public PHRPReaderParser(string synopsisFilePath, FragmentLadderOptions fragLadderOptions)
{
m_fragLadderOptions = fragLadderOptions;
m_fragLadderOptions.modificationList.Clear();
using (var reader = new StreamReader(synopsisFilePath))
{
m_firstLine = reader.ReadLine().Split('\t');
for (int i = 0; i < m_firstLine.Length; i++)
{
if (m_firstLine[i] == "Peptide")
{
m_peptideColumnIndex = i;
break;
}
}
}
var oStartupOptions = new clsPHRPStartupOptions
{
LoadModsAndSeqInfo = true,
LoadMSGFResults = true,
LoadScanStatsData = false,
MaxProteinsPerPSM = 100
};
m_reader = new clsPHRPReader(synopsisFilePath, oStartupOptions);
//m_reader.FastReadMode = true;
m_reader.SkipDuplicatePSMs = true;
m_parser = m_reader.PHRPParser;
}
public async Task <IEnumerable <PrSm> > ReadAsync(IEnumerable <string> modIgnoreList = null, IProgress <double> progress = null)
{
var oStartupOptions = new clsPHRPStartupOptions {
LoadModsAndSeqInfo = true
};
var phrpReader = new clsPHRPReader(filePath, oStartupOptions);
if (!string.IsNullOrEmpty(phrpReader.ErrorMessage))
{
throw new Exception(phrpReader.ErrorMessage);
}
var identifications = await Task.Run(
() =>
{
var ids = new List <PrSm>();
while (phrpReader.MoveNext())
{
phrpReader.FinalizeCurrentPSM();
var psm = phrpReader.CurrentPSM;
var proteins = psm.Proteins;
var parsedSequence = ParseSequence(psm.PeptideCleanSequence, psm.ModifiedResidues);
foreach (var protein in proteins)
{
var prsm = new PrSm
{
Heavy = false,
ProteinName = protein,
ProteinDesc = string.Empty,
Charge = psm.Charge,
Sequence = parsedSequence,
Scan = psm.ScanNumber,
Score = Convert.ToDouble(psm.MSGFSpecProb),
UseGolfScoring = true,
QValue = 0,
};
prsm.SetSequence(GetSequenceText(parsedSequence), parsedSequence);
ids.Add(prsm);
}
}
return(ids);
});
return(identifications);
}
/// <summary>
/// Store Protein Info
/// </summary>
/// <param name="reader"></param>
/// <param name="result"></param>
protected static void StoreProteinInfo(clsPHRPReader reader, Evidence result)
{
foreach (var p in reader.CurrentPSM.ProteinDetails)
{
var protein = new ProteinInformation
{
ProteinName = p.Value.ProteinName,
CleavageState = p.Value.CleavageState,
TerminusState = p.Value.TerminusState,
ResidueStart = p.Value.ResidueStart,
ResidueEnd = p.Value.ResidueEnd
};
result.Proteins.Add(protein);
}
}
/// <summary>
/// PHRPReader configuration
/// </summary>
/// <param name="path"></param>
/// <returns></returns>
protected clsPHRPReader InitializeReader(string path)
{
AbortRequested = false;
var oStartupOptions = new clsPHRPStartupOptions
{
LoadModsAndSeqInfo = true,
LoadMSGFResults = true,
LoadScanStatsData = false,
MaxProteinsPerPSM = 100
};
UpdateProgress(0, "Initializing reader");
var reader = new clsPHRPReader(path, oStartupOptions)
{
SkipDuplicatePSMs = true,
FastReadMode = true
};
return(reader);
}
/// <summary>
/// Store PSM Data
/// </summary>
/// <param name="result"></param>
/// <param name="reader"></param>
/// <param name="specProb"></param>
protected void StorePsmData(Evidence result, clsPHRPReader reader, double specProb)
{
result.Charge = reader.CurrentPSM.Charge;
result.CleanPeptide = reader.CurrentPSM.PeptideCleanSequence;
result.SeqWithNumericMods = reader.CurrentPSM.PeptideWithNumericMods;
result.MonoisotopicMass = reader.CurrentPSM.PeptideMonoisotopicMass;
result.ObservedMonoisotopicMass = reader.CurrentPSM.PrecursorNeutralMass;
result.MultiProteinCount = (short)reader.CurrentPSM.Proteins.Count;
result.Scan = reader.CurrentPSM.ScanNumber;
result.Sequence = reader.CurrentPSM.Peptide;
result.Mz =
clsPeptideMassCalculator.ConvoluteMass(reader.CurrentPSM.PrecursorNeutralMass, 0,
reader.CurrentPSM.Charge);
result.SpecProb = specProb;
result.DelM = Convert.ToDouble(reader.CurrentPSM.MassErrorDa);
result.ModificationCount = (short)reader.CurrentPSM.ModifiedResidues.Count;
result.PeptideInfo = new TargetPeptideInfo
{
Peptide = result.Sequence,
CleanPeptide = result.CleanPeptide,
PeptideWithNumericMods = result.SeqWithNumericMods
};
if (reader.CurrentPSM.MassErrorPPM.Length != 0)
{
result.DelMPpm = Convert.ToDouble(reader.CurrentPSM.MassErrorPPM);
}
result.SeqInfoMonoisotopicMass = result.MonoisotopicMass;
StoreProteinInfo(reader, result);
if (result.ModificationCount != 0)
{
foreach (var info in reader.CurrentPSM.ModifiedResidues)
{
result.ModificationDescription += info.ModDefinition.MassCorrectionTag + ":" + info.ResidueLocInPeptide + " ";
var ptm = new PostTranslationalModification
{
Location = info.ResidueLocInPeptide,
Mass = info.ModDefinition.ModificationMass,
Formula = info.ModDefinition.MassCorrectionTag,
Name = info.ModDefinition.MassCorrectionTag
};
result.Ptms.Add(ptm);
}
var encodedSeq = result.Sequence[0] + ".";
int j = 0;
foreach (var ptm in result.Ptms)
{
for (; j < ptm.Location; j++)
{
encodedSeq = encodedSeq + result.CleanPeptide[j];
}
encodedSeq += "[" + ((ptm.Mass > 0)? "+":"-") + ptm.Formula + "]";
}
for (; j < result.CleanPeptide.Length; j++)
{
encodedSeq += result.CleanPeptide[j];
}
encodedSeq += "." + result.Sequence.Last();
result.EncodedNonNumericSequence = encodedSeq;
}
else
{
result.EncodedNonNumericSequence = result.Sequence;
}
}
/// <summary>
/// Store Dataset Info
/// </summary>
/// <param name="result"></param>
/// <param name="reader"></param>
/// <param name="dataFilePath"></param>
protected void StoreDatasetInfo(Evidence result, clsPHRPReader reader, string dataFilePath)
{
StoreDatasetInfo(result, reader.DatasetName, dataFilePath);
}
