public static int getBondCount(IChemFile file)
{
int count = 0;
for (int i = 0; i < file.ChemSequenceCount; i++)
{
count += ChemSequenceManipulator.getBondCount(file.getChemSequence(i));
}
return count;
}
/// <summary> Puts all the Molecules of this container together in one
/// AtomCcntainer.
///
/// </summary>
/// <returns> The AtomContainer with all the Molecules of this container
///
/// </returns>
/// <deprecated> This method has a serious performace impact. Try to use
/// other methods.
/// </deprecated>
public static IAtomContainer getAllInOneContainer(IChemFile file)
{
IAtomContainer container = file.Builder.newAtomContainer();
for (int i = 0; i < file.ChemSequenceCount; i++)
{
IChemSequence sequence = file.getChemSequence(i);
container.add(ChemSequenceManipulator.getAllInOneContainer(sequence));
}
return container;
}
// private procedures
/// <summary>
/// Private method that actually parses the input to read a <see cref="IChemFile"/> object.
/// </summary>
/// <returns>A ChemFile containing the data parsed from input.</returns>
private IChemFile ReadChemFile(IChemFile file)
{
IChemSequence chemSequence = file.Builder.NewChemSequence();
int number_of_atoms = 0;
try
{
string line;
while ((line = input.ReadLine()) != null)
{
// parse frame by frame
string token = line.Split('\t', ' ', ',', ';')[0];
number_of_atoms = int.Parse(token, NumberFormatInfo.InvariantInfo);
string info = input.ReadLine();
IChemModel chemModel = file.Builder.NewChemModel();
var setOfMolecules = file.Builder.NewAtomContainerSet();
IAtomContainer m = file.Builder.NewAtomContainer();
m.Title = info;
for (int i = 0; i < number_of_atoms; i++)
{
line = input.ReadLine();
if (line == null)
{
break;
}
if (line.StartsWithChar('#') && line.Length > 1)
{
var comment = m.GetProperty(CDKPropertyName.Comment, "");
comment = comment + line.Substring(1).Trim();
m.SetProperty(CDKPropertyName.Comment, comment);
Debug.WriteLine($"Found and set comment: {comment}");
i--; // a comment line does not count as an atom
}
else
{
double x = 0.0f, y = 0.0f, z = 0.0f;
double charge = 0.0f;
var tokenizer = Strings.Tokenize(line, '\t', ' ', ',', ';');
int fields = tokenizer.Count;
if (fields < 4)
{
// this is an error but cannot throw exception
}
else
{
string atomtype = tokenizer[0];
x = double.Parse(tokenizer[1], NumberFormatInfo.InvariantInfo);
y = double.Parse(tokenizer[2], NumberFormatInfo.InvariantInfo);
z = double.Parse(tokenizer[3], NumberFormatInfo.InvariantInfo);
if (fields == 8)
{
charge = double.Parse(tokenizer[4], NumberFormatInfo.InvariantInfo);
}
IAtom atom = file.Builder.NewAtom(atomtype, new Vector3(x, y, z));
atom.Charge = charge;
m.Atoms.Add(atom);
}
}
}
setOfMolecules.Add(m);
chemModel.MoleculeSet = setOfMolecules;
chemSequence.Add(chemModel);
line = input.ReadLine();
}
file.Add(chemSequence);
}
catch (IOException e)
{
// should make some noise now
file = null;
Trace.TraceError($"Error while reading file: {e.Message}");
Debug.WriteLine(e);
}
return(file);
}
public CMLCml CDKChemFileToCMLList(IChemFile file)
{
return(CDKChemFileToCMLList(file, true));
}
// private functions
private IChemFile readChemFile(IChemFile file)
{
//logger.debug("Started parsing from input...");
ChemFileCDO cdo = new ChemFileCDO(file);
try
{
parser.setFeature("http://xml.org/sax/features/validation", false);
//logger.info("Deactivated validation");
}
//UPGRADE_TODO: Class 'org.xml.sax.SAXException' was converted to 'System.Xml.XmlException' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073'"
catch (System.Xml.XmlException e)
{
//logger.warn("Cannot deactivate validation.");
return(cdo);
}
parser.setContentHandler(new CMLHandler((IChemicalDocumentObject)cdo));
parser.setEntityResolver(new CMLResolver());
//UPGRADE_TODO: Method 'org.xml.sax.XMLReader.setErrorHandler' was converted to 'XmlSAXDocumentManager.SetErrorHandler' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_orgxmlsaxXMLReadersetErrorHandler_orgxmlsaxErrorHandler'"
parser.setErrorHandler(new CMLErrorHandler());
try
{
if (input == null)
{
//logger.debug("Parsing from URL: ", url);
parser.parse(url);
}
else
{
//logger.debug("Parsing from Reader");
input.BaseStream.Seek(0, SeekOrigin.Begin);
parser.parse(new XmlSourceSupport(input));
}
}
catch (System.IO.IOException e)
{
//UPGRADE_TODO: The equivalent in .NET for method 'java.lang.Throwable.getMessage' may return a different value. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1043'"
System.String error = "Error while reading file: " + e.Message;
//logger.error(error);
//logger.debug(e);
throw new CDKException(error, e);
}
//UPGRADE_TODO: Class 'org.xml.sax.SAXParseException' was converted to 'System.xml.XmlException' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073'"
catch (System.Xml.XmlException saxe)
{
//UPGRADE_TODO: Class 'org.xml.sax.SAXParseException' was converted to 'System.xml.XmlException' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073'"
System.Xml.XmlException spe = (System.Xml.XmlException)saxe;
System.String error = "Found well-formedness error in line " + spe.LineNumber;
//logger.error(error);
//logger.debug(saxe);
throw new CDKException(error, saxe);
}
//UPGRADE_TODO: Class 'org.xml.sax.SAXException' was converted to 'System.Xml.XmlException' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073'"
//catch (System.Xml.XmlException saxe)
//{
// System.String error = "Error while parsing XML: " + saxe.Message;
// //logger.error(error);
// //logger.debug(saxe);
// throw new CDKException(error, saxe);
//}
return(cdo);
}
private void writeChemFile(IChemFile file)
{
IAtomContainer[] molecules = ChemFileManipulator.getAllAtomContainers(file);
for (int i = 0; i < molecules.Length; i++)
{
try
{
bool[] isVisible = new bool[molecules[i].AtomCount];
for (int k = 0; k < isVisible.Length; k++)
{
isVisible[k] = true;
}
writeMolecule(file.Builder.newMolecule(molecules[i]), isVisible);
}
catch (System.Exception exc)
{
}
}
}
/// <summary> Private method that actually parses the input to read a ChemFile
/// object. In its current state it is able to read all the molecules
/// (if more than one is present) in the specified HIN file. These are
/// placed in a SetOfMolecules object which in turn is placed in a ChemModel
/// which in turn is placed in a ChemSequence object and which is finally
/// placed in a ChemFile object and returned to the user.
///
/// </summary>
/// <returns> A ChemFile containing the data parsed from input.
/// </returns>
private IChemFile readChemFile(IChemFile file)
{
IChemSequence chemSequence = file.Builder.newChemSequence();
IChemModel chemModel = file.Builder.newChemModel();
ISetOfMolecules setOfMolecules = file.Builder.newSetOfMolecules();
System.String info;
SupportClass.Tokenizer tokenizer;
try
{
System.String line;
// read in header info
while (true)
{
line = input.ReadLine();
if (line.IndexOf("mol ") == 0)
{
info = getMolName(line);
break;
}
}
// start the actual molecule data - may be multiple molecule
line = input.ReadLine();
while (true)
{
if (line == null)
break; // end of file
if (line.IndexOf(';') == 0)
continue; // comment line
if (line.IndexOf("mol ") == 0)
{
info = getMolName(line);
line = input.ReadLine();
}
IMolecule m = file.Builder.newMolecule();
m.setProperty(CDKConstants.TITLE, info);
// Each elemnt of cons is an ArrayList of length 3 which stores
// the start and end indices and bond order of each bond
// found in the HIN file. Before adding bonds we need to reduce
// the number of bonds so as not to count the same bond twice
System.Collections.ArrayList cons = System.Collections.ArrayList.Synchronized(new System.Collections.ArrayList(10));
// read data for current molecule
int atomSerial = 0;
while (true)
{
if (line.IndexOf("endmol ") >= 0)
{
break;
}
if (line.IndexOf(';') == 0)
continue; // comment line
tokenizer = new SupportClass.Tokenizer(line, " ");
int ntoken = tokenizer.Count;
System.String[] toks = new System.String[ntoken];
for (int i = 0; i < ntoken; i++)
toks[i] = tokenizer.NextToken();
System.String sym = new System.Text.StringBuilder(toks[3]).ToString();
double charge = System.Double.Parse(toks[6]);
double x = System.Double.Parse(toks[7]);
double y = System.Double.Parse(toks[8]);
double z = System.Double.Parse(toks[9]);
int nbond = System.Int32.Parse(toks[10]);
IAtom atom = file.Builder.newAtom(sym, new Point3d(x, y, z));
atom.setCharge(charge);
for (int j = 11; j < (11 + nbond * 2); j += 2)
{
double bo = 1;
int s = System.Int32.Parse(toks[j]) - 1; // since atoms start from 1 in the file
char bt = toks[j + 1][0];
switch (bt)
{
case 's':
bo = 1;
break;
case 'd':
bo = 2;
break;
case 't':
bo = 3;
break;
case 'a':
bo = 1.5;
break;
}
System.Collections.ArrayList ar = new System.Collections.ArrayList(3);
ar.Add((System.Int32)atomSerial);
ar.Add((System.Int32)s);
ar.Add((double)bo);
cons.Add(ar);
}
m.addAtom(atom);
atomSerial++;
line = input.ReadLine();
}
// before storing the molecule lets include the connections
// First we reduce the number of bonds stored, since we have
// stored both, say, C1-H1 and H1-C1.
System.Collections.ArrayList blist = System.Collections.ArrayList.Synchronized(new System.Collections.ArrayList(10));
for (int i = 0; i < cons.Count; i++)
{
System.Collections.ArrayList ar = (System.Collections.ArrayList)cons[i];
// make a reversed list
System.Collections.ArrayList arev = new System.Collections.ArrayList(3);
arev.Add(ar[1]);
arev.Add(ar[0]);
arev.Add(ar[2]);
// Now see if ar or arev are already in blist
if (blist.Contains(ar) || blist.Contains(arev))
continue;
else
blist.Add(ar);
}
// now just store all the bonds we have
for (int i = 0; i < blist.Count; i++)
{
System.Collections.ArrayList ar = (System.Collections.ArrayList)blist[i];
int s = ((System.Int32)ar[0]);
int e = ((System.Int32)ar[1]);
double bo = ((System.Double)ar[2]);
m.addBond(s, e, bo);
}
setOfMolecules.addMolecule(m);
line = input.ReadLine(); // read in the 'mol N'
}
// got all the molecule in the HIN file (hopefully!)
chemModel.SetOfMolecules = setOfMolecules;
chemSequence.addChemModel(chemModel);
file.addChemSequence(chemSequence);
}
catch (System.IO.IOException e)
{
// should make some noise now
file = null;
}
return file;
}
/// <summary> Reads data from the "file system" file through the use of the "input"
/// field, parses data and feeds the ChemFile object with the extracted data.
///
/// </summary>
/// <returns> A ChemFile containing the data parsed from input.
///
/// </returns>
/// <throws IOException may> be thrown buy the <code>this.input.readLine()</code> instruction. </throws IOException may>
/// <summary>
/// </summary>
/// <seealso cref="org.openscience.cdk.io.GamessReader.input">
/// </seealso>
//TODO Answer the question : Is this method's name appropriate (given the fact that it do not read a ChemFile object, but return it)?
private IChemFile readChemFile(IChemFile file)
{
IChemSequence sequence = file.Builder.newChemSequence(); // TODO Answer the question : Is this line needed ?
IChemModel model = file.Builder.newChemModel(); // TODO Answer the question : Is this line needed ?
ISetOfMolecules moleculeSet = file.Builder.newSetOfMolecules();
model.SetOfMolecules = moleculeSet; //TODO Answer the question : Should I do this?
sequence.addChemModel(model); //TODO Answer the question : Should I do this?
file.addChemSequence(sequence); //TODO Answer the question : Should I do this?
System.String currentReadLine = this.input.ReadLine();
while (this.input.Peek() != -1 == true && (currentReadLine != null))
{
/*
* There are 2 types of coordinate sets:
* - bohr coordinates sets (if statement)
* - angstr???m coordinates sets (else statement)
*/
if (currentReadLine.IndexOf("COORDINATES (BOHR)") >= 0)
{
/*
* The following line do no contain data, so it is ignored.
*/
this.input.ReadLine();
moleculeSet.addMolecule(this.readCoordinates(file.Builder.newMolecule(), GamessReader.BOHR_UNIT));
//break; //<- stops when the first set of coordinates is found.
}
else if (currentReadLine.IndexOf(" COORDINATES OF ALL ATOMS ARE (ANGS)") >= 0)
{
/*
* The following 2 lines do no contain data, so it are ignored.
*/
this.input.ReadLine();
this.input.ReadLine();
moleculeSet.addMolecule(this.readCoordinates(file.Builder.newMolecule(), GamessReader.ANGSTROM_UNIT));
//break; //<- stops when the first set of coordinates is found.
