pseudocode.txt

call init function
call exon_intron_init function




Set $exons_only to what funtion make_spliced returns sending as parameter 'exon'
Set $introns_only to what function make_spliced returns sending as parameter 'intron' 

print message "Exons stats: \n\n"

set $len to the length of @estart

for  $i equals 0 to $i equals $len - 1:
    print "Exon " 
	print "$i + 1"
    print each element of @estart
    call funcition Main sending as parameter $sequence , the current element of @estart, and the subs of the next element - the current element of @estart 
    
print "\nIntron stats:\n\n";

set $len to the length of @istart
for $i equals 0 to $i equals $len - 1 :
    print "Exon "
	print "$i + 1"
    print each element of @istart
    call function Main sending as a parameter $sequence , the current element of @istart, and the subs of the next element - the current element of @istart



Function GenerateHash :

    return a hashmap of all possible nucleotides according to a length it receives as argument


Function Frequency :
    
    Set %hash to the first argument received 
    Set $total to 0
    Set $total to $total + the sum of all elements of %hash
    Generate a tuple with %result and $f
    for each element of %hash :
        if the current element exists:
            Set $f to the current element divided by $total
            Set the current element of $result to $f
            print the current element, $f times 100 
        
    
    return %result


Function CountKmers :
    
    Set $seq and $kmerSize to the arguments received
    Create an empty hash %kmers
    for $i equals 0 to $i equals length of $seq:
        Create one element for $kmers whose key is a substring of $seq, from position $i and lenghth of $KmerSize, and its value is a counter
    
    return %kmers;
}

Function Main :
    
    Set $seq to the first element of the fist argument;
    
    Set %single to the value returned by function GenerateHash with a parameter 1
    my %double = GenerateHash(2);
    
    for $index equals 0 to $index equals length of $seq - 1:
        Add an element to $single whose key is a a substring of $seq from position $index and length 1  and its value is a counter
        Add an element to $double whose key is a a substring of $seq from position $index and length 2  and its value is a counter
    
    Add an element to $single whose key is a substring of $seq with length: length of $seq - 1

    
    print "**** Frequencies of single nucleotide:";
    Set %singleF to the value returned by function Frequency with a parameter %single
    print "**** Frequencies of dinucleotide:";
    Set %doubleF to the value returned by function Frequency with a parameter %double

  
    print "**** Dinucleotide odds ratio:";
    for each element of %double:
        if the current element exists:
            print %doubleF current element , %singleF element with current element substring of length 1 in position 1 divided by %singleF element with current element substring of length 1 in position 2
    

    # Task 4. Core promoter motifs detection
    print "**** Detecting core promoter motifs:";
    if (/TATA[AT]AA[GA]/ is in $seq) {print "TATA Box is detected on sense strand"}
    elsif (/[CT]TT[AT]TATA/ is in $seq) {print "TATA Box is detected on antisense strand"}
    if (/TCA[GT]T[CT]/ is in $seq) {print "Inr (Drosophila) is detected on sense strand"}
    elsif (/[GA]A[AC]TGA/ is in $seq) {print "Inr (Drosophila) is detected on antisense strand"}
    if (/[CT][CT]A[ACGT][AT][CT][CT]/ is in $seq) {print "Inr (Human) is detected on sense strand"}
    elsif (/[GA][GA][AT][ACGT]T[GA][GA]/ is in $seq) {print "Inr (Human) is detected on antisense strand"}
    if (/C[GC]A[GA]C[GC][GC]AAC/ is in $seq) {print "MTE (Drosophila) is detected on sense strand"}
    elsif (/GTT[GC][GC]G[CT]T[GC]G/ is in $seq) {print "MTE (Drosophila) is detected on antisense strand"}
    if (/[GA]G[AT][CT][^T]T/ is in $seq) {print "DPE (Drosophila) is detected on sense strand"}
    elsif (/A[^A][GA][AT]C[CT]/ is in $seq) {print "DPE (Drosophila) is detected on antisense strand"}
    if ( /[GC][GC][GA]CGCC/ is in $seq) {print "BRE^u is detected on sense strand"}
    elsif (/GGCG[CT][GC][GC]/ is in $seq) {print "BRE^u is detected on antisense strand"}
    if (/[GA]T[^C][GT][GT][GT][GT]/ is in $seq) {print "BRE^d is detected on sense strand"}
    elsif (/[AC][AC][AC][AC][^G]A[CT]/ is in $seq) {print "BRE^d is detected on antisense strand"}
    if (/[^C][GC]G[CT]GG[GA]A[GC][AC]/ is in $seq) {print "XCPE1 (Human) is detected on sense strand"}
    elsif (/[GT][GC]T[CT]CC[GA]C[GC][^G]/ is in $seq) {print "XCPE1 (Human) is detected on antisense strand"}
    if (/CTTC.{1,11}CTGT.{5,14}AGC/ is in $seq) {print "DCE is detected on sense strand"}
    elsif (/GCT.{5,14}ACAG.{1,11}GAAG/ is in $seq) {print "DCE is detected on antisense strand"}

