/// <summary>
/// Loads a PDB file. If target record types are specified, it will only load records of those types.
/// </summary>
/// <param name="filename">The filename of a PDB file.</param>
/// <param name="targetRecordTypes">Target PDB file record types.</param>
/// <param name="parseAll">Parse the whole PDB file into class instances.</param>
public void LoadFile(string filename, string[] targetRecordTypes = null, bool parseAll = true)
{
UnloadFile();
if (!File.Exists(filename))
{
throw new FileNotFoundException("The PDB file specified was not found.", filename);
//return;
}
FileLinesArray = File.ReadAllLines(filename);
TargetRecordTypes = targetRecordTypes;
if (parseAll)
{
ProteinDataBankFileRecordList = new List <ProteinDataBankFileRecord>();
for (int lineIndex = 0; lineIndex < FileLinesArray.Length; lineIndex++)
{
ProteinDataBankFileRecord proteinDataBankFileRecord = ProteinDataBaseFileLineRecord(FileLinesArray[lineIndex]);
ProteinDataBankFileRecordList.Add(proteinDataBankFileRecord);
}
FileLinesArray = null;
}
}
/// <summary>
/// ToString override. Returns a string representation of the currently loaded records of the PDB file.
/// </summary>
/// <returns></returns>
public override string ToString()
{
var stringBuilder = new StringBuilder();
for (int recordIndex = 0; recordIndex < Count; recordIndex++)
{
ProteinDataBankFileRecord proteinDataBankFileRecord = NextRecord();
stringBuilder.AppendLine(proteinDataBankFileRecord != null ? proteinDataBankFileRecord.ToString() : string.Empty);
}
return(stringBuilder.ToString());
}
/// <summary>
/// Returns the next PDB file record.
/// </summary>
/// <returns></returns>
public ProteinDataBankFileRecord NextRecord()
{
_currentFileRecordNumber++;
if (ProteinDataBankFileRecordList != null && _currentFileRecordNumber < ProteinDataBankFileRecordList.Count)
{
return(ProteinDataBankFileRecordList[_currentFileRecordNumber]);
}
if (FileLinesArray != null && _currentFileRecordNumber < FileLinesArray.Length)
{
ProteinDataBankFileRecord proteinDataBankFileRecord = ProteinDataBaseFileLineRecord(FileLinesArray[_currentFileRecordNumber]);
return(proteinDataBankFileRecord);
}
UnloadFile();
return(null);
}
public static int PdbModelCount(string pdbFilename, int maximumToFind = -1)
{
if (!File.Exists(pdbFilename))
{
throw new FileNotFoundException("File not found", pdbFilename);
}
// Load pdb/protein file, excluding all records but ATOM, HETATM and TER.
var proteinDataBankFile = new ProteinDataBankFile(pdbFilename, new[]
{
MODEL_Record.MODEL_Field.FieldName
//ProteinDataBankFile.ENDMDL_Record.ENDMDL_Field.FieldName,
});
int modelCount = 0;
//var endModelCount = 0;
for (int proteinDataBankFileRecordIndex = 0; proteinDataBankFileRecordIndex < proteinDataBankFile.Count; proteinDataBankFileRecordIndex++)
{
ProteinDataBankFileRecord currentRecord = proteinDataBankFile.NextRecord();
if (currentRecord == null)
{
continue;
}
if (currentRecord.GetType() == typeof(MODEL_Record))
{
var model = (MODEL_Record)currentRecord;
modelCount++;
if (maximumToFind > -1 && modelCount > maximumToFind)
{
break;
}
}
//else if (currentRecord.GetType() == typeof(ProteinDataBankFile.ENDMDL_Record))
//{
// var endModel = (ProteinDataBankFile.ENDMDL_Record)currentRecord;
// endModelCount++;
//}
}
return(modelCount);
}
/// <summary>
/// Loads a PDB file. If target record types are specified, it will only load records of those types.