}
currentReadLine = this.input.ReadLine();
}
return file;
}
public MDMoleculeConvention(IChemFile chemFile)
: base(chemFile)
{
}
public override ValidationReport ValidateChemFile(IChemFile subject)
{
return(ValidateChemFileNulls(subject));
}
public void TestMDMoleculeCustomizationRoundtripping()
{
StringWriter writer = new StringWriter();
CMLWriter cmlWriter = new CMLWriter(writer);
cmlWriter.RegisterCustomizer(new MDMoleculeCustomizer());
MDMolecule molecule = MakeMDBenzene();
cmlWriter.Write(molecule);
cmlWriter.Close();
string serializedMol = writer.ToString();
Debug.WriteLine("****************************** TestMDMoleculeCustomizationRoundtripping()");
Debug.WriteLine(serializedMol);
Debug.WriteLine("******************************");
Debug.WriteLine("****************************** testMDMoleculeCustomization Write first");
Debug.WriteLine(serializedMol);
Debug.WriteLine("******************************");
CMLReader reader = new CMLReader(new MemoryStream(Encoding.UTF8.GetBytes(serializedMol)));
reader.RegisterConvention("md:mdMolecule", new MDMoleculeConvention(builder.NewChemFile()));
IChemFile file = (IChemFile)reader.Read(builder.NewChemFile());
reader.Close();
var containers = ChemFileManipulator.GetAllAtomContainers(file).ToReadOnlyList();
Assert.AreEqual(1, containers.Count);
var molecule2 = containers[0];
Assert.IsTrue(molecule2 is MDMolecule);
MDMolecule mdMol = (MDMolecule)molecule2;
Assert.AreEqual(6, mdMol.Atoms.Count);
Assert.AreEqual(6, mdMol.Bonds.Count);
var residues = mdMol.GetResidues();
Assert.AreEqual(2, residues.Count);
Assert.AreEqual(3, ((Residue)residues[0]).Atoms.Count);
Assert.AreEqual(3, ((Residue)residues[1]).Atoms.Count);
Assert.AreEqual("myResidue1", ((Residue)residues[0]).Name);
Assert.AreEqual("myResidue2", ((Residue)residues[1]).Name);
Assert.AreEqual(0, ((Residue)residues[0]).GetNumber());
Assert.AreEqual(1, ((Residue)residues[1]).GetNumber());
var chargeGroup = mdMol.GetChargeGroups();
Assert.AreEqual(2, chargeGroup.Count);
Assert.AreEqual(2, ((ChargeGroup)chargeGroup[0]).Atoms.Count);
Assert.AreEqual(4, ((ChargeGroup)chargeGroup[1]).Atoms.Count);
Assert.IsNotNull(((ChargeGroup)chargeGroup[0]).GetSwitchingAtom());
Assert.AreEqual("a2", ((ChargeGroup)chargeGroup[0]).GetSwitchingAtom().Id);
Assert.IsNotNull(((ChargeGroup)chargeGroup[1]).GetSwitchingAtom());
Assert.AreEqual("a5", ((ChargeGroup)chargeGroup[1]).GetSwitchingAtom().Id);
Assert.AreEqual(2, ((ChargeGroup)chargeGroup[0]).GetNumber());
Assert.AreEqual(3, ((ChargeGroup)chargeGroup[1]).GetNumber());
writer = new StringWriter();
cmlWriter = new CMLWriter(writer);
cmlWriter.RegisterCustomizer(new MDMoleculeCustomizer());
cmlWriter.Write(mdMol);
cmlWriter.Close();
string serializedMDMol = writer.ToString();
Debug.WriteLine("****************************** TestMDMoleculeCustomizationRoundtripping()");
Debug.WriteLine(serializedMol);
Debug.WriteLine("******************************");
Debug.WriteLine("****************************** testMDMoleculeCustomization Write second");
Debug.WriteLine(serializedMDMol);
Debug.WriteLine("******************************");
Assert.AreEqual(serializedMol, serializedMDMol);
}
/// <summary>
/// Private method that actually parses the input to read a ChemFile
/// object. In its current state it is able to read all the molecules
/// (if more than one is present) in the specified HIN file. These are
/// placed in a MoleculeSet object which in turn is placed in a ChemModel
/// which in turn is placed in a ChemSequence object and which is finally
/// placed in a ChemFile object and returned to the user.
/// </summary>
/// <returns>A ChemFile containing the data parsed from input.</returns>
private IChemFile ReadChemFile(IChemFile file)
{
var chemSequence = file.Builder.NewChemSequence();
var chemModel = file.Builder.NewChemModel();
var setOfMolecules = file.Builder.NewAtomContainerSet();
string info;
var aroringText = new List <string>();
var mols = new List <IAtomContainer>();
try
{
string line;
// read in header info
while (true)
{
line = input.ReadLine();
if (line.StartsWith("mol", StringComparison.Ordinal))
{
info = GetMolName(line);
break;
}
}
// start the actual molecule data - may be multiple molecule
line = input.ReadLine();
while (true)
{
if (line == null)
{
break; // end of file
}
if (line.StartsWithChar(';'))
{
continue; // comment line
}
if (line.StartsWith("mol", StringComparison.Ordinal))
{
info = GetMolName(line);
line = input.ReadLine();
}
var m = file.Builder.NewAtomContainer();
m.Title = info;
// Each element of cons is an List of length 3 which stores
// the start and end indices and bond order of each bond
// found in the HIN file. Before adding bonds we need to reduce
// the number of bonds so as not to count the same bond twice
List <List <Object> > cons = new List <List <Object> >();
// read data for current molecule
int atomSerial = 0;
while (true)
{
if (line == null || line.Contains("endmol"))
{
break;
}
if (line.StartsWithChar(';'))
{
continue; // comment line
}
var toks = line.Split(' ');
var sym = toks[3];
var charge = double.Parse(toks[6], NumberFormatInfo.InvariantInfo);
var x = double.Parse(toks[7], NumberFormatInfo.InvariantInfo);
var y = double.Parse(toks[8], NumberFormatInfo.InvariantInfo);
var z = double.Parse(toks[9], NumberFormatInfo.InvariantInfo);
var nbond = int.Parse(toks[10], NumberFormatInfo.InvariantInfo);
var atom = file.Builder.NewAtom(sym, new Vector3(x, y, z));
atom.Charge = charge;
var bo = BondOrder.Single;
for (int j = 11; j < (11 + nbond * 2); j += 2)
{
var s = int.Parse(toks[j], NumberFormatInfo.InvariantInfo) - 1; // since atoms start from 1 in the file
var bt = toks[j + 1][0];
switch (bt)
{
case 's':
bo = BondOrder.Single;
break;
case 'd':
bo = BondOrder.Double;
break;
case 't':
bo = BondOrder.Triple;
break;
case 'a':
bo = BondOrder.Quadruple;
break;
}
var ar = new List <object>(3)
{
atomSerial,
s,
bo
};
cons.Add(ar);
}
m.Atoms.Add(atom);
atomSerial++;
line = input.ReadLine();
}
// now just store all the bonds we have
foreach (var ar in cons)
{
var s = m.Atoms[(int)ar[0]];
var e = m.Atoms[(int)ar[1]];
var bo = (BondOrder)ar[2];
if (!IsConnected(m, s, e))
{
m.Bonds.Add(file.Builder.NewBond(s, e, bo));
}
}
mols.Add(m);
// we may not get a 'mol N' immediately since
// the aromaticring keyword might be present
// and doesn't seem to be located within the molecule
// block. However, if we do see this keyword we save this
// since it can contain aromatic specs for any molecule
// listed in the file
//
// The docs do not explicitly state the the keyword comes
// after *all* molecules. So we save and then reprocess
// all the molecules in a second pass
while (true)
{
line = input.ReadLine();
if (line == null || line.StartsWith("mol", StringComparison.Ordinal))
{
break;
}
if (line.StartsWith("aromaticring", StringComparison.Ordinal))
{
aroringText.Add(line.Trim());
}
}
}
}
catch (IOException)
{
// FIXME: should make some noise now
file = null;
}
if (aroringText.Count > 0)
{ // process aromaticring annotations
foreach (var line in aroringText)
{
var toks = line.Split(' ');
var natom = int.Parse(toks[1], NumberFormatInfo.InvariantInfo);
int n = 0;
for (int i = 2; i < toks.Length; i += 2)
{
var molnum = int.Parse(toks[i], NumberFormatInfo.InvariantInfo); // starts from 1
var atnum = int.Parse(toks[i + 1], NumberFormatInfo.InvariantInfo); // starts from 1
mols[molnum - 1].Atoms[atnum - 1].IsAromatic = true;
n++;
}
Trace.Assert(n == natom);
}
}
foreach (var mol in mols)
{
setOfMolecules.Add(mol);
}
chemModel.MoleculeSet = setOfMolecules;
chemSequence.Add(chemModel);
file.Add(chemSequence);
return(file);
}
/// <summary>
/// Tests whether the file is indeed a single reaction file
/// </summary>
private IReaction CheckForSingleReactionFile(IChemFile chemFile)
{
return(CheckForXReactionFile(chemFile, 1));
}
/// <summary> Private method that actually parses the input to read a ChemFile
/// object.
///
/// </summary>
/// <returns> A ChemFile containing the data parsed from input.
/// </returns>
private IChemFile readChemFile(IChemFile file)
{
IChemSequence chemSequence = file.Builder.newChemSequence();
int number_of_atoms = 0;
SupportClass.Tokenizer tokenizer;
try
{
System.String line = input.ReadLine();
while (line.StartsWith("#"))
line = input.ReadLine();
/*while (input.ready() && line != null)
{*/
// System.out.println("lauf");
// parse frame by frame
tokenizer = new SupportClass.Tokenizer(line, "\t ,;");
System.String token = tokenizer.NextToken();
number_of_atoms = System.Int32.Parse(token);
System.String info = input.ReadLine();
IChemModel chemModel = file.Builder.newChemModel();
ISetOfMolecules setOfMolecules = file.Builder.newSetOfMolecules();
IMolecule m = file.Builder.newMolecule();
m.setProperty(CDKConstants.TITLE, info);
System.String[] types = new System.String[number_of_atoms];
double[] d = new double[number_of_atoms]; int[] d_atom = new int[number_of_atoms]; // Distances
double[] a = new double[number_of_atoms]; int[] a_atom = new int[number_of_atoms]; // Angles
double[] da = new double[number_of_atoms]; int[] da_atom = new int[number_of_atoms]; // Diederangles
//Point3d[] pos = new Point3d[number_of_atoms]; // calculated positions
int i = 0;
while (i < number_of_atoms)
{
line = input.ReadLine();
// System.out.println("line:\""+line+"\"");
if (line == null)
break;
if (line.StartsWith("#"))
{
// skip comment in file
}
else
{
d[i] = 0d; d_atom[i] = -1;
a[i] = 0d; a_atom[i] = -1;
da[i] = 0d; da_atom[i] = -1;
tokenizer = new SupportClass.Tokenizer(line, "\t ,;");
int fields = tokenizer.Count;
if (fields < System.Math.Min(i * 2 + 1, 7))
{
// this is an error but cannot throw exception
}
else if (i == 0)
{
types[i] = tokenizer.NextToken();
i++;
}
else if (i == 1)
{
types[i] = tokenizer.NextToken();
d_atom[i] = (System.Int32.Parse(tokenizer.NextToken())) - 1;
//UPGRADE_TODO: The differences in the format of parameters for constructor 'java.lang.Double.Double' may cause compilation errors. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1092'"
d[i] = (System.Double.Parse(tokenizer.NextToken()));
i++;
}
else if (i == 2)
{
types[i] = tokenizer.NextToken();
d_atom[i] = (System.Int32.Parse(tokenizer.NextToken())) - 1;
//UPGRADE_TODO: The differences in the format of parameters for constructor 'java.lang.Double.Double' may cause compilation errors. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1092'"
d[i] = (System.Double.Parse(tokenizer.NextToken()));
a_atom[i] = (System.Int32.Parse(tokenizer.NextToken())) - 1;
//UPGRADE_TODO: The differences in the format of parameters for constructor 'java.lang.Double.Double' may cause compilation errors. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1092'"
a[i] = (System.Double.Parse(tokenizer.NextToken()));
i++;
}
else
{
types[i] = tokenizer.NextToken();
d_atom[i] = (System.Int32.Parse(tokenizer.NextToken())) - 1;
//UPGRADE_TODO: The differences in the format of parameters for constructor 'java.lang.Double.Double' may cause compilation errors. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1092'"
d[i] = (System.Double.Parse(tokenizer.NextToken()));
a_atom[i] = (System.Int32.Parse(tokenizer.NextToken())) - 1;
//UPGRADE_TODO: The differences in the format of parameters for constructor 'java.lang.Double.Double' may cause compilation errors. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1092'"
a[i] = (System.Double.Parse(tokenizer.NextToken()));
da_atom[i] = (System.Int32.Parse(tokenizer.NextToken())) - 1;
//UPGRADE_TODO: The differences in the format of parameters for constructor 'java.lang.Double.Double' may cause compilation errors. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1092'"
da[i] = (System.Double.Parse(tokenizer.NextToken()));
i++;
}
}
}
// calculate cartesian coordinates
Point3d[] cartCoords = ZMatrixTools.zmatrixToCartesian(d, d_atom, a, a_atom, da, da_atom);
for (i = 0; i < number_of_atoms; i++)
{
m.addAtom(file.Builder.newAtom(types[i], cartCoords[i]));
}
// System.out.println("molecule:\n"+m);
setOfMolecules.addMolecule(m);
chemModel.SetOfMolecules = setOfMolecules;
chemSequence.addChemModel(chemModel);
line = input.ReadLine();
file.addChemSequence(chemSequence);
}
catch (System.IO.IOException e)
{
// should make some noise now
file = null;
}
return file;
}
/// <summary> Private method that actually parses the input to read a ChemFile
/// object. In its current state it is able to read all the molecules
/// (if more than one is present) in the specified HIN file. These are
/// placed in a SetOfMolecules object which in turn is placed in a ChemModel
/// which in turn is placed in a ChemSequence object and which is finally
/// placed in a ChemFile object and returned to the user.
///
/// </summary>
/// <returns> A ChemFile containing the data parsed from input.
