public static ATOM_Record FindAtomInsidePdbFileChain(ProteinChainListContainer pdbFileChains, int chainIndex, int residueSequenceIndex)
{
if (ParameterValidation.IsProteinChainListContainerNullOrEmpty(pdbFileChains))
{
return(null);
}
if (ParameterValidation.IsChainIndexInvalid(chainIndex))
{
throw new ArgumentOutOfRangeException(nameof(chainIndex));
}
if (ParameterValidation.IsResidueSequenceIndexInvalid(residueSequenceIndex, true))
{
throw new ArgumentOutOfRangeException(nameof(residueSequenceIndex));
}
for (int memberIndex = 0; memberIndex < pdbFileChains.ChainList[chainIndex].AtomList.Count; memberIndex++)
{
ATOM_Record atom = pdbFileChains.ChainList[chainIndex].AtomList[memberIndex];
if (ProteinDataBankFileOperations.NullableTryParseInt32(atom.resSeq.FieldValue) == residueSequenceIndex)
{
return(atom);
}
}
return(null);
}
public static ATOM_Record FindAtomInsideSingularInteractionsChain(ProteinChainListContainer singularAaToAaInteractions, int chainIndex, int residueSequenceIndex)
{
if (ParameterValidation.IsProteinChainListContainerNullOrEmpty(singularAaToAaInteractions))
{
return(null);
}
if (ParameterValidation.IsChainIndexInvalid(chainIndex))
{
throw new ArgumentOutOfRangeException(nameof(chainIndex));
}
if (ParameterValidation.IsResidueSequenceIndexInvalid(residueSequenceIndex, true))
{
throw new ArgumentOutOfRangeException(nameof(residueSequenceIndex));
}
// Loop through atoms in specified chain to find atom with given residue sequence index
for (int atomIndex = 0; atomIndex < singularAaToAaInteractions.ChainList[chainIndex].AtomList.Count; atomIndex++)
{
ATOM_Record atom = singularAaToAaInteractions.ChainList[chainIndex].AtomList[atomIndex];
if (ProteinDataBankFileOperations.NullableTryParseInt32(atom.resSeq.FieldValue) == residueSequenceIndex)
{
return(atom);
}
}
return(null);
}
public static bool IsAtomNullOrEmpty(ATOM_Record atom)
{
if (atom == null || string.IsNullOrWhiteSpace(atom.resName.FieldValue))
{
return(true);
}
return(false);
}
/// <summary>
/// Initializes a new instance of the <see cref="AtomPair" /> class.
/// </summary>
/// <param name="atom1">The first atom.</param>
/// <param name="atom2">The second atom.</param>
/// <param name="distance">
/// The distance between atom1 and atom2 (presumed already calculated as it is expensive to
/// calculate 3d distance).
/// </param>
public AtomPair(ATOM_Record atom1, ATOM_Record atom2, decimal distance = 0)
{
//PdbIdAtom1 = null;
Atom1 = atom1;
//PdbIdAtom2 = null;
Atom2 = atom2;
Distance = distance;
}
public static Point1D AtomResidueSequencePoint1D(ATOM_Record atom)
{
if (ParameterValidation.IsAtomNullOrEmpty(atom))
{
throw new ArgumentOutOfRangeException(nameof(atom));
}
return(new Point1D(atom.resSeq.FieldValue));
}
public static Point3D AtomPoint3D(ATOM_Record atom)
{
if (ParameterValidation.IsAtomNullOrEmpty(atom))
{
throw new ArgumentOutOfRangeException(nameof(atom));
}
return(new Point3D(atom.x.FieldValue, atom.y.FieldValue, atom.z.FieldValue));
}
public AtomPair(string pdbIdAtom1, ATOM_Record atom1, string pdbIdAtom2, ATOM_Record atom2, decimal distance = 0)
{
Atom1 = atom1;
Atom2 = atom2;
Distance = distance;
Atom1FullProteinInterfaceId.ProteinId = pdbIdAtom1;
Atom2FullProteinInterfaceId.ProteinId = pdbIdAtom2;
}
/// <summary>
/// This method returns the total number of interactions an atom has with non-proteinInterfaces in oppoproteinInterface chains. The method
/// requires the object returned by the FindInteractionsBetweenProteinInterfaces method.
/// </summary>
/// <param name="interactionBetweenProteinInterfacesContainer"></param>
/// <param name="sourceChainIndex"></param>
/// <param name="atomToFind"></param>
/// <returns></returns>
public static int CountAtomInteractionsOutsideProteinInterface(
InteractionBetweenProteinInterfacesListContainer interactionBetweenProteinInterfacesContainer,
int sourceChainIndex,
ATOM_Record atomToFind
)
{
int totalInteractionsOutsideProteinInterfaces = interactionBetweenProteinInterfacesContainer.InteractionBetweenNonProteinInterfacesList.Count(
a => (a.Atom1.FullProteinInterfaceId.ChainId == sourceChainIndex && a.Atom1.Atom == atomToFind) ||
(a.Atom2.FullProteinInterfaceId.ChainId == sourceChainIndex && a.Atom2.Atom == atomToFind));
return(totalInteractionsOutsideProteinInterfaces);
}
/// <summary>
/// Get the lowest (minimum) and highest (maximum) residue sequence index (as found in the pdb file) in an interaction
/// proteinInterface.
/// </summary>
/// <param name="proteinInterface"></param>
/// <param name="singularAaToAaInteractions"></param>
/// <param name="chainIndex"></param>
/// <returns></returns>
public static MinMax MinMaxResidueSequenceIndex(ClusteringFullResultListContainer.Chain.Stage.Cluster proteinInterface, ProteinChainListContainer singularAaToAaInteractions, int chainIndex)
{
if (ParameterValidation.IsClusterNullOrEmpty(proteinInterface))
{
throw new ArgumentNullException(nameof(proteinInterface));
}
if (ParameterValidation.IsProteinChainListContainerNullOrEmpty(singularAaToAaInteractions))
{
throw new ArgumentNullException(nameof(singularAaToAaInteractions));
}
if (ParameterValidation.IsChainIndexInvalid(chainIndex))
{
throw new ArgumentOutOfRangeException(nameof(chainIndex));
}
int proteinInterfaceMin = 0;
int proteinInterfaceMax = 0;
for (int memberIndex = 0; memberIndex < proteinInterface.AtomIndexList.Count; memberIndex++)
{
int member = proteinInterface.AtomIndexList[memberIndex];
ATOM_Record atom = singularAaToAaInteractions.ChainList[chainIndex].AtomList[member];
var residueSequenceIndex = ProteinDataBankFileOperations.NullableTryParseInt32(atom.resSeq.FieldValue);
if (residueSequenceIndex == null)
{
continue;
}
if (memberIndex == 0 || residueSequenceIndex < proteinInterfaceMin)
{
proteinInterfaceMin = residueSequenceIndex.Value;
}
if (memberIndex == 0 || residueSequenceIndex > proteinInterfaceMax)
{
proteinInterfaceMax = residueSequenceIndex.Value;
}
}
return(new MinMax(proteinInterfaceMin, proteinInterfaceMax));
}
public static int AtomIndexPositionInProteinInterface(
ProteinChainListContainer singularAaToAaInteractions,
ClusteringFullResultListContainer proteinInterfacesClusteringResult,
int[] detectedBestStages,
int chainIndex,
int proteinInterfaceIndex,
ATOM_Record atomPositionToFind)
{
List <ClusteringFullResultListContainer.Chain.Stage.Cluster> proteinInterfaceList = proteinInterfacesClusteringResult.ChainList[chainIndex].StageList[detectedBestStages[chainIndex]].ClusterList;
List <ClusteringFullResultListContainer.Chain.Stage.Cluster> nonEmptyProteinInterfaceList = proteinInterfaceList.Where(a => a != null && a.AtomIndexList != null && a.AtomIndexList.Count > 0).ToList();
if (proteinInterfaceIndex > nonEmptyProteinInterfaceList.Count - 1)
{
throw new ArgumentOutOfRangeException(nameof(proteinInterfaceIndex), proteinInterfaceIndex, "proteinInterfaceIndex was greater than the number of proteinInterfaces found.");
}
ClusteringFullResultListContainer.Chain.Stage.Cluster proteinInterface = nonEmptyProteinInterfaceList[proteinInterfaceIndex];
if (proteinInterface.AtomIndexList.Count == 0)
{
return(-1);
}
MinMax minMaxResidueSequenceIndex = MinMaxResidueSequenceIndex(proteinInterface, singularAaToAaInteractions, chainIndex);
int proteinInterfaceLength = CalculateProteinInterfaceLength(minMaxResidueSequenceIndex.Min, minMaxResidueSequenceIndex.Max);
var residueSequenceToFind = ProteinDataBankFileOperations.NullableTryParseInt32(atomPositionToFind.resSeq.FieldValue);
if (residueSequenceToFind == null)
{
return(-1);
}
int index = residueSequenceToFind.Value - minMaxResidueSequenceIndex.Min; // zero based
return(index);
}
public InteractionAtom(ATOM_Record atom, FullProteinInterfaceId fullProteinInterfaceId)
{
Atom = atom;
FullProteinInterfaceId = fullProteinInterfaceId;
}
public InteractionAtom(ATOM_Record atom)
{
Atom = atom;
}
/// <summary>
/// This method loads 1 pdb file and returns the atoms contained in the different chains.
