private string MutateSequence(string argSequence, enumPeptideMutation argMutation)
{
if (argMutation == enumPeptideMutation.NoMutation)
{
return(argSequence);
}
else if (argMutation == enumPeptideMutation.DtoN)
{
StringBuilder sb = new StringBuilder(argSequence);
foreach (
Match match in Regex.Matches(argSequence, "D[ARNDCEQGHILKMFSTWYV][S|T]", RegexOptions.IgnoreCase))
//DXS DXT X!=P
{
sb.Remove(match.Index, 1);
sb.Insert(match.Index, "N");
}
return(sb.ToString());
}
else //(argMutation == enumPeptideMutation.AnyToN)
{
StringBuilder sb = new StringBuilder(argSequence);
foreach (
Match match in Regex.Matches(argSequence, "[ARNDCEQGHILKMFSTWYV][S|T]", RegexOptions.IgnoreCase))
//XS XT X!=P
{
if (match.Index == 0)
{
continue;
}
sb.Remove(match.Index - 1, 1);
sb.Insert(match.Index - 1, "N");
}
return(sb.ToString());
}
}
public List<string> CreateCleavedNGlycoPeptides(int argAllowMissCleavage, List<Protease.Type> argProteaseType, enumPeptideMutation argMutation)
{
_misscleavaged = argAllowMissCleavage;
List<string> glycopeptides = new List<string>();
foreach (ProteinInfo prot in _proteinInfo)
{
glycopeptides.AddRange(prot.NGlycopeptide(_misscleavaged, argProteaseType, argMutation));
}
return glycopeptides;
}
private void btnReadFasta_Click(object sender, EventArgs e)
{
if (openFileDialog1.ShowDialog() == DialogResult.OK)
{
List<Protease.Type> ProteaseType = new List<Protease.Type>();
if (chkEnzy_Trypsin.Checked)//Trypsin
{
ProteaseType.Add(Protease.Type.Trypsin);
}
if (chkEnzy_GlucE.Checked)//GlucE
{
ProteaseType.Add(Protease.Type.GlucE);
}
if (chkEnzy_GlucED.Checked) //GlucED
{
ProteaseType.Add(Protease.Type.GlucED);
}
if (chkEnzy_None.Checked || ProteaseType.Count == 0)
{
ProteaseType.Add(Protease.Type.None);
}
enumPeptideMutation pepMuta = enumPeptideMutation.NoMutation;
if (cboPepMutation.SelectedIndex == 1)
{
pepMuta = enumPeptideMutation.DtoN;
}
else if (cboPepMutation.SelectedIndex == 2)
{
pepMuta = enumPeptideMutation.AnyToN;
}
string fastaFile = openFileDialog1.FileName;
FastaFile file = new FastaFile(fastaFile);
List<string> Peptides = file.CreateCleavedPeptides(Convert.ToInt32(txtMissCleavage.Text), ProteaseType);
txtPeptides.Text = "Digested Peptides" + Environment.NewLine + Environment.NewLine;
foreach (string p in Peptides)
{
txtPeptides.Text += p + Environment.NewLine;
}
txtPeptides.Text += Environment.NewLine + Environment.NewLine + Environment.NewLine + Environment.NewLine;
txtPeptides.Text += "N-linked Peptides" + Environment.NewLine + Environment.NewLine;
List<string> lstPeptides = file.CreateCleavedNGlycoPeptides(Convert.ToInt32(txtMissCleavage.Text), ProteaseType, pepMuta);
foreach (string p in lstPeptides)
{
txtPeptides.Text += p + Environment.NewLine;
}
}
}
/// <summary>
/// Old function, no use anymore
/// </summary>
/// <param name="argSequence"></param>
/// <param name="argMutation"></param>
/// <param name="lstGlycopeptideSeq"></param>
/// <returns></returns>
