//var scoresGrouped = scores.GroupBy(a => new Tuple<string, bool>(a.StructureFilename, a.StructureFolder.Contains("Reversed")));
//foreach (var scoreGrouped in scoresGrouped)
//{
//var output = scoreGrouped.ToList().Select(a=>a.ToString()).ToList();// .SelectMany(a => a.SubstitutionDescription == "Native (No change)" ? new[] {"", a.ToString()} : new[] {a.ToString()}).ToList();
//var output = scores.ToList().Select(a => a.ToString()).ToList();// .SelectMany(a => a.SubstitutionDescription == "Native (No change)" ? new[] {"", a.ToString()} : new[] {a.ToString()}).ToList();
//output.Insert(0, EnergyScore.Header());
//scores[1].ToString()
//File.WriteAllLines(logResultsFolder + Environment.MachineName + "_energy.csv", output);
//Environment.MachineName
//File.WriteAllLines(saveFile, output);
//}
//}
/*
* var pisaLogFiles = Directory.GetFiles(logResultsFolder, "pisa_monomer.log", SearchOption.AllDirectories);
* //var pdbtoolsLogFiles = Directory.GetFiles(logResultsFolder, "pdbtools_monomer.log", SearchOption.AllDirectories);
* var infoLogFiles = Directory.GetFiles(logResultsFolder, "substitution.log", SearchOption.AllDirectories);
*
* var folders = new List<string>();
*
* folders.AddRange(modellerLogFiles.Select(Path.GetDirectoryName).ToList());
* folders.AddRange(pisaLogFiles.Select(Path.GetDirectoryName).ToList());
* //folders.AddRange(pdbtoolsLogFiles.Select(Path.GetDirectoryName).ToList());
* folders.AddRange(infoLogFiles.Select(Path.GetDirectoryName).ToList());
* folders = folders.Distinct().ToList();
*
* var scores = new List<EnergyScore>();
*
* for (int folderIndex = 0; folderIndex < folders.Count; folderIndex++)
* {
* var folder = folders[folderIndex];
* var modellerMonomerLogFile = folder + @"\modeller_monomer_assessment.log";
* var modellerDimerLogFile = folder + @"\modeller_dimer_assessment.log";
* var pisaMonomerLogFile = folder + @"\pisa_monomer.log";
* var pisaDimerLogFile = folder + @"\pisa_dimer.log";
* //var pdbtoolsLogFile = folder + @"\pdbtools_monomer.log";
* var infoLogFile = folder + @"\substitution.log";
*
* var pisaMonomerLogFileLines = new string[0];
* var pisaDimerLogFileLines = new string[0];
* var pdbtoolsLogFileLines = new string[0];
* var modellerMonomerLogFileLines = new string[0];
* var modellerDimerLogFileLines = new string[0];
* var infoLogFileLines = new string[0];
*
* if (File.Exists(modellerMonomerLogFile)) modellerMonomerLogFileLines = File.ReadAllLines(modellerMonomerLogFile);
* if (File.Exists(modellerDimerLogFile)) modellerMonomerLogFileLines = File.ReadAllLines(modellerMonomerLogFile);
* if (File.Exists(pisaMonomerLogFile)) pisaMonomerLogFileLines = File.ReadAllLines(pisaMonomerLogFile);
* if (File.Exists(pisaDimerLogFile)) pisaDimerLogFileLines = File.ReadAllLines(pisaDimerLogFile);
*
* if (File.Exists(infoLogFile)) infoLogFileLines = File.ReadAllLines(infoLogFile);
*
* if (pisaMonomerLogFileLines.Length == 0 && pdbtoolsLogFileLines.Length == 0 && modellerMonomerLogFileLines.Length == 0 &&
* infoLogFileLines.Length == 0) continue;
*
* var folderNameSplit = folder.Replace(logResultsFolder, @"").Replace('\\', ',').Split(',');
*
* var infoScore = new EnergyScore();
*
* infoScore.StructureFolder = folder;
*
* infoScore.StructuralTruncation = folderNameSplit[0];
*
* var line = -1;
*
*
*
* infoScore.Input1QprReceptorCluster = infoLogFileLines[++line] + "-" + infoLogFileLines[++line];
* infoScore.Input1QprLigandCluster = infoLogFileLines[++line] + "-" + infoLogFileLines[++line];
