public void TestReadFromFile()
{
IIdentifiedResult ir = new SequestResultTextFormat().ReadFromFile(@"../../../data/Standard_Protein_FIT_060222.noredundant");
Assert.AreEqual(19, ir.Count);
List<IIdentifiedProtein> prohits = ir.GetProteins();
Assert.AreEqual(43, prohits.Count);
List<IIdentifiedSpectrum> pephits = ir.GetSpectra();
Assert.AreEqual(287, pephits.Count);
IIdentifiedProtein protein1_1 = ir[0][0];
Assert.AreEqual(1, protein1_1.GroupIndex);
Assert.AreEqual("sp|P00489|PHS2_RABIT Glycogen phosphorylase, muscle form (EC 2.4.1.1) (Myophosphorylase) - Oryctolagus cuniculus (Rabbit).", protein1_1.Reference.Trim());
Assert.AreEqual(97, protein1_1.Peptides.Count);
IIdentifiedSpectrum pephit = protein1_1.Peptides[0].Spectrum;
Assert.AreEqual(1689.886, pephit.TheoreticalMH, 0.001);
Assert.AreEqual(3.8133, pephit.Score, 0.01);
Assert.AreEqual(0.65, pephit.DeltaScore, 0.01);
Assert.AreEqual(1602.8, pephit.SpScore, 0.1);
Assert.AreEqual(1, pephit.SpRank);
Assert.AreEqual(27, pephit.MatchedIonCount);
Assert.AreEqual(52, pephit.TheoreticalIonCount);
Assert.AreEqual("K.ARPEFTLPVHFYGR.V", protein1_1.Peptides[0].Sequence);
Assert.AreEqual("Standard_Protein_FIT_060222,7066", protein1_1.Peptides[0].Spectrum.Query.FileScan.ShortFileName);
}
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 });
}
public override IEnumerable <string> Process(string fileName)
{
var ir = new MascotResultTextFormat().ReadFromFile(fileName);
var oldFormat = new SequestResultTextFormat("\tReference\tPepCount\tUniquePepCount\tCoverPercent\tMW\tPI", "\t\"File, Scan(s)\"\tSequence\tMH+\tDiff(MH+)\tCharge\tRank\tXC\tDeltaCn\tSp\tRSp\tIons\tReference\tDIFF_MODIFIED_CANDIDATE\tPI\tGroupCount\tProteinCount");
var result = fileName + ".tmp";
oldFormat.WriteToFile(result, ir);
return(new string[] { result });
}
protected override IFileProcessor GetFileProcessor()
{
double ppmTolerance = precursorPPMTolerance.Value;
string rawDirectory;
if (rawDir.FullName == "")
{
rawDirectory = new FileInfo(GetOriginFile()).DirectoryName;
}
else
{
rawDirectory = rawDir.FullName;
}
IIdentifiedResultTextFormat fileFormat;
switch (searchEngine.SelectedItem)
{
case SearchEngineType.MASCOT:
fileFormat = new MascotResultTextFormat();
break;
case SearchEngineType.SEQUEST:
fileFormat = new SequestResultTextFormat();
break;
default:
throw new Exception(MyConvert.Format("Unsupported search engine {0}, contact with author.", searchEngine.SelectedItem));
}
return(new ExtendSilacQuantificationProteinFileProcessor(
new SilacQuantificationOption()
{
RawFormat = rawFormats.SelectedItem,
RawDir = rawDirectory,
SilacParamFile = silacFile.FullName,
PPMTolerance = ppmTolerance,
IgnoreModifications = ignoreModifications.Text,
ProfileLength = _profileLength.Value
},
fileFormat,
datasetClassification.GetClassificationSet(), rawPairClassification.GetClassificationSet())
{
MinPeptideRegressionCorrelation = minCorrelation.Value
});
}
/// <summary>
/// 输出每次条件下，每个fraction的protein group文件
/// </summary>
protected override void ExportIndividualFractionFile()
{
DirectoryInfo individualDir = new DirectoryInfo(resultDir.FullName + "\\individual");
FileInfo sourceFile = new FileInfo(option.SourceFileName);
SequestResultTextFormat writeFormat = GetWriteFormat();
for (int iMinCount = option.FilterFrom; iMinCount <= option.FilterTo; iMinCount += option.FilterStep)
{
List <CalculationItem> currentItems = GetFilteredItems(iMinCount);
if (!individualDir.Exists)
{
individualDir.Create();
}
foreach (string keptClassifiedName in option.GetClassifiedNames())
{
string result_file = MyConvert.Format(@"{0}\{1}.{2}.{3}{4}",
individualDir.FullName,
FileUtils.ChangeExtension(sourceFile.Name, ""),
GetOptionCondition(iMinCount),
keptClassifiedName,
sourceFile.Extension);
List <IIdentifiedProteinGroup> groups = new List <IIdentifiedProteinGroup>();
foreach (var item in currentItems)
{
if (item.GetClassifiedCount(keptClassifiedName) >= iMinCount)
{
IIdentifiedProteinGroup group = (IIdentifiedProteinGroup)item.Key;
IIdentifiedProteinGroup clonedGroup = GetGroupContainClassifiedPeptideHitOnly(keptClassifiedName, group);
groups.Add(clonedGroup);
}
}
IdentifiedResult curResult = new IdentifiedResult();
curResult.AddRange(groups);
curResult.Sort();
writeFormat.WriteToFile(result_file, curResult);
}
}
}
public void TestClassifyPeptideHit2()
{
var ir = new SequestResultTextFormat().ReadFromFile(@"../../../data/TestDistributionOption.noredundant");
CalculationItem item = new CalculationItem()
{
Peptides = ir[0][0].GetDistinctPeptides()
};
item.ClassifyPeptideHit(m => "G1");
Assert.AreEqual(1360, item.Classifications["G1"].PeptideCount);
Assert.AreEqual(24, item.Classifications["G1"].UniquePeptideCount);
item.Peptides = ir[1][0].GetDistinctPeptides();
item.ClassifyPeptideHit(m => "G1");
Assert.AreEqual(5, item.Classifications["G1"].PeptideCount);
Assert.AreEqual(1, item.Classifications["G1"].UniquePeptideCount);
}
public void TestClassifyPeptideHit2()
{
var ir = new SequestResultTextFormat().ReadFromFile(TestContext.CurrentContext.TestDirectory + "/../../../data/TestDistributionOption.noredundant");
CalculationItem item = new CalculationItem()
{
Peptides = ir[0][0].GetDistinctPeptides()
};
item.ClassifyPeptideHit(m => "G1");
Assert.AreEqual(1360, item.Classifications["G1"].PeptideCount);
Assert.AreEqual(24, item.Classifications["G1"].UniquePeptideCount);
item.Peptides = ir[1][0].GetDistinctPeptides();
item.ClassifyPeptideHit(m => "G1");
Assert.AreEqual(5, item.Classifications["G1"].PeptideCount);
Assert.AreEqual(1, item.Classifications["G1"].UniquePeptideCount);
}
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 });
}