public bool IsGlycopeptide(string argSequence, enumPeptideMutation argMutation, out List <string> lstGlycopeptideSeq)
{
List <string> _glycopep = new List <string>();
Regex sequon = new Regex("N[ARNDCEQGHILKMFSTWYV][S|T]", RegexOptions.IgnoreCase); //NXS NXT X!=P
Regex sequonEnd = new Regex("N[ARNDCEQGHILKMFSTWYV]$", RegexOptions.IgnoreCase); //NX NX X!=P in the end
Match Sequon = sequon.Match(argSequence);
if (Sequon.Length != 0)
{
_glycopep.Add(argSequence);
}
Match SequonEnd = sequonEnd.Match(argSequence); //Go to full sequence to check if the sequence contain S/T
if (SequonEnd.Length != 0)
{
int idx = _sequence.IndexOf(argSequence) + argSequence.Length;
if (idx < _sequence.Length)
{
if (_sequence[idx] == 'S' || _sequence[idx] == 'T')
{
_glycopep.Add(argSequence);
}
}
}
if (argMutation == enumPeptideMutation.DtoN)
{
Regex sequonMutaDN = new Regex("D[ARNDCEQGHILKMFSTWYV][S|T]", RegexOptions.IgnoreCase); //DXS DXT X!=P
Regex sequonMutaDNEnd = new Regex("D[ARNDCEQGHILKMFSTWYV]$", RegexOptions.IgnoreCase); //DX DX X!=P in the end
foreach (Match SequonMutaDN in sequonMutaDN.Matches(argSequence))
{
if (SequonMutaDN.Length != 0)
{
StringBuilder sb = new StringBuilder(argSequence);
sb.Remove(SequonMutaDN.Index, 1);
sb.Insert(SequonMutaDN.Index, "N");
_glycopep.Add(sb.ToString());
}
}
Match SequonMutaDNEnd = sequonMutaDNEnd.Match(argSequence); //Go to full sequence to check if the sequence contain S/T
if (SequonMutaDNEnd.Length != 0)
{
int idx = _sequence.IndexOf(argSequence) + argSequence.Length;
if (idx < _sequence.Length)
{
if ((_sequence[idx] == 'S' || _sequence[idx] == 'T'))
{
StringBuilder sb = new StringBuilder(argSequence);
sb.Remove(SequonMutaDNEnd.Index, 1);
sb.Insert(SequonMutaDNEnd.Index, "N");
_glycopep.Add(sb.ToString());
}
}
}
}
else if (argMutation == enumPeptideMutation.AnyToN)
{
foreach (Match match in Regex.Matches(argSequence, "[ARNDCEQGHILKMFSTWYV][S|T]", RegexOptions.IgnoreCase))
{
int IndexInOriginalSequence = _sequence.IndexOf(match.Value);
if (IndexInOriginalSequence == 0)
{
continue;
}
StringBuilder sb = new StringBuilder(argSequence);
sb.Remove(match.Index - 1, 1);
sb.Insert(match.Index - 1, "N");
if (!_glycopep.Contains(sb.ToString()))
{
_glycopep.Add(sb.ToString());
}
}
if (argSequence[argSequence.Length - 1] != 'P')
{
int idx = _sequence.IndexOf(argSequence) + argSequence.Length;
if (idx < _sequence.Length)
{
if ((_sequence[idx] == 'S' || _sequence[idx] == 'T'))
{
StringBuilder sb = new StringBuilder(argSequence);
sb.Remove(argSequence.Length - 2, 1);
sb.Insert(argSequence.Length - 2, "N");
_glycopep.Add(sb.ToString());
}
}
}
}
lstGlycopeptideSeq = _glycopep;
if (lstGlycopeptideSeq.Count == 0)
{
return(false);
}
return(true);
}
public List <string> NGlycopeptide(int argAllowMissCleavage, List <Protease.Type> argProteaseType, enumPeptideMutation argMutation)
{
string MutatedPeptide = MutateSequence(_sequence, argMutation);
