bioinformatic problem urgent!

[0210828176]

Hi I am new to this forum. I had a query regarding converting DNA code to proteins... which is simple by explanation but I find it hard to get accurate results with code. For ex: In a code like ATGTACTAT (here every 3 non overlapping alphabets get replaced by a single alphabet. For ex: ATG -> M; TAC-> Y; TAT -> Y. I am very new to AWK, I tried making a code below but it doesnt work accurately. can u fix it? thanks in advance



awk 'BEGIN{
c["ATG"]="M"; c["TTT"]="F"; c["TTC"]="F"; c["TTA"]="L"; c["TTG"]="L"; c["CTT"]="L"; c["CTC"]="L"; c["CTA"]="L"; c["CTG"]="L"; c["ATT"]="I"; c["ATC"]="I";
c["ATA"]="I"; c["GTT"]="V"; c["GTC"]="V"; c["GTA"]="V"; c["GTG"]="V"; c["TCT"]="S"; c["TCC"]="S"; c["TCA"]="S"; c["TCG"]="S"; c["CCT"]="P"; c["CCC"]="P";
c["CCA"]="P"; c["CCG"]="P"; c["ACT"]="T"; c["ACC"]="T"; c["ACA"]="T"; c["ACG"]="T"; c["GCT"]="A"; c["GCC"]="A"; c["GCA"]="A"; c["GCG"]="A";c["TAT"]="Y";
c["TAC"]="Y"; c["CAT"]="H"; c["CAC"]="H"; c["CAA"]="Q"; c["CAG"]="Q"; c["AAT"]="N"; c["AAC"]="N"; c["AAA"]="K"; c["AAG"]="K"; c["GAT"]="D"; c["GAC"]="D";
c["GAA"]="E"; c["GAG"]="E"; c["TGT"]="C"; c["TGC"]="C"; c["TGG"]="W"; c["CGT"]=R; c["CGC"]=R; c["CGA"]=R; c["CGG"]=R; c["AGA"]=R; c["AGG"]=R; c["AGT"]="S";
c["AGC"]="S"; c["GGT"]="G"; c["GGC"]="G"; c["GGA"]="G"; c["GGG"]="G";}
{i=1; p=""}
{do {
s=substr($0,i,3)
printf ("%s",s)
{if (c==""){p=p" "} else {p=p c" "}}
i=i+3}
while (s!="")}
{printf("\n%s\n",p)} ' genes_contig0028.txt

 

[feherke]

Hi

I tried making a code below but it doesnt work accurately.

Supposing the input is that "ATGTACTAT" you specified, your code gives the result "M Y Y". As far as I understood, that is exactly what you expect.

If I got it wrong, please post some sample input and the desired output.

Maybe also specify the used Awk implementation and version.

Feherke.

http://feherke.github.com/

 

[mikrom]

Just for curiosity I tried it to code:

[COLOR=#0000ff]#! /bin/awk -f[/color]
[COLOR=#6a5acd]BEGIN[/color]{
  c[[COLOR=#6a5acd]"ATG"[/color]]=[COLOR=#ff00ff]"M"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"TTT"[/color]]=[COLOR=#ff00ff]"F"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"TTC"[/color]]=[COLOR=#ff00ff]"F"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"TTA"[/color]]=[COLOR=#ff00ff]"L"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"TTG"[/color]]=[COLOR=#ff00ff]"L"[/color][COLOR=#6a5acd];[/color] 
  c[[COLOR=#6a5acd]"CTT"[/color]]=[COLOR=#ff00ff]"L"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"CTC"[/color]]=[COLOR=#ff00ff]"L"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"CTA"[/color]]=[COLOR=#ff00ff]"L"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"CTG"[/color]]=[COLOR=#ff00ff]"L"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"ATT"[/color]]=[COLOR=#ff00ff]"I"[/color][COLOR=#6a5acd];[/color] 
  c[[COLOR=#6a5acd]"ATC"[/color]]=[COLOR=#ff00ff]"I"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"ATA"[/color]]=[COLOR=#ff00ff]"I"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"GTT"[/color]]=[COLOR=#ff00ff]"V"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"GTC"[/color]]=[COLOR=#ff00ff]"V"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"GTA"[/color]]=[COLOR=#ff00ff]"V"[/color][COLOR=#6a5acd];[/color] 
  c[[COLOR=#6a5acd]"GTG"[/color]]=[COLOR=#ff00ff]"V"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"TCT"[/color]]=[COLOR=#ff00ff]"S"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"TCC"[/color]]=[COLOR=#ff00ff]"S"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"TCA"[/color]]=[COLOR=#ff00ff]"S"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"TCG"[/color]]=[COLOR=#ff00ff]"S"[/color][COLOR=#6a5acd];[/color] 
  c[[COLOR=#6a5acd]"CCT"[/color]]=[COLOR=#ff00ff]"P"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"CCC"[/color]]=[COLOR=#ff00ff]"P"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"CCA"[/color]]=[COLOR=#ff00ff]"P"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"CCG"[/color]]=[COLOR=#ff00ff]"P"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"ACT"[/color]]=[COLOR=#ff00ff]"T"[/color][COLOR=#6a5acd];[/color] 
  c[[COLOR=#6a5acd]"ACC"[/color]]=[COLOR=#ff00ff]"T"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"ACA"[/color]]=[COLOR=#ff00ff]"T"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"ACG"[/color]]=[COLOR=#ff00ff]"T"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"GCT"[/color]]=[COLOR=#ff00ff]"A"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"GCC"[/color]]=[COLOR=#ff00ff]"A"[/color][COLOR=#6a5acd];[/color] 
  c[[COLOR=#6a5acd]"GCA"[/color]]=[COLOR=#ff00ff]"A"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"GCG"[/color]]=[COLOR=#ff00ff]"A"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"TAT"[/color]]=[COLOR=#ff00ff]"Y"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"TAC"[/color]]=[COLOR=#ff00ff]"Y"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"CAT"[/color]]=[COLOR=#ff00ff]"H"[/color][COLOR=#6a5acd];[/color] 
  c[[COLOR=#6a5acd]"CAC"[/color]]=[COLOR=#ff00ff]"H"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"CAA"[/color]]=[COLOR=#ff00ff]"Q"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"CAG"[/color]]=[COLOR=#ff00ff]"Q"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"AAT"[/color]]=[COLOR=#ff00ff]"N"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"AAC"[/color]]=[COLOR=#ff00ff]"N"[/color][COLOR=#6a5acd];[/color] 
  c[[COLOR=#6a5acd]"AAA"[/color]]=[COLOR=#ff00ff]"K"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"AAG"[/color]]=[COLOR=#ff00ff]"K"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"GAT"[/color]]=[COLOR=#ff00ff]"D"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"GAC"[/color]]=[COLOR=#ff00ff]"D"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"GAA"[/color]]=[COLOR=#ff00ff]"E"[/color][COLOR=#6a5acd];[/color] 
  c[[COLOR=#6a5acd]"GAG"[/color]]=[COLOR=#ff00ff]"E"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"TGT"[/color]]=[COLOR=#ff00ff]"C"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"TGC"[/color]]=[COLOR=#ff00ff]"C"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"TGG"[/color]]=[COLOR=#ff00ff]"W"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"CGT"[/color]]=[COLOR=#ff00ff]"R"[/color][COLOR=#6a5acd];[/color] 
  c[[COLOR=#6a5acd]"CGC"[/color]]=[COLOR=#ff00ff]"R"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"CGA"[/color]]=[COLOR=#ff00ff]"R"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"CGG"[/color]]=[COLOR=#ff00ff]"R"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"AGA"[/color]]=[COLOR=#ff00ff]"R"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"AGG"[/color]]=[COLOR=#ff00ff]"R"[/color][COLOR=#6a5acd];[/color] 
  c[[COLOR=#6a5acd]"AGT"[/color]]=[COLOR=#ff00ff]"S"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"AGC"[/color]]=[COLOR=#ff00ff]"S"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"GGT"[/color]]=[COLOR=#ff00ff]"G"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"GGC"[/color]]=[COLOR=#ff00ff]"G"[/color][COLOR=#6a5acd];[/color] c[[COLOR=#6a5acd]"GGA"[/color]]=[COLOR=#ff00ff]"G"[/color][COLOR=#6a5acd];[/color] 
  c[[COLOR=#6a5acd]"GGG"[/color]]=[COLOR=#ff00ff]"G"[/color][COLOR=#6a5acd];[/color]
}