/// </summary>
/// <param name="pdbFilename"></param>
/// <param name="chainIdWhiteList"></param>
/// <param name="minimumChains"></param>
/// <param name="maximumChains"></param>
/// <returns></returns>
public static ProteinChainListContainer PdbAtomicChains(string pdbFilename, string[] chainIdWhiteList, int minimumChains = 2, int maximumChains = 2, bool onlyCarbonAlphas = false)
{
////////Console.WriteLine(pdbFilename);
// Check file exists.
if (!File.Exists(pdbFilename))
{
//return null;
throw new FileNotFoundException("File not found", pdbFilename);
}
// Check min chains not more than max chains.
if (minimumChains > maximumChains)
{
throw new ArgumentOutOfRangeException(nameof(minimumChains));
}
// Load pdb/protein file, excluding all records but ATOM, HETATM and TER.
var proteinDataBankFile = new ProteinDataBankFile(pdbFilename, new[]
{
ATOM_Record.ATOM_Field.FieldName,
HETATM_Record.HETATM_Field.FieldName,
TER_Record.TER_Field.FieldName,
MODEL_Record.MODEL_Field.FieldName,
ENDMDL_Record.ENDMDL_Field.FieldName
});
// Make new array for atom chain.
//List<ATOM_Record>[] proteinFileChains = new List<ATOM_Record>[maximumChains];
var pdbFileChains = new ProteinChainListContainer();
//var fileError = false;
//var chainCount = 0;
// Loop through all the previously loaded protein file records to make lists of atoms in each chain.
// Also make a list of residue numbers (which will be sorted later just in case it is out of order).
var atomRecordListDictionary = new Dictionary <string, List <ProteinDataBankFileRecord> >();
var hetAtomRecordListDictionary = new Dictionary <string, List <ProteinDataBankFileRecord> >();
int terCount = 0;
for (int proteinDataBankFileRecordIndex = 0; proteinDataBankFileRecordIndex < proteinDataBankFile.Count; proteinDataBankFileRecordIndex++)
{
ProteinDataBankFileRecord currentRecord = proteinDataBankFile.NextRecord();
if (currentRecord == null)
{
continue;
}
if (currentRecord.GetType() == typeof(ATOM_Record))
{
var atom = (ATOM_Record)currentRecord;
if (onlyCarbonAlphas && atom.name.FieldValue.Trim().ToUpperInvariant() != StaticValues.CarbonAlpha)
{
continue;
}
string chainIdKey = atom.chainID.FieldValue.Trim().ToUpperInvariant();
if (chainIdWhiteList != null && !chainIdWhiteList.Contains(chainIdKey))
{
continue;
}
if (!atomRecordListDictionary.ContainsKey(chainIdKey))
{
atomRecordListDictionary.Add(chainIdKey, new List <ProteinDataBankFileRecord>());
}
if (ParameterValidation.IsAminoAcidCodeValid(atom.resName.FieldValue))
{
atomRecordListDictionary[chainIdKey].Add(atom);
}
}
else if (currentRecord.GetType() == typeof(HETATM_Record))
{
var hetatm = (HETATM_Record)currentRecord;
if (onlyCarbonAlphas && hetatm.name.FieldValue.Trim().ToUpperInvariant() != StaticValues.CarbonAlpha)
{
continue;
}
string chainIdKey = hetatm.chainID.FieldValue.Trim().ToUpperInvariant();
if (chainIdWhiteList != null && !chainIdWhiteList.Contains(chainIdKey))
{
continue;
}
if (!hetAtomRecordListDictionary.ContainsKey(chainIdKey))
{
hetAtomRecordListDictionary.Add(chainIdKey, new List <ProteinDataBankFileRecord>());
}
//if (!ParameterValidation.IsAminoAcidCodeValid(hetatm.resName.FieldValue))
//{
// ////////Console.WriteLine(hetatm.columnFormatLine);
// hetatm.resName.FieldValue = UnspecifiedOrUnknownAminoAcid.Code3L;
// hetatm.columnFormatLine = hetatm.columnFormatLine.Remove(ProteinDataBankFile.HETATM_Record.resName_Field.FirstColumn - 1, (ProteinDataBankFile.HETATM_Record.resName_Field.LastColumn - ProteinDataBankFile.HETATM_Record.resName_Field.FirstColumn) + 1);
// hetatm.columnFormatLine = hetatm.columnFormatLine.Insert(ProteinDataBankFile.HETATM_Record.resName_Field.FirstColumn - 1, UnspecifiedOrUnknownAminoAcid.Code3L);
// ////////Console.WriteLine(hetatm.columnFormatLine);
//}
if (ParameterValidation.IsAminoAcidCodeValid(hetatm.resName.FieldValue))
{
hetAtomRecordListDictionary[chainIdKey].Add(hetatm);
}
}
else if (currentRecord.GetType() == typeof(TER_Record))
{
var ter = (TER_Record)currentRecord;
string chainIdKey = ter.chainID.FieldValue.Trim().ToUpperInvariant();
if (chainIdWhiteList != null && !chainIdWhiteList.Contains(chainIdKey))
{
continue;
}
terCount++;
if (terCount >= maximumChains)
{
break;
//return null;
}
}
else if (currentRecord.GetType() == typeof(ENDMDL_Record))
{
break;
}
}
// file has been parsed so clear used file data from memory as soon as possible
proteinDataBankFile.UnloadFile();
int totalChains = atomRecordListDictionary.Count > hetAtomRecordListDictionary.Count ? atomRecordListDictionary.Count : hetAtomRecordListDictionary.Count;
for (int chainIndex = 0; chainIndex < totalChains; chainIndex++)
{
pdbFileChains.ChainList.Add(new ProteinAtomListContainer());
}
atomRecordListDictionary = atomRecordListDictionary.OrderBy(a => a.Key).ToDictionary(a => a.Key, a => a.Value);
int chainIndex2 = -1;
foreach (var atomRecordListKvp in atomRecordListDictionary)
{
chainIndex2++;
string chainName = atomRecordListKvp.Key;
List <ProteinDataBankFileRecord> chainRecords = atomRecordListKvp.Value;
if (chainRecords == null || chainRecords.Count == 0)
{
continue;
}
chainRecords = chainRecords.OrderBy(a => NullableTryParseInt32(((ATOM_Record)a).serial.FieldValue)).ToList();
pdbFileChains.ChainList[chainIndex2].AtomList = chainRecords.Select(a => (ATOM_Record)a).ToList();
}
hetAtomRecordListDictionary = hetAtomRecordListDictionary.OrderBy(a => a.Key).ToDictionary(a => a.Key, a => a.Value);
int chainIndex3 = -1;
foreach (var hetAtomRecordListKvp in hetAtomRecordListDictionary)
{
chainIndex3++;
string chainName = hetAtomRecordListKvp.Key;
List <ProteinDataBankFileRecord> chainRecords = hetAtomRecordListKvp.Value;
if (chainRecords == null || chainRecords.Count == 0)
{
continue;
}
chainRecords = chainRecords.OrderBy(a => NullableTryParseInt32(((HETATM_Record)a).serial.FieldValue)).ToList();
foreach (ProteinDataBankFileRecord proteinDataBankFileRecord in chainRecords)
{
var chainRecord = (HETATM_Record)proteinDataBankFileRecord;
string residueSequenceToFind = chainRecord.resSeq.FieldValue;
string atomChainId = chainRecord.chainID.FieldValue.Trim().ToUpperInvariant();
if (!atomRecordListDictionary.ContainsKey(atomChainId) || atomRecordListDictionary[atomChainId].Count(a => ((ATOM_Record)a).resSeq.FieldValue == residueSequenceToFind) == 0)
{
ATOM_Record atom = ConvertHetatmRecordToAtomRecord(chainRecord);
pdbFileChains.ChainList[chainIndex3].AtomList.Add(atom);
}
}
}
int nonEmptyChainCount = pdbFileChains.ChainList.Count(a => a != null && a.AtomList != null && a.AtomList.Count > 0);
if (nonEmptyChainCount >= minimumChains && nonEmptyChainCount <= maximumChains)
{
return(pdbFileChains);
}
////////Console.WriteLine("Too many chains (" + nonEmptyChainCount + "): " + pdbFilename);
return(null);
}
/// <summary>
/// This method finds interactions between detected proteinInterfaces. It is specific to dimers with exactly two chains. [Chain A
/// ProteinInterface Index, Chain B ProteinInterface Index]
/// </summary>
/// <param name="cancellationToken"></param>
/// <param name="pdbFilename"></param>
/// <param name="pdbFileChains"></param>
