The Q6600
Benchmarks Game

k-nucleotide Lua #2 program

source code

-- The Computer Language Benchmarks Game
-- https://salsa.debian.org/benchmarksgame-team/benchmarksgame/
-- contributed by Mike Pall

local function kfrequency(seq, freq, k, frame)
  local sub = string.sub
  local k1 = k - 1
  for i=frame,string.len(seq)-k1,k do
    local c = sub(seq, i, i+k1)
    freq[c] = freq[c] + 1
  end
end

local function freqdefault()
  return 0
end

local function count(seq, frag)
  local k = string.len(frag)
  local freq = setmetatable({}, { __index = freqdefault })
  for frame=1,k do kfrequency(seq, freq, k, frame) end
  io.write(freq[frag] or 0, "\t", frag, "\n")
end

local function frequency(seq, k)
  local freq = setmetatable({}, { __index = freqdefault })
  for frame=1,k do kfrequency(seq, freq, k, frame) end
  local sfreq, sn = {}, 1
  for c,v in pairs(freq) do sfreq[sn] = c; sn = sn + 1 end
  table.sort(sfreq, function(a, b)
    local fa, fb = freq[a], freq[b]
    return fa == fb and a > b or fa > fb
  end)
  sum = string.len(seq)-k+1
  for _,c in ipairs(sfreq) do
    io.write(string.format("%s %0.3f\n", c, (freq[c]*100)/sum))
  end
  io.write("\n")
end

local function readseq()
  local sub = string.sub
  for line in io.lines() do
    if sub(line, 1, 1) == ">" and sub(line, 2, 6) == "THREE" then break end
  end
  local lines, ln = {}, 0
  for line in io.lines() do
    local c = sub(line, 1, 1)
    if c == ">" then
      break
    elseif c ~= ";" then
      ln = ln + 1
      lines[ln] = line
    end
  end
  return string.upper(table.concat(lines, "", 1, ln))
end

local seq = readseq()
frequency(seq, 1)
frequency(seq, 2)
count(seq, "GGT")
count(seq, "GGTA")
count(seq, "GGTATT")
count(seq, "GGTATTTTAATT")
count(seq, "GGTATTTTAATTTATAGT")
    

notes, command-line, and program output

NOTES:
64-bit Ubuntu quad core
Lua 5.4.0  Copyright (C) 1994-2020 Lua.org, PUC-Rio


Tue, 30 Jun 2020 23:14:42 GMT

COMMAND LINE:
/opt/src/lua-5.4.0/bin/lua  knucleotide.lua-2.lua 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