/// <summary>
/// This method parses a GRO formatted file for a molecular structures.
/// If there are multiple 'frames' in the file it returns a list of structures rather than
/// a structure and a trajectory. i.e. each frame is a new structure added to the output structure list.
/// </summary>
/// <param name="filename"></param>
/// <returns></returns>
public static List <PrimaryStructure> GetAllStructures(string filename)
{
StreamReader sr = null;
List <PrimaryStructure> models = new List <PrimaryStructure>();
PrimaryStructure model = null;
try {
sr = new StreamReader(filename);
model = GetFrame(sr);
while (model != null)
{
models.Add(model);
model = GetFrame(sr);
}
}
catch (Exception e) {
throw new FileParseException(e.Message);
}
finally {
if (sr != null)
{
sr.Close();
}
}
return(models);
}
public static void Run()
{
Console.WriteLine("Parsing PBD File");
Stopwatch stopWatch = new Stopwatch();
stopWatch.Start();
PrimaryStructure model = PDBStructureParser.GetPrimaryStructure(inputFilePath + inputFileName);
stopWatch.Stop();
Console.WriteLine("Structure Parsing Complete [" + stopWatch.ElapsedMilliseconds + " ms]");
Console.WriteLine("Atom Count: " + model.Atoms().Count);
Console.WriteLine("Running Stride Analysis");
stopWatch = new Stopwatch();
stopWatch.Start();
StrideAnalysis stride = new StrideAnalysis(exePath);
SecondaryStructure structure = stride.GetSecondaryStructure(inputFilePath + inputFileName);
// Console.WriteLine("Secondary structure:\n\n" + structure);
stopWatch.Stop();
Console.WriteLine("Processing complete [" + stopWatch.ElapsedMilliseconds + " ms]");
Console.WriteLine("End Testing Stride");
foreach (Chain chain in model.Chains())
{
Console.WriteLine("Chain ID: " + chain.ID);
if (chain.ResidueType != StandardResidue.AminoAcid)
{
Console.WriteLine("Not a protein chain");
continue;
}
foreach (Residue residue in chain.MainChainResidues)
{
if (residue.CarbonylOxygen == null)
{
Console.WriteLine("Residue ID: " + residue.ID + " has no oxygen");
}
SecondaryStructureInfomation structureInfo = structure.GetStructureInformation(residue.Index);
if (structureInfo == null)
{
Console.WriteLine("Couldn't find structure info for residue index: " + residue.Index);
}
else
{
Console.WriteLine("Residue [" + residue.ID + "][" + residue.Name + "] has structure [" + structureInfo.ToString() + "] and Alpha Carbon: " + residue.AlphaCarbon);
}
}
}
}
public static void Run()
{
// get the primary structure
Console.WriteLine("Parsing GRO File");
Stopwatch stopWatch = new Stopwatch();
stopWatch.Start();
PrimaryStructure primaryStructure = GROStructureParser.GetStructure(inputFilePath + inputFileName);
stopWatch.Stop();
Console.WriteLine("Structure Parsing Complete [" + stopWatch.ElapsedMilliseconds + " ms]");
// get the structure trajectory
int atomCount = XTCTrajectoryParser.GetAtomCount(inputFilePath + trajectoryFileName);
if (atomCount == primaryStructure.AtomCount())
{
Console.WriteLine("Atom Count matches.");
}
else
{
Console.WriteLine("Atom count doesnt match between primary structure and trajectory");
}
Stopwatch stopWatch2 = new Stopwatch();
stopWatch2.Start();
PrimaryStructureTrajectory trajectory = XTCTrajectoryParser.GetTrajectory(inputFilePath + trajectoryFileName, 0, 100, 1);
stopWatch2.Stop();
Console.WriteLine("Trajectory Parsing Complete [" + stopWatch2.ElapsedMilliseconds + " ms]");
// get the secondary structure for the base primary structure
Stopwatch stopWatch3 = new Stopwatch();
stopWatch3.Start();
SecondaryStructure secondaryStructure = SecondaryStructure.CreateFromPrimaryStructure(primaryStructure, strideExePath, tmpFilePath);
