Bioinformatics/Subsequence: Difference between revisions

</pre>

=={{header|Phix}}==

Note: match_all() is due to become a builtin in the next release, so the version below may or may not need renaming/deleting before it will run.

<lang Phix>constant cheat = false

function grandna(integer len)

string dna = repeat(' ',len)

for i=1 to len do dna[i] = "ACGT"[rand(4)] end for

return dna

end function

procedure show(string dna, sequence idx)

idx &= length(dna)+100 -- (add an otherwise unused sentinel)

sequence s = split(trim(join_by(split(join_by(dna,1,10,""),"\n"),1,5," ")),"\n")

integer ii = 1, -- idx index

i = idx[ii], -- current target

ux = 1, -- underline index (1..4)

ldx = 1 -- line index (1, 51, 101, etc)

for si=1 to length(s) do

printf(1,"%3d: %s\n",{ldx,s[si]})

ldx += 50

if i and i<ldx then

string ul = repeat(' ',59)

while i and i<ldx do

integer up = i-ldx+51 -- underline pos (relative to ldx)

up += floor((up-1)/10)+5 -- (plus any needed spacing)

ul[up] = "<==>"[ux]

ux += 1

i += 1

if ux>4 then

ux = 1

ii += 1

i = idx[ii]

end if

end while

printf(1,"%s\n",ul)

end if

end for

if length(idx) then

string s = iff(length(idx)>1?"s":""),

t = join(apply(idx,sprint),", ")

printf(1,"%s occurs at location%s: %s\n",{test,s,t})

else

printf(1,"%s does not occur\n",{test})

end if

end procedure

function match_all(object needle, sequence haystack)

integer start = 1

sequence res = {}

while 1 do

start = match(needle,haystack,start)

if start=0 then exit end if

res = append(res,start)

start += length(needle)

end while

return res

end function

string dna = grandna(200),

test = grandna(4)

constant cheats = iff(cheat?{9,13,49,60,64,68}:{})

for i=1 to length(cheats) do

dna[cheats[i]..cheats[i]+3] = test

end for

sequence idx = match_all(test,dna)

show(dna,idx)</lang>

{{out}}

with cheat enabled

<pre>

1: GGAGATATCG ACCGACCGAA GTAAAGTCAA AGTCGTCCAA TCCACGGACG

<= =><==> <=

51: ACTTCAGCAC GACCGACCGA CCTATTTAAG AGACCACACT TAAGGAATCC

=> < ==><==><== >

101: ATGCGAAATA AAAATGGGCG AGTAGCCGTG GGGCGCTAAA GCACCCACCT

151: AGTTTTCGCC GAAGTACTAG ACCACCTTCG GATCGACAAA GCTTTCACCA

<==>

CGAC occurs at locations: 9, 13, 49, 60, 64, 68, 184

</pre>

with cheat disabled

<pre>

1: TGATTTAAAC CGTGGTGCAA TTTATAAACA CTGCGATATG CCTCCTGATG

51: GCATGGTATT CGACACCAAG ACGCTGGTGG GCACACTGGC TTTCAGAATA

101: GGAGTCACAA TCCCTCTATG ATGTCCTCTA GCGGGTGTGT GTTCAGTGCC

151: AGCGCTTACT TCCGGCGTGG CCGACTCTTT TTAAAGCGTA TAGCTGGGGT

GCTA does not occur