/// </returns>
private IChemFile readChemFile(IChemFile file)
{
IChemSequence chemSequence = file.Builder.newChemSequence();
IChemModel chemModel = file.Builder.newChemModel();
ISetOfMolecules setOfMolecules = file.Builder.newSetOfMolecules();
System.String info;
SupportClass.Tokenizer tokenizer;
try
{
System.String line;
// read in header info
while (true)
{
line = input.ReadLine();
if (line.IndexOf("mol ") == 0)
{
info = getMolName(line);
break;
}
}
// start the actual molecule data - may be multiple molecule
line = input.ReadLine();
while (true)
{
if (line == null)
{
break; // end of file
}
if (line.IndexOf(';') == 0)
{
continue; // comment line
}
if (line.IndexOf("mol ") == 0)
{
info = getMolName(line);
line = input.ReadLine();
}
IMolecule m = file.Builder.newMolecule();
m.setProperty(CDKConstants.TITLE, info);
// Each elemnt of cons is an ArrayList of length 3 which stores
// the start and end indices and bond order of each bond
// found in the HIN file. Before adding bonds we need to reduce
// the number of bonds so as not to count the same bond twice
System.Collections.ArrayList cons = System.Collections.ArrayList.Synchronized(new System.Collections.ArrayList(10));
// read data for current molecule
int atomSerial = 0;
while (true)
{
if (line.IndexOf("endmol ") >= 0)
{
break;
}
if (line.IndexOf(';') == 0)
{
continue; // comment line
}
tokenizer = new SupportClass.Tokenizer(line, " ");
int ntoken = tokenizer.Count;
System.String[] toks = new System.String[ntoken];
for (int i = 0; i < ntoken; i++)
{
toks[i] = tokenizer.NextToken();
}
System.String sym = new System.Text.StringBuilder(toks[3]).ToString();
double charge = System.Double.Parse(toks[6]);
double x = System.Double.Parse(toks[7]);
double y = System.Double.Parse(toks[8]);
double z = System.Double.Parse(toks[9]);
int nbond = System.Int32.Parse(toks[10]);
IAtom atom = file.Builder.newAtom(sym, new Point3d(x, y, z));
atom.setCharge(charge);
for (int j = 11; j < (11 + nbond * 2); j += 2)
{
double bo = 1;
int s = System.Int32.Parse(toks[j]) - 1; // since atoms start from 1 in the file
char bt = toks[j + 1][0];
switch (bt)
{
case 's':
bo = 1;
break;
case 'd':
bo = 2;
break;
case 't':
bo = 3;
break;
case 'a':
bo = 1.5;
break;
}
System.Collections.ArrayList ar = new System.Collections.ArrayList(3);
ar.Add((System.Int32)atomSerial);
ar.Add((System.Int32)s);
ar.Add((double)bo);
cons.Add(ar);
}
m.addAtom(atom);
atomSerial++;
line = input.ReadLine();
}
// before storing the molecule lets include the connections
// First we reduce the number of bonds stored, since we have
// stored both, say, C1-H1 and H1-C1.
System.Collections.ArrayList blist = System.Collections.ArrayList.Synchronized(new System.Collections.ArrayList(10));
for (int i = 0; i < cons.Count; i++)
{
System.Collections.ArrayList ar = (System.Collections.ArrayList)cons[i];
// make a reversed list
System.Collections.ArrayList arev = new System.Collections.ArrayList(3);
arev.Add(ar[1]);
arev.Add(ar[0]);
arev.Add(ar[2]);
// Now see if ar or arev are already in blist
if (blist.Contains(ar) || blist.Contains(arev))
{
continue;
}
else
{
blist.Add(ar);
}
}
// now just store all the bonds we have
for (int i = 0; i < blist.Count; i++)
{
System.Collections.ArrayList ar = (System.Collections.ArrayList)blist[i];
int s = ((System.Int32)ar[0]);
int e = ((System.Int32)ar[1]);
double bo = ((System.Double)ar[2]);
m.addBond(s, e, bo);
}
setOfMolecules.addMolecule(m);
line = input.ReadLine(); // read in the 'mol N'
}
// got all the molecule in the HIN file (hopefully!)
chemModel.SetOfMolecules = setOfMolecules;
chemSequence.addChemModel(chemModel);
file.addChemSequence(chemSequence);
}
catch (System.IO.IOException e)
{
// should make some noise now
file = null;
}
return(file);
}
/// <summary> Read a <code>ChemFile</code> from a file in PDB format. The molecules
/// in the file are stored as <code>BioPolymer</code>s in the
/// <code>ChemFile</code>. The residues are the monomers of the
/// <code>BioPolymer</code>, and their names are the concatenation of the
/// residue, chain id, and the sequence number. Separate chains (denoted by
/// TER records) are stored as separate <code>BioPolymer</code> molecules.
///
/// <p>Connectivity information is not currently read.
///
/// </summary>
/// <returns> The ChemFile that was read from the PDB file.
/// </returns>
private IChemFile readChemFile(IChemFile oFile)
{
int bonds = 0;
// initialize all containers
IChemSequence oSeq = oFile.Builder.newChemSequence();
IChemModel oModel = oFile.Builder.newChemModel();
ISetOfMolecules oSet = oFile.Builder.newSetOfMolecules();
// some variables needed
string cCol;
PDBAtom oAtom;
PDBPolymer oBP = new PDBPolymer();
System.Text.StringBuilder cResidue;
string oObj;
IMonomer oMonomer;
string cRead = "";
char chain = 'A'; // To ensure stringent name giving of monomers
IStrand oStrand;
int lineLength = 0;
atomNumberMap = System.Collections.Hashtable.Synchronized(new System.Collections.Hashtable());
// do the reading of the Input
try
{
do
{
cRead = _oInput.ReadLine();
//logger.debug("Read line: ", cRead);
if (cRead != null)
{
lineLength = cRead.Length;
if (lineLength < 80)
{
//logger.warn("Line is not of the expected length 80!");
}
// make sure the record name is 6 characters long
if (lineLength < 6)
{
cRead = cRead + " ";
}
// check the first column to decide what to do
cCol = cRead.Substring(0, (6) - (0));
if ("ATOM ".ToUpper().Equals(cCol.ToUpper()))
{
// read an atom record
oAtom = readAtom(cRead, lineLength);
// construct a string describing the residue
cResidue = new System.Text.StringBuilder(8);
oObj = oAtom.ResName;
if (oObj != null)
{
cResidue = cResidue.Append(oObj.Trim());
}
oObj = oAtom.ChainID;
if (oObj != null)
{
// cResidue = cResidue.append(((String)oObj).trim());
cResidue = cResidue.Append(System.Convert.ToString(chain));
}
oObj = oAtom.ResSeq;
if (oObj != null)
{
cResidue = cResidue.Append(oObj.Trim());
}
// search for an existing strand or create a new one.
oStrand = oBP.getStrand(System.Convert.ToString(chain));
if (oStrand == null)
{
oStrand = new PDBStrand();
oStrand.StrandName = System.Convert.ToString(chain);
}
// search for an existing monomer or create a new one.
oMonomer = oBP.getMonomer(cResidue.ToString(), System.Convert.ToString(chain));
if (oMonomer == null)
{
PDBMonomer monomer = new PDBMonomer();
monomer.MonomerName = cResidue.ToString();
monomer.MonomerType = oAtom.ResName;
monomer.ChainID = oAtom.ChainID;
monomer.ICode = oAtom.ICode;
oMonomer = monomer;
}
// add the atom
oBP.addAtom(oAtom, oMonomer, oStrand);
System.Object tempObject;
//UPGRADE_WARNING: At least one expression was used more than once in the target code. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1181'"
tempObject = atomNumberMap[(System.Int32)oAtom.Serial];
atomNumberMap[(System.Int32)oAtom.Serial] = oAtom;
if (readConnect.Set && tempObject != null)
{
//logger.warn("Duplicate serial ID found for atom: ", oAtom);
}
// //logger.debug("Added ATOM: ", oAtom);
/** As HETATMs cannot be considered to either belong to a certain monomer or strand,
* they are dealt with seperately.*/
}
else if ("HETATM".ToUpper().Equals(cCol.ToUpper()))
{
// read an atom record
oAtom = readAtom(cRead, lineLength);
oAtom.HetAtom = true;
oBP.addAtom(oAtom);
System.Object tempObject2;
//UPGRADE_WARNING: At least one expression was used more than once in the target code. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1181'"
tempObject2 = atomNumberMap[(System.Int32)oAtom.Serial];
atomNumberMap[(System.Int32)oAtom.Serial] = oAtom;
if (tempObject2 != null)
{
//logger.warn("Duplicate serial ID found for atom: ", oAtom);
}
//logger.debug("Added HETATM: ", oAtom);
}
else if ("TER ".ToUpper().Equals(cCol.ToUpper()))
{
// start new strand
chain++;
oStrand = new PDBStrand();
oStrand.StrandName = System.Convert.ToString(chain);
//logger.debug("Added new STRAND");
}
else if ("END ".ToUpper().Equals(cCol.ToUpper()))
{
atomNumberMap.Clear();
// create bonds and finish the molecule
if (deduceBonding.Set)
{
// OK, try to deduce the bonding patterns
if (oBP.AtomCount != 0)
{
// Create bonds. If bonds could not be created, all bonds are deleted.
try
{
if (useRebondTool.Set)
{
if (!createBondsWithRebondTool(oBP))
{
// Get rid of all potentially created bonds.
//logger.info("Bonds could not be created using the RebondTool when PDB file was read.");
oBP.removeAllBonds();
}
}
else
{
if (!createBonds(oBP))
{
// Get rid of all potentially created bonds.
//logger.info("Bonds could not be created when PDB file was read.");
oBP.removeAllBonds();
}
}
}
catch (System.Exception exception)
{
//logger.info("Bonds could not be created when PDB file was read.");
//logger.debug(exception);
}
}
}
oSet.addMolecule(oBP);
// oBP = new BioPolymer();
// } else if (cCol.equals("USER ")) {
// System.out.println(cLine);
// System.out.println(cLine);
// } else if (cCol.equals("ENDMDL")) {
// System.out.println(cLine);
}
else if (cCol.Equals("MODEL "))
{
// OK, start a new model and save the current one first *if* it contains atoms
if (oBP.AtomCount > 0)
{
// save the model
oSet.addAtomContainer(oBP);
oModel.SetOfMolecules = oSet;
oSeq.addChemModel(oModel);
// setup a new one
oBP = new PDBPolymer();
oModel = oFile.Builder.newChemModel();
oSet = oFile.Builder.newSetOfMolecules();
}
}
else if ("REMARK".ToUpper().Equals(cCol.ToUpper()))
{
System.Object comment = oFile.getProperty(CDKConstants.COMMENT);
if (comment == null)
{
comment = "";
}
if (lineLength > 12)
{
//UPGRADE_TODO: The equivalent in .NET for method 'java.lang.Object.toString' may return a different value. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1043'"
comment = comment.ToString() + cRead.Substring(11).Trim() + "\n";
oFile.setProperty(CDKConstants.COMMENT, comment);
}
else
{
//logger.warn("REMARK line found without any comment!");
}
}
else if ("COMPND".ToUpper().Equals(cCol.ToUpper()))
{
string title = cRead.Substring(10).Trim();
oFile.setProperty(CDKConstants.TITLE, title);
}
/*************************************************************
* Read connectivity information from CONECT records.
* Only covalent bonds are dealt with. Perhaps salt bridges
* should be dealt with in the same way..?
*/
else if (readConnect.Set && "CONECT".ToUpper().Equals(cCol.ToUpper()))
{
cRead.Trim();
if (cRead.Length < 16)
{
//logger.debug("Skipping unexpected empty CONECT line! : ", cRead);
}
else
{
string bondAtom = cRead.Substring(7, 5).Trim();
int bondAtomNo = System.Int32.Parse(bondAtom);
for (int b = 0; b < 9; b += (b == 5 ? 2 : 1))
{
string bondedAtom = cRead.Substring((b * 5) + 11, 5).Trim();
int bondedAtomNo;
if (int.TryParse(bondedAtom, out bondedAtomNo))
{
bonds++;
addBond(oBP, bondAtomNo, bondedAtomNo);
}
}
//string bondedAtom = cRead.Substring(12, 5).Trim();
//int bondedAtomNo = -1;
//try
//{
// bondedAtomNo = System.Int32.Parse(bondedAtom);
//}
//catch (System.Exception e)
//{
// bondedAtomNo = -1;
//}
//if (bondedAtomNo != -1)
//{
// bonds++;
// addBond(oBP, bondAtomNo, bondedAtomNo);
// //logger.warn("Bonded " + bondAtomNo + " with " + bondedAtomNo);
//}
//else
//{
//}
//if (cRead.Length > 17)
//{
// bondedAtom = cRead.Substring(16, 5);
// bondedAtom = bondedAtom.Trim();
// try
// {
// bondedAtomNo = System.Int32.Parse(bondedAtom);
// }
// catch (System.Exception e)
// {
// bondedAtomNo = -1;
// }
// if (bondedAtomNo != -1)
// {
// bonds++;
// addBond(oBP, bondAtomNo, bondedAtomNo);
// //logger.warn("Bonded " + bondAtomNo + " with " + bondedAtomNo);
// }
//}
//if (cRead.Length > 22)
//{
// bondedAtom = cRead.Substring(22, 5);
// bondedAtom = bondedAtom.Trim();
// try
// {
// bondedAtomNo = System.Int32.Parse(bondedAtom);
// }
// catch (System.Exception e)
// {
// bondedAtomNo = -1;
// }
// if (bondedAtomNo != -1)
// {
// bonds++;
// addBond(oBP, bondAtomNo, bondedAtomNo);
// //logger.warn("Bonded " + bondAtomNo + " with " + bondedAtomNo);
// }
//}
//if (cRead.Length > 27)
//{
// bondedAtom = cRead.Substring(27, 5);
// bondedAtom = bondedAtom.Trim();
// try
// {
// bondedAtomNo = System.Int32.Parse(bondedAtom);
// }
// catch (System.Exception e)
// {
// bondedAtomNo = -1;
// }
// if (bondedAtomNo != -1)
// {
// bonds++;
// addBond(oBP, bondAtomNo, bondedAtomNo);
// //logger.warn("Bonded " + bondAtomNo + " with " + bondedAtomNo);
// }
//}
}
}
/*************************************************************/
else if ("HELIX ".ToUpper().Equals(cCol.ToUpper()))
{
// HELIX 1 H1A CYS A 11 LYS A 18 1 RESIDUE 18 HAS POSITIVE PHI 1D66 72
// 1 2 3 4 5 6 7
// 01234567890123456789012345678901234567890123456789012345678901234567890123456789
PDBStructure structure = new PDBStructure();
structure.StructureType = PDBStructure.HELIX;
structure.StartChainID = cRead[19];
structure.StartSequenceNumber = System.Int32.Parse(cRead.Substring(21, (25) - (21)).Trim());
structure.StartInsertionCode = cRead[25];
structure.EndChainID = cRead[31];
structure.EndSequenceNumber = System.Int32.Parse(cRead.Substring(33, (37) - (33)).Trim());
structure.EndInsertionCode = cRead[37];
oBP.addStructure(structure);
}
else if ("SHEET ".ToUpper().Equals(cCol.ToUpper()))
{
PDBStructure structure = new PDBStructure();
structure.StructureType = PDBStructure.SHEET;
structure.StartChainID = cRead[21];
structure.StartSequenceNumber = System.Int32.Parse(cRead.Substring(22, (26) - (22)).Trim());
structure.StartInsertionCode = cRead[26];
structure.EndChainID = cRead[32];
structure.EndSequenceNumber = System.Int32.Parse(cRead.Substring(33, (37) - (33)).Trim());
structure.EndInsertionCode = cRead[37];
oBP.addStructure(structure);
}
else if ("TURN ".ToUpper().Equals(cCol.ToUpper()))
{
PDBStructure structure = new PDBStructure();
structure.StructureType = PDBStructure.TURN;
structure.StartChainID = cRead[19];
structure.StartSequenceNumber = System.Int32.Parse(cRead.Substring(20, (24) - (20)).Trim());
structure.StartInsertionCode = cRead[24];
structure.EndChainID = cRead[30];
structure.EndSequenceNumber = System.Int32.Parse(cRead.Substring(31, (35) - (31)).Trim());
structure.EndInsertionCode = cRead[35];
oBP.addStructure(structure);
} // ignore all other commands
}
}
while (_oInput.Peek() != -1 && (cRead != null));
}
catch (System.Exception e)
{
//logger.error("Found a problem at line:\n");
//logger.error(cRead);
//logger.error("01234567890123456789012345678901234567890123456789012345678901234567890123456789");
//logger.error(" 1 2 3 4 5 6 7 ");
//UPGRADE_TODO: The equivalent in .NET for method 'java.lang.Throwable.getMessage' may return a different value. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1043'"
//logger.error(" error: " + e.Message);
//logger.debug(e);
}
// try to close the Input
try
{
_oInput.Close();
}
catch (System.Exception e)
{
//logger.debug(e);
}
// Set all the dependencies
oModel.SetOfMolecules = oSet;
oSeq.addChemModel(oModel);
oFile.addChemSequence(oSeq);
return oFile;
}
/// <summary> Read the ShelX from input. Each ShelX document is expected to contain
/// one crystal structure.