*
* infoScore.Input2QplReceptorCluster = infoLogFileLines[++line] + "-" + infoLogFileLines[++line];
* infoScore.Input2QplLigandCluster = infoLogFileLines[++line] + "-" + infoLogFileLines[++line];
*
* infoScore.Input1QprReceptorPdbId = infoLogFileLines[++line] + "-" + infoLogFileLines[++line];
* infoScore.Input1QprLigandPdbId = infoLogFileLines[++line] + "-" + infoLogFileLines[++line];
*
* infoScore.Input2QplReceptorPdbId = infoLogFileLines[++line] + "-" + infoLogFileLines[++line];
* infoScore.Input2QplLigandPdbId = infoLogFileLines[++line] + "-" + infoLogFileLines[++line];
*
* infoScore.SubstitutionDescription = infoLogFileLines[++line].Replace("_", " ").Replace("Reversed", "(Reversed)");
*
* infoScore.Input1QprLigandInterface = infoLogFileLines[++line];
*
++line;
*
* infoScore.Input2QplLigandInterface = infoLogFileLines[++line];
*
*
*
* //var monomerStructFiles = new List<string> { "model_monomer.pdb", "model_locked_monomer.pdb", "model_fragment_monomer.pdb" };
* //var dimerStructFiles = new List<string> {"model_dimer.pdb", "model_locked_dimer.pdb", "model_fragment_dimer.pdb"};
*
* //crystal structure
* //if (infoScore.Input2QplLigandCluster == infoScore.Input1QprLigandCluster && infoScore.SubstitutionDescription.Replace("_", " ").ToUpperInvariant() == "Query Interface".ToUpperInvariant()) { structFiles.Add("template_ligand_all.pdb"); }
*
* foreach (var p in pdbFileNames)
* {
* var modellerMonomerLogResult = ParseModellerLog(modellerMonomerLogFileLines, infoScore, new List<string>() { p });
* //var modellerDimerLogResult = ParseModellerLog(modellerDimerLogFileLines, infoScore, new List<string>() {p});
* var pisaMonomerLogResult = ParsePisaLog(pisaMonomerLogFileLines, infoScore, new List<string>() { p });
* //var pisaDimerLogResult = ParsePisaLog(pisaDimerLogFileLines, infoScore, dimerStructFiles);
* //var pdbtoolsLogResult = ParsePdbtoolsLog(pdbtoolsLogFileLines, infoScore, structFiles);
*
*
*
* //var monomerStructFile = monomerStructFiles[index];
* //var dimerStructFile = dimerStructFiles[index];
*
* var score = new EnergyScore();
*
* var modellerMonomerScore = modellerMonomerLogResult.FirstOrDefault(a => a.StructureFilename == p);
* //var modellerDimerScoreA = modellerDimerLogResult.FirstOrDefault(a => a.StructureFilename == dimerStructFile);
* //var modellerDimerScoreB = modellerDimerLogResult.Skip(1).FirstOrDefault(a => a.StructureFilename == dimerStructFile);
*
* var pisaMonomerScore = pisaMonomerLogResult.FirstOrDefault(a => a.StructureFilename == p);
* //var pisaDimerScoreA = pisaDimerLogResult.FirstOrDefault(a => a.StructureFilename == dimerStructFile);
* //var pisaDimerScoreB = pisaDimerLogResult.Skip(1).FirstOrDefault(a => a.StructureFilename == dimerStructFile);
*
* //var pdbtoolsScore = pdbtoolsLogResult.FirstOrDefault(a => a.StructureFilename == structFile);
*
* //score.ResultGroupNumber = infoScore.ResultGroupNumber;
* score.StructureFilename = p;
* score.StructureFolder = infoScore.StructureFolder;
* score.StructuralTruncation = infoScore.StructuralTruncation;
*
* score.Input1QprReceptorCluster = infoScore.Input1QprReceptorCluster;
* score.Input1QprLigandCluster = infoScore.Input1QprLigandCluster;
* score.Input2QplReceptorCluster = infoScore.Input2QplReceptorCluster;
* score.Input2QplLigandCluster = infoScore.Input2QplLigandCluster;
* score.Input1QprReceptorPdbId = infoScore.Input1QprReceptorPdbId;
* score.Input1QprLigandPdbId = infoScore.Input1QprLigandPdbId;