List <string> _cleavages = CreateCleavage(MutatedPeptide, argAllowMissCleavage, argProteaseType);
List <string> _glycopep = new List <string>();
foreach (string pep in _cleavages)
{
foreach (Match match in Regex.Matches(pep, "N[ARNDCEQGHILKMFSTWYV][S|T]", RegexOptions.IgnoreCase))
{
if (!_glycopep.Contains(pep))
{
_glycopep.Add(pep);
}
}
}
return(_glycopep);
}
/// <summary>
/// Old function, no use anymore
/// </summary>
/// <param name="argSequence"></param>
/// <param name="argMutation"></param>
/// <param name="lstGlycopeptideSeq"></param>
/// <returns></returns>
public bool IsGlycopeptide(string argSequence, enumPeptideMutation argMutation, out List<string> lstGlycopeptideSeq)
{
List<string> _glycopep = new List<string>();
Regex sequon = new Regex("N[ARNDCEQGHILKMFSTWYV][S|T]", RegexOptions.IgnoreCase); //NXS NXT X!=P
Regex sequonEnd = new Regex("N[ARNDCEQGHILKMFSTWYV]$", RegexOptions.IgnoreCase); //NX NX X!=P in the end
Match Sequon = sequon.Match(argSequence);
if (Sequon.Length != 0)
{
_glycopep.Add(argSequence);
}
Match SequonEnd = sequonEnd.Match(argSequence); //Go to full sequence to check if the sequence contain S/T
if (SequonEnd.Length != 0)
{
int idx = _sequence.IndexOf(argSequence) + argSequence.Length;
if (idx < _sequence.Length)
{
if (_sequence[idx] == 'S' || _sequence[idx] == 'T')
{
_glycopep.Add(argSequence);
}
}
}
if (argMutation == enumPeptideMutation.DtoN)
{
Regex sequonMutaDN = new Regex("D[ARNDCEQGHILKMFSTWYV][S|T]", RegexOptions.IgnoreCase); //DXS DXT X!=P
Regex sequonMutaDNEnd = new Regex("D[ARNDCEQGHILKMFSTWYV]$", RegexOptions.IgnoreCase); //DX DX X!=P in the end
foreach (Match SequonMutaDN in sequonMutaDN.Matches(argSequence))
{
if (SequonMutaDN.Length != 0)
{
StringBuilder sb = new StringBuilder(argSequence);
sb.Remove(SequonMutaDN.Index, 1);
sb.Insert(SequonMutaDN.Index, "N");
_glycopep.Add(sb.ToString());
}
}
Match SequonMutaDNEnd = sequonMutaDNEnd.Match(argSequence); //Go to full sequence to check if the sequence contain S/T
if (SequonMutaDNEnd.Length != 0)
{
int idx = _sequence.IndexOf(argSequence) + argSequence.Length;
if (idx < _sequence.Length)
{
if ((_sequence[idx] == 'S' || _sequence[idx] == 'T'))
{
StringBuilder sb = new StringBuilder(argSequence);
sb.Remove(SequonMutaDNEnd.Index, 1);
sb.Insert(SequonMutaDNEnd.Index, "N");
_glycopep.Add(sb.ToString());
}
}
}
}
else if (argMutation == enumPeptideMutation.AnyToN)
{
foreach (Match match in Regex.Matches(argSequence, "[ARNDCEQGHILKMFSTWYV][S|T]", RegexOptions.IgnoreCase))
{
int IndexInOriginalSequence = _sequence.IndexOf(match.Value);
if (IndexInOriginalSequence == 0)
{
continue;
}
StringBuilder sb = new StringBuilder(argSequence);
sb.Remove(match.Index - 1, 1);
sb.Insert(match.Index - 1, "N");
if (!_glycopep.Contains(sb.ToString()))
{
_glycopep.Add(sb.ToString());
}
}
if (argSequence[argSequence.Length - 1] != 'P')
{
int idx = _sequence.IndexOf(argSequence) + argSequence.Length;
if (idx < _sequence.Length)
{