///
/// </summary>
/// <returns> a ChemFile with the coordinates, charges, vectors, etc.
/// </returns>
private IChemFile readChemFile(IChemFile file)
{
IChemSequence seq = file.Builder.newChemSequence();
IChemModel model = file.Builder.newChemModel();
crystal = file.Builder.newCrystal();
System.String line = input.ReadLine();
bool end_found = false;
while (input.Peek() != -1 && line != null && !end_found)
{
if (line.StartsWith("#"))
{
//logger.warn("Skipping comment: " + line);
// skip comment lines
}
else if (line.Length == 0)
{
//logger.debug("Skipping empty line");
// skip empty lines
}
else if (!(line.StartsWith("_") || line.StartsWith("loop_")))
{
//logger.warn("Skipping unrecognized line: " + line);
// skip line
}
else
{
/* determine CIF command */
System.String command = "";
int spaceIndex = line.IndexOf(" ");
if (spaceIndex != -1)
{
// everything upto space is command
try
{
command = new System.Text.StringBuilder(line.Substring(0, (spaceIndex) - (0))).ToString();
}
catch (System.ArgumentOutOfRangeException sioobe)
{
// disregard this line
break;
}
}
else
{
// complete line is command
command = line;
}
//logger.debug("command: " + command);
if (command.StartsWith("_cell"))
{
processCellParameter(command, line);
}
else if (command.Equals("loop_"))
{
processLoopBlock();
}
else if (command.Equals("_symmetry_space_group_name_H-M"))
{
System.String value_Renamed = line.Substring(29).Trim();
crystal.SpaceGroup = value_Renamed;
}
else
{
// skip command
//logger.warn("Skipping command: " + command);
line = input.ReadLine();
if (line.StartsWith(";"))
{
//logger.debug("Skipping block content");
line = input.ReadLine().Trim();
while (!line.Equals(";"))
{
line = input.ReadLine().Trim();
//logger.debug("Skipping block line: " + line);
}
line = input.ReadLine();
}
}
}
line = input.ReadLine();
}
//logger.info("Adding crystal to file with #atoms: " + crystal.AtomCount);
model.Crystal = crystal;
seq.addChemModel(model);
file.addChemSequence(seq);
return file;
}
public JMOLANIMATIONConvention(IChemFile chemFile)
: base(chemFile)
{
current = Unknown;
}
private IChemFile readChemFile(IChemFile file)
{
IChemSequence seq = readChemSequence(file.Builder.newChemSequence());
file.addChemSequence(seq);
return file;
}
/// <summary> Read the Gaussian98 output.
///
/// </summary>
/// <returns> a ChemFile with the coordinates, energies, and
/// vibrations.
/// </returns>
/// <throws> IOException if an I/O error occurs </throws>
/// <throws> CDKException Description of the Exception </throws>
private IChemFile readChemFile(IChemFile chemFile)
{
IChemSequence sequence = chemFile.Builder.newChemSequence();
IChemModel model = null;
System.String line = input.ReadLine();
System.String levelOfTheory;
System.String description;
int modelCounter = 0;
// Find first set of coordinates by skipping all before "Standard orientation"
while (input.Peek() != -1 && (line != null))
{
if (line.IndexOf("Standard orientation:") >= 0)
{
// Found a set of coordinates
model = chemFile.Builder.newChemModel();
readCoordinates(model);
break;
}
line = input.ReadLine();
}
if (model != null)
{
// Read all other data
line = input.ReadLine().Trim();
while (input.Peek() != -1 && (line != null))
{
if (line.IndexOf("#") == 0)
{
// Found the route section
// Memorizing this for the description of the chemmodel
lastRoute = line;
modelCounter = 0;
}
else if (line.IndexOf("Standard orientation:") >= 0)
{
// Found a set of coordinates
// Add current frame to file and create a new one.
if (!readOptimizedStructureOnly.Set)
{
sequence.addChemModel(model);
}
else
{
//logger.info("Skipping frame, because I was told to do");
}
fireFrameRead();
model = chemFile.Builder.newChemModel();
modelCounter++;
readCoordinates(model);
}
else if (line.IndexOf("SCF Done:") >= 0)
{
// Found an energy
model.setProperty(CDKConstants.REMARK, line.Trim());
}
else if (line.IndexOf("Harmonic frequencies") >= 0)
{
// Found a set of vibrations
// readFrequencies(frame);
}
else if (line.IndexOf("Total atomic charges") >= 0)
{
readPartialCharges(model);
}
else if (line.IndexOf("Magnetic shielding") >= 0)
{
// Found NMR data
readNMRData(model, line);
}
else if (line.IndexOf("GINC") >= 0)
{
// Found calculation level of theory
levelOfTheory = parseLevelOfTheory(line);
//logger.debug("Level of Theory for this model: " + levelOfTheory);
description = lastRoute + ", model no. " + modelCounter;
model.setProperty(CDKConstants.DESCRIPTION, description);
}
else
{
////logger.debug("Skipping line: " + line);
}
line = input.ReadLine();
}
// Add last frame to file
sequence.addChemModel(model);
fireFrameRead();
}
chemFile.addChemSequence(sequence);
return chemFile;
}
/// <summary> Returns all the AtomContainer's of a ChemFile.</summary>
public static IAtomContainer[] getAllAtomContainers(IChemFile file)
{
IChemSequence[] sequences = file.ChemSequences;
int acCount = 0;
System.Collections.ArrayList acArrays = System.Collections.ArrayList.Synchronized(new System.Collections.ArrayList(10));
for (int i = 0; i < sequences.Length; i++)
{
IAtomContainer[] sequenceContainers = ChemSequenceManipulator.getAllAtomContainers(sequences[i]);
acArrays.Add(sequenceContainers);
acCount += sequenceContainers.Length;
}
IAtomContainer[] containers = new IAtomContainer[acCount];
int arrayOffset = 0;
//UPGRADE_TODO: Method 'java.util.Enumeration.hasMoreElements' was converted to 'System.Collections.IEnumerator.MoveNext' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javautilEnumerationhasMoreElements'"
for (System.Collections.IEnumerator acArraysElements = acArrays.GetEnumerator(); acArraysElements.MoveNext(); )
{
//UPGRADE_TODO: Method 'java.util.Enumeration.nextElement' was converted to 'System.Collections.IEnumerator.Current' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_javautilEnumerationnextElement'"
IAtomContainer[] modelContainers = (IAtomContainer[])acArraysElements.Current;
Array.Copy(modelContainers, 0, containers, arrayOffset, modelContainers.Length);
arrayOffset += modelContainers.Length;
}
return containers;
}
/// <summary> Private method that actually parses the input to read a ChemFile
/// object.
///
/// </summary>
/// <returns> A ChemFile containing the data parsed from input.
/// </returns>
private IChemFile readChemFile(IChemFile file)
{
IChemSequence chemSequence = file.Builder.newChemSequence();
int number_of_atoms = 0;
SupportClass.Tokenizer tokenizer;
try
{
System.String line = input.ReadLine();
while (line.StartsWith("#"))
{
line = input.ReadLine();
}
/*while (input.ready() && line != null)
* {*/
// System.out.println("lauf");
// parse frame by frame
tokenizer = new SupportClass.Tokenizer(line, "\t ,;");
System.String token = tokenizer.NextToken();
number_of_atoms = System.Int32.Parse(token);
System.String info = input.ReadLine();
IChemModel chemModel = file.Builder.newChemModel();
ISetOfMolecules setOfMolecules = file.Builder.newSetOfMolecules();
IMolecule m = file.Builder.newMolecule();
m.setProperty(CDKConstants.TITLE, info);
System.String[] types = new System.String[number_of_atoms];
double[] d = new double[number_of_atoms]; int[] d_atom = new int[number_of_atoms]; // Distances
double[] a = new double[number_of_atoms]; int[] a_atom = new int[number_of_atoms]; // Angles
double[] da = new double[number_of_atoms]; int[] da_atom = new int[number_of_atoms]; // Diederangles
//Point3d[] pos = new Point3d[number_of_atoms]; // calculated positions
int i = 0;
while (i < number_of_atoms)
{
line = input.ReadLine();
// System.out.println("line:\""+line+"\"");
if (line == null)
{
break;
}
if (line.StartsWith("#"))
{
// skip comment in file
}
else
{
d[i] = 0d; d_atom[i] = -1;
a[i] = 0d; a_atom[i] = -1;
da[i] = 0d; da_atom[i] = -1;
tokenizer = new SupportClass.Tokenizer(line, "\t ,;");
int fields = tokenizer.Count;
if (fields < System.Math.Min(i * 2 + 1, 7))
{
// this is an error but cannot throw exception
}
else if (i == 0)
{
types[i] = tokenizer.NextToken();
i++;
}
else if (i == 1)
{
types[i] = tokenizer.NextToken();
d_atom[i] = (System.Int32.Parse(tokenizer.NextToken())) - 1;
//UPGRADE_TODO: The differences in the format of parameters for constructor 'java.lang.Double.Double' may cause compilation errors. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1092'"
d[i] = (System.Double.Parse(tokenizer.NextToken()));
i++;
}
else if (i == 2)
{
types[i] = tokenizer.NextToken();
d_atom[i] = (System.Int32.Parse(tokenizer.NextToken())) - 1;
//UPGRADE_TODO: The differences in the format of parameters for constructor 'java.lang.Double.Double' may cause compilation errors. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1092'"
d[i] = (System.Double.Parse(tokenizer.NextToken()));
a_atom[i] = (System.Int32.Parse(tokenizer.NextToken())) - 1;
//UPGRADE_TODO: The differences in the format of parameters for constructor 'java.lang.Double.Double' may cause compilation errors. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1092'"
a[i] = (System.Double.Parse(tokenizer.NextToken()));
i++;
}
else
{
types[i] = tokenizer.NextToken();
d_atom[i] = (System.Int32.Parse(tokenizer.NextToken())) - 1;
//UPGRADE_TODO: The differences in the format of parameters for constructor 'java.lang.Double.Double' may cause compilation errors. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1092'"
d[i] = (System.Double.Parse(tokenizer.NextToken()));
a_atom[i] = (System.Int32.Parse(tokenizer.NextToken())) - 1;
//UPGRADE_TODO: The differences in the format of parameters for constructor 'java.lang.Double.Double' may cause compilation errors. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1092'"
a[i] = (System.Double.Parse(tokenizer.NextToken()));
da_atom[i] = (System.Int32.Parse(tokenizer.NextToken())) - 1;
//UPGRADE_TODO: The differences in the format of parameters for constructor 'java.lang.Double.Double' may cause compilation errors. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1092'"
da[i] = (System.Double.Parse(tokenizer.NextToken()));
i++;
}
}
}
// calculate cartesian coordinates
Point3d[] cartCoords = ZMatrixTools.zmatrixToCartesian(d, d_atom, a, a_atom, da, da_atom);
for (i = 0; i < number_of_atoms; i++)
{
m.addAtom(file.Builder.newAtom(types[i], cartCoords[i]));
}
// System.out.println("molecule:\n"+m);
setOfMolecules.addMolecule(m);
chemModel.SetOfMolecules = setOfMolecules;
chemSequence.addChemModel(chemModel);
line = input.ReadLine();
file.addChemSequence(chemSequence);
}
catch (System.IO.IOException e)
{
// should make some noise now
file = null;
}
return(file);
}
/// <summary> Returns a List of all IChemObject in this ChemFile.
///
/// </summary>
/// <returns> A list of all ChemObjects
/// </returns>
public static System.Collections.IList getAllChemObjects(IChemFile file)
{
System.Collections.ArrayList list = new System.Collections.ArrayList();
list.Add(file);
for (int i = 0; i < file.ChemSequenceCount; i++)
{
list.AddRange(ChemSequenceManipulator.getAllChemObjects(file.getChemSequence(i)));
}
return list;
}
private void LoadOutline(IChemFile root)
{
outlineTreeView.Nodes.Clear();
TreeNode rootNode = new TreeNode(root.GetType().Name + ":" + root.ID);
BuildNodes(rootNode, root.ChemSequences);
outlineTreeView.Nodes.Add(rootNode);
}
/// <summary>
/// Read the ShelX from input. Each ShelX document is expected to contain one crystal structure.
