/// <summary>
/// Parse the header line of a SEQUEST _syn.txt file, populating columnMapping
/// </summary>
/// <param name="lineIn"></param>
/// <param name="columnMapping"></param>
/// <returns>True if successful, false if an error</returns>
private bool ParseSequestSynFileHeaderLine(string lineIn, IDictionary <SequestSynopsisFileColumns, int> columnMapping)
{
var columnNames = SequestSynFileReader.GetColumnHeaderNamesAndIDs();
columnMapping.Clear();
try
{
// Initialize each entry in columnMapping to -1
foreach (SequestSynopsisFileColumns resultColumn in Enum.GetValues(typeof(SequestSynopsisFileColumns)))
{
columnMapping.Add(resultColumn, -1);
}
var splitLine = lineIn.Split('\t');
for (var index = 0; index < splitLine.Length; index++)
{
if (columnNames.TryGetValue(splitLine[index], out var resultFileColumn))
{
// Recognized column name; update columnMapping
columnMapping[resultFileColumn] = index;
}
}
}
catch (Exception ex)
{
SetErrorMessage("Error parsing the header line in the Sequest synopsis file", ex);
return(false);
}
return(true);
}
private static void TestPHRPReader(string synOrFhtFile, bool blnSkipDuplicates)
{
var inputFile = new FileInfo(synOrFhtFile);
Console.WriteLine("Instantiating reader");
var startupOptions = new StartupOptions
{
LoadModsAndSeqInfo = true,
LoadMSGFResults = true,
LoadScanStatsData = false,
MaxProteinsPerPSM = 100
};
var phrpReader =
new ReaderFactory(inputFile.FullName, PeptideHitResultTypes.Unknown, startupOptions)
{
EchoMessagesToConsole = false,
SkipDuplicatePSMs = blnSkipDuplicates
};
// Check for any load errors
if (phrpReader.ErrorMessages.Count > 0)
{
Console.WriteLine("Error(s) instantiating the reader:");
foreach (var errorMessage in phrpReader.ErrorMessages)
{
Console.WriteLine(" " + errorMessage);
}
}
phrpReader.ErrorEvent += ErrorEventHandler;
phrpReader.StatusEvent += MessageEventHandler;
phrpReader.WarningEvent += WarningEventHandler;
const bool fastReadEnabled = true;
phrpReader.FastReadMode = fastReadEnabled;
var massCalculator = new PeptideMassCalculator();
if (!phrpReader.CanRead)
{
Console.WriteLine("Aborting since PHRPReader is not ready: " + phrpReader.ErrorMessage);
return;
}
var lstValues = new List <string>();
var intPSMsRead = 0;
var intModifiedPSMsRead = 0;
// ReSharper disable once CollectionNeverQueried.Local
var dctCachedValues = new Dictionary <int, PSM>();
Console.WriteLine("Reading data");
while (phrpReader.MoveNext())
{
var psm = phrpReader.CurrentPSM;
intPSMsRead += 1;
lstValues.Clear();
phrpReader.FinalizeCurrentPSM();
PeptideCleavageStateCalculator.SplitPrefixAndSuffixFromSequence(psm.Peptide, out _, out _, out _);
var strMassErrorPPM = GetCorrectedMassErrorPPM(psm, out _);
lstValues.Add(phrpReader.DatasetName + "_dta.txt"); // #SpecFile
lstValues.Add("index=" + intPSMsRead); // SpecID
lstValues.Add(psm.ScanNumber.ToString()); // ScanNum
lstValues.Add(psm.CollisionMode); // FragMethod
lstValues.Add(massCalculator.ConvoluteMass(psm.PrecursorNeutralMass, 0, psm.Charge).ToString(CultureInfo.InvariantCulture)); // Precursor m/z
