//Returns an empirical formula string with or without PTMs.
//Accounts for the PTMs using the Averagine formula.
//Parses out the PTMs and calculates the empirical formula for the known unmodified sequence.
//Adds or subtracts the PTM formula from the sequence formula based on the overall mass of the PTMs
public string GetEmpiricalFormulaFromSequence(string code, bool cysteinesAreModified = false)
{
var ptmFormula = "";
var sequenceFormula = "";
var empiricalFormula = "";
var ptmMass = PtmMassFromCode(code);
ptmFormula = IsotopicDistributionCalculator.Instance.GetAveragineFormulaAsString(Math.Abs(ptmMass), false);
sequenceFormula = SequenceToEmpiricalFormula(code, cysteinesAreModified);
if (ptmMass < 0)
{
empiricalFormula = EmpiricalFormulaUtilities.SubtractFormula(sequenceFormula, ptmFormula);
}
else
{
empiricalFormula = EmpiricalFormulaUtilities.AddFormula(sequenceFormula, ptmFormula);
}
//TEMPORARY HANDLING OF BAD TARGETS WITH PTM > SEQUENCE
//CHECK THE UPDATEMISSINGTARGETINFO IN IQTARGETUTILITES WHEN CHANGING
if (String.IsNullOrEmpty(empiricalFormula))
{
empiricalFormula = "C0H0N0O0S0";
}
return(empiricalFormula);
}
public void addUnimodFormulaTest1()
{
var testPeptide = "SAMPLER";
var peptideUtils = new PeptideUtils();
var baseFormula = peptideUtils.GetEmpiricalFormulaForPeptideSequence(testPeptide);
var mod = "H3 C2 N O";
var modFormula = EmpiricalFormulaUtilities.AddFormula(baseFormula, mod);
Console.WriteLine("Unmodified peptide= " + baseFormula);
Console.WriteLine("Modified peptide= " + modFormula);
Assert.AreEqual("C35H61N11O12S", modFormula);
}
public List <IqTarget> Import()
{
var targets = GetMassTagDataFromDb();
if (IsEmpiricalFormulaExtracted)
{
GetModDataFromDb(_targetsContainingMods);
var peptideUtils = new PeptideUtils();
foreach (IqTargetDms iqTarget in targets)
{
var baseEmpiricalFormula = peptideUtils.GetEmpiricalFormulaForPeptideSequence(iqTarget.Code);
if (!string.IsNullOrEmpty(iqTarget.ModDescription))
{
var target = iqTarget;
var mods = (from n in _massTagModData where n.Item1 == target.ID select n);
foreach (var tuple in mods)
{
var modString = tuple.Item4;
try
{
baseEmpiricalFormula = EmpiricalFormulaUtilities.AddFormula(baseEmpiricalFormula, modString);
}
catch (Exception ex)
{
IqLogger.Log.Debug("Failed to calculate empirical formula for the Target " + target.ID + " (" + ex.Message + ")" +
"; Having trouble with the mod: " + modString + "; This Target was NOT imported!!");
}
}
}
iqTarget.EmpiricalFormula = baseEmpiricalFormula;
if (IsMonoMassCalculatedFromEmpiricalFormula)
{
iqTarget.MonoMassTheor = EmpiricalFormulaUtilities.GetMonoisotopicMassFromEmpiricalFormula(iqTarget.EmpiricalFormula);
}
}
}
return(targets);
}
public void AddPhosphorylationTest1()
{
const string testPeptide = "SAMPLER";
var peptideUtils = new PeptideUtils();
var formula = peptideUtils.GetEmpiricalFormulaForPeptideSequence(testPeptide);
const string phosphorylationMod = "HPO3";
var empiricalFormula = EmpiricalFormulaUtilities.AddFormula(formula, phosphorylationMod);
var massUnmodified = EmpiricalFormulaUtilities.GetMonoisotopicMassFromEmpiricalFormula(formula);
var massModified = EmpiricalFormulaUtilities.GetMonoisotopicMassFromEmpiricalFormula(empiricalFormula);
var diff = Math.Round(massModified - massUnmodified, 1, MidpointRounding.AwayFromZero);
Console.WriteLine(formula + "\t" + massUnmodified);
Console.WriteLine(empiricalFormula + "\t" + massModified);