Console.WriteLine("Main Secondary Structure Parsing Complete [" + stopWatch3.ElapsedMilliseconds + " ms]");
Console.WriteLine(secondaryStructure);
// get the secondary structure for a frame of the trajectory
Stopwatch stopWatch4 = new Stopwatch();
stopWatch4.Start();
SecondaryStructureTrajectory secondaryStructureTrajectory = new SecondaryStructureTrajectory(primaryStructure, trajectory, strideExePath, tmpFilePath);
SecondaryStructure secondaryStructure2 = secondaryStructureTrajectory.GetStructure(50);
Console.WriteLine("Secondary Structure Parsing for frame 50 Complete [" + stopWatch3.ElapsedMilliseconds + " ms]");
Console.WriteLine(secondaryStructure2);
}
public SecondaryStructureTrajectory(PrimaryStructure primaryStructure, PrimaryStructureTrajectory primaryTrajectory, string strideExePath, string tmpFilePath)
{
this.primaryStructure = primaryStructure;
this.primaryTrajectory = primaryTrajectory;
this.strideExePath = strideExePath;
this.tmpFilePath = tmpFilePath;
secondaryStructuresFrames = new Dictionary <int, SecondaryStructure>();
badFrames = new HashSet <int>();
}
public static void Run()
{
Console.WriteLine("Parsing PDB File");
PrimaryStructure primaryStructure = PDBStructureParser.GetPrimaryStructure(inputFilePath + inputFileName);
// dump structure to PDB file. Can check this file against the original input file for equivalence
string tmpFileName = tmpFilePath + @"tempStructure.pdb";
PDBStructureCreator pdbCreator = new PDBStructureCreator(primaryStructure, null);
pdbCreator.CreatePDBFile(tmpFileName, true, true);
// FileUtil.DeleteFile(tmpFileName);
}
public static void Run()
{
Console.WriteLine("Parsing PDB File");
Stopwatch stopWatch = new Stopwatch();
stopWatch.Start();
PrimaryStructure primaryStructure = PDBStructureParser.GetPrimaryStructure(filepath + structureFile);
stopWatch.Stop();
Console.WriteLine("Structure Parsing Complete [" + stopWatch.ElapsedMilliseconds + " ms]");
stopWatch.Reset();
stopWatch.Start();
SecondaryStructure.CreateFromPrimaryStructure(primaryStructure, strideExePath, tmpFilePath);
Console.WriteLine("Main Secondary Structure Parsing Complete [" + stopWatch.ElapsedMilliseconds + " ms]");
foreach (Chain chain in primaryStructure.Chains())
{
foreach (Atom atom in chain.MainChainAtoms)
{
// if no frame number use the base structure coordinates.
if (atom == null)
{
Console.WriteLine("Main chain atom is null");
}
else
{
Console.WriteLine("Atom found: " + atom.ToString());
}
}
//Console.WriteLine("\n---------------------\n");
//Console.WriteLine("Chain ID: " + chain.ID);
//Console.WriteLine("Chain Residue Count: " + chain.Residues.Count);
//if (chain.ResidueType == MolecularDynamics.Definitions.StandardResidue.AminoAcid) {
// foreach (Residue residue in chain.Residues) {
// Console.WriteLine("Residue index: " + residue.Index + ", ResidueID: " + residue.ID + ", Residue Name: " + residue.Name);
// SecondaryStructureInfomation information = secondaryStructure.GetStructureInformation(residue.Index);
// if (information == null) {
// Console.WriteLine("information null: " + residue.Index);
// }
// }
//}
//else {
// Console.WriteLine("Not an amino acid residue");
//}
}
}
public static PrimaryStructure GetStructure(string filename)
{
PrimaryStructure model;
StreamReader sr = null;
try {
sr = new StreamReader(filename);
int atomCount = Int32.Parse(sr.ReadLine().Trim());
string titleLine = sr.ReadLine();
model = new PrimaryStructure();
model.Title = titleLine;
model.Time = 0;
for (int i = 0; i < atomCount; i++)
