/// <summary>
/// Peptide Encoding Problem: Find substrings of a genome encoding a given amino acid sequence.
/// </summary>
/// <param name="DNA">A DNA string</param>
/// <param name="Peptide">An amino acid string</param>
/// <returns>All substrings of Text encoding Peptide (if any such substrings exist).</returns>
public static string PeptideEncoding(string DNA, string Peptide)
{
List<string>[] encodes = new List<string>[Peptide.Length];
Protein p = new Protein();
for (int i = 0; i < Peptide.Length; i++) {
encodes[i] = p.GetPeptideEncodes(Peptide[i].ToString());
}
string cur_adv, cur_rev;
List<int> adv_match, rev_match;
Dictionary<int, string> matches = new Dictionary<int, string>();
RNAConstructorState cur_pos = new RNAConstructorState(0, "", true, true);
Stack<RNAConstructorState> stack = new Stack<RNAConstructorState>();
stack.Push(cur_pos);
FileStream fs1 = File.OpenWrite(@".\PA2_2_debug.txt");
TextWriter wr = new StreamWriter(fs1);
foreach (List<string> e in encodes) {
foreach(string s in e)
wr.Write(s + " ");
wr.WriteLine();
}
do {
if (cur_pos.Position < encodes[stack.Count - 1].Count) { // position in the range -> check substring
cur_adv = stack.Peek().AdvRNA + Protein.UntranscribeRNA(encodes[stack.Count - 1][cur_pos.Position]);
//adv_match = cur_pos.IsAdvMatch ? BioInf_PA1.FindPatternPositions(cur_adv, DNA) : null;
adv_match = BioInf_PA1.FindPatternPositions(cur_adv, DNA); //todo Fix the check (is previous IsAdvMatch spoiled?)
cur_rev = BioInf_PA1.ReverseComplement(cur_adv);
//rev_match = cur_pos.IsRevMatch ? BioInf_PA1.FindPatternPositions(cur_rev, DNA) : null;
rev_match = BioInf_PA1.FindPatternPositions(cur_rev, DNA);
wr.WriteLine("Adv[{1}.{0}]: {2} - {3}", stack.Count, cur_pos.Position, cur_adv, adv_match != null ? adv_match.Count : 0);
wr.WriteLine("Rev[{1}.{0}]: {2} - {3}", stack.Count, cur_pos.Position, cur_rev, rev_match != null ? rev_match.Count : 0);
if (adv_match != null || rev_match != null) {
// There are some matches
if (stack.Count < encodes.Length) {
// Not last level -> Go to next level (INTO)
cur_pos.AdvRNA = cur_adv;
cur_pos.IsAdvMatch = adv_match != null;
cur_pos.IsRevMatch = rev_match != null;
stack.Push(cur_pos);
cur_pos.Position = 0;
}
else { // Last level -> Add the match and go to next substring (ADD + NEXT)
if (adv_match != null)
foreach(int pos in adv_match)
matches.Add(pos, cur_adv); // Full string was matched
if (rev_match != null)
foreach(int pos in rev_match)
matches.Add(pos, cur_rev);
cur_pos.Position++;
}
}
else { // Go to next substring on the current level (NEXT)
cur_pos.Position++;
}
}
else { // x out of the range for current level
if (stack.Count > 1) {
// Not the first level -> Go to previous level (OUT)
cur_pos = stack.Pop();
cur_pos.Position++;
}
else { // Last substring of last level -> EXIT
break;
}
}
} while (true);
string str = "";
foreach (KeyValuePair<int, string> kv in matches) {
//str = str + kv.Value + " " + kv.Key + "\n";
str = str + kv.Value + " ";
}
return str.TrimEnd(' ');
}
/// <summary>
/// Peptide Encoding Problem: Find substrings of a genome encoding a given amino acid sequence.
/// </summary>
/// <param name="DNA">A DNA string</param>
/// <param name="Peptide">An amino acid string</param>
/// <returns>All substrings of Text encoding Peptide (if any such substrings exist).</returns>
public static string PeptideEncoding(string DNA, string Peptide)
{
List <string>[] encodes = new List <string> [Peptide.Length];
Protein p = new Protein();
for (int i = 0; i < Peptide.Length; i++)
{
encodes[i] = p.GetPeptideEncodes(Peptide[i].ToString());
}
string cur_adv, cur_rev;
List <int> adv_match, rev_match;
Dictionary <int, string> matches = new Dictionary <int, string>();
RNAConstructorState cur_pos = new RNAConstructorState(0, "", true, true);
Stack <RNAConstructorState> stack = new Stack <RNAConstructorState>();
stack.Push(cur_pos);
FileStream fs1 = File.OpenWrite(@".\PA2_2_debug.txt");
TextWriter wr = new StreamWriter(fs1);
foreach (List <string> e in encodes)
{
foreach (string s in e)
{
wr.Write(s + " ");
}
wr.WriteLine();
}
do
{
if (cur_pos.Position < encodes[stack.Count - 1].Count) // position in the range -> check substring
{
cur_adv = stack.Peek().AdvRNA + Protein.UntranscribeRNA(encodes[stack.Count - 1][cur_pos.Position]);
//adv_match = cur_pos.IsAdvMatch ? BioInf_PA1.FindPatternPositions(cur_adv, DNA) : null;
adv_match = BioInf_PA1.FindPatternPositions(cur_adv, DNA); //todo Fix the check (is previous IsAdvMatch spoiled?)
cur_rev = BioInf_PA1.ReverseComplement(cur_adv);
//rev_match = cur_pos.IsRevMatch ? BioInf_PA1.FindPatternPositions(cur_rev, DNA) : null;
rev_match = BioInf_PA1.FindPatternPositions(cur_rev, DNA);
wr.WriteLine("Adv[{1}.{0}]: {2} - {3}", stack.Count, cur_pos.Position, cur_adv, adv_match != null ? adv_match.Count : 0);
wr.WriteLine("Rev[{1}.{0}]: {2} - {3}", stack.Count, cur_pos.Position, cur_rev, rev_match != null ? rev_match.Count : 0);
if (adv_match != null || rev_match != null)
{
// There are some matches
if (stack.Count < encodes.Length)
{
// Not last level -> Go to next level (INTO)
cur_pos.AdvRNA = cur_adv;
cur_pos.IsAdvMatch = adv_match != null;
cur_pos.IsRevMatch = rev_match != null;
stack.Push(cur_pos);
cur_pos.Position = 0;
}
else // Last level -> Add the match and go to next substring (ADD + NEXT)
{
if (adv_match != null)
{
foreach (int pos in adv_match)
{
matches.Add(pos, cur_adv); // Full string was matched
}
}
if (rev_match != null)
{
foreach (int pos in rev_match)
{
matches.Add(pos, cur_rev);
}
}
cur_pos.Position++;
}
}
else // Go to next substring on the current level (NEXT)
{
cur_pos.Position++;
}
}
else // x out of the range for current level
{
if (stack.Count > 1)
{
// Not the first level -> Go to previous level (OUT)
cur_pos = stack.Pop();
cur_pos.Position++;
}
else // Last substring of last level -> EXIT
{
break;
}
}
} while (true);
string str = "";
foreach (KeyValuePair <int, string> kv in matches)
{
//str = str + kv.Value + " " + kv.Key + "\n";
str = str + kv.Value + " ";
}
return(str.TrimEnd(' '));
}