Bio.Data.Bed

Documentation

class BEDLike b where

A class representing BED-like data, e.g., BED3, BED6 and BED12. BED format uses 0-based index (see documentation).

Minimal complete definition

asBed, fromLine, toLine, chrom, chromStart, chromEnd, bedName, bedScore, bedStrand

Methods

asBed :: ByteString -> Int -> Int -> b

Construct bed record from chromsomoe, start location and end location

fromLine :: ByteString -> b

Convert bytestring to bed format

toLine :: b -> ByteString

Convert bed to bytestring

chrom :: b -> ByteString

Field accessor

chromStart :: b -> Int

chromEnd :: b -> Int

bedName :: b -> Maybe ByteString

bedScore :: b -> Maybe Double

bedStrand :: b -> Maybe Bool

convert :: BEDLike b' => b' -> b

bedSize :: b -> Int

Return the size of a bed region.

Instances

BEDLike NarrowPeak

Methods

asBed :: ByteString -> Int -> Int -> NarrowPeak

fromLine :: ByteString -> NarrowPeak

toLine :: NarrowPeak -> ByteString

chrom :: NarrowPeak -> ByteString

chromStart :: NarrowPeak -> Int

chromEnd :: NarrowPeak -> Int

bedName :: NarrowPeak -> Maybe ByteString

bedScore :: NarrowPeak -> Maybe Double

bedStrand :: NarrowPeak -> Maybe Bool

convert :: BEDLike b' => b' -> NarrowPeak

bedSize :: NarrowPeak -> Int

BEDLike BED3

Methods

asBed :: ByteString -> Int -> Int -> BED3

fromLine :: ByteString -> BED3

toLine :: BED3 -> ByteString

chrom :: BED3 -> ByteString

chromStart :: BED3 -> Int

chromEnd :: BED3 -> Int

bedName :: BED3 -> Maybe ByteString

bedScore :: BED3 -> Maybe Double

bedStrand :: BED3 -> Maybe Bool

convert :: BEDLike b' => b' -> BED3

bedSize :: BED3 -> Int

BEDLike BED

Methods

asBed :: ByteString -> Int -> Int -> BED

fromLine :: ByteString -> BED

toLine :: BED -> ByteString

chrom :: BED -> ByteString

chromStart :: BED -> Int

chromEnd :: BED -> Int

bedName :: BED -> Maybe ByteString

bedScore :: BED -> Maybe Double

bedStrand :: BED -> Maybe Bool

convert :: BEDLike b' => b' -> BED

bedSize :: BED -> Int

BED6 format

data BED

BED6 format, as described in http://genome.ucsc.edu/FAQ/FAQformat.html#format1.7

Constructors

BED

Fields

• _chrom :: !ByteString
• _chromStart :: !Int
• _chromEnd :: !Int
• _name :: !(Maybe ByteString)
• _score :: !(Maybe Double)
• _strand :: !(Maybe Bool)

  True: "+", False: "-"

Instances

Eq BED

Methods

(==) :: BED -> BED -> Bool

(/=) :: BED -> BED -> Bool

Ord BED

Methods

compare :: BED -> BED -> Ordering

(<) :: BED -> BED -> Bool

(<=) :: BED -> BED -> Bool

(>) :: BED -> BED -> Bool

(>=) :: BED -> BED -> Bool

max :: BED -> BED -> BED

min :: BED -> BED -> BED

Read BED

Methods

readsPrec :: Int -> ReadS BED

readList :: ReadS [BED]

readPrec :: ReadPrec BED

readListPrec :: ReadPrec [BED]

Show BED

Methods

showsPrec :: Int -> BED -> ShowS

show :: BED -> String

showList :: [BED] -> ShowS

Default BED

Methods

def :: BED

BEDLike BED

Methods

asBed :: ByteString -> Int -> Int -> BED

fromLine :: ByteString -> BED

toLine :: BED -> ByteString

chrom :: BED -> ByteString

chromStart :: BED -> Int

chromEnd :: BED -> Int

bedName :: BED -> Maybe ByteString

bedScore :: BED -> Maybe Double

bedStrand :: BED -> Maybe Bool

convert :: BEDLike b' => b' -> BED

bedSize :: BED -> Int

BED3 format

data BED3

Constructors

BED3 !ByteString !Int !Int

Instances

Eq BED3

Methods

(==) :: BED3 -> BED3 -> Bool

(/=) :: BED3 -> BED3 -> Bool

Ord BED3

Methods

compare :: BED3 -> BED3 -> Ordering

(<) :: BED3 -> BED3 -> Bool

(<=) :: BED3 -> BED3 -> Bool

(>) :: BED3 -> BED3 -> Bool

(>=) :: BED3 -> BED3 -> Bool

max :: BED3 -> BED3 -> BED3

min :: BED3 -> BED3 -> BED3

Read BED3

Methods

readsPrec :: Int -> ReadS BED3

readList :: ReadS [BED3]

