public void TestSort()
{
var mph1 = new IdentifiedSpectrum();
var peptide1 = new IdentifiedPeptide(mph1);
var mph2 = new IdentifiedSpectrum();
var peptide2 = new IdentifiedPeptide(mph2);
var mpro1 = new IdentifiedProtein("Protein1");
mpro1.Peptides.Add(peptide1);
mpro1.Peptides.Add(peptide2);
var mpro2 = new IdentifiedProtein("Protein2");
mpro2.Peptides.Add(peptide1);
var mpro3 = new IdentifiedProtein("Protein3");
mpro3.Peptides.Add(peptide2);
var mpros = new List <IdentifiedProtein>();
mpros.Add(mpro3);
mpros.Add(mpro2);
mpros.Add(mpro1);
mpros.Sort();
Assert.AreEqual(mpro1, mpros[0]);
Assert.AreEqual(mpro2, mpros[1]);
Assert.AreEqual(mpro3, mpros[2]);
}
public List <IIdentifiedSpectrum> ReadFromFile(string fileName)
{
var result = new List <IIdentifiedSpectrum>();
XElement root = XElement.Load(fileName);
var psms = root.FindElement("psms").FindElements("psm");
foreach (var psm in psms)
{
IIdentifiedSpectrum spec = new IdentifiedSpectrum();
spec.Id = psm.FindAttribute("psm_id").Value.StringAfter("decoy_");
spec.FromDecoy = psm.FindAttribute("decoy").Value.Equals("true");
spec.SpScore = double.Parse(psm.FindElement("svm_score").Value);
spec.QValue = double.Parse(psm.FindElement("q_value").Value);
spec.Score = double.Parse(psm.FindElement("pep").Value);
spec.Probability = double.Parse(psm.FindElement("p_value").Value);
spec.TheoreticalMH = double.Parse(psm.FindElement("calc_mass").Value);
spec.Query.FileScan.Experimental = Path.GetFileName(fileName).StringBefore(".");
var pep = new IdentifiedPeptide(spec);
var pepseq = psm.FindElement("peptide_seq");
pep.Sequence = pepseq.FindAttribute("seq").Value;
pep.AddProtein(psm.FindElement("protein_id").Value);
result.Add(spec);
}
return(result);
}
public Dictionary <int, IIdentifiedSpectrum> ParseSpectrumMap(string fileName)
{
SQLiteDBHelper sqlite = new SQLiteDBHelper(fileName);
Dictionary <int, IIdentifiedSpectrum> result = new Dictionary <int, IIdentifiedSpectrum>();
var fileMap = ParseFileMap(fileName);
//读取肽段列表
var peptideReader = sqlite.ExecuteReader("select sh.SpectrumID, sh.FirstScan, sh.LastScan, sh.RetentionTime, sh.Charge, mp.FileID, sh.Mass from spectrumheaders as sh, MassPeaks as mp where sh.MassPeakID=mp.MassPeakID", null);
Progress.SetMessage("Parsing peptides ...");
while (peptideReader.Read())
{
var specid = peptideReader.GetInt32(0);
IIdentifiedSpectrum spectrum = new IdentifiedSpectrum();
result[specid] = spectrum;
spectrum.Query.FileScan.FirstScan = peptideReader.GetInt32(1);
spectrum.Query.FileScan.LastScan = peptideReader.GetInt32(2);
//retention time
spectrum.Query.FileScan.Charge = peptideReader.GetInt32(4);
spectrum.Query.FileScan.Experimental = fileMap[peptideReader.GetInt32(5)];
spectrum.ExperimentalMH = peptideReader.GetDouble(6);
spectrum.Rank = 1;
}
return(result);
}
public void TestSort()
{
var mph1 = new IdentifiedSpectrum();
var peptide1 = new IdentifiedPeptide(mph1);
var mph2 = new IdentifiedSpectrum();
var peptide2 = new IdentifiedPeptide(mph2);
var mpro1 = new IdentifiedProtein("Protein1");
mpro1.Peptides.Add(peptide1);
mpro1.Peptides.Add(peptide2);
var mpro2 = new IdentifiedProtein("Protein2");
mpro2.Peptides.Add(peptide1);
var mpro3 = new IdentifiedProtein("Protein3");
mpro3.Peptides.Add(peptide2);
var mpros = new List<IdentifiedProtein>();
mpros.Add(mpro3);
mpros.Add(mpro2);
mpros.Add(mpro1);
mpros.Sort();
Assert.AreEqual(mpro1, mpros[0]);
Assert.AreEqual(mpro2, mpros[1]);
Assert.AreEqual(mpro3, mpros[2]);
}
public void Test()
{
IPropertyConverter <IdentifiedSpectrum> io = new IdentifiedSpectrumReferenceConverter <IdentifiedSpectrum>();
var mph = new IdentifiedSpectrum();
var mp1 = new IdentifiedPeptide(mph);
mp1.AddProtein("11111");
var mp2 = new IdentifiedPeptide(mph);
mp2.AddProtein("22222");
mp2.AddProtein("33333");
Assert.AreEqual("Reference", io.Name);
Assert.AreEqual("11111 ! 22222/33333", io.GetProperty(mph));
io.SetProperty(mph, "44444/55555 ! 66666");
