Bio.Motif

Documentation

data PWM

k x 4 position weight matrix for motifs

Constructors

PWM

Fields

• _nSites :: !(Maybe Int)

  number of sites used to generate this matrix

• _mat :: !(Matrix Double)

Instances

Read PWM

Defined in Bio.Motif

Methods

readsPrec :: Int -> ReadS PWM

readList :: ReadS [PWM]

readPrec :: ReadPrec PWM

readListPrec :: ReadPrec [PWM]

Show PWM

Defined in Bio.Motif

Methods

showsPrec :: Int -> PWM -> ShowS

show :: PWM -> String

showList :: [PWM] -> ShowS

size :: PWM -> Int

subPWM :: Int -> Int -> PWM -> PWM

Extract sub-PWM given starting position and length, zero indexed.

rcPWM :: PWM -> PWM

Reverse complementary of PWM.

gcContentPWM :: PWM -> Double

GC content of PWM.

data Motif

Constructors

Motif

Fields

• _name :: !ByteString
• _pwm :: !PWM

Instances

Read Motif

Defined in Bio.Motif

Methods

readsPrec :: Int -> ReadS Motif

readList :: ReadS [Motif]

readPrec :: ReadPrec Motif

readListPrec :: ReadPrec [Motif]

Show Motif

Defined in Bio.Motif

Methods

showsPrec :: Int -> Motif -> ShowS

show :: Motif -> String

showList :: [Motif] -> ShowS

FastaLike Motif

Defined in Bio.Data.Fasta

Methods

fromFastaRecord :: (ByteString, [ByteString]) -> Motif

readFasta :: FilePath -> ConduitT i Motif (ResourceT IO) ()

readFasta' :: FilePath -> IO [Motif]

newtype Bkgd

background model which consists of single nucletide frequencies, and di-nucletide frequencies.

Constructors

BG (Double, Double, Double, Double)

Instances

Default Bkgd

Defined in Bio.Motif

Methods

def :: Bkgd

toPWM :: [ByteString] -> PWM

Get pwm from a matrix.

ic :: PWM -> Int -> Double

Information content of a poistion in pwm. (Not implemented)

scores :: Bkgd -> PWM -> DNA a -> [Double]

Get scores of a long sequences at each position.

scores' :: Monad m => Bkgd -> PWM -> DNA a -> ConduitT i Double m ()

A streaming version of scores.

score :: Bkgd -> PWM -> DNA a -> Double

optimalScore :: Bkgd -> PWM -> Double

The best possible matching score of a pwm.

newtype CDF

The cumulative distribution function in the form of (x, P(X <= x)).

Constructors

CDF (Vector (Double, Double))

Instances

Read CDF

Defined in Bio.Motif

Methods

readsPrec :: Int -> ReadS CDF

readList :: ReadS [CDF]

readPrec :: ReadPrec CDF

readListPrec :: ReadPrec [CDF]

Show CDF

Defined in Bio.Motif

Methods

showsPrec :: Int -> CDF -> ShowS

show :: CDF -> String

showList :: [CDF] -> ShowS

cdf :: CDF -> Double -> Double

cdf' :: CDF -> Double -> Double

The inverse of cdf.

truncateCDF :: Double -> CDF -> CDF

Truncate the CDF by a value, in order to reduce the memory usage.

scoreCDF :: Bkgd -> PWM -> CDF

Approximate the cdf of motif matching scores using dynamic programming. Algorithm: Scan the PWM from left to right. For each position $i$, compute a score density function $s_i$ such that $s_i(x)$ is the total number of sequences with score $x$.

pValueToScore :: Double -> Bkgd -> PWM -> Double

calculate the minimum motif mathching score that would produce a kmer with p-Value less than the given number. This score would then be used to search for motif occurrences with significant p-Value

pValueToScoreExact

Arguments

:: Double

desirable p-Value

-> Bkgd

-> PWM

-> Double

Unlike pValueToScore, this version compute the exact score but much slower and is inpractical for long motifs.

toIUPAC :: PWM -> DNA IUPAC

Convert pwm to consensus sequence, see D. R. Cavener (1987).

readMEME :: FilePath -> IO [Motif]

toMEME :: [Motif] -> Bkgd -> ByteString

fromMEME :: ByteString -> [Motif]

writeMEME :: FilePath -> [Motif] -> Bkgd -> IO ()

writeFasta :: FilePath -> [Motif] -> IO ()

References

• Douglas R. Cavener. (1987) Comparison of the consensus sequence flanking translational start sites in Drosophila and vertebrates. Nucleic Acids Research 15 (4): 1353–1361. http://nar.oxfordjournals.org/content/15/4/1353