) /-                   ((fromIntegral . length $ sample) :: Double)-    speciesList  = group . sort $ sample---- Calculates the binary coefficient-choose :: (Integral a) => a -> a -> a-choose _ 0 = 1-choose 0 _ = 0-choose n k = choose (n - 1) (k - 1) * n `div` k---- Returns the rarefaction curve for each position in a list-rarefactionCurve :: (Eq a, Ord a) => [a] -> [Double]-rarefactionCurve xs = map rarefact [1..n_total]-  where-    rarefact n-        | n == 0       = 0-        | n == 1       = 1-        | n == n_total = k-        | otherwise    = k - ((1 / (fromIntegral (choose n_total n))) * inner n)-    inner n = fromIntegral                              .-              sum                                       .-              map (\g -> choose (n_total - length g) n) $-              grouped-    n_total = length xs-    k       = genericLength grouped-    grouped = group . sort $ xs---- Calculates the percent of the curve that is above 95% of height of the curve-rarefactionViable :: [Double] -> Double-rarefactionViable xs = (genericLength valid / genericLength xs) * 100-  where-    valid = dropWhile (< (0.95 * last xs)) xs-

@@ -22,7 +22,7 @@ -- Local import Types --- Remove highly mutated sequences (sequences with more than a third of+-- | Remove highly mutated sequences (sequences with more than a third of -- their sequence being mutated). filterHighlyMutatedEntry :: GeneticUnit -> CloneEntry -> CloneEntry filterHighlyMutatedEntry !genUnit = newEntry

@@ -25,17 +25,17 @@ import Types import Diversity --- Check if the data structure is Right+-- | Check if the data structure is Right isRight' :: Either a b -> Bool isRight' (Right _)       = True isRight' _               = False --- Altered version of listToMaybe+-- | Altered version of listToMaybe listToMaybe' :: [a] -> Maybe [a] listToMaybe' []      = Nothing listToMaybe' x       = Just x --- Remove highly mutated sequences (sequences with more than a third of+-- | Remove highly mutated sequences (sequences with more than a third of -- their sequence being mutated). filterHighlyMutated :: GeneticUnit -> CloneMap -> (CloneMap, Maybe String) filterHighlyMutated !genUnit !cloneMap = (newCloneMap, errorString)@@ -86,7 +86,7 @@     readSeq Nucleotide x = Right x     readSeq AminoAcid x  = translate 1 x --- Replace codons that have more than CodonMut mutations (make them "---"+-- | Replace codons that have more than CodonMut mutations (make them "---" -- codons). removeCodonMutCount :: CodonMut -> T.Text -> T.Text -> CloneMap -> CloneMap removeCodonMutCount codonMut codonMutType mutType = M.mapWithKey mapRemove@@ -112,7 +112,7 @@     isMutType "SILENT" x y      = codon2aa x == codon2aa y     isMutType _ _ _             = True --- Remove clone sequences that have stop codons in the first stopRange+-- | Remove clone sequences that have stop codons in the first stopRange -- codons removeStopsCloneMap :: GeneticUnit                     -> Int@@ -148,7 +148,7 @@     fromEither (Right x)     = x     fromEither (Left x)      = error (T.unpack x) --- Remove duplicate sequences+-- | Remove duplicate sequences removeDuplicatesCloneMap :: CloneMap -> CloneMap removeDuplicatesCloneMap cloneMap = M.map                                     (filter (`S.member` duplicateSet))@@ -160,7 +160,7 @@                  . M.toAscList                  $ cloneMap --- Remove out of frame sequences+-- | Remove out of frame sequences removeOutOfFrameSeqs :: CloneMap -> CloneMap removeOutOfFrameSeqs = M.map (filter isInFrame)   where@@ -170,7 +170,7 @@                . T.filter (\x -> not $ T.isInfixOf (T.singleton x) ".-")                . fastaSeq --- Remove sequences that do not contain the string customFilter in the+-- | Remove sequences that do not contain the string customFilter in the -- customField location, split by "|". Note that this is 1 indexed and -- 0 means to search the entire header for the customFilter. If the -- customRemove option is enabled, this function will instead remove@@ -210,11 +210,11 @@   where     filterMap acc (x, y) = removeCustomFilter germ rm x y acc --- Remove clones that do not have any sequences after the filtrations+-- | Remove clones that do not have any sequences after the filtrations removeEmptyClone :: CloneMap -> CloneMap removeEmptyClone = M.filter (not . null) --- Convert sequences to amino acids+-- | Convert sequences to amino acids convertToAminoAcidsCloneMap :: CloneMap -> (CloneMap, Maybe String) convertToAminoAcidsCloneMap cloneMap = (newCloneMap, errorString)   where

