private List<CompositionHypothesisEntry> addWater(List<CompositionHypothesisEntry> Ans)
{
PeriodicTable PT = new PeriodicTable();
List<string> elementIDs = new List<string>();
List<string> molname = new List<string>();
for (int j = 0; j < Ans.Count(); j++)
{
if (Ans[j].ElementNames.Count > 0)
{
for (int i = 0; i < Ans[j].ElementNames.Count(); i++)
{
elementIDs.Add(Ans[j].ElementNames[i]);
}
for (int i = 0; i < Ans[j].MoleculeNames.Count(); i++)
{
molname.Add(Ans[j].MoleculeNames[i]);
}
break;
}
}
string H = "H";
string O = "O";
string Water = "Water";
if (!elementIDs.Any(H.Contains))
{
elementIDs.Add(H);
foreach (CompositionHypothesisEntry CH in Ans)
{
CH.ElementAmount.Add(0);
}
}
if (!elementIDs.Any(O.Contains))
{
elementIDs.Add(O);
foreach (CompositionHypothesisEntry CH in Ans)
{
CH.ElementAmount.Add(0);
}
}
if (!molname.Any(Water.Contains))
{
molname.Add(Water);
foreach (CompositionHypothesisEntry CH in Ans)
{
CH.eqCounts.Add(0);
}
}
foreach (CompositionHypothesisEntry CH in Ans)
{
CH.ElementAmount[elementIDs.IndexOf("H")] = CH.ElementAmount[elementIDs.IndexOf("H")] + 2;
CH.ElementAmount[elementIDs.IndexOf("O")] = CH.ElementAmount[elementIDs.IndexOf("O")] + 1;
CH.MassWeight = CH.MassWeight + PT.getMass("H") * 2 + PT.getMass("O");
CH.eqCounts[molname.IndexOf("Water")] = CH.eqCounts[molname.IndexOf("Water")] + 1;
}
for (int i = 0; i < Ans.Count(); i++)
{
Ans[i].ElementNames.Clear();
Ans[i].MoleculeNames.Clear();
if (i == Ans.Count() - 1)
{
Ans[0].ElementNames = elementIDs;
Ans[0].MoleculeNames = molname;
}
}
return Ans;
}
public double AdductMassDelta()
{
String adduct = this.Modification[0];
String replacement = this.Modification[1];
//Regex for the capital letters
string regexpattern = @"[A-Z]{1}[a-z]?[a-z]?\d?";
MatchCollection adducts = Regex.Matches(adduct, regexpattern);
MatchCollection replacements = Regex.Matches(replacement, regexpattern);
//Regex for the element;
string elementregexpattern = @"[A-Z]{1}[a-z]?[a-z]?(\(([^)]*)\))?";
//Regex for the number of the element.
string numberregexpattern = @"\d+";
Double adductmass = 0;
Double replacementmass = 0;
PeriodicTable pTable = new PeriodicTable();
//For each element in adducts, add up their masses.
foreach (Match add in adducts)
{
String ad = Convert.ToString(add);
String element = Convert.ToString(Regex.Match(ad, elementregexpattern));
String snumber = Convert.ToString(Regex.Match(ad, numberregexpattern));
Int32 number = 0;
if (snumber == String.Empty)
{
number = 1;
}
else
{
number = Convert.ToInt32(snumber);
}
adductmass = adductmass + number * pTable.getMass(element);
}
// Adduct replacement should be the mass delta already counting the lost composition.
////For each element in replacements, add up their masses.
//foreach (Match el in replacements)
//{
// String element = Convert.ToString(Regex.Match(Convert.ToString(el), elementregexpattern));
// String snumber = Convert.ToString(Regex.Match(Convert.ToString(el), numberregexpattern));
// Int32 number = 0;
// if (snumber == String.Empty)
// {
// number = 1;
// }
// else
// {
// number = Convert.ToInt32(snumber);
// }
// replacementmass = replacementmass + number * pTable.getMass(element);
//}
//Finally, subtract them and obtain delta mass.