{ 
  old_line = [COLOR=#6a5acd]$0[/color]
  new_line = [COLOR=#ff00ff]""[/color]
  char3 = [COLOR=#ff00ff]"xxx"[/color]
  i = [COLOR=#ff00ff]1[/color]
  [COLOR=#804040][b]while[/b][/color] (char3) {
    [COLOR=#0000ff]# get 3 chars from line[/color]
    char3 = [COLOR=#008080]substr[/color](old_line[COLOR=#6a5acd],[/color] i[COLOR=#6a5acd],[/color] [COLOR=#ff00ff]3[/color])
    [COLOR=#804040][b]if[/b][/color] (char3) {
      [COLOR=#0000ff]#printf "char3 = '%s'\n", char3[/color]
      [COLOR=#804040][b]if[/b][/color] (char3 in c) {
        new_line = new_line c[[COLOR=#6a5acd]char3[/color]]
        [COLOR=#0000ff]#printf "* new_line = '%s'\n", new_line[/color]
      } 
      [COLOR=#804040][b]else[/b][/color] {
        [COLOR=#804040][b]printf[/b][/color] [COLOR=#ff00ff]"* Error: key '[/color][COLOR=#6a5acd]%s[/color][COLOR=#ff00ff]' not found in array c ![/color][COLOR=#6a5acd]\n[/color][COLOR=#ff00ff]"[/color][COLOR=#6a5acd],[/color] char3 
      }
    }
    [COLOR=#0000ff]# move to the next 3 chars[/color]
    i += [COLOR=#ff00ff]3[/color]  
  }
  [COLOR=#804040][b]printf[/b][/color] [COLOR=#ff00ff]"old: '[/color][COLOR=#6a5acd]%s[/color][COLOR=#ff00ff]' ==> new: '[/color][COLOR=#6a5acd]%s[/color][COLOR=#ff00ff]'[/color][COLOR=#6a5acd]\n[/color][COLOR=#ff00ff]"[/color][COLOR=#6a5acd],[/color] old_line[COLOR=#6a5acd],[/color] new_line  
}

For following example data

ACTCGCTAT
GCGTGGAAA
TACGAGACT

it outputs

old: 'ACTCGCTAT' ==> new: 'TRY'
old: 'GCGTGGAAA' ==> new: 'AWK'
old: 'TACGAGACT' ==> new: 'YET'

 

[PHV]

Replace this:
c["CGT"]=R; c["CGC"]=R; c["CGA"]=R; c["CGG"]=R; c["AGA"]=R; c["AGG"]=R
with this:
c["CGT"]="R"; c["CGC"]="R"; c["CGA"]="R"; c["CGG"]="R"; c["AGA"]="R"; c["AGG"]="R"

Hope This Helps, PH.
FAQ219-2884
FAQ181-2886

 

[PHV]

Anywy, a simpler way for OP's code:

awk 'BEGIN{
c["ATG"]="M"
c["TTT"]=c["TTC"]="F"
c["TTA"]=c["TTG"]=c["CTT"]=c["CTC"]=c["CTA"]=c["CTG"]="L"
c["ATT"]=c["ATC"]=c["ATA"]="I"
c["GTT"]=c["GTC"]=c["GTA"]=c["GTG"]="V"
c["TCT"]=c["TCC"]=c["TCA"]=c["TCG"]=c["AGT"]=c["AGC"]="S"
 c["CCT"]=c["CCC"]=c["CCA"]=c["CCG"]="P"
c["ACT"]=c["ACC"]=c["ACA"]=c["ACG"]="T"
c["GCT"]=c["GCC"]=c["GCA"]=c["GCG"]="A"
c["TAT"]=c["TAC"]="Y"
c["CAT"]=c["CAC"]="H"
c["CAA"]=c["CAG"]="Q"
c["AAT"]=c["AAC"]="N"
c["AAA"]=c["AAG"]="K"
c["GAT"]=c["GAC"]="D"
c["GAA"]=c["GAG"]="E"
c["TGT"]=c["TGC"]="C"
c["TGG"]="W"
c["CGT"]=c["CGC"]=c["CGA"]=c["CGG"]=c["AGA"]=c["AGG"]="R"
c["GGT"]=c["GGC"]=c["GGA"]=c["GGG"]="G"
}
{print;p="";for(i=1;i<=length($0);i+=3)p=p c[substr($0,i,3)]" ";print p}
' genes_contig0028.txt

Hope This Helps, PH.
FAQ219-2884
FAQ181-2886