Assert.AreEqual(2, mph.Peptides[0].Proteins.Count);
Assert.AreEqual("44444", mph.Peptides[0].Proteins[0]);
Assert.AreEqual("55555", mph.Peptides[0].Proteins[1]);
Assert.AreEqual(1, mph.Peptides[1].Proteins.Count);
Assert.AreEqual("66666", mph.Peptides[1].Proteins[0]);
}
public void TestSort()
{
IdentifiedSpectrum sp1 = new IdentifiedSpectrum();
sp1.Query.FileScan.LongFileName = "YEAST_0612_G1_SAX_080806_09.17702.17702.2.out";
new IdentifiedPeptide(sp1) { Sequence = "K.GFFSFATQK.L" };
IdentifiedSpectrum sp2 = new IdentifiedSpectrum();
sp2.Query.FileScan.LongFileName = "YEAST_0612_G1_SAX_080806_09.17707.17708.1.out";
new IdentifiedPeptide(sp2) { Sequence = "K.GFFSFATQK.L" };
IdentifiedSpectrum sp3 = new IdentifiedSpectrum();
sp3.Query.FileScan.LongFileName = "YEAST_0612_G1_SAX_080806_09.7707.7708.2.out";
new IdentifiedPeptide(sp3) { Sequence = "K.GFFSFATQK.L" };
IdentifiedSpectrum sp4 = new IdentifiedSpectrum();
sp4.Query.FileScan.LongFileName = "YEAST_0612_G1_SAX_080806_09.7707.7708.2.out";
new IdentifiedPeptide(sp4) { Sequence = "K.AAAAAAAK.L" };
List<IIdentifiedSpectrum> spectra = new List<IIdentifiedSpectrum>();
spectra.Add(sp2);
spectra.Add(sp1);
spectra.Add(sp3);
spectra.Add(sp4);
spectra.Sort();
Assert.AreSame(sp4, spectra[0]);
Assert.AreSame(sp3, spectra[1]);
Assert.AreSame(sp1, spectra[2]);
Assert.AreSame(sp2, spectra[3]);
}
private static List<IIdentifiedProtein> InitProteins()
{
var mph1 = new IdentifiedSpectrum();
mph1.Query.FileScan.Experimental = "EXP1";
var mp1 = new IdentifiedPeptide(mph1);
mp1.AddProtein("Protein1");
mp1.AddProtein("Protein2");
mp1.Sequence = "SEQ1";
var mph2 = new IdentifiedSpectrum();
mph2.Query.FileScan.Experimental = "EXP2";
var mp2 = new IdentifiedPeptide(mph2);
mp2.AddProtein("Protein1");
mp2.AddProtein("Protein3");
mp2.Sequence = "SEQ2";
var mpro1 = new IdentifiedProtein("Protein1");
mpro1.Peptides.Add(mp1);
mpro1.Peptides.Add(mp2);
var mpro2 = new IdentifiedProtein("Protein2");
mpro2.Peptides.Add(mp1);
var mpro3 = new IdentifiedProtein("Protein3");
mpro3.Peptides.Add(mp2);
var result = new List<IIdentifiedProtein>();
result.Add(mpro3);
result.Add(mpro2);
result.Add(mpro1);
return result;
}
public void TestKeepDistinctPeptideOnly()
{
var spectrum1 = new IdentifiedSpectrum();
var pep1 = spectrum1.NewPeptide();
var spectrum2 = new IdentifiedSpectrum();
var pep2 = spectrum2.NewPeptide();
var spectrum3 = new IdentifiedSpectrum();
var pep3 = spectrum3.NewPeptide();
var spectrum4 = new IdentifiedSpectrum();
var pep4 = spectrum4.NewPeptide();
var protein1 = new IdentifiedProtein();
protein1.Peptides.Add(pep1);
protein1.Peptides.Add(pep2);
var protein2 = new IdentifiedProtein();
protein2.Peptides.Add(pep1);
protein2.Peptides.Add(pep3);
var protein3 = new IdentifiedProtein();
protein3.Peptides.Add(pep2);
protein3.Peptides.Add(pep4);
var g1 = new IdentifiedProteinGroup();
g1.Add(protein1);
var g2 = new IdentifiedProteinGroup();
g2.Add(protein2);
var g3 = new IdentifiedProteinGroup();
g3.Add(protein3);
IIdentifiedResult ir = new IdentifiedResult();
ir.Add(g1);
ir.Add(g2);
ir.Add(g3);
new DistinctResultDistiller().KeepDistinctPeptideOnly(ir);
Assert.AreEqual(2, ir.Count);
Assert.AreEqual(g2, ir[0]);
Assert.AreEqual(g3, ir[1]);
Assert.AreEqual(1, ir[0].GetPeptides().Count);
Assert.AreEqual(spectrum3, ir[0].GetPeptides()[0]);
Assert.AreEqual(1, ir[1].GetPeptides().Count);
Assert.AreEqual(spectrum4, ir[1].GetPeptides()[0]);
}
public void TestDiffOfMassPPM()
{
var sp = new IdentifiedSpectrum();
sp.TheoreticalMH = 1000;
sp.ExperimentalMH = 999.95;
sp.Query.Charge = 1;
Assert.AreEqual(0.05, sp.TheoreticalMinusExperimentalMass, 0.01);
}
public void TestDiffOfMassPPM()
{
var sp = new IdentifiedSpectrum();
sp.TheoreticalMH = 1000;
sp.ExperimentalMH = 999.95;
sp.Query.Charge = 1;
Assert.AreEqual(0.05, sp.TheoreticalMinusExperimentalMass, 0.01);
}
/// <summary>
///
/// Get the query/peptide map from pNovo result.