Double dMass = adductmass - replacementmass;
return dMass;
}
//This function is used by generateHypo to get the mass of a composition in the composition table.
public Double getcompMass(GlycanCompositionTable CT, List<string> elementIDs)
{
Double Mass = 0;
PeriodicTable PT = new PeriodicTable();
for (int i = 0; i < CT.elementAmount.Count(); i++)
{
Mass = Mass + CT.elementAmount[i] * PT.getMass(elementIDs[i]);
}
return Mass;
}
//This class calculates delta adduct mass.
public Double CalculateAdductMass(GlycanHypothesisCombinatorialGenerator GD)
{
String adduct = GD.Modification[0];
String replacement = GD.Modification[1];
//Regex for the capital letters
string regexpattern = @"[A-Z]{1}[a-z]?[a-z]?\d?";
MatchCollection adducts = Regex.Matches(adduct, regexpattern);
MatchCollection replacements = Regex.Matches(replacement, regexpattern);
//Regex for the element;
string elementregexpattern = @"[A-Z]{1}[a-z]?[a-z]?(\(([^)]*)\))?";
//Regex for the number of the element.
string numberregexpattern = @"\d+";
Double adductmass = 0;
Double replacementmass = 0;
PeriodicTable pTable = new PeriodicTable();
//For each element in adducts, add up their masses.
foreach (Match add in adducts)
{
String ad = Convert.ToString(add);
String element = Convert.ToString(Regex.Match(ad, elementregexpattern));
String snumber = Convert.ToString(Regex.Match(ad, numberregexpattern));
Int32 number = 0;
if (snumber == String.Empty)
{
number = 1;
}
else
{
number = Convert.ToInt32(snumber);
}
adductmass = adductmass + number * pTable.getMass(element);
}
//For each element in replacements, add up their masses.
foreach (Match el in replacements)
{
String element = Convert.ToString(Regex.Match(Convert.ToString(el), elementregexpattern));
String snumber = Convert.ToString(Regex.Match(Convert.ToString(el), numberregexpattern));
Int32 number = 0;
if (snumber == String.Empty)
{
number = 1;
}
else
{
number = Convert.ToInt32(snumber);
}
replacementmass = replacementmass + number * pTable.getMass(element);
}
//Finally, subtract them and obtain delta mass.
Double dMass = adductmass - replacementmass;
return dMass;
}
//This function is used by glycopeptide tag to populate the datagridview after adding a file.
private void populateGPForm(String currentpath)
{
string extension = Path.GetExtension(currentpath);
List<Peptide> data = new List<Peptide>();
//This is tab delimited file.
if (extension == ".txt")
{
data = ReadTabDelimitedProteinProspecter(currentpath);
}
//This is XML File implemented by JK
else if (extension == ".xml")
{
MSDigestReport report = MSDigestReport.Load(currentpath);
Console.WriteLine(report.Peptides.Count);
data = report.Peptides.ConvertAll(x => new Peptide(x));
}
Console.WriteLine(data.Count);
foreach (Peptide x in data)
{
Console.WriteLine(x);
}
PeriodicTable pt = new PeriodicTable();
SequenceDisplayTextBox.Text = GetSequenceFromCleavedPeptides(data);
foreach (Peptide pp in data)
{
PeptideGridView.Rows.Add(
pp.NumGlycosylations > 0 ? 1 : 0,
pp.Mass - (pp.Charge * pt.getMass("H+")),
pp.Modifications,
pp.StartAA,
pp.EndAA,
pp.MissedCleavages,
pp.Sequence,
Convert.ToString(pp.NumGlycosylations),
pp.ProteinID
);
}
}
public CompositionHypothesisTabbedForm()
{
InitializeComponent();
//Initialize the additional rules table.