/// <param name="chainInteractingAtomLists"></param>
/// <param name="fullClusteringResult"></param>
/// <param name="proteinInterfacesClusteringResult"></param>
/// <param name="detectedFinalStageIndexes"></param>
/// <param name="pdbIdChainIdList"></param>
/// <returns></returns>
public static InteractionBetweenProteinInterfacesListContainer FindInteractionsBetweenAnyProteinInterfaces(
CancellationToken cancellationToken,
decimal maxAtomInterationDistance,
string pdbFilename,
Dictionary<string, List<string>> pdbIdChainIdList,
ProteinChainListContainer pdbFileChains,
ProteinChainListContainer chainInteractingAtomLists,
ClusteringFullResultListContainer fullClusteringResult,
ClusteringFullResultListContainer proteinInterfacesClusteringResult,
int[] detectedFinalStageIndexes)
{
if (string.IsNullOrWhiteSpace(pdbFilename))
{
throw new ArgumentOutOfRangeException(nameof(pdbFilename));
}
if (!File.Exists(pdbFilename))
{
throw new FileNotFoundException("File not found", pdbFilename);
}
if (ParameterValidation.IsProteinChainListContainerNullOrEmpty(chainInteractingAtomLists))
{
throw new ArgumentOutOfRangeException(nameof(chainInteractingAtomLists));
}
if (ParameterValidation.IsClusteringFullResultListContainerNullOrEmpty(fullClusteringResult))
{
throw new ArgumentOutOfRangeException(nameof(fullClusteringResult));
}
if (ParameterValidation.IsClusteringFullResultListContainerNullOrEmpty(proteinInterfacesClusteringResult))
{
throw new ArgumentOutOfRangeException(nameof(proteinInterfacesClusteringResult));
}
if (ParameterValidation.IsIntArrayNullOrEmpty(detectedFinalStageIndexes))
{
throw new ArgumentOutOfRangeException(nameof(detectedFinalStageIndexes));
}
string proteinId = ProteinDataBankFileOperations.PdbIdFromPdbFilename(pdbFilename);
var interactionBetweenProteinInterfacesListContainer = new InteractionBetweenProteinInterfacesListContainer();
List<AtomPair> interactionList;
if (pdbFileChains != null && pdbFileChains.ChainList != null && pdbFileChains.ChainList.Count > 0)
{
interactionList = SearchInteractions.FindInteractions(cancellationToken, maxAtomInterationDistance, proteinId, pdbIdChainIdList, pdbFileChains); //, false, -1, pdbFileChains);
}
else
{
interactionList = SearchInteractions.FindInteractions(cancellationToken, maxAtomInterationDistance, pdbFilename, pdbIdChainIdList);
}
var interactionInsideProteinInterfaceArray = new bool[interactionList.Count];
////////Console.WriteLine("");
////////Console.WriteLine("");
////////Console.WriteLine("------------------ START ------------------");
//int c = 0;
for (int chainIndexA = 0; chainIndexA < proteinInterfacesClusteringResult.ChainList.Count; chainIndexA++)
{
for (int chainIndexB = 0; chainIndexB < proteinInterfacesClusteringResult.ChainList.Count; chainIndexB++)
{
if (chainIndexA == chainIndexB || chainIndexB < chainIndexA)
{
continue;
}
List<ClusteringFullResultListContainer.Chain.Stage.Cluster> proteinInterfaceListA = proteinInterfacesClusteringResult.ChainList[chainIndexA].StageList[detectedFinalStageIndexes[chainIndexA]].ClusterList;
List<ClusteringFullResultListContainer.Chain.Stage.Cluster> proteinInterfaceListB = proteinInterfacesClusteringResult.ChainList[chainIndexB].StageList[detectedFinalStageIndexes[chainIndexB]].ClusterList;
int realProteinInterfaceIndexA = -1;
for (int proteinInterfaceIndexA = 0; proteinInterfaceIndexA < proteinInterfaceListA.Count; proteinInterfaceIndexA++)
{
int realProteinInterfaceIndexB = -1;
List<int> proteinInterfaceMemberIndexListA = proteinInterfaceListA[proteinInterfaceIndexA].AtomIndexList;
List<ATOM_Record> proteinInterfaceAtomListA = proteinInterfaceMemberIndexListA.Select(proteinInterfaceMemberIndexA => chainInteractingAtomLists.ChainList[chainIndexA].AtomList[proteinInterfaceMemberIndexA]).ToList();
proteinInterfaceAtomListA = proteinInterfaceAtomListA.OrderBy(a => ProteinDataBankFileOperations.NullableTryParseInt32(a.resSeq.FieldValue)).ToList();
if (proteinInterfaceAtomListA.Count > 0)
{
realProteinInterfaceIndexA++;
}
else
{
continue;
}
for (int proteinInterfaceIndexB = 0; proteinInterfaceIndexB < proteinInterfaceListB.Count; proteinInterfaceIndexB++)
{
List<int> proteinInterfaceMemberIndexListB = proteinInterfaceListB[proteinInterfaceIndexB].AtomIndexList;
List<ATOM_Record> proteinInterfaceAtomListB = proteinInterfaceMemberIndexListB.Select(proteinInterfaceMemberIndexB => chainInteractingAtomLists.ChainList[chainIndexB].AtomList[proteinInterfaceMemberIndexB]).ToList();
proteinInterfaceAtomListB = proteinInterfaceAtomListB.OrderBy(b => ProteinDataBankFileOperations.NullableTryParseInt32(b.resSeq.FieldValue)).ToList();
if (proteinInterfaceAtomListB.Count > 0)
{
realProteinInterfaceIndexB++;
}
else
{
continue;
}
for (int proteinInterfaceAtomListIndexA = 0; proteinInterfaceAtomListIndexA < proteinInterfaceAtomListA.Count; proteinInterfaceAtomListIndexA++)
{
ATOM_Record atomA = proteinInterfaceAtomListA[proteinInterfaceAtomListIndexA];
for (int proteinInterfaceAtomListIndexB = 0; proteinInterfaceAtomListIndexB < proteinInterfaceAtomListB.Count; proteinInterfaceAtomListIndexB++)
{
ATOM_Record atomB = proteinInterfaceAtomListB[proteinInterfaceAtomListIndexB];
//c++;
////////Console.WriteLine(c.ToString().PadLeft(5) +
// " Chain " + chainIndexA + " (" + proteinInterfaceListA.Count(a => a.AtomIndexList.Count > 0) + " proteinInterfaces) ProteinInterface " + realProteinInterfaceIndexA + " (" + proteinInterfaceAtomListA.Count + " atoms) <--->" +
// " Chain " + chainIndexB + " (" + proteinInterfaceListB.Count(a => a.AtomIndexList.Count > 0) + " proteinInterfaces) ProteinInterface " + realProteinInterfaceIndexB + " (" + proteinInterfaceAtomListB.Count + " atoms) --->" +
// " chainID " + atomA.chainID.FieldValue + " resName " + atomA.resName.FieldValue + " resSeq " + atomA.resSeq.FieldValue + " <--->" +
// " chainID " + atomB.chainID.FieldValue + " resName " + atomB.resName.FieldValue + " resSeq " + atomB.resSeq.FieldValue);
for (int interactionIndex = 0; interactionIndex < interactionList.Count; interactionIndex++)
{
AtomPair interaction = interactionList[interactionIndex];
if ((interaction.Atom1 == atomA && interaction.Atom2 == atomB) || (interaction.Atom1 == atomB && interaction.Atom2 == atomA))
{
interactionInsideProteinInterfaceArray[interactionIndex] = true;
var interactionBetweenProteinInterfaces = new InteractionBetweenProteinInterfaces();
interactionBetweenProteinInterfacesListContainer.InteractionBetweenProteinInterfacesList.Add(interactionBetweenProteinInterfaces);
interactionBetweenProteinInterfaces.Atom1.Atom = atomA;
interactionBetweenProteinInterfaces.Atom1.FullProteinInterfaceId.ProteinId = proteinId;
interactionBetweenProteinInterfaces.Atom1.FullProteinInterfaceId.ChainId = chainIndexA;
interactionBetweenProteinInterfaces.Atom1.FullProteinInterfaceId.ProteinInterfaceId = realProteinInterfaceIndexA;
interactionBetweenProteinInterfaces.Atom2.Atom = atomB;
interactionBetweenProteinInterfaces.Atom2.FullProteinInterfaceId.ProteinId = proteinId;
interactionBetweenProteinInterfaces.Atom2.FullProteinInterfaceId.ChainId = chainIndexB;