///
/// </summary>
/// <param name="filename">pNovo proteins file</param>
/// <param name="minRank">Minimum rank of peptide identified in same spectrum</param>
/// <param name="minScore">Minimum score of peptide identified in same spectrum</param>
/// <returns>Query/peptide map</returns>
public List <IIdentifiedSpectrum> ParsePeptides(string filename, int maxRank, double minScore)
{
var result = new List <IIdentifiedSpectrum>();
SequestFilename sf = null;
int charge = 2;
double expmh = 0;
using (var sr = new StreamReader(filename))
{
string line;
while ((line = sr.ReadLine()) != null)
{
var parts = line.Split('\t');
if (parts.Length <= 5)
{ //spectrum information
var seqcount = Convert.ToInt32(parts.Last());
if (seqcount == 0)
{
continue;
}
sf = parser.GetValue(parts[0]);
expmh = MyConvert.ToDouble(parts[1]);
charge = Convert.ToInt32(parts[2]);
}
else
{
int curIndex = Convert.ToInt32(parts[0]);
if (curIndex <= maxRank)
{
var score = MyConvert.ToDouble(parts[2]);
if (score < minScore)
{
continue;
}
var curSpectrum = new IdentifiedSpectrum();
curSpectrum.Query.FileScan = sf;
curSpectrum.Query.Charge = charge;
curSpectrum.ExperimentalMH = expmh;
curSpectrum.Score = score;
result.Add(curSpectrum);
IdentifiedPeptide pep = new IdentifiedPeptide(curSpectrum);
pep.Sequence = ModifySequence(parts[9]);
pep.Spectrum.TheoreticalMH = MyConvert.ToDouble(parts[11]);
pep.Spectrum.Rank = curIndex;
}
}
}
}
return(result);
}
private static void AddSpectrum(List<IIdentifiedSpectrum> isoSpectra, string seq, string site)
{
var spec = new IdentifiedSpectrum();
spec.AddPeptide(new IdentifiedPeptide(spec)
{
Sequence = seq,
SiteProbability = site
});
isoSpectra.Add(spec);
}
private IIdentifiedProteinGroup ReadNextProteinGroup(StreamReader filein,
Dictionary <string, IIdentifiedSpectrum> peptideMap,
ref string lastLine)
{
while (!IsProteinLine(lastLine) && (lastLine = filein.ReadLine()) != null)
{
}
if (lastLine == null)
{
return(null);
}
IIdentifiedProteinGroup result = new IdentifiedProteinGroup();
while (IsProteinLine(lastLine))
{
IIdentifiedProtein protein = new IdentifiedProtein();
this.proteinConverter.SetProperty(protein, lastLine);
result.Add(protein);
lastLine = filein.ReadLine();
}
var peptides = new List <IIdentifiedSpectrum>();
while (!IsProteinLine(lastLine))
{
IIdentifiedSpectrum mphit = new IdentifiedSpectrum();
this.peptideConverter.SetProperty(mphit, lastLine);
string id = mphit.Query.FileScan.LongFileName + "-" + mphit.Rank;
if (!peptideMap.ContainsKey(id))
{
peptideMap[id] = mphit;
}
else
{
mphit = peptideMap[id];
}
peptides.Add(mphit);
lastLine = filein.ReadLine();
if (lastLine == null || lastLine.Trim().Length == 0)
{
break;
}
}
peptides.Sort();
result.AddIdentifiedSpectra(peptides);
return(result);
}
public void Test()
{
IPropertyConverter<IdentifiedSpectrum> io = new IdentifiedSpectrumModificationConverter<IdentifiedSpectrum>();
var mph = new IdentifiedSpectrum();
Assert.AreEqual("Modification", io.Name);
io.SetProperty(mph, "O18(2)");
Assert.AreEqual("O18(2)", io.GetProperty(mph));
Assert.AreEqual("O18(2)", mph.Modifications);
}
public void Test()
{
IPropertyConverter <IdentifiedSpectrum> io = new IdentifiedSpectrumScoreConverter <IdentifiedSpectrum>();
var mph = new IdentifiedSpectrum();
Assert.AreEqual("Score", io.Name);
io.SetProperty(mph, "32.1");
Assert.AreEqual("32.1", io.GetProperty(mph));
Assert.AreEqual(32.1, mph.Score, 0.01);
}
public void Test()
{
AbstractPropertyConverter<IdentifiedSpectrum> io = new IdentifiedSpectrumRankConverter<IdentifiedSpectrum>();
var mph = new IdentifiedSpectrum();
Assert.AreEqual("Rank", io.Name);
io.SetProperty(mph, "2");
Assert.AreEqual("2", io.GetProperty(mph));
Assert.AreEqual(2, mph.Rank);
}
public void Test()
{
IPropertyConverter <IdentifiedSpectrum> io = new IdentifiedSpectrumMissCleavageConverter <IdentifiedSpectrum>();
var mph = new IdentifiedSpectrum();
Assert.AreEqual("MissCleavage", io.Name);
io.SetProperty(mph, "1");
Assert.AreEqual("1", io.GetProperty(mph));
Assert.AreEqual(1, mph.NumMissedCleavages);
}
public void Test()
{
AbstractPropertyConverter<IdentifiedSpectrum> io = new IdentifiedSpectrumChargeConverter<IdentifiedSpectrum>();
var mph = new IdentifiedSpectrum();
Assert.AreEqual("Charge", io.Name);
io.SetProperty(mph, "1");
Assert.AreEqual("1", io.GetProperty(mph));
Assert.AreEqual(1, mph.Query.Charge);
}
public void Test()
{
IPropertyConverter<IdentifiedSpectrum> io = new IdentifiedSpectrumScoreConverter<IdentifiedSpectrum>();
var mph = new IdentifiedSpectrum();
Assert.AreEqual("Score", io.Name);
io.SetProperty(mph, "32.1");
Assert.AreEqual("32.1", io.GetProperty(mph));
Assert.AreEqual(32.1, mph.Score, 0.01);
}
public void Test()
{
AbstractPropertyConverter <IdentifiedSpectrum> io = new IdentifiedSpectrumChargeConverter <IdentifiedSpectrum>();
