public override IEnumerable <string> Process(string filename)
{
SequestResultTextFormat format = new SequestResultTextFormat();
Progress.SetMessage("Reading from " + filename + "...");
IIdentifiedResult sr = format.ReadFromFile(filename);
HashSet <IIdentifiedSpectrum> result = new HashSet <IIdentifiedSpectrum>();
foreach (IIdentifiedProteinGroup spg in sr)
{
if (acceptFunc(spg))
{
result.UnionWith(spg[0].GetSpectra());
}
}
List <IIdentifiedSpectrum> spectra = new List <IIdentifiedSpectrum>(result);
spectra.Sort();
string resultFilename = MyConvert.Format("{0}.{1}.peptides", filename, uniqueStr);
Progress.SetMessage("Writing to " + resultFilename + "...");
new SequestPeptideTextFormat(format.PeptideFormat.GetHeader()).WriteToFile(resultFilename, spectra);
Progress.SetMessage("Finished");
return(new[] { resultFilename });
}
protected override void ParseToCalculationItems()
{
IIdentifiedResult sr = format.ReadFromFile(option.SourceFileName);
calculationItems =
(from proteinGroup in sr
select new CalculationItem()
{
Key = proteinGroup,
Peptides = proteinGroup[0].GetDistinctPeptides()
}).ToList();
}
public override IEnumerable <string> Process(string fileName)
{
var format = new SequestResultTextFormat();
format.Progress = this.Progress;
Progress.SetMessage("Reading identified result from " + fileName + " ...");
IIdentifiedResult ir = format.ReadFromFile(fileName);
Progress.SetMessage("Removing duplicated peptide ...");
Progress.SetRange(0, ir.Count);
for (int i = 0; i < ir.Count; i++)
{
Progress.SetPosition(i);
IIdentifiedProteinGroup group = ir[i];
List <IIdentifiedSpectrum> peps = UniquePeptideDistiller.KeepMaxScorePeptideOnly(group.GetPeptides());
foreach (var protein in group)
{
protein.Peptides.RemoveAll(m => !peps.Contains(m.Spectrum));
}
}
string resultFileName = fileName + ".unique";
Progress.SetMessage("Saving proteins to " + resultFileName + " ...");
format.WriteToFile(resultFileName, ir);
List <IIdentifiedSpectrum> spectra = ir.GetSpectra();
var peptideFormat = new SequestPeptideTextFormat(format.PeptideFormat.GetHeader());
string peptideFileName = fileName + ".unique.peptides";
Progress.SetMessage("Saving peptides to " + peptideFileName + " ...");
peptideFormat.WriteToFile(peptideFileName, spectra);
Progress.SetMessage("Finished.");
return(new[] { resultFileName, peptideFileName });
}
public override IEnumerable <string> Process(string fileName)
{
SequestResultTextFormat format = new SequestResultTextFormat();
IIdentifiedResult sr = format.ReadFromFile(fileName);
Dictionary <string, HashSet <IIdentifiedSpectrum> > peptideMap = sr.GetExperimentalPeptideMap();
Dictionary <IIdentifiedSpectrum, int> confused = new Dictionary <IIdentifiedSpectrum, int>();
List <IIdentifiedSpectrum> wrongMs2 = new List <IIdentifiedSpectrum>();
List <IIdentifiedSpectrum> wrongMs3 = new List <IIdentifiedSpectrum>();
int pepcount = 0;
List <string> exps = new List <string>(peptideMap.Keys);
exps.Sort();
foreach (string exp in exps)
{
Console.Out.WriteLine(exp);
HashSet <IIdentifiedSpectrum> peps = peptideMap[exp];
pepcount += peps.Count;
using (IRawFile rawFile = new RawFileImpl(expRawMap[exp]))
{
foreach (IIdentifiedSpectrum pep in peps)
{
int msLevel = rawFile.GetMsLevel(pep.Query.FileScan.FirstScan);
bool bMs2 = ms2seqPattern.Match(pep.Sequence).Success;
bool bMs3 = ms3seqPattern.Match(pep.Sequence).Success;
if (bMs2 && bMs3)
{
confused[pep] = msLevel;
continue;
}
if (bMs3)
{
if (msLevel != 3)
{
wrongMs3.Add(pep);
continue;
}
}
else if (bMs2)
{
if (msLevel != 2)
{
wrongMs2.Add(pep);
continue;
}
}
}
}
}
string incorrectFilename = FileUtils.ChangeExtension(fileName, ".incorrect.peptides.txt");
using (StreamWriter sw = new StreamWriter(incorrectFilename))
{
sw.WriteLine("Type\tFilename\tSequence\tScore\tDeltaScore\tmsLevel");
foreach (IIdentifiedSpectrum pep in confused.Keys)
{
sw.WriteLine(MyConvert.Format("Confused\t{0}\t{1}\t{2:0.00}\t{3:0.00}\t{4}",
pep.Query.FileScan.LongFileName,
pep.Sequence,
pep.Score,
pep.DeltaScore,
confused[pep]));
}
foreach (IIdentifiedSpectrum pep in wrongMs2)
{
sw.WriteLine(MyConvert.Format("WrongMS2\t{0}\t{1}\t{2:0.00}\t{3:0.00}\t3",
pep.Query.FileScan.LongFileName,
pep.Sequence,
pep.Score,
pep.DeltaScore));
}
foreach (IIdentifiedSpectrum pep in wrongMs3)
{
sw.WriteLine(MyConvert.Format("WrongMS3\t{0}\t{1}\t{2:0.00}\t{3:0.00}\t2",
pep.Query.FileScan.LongFileName,
pep.Sequence,
pep.Score,
pep.DeltaScore));
}
sw.WriteLine();
sw.WriteLine("Total\t" + pepcount);
sw.WriteLine("Confused\t" + confused.Count);
sw.WriteLine("WrongMs2\t" + wrongMs2.Count);
sw.WriteLine("WrongMs3\t" + wrongMs3.Count);
}
List <string> incorrectDtafilenames = new List <string>();
foreach (IIdentifiedSpectrum pep in confused.Keys)
{
incorrectDtafilenames.Add(pep.Query.FileScan.LongFileName);
}
foreach (IIdentifiedSpectrum pep in wrongMs2)
{
incorrectDtafilenames.Add(pep.Query.FileScan.LongFileName);
}
foreach (IIdentifiedSpectrum pep in wrongMs3)
{
incorrectDtafilenames.Add(pep.Query.FileScan.LongFileName);
}
for (int i = sr.Count - 1; i >= 0; i--)
{
foreach (IIdentifiedProtein sp in sr[i])
{
for (int j = sp.Peptides.Count - 1; j >= 0; j--)
{
if (incorrectDtafilenames.Contains(sp.Peptides[j].Spectrum.Query.FileScan.Experimental))
{
sp.Peptides.RemoveAt(j);
}
}
}
if (sr[i][0].Peptides.Count == 0)
{
sr.RemoveAt(i);
}
}
string correctFilename = FileUtils.ChangeExtension(fileName, ".correct.txt");
//BuildSummaryResultUtils.Write(correctFilename, cr);
return(new[] { correctFilename });
}