/// </summary>
/// <param name="file"></param>
/// <returns>a ChemFile with the coordinates, charges, vectors, etc.</returns>
private IChemFile ReadChemFile(IChemFile file)
{
IChemSequence seq = file.Builder.NewChemSequence();
IChemModel model = file.Builder.NewChemModel();
crystal = file.Builder.NewCrystal();
string line = input.ReadLine();
bool end_found = false;
while (input.Ready() && line != null && !end_found)
{
if (line.Length == 0)
{
Debug.WriteLine("Skipping empty line");
// skip empty lines
}
else if (line[0] == '#')
{
Trace.TraceWarning("Skipping comment: " + line);
// skip comment lines
}
else if (!(line[0] == '_' || line.StartsWith("loop_", StringComparison.Ordinal)))
{
Trace.TraceWarning("Skipping unrecognized line: " + line);
// skip line
}
else
{
/* determine CIF command */
string command = "";
int spaceIndex = line.IndexOf(' ');
if (spaceIndex != -1)
{
// everything upto space is command
try
{
command = line.Substring(0, spaceIndex);
}
catch (ArgumentOutOfRangeException)
{
// disregard this line
break;
}
}
else
{
// complete line is command
command = line;
}
Debug.WriteLine($"command: {command}");
if (command.StartsWith("_cell", StringComparison.Ordinal))
{
ProcessCellParameter(command, line);
}
else if (string.Equals(command, "loop_", StringComparison.Ordinal))
{
line = ProcessLoopBlock();
continue;
}
else if (string.Equals(command, "_symmetry_space_group_name_H-M", StringComparison.Ordinal))
{
string value = line.Substring(29).Trim();
crystal.SpaceGroup = value;
}
else
{
// skip command
Trace.TraceWarning("Skipping command: " + command);
line = input.ReadLine();
if (line.StartsWithChar(';'))
{
Debug.WriteLine("Skipping block content");
line = input.ReadLine();
if (line != null)
{
line = line.Trim();
}
while (!string.Equals(line, ";", StringComparison.Ordinal))
{
line = input.ReadLine();
if (line != null)
{
line = line.Trim();
}
Debug.WriteLine($"Skipping block line: {line}");
}
line = input.ReadLine();
}
}
}
line = input.ReadLine();
}
Trace.TraceInformation("Adding crystal to file with #atoms: " + crystal.Atoms.Count);
model.Crystal = crystal;
seq.Add(model);
file.Add(seq);
return(file);
}
/// <summary>
/// Private method that actually parses the input to read a <see cref="IChemFile"/> object.
/// </summary>
/// <param name="file">the file to read from</param>
/// <returns>A ChemFile containing the data parsed from input.</returns>
private IChemFile ReadChemFile(IChemFile file)
{
IChemSequence chemSequence = file.Builder.NewChemSequence();
int number_of_atoms;
try
{
string line = input.ReadLine();
while (line.StartsWithChar('#'))
{
line = input.ReadLine();
}
// while (input.Ready() && line != null) {
// Debug.WriteLine("lauf");
// parse frame by frame
string token = Strings.Tokenize(line, '\t', ' ', ',', ';')[0];
number_of_atoms = int.Parse(token, NumberFormatInfo.InvariantInfo);
string info = input.ReadLine();
IChemModel chemModel = file.Builder.NewChemModel();
var setOfMolecules = file.Builder.NewAtomContainerSet();
IAtomContainer m = file.Builder.NewAtomContainer();
m.Title = info;
string[] types = new string[number_of_atoms];
double[] d = new double[number_of_atoms];
int[] d_atom = new int[number_of_atoms]; // Distances
double[] a = new double[number_of_atoms];
int[] a_atom = new int[number_of_atoms]; // Angles
double[] da = new double[number_of_atoms];
int[] da_atom = new int[number_of_atoms]; // Diederangles
//Vector3[] pos = new Vector3[number_of_atoms]; // calculated positions
int i = 0;
while (i < number_of_atoms)
{
line = input.ReadLine();
// Debug.WriteLine("line:\""+line+"\"");
if (line == null)
{
break;
}
if (line.StartsWithChar('#'))
{
// skip comment in file
}
else
{
d[i] = 0d;
d_atom[i] = -1;
a[i] = 0d;
a_atom[i] = -1;
da[i] = 0d;
da_atom[i] = -1;
var tokens = Strings.Tokenize(line, '\t', ' ', ',', ';');
int fields = int.Parse(tokens[0], NumberFormatInfo.InvariantInfo);
if (fields < Math.Min(i * 2 + 1, 7))
{
// this is an error but cannot throw exception
}
else if (i == 0)
{
types[i] = tokens[1];
i++;
}
else if (i == 1)
{
types[i] = tokens[1];
d_atom[i] = int.Parse(tokens[2], NumberFormatInfo.InvariantInfo) - 1;
d[i] = double.Parse(tokens[3], NumberFormatInfo.InvariantInfo);
i++;
}
else if (i == 2)
{
types[i] = tokens[1];
d_atom[i] = int.Parse(tokens[2], NumberFormatInfo.InvariantInfo) - 1;
d[i] = double.Parse(tokens[3], NumberFormatInfo.InvariantInfo);
a_atom[i] = int.Parse(tokens[4], NumberFormatInfo.InvariantInfo) - 1;
a[i] = double.Parse(tokens[5], NumberFormatInfo.InvariantInfo);
i++;
}
else
{
types[i] = tokens[1];
d_atom[i] = int.Parse(tokens[2], NumberFormatInfo.InvariantInfo) - 1;
d[i] = double.Parse(tokens[3], NumberFormatInfo.InvariantInfo);
a_atom[i] = int.Parse(tokens[4], NumberFormatInfo.InvariantInfo) - 1;
a[i] = double.Parse(tokens[5], NumberFormatInfo.InvariantInfo);
da_atom[i] = int.Parse(tokens[6], NumberFormatInfo.InvariantInfo) - 1;
da[i] = double.Parse(tokens[7], NumberFormatInfo.InvariantInfo);
i++;
}
}
}
// calculate cartesian coordinates
var cartCoords = ZMatrixTools.ZMatrixToCartesian(d, d_atom, a, a_atom, da, da_atom);
for (i = 0; i < number_of_atoms; i++)
{
m.Atoms.Add(file.Builder.NewAtom(types[i], cartCoords[i]));
}
// Debug.WriteLine("molecule:"+m);
setOfMolecules.Add(m);
chemModel.MoleculeSet = setOfMolecules;
chemSequence.Add(chemModel);
line = input.ReadLine();
file.Add(chemSequence);
}
catch (IOException)
{
// should make some noise now
file = null;
}
return(file);
}
// private functions
private IChemFile readChemFile(IChemFile file)
{
//logger.debug("Started parsing from input...");
ChemFileCDO cdo = new ChemFileCDO(file);
try
{
parser.setFeature("http://xml.org/sax/features/validation", false);
//logger.info("Deactivated validation");
}
//UPGRADE_TODO: Class 'org.xml.sax.SAXException' was converted to 'System.Xml.XmlException' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073'"
catch (System.Xml.XmlException e)
{
//logger.warn("Cannot deactivate validation.");
return cdo;
}
parser.setContentHandler(new CMLHandler((IChemicalDocumentObject)cdo));
parser.setEntityResolver(new CMLResolver());
//UPGRADE_TODO: Method 'org.xml.sax.XMLReader.setErrorHandler' was converted to 'XmlSAXDocumentManager.SetErrorHandler' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073_orgxmlsaxXMLReadersetErrorHandler_orgxmlsaxErrorHandler'"
parser.setErrorHandler(new CMLErrorHandler());
try
{
if (input == null)
{
//logger.debug("Parsing from URL: ", url);
parser.parse(url);
}
else
{
//logger.debug("Parsing from Reader");
input.BaseStream.Seek(0, SeekOrigin.Begin);
parser.parse(new XmlSourceSupport(input));
}
}
catch (System.IO.IOException e)
{
//UPGRADE_TODO: The equivalent in .NET for method 'java.lang.Throwable.getMessage' may return a different value. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1043'"
System.String error = "Error while reading file: " + e.Message;
//logger.error(error);
//logger.debug(e);
throw new CDKException(error, e);
}
//UPGRADE_TODO: Class 'org.xml.sax.SAXParseException' was converted to 'System.xml.XmlException' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073'"
catch (System.Xml.XmlException saxe)
{
//UPGRADE_TODO: Class 'org.xml.sax.SAXParseException' was converted to 'System.xml.XmlException' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073'"
System.Xml.XmlException spe = (System.Xml.XmlException)saxe;
System.String error = "Found well-formedness error in line " + spe.LineNumber;
//logger.error(error);
//logger.debug(saxe);
throw new CDKException(error, saxe);
}
//UPGRADE_TODO: Class 'org.xml.sax.SAXException' was converted to 'System.Xml.XmlException' which has a different behavior. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1073'"
//catch (System.Xml.XmlException saxe)
//{
// System.String error = "Error while parsing XML: " + saxe.Message;
// //logger.error(error);
// //logger.debug(saxe);
// throw new CDKException(error, saxe);
//}
return cdo;
}
private IChemFile readChemFile(IChemFile file)
{
IChemSequence seq = file.Builder.newChemSequence();
IChemModel model = file.Builder.newChemModel();
ICrystal crystal = null;
int lineNumber = 0;
Vector3d a, b, c;
try
{
System.String line = input.ReadLine();
while (input.Peek() != -1 && line != null)
{
//logger.debug((lineNumber++) + ": ", line);
if (line.StartsWith("frame:"))
{
//logger.debug("found new frame");
model = file.Builder.newChemModel();
crystal = file.Builder.newCrystal();
// assume the file format is correct
//logger.debug("reading spacegroup");
line = input.ReadLine();
//logger.debug((lineNumber++) + ": ", line);
crystal.SpaceGroup = line;
//logger.debug("reading unit cell axes");
Vector3d axis = new Vector3d();
//logger.debug("parsing A: ");
line = input.ReadLine();
//logger.debug((lineNumber++) + ": ", line);
axis.x = FortranFormat.atof(line);
line = input.ReadLine();
//logger.debug((lineNumber++) + ": ", line);
axis.y = FortranFormat.atof(line);
line = input.ReadLine();
//logger.debug((lineNumber++) + ": ", line);
axis.z = FortranFormat.atof(line);
crystal.A = axis;
axis = new Vector3d();
//logger.debug("parsing B: ");
line = input.ReadLine();
//logger.debug((lineNumber++) + ": ", line);
axis.x = FortranFormat.atof(line);
line = input.ReadLine();
//logger.debug((lineNumber++) + ": ", line);
axis.y = FortranFormat.atof(line);
line = input.ReadLine();
//logger.debug((lineNumber++) + ": ", line);
axis.z = FortranFormat.atof(line);
crystal.B = axis;
axis = new Vector3d();
//logger.debug("parsing C: ");
line = input.ReadLine();
//logger.debug((lineNumber++) + ": ", line);
axis.x = FortranFormat.atof(line);
line = input.ReadLine();
//logger.debug((lineNumber++) + ": ", line);
axis.y = FortranFormat.atof(line);
line = input.ReadLine();
//logger.debug((lineNumber++) + ": ", line);
axis.z = FortranFormat.atof(line);
crystal.C = axis;
//logger.debug("Crystal: ", crystal);
a = crystal.A;
b = crystal.B;
c = crystal.C;
//logger.debug("Reading number of atoms");
line = input.ReadLine();
//logger.debug((lineNumber++) + ": ", line);
int atomsToRead = System.Int32.Parse(line);
//logger.debug("Reading no molecules in assym unit cell");
line = input.ReadLine();
//logger.debug((lineNumber++) + ": ", line);
int Z = System.Int32.Parse(line);
crystal.Z = Z;
System.String symbol;
double charge;
Point3d cart;
for (int i = 1; i <= atomsToRead; i++)
{
cart = new Point3d();
line = input.ReadLine();
//logger.debug((lineNumber++) + ": ", line);
symbol = line.Substring(0, (line.IndexOf(":")) - (0));
charge = System.Double.Parse(line.Substring(line.IndexOf(":") + 1));
line = input.ReadLine();
//logger.debug((lineNumber++) + ": ", line);
cart.x = System.Double.Parse(line); // x
line = input.ReadLine();
//logger.debug((lineNumber++) + ": ", line);
cart.y = System.Double.Parse(line); // y
line = input.ReadLine();
//logger.debug((lineNumber++) + ": ", line);
cart.z = System.Double.Parse(line); // z
IAtom atom = file.Builder.newAtom(symbol);
atom.setCharge(charge);
// convert cartesian coords to fractional
Point3d frac = CrystalGeometryTools.cartesianToFractional(a, b, c, cart);
atom.setFractionalPoint3d(frac);
crystal.addAtom(atom);
//logger.debug("Added atom: ", atom);
}
model.Crystal = crystal;
seq.addChemModel(model);
}
else
{
//logger.debug("Format seems broken. Skipping these lines:");
while (!line.StartsWith("frame:") && input.Peek() != -1 && line != null)
{
line = input.ReadLine();
//logger.debug(lineNumber++ + ": ", line);
}
//logger.debug("Ok, resynched: found new frame");
}
}
file.addChemSequence(seq);
}
catch (System.Exception exception)
{
//UPGRADE_TODO: The equivalent in .NET for method 'java.lang.Throwable.getMessage' may return a different value. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1043'"