* score.Input2QplReceptorPdbId = infoScore.Input2QplReceptorPdbId;
* score.Input2QplLigandPdbId = infoScore.Input2QplLigandPdbId;
* score.SubstitutionDescription = infoScore.SubstitutionDescription;
* score.Input1QprLigandInterface = infoScore.Input1QprLigandInterface;
* score.Input2QplLigandInterface = infoScore.Input2QplLigandInterface;
*
* if (modellerMonomerScore != null)
* {
* score.ModellerModelChainName = modellerMonomerScore.ModellerModelChainName;
*
* score.ModellerGa341 = modellerMonomerScore.ModellerGa341;
* score.ModellerGa341Comptactness = modellerMonomerScore.ModellerGa341Comptactness;
* score.ModellerGa341NativeEnergyCombined = modellerMonomerScore.ModellerGa341NativeEnergyCombined;
* score.ModellerGa341NativeEnergyPair = modellerMonomerScore.ModellerGa341NativeEnergyPair;
* score.ModellerGa341NativeEnergySurface = modellerMonomerScore.ModellerGa341NativeEnergySurface;
* score.ModellerGa341ZScoreCombined = modellerMonomerScore.ModellerGa341ZScoreCombined;
* score.ModellerGa341ZScorePair = modellerMonomerScore.ModellerGa341ZScorePair;
* score.ModellerGa341ZScoreSurface = modellerMonomerScore.ModellerGa341ZScoreSurface;
*
* score.ModellerMolPdf = modellerMonomerScore.ModellerMolPdf;
* score.ModellerDope = modellerMonomerScore.ModellerDope;
* score.ModellerDopeHr = modellerMonomerScore.ModellerDopeHr;
* score.ModellerDopeNormalized = modellerMonomerScore.ModellerDopeNormalized;
* score.ModellerSoap = modellerMonomerScore.ModellerSoap;
* }
*
* if (pisaMonomerScore != null)
* {
* score.PisaMonomerSerial1 = pisaMonomerScore.PisaMonomerSerial1;
* score.PisaMonomerId1 = pisaMonomerScore.PisaMonomerId1;
* score.PisaMonomerName1 = pisaMonomerScore.PisaMonomerName1;
* score.PisaMonomerClass1 = pisaMonomerScore.PisaMonomerClass1;
* score.PisaMonomerTotalAtoms1 = pisaMonomerScore.PisaMonomerTotalAtoms1;
* score.PisaMonomerTotalResidues1 = pisaMonomerScore.PisaMonomerTotalResidues1;
* score.PisaMonomerSurfaceAtoms1 = pisaMonomerScore.PisaMonomerSurfaceAtoms1;
* score.PisaMonomerSurfaceResidues1 = pisaMonomerScore.PisaMonomerSurfaceResidues1;
* score.PisaMonomerArea1 = pisaMonomerScore.PisaMonomerArea1;
* score.PisaMonomerDeltaG1 = pisaMonomerScore.PisaMonomerDeltaG1;
* }
*
*
* //if (pdbtoolsScore != null)
* //{
* // score.PdbToolsCoulombEp1 = pdbtoolsScore.PdbToolsCoulombEp1;
* // score.PdbToolsCoulombIonStr1 = pdbtoolsScore.PdbToolsCoulombIonStr1;
* // score.PdbToolsCoulombPh1 = pdbtoolsScore.PdbToolsCoulombPh1;
* // score.PdbToolsCoulombT1 = pdbtoolsScore.PdbToolsCoulombT1;
* // score.PdbToolsCoulombDeltaG1 = pdbtoolsScore.PdbToolsCoulombDeltaG1;
* //}
*
* if (score.StructureFilename == "template_ligand_all.pdb" && score.SubstitutionDescription.Replace("_", " ").ToUpperInvariant() == "Query Interface".ToUpperInvariant()) { score.SubstitutionDescription = "Native (No change)"; }
* else if (score.Input2QplLigandCluster == score.Input1QprLigandCluster && score.SubstitutionDescription.Replace("_", " ").ToUpperInvariant() == "Query Interface".ToUpperInvariant()) { score.SubstitutionDescription = "Native Theoretical Model"; }
* else if (score.Input2QplLigandCluster == score.Input1QprLigandCluster && score.SubstitutionDescription.Replace("_", " ").ToUpperInvariant() == "Query Interface (Reversed)".ToUpperInvariant()) { score.SubstitutionDescription = "Native Theoretical Model (Reversed)"; }
*
* scores.Add(score);
* //}
* }
* var subDesc = new List<string>
* {
* "Native (No change)",