DataGridViewTextBoxColumn Formula = new DataGridViewTextBoxColumn();
Formula.HeaderText = "Formula";
Formula.Name = "Formula";
Formula.ValueType = typeof(String);
this.dataGridView3.Columns.Add(Formula);
DataGridViewComboBoxColumn Relationship = new DataGridViewComboBoxColumn();
Relationship.HeaderText = "Relationship";
Relationship.Name = "Relationship";
Relationship.Items.AddRange("=", ">", "<", "≥", "≤", "≠");
this.dataGridView3.Columns.Add(Relationship);
DataGridViewTextBoxColumn constraint = new DataGridViewTextBoxColumn();
constraint.HeaderText = "constraint";
constraint.Name = "constraint";
constraint.ValueType = typeof(String);
this.dataGridView3.Columns.Add(constraint);
//Populate the tables.
//Get the path of the source file.
String currentpath = Application.StartupPath + "\\compositionsCurrent.cpos";
this.populateForm(currentpath);
PeriodicTable PT = new PeriodicTable();
List<string> elements = PT.getElements();
List<string> elementsInHeader = new List<string>();
for (int j = 2; j < this.dataGridView1.ColumnCount -2; ++j)
{
elementsInHeader.Add(dataGridView1.Columns[j].HeaderText);
}
foreach (string ele in elements)
{
bool eleNotInTable = true;
foreach (string element in elementsInHeader)
{
if (element == ele)
{
eleNotInTable = false;
comboBox2.Items.Add(ele);
}
}
if (eleNotInTable)
comboBox1.Items.Add(ele);
}
try
{
dataGridView1.AllowUserToAddRows = false;
dataGridView1.Columns[0].ReadOnly = true;
dataGridView1.AutoSizeColumnsMode = DataGridViewAutoSizeColumnsMode.AllCells;
dataGridView2.AutoSizeColumnsMode = DataGridViewAutoSizeColumnsMode.AllCells;
dataGridView3.AutoSizeColumnsMode = DataGridViewAutoSizeColumnsMode.AllCells;
}
catch (Exception compoex)
{
MessageBox.Show("Error in populating GlycanCompositions Table. Error:" + compoex);
}
}
private void BuildGlycopeptideHypothesis1(string comhypopath)
{
List<CompositionHypothesisEntry> CHy = getCompHypo(comhypopath);
List<string> elementIDs = new List<string>();
List<string> molename = new List<string>();
for (int j = 0; j < CHy.Count(); j++)
{
if (CHy[j].ElementNames.Count > 0)
{
for (int i = 0; i < CHy[j].ElementNames.Count(); i++)
{
elementIDs.Add(CHy[j].ElementNames[i]);
}
for (int i = 0; i < CHy[j].MoleculeNames.Count(); i++)
{
molename.Add(CHy[j].MoleculeNames[i]);
}
break;
}
}
String AddRep = CHy[0].AddRep;
int indexH = 0;
int indexO = 0;
int indexWater = 0;
try
{
indexH = elementIDs.IndexOf("H");
indexO = elementIDs.IndexOf("O");
indexWater = molename.IndexOf("Water");
if (indexWater < 0)
{
indexWater = molename.IndexOf("G:Water");
}
if (indexWater < 0)
{
throw new Exception("No Water!");
}
}
catch
{
MessageBox.Show("Your composition hypothesis contains a compound without Water. Job terminated.");
return;
}
List<Peptide> PP = GetPeptidesFromTable();
List<CompositionHypothesisEntry> Ans = new List<CompositionHypothesisEntry>();
//Ans.AddRange(CHy);
PeriodicTable PT = new PeriodicTable();
for (int i = 0; i < PP.Count; i++)
{
if (PP[i].Selected)
{
Int32 Count = Convert.ToInt32(PP[i].NumGlycosylations);
List<CompositionHypothesisEntry> Temp = new List<CompositionHypothesisEntry>();
CompositionHypothesisEntry temp = new CompositionHypothesisEntry();
//First line:
temp.CompoundComposition = "";
temp.AdductNum = 0;
temp.AddRep = "";
temp.MassWeight = PP[i].Mass;
for (int s = 0; s < CHy[0].eqCounts.Count; s++)
{
temp.eqCounts.Add(0);
}
for (int s = 0; s < CHy[0].ElementAmount.Count; s++)
{
temp.ElementAmount.Add(0);
}
//columns for glycopeptides
temp.PepModification = PP[i].Modifications;
temp.PepSequence = PP[i].Sequence;
temp.MissedCleavages = PP[i].MissedCleavages;
temp.StartAA = PP[i].StartAA;
temp.EndAA = PP[i].EndAA;
temp.NumGlycosylations = 0;
Temp.Add(temp);
for (int j = 0; j < Count; j++)
{
List<CompositionHypothesisEntry> Temp2 = new List<CompositionHypothesisEntry>();
for (int k = 0; k < Temp.Count(); k++)
{
//need to reread the file and get new reference, because c# keeps passing by reference which creates a problem.