readPrec :: ReadPrec BED3

readListPrec :: ReadPrec [BED3]

Show BED3

Methods

showsPrec :: Int -> BED3 -> ShowS

show :: BED3 -> String

showList :: [BED3] -> ShowS

BEDLike BED3

Methods

asBed :: ByteString -> Int -> Int -> BED3

fromLine :: ByteString -> BED3

toLine :: BED3 -> ByteString

chrom :: BED3 -> ByteString

chromStart :: BED3 -> Int

chromEnd :: BED3 -> Int

bedName :: BED3 -> Maybe ByteString

bedScore :: BED3 -> Maybe Double

bedStrand :: BED3 -> Maybe Bool

convert :: BEDLike b' => b' -> BED3

bedSize :: BED3 -> Int

NarrowPeak format

data NarrowPeak

ENCODE narrowPeak format: https://genome.ucsc.edu/FAQ/FAQformat.html#format12

Constructors

NarrowPeak

Fields

• _npChrom :: !ByteString
• _npStart :: !Int
• _npEnd :: !Int
• _npName :: !(Maybe ByteString)
• _npScore :: !Double
• _npStrand :: !(Maybe Bool)
• _npSigal :: !Double
• _npPvalue :: !(Maybe Double)
• _npQvalue :: !(Maybe Double)
• _npPeak :: !(Maybe Int)

Instances

Eq NarrowPeak

Methods

(==) :: NarrowPeak -> NarrowPeak -> Bool

(/=) :: NarrowPeak -> NarrowPeak -> Bool

Read NarrowPeak

Methods

readsPrec :: Int -> ReadS NarrowPeak

readList :: ReadS [NarrowPeak]

readPrec :: ReadPrec NarrowPeak

readListPrec :: ReadPrec [NarrowPeak]

Show NarrowPeak

Methods

showsPrec :: Int -> NarrowPeak -> ShowS

show :: NarrowPeak -> String

showList :: [NarrowPeak] -> ShowS

BEDLike NarrowPeak

Methods

asBed :: ByteString -> Int -> Int -> NarrowPeak

fromLine :: ByteString -> NarrowPeak

toLine :: NarrowPeak -> ByteString

chrom :: NarrowPeak -> ByteString

chromStart :: NarrowPeak -> Int

chromEnd :: NarrowPeak -> Int

bedName :: NarrowPeak -> Maybe ByteString

bedScore :: NarrowPeak -> Maybe Double

bedStrand :: NarrowPeak -> Maybe Bool

convert :: BEDLike b' => b' -> NarrowPeak

bedSize :: NarrowPeak -> Int

type BEDTree a = HashMap ByteString (IntervalMap Int a)

bedToTree :: BEDLike b => (a -> a -> a) -> [(b, a)] -> BEDTree a

sortedBedToTree :: (BEDLike b, Foldable f) => (a -> a -> a) -> Sorted (f (b, a)) -> BEDTree a

Convert a set of sorted bed records to interval tree, with combining function for equal keys.

intersecting :: BEDLike b => BEDTree a -> b -> IntervalMap Int a

isIntersected :: BEDLike b => BEDTree a -> b -> Bool

sizeOverlapped :: (BEDLike b1, BEDLike b2) => b1 -> b2 -> Int

splitBed :: BEDLike b => Int -> b -> [b]

split a bed region into k consecutive subregions, discarding leftovers

splitBedBySize :: BEDLike b => Int -> b -> [b]

split a bed region into consecutive fixed size subregions, discarding leftovers

splitBedBySizeLeft :: BEDLike b => Int -> b -> [b]

split a bed region into consecutive fixed size subregions, including leftovers

splitBedBySizeOverlap

Arguments

:: BEDLike b

=> Int

bin size

-> Int

overlap size

-> b

-> [b]

newtype Sorted b

a type to imply that underlying data structure is sorted

Constructors

Sorted

Fields

• fromSorted :: b

Instances

Eq b => Eq (Sorted b)