System.String message = "Error while parsing CrystClust file: " + exception.Message;
//logger.error(message);
//logger.debug(exception);
throw new CDKException(message, exception);
}
return(file);
}
#pragma warning disable CA1810 // Initialize reference type static fields inline
static AminoAcids()
#pragma warning restore CA1810 // Initialize reference type static fields inline
{
// Create set of AtomContainers
proteinogenics = new IAminoAcid[20];
#region Create proteinogenics
{
IChemFile list = CDK.Builder.NewChemFile();
using (var reader = new CMLReader(ResourceLoader.GetAsStream("NCDK.Templates.Data.list_aminoacids.cml")))
{
try
{
list = (IChemFile)reader.Read(list);
var containersList = ChemFileManipulator.GetAllAtomContainers(list);
int counter = 0;
foreach (var ac in containersList)
{
Debug.WriteLine($"Adding AA: {ac}");
// convert into an AminoAcid
var aminoAcid = CDK.Builder.NewAminoAcid();
foreach (var next in ac.GetProperties().Keys)
{
Debug.WriteLine("Prop: " + next.ToString());
if (next is DictRef dictRef)
{
// Debug.WriteLine("DictRef type: " + dictRef.Type}");
if (string.Equals(dictRef.Type, "pdb:residueName", StringComparison.Ordinal))
{
aminoAcid.SetProperty(ResidueNameKey, ac.GetProperty <string>(next).ToUpperInvariant());
aminoAcid.MonomerName = ac.GetProperty <string>(next);
}
else if (string.Equals(dictRef.Type, "pdb:oneLetterCode", StringComparison.Ordinal))
{
aminoAcid.SetProperty(ResidueNameShortKey, ac.GetProperty <string>(next));
}
else if (string.Equals(dictRef.Type, "pdb:id", StringComparison.Ordinal))
{
aminoAcid.SetProperty(IdKey, ac.GetProperty <string>(next));
Debug.WriteLine($"Set AA ID to: {ac.GetProperty<string>(next)}");
}
else
{
Trace.TraceError("Cannot deal with dictRef!");
}
}
}
foreach (var atom in ac.Atoms)
{
string dictRef = atom.GetProperty <string>("org.openscience.cdk.dict");
switch (dictRef)
{
case "pdb:nTerminus":
aminoAcid.AddNTerminus(atom);
break;
case "pdb:cTerminus":
aminoAcid.AddCTerminus(atom);
break;
default:
aminoAcid.Atoms.Add(atom);
break;
}
}
foreach (var bond in ac.Bonds)
{
aminoAcid.Bonds.Add(bond);
}
AminoAcidManipulator.RemoveAcidicOxygen(aminoAcid);
aminoAcid.SetProperty(NoAtomsKey, "" + aminoAcid.Atoms.Count);
aminoAcid.SetProperty(NoBoundsKey, "" + aminoAcid.Bonds.Count);
if (counter < proteinogenics.Length)
{
proteinogenics[counter] = aminoAcid;
}
else
{
Trace.TraceError("Could not store AminoAcid! Array too short!");
}
counter++;
}
}
catch (Exception exception)
{
if (exception is CDKException | exception is IOException)
{
Trace.TraceError($"Failed reading file: {exception.Message}");
Debug.WriteLine(exception);
}
else
{
throw;
}
}
}
}
#endregion
int count = proteinogenics.Length;
singleLetterCodeMap = new Dictionary <string, IAminoAcid>(count);
threeLetterCodeMap = new Dictionary <string, IAminoAcid>(count);
singleLetterToThreeLetter = new Dictionary <string, string>(count);
threeLetterToSingleLetter = new Dictionary <string, string>(count);
foreach (IAminoAcid aa in proteinogenics)
{
var single = aa.GetProperty <string>(ResidueNameShortKey);
var three = aa.GetProperty <string>(ResidueNameKey);
singleLetterCodeMap[single] = aa;
threeLetterCodeMap[three] = aa;
singleLetterToThreeLetter[single] = three;
threeLetterToSingleLetter[three] = single;
}
}
public MDLMolConvention(IChemFile chemFile)
: base(chemFile)
{
}
//protected internal LoggingTool logger;
/// <summary> Basic contructor</summary>
public ChemFileCDO(IChemFile file)
{
//logger = new LoggingTool(this);
currentChemFile = file;
currentChemSequence = file.Builder.newChemSequence();
currentChemModel = file.Builder.newChemModel();
currentSetOfMolecules = file.Builder.newSetOfMolecules();
currentSetOfReactions = null;
currentReaction = null;
currentMolecule = file.Builder.newMolecule();
atomEnumeration = System.Collections.Hashtable.Synchronized(new System.Collections.Hashtable());
}
public PDBConvention(IChemFile chemFile)
: base(chemFile)
{
}
public ChemRenderingSource3D(IChemFile file)
{
this.file = file;
SourceModified();
}
/// <summary> Read a ChemFile from a file in MDL SDF format.
///
/// </summary>
/// <returns> The ChemFile that was read from the MDL file.
/// </returns>
private IChemFile readChemFile(IChemFile chemFile)
{
IChemSequence chemSequence = chemFile.Builder.newChemSequence();
IChemModel chemModel = chemFile.Builder.newChemModel();
ISetOfMolecules setOfMolecules = chemFile.Builder.newSetOfMolecules();
IMolecule m = readMolecule(chemFile.Builder.newMolecule());
if (m != null)
{
setOfMolecules.addMolecule(m);
}
chemModel.SetOfMolecules = setOfMolecules;
chemSequence.addChemModel(chemModel);
setOfMolecules = chemFile.Builder.newSetOfMolecules();
chemModel = chemFile.Builder.newChemModel();
System.String str;
try
{
System.String line;
while ((line = input.ReadLine()) != null)
{
//logger.debug("line: ", line);
// apparently, this is a SDF file, continue with
// reading mol files
str = new System.Text.StringBuilder(line).ToString();
if (str.Equals("$$$$"))
{
m = readMolecule(chemFile.Builder.newMolecule());
if (m != null)
{
setOfMolecules.addMolecule(m);
chemModel.SetOfMolecules = setOfMolecules;
chemSequence.addChemModel(chemModel);
setOfMolecules = chemFile.Builder.newSetOfMolecules();
chemModel = chemFile.Builder.newChemModel();
}
}
else
{
// here the stuff between 'M END' and '$$$$'
if (m != null)
{
// ok, the first lines should start with '>'
System.String fieldName = null;
if (str.StartsWith("> "))
{
// ok, should extract the field name
str.Substring(2); // String content =
int index = str.IndexOf("<");
if (index != -1)
{
int index2 = str.Substring(index).IndexOf(">");
if (index2 != -1)
{
fieldName = str.Substring(index + 1, (index + index2) - (index + 1));
}
}
// end skip all other lines
while ((line = input.ReadLine()) != null && line.StartsWith(">"))
{
//logger.debug("data header line: ", line);
}
}
if (line == null)
{
throw new CDKException("Expecting data line here, but found null!");
}
System.String data = line;
while ((line = input.ReadLine()) != null && line.Trim().Length > 0)
{
if (line.Equals("$$$$"))
{
//logger.error("Expecting data line here, but found end of molecule: ", line);
break;
}
//logger.debug("data line: ", line);
data += line;
}
if (fieldName != null)
{
//logger.info("fieldName, data: ", fieldName, ", ", data);
m.setProperty(fieldName, data);
}
}
}
}
}
catch (CDKException cdkexc)
{
throw cdkexc;
}
catch (System.Exception exception)
{
System.String error = "Error while parsing SDF";
//logger.error(error);
//logger.debug(exception);
throw new CDKException(error, exception);
}
try
{
input.Close();
}
catch (System.Exception exc)
{
//UPGRADE_TODO: The equivalent in .NET for method 'java.lang.Throwable.getMessage' may return a different value. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1043'"
System.String error = "Error while closing file: " + exc.Message;
//logger.error(error);
throw new CDKException(error, exc);
}
chemFile.addChemSequence(chemSequence);
return(chemFile);
}
private IChemFile readChemFile(IChemFile file)
{
IChemSequence seq = file.Builder.newChemSequence();
IChemModel model = file.Builder.newChemModel();
ICrystal crystal = null;
int lineNumber = 0;
Vector3d a, b, c;
try
{
System.String line = input.ReadLine();
while (input.Peek() != -1 && line != null)
{
//logger.debug((lineNumber++) + ": ", line);
if (line.StartsWith("frame:"))
{
//logger.debug("found new frame");
model = file.Builder.newChemModel();
crystal = file.Builder.newCrystal();
// assume the file format is correct
//logger.debug("reading spacegroup");
line = input.ReadLine();
//logger.debug((lineNumber++) + ": ", line);
crystal.SpaceGroup = line;
//logger.debug("reading unit cell axes");
Vector3d axis = new Vector3d();
//logger.debug("parsing A: ");
line = input.ReadLine();
//logger.debug((lineNumber++) + ": ", line);
axis.x = FortranFormat.atof(line);
line = input.ReadLine();
//logger.debug((lineNumber++) + ": ", line);
axis.y = FortranFormat.atof(line);
line = input.ReadLine();
//logger.debug((lineNumber++) + ": ", line);
axis.z = FortranFormat.atof(line);
crystal.A = axis;
axis = new Vector3d();
//logger.debug("parsing B: ");
line = input.ReadLine();
//logger.debug((lineNumber++) + ": ", line);
axis.x = FortranFormat.atof(line);
line = input.ReadLine();
//logger.debug((lineNumber++) + ": ", line);
axis.y = FortranFormat.atof(line);
line = input.ReadLine();
//logger.debug((lineNumber++) + ": ", line);
axis.z = FortranFormat.atof(line);
crystal.B = axis;
axis = new Vector3d();
//logger.debug("parsing C: ");
line = input.ReadLine();
//logger.debug((lineNumber++) + ": ", line);
axis.x = FortranFormat.atof(line);
line = input.ReadLine();
//logger.debug((lineNumber++) + ": ", line);
axis.y = FortranFormat.atof(line);
line = input.ReadLine();
//logger.debug((lineNumber++) + ": ", line);
axis.z = FortranFormat.atof(line);
crystal.C = axis;
//logger.debug("Crystal: ", crystal);
a = crystal.A;
b = crystal.B;
c = crystal.C;
//logger.debug("Reading number of atoms");
line = input.ReadLine();
//logger.debug((lineNumber++) + ": ", line);
int atomsToRead = System.Int32.Parse(line);
//logger.debug("Reading no molecules in assym unit cell");
line = input.ReadLine();
//logger.debug((lineNumber++) + ": ", line);
int Z = System.Int32.Parse(line);
crystal.Z = Z;
System.String symbol;
double charge;
Point3d cart;
for (int i = 1; i <= atomsToRead; i++)
{
cart = new Point3d();
line = input.ReadLine();
//logger.debug((lineNumber++) + ": ", line);
symbol = line.Substring(0, (line.IndexOf(":")) - (0));
charge = System.Double.Parse(line.Substring(line.IndexOf(":") + 1));
line = input.ReadLine();
//logger.debug((lineNumber++) + ": ", line);
cart.x = System.Double.Parse(line); // x
line = input.ReadLine();
//logger.debug((lineNumber++) + ": ", line);
cart.y = System.Double.Parse(line); // y
line = input.ReadLine();
//logger.debug((lineNumber++) + ": ", line);
cart.z = System.Double.Parse(line); // z
IAtom atom = file.Builder.newAtom(symbol);
atom.setCharge(charge);
// convert cartesian coords to fractional
Point3d frac = CrystalGeometryTools.cartesianToFractional(a, b, c, cart);
atom.setFractionalPoint3d(frac);
crystal.addAtom(atom);
//logger.debug("Added atom: ", atom);
}
model.Crystal = crystal;
seq.addChemModel(model);
}
else
{
//logger.debug("Format seems broken. Skipping these lines:");
while (!line.StartsWith("frame:") && input.Peek() != -1 && line != null)
{
line = input.ReadLine();
//logger.debug(lineNumber++ + ": ", line);
}
//logger.debug("Ok, resynched: found new frame");
}
}
file.addChemSequence(seq);
}
catch (System.Exception exception)
{
//UPGRADE_TODO: The equivalent in .NET for method 'java.lang.Throwable.getMessage' may return a different value. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1043'"
System.String message = "Error while parsing CrystClust file: " + exception.Message;
//logger.error(message);
//logger.debug(exception);
throw new CDKException(message, exception);
}
return file;
}
public ChemRenderingSource3D(IChemFile file)
{
this.file = file;
SourceModified();
}
private IChemFile readChemFile(IChemFile chemFile)
{
IChemSequence sequence = readChemSequence(chemFile.Builder.newChemSequence());
chemFile.addChemSequence(sequence);
return chemFile;
}
public CMLReactionModule(IChemFile chemFile)
: base(chemFile)
{
}
public ChemRenderingSource2D(IChemFile file)
{
this.file = file;
}
/// <summary>
/// Tests whether the file is indeed a single molecule file
/// </summary>
private IAtomContainer CheckForSingleMoleculeFile(IChemFile chemFile)
{
return(CheckForXMoleculeFile(chemFile, 1));
}
// private procedures
/// <summary> Private method that actually parses the input to read a ChemFile
/// object.
///
/// </summary>
/// <returns> A ChemFile containing the data parsed from input.