@@ -24,7 +24,7 @@ -- Local import Types --- Remove clone sequences that have stop codons in the first stopRange+-- | Remove clone sequences that have stop codons in the first stopRange -- codons hasNoStops :: GeneticUnit            -> Int@@ -41,7 +41,7 @@                     . translate 1     stop AminoAcid = Right . not . T.isInfixOf "*" . T.take stopRange . fastaSeq --- Remove out of frame sequences+-- | Remove out of frame sequences isInFrame :: FastaSequence -> Bool isInFrame = (== 0)           . mod 3@@ -49,7 +49,7 @@           . T.filter (\x -> not . T.isInfixOf (T.singleton x) $ ".-")           . fastaSeq --- Remove sequences that do not contain the string customFilter in the+-- | Remove sequences that do not contain the string customFilter in the -- customField location, split by "|". Note that this is 1 indexed and -- 0 means to search the entire header for the customFilter. If the -- customRemove option is enabled, this function will instead remove

@@ -20,7 +20,7 @@ -- Local import Types --- Return the results of the filtration in text form for saving+-- | Return the results of the filtration in text form for saving -- to a file printFasta :: CloneMap -> T.Text printFasta = body@@ -37,7 +37,7 @@                                   , z                                   ] --- Return the results of the filtration in text form for saving+-- | Return the results of the filtration in text form for saving -- to a file and excluding germline printFastaNoGermline :: CloneMap -> T.Text printFastaNoGermline = body

@@ -31,7 +31,7 @@ noGaps :: T.Text -> Bool noGaps = not . any (\x -> x == '.' || x == '-') . T.unpack --- Replace codons that have more than CodonMut mutations (make them "---"+-- | Replace codons that have more than CodonMut mutations (make them "---" -- codons) and don't have gaps in them. onlyMutations :: CodonMut -> T.Text -> T.Text -> CloneEntry -> CloneEntry onlyMutations codonMut codonMutType mutType = newEntry@@ -61,7 +61,7 @@     isMutType "ALL" _ _         = True     isMutType _ _ _             = error "Unknown mutation type" --- Only include codons containing mutations found in a certain number of+-- | Only include codons containing mutations found in a certain number of -- mutants frequentMutations :: Maybe Int                   -> Maybe Int

@@ -34,7 +34,7 @@     insertDummy x   = (dummy, [x])     dummy = FastaSequence {fastaHeader = "filler", fastaSeq = "---"} --- Like zipWith, but if one if one list is longer than the other than use+-- | Like zipWith, but if one if one list is longer than the other than use -- the remaining, needs to be the same type zipWithRetain :: (a -> a -> a) -> [a] -> [a] -> [a] zipWithRetain _ [] [] = []@@ -42,7 +42,7 @@ zipWithRetain _ [] ys = ys zipWithRetain f (x:xs) (y:ys) = f x y : zipWithRetain f xs ys --- Like zipWithRetain, but for text+-- | Like zipWithRetain, but for text zipWithRetainText :: (Char -> Char -> Char) -> T.Text -> T.Text -> T.Text zipWithRetainText _ (T.uncons -> Nothing) (T.uncons -> Nothing) = T.empty zipWithRetainText _ xs (T.uncons -> Nothing) = xs@@ -50,7 +50,7 @@ zipWithRetainText f (T.uncons -> Just (x, xs)) (T.uncons -> Just (y, ys))     = f x y `T.cons` zipWithRetainText f xs ys --- Replace characters in the first string with another in the second string+-- | Replace characters in the first string with another in the second string -- if they are equal to a certain character and they aren't replaced with -- a gap. replaceChars :: Char -> T.Text -> T.Text -> T.Text