if ((_sequence[idx] == 'S' || _sequence[idx] == 'T'))
{
StringBuilder sb = new StringBuilder(argSequence);
sb.Remove(argSequence.Length-2, 1);
sb.Insert(argSequence.Length-2, "N");
_glycopep.Add(sb.ToString());
}
}
}
}
lstGlycopeptideSeq = _glycopep;
if (lstGlycopeptideSeq.Count == 0)
{
return false;
}
return true;
}
private string MutateSequence(string argSequence, enumPeptideMutation argMutation)
{
if (argMutation == enumPeptideMutation.NoMutation)
{
return argSequence;
}
else if (argMutation == enumPeptideMutation.DtoN)
{
StringBuilder sb = new StringBuilder(argSequence);
foreach (
Match match in Regex.Matches(argSequence, "D[ARNDCEQGHILKMFSTWYV][S|T]", RegexOptions.IgnoreCase))
//DXS DXT X!=P
{
sb.Remove(match.Index, 1);
sb.Insert(match.Index, "N");
}
return sb.ToString();
}
else //(argMutation == enumPeptideMutation.AnyToN)
{
StringBuilder sb = new StringBuilder(argSequence);
foreach (
Match match in Regex.Matches(argSequence, "[ARNDCEQGHILKMFSTWYV][S|T]", RegexOptions.IgnoreCase))
//XS XT X!=P
{
if (match.Index == 0)
{
continue;
}
sb.Remove(match.Index-1, 1);
sb.Insert(match.Index-1, "N");
}
return sb.ToString();
}
}
public List<string> NGlycopeptide(int argAllowMissCleavage, List<Protease.Type> argProteaseType, enumPeptideMutation argMutation)
{
List<string> _glycopep = new List<string>();
//Native Part
List<string> _cleavages = CreateCleavage(_sequence, argAllowMissCleavage, argProteaseType);
foreach (string pep in _cleavages)
{
if (ContainSequon(pep) && !_glycopep.Contains(pep))
{
_glycopep.Add(pep);
}
}
//Mutation Part
string MutatedPeptide = MutateSequence(_sequence,argMutation);
_cleavages = CreateCleavage(MutatedPeptide,argAllowMissCleavage, argProteaseType);
foreach (string pep in _cleavages)
{
if (ContainSequon(pep) && !_glycopep.Contains(pep))
{
_glycopep.Add(pep);
}
}
return _glycopep;
}
public List <string> CreateCleavedNGlycoPeptides(int argAllowMissCleavage, List <Protease.Type> argProteaseType, enumPeptideMutation argMutation)
{
_misscleavaged = argAllowMissCleavage;
List <string> glycopeptides = new List <string>();
foreach (ProteinInfo prot in _proteinInfo)
{
glycopeptides.AddRange(prot.NGlycopeptide(_misscleavaged, argProteaseType, argMutation));
}
return(glycopeptides);
}
public List <string> NGlycopeptide(int argAllowMissCleavage, List <Protease.Type> argProteaseType, enumPeptideMutation argMutation)
{
List <string> _glycopep = new List <string>();
//Native Part
List <string> _cleavages = CreateCleavage(_sequence, argAllowMissCleavage, argProteaseType);
foreach (string pep in _cleavages)
{
if (ContainSequon(pep) && !_glycopep.Contains(pep))
{
_glycopep.Add(pep);
}
}
//Mutation Part
string MutatedPeptide = MutateSequence(_sequence, argMutation);
_cleavages = CreateCleavage(MutatedPeptide, argAllowMissCleavage, argProteaseType);
foreach (string pep in _cleavages)
{
if (ContainSequon(pep) && !_glycopep.Contains(pep))
{
_glycopep.Add(pep);
}
}
return(_glycopep);
}