var mph = new IdentifiedSpectrum();
Assert.AreEqual("Charge", io.Name);
io.SetProperty(mph, "1");
Assert.AreEqual("1", io.GetProperty(mph));
Assert.AreEqual(1, mph.Query.Charge);
}
public void Test()
{
IPropertyConverter<IdentifiedSpectrum> io = new IdentifiedSpectrumExpectValueConverter<IdentifiedSpectrum>();
var mph = new IdentifiedSpectrum();
Assert.AreEqual("ExpectValue", io.Name);
io.SetProperty(mph, "0.1234");
Assert.AreEqual("1.23E-001", io.GetProperty(mph));
Assert.AreEqual(0.1234, mph.ExpectValue, 0.0001);
}
public void Test()
{
IPropertyConverter <IdentifiedSpectrum> io = new IdentifiedSpectrumModificationConverter <IdentifiedSpectrum>();
var mph = new IdentifiedSpectrum();
Assert.AreEqual("Modification", io.Name);
io.SetProperty(mph, "O18(2)");
Assert.AreEqual("O18(2)", io.GetProperty(mph));
Assert.AreEqual("O18(2)", mph.Modifications);
}
public void Test()
{
IPropertyConverter <IdentifiedSpectrum> io = new IdentifiedSpectrumDeltaScoreConverter <IdentifiedSpectrum>();
var mph = new IdentifiedSpectrum();
Assert.AreEqual("DeltaScore", io.Name);
io.SetProperty(mph, "0.12");
Assert.AreEqual("0.12", io.GetProperty(mph));
Assert.AreEqual(0.12, mph.DeltaScore, 0.01);
}
public void Test()
{
IPropertyConverter<IdentifiedSpectrum> io = new IdentifiedSpectrumDeltaScoreConverter<IdentifiedSpectrum>();
var mph = new IdentifiedSpectrum();
Assert.AreEqual("DeltaScore", io.Name);
io.SetProperty(mph, "0.12");
Assert.AreEqual("0.12", io.GetProperty(mph));
Assert.AreEqual(0.12, mph.DeltaScore, 0.01);
}
private static void AddSpectrum(List <IIdentifiedSpectrum> isoSpectra, string seq, string site)
{
var spec = new IdentifiedSpectrum();
spec.AddPeptide(new IdentifiedPeptide(spec)
{
Sequence = seq,
SiteProbability = site
});
isoSpectra.Add(spec);
}
protected bool ParseFromOutfileLineWithoutId(List <string> sLines, IdentifiedSpectrum entry)
{
if (sLines.Count < 11)
{
return(false);
}
sLines.Insert(3, "0");
return(ParseFromOutfileLineWithId(sLines, entry));
}
public void Test()
{
IPropertyConverter<IdentifiedSpectrum> io = new IdentifiedSpectrumMissCleavageConverter<IdentifiedSpectrum>();
var mph = new IdentifiedSpectrum();
Assert.AreEqual("MissCleavage", io.Name);
io.SetProperty(mph, "1");
Assert.AreEqual("1", io.GetProperty(mph));
Assert.AreEqual(1, mph.NumMissedCleavages);
}
public void Test()
{
IPropertyConverter <IdentifiedSpectrum> io = new IdentifiedSpectrumExpectValueConverter <IdentifiedSpectrum>();
var mph = new IdentifiedSpectrum();
Assert.AreEqual("ExpectValue", io.Name);
io.SetProperty(mph, "0.1234");
Assert.AreEqual("1.23E-001", io.GetProperty(mph));
Assert.AreEqual(0.1234, mph.ExpectValue, 0.0001);
}
public void Test()
{
AbstractPropertyConverter <IdentifiedSpectrum> io = new IdentifiedSpectrumRankConverter <IdentifiedSpectrum>();
var mph = new IdentifiedSpectrum();
Assert.AreEqual("Rank", io.Name);
io.SetProperty(mph, "2");
Assert.AreEqual("2", io.GetProperty(mph));
Assert.AreEqual(2, mph.Rank);
}
public void TestGetSequenceString()
{
var mph = new IdentifiedSpectrum();
var mp1 = new IdentifiedPeptide(mph);
mp1.Sequence = "P1";
var mp2 = new IdentifiedPeptide(mph);
mp2.Sequence = "P2";
Assert.AreEqual("P1 ! P2", MascotPeptideHitTextWriter.GetSequenceString(mph));
}
public void Test()
{
AbstractPropertyConverter<IdentifiedSpectrum> io = new IdentifiedSpectrumFileScanConverter<IdentifiedSpectrum>();
var mph = new IdentifiedSpectrum();
mph.Query.FileScan.ShortFileName = "ABC,1-2";
Assert.AreEqual("\"File, Scan(s)\"", io.Name);
Assert.AreEqual("ABC,1 - 2", io.GetProperty(mph));
io.SetProperty(mph, "DEF,3");
Assert.AreEqual("DEF,3", mph.Query.FileScan.ShortFileName);
}
private void CheckPlexType(IsobaricType plexType, string expectHeader, string expectValue)
{
var ann = new IdentifiedSpectrum();
var pqr = new IsobaricItem()
{
PlexType = plexType,
Valid = true,
ValidProbability = 0.0005
};
var refItems = plexType.GetDefinition().Items;
foreach (var item in refItems)
{
pqr[item.Index] = item.Mass;
}
ann.SetIsobaricItem(pqr);
//从实例构建converter
var converter = new ITraqItemPlexConverter <IAnnotation>();
List <IPropertyConverter <IAnnotation> > converters = new List <IPropertyConverter <IAnnotation> >();
converters.Add(converter);
converters.AddRange(converter.GetRelativeConverter(new IAnnotation[] { ann }.ToList()));
CompositePropertyConverter <IAnnotation> finalConverter = new CompositePropertyConverter <IAnnotation>(converters, ',');
if (exportToConsole)
{
Console.WriteLine(finalConverter.Name);
}
Assert.AreEqual(expectHeader, finalConverter.Name);
var line1 = finalConverter.GetProperty(ann);
if (exportToConsole)
{
Console.WriteLine(line1);
}
Assert.AreEqual(expectValue, line1);
var protein2 = new IdentifiedSpectrum();
//从factory根据header构建converter