{
string atomLine = sr.ReadLine();
Regex g = new Regex(@"\s*?(\w+)\s+([\d\.\-]+)\s+([\d\.\-]+)\s+([\d\.\-]+).*$");
Match m = g.Match(atomLine);
int atomID = int.Parse(i.ToString());
string name = m.Groups[1].Value.Trim();
Element element = ElementHelper.Parse(name);
Vector3 position = new Vector3();
position.x = float.Parse(m.Groups[2].Value) / 10f;
position.y = float.Parse(m.Groups[3].Value) / 10f;
position.z = float.Parse(m.Groups[4].Value) / 10f;
Atom atom = new Atom(i, atomID, name, element, position);
atom.ResidueType = StandardResidue.None;
model.AddAtom(i, atom);
}
}
catch (Exception e) {
throw new FileParseException(e.Message);
}
finally {
if (sr != null)
{
sr.Close();
}
}
return(model);
}
public static SecondaryStructure CreateFromPrimaryStructure(PrimaryStructure primaryStructure, string strideExePath, string tmpFilePath)
{
string tmpFileName = tmpFilePath + @"tempStructure.pdb";
PDBStructureCreator pdbCreator = new PDBStructureCreator(primaryStructure, null);
//pdbCreator.CreatePDBFile(tmpFileName, true, true, true);
pdbCreator.CreatePDBFile(tmpFileName);
SecondaryStructure secondaryStructure = null;
try {
StrideAnalysis stride = new StrideAnalysis(strideExePath);
secondaryStructure = stride.GetSecondaryStructure(tmpFileName);
}
finally {
FileUtil.DeleteFile(tmpFileName);
}
return(secondaryStructure);
}
/// <summary>
/// This method parses a GRO formatted file for a molecular structure.
/// It will only parse the first frame in the file and return a MolecularModel with one frame. Additional frames in the GRO file will be discarded.
/// </summary>
/// <param name="filename"></param>
/// <returns></returns>
public static PrimaryStructure GetStructure(string filename)
{
StreamReader sr = null;
PrimaryStructure model = null;
try {
sr = new StreamReader(filename);
model = GetFrame(sr);
}
catch (Exception e) {
throw new FileParseException(e.Message);
}
finally {
if (sr != null)
{
sr.Close();
}
}
return(model);
}
// private static string inputFileFileName = @"lipoprotein_DS.pdb";
//private static string inputFileFileName = @"lipoprotein.pdb";
//private static string inputFilePath = @"D:\Molecule Examples\PDB Example Files\";
//private static string inputFileFileName = @"Zika_Virus_5ire.pdb";
public static void Run()
{
Console.WriteLine("Parsing PBD File");
Stopwatch stopWatch = new Stopwatch();
stopWatch.Start();
// PrimaryStructure model = PDBStructureParser.GetStructure(inputFilePath + inputFileFileName);
PrimaryStructure model = GROStructureParser.GetStructure(inputFilePath + inputFileFileName);
stopWatch.Stop();
Console.WriteLine("Structure Parsing Complete [" + stopWatch.ElapsedMilliseconds + " ms]");
Console.WriteLine("Atom Count: " + model.Atoms().Count);
// Console.WriteLine(model.ToString());
foreach (Chain chain in model.Chains())
{
Console.WriteLine("Chain " + chain.ID + ": ");// + residue.ToString());
if (chain.ResidueType == StandardResidue.AminoAcid)
{
foreach (Residue residue in chain.MainChainResidues)
{
Console.WriteLine(residue);
}
//foreach (Atom mainChainAtom in chain.Value.MainChainAtoms) {
// Console.WriteLine(mainChainAtom);
//}
}
else
{
Console.WriteLine("Chain " + chain.ID + " is not a protein chain");
//foreach (KeyValuePair<int, Residue> residue in chain.Value.Residues) {
// Console.WriteLine(residue.Value.ResidueType.ToString());
//}
}
}
}
public static void Run()
{
Console.WriteLine("Parsing GRO File");
Stopwatch stopWatch = new Stopwatch();
stopWatch.Start();
PrimaryStructure primaryStructure = GROStructureParser.GetStructure(filepath + structureFile);