    # Task 5. CTCF binding motif detection
    print "**** Detecting CTCF binding motif:"
    if (/CCGCG.GG.GGCAG/ is in $seq) {print "CTCF binding motif is detected on sense strand"}
    elsif (/CTGCC.CC.CGCGG/ is in $seq) {print "CTCF binding motif is detected on antisense strand"}
    else { print "No CTCF binding motif detected in this region" }

    # Task 6. Count 5-mer
    print "**** Counting 5-mers. Result not shown (too many entries...)"
    set %fiveMer to the value returned by function CountKmers with parameters $seq and 5
    Set $totalCount to the size of %fiveMer
    print "Unique fiveMer count: $totalCount";

return 1;


Function freq(2):
  my $relative_freq
  

return $relative_freq


Function make_spliced(1):
  my $spliced;
  if first argument equals 'exon':
    for each element of @exons:   
      set $spliced to concatenate $spliced with $exon
    
  elsif first argument equals 'intron':
    foreach element in @introns
      Set $spliced to concatenate $spliced with $intron

  else :
    print "Subroutine make_spliced passed bad input. \"exon\" for exonstring,";
    print " \"intron\" for intron string. You passed: ";
    print first argument;
  
return $spliced;
}

Function sub exon_intron_init:
  @exons;
  @introns;

  for $c equals 0 to $c equals size of @estart:
    Set $temp to substring of $sequence starting at @estart[$c] with length @istart[$c]-@estart[$c]
    Insert $temp into @exons
  

  for $c equals 0 to $c equals size of @istart:
    Set $temp to substring of $sequence starting at @istart[$c] with length @estart[$c]-@istart[$c]
    Insert $temp into @introns
  
  

sub file_test{
  print "Sequence size:";
  print length($sequence); print " Printing sequence: $sequence";
  print "\n\n\n";
  print $promoter;
  print "\n\n\n";
  print "exon start: @estart \n";
  print "intron start: @istart \n";
}

sub init{ 
  set $seqnam to 'sequence.txt'
  set $pronam to 'promoter.txt'
  set $indexnam to 'index.txt'

  open($seqin, '<', $seqnam);
    Set $sequence to file data;
  close $seqin;

  open($promin, '<', $pronam);
    set $promoter to file data;
  close $promin;

  @estart;
  @istart;
  set $indexnam to 'index.txt'
  open($indexin, '<', $indexnam);


    set $prom_len to file data 
    Removes new line character from $prom_len


    set $prime to file data  
    Removes new line character from $prime)
    for $c equeals 0 to $prime not equals -1776:
      set @estart[$c] to $prime
      set prime to file data
      Removes new line character from $prime
    

    set $prime to file data   
    Removes new line character from $prime
    for $c equals 0 to $prime not equals -1776:  
      set @istart[$c] to $prime
      set $prime to file data
      Removes new line character from $prime
    
  close $indexin;

  print "@estart";


return 1;