var finalC = IdentifiedSpectrumPropertyConverterFactory.GetInstance().GetConverters(finalConverter.Name, ',');
finalC.SetProperty(protein2, line1);
var line2 = finalConverter.GetProperty(protein2);
Assert.AreEqual(line1, line2);
}
public void Test()
{
IPropertyConverter<IdentifiedSpectrum> io = new IdentifiedSpectrumTheoreticalMHConverter<IdentifiedSpectrum>();
var mph = new IdentifiedSpectrum();
mph.IsPrecursorMonoisotopic = true;
Assert.AreEqual("MH+", io.Name);
io.SetProperty(mph, "2000.0000");
Assert.AreEqual("2000.00000", io.GetProperty(mph));
Assert.AreEqual(2000.0000 - Atom.H.MonoMass + Atom.ElectronMass, mph.TheoreticalMass, 0.0001);
}
public void TestKeepDistinctPeptideOnly()
{
var spectrum1 = new IdentifiedSpectrum();
var pep1 = spectrum1.NewPeptide();
var spectrum2 = new IdentifiedSpectrum();
var pep2 = spectrum2.NewPeptide();
var spectrum3 = new IdentifiedSpectrum();
var pep3 = spectrum3.NewPeptide();
var spectrum4 = new IdentifiedSpectrum();
var pep4 = spectrum4.NewPeptide();
var protein1 = new IdentifiedProtein();
protein1.Peptides.Add(pep1);
protein1.Peptides.Add(pep2);
var protein2 = new IdentifiedProtein();
protein2.Peptides.Add(pep1);
protein2.Peptides.Add(pep3);
var protein3 = new IdentifiedProtein();
protein3.Peptides.Add(pep2);
protein3.Peptides.Add(pep4);
var g1 = new IdentifiedProteinGroup();
g1.Add(protein1);
var g2 = new IdentifiedProteinGroup();
g2.Add(protein2);
var g3 = new IdentifiedProteinGroup();
g3.Add(protein3);
IIdentifiedResult ir = new IdentifiedResult();
ir.Add(g1);
ir.Add(g2);
ir.Add(g3);
new DistinctResultDistiller().KeepDistinctPeptideOnly(ir);
Assert.AreEqual(2, ir.Count);
Assert.AreEqual(g2, ir[0]);
Assert.AreEqual(g3, ir[1]);
Assert.AreEqual(1, ir[0].GetPeptides().Count);
Assert.AreEqual(spectrum3, ir[0].GetPeptides()[0]);
Assert.AreEqual(1, ir[1].GetPeptides().Count);
Assert.AreEqual(spectrum4, ir[1].GetPeptides()[0]);
}
private IIdentifiedSpectrum ParsePeptide(string line)
{
IIdentifiedSpectrum result = new IdentifiedSpectrum();
string[] parts = line.Split(splits);
result.Query.FileScan.Experimental = parts[bestLocalizationRawFileIndex];
result.Query.FileScan.FirstScan = int.Parse(parts[bestLocalizationScanNumberIndex]);
result.Query.FileScan.LastScan = result.Query.FileScan.FirstScan;
result.Query.FileScan.Charge = int.Parse(parts[chargeIndex]);
result.Score = MyConvert.ToDouble(parts[scoreIndex]);
result.DeltaScore = MyConvert.ToDouble(parts[scoreDiffIndex]);
result.ExpectValue = MyConvert.ToDouble(parts[pepIndex]);
result.Probability = MyConvert.ToDouble(parts[localizationProbIndex]);
string seq = parts[sequenceWindowIndex];
string modifications = parts[modificationWindowIndex];
seq = GetModifiedSequence(seq, modifications);
seq = seq.Replace("_", "");
Match m = modReg.Match(seq);
if (m.Success)
{
while (m.Success)
{
string mod = m.Groups[1].Value;
if (!modCharMap.ContainsKey(mod))
{
modCharMap[mod] = ModificationConsts.MODIFICATION_CHAR.Substring(modCharMap.Count + 1, 1);
}
m = m.NextMatch();
}
seq = ReplaceModificationStringToChar(seq);
}
result.NewPeptide().Sequence = seq;
StringBuilder sb = new StringBuilder();
foreach (var mod in modCharMap)
{
if (seq.Contains(mod.Value))
{
sb.Append(MyConvert.Format("{0}={1};", mod.Value, mod.Key));
}
}
result.Modifications = sb.ToString();
return(result);
}
public void Test()
{
IPropertyConverter <IdentifiedSpectrum> io = new IdentifiedSpectrumTheoreticalMHConverter <IdentifiedSpectrum>();
var mph = new IdentifiedSpectrum();
mph.IsPrecursorMonoisotopic = true;
Assert.AreEqual("MH+", io.Name);
io.SetProperty(mph, "2000.0000");
Assert.AreEqual("2000.00000", io.GetProperty(mph));
Assert.AreEqual(2000.0000 - Atom.H.MonoMass + Atom.ElectronMass, mph.TheoreticalMass, 0.0001);
}
public void TestSetIons()
{
var sp = new IdentifiedSpectrum();
sp.Ions = "10/20";
Assert.AreEqual(10, sp.MatchedIonCount);
Assert.AreEqual(20, sp.TheoreticalIonCount);
sp.Ions = "10|20";
Assert.AreEqual(10, sp.MatchedIonCount);
Assert.AreEqual(20, sp.TheoreticalIonCount);
Assert.AreEqual("10/20", sp.Ions);
}
public void Test()
{
AbstractPropertyConverter <IdentifiedSpectrum> io = new IdentifiedSpectrumFileScanConverter <IdentifiedSpectrum>();
var mph = new IdentifiedSpectrum();
mph.Query.FileScan.ShortFileName = "ABC,1-2";
Assert.AreEqual("\"File, Scan(s)\"", io.Name);
Assert.AreEqual("ABC,1 - 2", io.GetProperty(mph));
io.SetProperty(mph, "DEF,3");
Assert.AreEqual("DEF,3", mph.Query.FileScan.ShortFileName);
}
public void TestGetProteinString()
{
var mph = new IdentifiedSpectrum();
var mp1 = new IdentifiedPeptide(mph);
mp1.AddProtein("P1");
var mp2 = new IdentifiedPeptide(mph);
mp2.AddProtein("P2");
mp2.AddProtein("P3");
Assert.AreEqual("P1 ! P2/P3", MascotPeptideHitTextWriter.GetProteinString(mph));
}
