internal static void ConvertElementTableToFormula(
ref clsElementIsotopes elemental_isotope_composition,
Hashtable elementCounts, out DeconToolsV2.MolecularFormula formula)
{
var elements = elementCounts.Keys.GetEnumerator();
formula = new DeconToolsV2.MolecularFormula();
while (elements.MoveNext())
{
// Get the next element symbol in the table
var element = (string)elements.Current;
// Put it in a character array
var count = (int)elementCounts[element];
// find the index of the element in the AtomicInformation
var index = elemental_isotope_composition.GetElementIndex(element);
if (index == -1)
{
throw new ApplicationException(string.Concat("Unknown element ", element));
}
var atomic_count = new DeconToolsV2.AtomicCount(index, count);
var mono_mass =
elemental_isotope_composition.ElementalIsotopesList[index].Isotopes[0].Mass * count;
var avg_mass = elemental_isotope_composition.ElementalIsotopesList[index].AverageMass *
count;
formula.AddAtomicCount(atomic_count, mono_mass, avg_mass);
}
}
public void TestParseFormulaNew()
{
string formula = "C4.9384 H7.7583 N1.3577 O1.4773 S0.0417";
//string formula = "Ct H7.7583 N1.3577 O1.4773 S0.0417";
var elements = new clsElementIsotopes();
//var molecule = new MolecularFormula(formula, elements);
var molecule = new MolecularFormula();
molecule.SetMolecularFormula(formula, elements);
var results = molecule.ElementalComposition;
var carbon = results[0];
var hydrogen = results[1];
var nitrogen = results[2];
var oxygen = results[3];
var sulfur = results[4];
Assert.AreEqual(carbon.Index, 5);
Assert.AreEqual(carbon.NumCopies, 4.9384);
Assert.AreEqual(hydrogen.Index, 0);
Assert.AreEqual(hydrogen.NumCopies, 7.7583);
Assert.AreEqual(nitrogen.Index, 6);
Assert.AreEqual(nitrogen.NumCopies, 1.3577);
Assert.AreEqual(oxygen.Index, 7);
Assert.AreEqual(oxygen.NumCopies, 1.4773);
Assert.AreEqual(sulfur.Index, 15);
Assert.AreEqual(sulfur.NumCopies, 0.0417);
}
public MercuryIsotopeDistribution(MercuryIsotopeDistribution mercDistribution)
{
ElementalIsotopeComposition = mercDistribution.ElementalIsotopeComposition;
ChargeCarrierMass = mercDistribution.ChargeCarrierMass;
ApType = mercDistribution.ApType;
MercurySize = mercDistribution.MercurySize;
PointsPerAmu = mercDistribution.PointsPerAmu;
}
public void SetMolecularFormula(string molFormula, clsElementIsotopes atomicInformation)
{
Formula = molFormula;
var formula = molFormula;
TotalAtomCount = 0;
MonoisotopicMass = 0;
ElementalComposition.Clear();
var validator = new Regex(@"^(\s*[A-Z][a-z]?\s*\d*\.?\d*)*\s*$", RegexOptions.CultureInvariant);
if (!validator.IsMatch(molFormula))
{
throw new Exception("Molecular formula specified was invalid. Format required is one or more " +
"groups similar to \"[atomic symbol][count]\", where atomic symbol is an " +
"uppercase letter that may be followed by a lowercase letter, and count " +
"is a number that consists of numeric digits and maybe one decimal point.");
}
var grouper = new Regex(@"([A-Z][a-z]?)\s*(\d*\.?\d*)", RegexOptions.CultureInvariant);
var groups = grouper.Matches(molFormula);
foreach (Match group in groups)
{
var match = group.Groups;
// match[0] returns the entire match, match[1] and match[2] will have the individual groups
var atomicSymbol = match[1].Value;
var countStr = match[2].Value;
double count = 1;
if (!string.IsNullOrWhiteSpace(countStr))
{
count = Convert.ToDouble(countStr.Trim());
}
// now we should have a symbol and a count. Lets get the atomicity of the atom.
var elementIndex = atomicInformation.GetElementIndex(atomicSymbol);
if (elementIndex == -1)
{
// theres an error. two decimals.
var errorStr =
"Molecular Formula specified was incorrect. Symbol in formula was not recognize from elements provided: ";
errorStr += atomicSymbol;
throw new Exception(errorStr);
}
ElementalComposition.Add(new AtomicCount(elementIndex, count));
TotalAtomCount += count;
MonoisotopicMass += atomicInformation.ElementalIsotopesList[elementIndex].Isotopes[0].Mass * count;
AverageMass += atomicInformation.ElementalIsotopesList[elementIndex].AverageMass * count;
}
/*
* // Regular expressions simplify this code so much. See above.
* var formulaLength = formula.Length;
* var index = 0;
* //var numAtoms = atomicInformation.GetNumElements();
* while (index < formulaLength)
* {
* while (index < formulaLength && (formula[index] == ' ' || formula[index] == '\t'))
* {
* index++;
* }
*
* var startIndex = index;
* var stopIndex = startIndex;
* var symbolChar = formula[stopIndex];
* if (!(symbolChar >= 'A' && symbolChar <= 'Z') && !(symbolChar >= 'a' && symbolChar <= 'z'))
* {
* var errorStr = "Molecular Formula specified was incorrect at position: " + (stopIndex + 1) +
* ". Should have element symbol there";
* throw new Exception(errorStr);
* }
*
* while ((symbolChar >= 'A' && symbolChar <= 'Z') || (symbolChar >= 'a' && symbolChar <= 'z'))
* {
* stopIndex++;
* if (stopIndex == formulaLength)
* break;
* symbolChar = formula[stopIndex];
* }
*
* var atomicSymbol = formula.Substring(startIndex, stopIndex - startIndex);
* index = stopIndex;
* while (index < formulaLength && (formula[index] == ' ' || formula[index] == '\t'))
* {
* index++;
* }
* double count = 0;
* if (index == formulaLength)
* {
* // assume that the last symbol had a 1.
