k-nucleotide F# .NET program

(* The Computer Language Benchmarks Game
 * https://salsa.debian.org/benchmarksgame-team/benchmarksgame/
 *
 * contributed by Jimmy Tang
 *)
 
open System
open System.IO
open System.Collections.Generic

// make our hashtable using System.Collections.Generic.Dictionary
let maketable (dna:string) (length:int) =
   let d = new Dictionary<_,_>()
   for start in 0..(dna.Length - length) do
      let substr = dna.Substring(start, length)
      let x = ref (ref 0)
      if d.TryGetValue(substr, x) then x.Value := ! !x + 1
      else d.[substr] <- ref 1
   d

// frequency for all substrings of a given length
let frequencies (dna:string) (length:int) = [
   let d = maketable dna length
   let total = d.Values |> Seq.map (!) |> Seq.sum
   yield! [ for pair in d ->
             pair.Key.ToUpper(), (float(pair.Value.Value) * 100.0 /float(total))]
         |> List.sortBy (snd >> (~-))
         |> List.map (fun (s,c) -> sprintf "%s %.3f" s c)
   yield ""
]

// frequency of occurrence for a particular substring
let countSubstring dna (substring:string) = [
   let d = maketable dna (substring.Length)
   yield (sprintf "%d\t%s"
      (if d.ContainsKey(substring) then !d.[substring] else 0)
      (substring.ToUpper()))
]

let input = Console.In
let dna = seq { while true do yield input.ReadLine() }
        |> Seq.takeWhile (fun x -> x <> null)
        |> Seq.skipWhile (fun x -> not(x.StartsWith(">THREE")))
        |> Seq.skip 1
        |> String.concat ""

[for len in [1;2] -> async { return frequencies dna len }] @
[for str in ["ggt";"ggta";"ggtatt";"ggtattttaatt";"ggtattttaatttatagt"]
 -> async { return countSubstring dna str }]
|> List.rev
|> Async.Parallel
|> Async.RunSynchronously
|> Array.rev
|> Seq.concat
|> Seq.iter (printfn "%s")
    

NOTES:
64-bit Ubuntu quad core
.NET SDK 9.0.100
Host Version: 9.0.0
Commit: 9d5a6a9aa4

<OutputType>Exe
<TargetFramework>net9.0
<ImplicitUsings>enable
<Nullable>enable
<AllowUnsafeBlocks>true
<ServerGarbageCollection>true
<ConcurrentGarbageCollection>true
<PublishAot>false


 Fri, 15 Nov 2024 02:01:14 GMT

MAKE:
cp knucleotide.fsharpcore Program.fs
cp Include/fsharpcore/program.fsproj .
mkdir obj
cp Include/fsharpcore/project.assets.json ./obj
/opt/src/dotnet-sdk-9.0.100/dotnet build -c Release --use-current-runtime  	
  Determining projects to restore...
  Restored /home/dunham/all-benchmarksgame/benchmarksgame_i53330/knucleotide/tmp/program.fsproj (in 759 ms).
/home/dunham/all-benchmarksgame/benchmarksgame_i53330/knucleotide/tmp/Program.fs(43,40): warning FS3261: Nullness warning: The types 'string' and 'string | null' do not have compatible nullability. [/home/dunham/all-benchmarksgame/benchmarksgame_i53330/knucleotide/tmp/program.fsproj]
/home/dunham/all-benchmarksgame/benchmarksgame_i53330/knucleotide/tmp/Program.fs(45,12): warning FS3261: Nullness warning: The types 'string' and 'string | null' do not have equivalent nullability. [/home/dunham/all-benchmarksgame/benchmarksgame_i53330/knucleotide/tmp/program.fsproj]
  program -> /home/dunham/all-benchmarksgame/benchmarksgame_i53330/knucleotide/tmp/bin/Release/net9.0/linux-x64/program.dll

Build succeeded.

/home/dunham/all-benchmarksgame/benchmarksgame_i53330/knucleotide/tmp/Program.fs(43,40): warning FS3261: Nullness warning: The types 'string' and 'string | null' do not have compatible nullability. [/home/dunham/all-benchmarksgame/benchmarksgame_i53330/knucleotide/tmp/program.fsproj]
/home/dunham/all-benchmarksgame/benchmarksgame_i53330/knucleotide/tmp/Program.fs(45,12): warning FS3261: Nullness warning: The types 'string' and 'string | null' do not have equivalent nullability. [/home/dunham/all-benchmarksgame/benchmarksgame_i53330/knucleotide/tmp/program.fsproj]
    2 Warning(s)
    0 Error(s)

Time Elapsed 00:00:10.21

12.32s to complete and log all make actions

COMMAND LINE:
 ./bin/Release/net9.0/linux-x64/program 0 < knucleotide-input25000000.txt

PROGRAM OUTPUT:
A 30.295
T 30.151
C 19.800
G 19.754

AA 9.177
TA 9.132
AT 9.131
TT 9.091
CA 6.002
AC 6.001
AG 5.987
GA 5.984
CT 5.971
TC 5.971
GT 5.957
TG 5.956
CC 3.917
GC 3.911
CG 3.909
GG 3.902

1471758	GGT
446535	GGTA
47336	GGTATT
893	GGTATTTTAATT
893	GGTATTTTAATTTATAGT