* "Native Theoretical Model",
* "Query Interface",
* "Similar Physiochemical",
* "Similar Propensity",
* "Similar Blosum62",
* "Dissimilar Physiochemical",
* "Dissimilar Propensity",
* "Dissimilar Blosum62",
* };
*
* subDesc.AddRange(subDesc.Select(s => s + " (Reversed)").ToList());
* subDesc = subDesc.Select(a => a.Replace("_", " ").ToUpperInvariant()).ToList();
*
* var scoresDistinct = scores.Select(a => new
* {
* Input1QPR_ReceptorCluster = a.Input1QprReceptorCluster,
* Input1QPR_LigandCluster = a.Input1QprLigandCluster,
* Input2QPL_ReceptorCluster = a.Input2QplReceptorCluster,
* }).Distinct().ToList();
*
* scores =
* scores.OrderBy(a => a.StructuralTruncation.Trim())
* .ThenBy(a => a.StructureFolder.Substring(0, a.StructureFolder.LastIndexOfAny(new char[] { '/', '\\' })).Trim())
*
* .ThenBy(a => subDesc.IndexOf(a.SubstitutionDescription.Replace("_", " ").ToUpperInvariant()))
* .ToList();
* var scoresGrouped = scores.GroupBy(a => new Tuple<string,bool>(a.StructureFilename,a.SubstitutionDescription.Contains("(Reversed)")));
* foreach (var scoreGrouped in scoresGrouped)
* {
*
* var output = scoreGrouped.ToList().SelectMany(a => a.SubstitutionDescription == "Native (No change)" ? new[] {"", a.ToString()} : new[] {a.ToString()}).ToList();
* output.Insert(0, EnergyScore.Header());
* File.WriteAllLines(logResultsFolder + "energy_" + scoreGrouped.Key.Item1 + (scoreGrouped.Key.Item2?" reversed":"") + ".csv", output);
* }
*
*
* }
*/
//}
//public static List<EnergyScore> ParsePdbtoolsLog(string[] pdbtoolsLogFileLines, EnergyScore paramEnergyScore, List<string> structFiles)
//{
// var monomerMarker = " pdb ep ion_str pH T dG";
// var result = new List<EnergyScore>();
// var score = new EnergyScore();
// for (int index = 0; index < pdbtoolsLogFileLines.Length; index++)
// {
// var line = pdbtoolsLogFileLines[index];
// var lineSplit = line.Split(new char[] { ' ' }, StringSplitOptions.RemoveEmptyEntries).ToList();
// if (line.StartsWith("; pdb_coulomb.py")) score.StructureFilename = lineSplit[2];
// if (line == monomerMarker)
// {
// var line2 = pdbtoolsLogFileLines[index + 1];
// var lineSplit2 = line2.Split(new char[] { ' ' }, StringSplitOptions.RemoveEmptyEntries).Where(a => a != "|").ToList();
// if (structFiles.Contains(score.StructureFilename))
// {
// score.PdbToolsCoulombEp1 = lineSplit2[2];
// score.PdbToolsCoulombIonStr1 = lineSplit2[3];
// score.PdbToolsCoulombPh1 = lineSplit2[4];
// score.PdbToolsCoulombT1 = lineSplit2[5];
// score.PdbToolsCoulombDeltaG1 = lineSplit2[6];
// result.Add(score);
// score = new EnergyScore();
// }
// }
// }
// return result;
//}
public static List <EnergyScore> ParsePisaLog(string[] pisaLogFileLines, /*EnergyScore paramEnergyScore,*/ List <string> structFiles = null)
{
var monomerMarker = " ## Id | Monomer | Class Nat Nres Sat Sres Area DeltaG";
//var interfaceMarker = " ## Id | Monomer1 | Monomer2 Symmetry operation Sym.Id | Area DeltaG Nhb Nsb Nds";
var result = new List <EnergyScore>();
var score = new EnergyScore();
for (int index = 0; index < pisaLogFileLines.Length; index++)
{
var line = pisaLogFileLines[index];
var lineSplit = line.Split(new char[] { ' ' }, StringSplitOptions.RemoveEmptyEntries).ToList();
if (line.StartsWith("; pisa"))
{
score.StructureFilename = lineSplit[2];
}
if (line == monomerMarker)
{
var line2 = pisaLogFileLines[index + 2];
var lineSplit2 = line2.Split(new char[] { ' ' }, StringSplitOptions.RemoveEmptyEntries).Where(a => a != "|").ToList();