* count = 1;
* }
* startIndex = index;
* stopIndex = startIndex;
* symbolChar = formula[stopIndex];
* var decimalFound = false;
* while ((symbolChar >= '0' && symbolChar <= '9') || symbolChar == '.')
* {
* if (symbolChar == '.')
* {
* if (decimalFound)
* {
* // theres an error. two decimals.
* var errorStr = "Molecular Formula specified was incorrect at position: " +
* (stopIndex + 1) + ". Two decimal points present";
* throw new Exception(errorStr);
* }
* decimalFound = true;
* }
* stopIndex++;
* if (stopIndex == formulaLength)
* break;
* symbolChar = formula[stopIndex];
* }
* if (startIndex == stopIndex)
* {
* count = 1;
* }
* else
* {
* count = Convert.ToDouble(formula.Substring(startIndex, stopIndex - startIndex));
* //count = Helpers.atof(formula.Substring(index));
* }
* // now we should have a symbol and a count. Lets get the atomicity of the atom.
* var elementIndex = atomicInformation.GetElementIndex(atomicSymbol);
* if (elementIndex == -1)
* {
* // theres an error. two decimals.
* var errorStr =
* "Molecular Formula specified was incorrect. Symbol in formula was not recognize from elements provided: ";
* errorStr += atomicSymbol;
* throw new Exception(errorStr);
* }
* ElementalComposition.Add(new AtomicCount(elementIndex, count));
* index = stopIndex;
* TotalAtomCount += count;
* MonoisotopicMass += atomicInformation.ElementalIsotopesList[elementIndex].Isotopes[0].Mass * count;
* AverageMass += atomicInformation.ElementalIsotopesList[elementIndex].AverageMass * count;
* }
*/
}
public MolecularFormula(string formula, clsElementIsotopes atomicInformation)
{
SetMolecularFormula(formula, atomicInformation);
}
public void SetMolecularFormula(string molFormula, clsElementIsotopes atomicInformation)
{
Formula = molFormula;
var formula = molFormula;
TotalAtomCount = 0;
ElementalComposition.Clear();
var formulaLength = formula.Length;
var index = 0;
//var numAtoms = atomicInformation.GetNumElements();
MonoisotopicMass = 0;
while (index < formulaLength)
{
while (index < formulaLength && (formula[index] == ' ' || formula[index] == '\t'))
{
index++;
}
var startIndex = index;
var stopIndex = startIndex;
var symbolChar = formula[stopIndex];
if (!(symbolChar >= 'A' && symbolChar <= 'Z') && !(symbolChar >= 'a' && symbolChar <= 'z'))
{
var errorStr = "Molecular Formula specified was incorrect at position: " + (stopIndex + 1) +
". Should have element symbol there";
throw new Exception(errorStr);
}
while ((symbolChar >= 'A' && symbolChar <= 'Z') || (symbolChar >= 'a' && symbolChar <= 'z'))
{
stopIndex++;
if (stopIndex == formulaLength)
{
break;
}
symbolChar = formula[stopIndex];
}
var atomicSymbol = formula.Substring(startIndex, stopIndex - startIndex);
index = stopIndex;
while (index < formulaLength && (formula[index] == ' ' || formula[index] == '\t'))
{
index++;
}
double count = 0;
if (index == formulaLength)
{
// assume that the last symbol had a 1.
count = 1;
}
startIndex = index;
stopIndex = startIndex;
symbolChar = formula[stopIndex];
var decimalFound = false;
while ((symbolChar >= '0' && symbolChar <= '9') || symbolChar == '.')
{
if (symbolChar == '.')
{
if (decimalFound)
{
// theres an error. two decimals.
var errorStr = "Molecular Formula specified was incorrect at position: " +
(stopIndex + 1) + ". Two decimal points present";
throw new Exception(errorStr);
}
decimalFound = true;
}
stopIndex++;
if (stopIndex == formulaLength)
{
break;
}
symbolChar = formula[stopIndex];
}
if (startIndex == stopIndex)
{
count = 1;
}
else
{
count = Helpers.atof(formula.Substring(index));
}
// now we should have a symbol and a count. Lets get the atomicity of the atom.
var elementIndex = atomicInformation.GetElementIndex(atomicSymbol);
if (elementIndex == -1)
{
// theres an error. two decimals.
var errorStr =
"Molecular Formula specified was incorrect. Symbol in formula was not recognize from elements provided: ";
errorStr += atomicSymbol;
throw new Exception(errorStr);
}
var currentAtom = new AtomicCount(elementIndex, count);
ElementalComposition.Add(currentAtom);
index = stopIndex;
TotalAtomCount += count;
MonoisotopicMass += atomicInformation.ElementalIsotopesList[elementIndex].Isotopes[0].Mass * count;
AverageMass += atomicInformation.ElementalIsotopesList[elementIndex].AverageMass * count;
}
}
public void SetElementalIsotopeComposition(clsElementIsotopes isoComp)
{
ElementalIsotopeComposition = isoComp;
}