/// </summary>
/// <param name="filename">The filename of a PDB file.</param>
/// <param name="targetRecordTypes">Target PDB file record types.</param>
/// <param name="parseAll">Parse the whole PDB file into class instances.</param>
public void LoadFile(string[] structureFileLines, string[] targetRecordTypes = null, bool parseAll = true)
{
UnloadFile();
FileLinesArray = structureFileLines;
TargetRecordTypes = targetRecordTypes;
if (parseAll)
{
ProteinDataBankFileRecordList = new List <ProteinDataBankFileRecord>();
for (int lineIndex = 0; lineIndex < FileLinesArray.Length; lineIndex++)
{
ProteinDataBankFileRecord proteinDataBankFileRecord = ProteinDataBaseFileLineRecord(FileLinesArray[lineIndex]);
ProteinDataBankFileRecordList.Add(proteinDataBankFileRecord);
}
FileLinesArray = null;
}
}
/// <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);
}
/// <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);
}
public static int PdbAtomicChainsCount(string pdbFilename, string[] chainIdWhiteList = null, int maximumToFind = -1)
{
if (!File.Exists(pdbFilename))
{
throw new FileNotFoundException("File not found", pdbFilename);
}
// 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
});
int atomCount = 0;
int hetAtomCount = 0;
var terCount = 0;
var chainNames = new List <string>();
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;
string chainIdKey = atom.chainID.FieldValue.Trim().ToUpperInvariant();
if (chainIdWhiteList != null && !chainIdWhiteList.Contains(chainIdKey))
{
continue;
}
atomCount++;
if (!string.IsNullOrWhiteSpace(atom.chainID.FieldValue) && !chainNames.Contains(atom.chainID.FieldValue))
{
chainNames.Add(atom.chainID.FieldValue);
if (maximumToFind > -1 && chainNames.Count > maximumToFind)
{
break;
}
}
}
else if (currentRecord.GetType() == typeof(HETATM_Record))
{
var hetatm = (HETATM_Record)currentRecord;
string chainIdKey = hetatm.chainID.FieldValue.Trim().ToUpperInvariant();
if (chainIdWhiteList != null && !chainIdWhiteList.Contains(chainIdKey))
{
continue;
}
hetAtomCount++;
if (!string.IsNullOrWhiteSpace(hetatm.chainID.FieldValue) && !chainNames.Contains(hetatm.chainID.FieldValue))
{
chainNames.Add(hetatm.chainID.FieldValue);
if (maximumToFind > -1 && chainNames.Count > maximumToFind)
{
break;
}
}
}
else if (currentRecord.GetType() == typeof(ENDMDL_Record))
{
break;
}
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 (!string.IsNullOrWhiteSpace(ter.chainID.FieldValue) && !chainNames.Contains(ter.chainID.FieldValue))
{
chainNames.Add(ter.chainID.FieldValue);
}
}
}
int chainNamesCount = chainNames.Distinct().Count();
//var chainCount = chainNamesCount > terCount ? chainNamesCount : terCount;
return(chainNamesCount);
}
public static List <string> PdbAtomAcidList(string pdbFilename, string[] chainIdWhiteList = null, bool onlyCarbonAlphas = true, bool distinct = true)
{
if (!File.Exists(pdbFilename))
{
throw new FileNotFoundException("File not found", pdbFilename);
}
// 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
});
var atomAcidList = new List <string>();
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;
string chainIdKey = atom.chainID.FieldValue.Trim().ToUpperInvariant();
if (chainIdWhiteList != null && !chainIdWhiteList.Contains(chainIdKey))
{
continue;
}
if (onlyCarbonAlphas && atom.name.FieldValue.Trim().ToUpperInvariant() != StaticValues.CarbonAlpha)
{
continue;
}
if (!distinct || !atomAcidList.Contains(atom.resName.FieldValue))
{
atomAcidList.Add(atom.resName.FieldValue);
}
}
else if (currentRecord.GetType() == typeof(HETATM_Record))
{
var hetatm = (HETATM_Record)currentRecord;
string chainIdKey = hetatm.chainID.FieldValue.Trim().ToUpperInvariant();
if (chainIdWhiteList != null && !chainIdWhiteList.Contains(chainIdKey))
{
continue;
}
if (onlyCarbonAlphas && hetatm.name.FieldValue.Trim().ToUpperInvariant() != StaticValues.CarbonAlpha)
{
continue;
}
if (!distinct || !atomAcidList.Contains(hetatm.resName.FieldValue))
{
atomAcidList.Add(hetatm.resName.FieldValue);
}
}
//else if (currentRecord.GetType() == typeof (HETATM_Record))
//{
// var ter = (HETATM_Record)currentRecord;
// string chainIdKey = ter.chainID.FieldValue.Trim().ToUpperInvariant();
// if (chainIdWhiteList != null && !chainIdWhiteList.Contains(chainIdKey))
// {
// continue;
// }
//}
}
return(atomAcidList);
}