/// </returns>
private IChemFile readChemFile(IChemFile file)
{
IChemSequence chemSequence = file.Builder.newChemSequence();
int number_of_atoms = 0;
SupportClass.Tokenizer tokenizer;
try
{
System.String line = input.ReadLine();
while (input.Peek() != -1 && line != null)
{
// parse frame by frame
tokenizer = new SupportClass.Tokenizer(line, "\t ,;");
System.String token = tokenizer.NextToken();
number_of_atoms = System.Int32.Parse(token);
System.String info = input.ReadLine();
IChemModel chemModel = file.Builder.newChemModel();
ISetOfMolecules setOfMolecules = file.Builder.newSetOfMolecules();
IMolecule m = file.Builder.newMolecule();
m.setProperty(CDKConstants.TITLE, info);
for (int i = 0; i < number_of_atoms; i++)
{
line = input.ReadLine();
if (line == null)
break;
if (line.StartsWith("#") && line.Length > 1)
{
System.Object comment = m.getProperty(CDKConstants.COMMENT);
if (comment == null)
{
comment = "";
}
//UPGRADE_TODO: The equivalent in .NET for method 'java.lang.Object.toString' may return a different value. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1043'"
comment = comment.ToString() + line.Substring(1).Trim();
m.setProperty(CDKConstants.COMMENT, comment);
//logger.debug("Found and set comment: ", comment);
}
else
{
double x = 0.0f, y = 0.0f, z = 0.0f;
double charge = 0.0f;
tokenizer = new SupportClass.Tokenizer(line, "\t ,;");
int fields = tokenizer.Count;
if (fields < 4)
{
// this is an error but cannot throw exception
}
else
{
System.String atomtype = tokenizer.NextToken();
//UPGRADE_TODO: The differences in the format of parameters for constructor 'java.lang.Double.Double' may cause compilation errors. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1092'"
x = (System.Double.Parse(tokenizer.NextToken()));
//UPGRADE_TODO: The differences in the format of parameters for constructor 'java.lang.Double.Double' may cause compilation errors. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1092'"
y = (System.Double.Parse(tokenizer.NextToken()));
//UPGRADE_TODO: The differences in the format of parameters for constructor 'java.lang.Double.Double' may cause compilation errors. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1092'"
z = (System.Double.Parse(tokenizer.NextToken()));
if (fields == 8)
{
//UPGRADE_TODO: The differences in the format of parameters for constructor 'java.lang.Double.Double' may cause compilation errors. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1092'"
charge = (System.Double.Parse(tokenizer.NextToken()));
}
IAtom atom = file.Builder.newAtom(atomtype, new Point3d(x, y, z));
atom.setCharge(charge);
m.addAtom(atom);
}
}
}
setOfMolecules.addMolecule(m);
chemModel.SetOfMolecules = setOfMolecules;
chemSequence.addChemModel(chemModel);
line = input.ReadLine();
}
file.addChemSequence(chemSequence);
}
catch (System.IO.IOException e)
{
// should make some noise now
file = null;
//UPGRADE_TODO: The equivalent in .NET for method 'java.lang.Throwable.getMessage' may return a different value. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1043'"
//logger.error("Error while reading file: ", e.Message);
//logger.debug(e);
}
return file;
}
/// <summary>
/// Read the Gaussian98 output.
/// </summary>
/// <param name="chemFile"></param>
/// <returns>a ChemFile with the coordinates, energies, and vibrations.</returns>
private IChemFile ReadChemFile(IChemFile chemFile)
{
IChemSequence sequence = chemFile.Builder.NewChemSequence();
IChemModel model = null;
string line = input.ReadLine();
string levelOfTheory;
string description;
int modelCounter = 0;
// Find first set of coordinates by skipping all before "Standard orientation"
while (line != null)
{
if (line.Contains("Standard orientation:"))
{
// Found a set of coordinates
model = chemFile.Builder.NewChemModel();
ReadCoordinates(model);
break;
}
line = input.ReadLine();
}
if (model != null)
{
// Read all other data
line = input.ReadLine().Trim();
while (line != null)
{
if (line.IndexOf('#') == 0)
{
// Found the route section
// Memorizing this for the description of the chemmodel
lastRoute = line;
modelCounter = 0;
}
else if (line.Contains("Standard orientation:"))
{
// Found a set of coordinates
// Add current frame to file and create a new one.
if (!readOptimizedStructureOnly.IsSet)
{
sequence.Add(model);
}
else
{
Trace.TraceInformation("Skipping frame, because I was told to do");
}
FrameRead();
model = chemFile.Builder.NewChemModel();
modelCounter++;
ReadCoordinates(model);
}
else if (line.Contains("SCF Done:"))
{
// Found an energy
model.SetProperty(CDKPropertyName.Remark, line.Trim());
}
else if (line.Contains("Harmonic frequencies"))
{
// Found a set of vibrations
// ReadFrequencies(frame);
}
else if (line.Contains("Total atomic charges"))
{
ReadPartialCharges(model);
}
else if (line.Contains("Magnetic shielding"))
{
// Found NMR data
ReadNMRData(model, line);
}
else if (line.Contains("GINC"))
{
// Found calculation level of theory
levelOfTheory = ParseLevelOfTheory(line);
Debug.WriteLine($"Level of Theory for this model: {levelOfTheory}");
description = lastRoute + ", model no. " + modelCounter;
model.SetProperty(CDKPropertyName.Description, description);
}
else
{
}
line = input.ReadLine();
}
// Add last frame to file
sequence.Add(model);
FrameRead();
}
chemFile.Add(sequence);
return(chemFile);
}
public static IChemModel[] getAllChemModels(IChemFile file)
{
IChemSequence[] sequences = file.ChemSequences;
int modelCounter = 0;
int counter = 0;
IChemModel[] tempModels = null;
for (int f = 0; f < sequences.Length; f++)
{
modelCounter += sequences[f].ChemModelCount;
}
IChemModel[] models = new IChemModel[modelCounter];
for (int f = 0; f < sequences.Length; f++)
{
tempModels = sequences[f].ChemModels;
for (int g = 0; g < tempModels.Length; g++)
{
models[counter] = tempModels[g];
counter++;
}
}
return models;
}
/// <summary> Read a <code>ChemFile</code> from a file in PDB format. The molecules
/// in the file are stored as <code>BioPolymer</code>s in the
/// <code>ChemFile</code>. The residues are the monomers of the
/// <code>BioPolymer</code>, and their names are the concatenation of the
/// residue, chain id, and the sequence number. Separate chains (denoted by
/// TER records) are stored as separate <code>BioPolymer</code> molecules.
///
/// <p>Connectivity information is not currently read.
///
/// </summary>
/// <returns> The ChemFile that was read from the PDB file.
/// </returns>
private IChemFile readChemFile(IChemFile oFile)
{
int bonds = 0;
// initialize all containers
IChemSequence oSeq = oFile.Builder.newChemSequence();
IChemModel oModel = oFile.Builder.newChemModel();
ISetOfMolecules oSet = oFile.Builder.newSetOfMolecules();
// some variables needed
string cCol;
PDBAtom oAtom;
PDBPolymer oBP = new PDBPolymer();
System.Text.StringBuilder cResidue;
string oObj;
IMonomer oMonomer;
string cRead = "";
char chain = 'A'; // To ensure stringent name giving of monomers
IStrand oStrand;
int lineLength = 0;
atomNumberMap = System.Collections.Hashtable.Synchronized(new System.Collections.Hashtable());
// do the reading of the Input
try
{
do
{
cRead = _oInput.ReadLine();
//logger.debug("Read line: ", cRead);
if (cRead != null)
{
lineLength = cRead.Length;
if (lineLength < 80)
{
//logger.warn("Line is not of the expected length 80!");
}
// make sure the record name is 6 characters long
if (lineLength < 6)
{
cRead = cRead + " ";
}
// check the first column to decide what to do
cCol = cRead.Substring(0, (6) - (0));
if ("ATOM ".ToUpper().Equals(cCol.ToUpper()))
{
// read an atom record
oAtom = readAtom(cRead, lineLength);
// construct a string describing the residue
cResidue = new System.Text.StringBuilder(8);
oObj = oAtom.ResName;
if (oObj != null)
{
cResidue = cResidue.Append(oObj.Trim());
}
oObj = oAtom.ChainID;
if (oObj != null)
{
// cResidue = cResidue.append(((String)oObj).trim());
cResidue = cResidue.Append(System.Convert.ToString(chain));
}
oObj = oAtom.ResSeq;
if (oObj != null)
{
cResidue = cResidue.Append(oObj.Trim());
}
// search for an existing strand or create a new one.
oStrand = oBP.getStrand(System.Convert.ToString(chain));
if (oStrand == null)
{
oStrand = new PDBStrand();
oStrand.StrandName = System.Convert.ToString(chain);
}
// search for an existing monomer or create a new one.
oMonomer = oBP.getMonomer(cResidue.ToString(), System.Convert.ToString(chain));
if (oMonomer == null)
{
PDBMonomer monomer = new PDBMonomer();
monomer.MonomerName = cResidue.ToString();
monomer.MonomerType = oAtom.ResName;
monomer.ChainID = oAtom.ChainID;
monomer.ICode = oAtom.ICode;
oMonomer = monomer;
}
// add the atom
oBP.addAtom(oAtom, oMonomer, oStrand);
System.Object tempObject;
//UPGRADE_WARNING: At least one expression was used more than once in the target code. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1181'"
tempObject = atomNumberMap[(System.Int32)oAtom.Serial];
atomNumberMap[(System.Int32)oAtom.Serial] = oAtom;
if (readConnect.Set && tempObject != null)
{
//logger.warn("Duplicate serial ID found for atom: ", oAtom);
}
// //logger.debug("Added ATOM: ", oAtom);
/** As HETATMs cannot be considered to either belong to a certain monomer or strand,
* they are dealt with seperately.*/
}
else if ("HETATM".ToUpper().Equals(cCol.ToUpper()))
{
// read an atom record
oAtom = readAtom(cRead, lineLength);
oAtom.HetAtom = true;
oBP.addAtom(oAtom);
System.Object tempObject2;
//UPGRADE_WARNING: At least one expression was used more than once in the target code. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1181'"
tempObject2 = atomNumberMap[(System.Int32)oAtom.Serial];
atomNumberMap[(System.Int32)oAtom.Serial] = oAtom;
if (tempObject2 != null)
{
//logger.warn("Duplicate serial ID found for atom: ", oAtom);
}
//logger.debug("Added HETATM: ", oAtom);
}
else if ("TER ".ToUpper().Equals(cCol.ToUpper()))
{
// start new strand
chain++;
oStrand = new PDBStrand();
oStrand.StrandName = System.Convert.ToString(chain);
//logger.debug("Added new STRAND");
}
else if ("END ".ToUpper().Equals(cCol.ToUpper()))
{
atomNumberMap.Clear();
// create bonds and finish the molecule
if (deduceBonding.Set)
{
// OK, try to deduce the bonding patterns
if (oBP.AtomCount != 0)
{
// Create bonds. If bonds could not be created, all bonds are deleted.
try
{
if (useRebondTool.Set)
{
if (!createBondsWithRebondTool(oBP))
{
// Get rid of all potentially created bonds.
//logger.info("Bonds could not be created using the RebondTool when PDB file was read.");
oBP.removeAllBonds();
}
}
else
{
if (!createBonds(oBP))
{
// Get rid of all potentially created bonds.
//logger.info("Bonds could not be created when PDB file was read.");
oBP.removeAllBonds();
}
}
}
catch (System.Exception exception)
{
//logger.info("Bonds could not be created when PDB file was read.");
//logger.debug(exception);
}
}
}
oSet.addMolecule(oBP);
// oBP = new BioPolymer();
// } else if (cCol.equals("USER ")) {
// System.out.println(cLine);
// System.out.println(cLine);
// } else if (cCol.equals("ENDMDL")) {
// System.out.println(cLine);
}
else if (cCol.Equals("MODEL "))
{
// OK, start a new model and save the current one first *if* it contains atoms
if (oBP.AtomCount > 0)
{
// save the model
oSet.addAtomContainer(oBP);
oModel.SetOfMolecules = oSet;
oSeq.addChemModel(oModel);
// setup a new one
oBP = new PDBPolymer();
oModel = oFile.Builder.newChemModel();
oSet = oFile.Builder.newSetOfMolecules();
}
}
else if ("REMARK".ToUpper().Equals(cCol.ToUpper()))
{
System.Object comment = oFile.getProperty(CDKConstants.COMMENT);
if (comment == null)
{
comment = "";
}
if (lineLength > 12)
{
//UPGRADE_TODO: The equivalent in .NET for method 'java.lang.Object.toString' may return a different value. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1043'"
comment = comment.ToString() + cRead.Substring(11).Trim() + "\n";
oFile.setProperty(CDKConstants.COMMENT, comment);
}
else
{
//logger.warn("REMARK line found without any comment!");
}
}
else if ("COMPND".ToUpper().Equals(cCol.ToUpper()))
{
string title = cRead.Substring(10).Trim();
oFile.setProperty(CDKConstants.TITLE, title);
}
/*************************************************************
* Read connectivity information from CONECT records.
* Only covalent bonds are dealt with. Perhaps salt bridges
* should be dealt with in the same way..?