if (structFiles == null || structFiles.Count == 0 || structFiles.Contains(score.StructureFilename))
{
score.PisaMonomerSerial1 = lineSplit2[0];
score.PisaMonomerId1 = lineSplit2[1];
score.PisaMonomerName1 = lineSplit2[2];
score.PisaMonomerClass1 = lineSplit2[3];
score.PisaMonomerTotalAtoms1 = lineSplit2[4];
score.PisaMonomerTotalResidues1 = lineSplit2[5];
score.PisaMonomerSurfaceAtoms1 = lineSplit2[6];
score.PisaMonomerSurfaceResidues1 = lineSplit2[7];
score.PisaMonomerArea1 = lineSplit2[8];
score.PisaMonomerDeltaG1 = lineSplit2[9];
result.Add(score);
score = new EnergyScore();
}
}
}
return(result);
}
public static List <EnergyScore> ParseModellerLog(string modellerLogFilename, /*EnergyScore paramEnergyScore,*/ List <string> structFiles = null)
{
var folder = Path.GetDirectoryName(modellerLogFilename);
var file = Path.GetFileName(modellerLogFilename);
var modellerLogFileLines = File.ReadAllLines(modellerLogFilename);
var modellerLogFileMarkers = new string[] { "; ENERGY ", "; FILE ", "; CHAIN ", "; FINISHED " };
modellerLogFileLines = modellerLogFileLines.Where(a => modellerLogFileMarkers.Any(a.StartsWith)).ToArray();
var result = new List <EnergyScore>();
var score = new EnergyScore();
score.StructureFolder = folder;
score.StructureFilename = file;
score.SubstitutionDescription = "";
score.StructuralTruncation = "";
foreach (var line in modellerLogFileLines)
{
var lineSplit = line.Split(' ').ToList();
lineSplit.RemoveAt(0);
if (lineSplit[0] == "FILE")
{
score.StructureFilename = lineSplit[1];
continue;
}
if (lineSplit[0] == "CHAIN")
{
//if (structFiles==null|| structFiles.Count == 0 || structFiles.Contains(score.StructureFilename))
{
score.ModellerModelChainName = lineSplit[1];
}
continue;
}
if (lineSplit[0] == "ENERGY")
{
//if (structFiles==null|| structFiles.Count == 0 || structFiles.Contains(score.StructureFilename))
{
if (lineSplit[1] == "assess_ga341")
{
var ga341Index = -1;
var ga341 = line.Substring("; ENERGY assess_ga341 ".Length).Replace("[", "").Replace("]", "").Replace(" ", "").Split(',');
score.ModellerGa341 = ga341[++ga341Index];
score.ModellerGa341Comptactness = ga341[++ga341Index];
score.ModellerGa341NativeEnergyPair = ga341[++ga341Index];
score.ModellerGa341NativeEnergySurface = ga341[++ga341Index];
score.ModellerGa341NativeEnergyCombined = ga341[++ga341Index];
score.ModellerGa341ZScoreSurface = ga341[++ga341Index];
score.ModellerGa341ZScorePair = ga341[++ga341Index];
score.ModellerGa341ZScoreCombined = ga341[++ga341Index];
}
if (lineSplit[1] == "molpdf")
{
score.ModellerMolPdf = lineSplit[2];
}
if (lineSplit[1] == "assess_dope")
{
score.ModellerDope = string.IsNullOrWhiteSpace(lineSplit[2]) ? "" : string.Format("{0:0.00}", Math.Round(decimal.Parse(lineSplit[2]), 2));
}
if (lineSplit[1] == "assess_dopehr")
{
score.ModellerDopeHr = lineSplit[2];
}
if (lineSplit[1] == "assess_normalized_dope")
{
score.ModellerDopeNormalized = lineSplit[2];
}
if (lineSplit[1] == "assess_soap_protein_od")
{
score.ModellerSoap = lineSplit[2];
}
}
continue;
}
if (lineSplit[0] == "FINISHED")
{
var lastScore = score;
//if (structFiles.Contains(score.StructureFilename))
//{
result.Add(lastScore);
//}
score = new EnergyScore();
score.StructureFolder = lastScore.StructureFolder;
score.StructureFilename = lastScore.StructureFilename;
score.SubstitutionDescription = lastScore.SubstitutionDescription;
score.StructuralTruncation = lastScore.StructuralTruncation;
}
}
return(result);
}