interactionBetweenProteinInterfaces.Atom2.FullProteinInterfaceId.ProteinInterfaceId = realProteinInterfaceIndexB;
}
}
}
}
}
}
}
}
for (int interactionIndex = 0; interactionIndex < interactionInsideProteinInterfaceArray.Length; interactionIndex++)
{
bool interactionInsideProteinInterface = interactionInsideProteinInterfaceArray[interactionIndex];
if (!interactionInsideProteinInterface)
{
var interactionBetweenNonProteinInterfaces = new InteractionBetweenProteinInterfaces();
interactionBetweenProteinInterfacesListContainer.InteractionBetweenNonProteinInterfacesList.Add(interactionBetweenNonProteinInterfaces);
interactionBetweenNonProteinInterfaces.Atom1.Atom = interactionList[interactionIndex].Atom1;
interactionBetweenNonProteinInterfaces.Atom1.FullProteinInterfaceId.ProteinId = proteinId;
interactionBetweenNonProteinInterfaces.Atom1.FullProteinInterfaceId.ChainId = interactionList[interactionIndex].Atom1FullProteinInterfaceId.ChainId;
interactionBetweenNonProteinInterfaces.Atom1.FullProteinInterfaceId.ProteinInterfaceId = -1;
interactionBetweenNonProteinInterfaces.Atom2.Atom = interactionList[interactionIndex].Atom2;
interactionBetweenNonProteinInterfaces.Atom2.FullProteinInterfaceId.ProteinId = proteinId;
interactionBetweenNonProteinInterfaces.Atom2.FullProteinInterfaceId.ChainId = interactionList[interactionIndex].Atom2FullProteinInterfaceId.ChainId;
interactionBetweenNonProteinInterfaces.Atom2.FullProteinInterfaceId.ProteinInterfaceId = -1;
}
}
////////Console.WriteLine("------------------ END ------------------");
// ensure sorted order
interactionBetweenProteinInterfacesListContainer.InteractionBetweenProteinInterfacesList = interactionBetweenProteinInterfacesListContainer.InteractionBetweenProteinInterfacesList
.OrderBy(a => a.Atom1.FullProteinInterfaceId.ChainId)
.ThenBy(a => a.Atom1.FullProteinInterfaceId.ProteinInterfaceId)
.ThenBy(a => ProteinDataBankFileOperations.NullableTryParseInt32(a.Atom1.Atom.resSeq.FieldValue))
.ThenBy(a => a.Atom2.FullProteinInterfaceId.ChainId)
.ThenBy(a => a.Atom2.FullProteinInterfaceId.ProteinInterfaceId)
.ThenBy(a => ProteinDataBankFileOperations.NullableTryParseInt32(a.Atom2.Atom.resSeq.FieldValue))
.ToList();
interactionBetweenProteinInterfacesListContainer.InteractionBetweenNonProteinInterfacesList = interactionBetweenProteinInterfacesListContainer.InteractionBetweenNonProteinInterfacesList
.OrderBy(a => a.Atom1.FullProteinInterfaceId.ChainId)
.ThenBy(a => a.Atom1.FullProteinInterfaceId.ProteinInterfaceId)
.ThenBy(a => ProteinDataBankFileOperations.NullableTryParseInt32(a.Atom1.Atom.resSeq.FieldValue))
.ThenBy(a => a.Atom2.FullProteinInterfaceId.ChainId)
.ThenBy(a => a.Atom2.FullProteinInterfaceId.ProteinInterfaceId)
.ThenBy(a => ProteinDataBankFileOperations.NullableTryParseInt32(a.Atom2.Atom.resSeq.FieldValue))
.ToList();
// remove duplicates (as the list is sorted, duplicates will always be together in the list)
for (int index = interactionBetweenProteinInterfacesListContainer.InteractionBetweenProteinInterfacesList.Count - 1; index > 0; index--)
{
InteractionBetweenProteinInterfaces lastInteractionBetweenProteinInterfaces = interactionBetweenProteinInterfacesListContainer.InteractionBetweenProteinInterfacesList[index - 1];
InteractionBetweenProteinInterfaces thisInteractionBetweenProteinInterfaces = interactionBetweenProteinInterfacesListContainer.InteractionBetweenProteinInterfacesList[index];
if (lastInteractionBetweenProteinInterfaces == null || thisInteractionBetweenProteinInterfaces == null)
{
continue;
}
if (thisInteractionBetweenProteinInterfaces.Atom1.FullProteinInterfaceId.ProteinId == lastInteractionBetweenProteinInterfaces.Atom1.FullProteinInterfaceId.ProteinId &&
thisInteractionBetweenProteinInterfaces.Atom1.FullProteinInterfaceId.ChainId == lastInteractionBetweenProteinInterfaces.Atom1.FullProteinInterfaceId.ChainId &&
thisInteractionBetweenProteinInterfaces.Atom1.FullProteinInterfaceId.ProteinInterfaceId == lastInteractionBetweenProteinInterfaces.Atom1.FullProteinInterfaceId.ProteinInterfaceId &&
thisInteractionBetweenProteinInterfaces.Atom1.Atom == lastInteractionBetweenProteinInterfaces.Atom1.Atom &&
thisInteractionBetweenProteinInterfaces.Atom2.FullProteinInterfaceId.ProteinId == lastInteractionBetweenProteinInterfaces.Atom2.FullProteinInterfaceId.ProteinId &&
thisInteractionBetweenProteinInterfaces.Atom2.FullProteinInterfaceId.ChainId == lastInteractionBetweenProteinInterfaces.Atom2.FullProteinInterfaceId.ChainId &&
thisInteractionBetweenProteinInterfaces.Atom2.FullProteinInterfaceId.ProteinInterfaceId == lastInteractionBetweenProteinInterfaces.Atom2.FullProteinInterfaceId.ProteinInterfaceId &&
thisInteractionBetweenProteinInterfaces.Atom2.Atom == lastInteractionBetweenProteinInterfaces.Atom2.Atom)
{
interactionBetweenProteinInterfacesListContainer.InteractionBetweenProteinInterfacesList.RemoveAt(index - 1);
//////Console.WriteLine("removed duplicate");
}
}
for (int index = interactionBetweenProteinInterfacesListContainer.InteractionBetweenNonProteinInterfacesList.Count - 1; index > 0; index--)
{
InteractionBetweenProteinInterfaces lastInteractionBetweenProteinInterfaces = interactionBetweenProteinInterfacesListContainer.InteractionBetweenNonProteinInterfacesList[index - 1];
InteractionBetweenProteinInterfaces thisInteractionBetweenProteinInterfaces = interactionBetweenProteinInterfacesListContainer.InteractionBetweenNonProteinInterfacesList[index];
if (lastInteractionBetweenProteinInterfaces == null || thisInteractionBetweenProteinInterfaces == null)
{
continue;
}
if (thisInteractionBetweenProteinInterfaces.Atom1.FullProteinInterfaceId.ProteinId == lastInteractionBetweenProteinInterfaces.Atom1.FullProteinInterfaceId.ProteinId &&
thisInteractionBetweenProteinInterfaces.Atom1.FullProteinInterfaceId.ChainId == lastInteractionBetweenProteinInterfaces.Atom1.FullProteinInterfaceId.ChainId &&
thisInteractionBetweenProteinInterfaces.Atom1.FullProteinInterfaceId.ProteinInterfaceId == lastInteractionBetweenProteinInterfaces.Atom1.FullProteinInterfaceId.ProteinInterfaceId &&
thisInteractionBetweenProteinInterfaces.Atom1.Atom == lastInteractionBetweenProteinInterfaces.Atom1.Atom &&
thisInteractionBetweenProteinInterfaces.Atom2.FullProteinInterfaceId.ProteinId == lastInteractionBetweenProteinInterfaces.Atom2.FullProteinInterfaceId.ProteinId &&
thisInteractionBetweenProteinInterfaces.Atom2.FullProteinInterfaceId.ChainId == lastInteractionBetweenProteinInterfaces.Atom2.FullProteinInterfaceId.ChainId &&
thisInteractionBetweenProteinInterfaces.Atom2.FullProteinInterfaceId.ProteinInterfaceId == lastInteractionBetweenProteinInterfaces.Atom2.FullProteinInterfaceId.ProteinInterfaceId &&
thisInteractionBetweenProteinInterfaces.Atom2.Atom == lastInteractionBetweenProteinInterfaces.Atom2.Atom)
{
interactionBetweenProteinInterfacesListContainer.InteractionBetweenNonProteinInterfacesList.RemoveAt(index - 1);
//////Console.WriteLine("removed duplicate");
}
}
return interactionBetweenProteinInterfacesListContainer;
}
/// <summary>
/// Load proteinInterface data from the PDB file based on a list of already detected proteinInterfaces.
