bioinformatics-toolkit 0.9.0 → 0.9.1

raw patch · 4 files changed

+41/−10 lines, 4 filesPVP: major bump suggested

API removals or changes: PVP suggests a major version bump

API changes (from Hackage documentation)

Files

• LICENSE +1/−1
• bioinformatics-toolkit.cabal +2/−2
• src/Bio/Data/Bed.hs +33/−5
• tests/Tests/Bed.hs +5/−2

@@ -1,6 +1,6 @@ The MIT License (MIT) -Copyright (c) 2014-2016 Kai Zhang+Copyright (c) 2014-2020 Kai Zhang  Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal

@@ -1,12 +1,12 @@ name:                bioinformatics-toolkit-version:             0.9.0+version:             0.9.1 synopsis:            A collection of bioinformatics tools description:         A collection of bioinformatics tools license:             MIT license-file:        LICENSE author:              Kai Zhang maintainer:          kai@kzhang.org-copyright:           (c) 2014-2019 Kai Zhang+copyright:           (c) 2014-2020 Kai Zhang category:            Bio build-type:          Simple extra-source-files:  README.md

@@ -35,7 +35,8 @@     , mergeBedWith     , mergeSortedBed     , mergeSortedBedWith-    , splitOverlapped+--    , splitOverlapped+    , countOverlapped      -- * IO     , streamBed@@ -58,7 +59,7 @@ import           Data.Function                (on) import qualified Data.HashMap.Strict          as M import qualified Data.IntervalMap.Strict      as IM-import           Data.List                    (groupBy, sortBy)+import           Data.List                    (groupBy, sortBy, group) import           Data.Ord                     (comparing) import           Data.Conduit.Zlib           (gzip, ungzip, multiple) import qualified Data.Vector                  as V@@ -236,14 +237,16 @@             e' = bed^.chromEnd {-# INLINE mergeSortedBedWith #-} +{- -- | Split overlapped regions into non-overlapped regions. The input must be overlapped. -- This function is usually used with `mergeBedWith`. splitOverlapped :: BEDLike b => ([b] -> a) -> [b] -> [(BED3, a)] splitOverlapped fun xs = filter ((>0) . size . fst) $-    evalState (F.foldrM f [] $ init xs') x0+    evalState (F.foldrM f [] $ init anchors) $+        (\(a,b) -> (fromEither a, M.singleton (b^.chromStart, b^.chromEnd) b)) $+        last anchors   where-    x0 = (\(a,b) -> (fromEither a, M.singleton (b^.chromStart, b^.chromEnd) b)) $ last xs'-    xs' = sortBy (comparing (fromEither . fst)) $ concatMap+    anchors = sortBy (comparing (fromEither . fst)) $ concatMap         ( \x -> [(Left $ x^.chromStart, x), (Right $ x^.chromEnd, x)] ) xs     f (i, x) acc = do         (j, s) <- get@@ -257,7 +260,32 @@     fromEither (Right x) = x     chr = head xs ^. chrom {-# INLINE splitOverlapped #-}+-} +-- | Split overlapped regions into non-overlapped regions. The input must be overlapped.+-- This function is usually used with `mergeBedWith`.+countOverlapped :: BEDLike b => [b] -> [(BED3, Int)]+countOverlapped xs = reverse $ (\(_,_,x) -> x) $+    F.foldl' go (p0, c0, []) $ tail anchors+  where+    (Left p0, c0) = head anchors+    go (x, accum, result) (Left p, count)+        | x == p = (p, accum + count, result)+        | otherwise = (p, accum + count, (asBed chr x $ p, accum):result)+    go (x, accum, result) (Right p, count) =+      (p+1, accum - count, (asBed chr x $ p + 1, accum):result)+    anchors = map (\x -> (head x, length x)) $ group $ sortBy cmp $ concatMap+        (\x -> [Left $ x^.chromStart, Right $ x^.chromEnd - 1]) xs+    cmp (Left x) (Left y) = compare x y+    cmp (Right x) (Right y) = compare x y+    cmp (Left x) (Right y) = case compare x y of+        EQ -> LT+        o -> o+    cmp (Right x) (Left y) = case compare x y of+        EQ -> GT+        o -> o+    chr = head xs ^. chrom+{-# INLINE countOverlapped #-}  streamBed :: (MonadResource m, BEDConvert b, MonadIO m)           => FilePath -> ConduitT i b m () 

@@ -57,9 +57,11 @@         , (120, 160)         , (155, 200)         , (155, 220)+        , (0, 10)+        , (0, 10)         ]     expect = map (\((a,b), x) -> (asBed "chr1" a b, x))-        [ ((0, 10), 1)+        [ ((0, 10), 3)         , ((10, 20), 2)         , ((20, 50), 1)         , ((50, 100), 2)@@ -70,7 +72,8 @@         , ((160, 200), 2)         , ((200, 220), 1)         ]-    result = sortBy (compareBed `on` fst) $ splitOverlapped length input+    --result = sortBy (compareBed `on` fst) $ splitOverlapped length input+    result = sortBy (compareBed `on` fst) $ countOverlapped input  mergeBedTest :: Assertion mergeBedTest = expect @=? result