public void TestSetIons()
{
var sp = new IdentifiedSpectrum();
sp.Ions = "10/20";
Assert.AreEqual(10, sp.MatchedIonCount);
Assert.AreEqual(20, sp.TheoreticalIonCount);
sp.Ions = "10|20";
Assert.AreEqual(10, sp.MatchedIonCount);
Assert.AreEqual(20, sp.TheoreticalIonCount);
Assert.AreEqual("10/20", sp.Ions);
}
public void TestBuildProteins()
{
var mph1 = new IdentifiedSpectrum();
mph1.Query.FileScan.Experimental = "EXP1";
var mp1 = new IdentifiedPeptide(mph1);
mp1.AddProtein("Protein1");
mp1.AddProtein("Protein2");
var mph2 = new IdentifiedSpectrum();
mph2.Query.FileScan.Experimental = "EXP2";
var mp2 = new IdentifiedPeptide(mph2);
mp2.AddProtein("Protein1");
mp2.AddProtein("Protein3");
var mphs = new List <IIdentifiedSpectrum>();
mphs.Add(mph1);
mphs.Add(mph2);
List <IIdentifiedProtein> proteins = MascotUtils.BuildProteins(mphs);
Assert.AreEqual(3, proteins.Count);
foreach (IdentifiedProtein mp in proteins)
{
if (mp.Name.Equals("Protein1"))
{
Assert.AreEqual(2, mp.Peptides.Count);
continue;
}
if (mp.Name.Equals("Protein2"))
{
Assert.AreEqual(1, mp.Peptides.Count);
Assert.AreEqual(mp1, mp.Peptides[0]);
continue;
}
if (mp.Name.Equals("Protein3"))
{
Assert.AreEqual(1, mp.Peptides.Count);
Assert.AreEqual(mp2, mp.Peptides[0]);
continue;
}
}
}
protected override void ParseUserParams(IdentifiedSpectrum spectrum, Dictionary <string, string> userParams)
{
base.ParseUserParams(spectrum, userParams);
string value;
if (userParams.TryGetValue("IsotopeError", out value))
{
spectrum.IsotopeError = int.Parse(value);
}
if (userParams.TryGetValue("MS2IonCurrent", out value))
{
spectrum.MatchedTIC = double.Parse(value);
}
}
public void TestGetSequenceString()
{
var mph = new IdentifiedSpectrum();
var mp1 = new IdentifiedPeptide(mph);
mp1.Sequence = "P1";
var mp2 = new IdentifiedPeptide(mph);
mp2.Sequence = "P2";
Assert.AreEqual("P1 ! P2", MascotPeptideHitTextWriter.GetSequenceString(mph));
}
public void Test()
{
IPropertyConverter<IdentifiedSpectrum> io =
new IdentifiedSpectrumTheoreticalMinusExperimentalMassConverter<IdentifiedSpectrum>();
var mph = new IdentifiedSpectrum();
mph.TheoreticalMass = 1000.1234;
Assert.AreEqual("Diff(MH+)", io.Name);
io.SetProperty(mph, "0.12340");
Assert.AreEqual(1000.0000, mph.ExperimentalMass, 0.0001);
Assert.AreEqual("0.12340", io.GetProperty(mph));
}
public void TestModifications()
{
var mphit = new IdentifiedSpectrum();
Assert.AreEqual(new string[0], mphit.GetModifications());
string expect = "Oxidation (M)";
mphit.Modifications = expect;
Assert.AreEqual(1, mphit.GetModifications().Length);
Assert.AreEqual(expect, mphit.GetModifications()[0]);
mphit.Modifications = "Oxidation (M); Label:18O(1) (C-term)";
Assert.AreEqual(2, mphit.GetModifications().Length);
Assert.AreEqual("Oxidation (M)", mphit.GetModifications()[0]);
Assert.AreEqual("Label:18O(1) (C-term)", mphit.GetModifications()[1]);
}
public void TestDistinctPeptides()
{
IdentifiedProtein protein = new IdentifiedProtein();
IdentifiedSpectrum sp1 = new IdentifiedSpectrum();
IdentifiedSpectrum sp2 = new IdentifiedSpectrum();
protein.Peptides.Add(new IdentifiedPeptide(sp1));
protein.Peptides.Add(new IdentifiedPeptide(sp1));
protein.Peptides.Add(new IdentifiedPeptide(sp2));
Assert.AreEqual(3, protein.Peptides.Count);
Assert.AreEqual(2, protein.GetSpectra().Count);
Assert.AreEqual(2, protein.GetDistinctPeptides().Count());
}
public void TestGetProteinString()
{
var mph = new IdentifiedSpectrum();
var mp1 = new IdentifiedPeptide(mph);
mp1.AddProtein("P1");
var mp2 = new IdentifiedPeptide(mph);
mp2.AddProtein("P2");
mp2.AddProtein("P3");
Assert.AreEqual("P1 ! P2/P3", MascotPeptideHitTextWriter.GetProteinString(mph));
}
public void Test()
{
IPropertyConverter <IdentifiedSpectrum> io =
new IdentifiedSpectrumTheoreticalMinusExperimentalMassConverter <IdentifiedSpectrum>();
var mph = new IdentifiedSpectrum();
mph.TheoreticalMass = 1000.1234;
Assert.AreEqual("Diff(MH+)", io.Name);
io.SetProperty(mph, "0.12340");
Assert.AreEqual(1000.0000, mph.ExperimentalMass, 0.0001);
Assert.AreEqual("0.12340", io.GetProperty(mph));
}
private void CheckPlexType(IsobaricType plexType, string expectHeader, string expectValue)
{
var ann = new IdentifiedSpectrum();
var pqr = new IsobaricItem()
{
PlexType = plexType,
Valid = true,
ValidProbability = 0.0005
};
var refItems = plexType.GetDefinition().Items;
foreach (var item in refItems)
{
pqr[item.Index] = item.Mass;
}
ann.SetIsobaricItem(pqr);
//从实例构建converter
var converter = new ITraqItemPlexConverter<IAnnotation>();
List<IPropertyConverter<IAnnotation>> converters = new List<IPropertyConverter<IAnnotation>>();
converters.Add(converter);
converters.AddRange(converter.GetRelativeConverter(new IAnnotation[] { ann }.ToList()));