Console.WriteLine("diff= " + diff);
Assert.AreEqual(80.0, diff);
}
public void AddAcetylationTest1()
{
var testPeptide = "SAMPLER";
var peptideUtils = new PeptideUtils();
var formula = peptideUtils.GetEmpiricalFormulaForPeptideSequence(testPeptide);
var acetylationFormula = "C2H2O";
var empiricalFormula = EmpiricalFormulaUtilities.AddFormula(formula, acetylationFormula);
var massUnmodified = EmpiricalFormulaUtilities.GetMonoisotopicMassFromEmpiricalFormula(formula);
var massModified = EmpiricalFormulaUtilities.GetMonoisotopicMassFromEmpiricalFormula(empiricalFormula);
var diff = Math.Round(massModified - massUnmodified, 1, MidpointRounding.AwayFromZero);
Console.WriteLine(formula + "\t" + massUnmodified);
Console.WriteLine(empiricalFormula + "\t" + massModified);
Console.WriteLine("diff= " + diff);
Assert.AreEqual(42.0, diff);
}
//Returns an empirical formula string with or without PTMs.
//Accounts for the PTMs using the Averagine formula.
//Parses out the PTMs and calculates the empirical formula for the known unmodified sequence.
//Adds or subtracts the PTM formula from the sequence formula based on the overall mass of the PTMs
public string GetEmpiricalFormulaFromSequence(string code)
{
string PTM_Formula = "";
string SequenceFormula = "";
string EmpiricalFormula = "";
double ptm_mass = PTMMassFromCode(code);
PTM_Formula = IsotopicDistributionCalculator.Instance.GetAveragineFormulaAsString(Math.Abs(ptm_mass), false);
SequenceFormula = SequenceToEmpiricalFormula(code);
if (ptm_mass < 0)
{
EmpiricalFormula = EmpiricalFormulaUtilities.SubtractFormula(SequenceFormula, PTM_Formula);
}
else
{
EmpiricalFormula = EmpiricalFormulaUtilities.AddFormula(SequenceFormula, PTM_Formula);
}
return(EmpiricalFormula);
}
private void CalculateEmpiricalFormulas(TargetCollection data)
{
var peptideUtils = new PeptideUtils();
foreach (var targetBase in data.TargetList)
{
var peptide = (PeptideTarget)targetBase;
var baseEmpiricalFormula = peptideUtils.GetEmpiricalFormulaForPeptideSequence(peptide.Code);
if (peptide.ContainsMods)
{
TargetBase peptide1 = peptide;
var mods = (from n in _massTagModData where n.Item1 == peptide1.ID select n);
foreach (var tuple in mods)
{
baseEmpiricalFormula = EmpiricalFormulaUtilities.AddFormula(baseEmpiricalFormula, tuple.Item4);
}
}
peptide.EmpiricalFormula = baseEmpiricalFormula;
}
}
public string GetEmpiricalFormulaForSequenceWithMods(string code)
{
// Check for pyroglutamate modification
var containsPyroglutamateMod = false;
if (_modPyroglutamate.IsMatch(code))
{
containsPyroglutamateMod = true;
// Remove the modification from the string
var pieces = _modPyroglutamate.Match(code).Groups;
code = pieces["prefix"].Value + pieces["modified"].Value + pieces["suffix"].Value;
}
// Check for acetylation modification
var containsAcetylationMod = false;
if (_modAcetylation.IsMatch(code))
{
containsAcetylationMod = true;
// Remove the modification from the string
var pieces = _modAcetylation.Match(code).Groups;
code = pieces["prefix"].Value + pieces["modified"].Value + pieces["suffix"].Value;
}
// Check for phosphorylation modification
// TODO: this function does not account for the fact that phosphorylation could occur multiple times
var containsPhosphorylationMod = false;
if (_modPhosphorylation.IsMatch(code))
{
containsPhosphorylationMod = true;
// Remove the modification from the string