stopWatch.Stop();
Console.WriteLine("Structure Parsing Complete [" + stopWatch.ElapsedMilliseconds + " ms]");
stopWatch.Reset();
stopWatch.Start();
SecondaryStructure secondaryStructure = SecondaryStructure.CreateFromPrimaryStructure(primaryStructure, strideExePath, tmpFilePath);
Console.WriteLine("Main Secondary Structure Parsing Complete [" + stopWatch.ElapsedMilliseconds + " ms]");
foreach (Chain chain in primaryStructure.Chains())
{
Console.WriteLine("\n---------------------\n");
Console.WriteLine("Chain ID: " + chain.ID);
Console.WriteLine("Chain Residue Count: " + chain.Residues.Count);
foreach (Residue residue in chain.Residues)
{
Console.WriteLine("Residue index: " + residue.Index + ", ResidueID: " + residue.ID + ", Residue Name: " + residue.Name);
SecondaryStructureInfomation information = secondaryStructure.GetStructureInformation(residue.Index);
if (information == null)
{
Console.WriteLine("information null: " + residue.Index);
}
}
}
}
public static void GetTrajectoryColours(string filename, PrimaryStructure model, PrimaryStructureTrajectory trajectory)
{
GetTrajectoryColours(filename, model, trajectory, 0, DEFAULT_FRAME_READ, 1);
}
public static void GetTrajectoryColours(string filename, PrimaryStructure model, PrimaryStructureTrajectory trajectory, int startFrame, int numFrames, int frameFrequency)
{
Stopwatch watch = new Stopwatch();
watch.Start();
StreamReader reader = null;
Regex g = new Regex(@"\s*(\d+)\s*(\d+\.?\d*)");
try {
reader = new StreamReader(filename);
discardFrames(reader, startFrame);
List <float[]> colourFrames = new List <float[]>();
int colourFrameNumber = -1;
int atomIndex = 0;
float colour = 0;
float[] colourFrame = null;
string line;
while ((line = readLine(reader)) != null && colourFrames.Count < numFrames)
{
if (line.Trim().Length == 0) // is empty string?
{
continue;
}
// discard everything but matches
Match m = g.Match(line);
if (m.Success)
{
atomIndex = int.Parse(m.Groups[1].Value);
colour = float.Parse(m.Groups[2].Value);
if (atomIndex == 1)
{
colourFrameNumber++;
// save colours
if (colourFrame != null)
{
colourFrames.Add(colourFrame);
colourFrame = null;
}
if (colourFrameNumber % frameFrequency == 0)
{
// initialise new colour arrary
colourFrame = new float[model.AtomCount()];
for (int i = 0; i < colourFrame.Length; i++)
{
colourFrame[i] = DEFAULT_COLOUR_VALUE;
}
}
}
if (colourFrame != null)
{
if (atomIndex > 0 && atomIndex <= colourFrame.Length)
{
colourFrame[atomIndex - 1] = colour;
}
}
}
}
PrimaryStructureFrame currentFrame = null;
int frameNumber = 0;
// copy all colour frames to trajectory frames
foreach (float[] frame in colourFrames)
{
currentFrame = trajectory.GetFrame(frameNumber);
currentFrame.Colours = frame;
frameNumber++;
// if we've run out of trajectory frames then stop copying
if (frameNumber >= trajectory.FrameCount())
{
break;
}
}
// if more trajectory frames than colour frames fill in rest of trajectory frames with default colours
float[] colours = new float[model.AtomCount()];
for (int i = 0; i < colours.Length; i++)
{
colours[i] = 0f;
}
foreach (PrimaryStructureFrame frame in trajectory.GetFrames())
{
if (frame.Colours == null)
{
frame.Colours = colours;
}
}
}
catch (Exception e) {
throw new FileParseException(e.Message);
}
finally {
if (reader != null)
{
reader.Close();
}
}
}
/// <summary>
/// This method parses a PDB formatted file for a molecular primary structure.
/// It will only parse the first model in the file (as defined by the ENDMDL record. Additional models in the PDB file will be discarded.