CompositePropertyConverter<IAnnotation> finalConverter = new CompositePropertyConverter<IAnnotation>(converters, ',');
if (exportToConsole)
{
Console.WriteLine(finalConverter.Name);
}
Assert.AreEqual(expectHeader, finalConverter.Name);
var line1 = finalConverter.GetProperty(ann);
if (exportToConsole)
{
Console.WriteLine(line1);
}
Assert.AreEqual(expectValue, line1);
var protein2 = new IdentifiedSpectrum();
//从factory根据header构建converter
var finalC = IdentifiedSpectrumPropertyConverterFactory.GetInstance().GetConverters(finalConverter.Name, ',');
finalC.SetProperty(protein2, line1);
var line2 = finalConverter.GetProperty(protein2);
Assert.AreEqual(line1, line2);
}
public void Test()
{
var mph = new IdentifiedSpectrum();
var io = new AnnotationConverter <IdentifiedSpectrum>("TEST");
Assert.AreEqual("TEST", io.Name);
Assert.AreEqual("", io.GetProperty(mph));
io = new AnnotationConverter <IdentifiedSpectrum>("TEST", "DEFAULT_VALUE");
Assert.AreEqual("DEFAULT_VALUE", io.GetProperty(mph));
io.SetProperty(mph, "TEST_VALUE");
Assert.AreEqual("TEST_VALUE", io.GetProperty(mph));
Assert.AreEqual("TEST_VALUE", mph.Annotations["TEST"]);
}
public void Test()
{
var mph = new IdentifiedSpectrum();
var io = new AnnotationConverter<IdentifiedSpectrum>("TEST");
Assert.AreEqual("TEST", io.Name);
Assert.AreEqual("", io.GetProperty(mph));
io = new AnnotationConverter<IdentifiedSpectrum>("TEST", "DEFAULT_VALUE");
Assert.AreEqual("DEFAULT_VALUE", io.GetProperty(mph));
io.SetProperty(mph, "TEST_VALUE");
Assert.AreEqual("TEST_VALUE", io.GetProperty(mph));
Assert.AreEqual("TEST_VALUE", mph.Annotations["TEST"]);
}
public void TestModifications()
{
var mphit = new IdentifiedSpectrum();
Assert.AreEqual(new string[0], mphit.GetModifications());
string expect = "Oxidation (M)";
mphit.Modifications = expect;
Assert.AreEqual(1, mphit.GetModifications().Length);
Assert.AreEqual(expect, mphit.GetModifications()[0]);
mphit.Modifications = "Oxidation (M); Label:18O(1) (C-term)";
Assert.AreEqual(2, mphit.GetModifications().Length);
Assert.AreEqual("Oxidation (M)", mphit.GetModifications()[0]);
Assert.AreEqual("Label:18O(1) (C-term)", mphit.GetModifications()[1]);
}
public void TestBuildProteins()
{
var mph1 = new IdentifiedSpectrum();
mph1.Query.FileScan.Experimental = "EXP1";
var mp1 = new IdentifiedPeptide(mph1);
mp1.AddProtein("Protein1");
mp1.AddProtein("Protein2");
var mph2 = new IdentifiedSpectrum();
mph2.Query.FileScan.Experimental = "EXP2";
var mp2 = new IdentifiedPeptide(mph2);
mp2.AddProtein("Protein1");
mp2.AddProtein("Protein3");
var mphs = new List<IIdentifiedSpectrum>();
mphs.Add(mph1);
mphs.Add(mph2);
List<IIdentifiedProtein> proteins = MascotUtils.BuildProteins(mphs);
Assert.AreEqual(3, proteins.Count);
foreach (IdentifiedProtein mp in proteins)
{
if (mp.Name.Equals("Protein1"))
{
Assert.AreEqual(2, mp.Peptides.Count);
continue;
}
if (mp.Name.Equals("Protein2"))
{
Assert.AreEqual(1, mp.Peptides.Count);
Assert.AreEqual(mp1, mp.Peptides[0]);
continue;
}
if (mp.Name.Equals("Protein3"))
{
Assert.AreEqual(1, mp.Peptides.Count);
Assert.AreEqual(mp2, mp.Peptides[0]);
continue;
}
}
}
public void SetUp()
{
s1 = new IdentifiedSpectrum();
s1.Query.FileScan.ShortFileName = "YEAST_0610_G1_SAX_080811_01,11110";
s1.Query.Charge = 2;
s1.Score = 3.0;
s1.AddPeptide(new IdentifiedPeptide(s1) { Sequence = "R.#VK*PDR.T" });
s2 = new IdentifiedSpectrum();
s2.Query.FileScan.ShortFileName = "YEAST_0610_G1_SAX_080811_01,11110";
s2.Query.Charge = 2;
s2.Score = 2.0;
s2.AddPeptide(new IdentifiedPeptide(s2) { Sequence = "R.#VK*PDR.T" });
s3 = new IdentifiedSpectrum();
s3.Score = 1.0;
s3.Query.FileScan.ShortFileName = "YEAST_0610_G1_SAX_080811_01,11110";
s3.Query.Charge = 3;
s3.AddPeptide(new IdentifiedPeptide(s3) { Sequence = "R.#VK*PDDEFER.T" });
s4 = new IdentifiedSpectrum();
s4.Query.FileScan.ShortFileName = "YEAST_0610_G1_SAX_080811_01,11111";
s4.Query.Charge = 3;
s4.Score = 5.0;
s4.AddPeptide(new IdentifiedPeptide(s4) { Sequence = "R.#VK*PDDSKEIEFER.T" });
s5 = new IdentifiedSpectrum();
s5.Query.FileScan.ShortFileName = "YEAST_0610_G1_SAX_080811_01,11111";
s5.Query.Charge = 3;
s5.Score = 4.0;
s5.AddPeptide(new IdentifiedPeptide(s5) { Sequence = "R.#VK*PEESKEIEFER.T" });
s6 = new IdentifiedSpectrum();
s6.Query.FileScan.ShortFileName = "YEAST_0610_G1_SAX_080811_01,11111";
s6.Query.Charge = 2;
s6.Score = 3.0;
s6.AddPeptide(new IdentifiedPeptide(s6) { Sequence = "R.#VK*PEESEFER.T" });
s7 = new IdentifiedSpectrum();
s7.Query.FileScan.ShortFileName = "YEAST_0610_G1_SAX_080811_01,11111";
s7.Query.Charge = 2;
s7.Score = 3.0;
s7.AddPeptide(new IdentifiedPeptide(s7) { Sequence = "R.#VKPEESEFER*.T" });
}
// 1. 1 / 1 0 1964.9940 0.0000 5.6970 2133.9 21/30 sw|P02666|CASBBOVIN +1 K.FQSEEQQQTEDELQDK.I
protected bool ParseFromOutfileLine(string line, IdentifiedSpectrum entry)
{