List<CompositionHypothesisEntry> CH = getCompHypo(comhypopath);
for (int l = 0; l < CH.Count(); l++)
{
CompositionHypothesisEntry temp2 = new CompositionHypothesisEntry();
temp2 = CH[l];
temp2.NumGlycosylations = Temp[k].NumGlycosylations + 1;
temp2.PepModification = Temp[k].PepModification;
temp2.PepSequence = Temp[k].PepSequence;
temp2.MissedCleavages = Temp[k].MissedCleavages;
temp2.StartAA = Temp[k].StartAA;
temp2.EndAA = Temp[k].EndAA;
List<string> forsorting = new List<string>();
forsorting.Add(Temp[k].CompoundComposition);
forsorting.Add(temp2.CompoundComposition);
forsorting = forsorting.OrderBy(a => a).ToList();
temp2.CompoundComposition = forsorting[0] + forsorting[1];
temp2.AdductNum = temp2.AdductNum + Temp[k].AdductNum;
for (int s = 0; s < temp2.eqCounts.Count; s++)
{
temp2.eqCounts[s] = temp2.eqCounts[s] + Temp[k].eqCounts[s];
}
for (int s = 0; s < temp2.ElementAmount.Count; s++)
{
temp2.ElementAmount[s] = temp2.ElementAmount[s] + Temp[k].ElementAmount[s];
}
for (int ui = 0; ui < molename.Count(); ui++)
{
if (molename[ui] == "Water")
{
if (temp2.eqCounts[ui] > 0)
{
temp2.eqCounts[ui] = temp2.eqCounts[ui] - 1;
}
break;
}
}
#region Modified by JK
//temp2.elementAmount[indexH] = temp2.elementAmount[indexH] - 2;
//temp2.elementAmount[indexO] = temp2.elementAmount[indexO] - 1;
//if (temp2.elementAmount[indexO] < 0)
// temp2.elementAmount[indexO] = 0;
//if (temp2.elementAmount[indexH] < 0)
// temp2.elementAmount[indexH] = 0;
/* These fields are not present in the Database-generated hypothesis,
* but they are not appropriately error-checked when computed earlier.
* This bandaid should let existing files work while letting Database-
* generated ones through as well. This function is very difficult to
* trace in and would benefit from rewriting in the future.
*/
if ((indexH > 0) && (indexO > 0))
{
temp2.ElementAmount[indexH] = temp2.ElementAmount[indexH] - 2;
temp2.ElementAmount[indexO] = temp2.ElementAmount[indexO] - 1;
if (temp2.ElementAmount[indexO] < 0)
temp2.ElementAmount[indexO] = 0;
if (temp2.ElementAmount[indexH] < 0)
temp2.ElementAmount[indexH] = 0;
}
//else
//{
// temp2.elementAmount[indexH] = 0;
// temp2.elementAmount[indexO] = 0;
//}
#endregion
//Hard coded removal of extra water from neutral Charge glycan.