/// </summary>
/// <param name="filename"></param>
/// <returns></returns>
public static PrimaryStructure GetPrimaryStructure(string filename)
{
PrimaryStructure model;
StreamReader sr = null;
try {
sr = new StreamReader(filename);
model = new PrimaryStructure();
bool EOF = false;
// all indexing is 1 based and will increment before first assignment
int atomIndex = 0;
int residueIndex = 0;
int chainIndex = 0;
Chain chain = null;
Residue residue = null;
int currentResidueID = -1;
string currentChainID = "";
bool TERFound = false;
while (!EOF)
{
string record = sr.ReadLine();
// Console.WriteLine("processing Line: " + record);
if (record == null || record.Trim().Equals("END"))
{
EOF = true;
}
else
{
if (record == null || record.Trim() == "")
{
continue;
}
string recordName = record;
if (recordName.Length < 6)
{
recordName = recordName.Trim();
}
else
{
recordName = record.Substring(0, 6).Trim();
}
switch (recordName)
{
case "ATOM":
case "HETATM":
int atomResidueID = int.Parse(record.Substring(22, 4).Trim());
if (atomResidueID != currentResidueID)
{
// store residue - first time here will be null
if (residue != null)
{
model.AddResidue(residueIndex, residue);
if (chain != null && currentChainID != "")
{
chain.AddResidue(residueIndex, residue);
}
}
residueIndex++;
currentResidueID = atomResidueID;
string residueName = record.Substring(17, 3).Trim();
residue = new Residue(residueIndex, atomResidueID, residueName);
}
string chainID = record.Substring(21, 1).Trim();
if (currentChainID != chainID || TERFound)
{
Console.WriteLine("Handling new chain");
if (chain != null && currentChainID != "")
{
model.AddChain(chain);
}
if (chainID != null)
{
chainIndex++;
chain = new Chain(chainIndex, chainID);
}
currentChainID = chainID;
TERFound = false;
}
int atomID = int.Parse(record.Substring(6, 5).Trim());
string atomName = record.Substring(12, 4).Trim();
Element element = ElementHelper.Parse(record.Substring(76, 2).Trim());
float charge = 0;
// if the file has extra columns at the end then assume they are for charge and try to parse
if (record.Length > 80)
{
string chargeString = record.Substring(80, record.Length - 80).Trim();
if (chargeString.Length > 0)
{
try {
charge = float.Parse(chargeString);
}
catch (Exception) {
// do nothing
}
}
}
// PDB coordinates are in angstroms. Convert to nanometres.
Vector3 position = new Vector3();
position.x = float.Parse(record.Substring(30, 8)) / 10;
position.y = float.Parse(record.Substring(38, 8)) / 10;
position.z = float.Parse(record.Substring(46, 8)) / 10;
atomIndex++;
Atom atom = new Atom(atomIndex, atomID, atomName, element, position, charge);
//Debug.Log("Atom: " + atom);
// check for and store main chain elements.
if (recordName.Equals("ATOM") && residue.ResidueType != StandardResidue.None)
{
switch (atom.Name)
{
case "N":
residue.AmineNitrogen = atom;
break;
case "CA":
residue.AlphaCarbon = atom;
break;
case "C":
residue.CarbonylCarbon = atom;
break;
case "O":
case "O1":
case "OT1":
residue.CarbonylOxygen = atom;
break;
}
}
atom.ResidueIndex = residueIndex;
atom.ResidueID = currentResidueID;
atom.ResidueName = residue.Name;
atom.ResidueType = residue.ResidueType;
if (currentChainID != "")
{
atom.ChainID = currentChainID;
}
residue.Atoms.Add(atomIndex, atom);
model.AddAtom(atomIndex, atom);
break;
case "TER":
Console.WriteLine("Found TER");
TERFound = true;
break;
case "TITLE":
if (model.Title == null)
{
model.Title = "";
}
// many PDB's have long remark sections. Abbreviate for now.