var pieces = _modPhosphorylation.Match(code).Groups;
code = pieces["prefix"].Value + pieces["modified"].Value + pieces["suffix"].Value;
}
// If the peptide sequence still has modifications, we can't get the empirical formula
if (code.Contains("("))
{
return(String.Empty);
}
// Get the empirical formula as if the peptide sequence was unmodified
var empiricalFormula = _peptideUtils.GetEmpiricalFormulaForPeptideSequence(code);
// Apply modifications to empirical formula
if (containsPyroglutamateMod)
{
empiricalFormula = EmpiricalFormulaUtilities.SubtractFormula(empiricalFormula, "H3N1");
}
if (containsAcetylationMod)
{
empiricalFormula = EmpiricalFormulaUtilities.AddFormula(empiricalFormula, "C2H2O");
}
if (containsPhosphorylationMod)
{
empiricalFormula = EmpiricalFormulaUtilities.AddFormula(empiricalFormula, "HPO3");
}
return(empiricalFormula);
}
public override TargetCollection Import()
{
var targetCollection = new TargetCollection();
targetCollection.TargetList.Clear();
GetMassTagDataFromDB(targetCollection, MassTagsToBeRetrieved);
GetModDataFromDB(targetCollection, MassTagsToBeRetrieved);
var peptideUtils = new PeptideUtils();
var troubleSomePeptides = new List <TargetBase>();
foreach (var targetBase in targetCollection.TargetList)
{
var peptide = (PeptideTarget)targetBase;
var baseEmpiricalFormula = peptideUtils.GetEmpiricalFormulaForPeptideSequence(peptide.Code);
if (peptide.ContainsMods)
{
var peptide1 = peptide;
var mods = (from n in _massTagModData where n.Item1 == peptide1.ID select n);
foreach (var tuple in mods)
{
var modString = tuple.Item4;
try
{
baseEmpiricalFormula = EmpiricalFormulaUtilities.AddFormula(baseEmpiricalFormula, modString);
}
catch
{
Console.WriteLine("Failed to calculate empirical formula for the Target " + peptide.ID +
"; Having trouble with the mod: " + modString + "; This Target was NOT imported!!");
troubleSomePeptides.Add(peptide);
}
}
}
try
{
peptide.EmpiricalFormula = baseEmpiricalFormula;
}
catch
{
Console.WriteLine("Failed to calculate empirical formula for the Target " + peptide.ID +
"; Cannot parse this formula: " + peptide.EmpiricalFormula + "; This Target was NOT imported!!");
troubleSomePeptides.Add(peptide);
}
}
var cleanTargetList = new List <TargetBase>();
//filter out the bad peptides (the once with errors during empirical formula parsing)
foreach (var peptide in targetCollection.TargetList)
{
if (!troubleSomePeptides.Contains(peptide))
{
cleanTargetList.Add(peptide);
}
}
targetCollection.TargetList = cleanTargetList;
if (ChargeStateRangeBasedOnDatabase)
{
targetCollection.ApplyChargeStateFilter(ChargeStateFilterThreshold);
}
else
{
var chargeStateTargets = new List <TargetBase>();
foreach (var targetBase in targetCollection.TargetList)
{
var minCharge = 1;
var maxCharge = 100;
for (var charge = minCharge; charge <= maxCharge; charge++)
{
var mz = targetBase.MonoIsotopicMass / charge + Globals.PROTON_MASS;
if (mz < MaxMZForChargeStateRange)
{
if (mz < MinMZForChargeStateRange)
{
break;
}
TargetBase chargeStateTarget = new PeptideTarget((PeptideTarget)targetBase);
chargeStateTarget.ChargeState = (short)charge;
chargeStateTarget.MZ = chargeStateTarget.MonoIsotopicMass / charge + Globals.PROTON_MASS;
chargeStateTarget.ObsCount = -1;
chargeStateTargets.Add(chargeStateTarget);
}
}
}
targetCollection.TargetList = chargeStateTargets.OrderBy(p => p.ID).ThenBy(p => p.ChargeState).ToList();
}
return(targetCollection);
}