/// The detected proteinInterfaces may be missing data such as other atoms or residues which are also in the proteinInterface but were not
/// directly interacting.
/// The positions and lengths of the proteinInterfaces are also calculated.
/// </summary>
/// <param name="pdbFilename"></param>
/// <param name="pdbFileChains"></param>
/// <param name="singularAaToAaInteractions"></param>
/// <param name="proteinInterfacesClusteringResult"></param>
/// <param name="detectedBestStages"></param>
/// <param name="interactionBetweenProteinInterfacesContainer"></param>
/// <returns></returns>
public static List <ProteinInterfaceSequenceAndPositionData> AnalyseProteinInterfacesSequenceAndPositionData(
string pdbFilename,
Dictionary <string, List <string> > pdbIdChainIdList,
ProteinChainListContainer pdbFileChains,
ProteinChainListContainer singularAaToAaInteractions,
ClusteringFullResultListContainer proteinInterfacesClusteringResult,
int[] detectedBestStages,
InteractionBetweenProteinInterfacesListContainer interactionBetweenProteinInterfacesContainer)
{
if (string.IsNullOrWhiteSpace(pdbFilename))
{
throw new ArgumentOutOfRangeException(nameof(pdbFilename));
}
if (!File.Exists(pdbFilename))
{
throw new FileNotFoundException("File not found", pdbFilename);
}
if (ParameterValidation.IsProteinChainListContainerNullOrEmpty(singularAaToAaInteractions))
{
throw new ArgumentOutOfRangeException(nameof(singularAaToAaInteractions));
}
if (ParameterValidation.IsClusteringFullResultListContainerNullOrEmpty(proteinInterfacesClusteringResult))
{
throw new ArgumentOutOfRangeException(nameof(proteinInterfacesClusteringResult));
}
if (ParameterValidation.IsIntArrayNullOrEmpty(detectedBestStages))
{
throw new ArgumentOutOfRangeException(nameof(detectedBestStages));
}
// ProteinInterfaces are clusters with non-proteinInterfaces removed.
var result = new List <ProteinInterfaceSequenceAndPositionData>();
string proteinId = ProteinDataBankFileOperations.PdbIdFromPdbFilename(pdbFilename);
int totalChains = proteinInterfacesClusteringResult.ChainList.Count;
for (int chainIndex = 0; chainIndex < totalChains; chainIndex++)
{
int stageIndex = detectedBestStages[chainIndex];
string chainIdLetter = SpreadsheetFileHandler.AlphabetLetterRollOver(chainIndex);
List <ClusteringFullResultListContainer.Chain.Stage.Cluster> proteinInterfaceList = proteinInterfacesClusteringResult.ChainList[chainIndex].StageList[stageIndex].ClusterList;
List <ClusteringFullResultListContainer.Chain.Stage.Cluster> nonEmptyProteinInterfaceList = proteinInterfaceList.Where(a => a != null && a.AtomIndexList != null && a.AtomIndexList.Count > 0).ToList();
// loop through each proteinInterface
for (int proteinInterfaceIndex = 0; proteinInterfaceIndex < nonEmptyProteinInterfaceList.Count; proteinInterfaceIndex++)
{
ClusteringFullResultListContainer.Chain.Stage.Cluster proteinInterface = nonEmptyProteinInterfaceList[proteinInterfaceIndex];
// Find min and max residue sequence index value in the proteinInterface
MinMax proteinInterfaceResidueSequenceIndexes = MinMaxResidueSequenceIndex(proteinInterface, singularAaToAaInteractions, chainIndex);
int proteinInterfaceLength = CalculateProteinInterfaceLength(proteinInterfaceResidueSequenceIndexes.Min, proteinInterfaceResidueSequenceIndexes.Max);
string proteinInterfaceIdLetter = SpreadsheetFileHandler.AlphabetLetterRollOver(proteinInterfaceIndex);
var proteinInterfacePositionData = new ProteinInterfaceSequenceAndPositionData
{
FullProteinInterfaceId = new FullProteinInterfaceId(proteinId, chainIndex, proteinInterfaceIndex, proteinInterfaceResidueSequenceIndexes.Min, proteinInterfaceResidueSequenceIndexes.Max),
ChainIdLetter = chainIdLetter,
ProteinInterfaceIdLetter = proteinInterfaceIdLetter,
StartPosition = proteinInterfaceResidueSequenceIndexes.Min,
EndPosition = proteinInterfaceResidueSequenceIndexes.Max,
ProteinInterfaceLength = CalculateProteinInterfaceLength(proteinInterfaceResidueSequenceIndexes.Min, proteinInterfaceResidueSequenceIndexes.Max)
};
proteinInterfacePositionData.AminoAcidSequenceAllResidueSequenceIndexes = new ProteinInterfaceAminoAcidMetaData[proteinInterfacePositionData.ProteinInterfaceLength];
proteinInterfacePositionData.AminoAcidSequenceAll1L = "";
proteinInterfacePositionData.AminoAcidSequenceInteractionsAll1L = "";
proteinInterfacePositionData.AminoAcidSequenceInteractionsInsideProteinInterfacesOnly1L = "";
proteinInterfacePositionData.AminoAcidSequenceInteractionsNone1L = "";
proteinInterfacePositionData.AminoAcidSequenceInteractionsOutsideProteinInterfacesOnly1L = "";
proteinInterfacePositionData.AminoAcidSequenceAll3L = "";
proteinInterfacePositionData.AminoAcidSequenceInteractionsAll3L = "";
proteinInterfacePositionData.AminoAcidSequenceInteractionsInsideProteinInterfacesOnly3L = "";
proteinInterfacePositionData.AminoAcidSequenceInteractionsNone3L = "";
proteinInterfacePositionData.AminoAcidSequenceInteractionsOutsideProteinInterfacesOnly3L = "";
//int foundAtomCount = 0;
const string placeholder1L = "_";
const string placeholder3L = "___";
for (int residueSequenceIndex = proteinInterfaceResidueSequenceIndexes.Min; residueSequenceIndex <= proteinInterfaceResidueSequenceIndexes.Max; residueSequenceIndex++)
{
/* questions
* 1. does this reside interact with another reside which is also part of a proteinInterface?
* 2. if not, does this reside interact at all?