*/
else if (readConnect.Set && "CONECT".ToUpper().Equals(cCol.ToUpper()))
{
cRead.Trim();
if (cRead.Length < 16)
{
//logger.debug("Skipping unexpected empty CONECT line! : ", cRead);
}
else
{
string bondAtom = cRead.Substring(7, 5).Trim();
int bondAtomNo = System.Int32.Parse(bondAtom);
for (int b = 0; b < 9; b += (b == 5 ? 2 : 1))
{
string bondedAtom = cRead.Substring((b * 5) + 11, 5).Trim();
int bondedAtomNo;
if (int.TryParse(bondedAtom, out bondedAtomNo))
{
bonds++;
addBond(oBP, bondAtomNo, bondedAtomNo);
}
}
//string bondedAtom = cRead.Substring(12, 5).Trim();
//int bondedAtomNo = -1;
//try
//{
// bondedAtomNo = System.Int32.Parse(bondedAtom);
//}
//catch (System.Exception e)
//{
// bondedAtomNo = -1;
//}
//if (bondedAtomNo != -1)
//{
// bonds++;
// addBond(oBP, bondAtomNo, bondedAtomNo);
// //logger.warn("Bonded " + bondAtomNo + " with " + bondedAtomNo);
//}
//else
//{
//}
//if (cRead.Length > 17)
//{
// bondedAtom = cRead.Substring(16, 5);
// bondedAtom = bondedAtom.Trim();
// try
// {
// bondedAtomNo = System.Int32.Parse(bondedAtom);
// }
// catch (System.Exception e)
// {
// bondedAtomNo = -1;
// }
// if (bondedAtomNo != -1)
// {
// bonds++;
// addBond(oBP, bondAtomNo, bondedAtomNo);
// //logger.warn("Bonded " + bondAtomNo + " with " + bondedAtomNo);
// }
//}
//if (cRead.Length > 22)
//{
// bondedAtom = cRead.Substring(22, 5);
// bondedAtom = bondedAtom.Trim();
// try
// {
// bondedAtomNo = System.Int32.Parse(bondedAtom);
// }
// catch (System.Exception e)
// {
// bondedAtomNo = -1;
// }
// if (bondedAtomNo != -1)
// {
// bonds++;
// addBond(oBP, bondAtomNo, bondedAtomNo);
// //logger.warn("Bonded " + bondAtomNo + " with " + bondedAtomNo);
// }
//}
//if (cRead.Length > 27)
//{
// bondedAtom = cRead.Substring(27, 5);
// bondedAtom = bondedAtom.Trim();
// try
// {
// bondedAtomNo = System.Int32.Parse(bondedAtom);
// }
// catch (System.Exception e)
// {
// bondedAtomNo = -1;
// }
// if (bondedAtomNo != -1)
// {
// bonds++;
// addBond(oBP, bondAtomNo, bondedAtomNo);
// //logger.warn("Bonded " + bondAtomNo + " with " + bondedAtomNo);
// }
//}
}
}
/*************************************************************/
else if ("HELIX ".ToUpper().Equals(cCol.ToUpper()))
{
// HELIX 1 H1A CYS A 11 LYS A 18 1 RESIDUE 18 HAS POSITIVE PHI 1D66 72
// 1 2 3 4 5 6 7
// 01234567890123456789012345678901234567890123456789012345678901234567890123456789
PDBStructure structure = new PDBStructure();
structure.StructureType = PDBStructure.HELIX;
structure.StartChainID = cRead[19];
structure.StartSequenceNumber = System.Int32.Parse(cRead.Substring(21, (25) - (21)).Trim());
structure.StartInsertionCode = cRead[25];
structure.EndChainID = cRead[31];
structure.EndSequenceNumber = System.Int32.Parse(cRead.Substring(33, (37) - (33)).Trim());
structure.EndInsertionCode = cRead[37];
oBP.addStructure(structure);
}
else if ("SHEET ".ToUpper().Equals(cCol.ToUpper()))
{
PDBStructure structure = new PDBStructure();
structure.StructureType = PDBStructure.SHEET;
structure.StartChainID = cRead[21];
structure.StartSequenceNumber = System.Int32.Parse(cRead.Substring(22, (26) - (22)).Trim());
structure.StartInsertionCode = cRead[26];
structure.EndChainID = cRead[32];
structure.EndSequenceNumber = System.Int32.Parse(cRead.Substring(33, (37) - (33)).Trim());
structure.EndInsertionCode = cRead[37];
oBP.addStructure(structure);
}
else if ("TURN ".ToUpper().Equals(cCol.ToUpper()))
{
PDBStructure structure = new PDBStructure();
structure.StructureType = PDBStructure.TURN;
structure.StartChainID = cRead[19];
structure.StartSequenceNumber = System.Int32.Parse(cRead.Substring(20, (24) - (20)).Trim());
structure.StartInsertionCode = cRead[24];
structure.EndChainID = cRead[30];
structure.EndSequenceNumber = System.Int32.Parse(cRead.Substring(31, (35) - (31)).Trim());
structure.EndInsertionCode = cRead[35];
oBP.addStructure(structure);
} // ignore all other commands
}
}while (_oInput.Peek() != -1 && (cRead != null));
}
catch (System.Exception e)
{
//logger.error("Found a problem at line:\n");
//logger.error(cRead);
//logger.error("01234567890123456789012345678901234567890123456789012345678901234567890123456789");
//logger.error(" 1 2 3 4 5 6 7 ");
//UPGRADE_TODO: The equivalent in .NET for method 'java.lang.Throwable.getMessage' may return a different value. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1043'"
//logger.error(" error: " + e.Message);
//logger.debug(e);
}
// try to close the Input
try
{
_oInput.Close();
}
catch (System.Exception e)
{
//logger.debug(e);
}
// Set all the dependencies
oModel.SetOfMolecules = oSet;
oSeq.addChemModel(oModel);
oFile.addChemSequence(oSeq);
return(oFile);
}
/// <summary>
/// Private method that actually parses the input to read a ChemFile
/// object.
///
/// Each PMP frame is stored as a Crystal in a ChemModel. The PMP
/// file is stored as a ChemSequence of ChemModels.
/// </summary>
/// <returns>A ChemFile containing the data parsed from input.</returns>
private IChemFile ReadChemFile(IChemFile chemFile)
{
IChemSequence chemSequence;
IChemModel chemModel;
ICrystal crystal;
try
{
string line = ReadLine();
while (line != null)
{
if (line.StartsWith("%%Header Start", StringComparison.Ordinal))
{
// parse Header section
while (line != null && !(line.StartsWith("%%Header End", StringComparison.Ordinal)))
{
if (line.StartsWith("%%Version Number", StringComparison.Ordinal))
{
string version = ReadLine().Trim();
if (!string.Equals(version, "3.00", StringComparison.Ordinal))
{
Trace.TraceError("The PMPReader only supports PMP files with version 3.00");
return(null);
}
}
line = ReadLine();
}
}
else if (line.StartsWith("%%Model Start", StringComparison.Ordinal))
{
// parse Model section
modelStructure = chemFile.Builder.NewAtomContainer();
while (line != null && !(line.StartsWith("%%Model End", StringComparison.Ordinal)))
{
var objHeaderMatcher = objHeader.Match(line);
if (objHeaderMatcher.Success)
{
var obj = objHeaderMatcher.Groups[2].Value;
ConstructObject(chemFile.Builder, obj);
var id = int.Parse(objHeaderMatcher.Groups[1].Value, NumberFormatInfo.InvariantInfo);
// Debug.WriteLine(object + " id: " + id);
line = ReadLine();
while (line != null && !(string.Equals(line.Trim(), ")", StringComparison.Ordinal)))
{
// parse object command (or new object header)
var objCommandMatcher = objCommand.Match(line);
objHeaderMatcher = objHeader.Match(line);
if (objHeaderMatcher.Success)
{
// ok, forget about nesting and hope for the best
obj = objHeaderMatcher.Groups[2].Value;
id = int.Parse(objHeaderMatcher.Groups[1].Value, NumberFormatInfo.InvariantInfo);
ConstructObject(chemFile.Builder, obj);
}
else if (objCommandMatcher.Success)
{
var format = objCommandMatcher.Groups[1].Value;
var command = objCommandMatcher.Groups[2].Value;
var field = objCommandMatcher.Groups[3].Value;
ProcessModelCommand(obj, command, format, field);
}
else
{
Trace.TraceWarning("Skipping line: " + line);
}
line = ReadLine();
}
if (chemObject is IAtom)
{
atomids[id] = modelStructure.Atoms.Count;
atomGivenIds[int.Parse(chemObject.GetProperty <string>(PMP_ID), NumberFormatInfo.InvariantInfo)] = id;
modelStructure.Atoms.Add((IAtom)chemObject);
}
else if (chemObject is IBond)
{
// ignored: bonds may be defined before their
// atoms so their handling is deferred until the
// end of the model
}
else
{
Trace.TraceError("chemObject is not initialized or of bad class type");
}
}
line = ReadLine();
}
Trace.Assert(line != null);
if (line.StartsWith("%%Model End", StringComparison.Ordinal))
{
// during the Model Start, all bonds are cached as PMP files might
// define bonds *before* the involved atoms :(
// the next lines dump the cache into the atom container
int bondsFound = bondids.Count;
Debug.WriteLine($"Found #bonds: {bondsFound}");
Debug.WriteLine($"#atom ones: {bondAtomOnes.Count}");
Debug.WriteLine($"#atom twos: {bondAtomTwos.Count}");
Debug.WriteLine($"#orders: {bondOrders.Count}");
foreach (var index in bondids.Keys)
{
if (!bondOrders.TryGetValue(index, out double order))
{
order = 1;
}
Debug.WriteLine($"index: {index}");
Debug.WriteLine($"ones: {bondAtomOnes[index]}");
var atom1 = modelStructure.Atoms[atomids[bondAtomOnes[index]]];
var atom2 = modelStructure.Atoms[atomids[bondAtomTwos[index]]];
var bond = modelStructure.Builder.NewBond(atom1, atom2);
if (order == 1.0)
{
bond.Order = BondOrder.Single;
}
else if (order == 2.0)
{
bond.Order = BondOrder.Double;
}
else if (order == 3.0)
{
bond.Order = BondOrder.Triple;
}
else if (order == 4.0)
{
bond.Order = BondOrder.Quadruple;
}
modelStructure.Bonds.Add(bond);
}
}
}
else if (line.StartsWith("%%Traj Start", StringComparison.Ordinal))
{
chemSequence = chemFile.Builder.NewChemSequence();
double energyFragment = 0.0;
double energyTotal = 0.0;
int Z = 1;
while (line != null && !(line.StartsWith("%%Traj End", StringComparison.Ordinal)))
{
if (line.StartsWith("%%Start Frame", StringComparison.Ordinal))
{
chemModel = chemFile.Builder.NewChemModel();
crystal = chemFile.Builder.NewCrystal();
while (line != null && !(line.StartsWith("%%End Frame", StringComparison.Ordinal)))
{
// process frame data
if (line.StartsWith("%%Atom Coords", StringComparison.Ordinal))
{
// calculate Z: as it is not explicitely given, try to derive it from the
// energy per fragment and the total energy
if (energyFragment != 0.0 && energyTotal != 0.0)
{
Z = (int)Math.Round(energyTotal / energyFragment);
Debug.WriteLine($"Z derived from energies: {Z}");
}
// add atomC as atoms to crystal
int expatoms = modelStructure.Atoms.Count;
for (int molCount = 1; molCount <= Z; molCount++)
{
IAtomContainer clone = modelStructure.Builder.NewAtomContainer();
for (int i = 0; i < expatoms; i++)
{
line = ReadLine();
IAtom a = clone.Builder.NewAtom();
var st = Strings.Tokenize(line, ' ');
a.Point3D = new Vector3(double.Parse(st[0], NumberFormatInfo.InvariantInfo), double.Parse(st[1], NumberFormatInfo.InvariantInfo), double.Parse(st[2], NumberFormatInfo.InvariantInfo));
a.CovalentRadius = 0.6;
IAtom modelAtom = modelStructure.Atoms[atomids[atomGivenIds[i + 1]]];
a.Symbol = modelAtom.Symbol;
clone.Atoms.Add(a);
}
rebonder.Rebond(clone);
crystal.Add(clone);
}
}
else if (line.StartsWith("%%E/Frag", StringComparison.Ordinal))
{
line = ReadLine().Trim();
energyFragment = double.Parse(line, NumberFormatInfo.InvariantInfo);
}
else if (line.StartsWith("%%Tot E", StringComparison.Ordinal))
{
line = ReadLine().Trim();
energyTotal = double.Parse(line, NumberFormatInfo.InvariantInfo);
}
else if (line.StartsWith("%%Lat Vects", StringComparison.Ordinal))
{
line = ReadLine();
IList <string> st;
st = Strings.Tokenize(line, ' ');
crystal.A = new Vector3(double.Parse(st[0], NumberFormatInfo.InvariantInfo), double.Parse(st[1], NumberFormatInfo.InvariantInfo), double.Parse(st[2], NumberFormatInfo.InvariantInfo));
line = ReadLine();
st = Strings.Tokenize(line, ' ');
crystal.B = new Vector3(double.Parse(st[0], NumberFormatInfo.InvariantInfo), double.Parse(st[1], NumberFormatInfo.InvariantInfo), double.Parse(st[2], NumberFormatInfo.InvariantInfo));
line = ReadLine();
st = Strings.Tokenize(line, ' ');
crystal.C = new Vector3(double.Parse(st[0], NumberFormatInfo.InvariantInfo), double.Parse(st[1], NumberFormatInfo.InvariantInfo), double.Parse(st[2], NumberFormatInfo.InvariantInfo));
}
else if (line.StartsWith("%%Space Group", StringComparison.Ordinal))
{
line = ReadLine().Trim();
// standardize space group name. See Crystal.SetSpaceGroup()
if (string.Equals("P 21 21 21 (1)", line, StringComparison.Ordinal))
{
crystal.SpaceGroup = "P 2_1 2_1 2_1";
}
else
{
crystal.SpaceGroup = "P1";
}
}
line = ReadLine();
}
chemModel.Crystal = crystal;
chemSequence.Add(chemModel);
}
line = ReadLine();
}
chemFile.Add(chemSequence);
}
// else disregard line
// read next line
line = ReadLine();
}
}
catch (IOException e)
{
Trace.TraceError($"An IOException happened: {e.Message}");
Debug.WriteLine(e);
chemFile = null;
}
catch (CDKException e)
{
Trace.TraceError($"An CDKException happened: {e.Message}");
Debug.WriteLine(e);
chemFile = null;
}
return(chemFile);
}
private IChemFile ReadChemFile(IChemFile chemFile)
{
var chemSequence = chemFile.Builder.NewChemSequence();
var chemModel = chemFile.Builder.NewChemModel();
var setOfMolecules = chemFile.Builder.NewAtomContainerSet();
var m = ReadMolecule(chemFile.Builder.NewAtomContainer());
if (m != null)
{
setOfMolecules.Add(m);
}
chemModel.MoleculeSet = setOfMolecules;
chemSequence.Add(chemModel);
setOfMolecules = chemFile.Builder.NewAtomContainerSet();
chemModel = chemFile.Builder.NewChemModel();
try
{
firstLineisMolecule = true;
while (m != null)
{
m = ReadMolecule(chemFile.Builder.NewAtomContainer());
if (m != null)
{
setOfMolecules.Add(m);
chemModel.MoleculeSet = setOfMolecules;
chemSequence.Add(chemModel);
setOfMolecules = chemFile.Builder.NewAtomContainerSet();
chemModel = chemFile.Builder.NewChemModel();
}
}
}
catch (CDKException)
{
throw;
}
catch (ArgumentException exception)
{
var error = "Error while parsing MOL2";
Trace.TraceError(error);
Debug.WriteLine(exception);
throw new CDKException(error, exception);
}
try
{
input.Close();
}
catch (Exception exc)
{
var error = "Error while closing file: " + exc.Message;
Trace.TraceError(error);
throw new CDKException(error, exc);
}
chemFile.Add(chemSequence);
// reset it to false so that other read methods called later do not get confused
firstLineisMolecule = false;
return(chemFile);
}
public virtual void createIDs(IChemFile file)
{
IChemSequence[] sequences = file.ChemSequences;
for (int i = 0; i < sequences.Length; i++)
{
createIDs(sequences[i]);
}
}
public CTXReader(TextReader input)
{
this.input = input;
file = null;
}