Methods

(==) :: Sorted b -> Sorted b -> Bool

(/=) :: Sorted b -> Sorted b -> Bool

Read b => Read (Sorted b)

Methods

readsPrec :: Int -> ReadS (Sorted b)

readList :: ReadS [Sorted b]

readPrec :: ReadPrec (Sorted b)

readListPrec :: ReadPrec [Sorted b]

Show b => Show (Sorted b)

Methods

showsPrec :: Int -> Sorted b -> ShowS

show :: Sorted b -> String

showList :: [Sorted b] -> ShowS

sortBed :: BEDLike b => [b] -> Sorted (Vector b)

sort BED, first by chromosome (alphabetical order), then by chromStart, last by chromEnd

intersectBed :: (BEDLike b1, BEDLike b2, Monad m) => [b2] -> Conduit b1 m b1

return records in A that are overlapped with records in B

intersectBedWith :: (BEDLike b1, BEDLike b2, Monad m) => ([b2] -> a) -> [b2] -> Conduit b1 m (b1, a)

intersectSortedBed :: (BEDLike b1, BEDLike b2, Monad m) => Sorted (Vector b2) -> Conduit b1 m b1

return records in A that are overlapped with records in B

intersectSortedBedWith :: (BEDLike b1, BEDLike b2, Monad m) => ([b2] -> a) -> Sorted (Vector b2) -> Conduit b1 m (b1, a)

isOverlapped :: (BEDLike b1, BEDLike b2) => b1 -> b2 -> Bool

mergeBed :: (BEDLike b, Monad m) => [b] -> Source m b

mergeBedWith :: (BEDLike b, Monad m) => ([b] -> a) -> [b] -> Source m a

mergeSortedBed :: (BEDLike b, Monad m) => Sorted (Vector b) -> Source m b

mergeSortedBedWith :: (BEDLike b, Monad m) => ([b] -> a) -> Sorted (Vector b) -> Source m a

splitOverlapped :: BEDLike b => ([b] -> a) -> [b] -> [(BED3, a)]

Split overlapped regions into non-overlapped regions. The input must be overlapped. This function is usually used with mergeBedWith.

hReadBed :: (BEDLike b, MonadIO m) => Handle -> Source m b

Read records from a bed file handler in a streaming fashion.

hReadBed' :: (BEDLike b, MonadIO m) => Handle -> m [b]

Non-streaming version.

readBed :: (BEDLike b, MonadIO m) => FilePath -> Source m b

Read records from a bed file in a streaming fashion.

readBed' :: (BEDLike b, MonadIO m) => FilePath -> m [b]

Non-streaming version.

hWriteBed :: (BEDLike b, MonadIO m) => Handle -> Sink b m ()

hWriteBed' :: (BEDLike b, MonadIO m) => Handle -> [b] -> m ()

writeBed :: (BEDLike b, MonadIO m) => FilePath -> Sink b m ()

writeBed' :: (BEDLike b, MonadIO m) => FilePath -> [b] -> m ()

Utilities

fetchSeq :: (BioSeq DNA a, MonadIO m) => Genome -> Conduit BED m (Either String (DNA a))

retreive sequences

fetchSeq' :: (BioSeq DNA a, MonadIO m) => Genome -> [BED] -> m [Either String (DNA a)]

motifScan :: (BEDLike b, MonadIO m) => Genome -> [Motif] -> Bkgd -> Double -> Conduit b m BED

Identify motif binding sites

getMotifScore :: MonadIO m => Genome -> [Motif] -> Bkgd -> Conduit BED m BED

Retrieve motif matching scores

getMotifPValue

Arguments

:: Monad m

=> Maybe Double

whether to truncate the motif score CDF. Doing this will significantly reduce memory usage without sacrifice accuracy.

-> [Motif]

-> Bkgd

-> Conduit BED m BED

compareBed :: (BEDLike b1, BEDLike b2) => b1 -> b2 -> Ordering

Compare bed records using only the chromosome, start and end positions. Unlike the `compare' from the Ord type class, this function can compare different types of BED data types.