*/
var proteinInterfaceAminoAcidMetaData = new ProteinInterfaceAminoAcidMetaData();
proteinInterfacePositionData.AminoAcidSequenceAllResidueSequenceIndexes[proteinInterfacePositionData.AminoAcidSequenceAll1L.Length] = proteinInterfaceAminoAcidMetaData;
ATOM_Record foundAtomInsidePdbFile = AtomSearchMethods.FindAtomInsidePdbFileChain(pdbFileChains, chainIndex, residueSequenceIndex);
if (foundAtomInsidePdbFile == null)
{
// Non-CA atom is loaded here in case of missing CA atom to find the AA code for the resSeq index
var chainIdList = pdbIdChainIdList != null ? (pdbIdChainIdList.ContainsKey(proteinId) ? pdbIdChainIdList[proteinId].ToArray() : null) : null;
ProteinChainListContainer pdbFileChains2 = ProteinDataBankFileOperations.PdbAtomicChains(pdbFilename, chainIdList, -1, -1, false);
foundAtomInsidePdbFile = AtomSearchMethods.FindAtomInsidePdbFileChain(pdbFileChains2, chainIndex, residueSequenceIndex);
}
proteinInterfaceAminoAcidMetaData.PdbResidueSequenceIndex = residueSequenceIndex;
proteinInterfaceAminoAcidMetaData.ArrayMemberIndex = pdbFileChains.ChainList[chainIndex].AtomList.IndexOf(foundAtomInsidePdbFile);
proteinInterfaceAminoAcidMetaData.OppoproteinInterfaceInteractions = new bool[proteinInterfaceLength];
if (foundAtomInsidePdbFile != null)
{
proteinInterfacePositionData.AminoAcidSequenceAll1L += AminoAcidConversions.AminoAcidNameToCode1L(foundAtomInsidePdbFile.resName.FieldValue);
proteinInterfacePositionData.AminoAcidSequenceAll3L += foundAtomInsidePdbFile.resName.FieldValue.PadRight(3, '_');
}
else
{
proteinInterfacePositionData.AminoAcidSequenceAll1L += placeholder1L;
proteinInterfacePositionData.AminoAcidSequenceInteractionsAll1L += placeholder1L;
proteinInterfacePositionData.AminoAcidSequenceInteractionsInsideProteinInterfacesOnly1L += placeholder1L;
proteinInterfacePositionData.AminoAcidSequenceInteractionsOutsideProteinInterfacesOnly1L += placeholder1L;
proteinInterfacePositionData.AminoAcidSequenceInteractionsNone1L += placeholder1L;
proteinInterfacePositionData.AminoAcidSequenceAll3L += placeholder3L;
proteinInterfacePositionData.AminoAcidSequenceInteractionsAll3L += placeholder3L;
proteinInterfacePositionData.AminoAcidSequenceInteractionsInsideProteinInterfacesOnly3L += placeholder3L;
proteinInterfacePositionData.AminoAcidSequenceInteractionsOutsideProteinInterfacesOnly3L += placeholder3L;
proteinInterfacePositionData.AminoAcidSequenceInteractionsNone3L += placeholder3L;
proteinInterfaceAminoAcidMetaData.ProteinInterfaceInteractionType = ProteinInterfaceInteractionType.NoInteractionFound;
proteinInterfaceAminoAcidMetaData.NonProteinInterfaceInteractionResidueNames1L += placeholder1L;
proteinInterfaceAminoAcidMetaData.NonProteinInterfaceInteractionResidueNames3L += placeholder3L;
continue;
}
List <ATOM_Record> foundAtomInteractingWithAnotherProteinInterface = AtomSearchMethods.FindAtomInteractingWithOtherProteinInterfaces(foundAtomInsidePdbFile, interactionBetweenProteinInterfacesContainer, FindAtomInteractingWithAnotherProteinInterfaceOptions.FindAtomsInteractingWithOtherProteinInterfaces);
List <ATOM_Record> foundAtomInteractingWithNonProteinInterface = AtomSearchMethods.FindAtomInteractingWithOtherProteinInterfaces(foundAtomInsidePdbFile, interactionBetweenProteinInterfacesContainer, FindAtomInteractingWithAnotherProteinInterfaceOptions.FindAtomsInteractingWithNonProteinInterfaces);
proteinInterfaceAminoAcidMetaData.OppoproteinInterfaceInteractions = AminoAcidInteractionVector(singularAaToAaInteractions, proteinInterfacesClusteringResult, detectedBestStages, interactionBetweenProteinInterfacesContainer, chainIndex, proteinInterfaceIndex, residueSequenceIndex);
proteinInterfaceAminoAcidMetaData.ResidueName1L = AminoAcidConversions.AminoAcidNameToCode1L(foundAtomInsidePdbFile.resName.FieldValue);
proteinInterfaceAminoAcidMetaData.ResidueName3L = foundAtomInsidePdbFile.resName.FieldValue.PadRight(3, '_');
if (foundAtomInteractingWithAnotherProteinInterface != null)
{
foreach (ATOM_Record atom in foundAtomInteractingWithAnotherProteinInterface)
{
proteinInterfaceAminoAcidMetaData.ProteinInterfaceInteractionResidueNames1L += AminoAcidConversions.AminoAcidNameToCode1L(atom.resName.FieldValue);
proteinInterfaceAminoAcidMetaData.ProteinInterfaceInteractionResidueNames3L += atom.resName.FieldValue.PadRight(3, '_');
}
}
if (foundAtomInteractingWithNonProteinInterface != null)
{
foreach (ATOM_Record atom in foundAtomInteractingWithNonProteinInterface)
{
proteinInterfaceAminoAcidMetaData.NonProteinInterfaceInteractionResidueNames1L += AminoAcidConversions.AminoAcidNameToCode1L(atom.resName.FieldValue);
proteinInterfaceAminoAcidMetaData.NonProteinInterfaceInteractionResidueNames3L += atom.resName.FieldValue.PadRight(3, '_');
}
}
if (foundAtomInteractingWithAnotherProteinInterface != null && foundAtomInteractingWithAnotherProteinInterface.Count > 0)
{
proteinInterfacePositionData.AminoAcidSequenceInteractionsAll1L += AminoAcidConversions.AminoAcidNameToCode1L(foundAtomInsidePdbFile.resName.FieldValue);
proteinInterfacePositionData.AminoAcidSequenceInteractionsInsideProteinInterfacesOnly1L += AminoAcidConversions.AminoAcidNameToCode1L(foundAtomInsidePdbFile.resName.FieldValue);
proteinInterfacePositionData.AminoAcidSequenceInteractionsOutsideProteinInterfacesOnly1L += placeholder1L;
proteinInterfacePositionData.AminoAcidSequenceInteractionsNone1L += placeholder1L;
proteinInterfacePositionData.AminoAcidSequenceInteractionsAll3L += foundAtomInsidePdbFile.resName.FieldValue.PadRight(3, '_');
proteinInterfacePositionData.AminoAcidSequenceInteractionsInsideProteinInterfacesOnly3L += foundAtomInsidePdbFile.resName.FieldValue.PadRight(3, '_');
proteinInterfacePositionData.AminoAcidSequenceInteractionsOutsideProteinInterfacesOnly3L += placeholder3L;
proteinInterfacePositionData.AminoAcidSequenceInteractionsNone3L += placeholder3L;
proteinInterfaceAminoAcidMetaData.ProteinInterfaceInteractionType = ProteinInterfaceInteractionType.InteractionWithAnotherProteinInterface;
if (foundAtomInteractingWithNonProteinInterface != null && foundAtomInteractingWithNonProteinInterface.Count > 0)
{
proteinInterfaceAminoAcidMetaData.ProteinInterfaceInteractionType |= ProteinInterfaceInteractionType.InteractionWithNonProteinInterface;
}
}
else if (foundAtomInteractingWithNonProteinInterface != null && foundAtomInteractingWithNonProteinInterface.Count > 0)
{
proteinInterfacePositionData.AminoAcidSequenceInteractionsAll1L += AminoAcidConversions.AminoAcidNameToCode1L(foundAtomInsidePdbFile.resName.FieldValue);