if (model.Title.Length < 200)
{
model.Title += record.Substring(7) + "\n";
}
break;
case "ENDMDL":
case "END":
// currently only parse the first model in the file
EOF = true;
break;
}
}
}
if (residue != null)
{
model.AddResidue(residueIndex, residue);
if (chain != null)
{
chain.AddResidue(residueIndex, residue);
}
}
if (chain != null && currentChainID != "")
{
model.AddChain(chain);
}
}
catch (Exception e) {
throw new FileParseException(e.Message);
}
finally {
if (sr != null)
{
sr.Close();
}
}
return(model);
}
public static void ParseGromacs()
{
Console.WriteLine("Parsing GRO File");
Stopwatch stopWatch = new Stopwatch();
stopWatch.Start();
PrimaryStructure model = GROStructureParser.GetStructure(filepath + structureFile);
stopWatch.Stop();
Console.WriteLine("Structure Parsing Complete [" + stopWatch.ElapsedMilliseconds + " ms]");
Console.WriteLine("Atom Count: " + model.Atoms().Count);
foreach (Atom atom in model.Atoms())
{
Console.WriteLine("Atom " + atom.Index + ": " + atom.ToString());
}
Console.WriteLine("\n---------------------\n");
Dictionary <Element, Dictionary <int, Atom> > atomSet = model.GetAtomsByElement();
foreach (KeyValuePair <Element, Dictionary <int, Atom> > set in atomSet)
{
Element element = set.Key;
Console.WriteLine("Element: " + element.ToString());
Dictionary <int, Atom> atoms = set.Value;
foreach (KeyValuePair <int, Atom> atom in atoms)
{
Console.WriteLine("Atom: " + atom.Value.ToString());
}
}
foreach (Chain chain in model.Chains())
{
Console.WriteLine("\n---------------------\n");
Console.WriteLine("Chain ID: " + chain.ID);
Console.WriteLine("Chain Residue Count: " + chain.Residues.Count);
foreach (Residue residue in chain.Residues)
{
Console.WriteLine("ResidueID: " + residue.ID + ", Residue Name: " + residue.Name);
}
}
stopWatch.Reset();
stopWatch.Start();
int NumberOfProcessorCores = 6;
Dictionary <int, Bond> bonds = model.GenerateBonds(NumberOfProcessorCores);
Console.WriteLine("Bond generation complete [" + stopWatch.ElapsedMilliseconds + " ms]");
int count = 0;
foreach (KeyValuePair <int, Bond> bond in bonds)
{
Atom atom1 = model.Atoms()[bond.Value.Atom1Index];
Atom atom2 = model.Atoms()[bond.Value.Atom2Index];
if ((atom1.Element == Element.O && atom2.Element == Element.H) ||
(atom2.Element == Element.O && atom1.Element == Element.H))
{
Console.WriteLine("O-H bond found. Distance: " + Vector3.Distance(atom1.Position, atom2.Position));
count++;
if (count > 5)
{
break;
}
}
}
Console.WriteLine("Getting frame count from trajectory file");
stopWatch.Reset();
stopWatch.Start();
count = XTCTrajectoryParser.GetFrameCount(filepath + trajectoryFile);
stopWatch.Stop();
Console.WriteLine("Frame count complete [" + stopWatch.ElapsedMilliseconds + " ms]");
Console.WriteLine("Frames counted: " + count);
}
public PDBStructureCreator(PrimaryStructure structure, PrimaryStructureFrame frame)
{
this.structure = structure;
this.frame = frame;
}
public PDBStructureCreator(PrimaryStructure structure)
{
this.structure = structure;
}
/// <summary>
/// generate a box from a provided Primary Structure
/// </summary>
/// <returns></returns>
public BoundingBox(PrimaryStructure structure, bool flipZ = false)
{
float minx = 0;
float maxx = 0;
float miny = 0;
float maxy = 0;
float minz = 0;
float maxz = 0;
bool firstAtom = true;
foreach (Atom atom in structure.Atoms())
{
if (firstAtom)
{
minx = atom.Position.x;
maxx = atom.Position.x;
miny = atom.Position.y;
maxy = atom.Position.y;
minz = atom.Position.z;
maxz = atom.Position.z;
firstAtom = false;
}
else
{
if (atom.Position.x < minx)
{
minx = atom.Position.x;
}
if (atom.Position.x > maxx)
{
maxx = atom.Position.x;
}
if (atom.Position.y < miny)
{
miny = atom.Position.y;
}
if (atom.Position.y > maxy)
{
maxy = atom.Position.y;
}
if (atom.Position.z < minz)
{
minz = atom.Position.z;
}
if (atom.Position.z > maxz)
{
maxz = atom.Position.z;
}
}
}
float edgeBuffer = 0.1f;
minx -= edgeBuffer;
maxx += edgeBuffer;
miny -= edgeBuffer;
maxy += edgeBuffer;
minz -= edgeBuffer;
maxz += edgeBuffer;
if (flipZ)
