DNANucleotide.hs

module Bioinformatics.DNANucleotide (
  DNANucleotide (..),
  charToDNANucleotide,
  nucleotideComplement,
  calculateGCContent
) where

import Data.Char
import Data.List

data DNANucleotide = A | C | G | T deriving(Show, Eq, Ord, Read)

charToDNANucleotide :: Char -> DNANucleotide
charToDNANucleotide c = read [toUpper c] :: DNANucleotide

nucleotideComplement :: DNANucleotide -> DNANucleotide
nucleotideComplement A = T
nucleotideComplement T = A
nucleotideComplement C = G
nucleotideComplement G = C

calculateGCContent :: [DNANucleotide] -> Double
calculateGCContent ns =
  let gcs = filter (\n -> n == G || n == C) ns
  in (fromIntegral $ length gcs) / (fromIntegral $ length ns)

gc.hs

import qualified Bioinformatics.DNANucleotide as D
import qualified Data.List.Split as S

getLines contents = do
  line <- getLine
  if null line
    then return contents
    else getLines $ contents ++ line ++ "\n"

type FASTAFormatLine = (String, [D.DNANucleotide])

fastaStringToFASTAFormat :: String -> FASTAFormatLine
fastaStringToFASTAFormat [] = ("", [])
fastaStringToFASTAFormat xs =
  let comps = lines xs
  in (head comps, map D.charToDNANucleotide . concat $ tail comps)

buildFASTALines :: String -> [FASTAFormatLine]
buildFASTALines = map fastaStringToFASTAFormat . S.splitOn ">"

determineGCContent :: [FASTAFormatLine] -> [(String, Double)]
determineGCContent = map (\(n, ns) -> (n, D.calculateGCContent ns))

main = do
  theLines <- getLines ""
  let greatestGC = foldl (\(an, agc) (n, gc) -> if gc > agc then (n, gc) else (an, agc)) ("", 0) . determineGCContent $ buildFASTALines theLines
  putStrLn $ fst greatestGC
  putStrLn . show $ 100.0 * (snd greatestGC)