proteinInterfacePositionData.AminoAcidSequenceInteractionsInsideProteinInterfacesOnly1L += placeholder1L;
proteinInterfacePositionData.AminoAcidSequenceInteractionsOutsideProteinInterfacesOnly1L += AminoAcidConversions.AminoAcidNameToCode1L(foundAtomInsidePdbFile.resName.FieldValue);
proteinInterfacePositionData.AminoAcidSequenceInteractionsNone1L += placeholder1L;
proteinInterfacePositionData.AminoAcidSequenceInteractionsAll3L += foundAtomInsidePdbFile.resName.FieldValue.PadRight(3, '_');
proteinInterfacePositionData.AminoAcidSequenceInteractionsInsideProteinInterfacesOnly3L += placeholder3L;
proteinInterfacePositionData.AminoAcidSequenceInteractionsOutsideProteinInterfacesOnly3L += foundAtomInsidePdbFile.resName.FieldValue.PadRight(3, '_');
proteinInterfacePositionData.AminoAcidSequenceInteractionsNone3L += placeholder3L;
proteinInterfaceAminoAcidMetaData.ProteinInterfaceInteractionType = ProteinInterfaceInteractionType.InteractionWithNonProteinInterface;
}
else
{
proteinInterfacePositionData.AminoAcidSequenceInteractionsAll1L += placeholder1L;
proteinInterfacePositionData.AminoAcidSequenceInteractionsInsideProteinInterfacesOnly1L += placeholder1L;
proteinInterfacePositionData.AminoAcidSequenceInteractionsOutsideProteinInterfacesOnly1L += placeholder1L;
proteinInterfacePositionData.AminoAcidSequenceInteractionsNone1L += AminoAcidConversions.AminoAcidNameToCode1L(foundAtomInsidePdbFile.resName.FieldValue);
proteinInterfacePositionData.AminoAcidSequenceInteractionsAll3L += placeholder3L;
proteinInterfacePositionData.AminoAcidSequenceInteractionsInsideProteinInterfacesOnly3L += placeholder3L;
proteinInterfacePositionData.AminoAcidSequenceInteractionsOutsideProteinInterfacesOnly3L += placeholder3L;
proteinInterfacePositionData.AminoAcidSequenceInteractionsNone3L += foundAtomInsidePdbFile.resName.FieldValue.PadRight(3, '_');
proteinInterfaceAminoAcidMetaData.ProteinInterfaceInteractionType = ProteinInterfaceInteractionType.NoInteractionFound;
}
}
result.Add(proteinInterfacePositionData);
}
}
return(result);
}
public static List <ATOM_Record> FindAtomInteractingWithOtherProteinInterfaces(ATOM_Record atom, InteractionBetweenProteinInterfacesListContainer interactionBetweenProteinInterfacesContainer, FindAtomInteractingWithAnotherProteinInterfaceOptions findAtomInteractingWithAnotherProteinInterfaceOptions)
{
if (ParameterValidation.IsAtomNullOrEmpty(atom))
{
throw new ArgumentNullException(nameof(atom));
}
if (ParameterValidation.IsInteractionBetweenProteinInterfacesListContainerNullOrEmpty(interactionBetweenProteinInterfacesContainer))
{
////////Console.WriteLine("empty");
return(null);
}
List <InteractionBetweenProteinInterfaces> searchList = null;
if (findAtomInteractingWithAnotherProteinInterfaceOptions == FindAtomInteractingWithAnotherProteinInterfaceOptions.FindAtomsInteractingWithOtherProteinInterfaces)
{
searchList = interactionBetweenProteinInterfacesContainer.InteractionBetweenProteinInterfacesList;
}
else if (findAtomInteractingWithAnotherProteinInterfaceOptions == FindAtomInteractingWithAnotherProteinInterfaceOptions.FindAtomsInteractingWithNonProteinInterfaces)
{
searchList = interactionBetweenProteinInterfacesContainer.InteractionBetweenNonProteinInterfacesList;
}
else
{
throw new NotImplementedException();
}
if (searchList == null)
{
////////Console.WriteLine("returning null");
return(null);
}
var result = new List <ATOM_Record>();
foreach (InteractionBetweenProteinInterfaces interaction in searchList)
{
if (interaction.Atom1.Atom == atom && interaction.Atom2.Atom != atom)
{
//return interaction.Atom1.Atom;
result.Add(interaction.Atom2.Atom);
}
if (interaction.Atom1.Atom != atom && interaction.Atom2.Atom == atom)
{
//return interaction.Atom2.Atom;
result.Add(interaction.Atom1.Atom);
}
}
//if (result.Count == 0)
//{
// //////Console.WriteLine("returning empty list");
//}
return(result);
}
/// <summary>
/// Returns a PDB record class instance of the appropriate type for the given line of PDB file.
/// </summary>
/// <param name="columnFormatLine"></param>
/// <returns></returns>
public ProteinDataBankFileRecord ProteinDataBaseFileLineRecord(string columnFormatLine)
{
ProteinDataBankFileRecord result = null;
string recordType = ProteinDataBankFileLineRecordType(columnFormatLine);
if ((TargetRecordTypes != null) && (TargetRecordTypes.Length > 0) && (!TargetRecordTypes.Contains(recordType)))
{
return(result);
}
switch (recordType)
{
case "HEADER":
result = new HEADER_Record(columnFormatLine);
break;
case "OBSLTE":
result = new OBSLTE_Record(columnFormatLine);
break;
case "TITLE":
result = new TITLE_Record(columnFormatLine);
break;
case "SPLIT":
result = new SPLIT_Record(columnFormatLine);
break;
case "CAVEAT":
result = new CAVEAT_Record(columnFormatLine);
break;
case "COMPND":
result = new COMPND_Record(columnFormatLine);
break;
case "SOURCE":
result = new SOURCE_Record(columnFormatLine);
break;
case "KEYWDS":
result = new KEYWDS_Record(columnFormatLine);
break;
case "EXPDTA":
result = new EXPDTA_Record(columnFormatLine);
break;
case "NUMMDL":
result = new NUMMDL_Record(columnFormatLine);
break;
case "MDLTYP":
result = new MDLTYP_Record(columnFormatLine);
break;
case "AUTHOR":
result = new AUTHOR_Record(columnFormatLine);
break;
case "REVDAT":
result = new REVDAT_Record(columnFormatLine);
break;
case "SPRSDE":
result = new SPRSDE_Record(columnFormatLine);
break;
case "JRNL":
result = new JRNL_DOI_Record(columnFormatLine);
if (((JRNL_DOI_Record)result).DOI.FieldValue == JRNL_DOI_Record.DOI_Field.FieldName)
{
break;
}
result = new JRNL_PMID_Record(columnFormatLine);
if (((JRNL_PMID_Record)result).PMID.FieldValue == JRNL_PMID_Record.PMID_Field.FieldName)
{
break;
}
result = new JRNL_PUBL_Record(columnFormatLine);
if (((JRNL_PUBL_Record)result).PUBL.FieldValue == JRNL_PUBL_Record.PUBL_Field.FieldName)
{
break;
}
result = new JRNL_REFN_ISSN_or_ESSN_Record(columnFormatLine);
if (((JRNL_REFN_ISSN_or_ESSN_Record)result).REFN.FieldValue == JRNL_REFN_ISSN_or_ESSN_Record.REFN_Field.FieldName && (((JRNL_REFN_ISSN_or_ESSN_Record)result).ISSN_or_ESSN.FieldValue.ToUpperInvariant() == "ISSN" || ((JRNL_REFN_ISSN_or_ESSN_Record)result).ISSN_or_ESSN.FieldValue.ToUpperInvariant() == "ESSN"))
{
break;
}
result = new JRNL_REF_V_Record(columnFormatLine);
if (((JRNL_REF_V_Record)result).REF.FieldValue == JRNL_REF_V_Record.REF_Field.FieldName && ((JRNL_REF_V_Record)result).V_.FieldValue == JRNL_REF_V_Record.V_Field.FieldName)