{
minz *= -1;
maxz *= -1;
}
setVectors(minx, maxx, miny, maxy, minz, maxz);
}
private static PrimaryStructure GetFrame(StreamReader sr)
{
PrimaryStructure model;
// todo: improve file format error handling for misformatted files
try {
model = new PrimaryStructure();
string titleLine = sr.ReadLine();
// remove any blank lines before title line
while (titleLine != null && titleLine.Trim().Equals(""))
{
titleLine = sr.ReadLine();
}
if (titleLine == null)
{
return(null);
}
model.Title = titleLine;
model.Time = 0;
Regex g = new Regex(@"\st=\s*(\d+\.?\d*)");
Match m = g.Match(titleLine);
if (m.Success)
{
string frameTimeString = m.Groups[1].Value;
model.Time = float.Parse(frameTimeString);
// Console.WriteLine("Success parsing[" + titleLine + "] for frame time");
}
else
{
// no frame time in header. Assume structure file, leave frame time at 0;
// return false;
}
int residueIndex = 0;
int chainIndex = 0;
Chain chain = null;
Residue residue = null;
int currentResidueID = -1;
Residue lastResidue = null;
int atomCount = Int32.Parse(sr.ReadLine().Trim());
for (int i = 0; i < atomCount; i++)
{
string atomLine = sr.ReadLine();
if (atomLine == null) // if something is wrong with the file, i.e. ends before total atom count
{
break;
}
// if atom residue number not the existing residue number store the existing residue and instantiate new residue
int atomResidueID = int.Parse(atomLine.Substring(0, 5).Trim());
if (atomResidueID != currentResidueID)
{
// store residue - first time here will be null
if (residue != null)
{
model.AddResidue(residueIndex, residue);
if (chain != null)
{
chain.AddResidue(residueIndex, residue);
}
}
residueIndex++;
currentResidueID = atomResidueID;
string residueName = atomLine.Substring(5, 5).Trim();
lastResidue = residue;
residue = new Residue(residueIndex, currentResidueID, residueName);
// Residue type changes used to capture chain information. May not be 100% accurate but not parsing topology files so options are limited.
// Also checking to see if last two atoms before end of amino acid were Oxygen, signifying a chain terminator
if ((lastResidue == null || residue.ResidueType != lastResidue.ResidueType) ||
(lastResidue.ResidueType == StandardResidue.AminoAcid && model.Atoms()[i - 1].Element == Element.O && model.Atoms()[i - 2].Element == Element.O))
{
if (chain != null)
{
model.AddChain(chain);
}
chainIndex++;
chain = new Chain(chainIndex, chainIndex.ToString());
}
}
int atomIndex = i;
int atomID = int.Parse((atomLine.Substring(15, 5)).Trim());
string atomName = atomLine.Substring(10, 5).Trim();
Element element = ElementHelper.Parse(atomName);
Vector3 position = new Vector3();
position.x = float.Parse(atomLine.Substring(20, 8));
position.y = float.Parse(atomLine.Substring(28, 8));
position.z = float.Parse(atomLine.Substring(36, 8));
Atom atom = new Atom(atomIndex, atomID, atomName, element, position);
// check for and store main chain elements.
if (residue.ResidueType != StandardResidue.None)
{
switch (atom.Name)
{
case "N":
residue.AmineNitrogen = atom;
break;
case "CA":
residue.AlphaCarbon = atom;
break;
case "C":
residue.CarbonylCarbon = atom;
break;
case "O":
case "O1":
case "OT1":
residue.CarbonylOxygen = atom;
break;
}
}
atom.ResidueIndex = residueIndex;
atom.ResidueID = currentResidueID;
atom.ResidueName = residue.Name;
atom.ResidueType = residue.ResidueType;
atom.ChainID = chainIndex.ToString();
residue.Atoms.Add(atomIndex, atom);
model.AddAtom(atomIndex, atom);
}
if (residue != null)
{
model.AddResidue(residueIndex, residue);
if (chain != null)
{
chain.AddResidue(residueIndex, residue);
}
}
if (chain != null)
{
model.AddChain(chain);
}
// Parse box vectors.
// todo: test and make this more robust for various string lengths
float[] vertices = parseBoxLine(sr.ReadLine());
model.OriginalBoundingBox = new BoundingBox(vertices[0], vertices[1], vertices[2], vertices[3], vertices[4], vertices[5], vertices[6], vertices[7], vertices[8]);
}
catch (Exception e) {
throw new FileParseException(e.Message);
}
return(model);
}
