BioinformnaticsFrequentWords

BioinformnaticsFrequentWords.fsx

let frequentWords (text:string) (k:int) =
    let patternCounts =
        text
        |> Seq.windowed k
        |> Seq.map(fun c -> new string(c))
        |> Seq.countBy(fun s -> s)
        |> Seq.sortByDescending(fun (s,c) -> c)
    let maxCount = patternCounts |> Seq.head |> snd
    patternCounts 
        |> Seq.filter(fun (s,c) -> c = maxCount)
        |> Seq.map(fun (s,c) -> s)

let getRandomNuclotide () =
    let dictionary = ["A";"C";"G";"T"]
    let random = new Random()
    dictionary.[random.Next(4)]

let getRandomSequence (length:int) =
    let nuclotides = [ for i in 0 .. length -> getRandomNuclotide() ]
    String.Join("", nuclotides)

let largerText = getRandomSequence 1000000

let currentFrequentWords = frequentWords largerText 9
currentFrequentWords