{
break;
}
result = new JRNL_REFN_Record(columnFormatLine);
if (((JRNL_REFN_Record)result).REFN.FieldValue == JRNL_REFN_Record.REFN_Field.FieldName)
{
break;
}
result = new JRNL_REF_TOBEPUBLISHED_Record(columnFormatLine);
if (((JRNL_REF_TOBEPUBLISHED_Record)result).REF.FieldValue == JRNL_REF_TOBEPUBLISHED_Record.REF_Field.FieldName)
{
break;
}
result = new JRNL_Record(columnFormatLine);
break;
case "REMARK":
result = new REMARK_1_AUTH_Record(columnFormatLine);
if (((REMARK_1_AUTH_Record)result)._1.FieldValue == REMARK_1_AUTH_Record._1_Field.FieldName && ((REMARK_1_AUTH_Record)result).AUTH.FieldValue == REMARK_1_AUTH_Record.AUTH_Field.FieldName)
{
break;
}
result = new REMARK_1_PUBL_Record(columnFormatLine);
if (((REMARK_1_PUBL_Record)result)._1.FieldValue == REMARK_1_PUBL_Record._1_Field.FieldName && ((REMARK_1_PUBL_Record)result).PUBL.FieldValue == REMARK_1_PUBL_Record.PUBL_Field.FieldName)
{
break;
}
result = new REMARK_1_REF_V_Record(columnFormatLine);
if (((REMARK_1_REF_V_Record)result)._1.FieldValue == REMARK_1_REF_V_Record._1_Field.FieldName && ((REMARK_1_REF_V_Record)result).REF.FieldValue == REMARK_1_REF_V_Record.REF_Field.FieldName && ((REMARK_1_REF_V_Record)result).V_.FieldValue == REMARK_1_REF_V_Record.V_Field.FieldName)
{
break;
}
result = new REMARK_1_REFERENCE_Record(columnFormatLine);
if (((REMARK_1_REFERENCE_Record)result)._1.FieldValue == REMARK_1_REFERENCE_Record._1_Field.FieldName && ((REMARK_1_REFERENCE_Record)result).REFERENCE.FieldValue == REMARK_1_REFERENCE_Record.REFERENCE_Field.FieldName)
{
break;
}
result = new REMARK_1_REFN_ISSN_or_ESSN_Record(columnFormatLine);
if (((REMARK_1_REFN_ISSN_or_ESSN_Record)result)._1.FieldValue == REMARK_1_REFN_ISSN_or_ESSN_Record._1_Field.FieldName && ((REMARK_1_REFN_ISSN_or_ESSN_Record)result).REFN.FieldValue == REMARK_1_REFN_ISSN_or_ESSN_Record.REFN_Field.FieldName && (((REMARK_1_REFN_ISSN_or_ESSN_Record)result).ISSN_or_ESSN.FieldValue == "ISSN" || ((REMARK_1_REFN_ISSN_or_ESSN_Record)result).ISSN_or_ESSN.FieldValue == "ESSN"))
{
break;
}
result = new REMARK_1_REFN_Record(columnFormatLine);
if (((REMARK_1_REFN_Record)result)._1.FieldValue == REMARK_1_REFN_Record._1_Field.FieldName && ((REMARK_1_REFN_Record)result).REFN.FieldValue == REMARK_1_REFN_Record.REFN_Field.FieldName)
{
break;
}
result = new REMARK_1_TITL_Record(columnFormatLine);
if (((REMARK_1_TITL_Record)result)._1.FieldValue == REMARK_1_TITL_Record._1_Field.FieldName && ((REMARK_1_TITL_Record)result).TITL.FieldValue == REMARK_1_TITL_Record.TITL_Field.FieldName)
{
break;
}
result = new REMARK_2_RESOLUTION_ANGSTROMS_Record(columnFormatLine);
if (((REMARK_2_RESOLUTION_ANGSTROMS_Record)result)._2.FieldValue == REMARK_2_RESOLUTION_ANGSTROMS_Record._2_Field.FieldName && ((REMARK_2_RESOLUTION_ANGSTROMS_Record)result).RESOLUTION_.FieldValue == REMARK_2_RESOLUTION_ANGSTROMS_Record.RESOLUTION_Field.FieldName && ((REMARK_2_RESOLUTION_ANGSTROMS_Record)result).ANGSTROMS_.FieldValue == REMARK_2_RESOLUTION_ANGSTROMS_Record.ANGSTROMS_Field.FieldName)
{
break;
}
result = new REMARK_2_RESOLUTION_NOTAPPLICABLE_Record(columnFormatLine);
if (((REMARK_2_RESOLUTION_NOTAPPLICABLE_Record)result)._2.FieldValue == REMARK_2_RESOLUTION_NOTAPPLICABLE_Record._2_Field.FieldName && ((REMARK_2_RESOLUTION_NOTAPPLICABLE_Record)result).RESOLUTION_NOT_APPLICABLE_.FieldValue == REMARK_2_RESOLUTION_NOTAPPLICABLE_Record.RESOLUTION_NOT_APPLICABLE_Field.FieldName)
{
break;
}
result = new REMARK_1_REF_TOBEPUBLISHED_Record(columnFormatLine);
if (((REMARK_1_REF_TOBEPUBLISHED_Record)result)._1.FieldValue == REMARK_1_REF_TOBEPUBLISHED_Record._1_Field.FieldName && ((REMARK_1_REF_TOBEPUBLISHED_Record)result).REF.FieldValue == REMARK_1_REF_TOBEPUBLISHED_Record.REF_Field.FieldName && ((REMARK_1_REF_TOBEPUBLISHED_Record)result).TO_BE_PUBLISHED.FieldValue == REMARK_1_REF_TOBEPUBLISHED_Record.TO_BE_PUBLISHED_Field.FieldName)
{
break;
}
result = new REMARK_Record(columnFormatLine);
break;
case "DBREF":
result = new DBREF_Record(columnFormatLine);
break;
case "DBREF1":
result = new DBREF1_Record(columnFormatLine);
break;
case "DBREF2":
result = new DBREF2_Record(columnFormatLine);
break;
case "SEQADV":
result = new SEQADV_Record(columnFormatLine);
break;
case "SEQRES":
result = new SEQRES_Record(columnFormatLine);
break;
case "MODRES":
result = new MODRES_Record(columnFormatLine);
break;
case "HET":
result = new HET_Record(columnFormatLine);
break;
case "HETNAM":
result = new HETNAM_Record(columnFormatLine);
break;
case "HETSYN":
result = new HETSYN_Record(columnFormatLine);
break;
case "FORMUL":
result = new FORMUL_Record(columnFormatLine);
break;
case "HELIX":
result = new HELIX_Record(columnFormatLine);
break;
case "SHEET":
result = new SHEET_Record(columnFormatLine);
break;
case "SSBOND":
result = new SSBOND_CYS_CYS_Record(columnFormatLine);
break;
case "LINK":
result = new LINK_Record(columnFormatLine);
break;
case "CISPEP":
result = new CISPEP_Record(columnFormatLine);
break;
case "SITE":
result = new SITE_Record(columnFormatLine);
break;
case "CRYST1":
result = new CRYST1_Record(columnFormatLine);
break;
case "ORIGX1":
result = new ORIGX1_Record(columnFormatLine);
break;
case "ORIGX2":
result = new ORIGX2_Record(columnFormatLine);
break;
case "ORIGX3":
result = new ORIGX3_Record(columnFormatLine);
break;
case "SCALE1":
result = new SCALE1_Record(columnFormatLine);
break;
case "SCALE2":
result = new SCALE2_Record(columnFormatLine);
break;
case "SCALE3":
result = new SCALE3_Record(columnFormatLine);
break;
case "MTRIX1":
result = new MTRIX1_Record(columnFormatLine);
break;
case "MTRIX2":
result = new MTRIX2_Record(columnFormatLine);
break;
case "MTRIX3":
result = new MTRIX3_Record(columnFormatLine);
break;
case "MODEL":
result = new MODEL_Record(columnFormatLine);
break;
case "ATOM":
result = new ATOM_Record(columnFormatLine);
break;
case "ANISOU":
result = new ANISOU_Record(columnFormatLine);
break;
case "TER":
result = new TER_Record(columnFormatLine);
break;
case "HETATM":
result = new HETATM_Record(columnFormatLine);
break;
case "ENDMDL":
result = new ENDMDL_Record(columnFormatLine);
break;
case "CONECT":
result = new CONECT_Record(columnFormatLine);
break;
case "MASTER":
result = new MASTER_0_Record(columnFormatLine);
break;
case "END":
result = new END_Record(columnFormatLine);
break;
}
return(result);
}
public static ATOM_Record ConvertHetatmRecordToAtomRecord(HETATM_Record hetatm)
{
var atom = new ATOM_Record("ATOM " + hetatm.ColumnFormatLine.Substring(6));
return(atom);
}
