bio 0.4.6 → 0.4.7

raw patch · 4 files changed

+18/−126 lines, 4 filesPVP: major bump suggested

API removals or changes: PVP suggests a major version bump

API changes (from Hackage documentation)

Files

• Bio/Alignment/AlignData.hs +2/−0
• Bio/Sequence.hs +14/−1
• Bio/Util/TestBase.hs +0/−123
• bio.cabal +2/−2

@@ -41,6 +41,8 @@  -- | Gaps are coded as '*'s, this function removes them, and returns --   the sequence along with the list of gap positions.+--   note that gaps are positioned relative to the *gapped* sequence +--   (contrast to stmassembler/Cluster.hs) extractGaps :: SeqData -> (SeqData,Gaps) extractGaps str = (BC.filter (/='*') str,BC.elemIndices '*' str) 

@@ -21,7 +21,10 @@     -- ** Other utility functions     , defragSeq, seqmap -    -- * File formats+    -- * File IO+    -- ** Generic sequence reading+    , readNuc, readProt+     -- ** The Fasta file format ("Bio.Sequence.Fasta")     , readFasta, hReadFasta      , writeFasta, hWriteFasta@@ -67,3 +70,13 @@ -- sequence-oriented stuff import Bio.Sequence.Entropy import Bio.Sequence.HashWord++-- | Read nucleotide sequences in any format - Fasta, SFF, FastQ, 2bit, PHD...+readNuc :: FilePath -> IO [Sequence Nuc]+readNuc = undefined+          -- check file contents+          -- magic number++-- | Read protein sequences in any supported format (i.e. Fasta)+readProt :: FilePath -> IO [Sequence Amino]+readProt xs = map castSeq `fmap` readFasta xs

@@ -1,123 +0,0 @@-{-# OPTIONS -fglasgow-exts #-}--module Bio.Util.TestBase where--import Control.Monad (liftM)-import System.CPUTime-import System.Time-import Test.QuickCheck-import System.Random--- import Data.Char (ord)-import Data.Word-import Data.ByteString.Lazy (pack)--import Bio.Sequence.SeqData--data Test = forall t . Testable t => T String t--newtype Nucleotide = N Char deriving Show-newtype Quality    = Q Word8 deriving Show--fromN :: Nucleotide -> Char-fromN (N c) = c--fromQ :: Quality -> Word8-fromQ (Q c) = c---- | For testing, variable lengths-newtype EST = E (Sequence Nuc) deriving Show-newtype ESTq = Eq (Sequence Nuc) deriving Show-newtype Protein = P (Sequence Amino) deriving Show---- | For benchmarking, fixed lengths-newtype EST_short = ES (Sequence Nuc) deriving Show-newtype EST_long  = EL (Sequence Nuc) deriving Show-newtype EST_set  = ESet [Sequence Nuc] deriving Show---- | Take time (CPU and wall clock) and report it-time :: String -> IO () -> IO ()-time msg action = do-    d1 <- getClockTime-    t1 <- getCPUTime-    action-    t2 <- getCPUTime-    d2 <- getClockTime-    putStrLn $ "\n"++msg++", CPU time: " ++ showT (t2-t1) ++ ", wall clock: "-                 ++ timeDiffToString (diffClockTimes d2 d1)---- | Print a CPUTime difference-showT :: Integral a => a -> String-showT t = show (fromIntegral t/1e12::Double)++"s"---- | Shamelessly stolen from FPS-integralRandomR :: (Integral a, RandomGen g) => (a,a) -> g -> (a,g)-integralRandomR  (a,b) g = case randomR (fromIntegral a :: Integer,-                                         fromIntegral b :: Integer) g of-                            (x,g') -> (fromIntegral x, g')---- | Constrained position generators--genOffset :: Gen Offset-genOffset = do isneg <- arbitrary-               nnoff <- genNonNegOffset-               return $ (if isneg then negate else id) nnoff--genNonNegOffset :: Gen Offset-genNonNegOffset = liftM (subtract 1) genPositiveOffset--genPositiveOffset :: Gen Offset-genPositiveOffset = do scale <- chooseInteger (1, 13)-                       liftM fromIntegral $ chooseInteger (1, 2^scale)-    where chooseInteger :: (Integer, Integer) -> Gen Integer-          chooseInteger = choose---instance Random Word8 where-    randomR = integralRandomR-    random = randomR (minBound,maxBound)--instance Arbitrary Word8 where-    arbitrary = choose (0,255)--instance Arbitrary Nucleotide where-    arbitrary = elements (map N "aaacccgggtttn")--instance Arbitrary Quality where-    arbitrary = do c <- choose (0,60)-                   return (Q c)--instance Arbitrary ESTq where-    arbitrary = do n <- choose (1,100)-                   s <- vector n-                   q <- vector n-                   return $ Eq $ Seq (fromStr "qctest")-                              (fromStr $ map fromN s) (Just $ pack $ map fromQ q)--instance Arbitrary EST where-    arbitrary = do n <- choose (1,100)-                   s <- vector n-                   return $ E $ Seq (fromStr "qctest")-                              (fromStr $ map fromN s) Nothing---- instance Arbitrary Char where---    arbitrary = elements (['A'..'Z']++['a'..'z']++" \t\n\r")--instance Arbitrary EST_short where-    arbitrary = do let n = 200-                   s <- vector n-                   q <- vector n-                   return $ ES $ Seq (fromStr "qctest")-                              (fromStr $ map fromN s) (Just $ pack $ map fromQ q)--instance Arbitrary EST_long where-    arbitrary = do let n = 1000-                   s <- vector n-                   q <- vector n-                   return $ EL $ Seq (fromStr "qctest")-                              (fromStr $ map fromN s) (Just $ pack $ map fromQ q)---- 1000 ESTs of length 1000-instance Arbitrary EST_set where-    arbitrary = do let n = 1000-                   s <- vector n-                   return (ESet $ map (\(EL x) -> x) s)

@@ -1,5 +1,5 @@ Name:                bio-Version:             0.4.6+Version:             0.4.7 License:             LGPL License-file:        LICENSE Author:              Ketil Malde@@ -50,7 +50,7 @@                      Bio.Alignment.Soap, 		     Bio.Alignment.BED, Bio.Alignment.PSL                      Bio.Clustering,-                     Bio.Util, Bio.Util.Parsex, Bio.Util.TestBase+                     Bio.Util, Bio.Util.Parsex 		 Bio.Location.Strand, Bio.Location.Position, 		 Bio.Location.ContigLocation, Bio.Location.Location, Bio.Location.LocMap, 		 Bio.Location.OnSeq, Bio.Location.SeqLocation, Bio.Location.SeqLocMap,