temp2.MassWeight = temp2.MassWeight + Temp[k].MassWeight - PT.getMass("H") * 2 - PT.getMass("O");
Temp2.Add(temp2);
}
}
Temp.AddRange(Temp2);
}
Ans.AddRange(Temp);
}
}
//Remove Duplicates from CHy
Ans = Ans.OrderBy(a => a.MassWeight).ToList();
CHy.Clear();
for (int i = 0; i < Ans.Count() - 1; i++)
{
bool thesame = false;
bool equal = (Ans[i].eqCounts.Count == Ans[i + 1].eqCounts.Count) && new HashSet<int>(Ans[i].eqCounts).SetEquals(Ans[i + 1].eqCounts);
if (Ans[i].PepSequence == Ans[i + 1].PepSequence && equal)
{
if (Ans[i].AdductNum == Ans[i + 1].AdductNum && Ans[i].PepModification == Ans[i + 1].PepModification)
{
thesame = true;
}
}
if (!thesame)
CHy.Add(Ans[i]);
}
Console.WriteLine("Ans Length {0}", Ans.Count());
//Enter elementID and MoleNames into each rows
CHy.Add(Ans[Ans.Count() - 1]);
for (int i = 0; i < CHy.Count(); i++)
{
CHy[i].ElementNames.Clear();
CHy[i].MoleculeNames.Clear();
if (i == CHy.Count() - 1)
{
CHy[0].ElementNames = elementIDs;
CHy[0].MoleculeNames = molename;
}
}
//Obtain the Name of the adduct molecules:
GlycanHypothesisCombinatorialGenerator GD = new GlycanHypothesisCombinatorialGenerator();
GD.Modification = AddRep.Split('/');
//Send to generate DataTable
Console.WriteLine(CHy[0]);
theComhypoOnTab2 = genDT(CHy, GD);
}
//This class calculates delta adduct mass.
private Double adductMass(List<CompositionHypothesisEntry> comhyp)
{
String adduct = "";
String replacement = "";
try
{
String AddRep = comhyp[1].AddRep;
String[] AddandRep = AddRep.Split('/');
adduct = AddandRep[0];
replacement = AddandRep[1];
}
catch
{
adduct = "0";
replacement = "0";
}
//Regex for the capital letters
string regexpattern = @"[A-Z]{1}[a-z]?[a-z]?\d?";
MatchCollection adducts = Regex.Matches(adduct, regexpattern);
MatchCollection replacements = Regex.Matches(replacement, regexpattern);
//Regex for the element;
string elementregexpattern = "[A-Z]{1}[a-z]?[a-z]?";
//Regex for the number of the element.
string numberregexpattern = "[0-9]*$";
Double adductmass = 0;
Double replacementmass = 0;
PeriodicTable pTable = new PeriodicTable();
//Console.WriteLine("Adduct String {0}, {1} Adduct Matches {1}", adduct, adducts);
//For each element in adducts, add up their masses.
foreach (Match add in adducts)
{
String ad = Convert.ToString(add);
String element = Convert.ToString(Regex.Match(ad, elementregexpattern));
String snumber = Convert.ToString(Regex.Match(ad, numberregexpattern));
Int32 number = 0;
if (snumber == String.Empty)
{
number = 1;
}
else
{
number = Convert.ToInt32(snumber);
}
adductmass = adductmass + number * pTable.getMass(element);
}
//For each element in replacements, add up their masses.
//Console.WriteLine("Replacement String {0}, {1} Replacement Matches {1}", replacement, replacements);
foreach (Match rep in replacements)
{
String el = Convert.ToString(rep);
String element = Convert.ToString(Regex.Match(el, elementregexpattern));
String snumber = Convert.ToString(Regex.Match(el, numberregexpattern));
Int32 number = 0;
if (snumber == String.Empty)
{
number = 1;
}
else
{
number = Convert.ToInt32(Regex.Match(el, numberregexpattern));
}
replacementmass = replacementmass + number * pTable.getMass(element);
}
//Finally, subtract them and obtain delta mass.
Double dMass = adductmass - replacementmass;
return dMass;
}