lstValues.Add(strMassErrorPPM); // PrecursorError(ppm)
lstValues.Add(psm.Charge.ToString()); // Charge
lstValues.Add(psm.NumTrypticTermini.ToString()); // Tryptic state (0, 1, or 2)
lstValues.Add(CleanupPeptide(psm.PeptideWithNumericMods)); // Peptide
if (psm.SeqID <= 0)
{
lstValues.Add("**" + psm.SeqID + "**"); // SeqID is undefined
}
else
{
lstValues.Add(psm.SeqID.ToString()); // SeqID
}
lstValues.Add(psm.ProteinFirst);
if (psm.ProteinDetails.Count > 0)
{
var firstProteinDetail = psm.ProteinDetails.First();
if (!string.Equals(psm.ProteinFirst, firstProteinDetail.Key))
{
lstValues.Add(firstProteinDetail.Key);
}
else
{
lstValues.Add("<Match>");
}
lstValues.Add(firstProteinDetail.Value.ResidueStart.ToString());
lstValues.Add(firstProteinDetail.Value.ResidueEnd.ToString());
}
var strXCorr = GetScore(psm, SequestSynFileReader.GetColumnNameByID(SequestSynopsisFileColumns.XCorr), "0");
lstValues.Add(strXCorr);
lstValues.Add(GetScore(psm, SequestSynFileReader.GetColumnNameByID(SequestSynopsisFileColumns.Sp), "0"));
lstValues.Add(psm.MSGFSpecEValue);
lstValues.Add(GetScore(psm, SequestSynFileReader.GetColumnNameByID(SequestSynopsisFileColumns.DeltaCn2), "0"));
lstValues.Add(GetScore(psm, MSGFPlusSynFileReader.GetMSGFDBColumnNameByID(MSGFDBSynFileColumns.PValue), "0"));
lstValues.Add(GetScore(psm, MSGFPlusSynFileReader.GetColumnNameByID(MSGFPlusSynFileColumns.EValue), "0"));
lstValues.Add(GetScore(psm, MSGFPlusSynFileReader.GetColumnNameByID(MSGFPlusSynFileColumns.RankSpecEValue), "0"));
lstValues.Add(GetScore(psm, MSGFPlusSynFileReader.GetMSGFDBColumnNameByID(MSGFDBSynFileColumns.FDR), "1"));
lstValues.Add(GetScore(psm, MSGFPlusSynFileReader.GetColumnNameByID(MSGFPlusSynFileColumns.QValue), "0"));
lstValues.Add(GetScore(psm, MSGFPlusSynFileReader.GetColumnNameByID(MSGFPlusSynFileColumns.PepQValue), "0"));
if (psm.PeptideCleanSequence == "QQIEESTSDYDKEK")
{
Console.WriteLine(psm.Peptide + " in scan " + psm.ScanNumber);
var parentIonMZ = massCalculator.ConvoluteMass(psm.PrecursorNeutralMass, 0, psm.Charge);
Console.WriteLine("ParentIonMZ = " + parentIonMZ);
Console.WriteLine("PeptideWithNumericMods = " + psm.PeptideWithNumericMods);
}
if (psm.ModifiedResidues.Count > 0)
{
intModifiedPSMsRead += 1;
if (intModifiedPSMsRead % 500 == 0)
{
Console.WriteLine("PeptideWithNumericMods = " + psm.PeptideWithNumericMods);
foreach (var modifiedResidue in psm.ModifiedResidues)
{
Console.WriteLine(" " + modifiedResidue.Residue + modifiedResidue.EndResidueLocInPeptide + ": " + modifiedResidue.ModDefinition.ModificationMassAsText);
}
}
var dblPeptideMassRecomputed = massCalculator.ComputeSequenceMassNumericMods(psm.PeptideWithNumericMods);
if (Math.Abs(psm.PeptideMonoisotopicMass - dblPeptideMassRecomputed) > 0.1)
{
Console.WriteLine(" Peptide mass disagreement: " + (psm.PeptideMonoisotopicMass - dblPeptideMassRecomputed).ToString("0.0000000"));
}
}
var strFlattened = FlattenList(lstValues);
if (intPSMsRead % 10000 == 0)
{
Console.WriteLine(strFlattened);
}
dctCachedValues.Add(intPSMsRead, psm);
}
}