// Console.Out.WriteLine(line);
// dfadfas entry.IsProteinFromOutFile = true;
string sLine = line.Trim().Replace('/', ' ');
string[] sLines = this.reg.Split(sLine);
if (sLines.Length < itemIndex.MinCount)
{
return(false);
}
entry.Rank = int.Parse(sLines[itemIndex.RankIndex]);
entry.SpRank = int.Parse(sLines[itemIndex.SpRankIndex]);
entry.TheoreticalMH = MyConvert.ToDouble(sLines[itemIndex.TheoreticalMHIndex]);
entry.DeltaScore = MyConvert.ToDouble(sLines[itemIndex.DeltaScoreIndex]);
entry.Score = MyConvert.ToDouble(sLines[itemIndex.ScoreIndex]);
entry.SpScore = MyConvert.ToDouble(sLines[itemIndex.SpScoreIndex]);
entry.MatchedIonCount = int.Parse(sLines[itemIndex.MatchedIonCountIndex]);
entry.TheoreticalIonCount = int.Parse(sLines[itemIndex.TheoreticalIonCountIndex]);
entry.ClearPeptides();
string sequence;
if ('+' != sLines[itemIndex.SequenceIndex][0])
{
entry.DuplicatedCount = 0;
sequence = sLines[itemIndex.SequenceIndex];
}
else
{
entry.DuplicatedCount = int.Parse(sLines[itemIndex.SequenceIndex].Substring(1, sLines[itemIndex.SequenceIndex].Length - 1));
sequence = sLines[itemIndex.SequenceIndex + 1];
}
CheckSequenceValid(ref sequence);
var sp = new IdentifiedPeptide(entry);
sp.Sequence = sequence;
sp.AddProtein(sLines[itemIndex.ProteinIndex]);
return(true);
}
public void Test()
{
IPropertyConverter<IdentifiedSpectrum> io = new IdentifiedSpectrumSequenceConverter<IdentifiedSpectrum>();
var mph = new IdentifiedSpectrum();
var mp1 = new IdentifiedPeptide(mph);
mp1.Sequence = "AAAAA";
var mp2 = new IdentifiedPeptide(mph);
mp2.Sequence = "BBBBB";
Assert.AreEqual("Sequence", io.Name);
Assert.AreEqual("AAAAA ! BBBBB", io.GetProperty(mph));
io.SetProperty(mph, "CCCCC ! DDDDD ! EEEEE");
Assert.AreEqual(3, mph.Peptides.Count);
Assert.AreEqual("CCCCC", mph.Peptides[0].Sequence);
Assert.AreEqual("DDDDD", mph.Peptides[1].Sequence);
Assert.AreEqual("EEEEE", mph.Peptides[2].Sequence);
}
public void TestFilter2()
{
var spectrum = new IdentifiedSpectrum();
spectrum.Query.FileScan.LongFileName = "ABDCDD.12.123.2.dat";
var pro1 = new IdentifiedProtein("P1");
pro1.Peptides.Add(new IdentifiedPeptide(spectrum) { Sequence = "AAAAAAA" });
var pro2 = new IdentifiedProtein("P2");
pro2.Peptides.Add(new IdentifiedPeptide(spectrum) { Sequence = "BBBBBBB" });
var g1 = new IdentifiedProteinGroup();
g1.Add(pro1);
g1.Add(pro2);
IdentifiedResult ir = new IdentifiedResult();
ir.Add(g1);
Assert.AreEqual(1, ir.Count);
Assert.AreEqual(2, ir[0].Count);
Assert.AreEqual(1, ir.GetSpectra().Count);
ir.Filter(m =>
{
return m.Sequence.Contains('A');
});
Assert.AreEqual(1, ir.Count);
Assert.AreEqual(1, ir[0].Count);
Assert.AreEqual(1, ir.GetSpectra().Count);
Assert.AreSame(pro1, ir[0][0]);
ir.Filter(m =>
{
return m.Sequence.Contains('C');
});
Assert.AreEqual(0, ir.Count);
}
public void TestCalculateCoverage()
{
IdentifiedProtein protein = new IdentifiedProtein();
//total 30 amino acids
protein.Sequence = "ABCDEDFDEFDSESLKJFDJLSLGFGDDGD";
IdentifiedSpectrum s1 = new IdentifiedSpectrum();
IdentifiedPeptide p1 = new IdentifiedPeptide(s1);
p1.Sequence = "B.CDEDF.D";
protein.Peptides.Add(p1);
protein.CalculateCoverage();
Assert.AreEqual(16.67, protein.Coverage, 0.01);
IdentifiedSpectrum s2 = new IdentifiedSpectrum();
IdentifiedPeptide p2 = new IdentifiedPeptide(s2);
p2.Sequence = "F.DSESL.K";
protein.Peptides.Add(p2);
protein.CalculateCoverage();
Assert.AreEqual(33.33, protein.Coverage, 0.01);
IdentifiedSpectrum s3 = new IdentifiedSpectrum();
IdentifiedPeptide p3 = new IdentifiedPeptide(s3);
p3.Sequence = "L.SLGF.G";
protein.Peptides.Add(p3);
protein.CalculateCoverage();
Assert.AreEqual(46.67, protein.Coverage, 0.01);
IdentifiedSpectrum s4 = new IdentifiedSpectrum();
IdentifiedPeptide p4 = new IdentifiedPeptide(s4);
p4.Sequence = "L.SLGFG.D";
protein.Peptides.Add(p4);
protein.CalculateCoverage();
Assert.AreEqual(50.00, protein.Coverage, 0.01);
}
public void TestUniqueCount()
{
var protein = new IdentifiedProtein();
var spectrum = new IdentifiedSpectrum();
var peptides = new List<IIdentifiedPeptide>();
peptides.Add(new IdentifiedPeptide(spectrum){
Sequence = "ILLLAR"
});
peptides.Add(new IdentifiedPeptide(spectrum){
Sequence = "LILIAR"
});
Assert.AreEqual(1, IdentifiedPeptideUtils.GetUniquePeptideCount(peptides));
peptides.Add(new IdentifiedPeptide(new IdentifiedSpectrum())
{
Sequence = "LIIIAR"
});
Assert.AreEqual(1, IdentifiedPeptideUtils.GetUniquePeptideCount(peptides));
}
public void TestKeepMaxScorePeptideOnly()
{
List<IIdentifiedSpectrum> spectra = new List<IIdentifiedSpectrum>();
spectra.Add(new IdentifiedSpectrum() { Score = 3.0 });
spectra.Add(new IdentifiedSpectrum() { Score = 2.0 });
spectra.ForEach(m =>
{
m.AddPeptide(new IdentifiedPeptide(m) { Sequence = "A1" });
m.Charge = 2;
});
IdentifiedSpectrum other = new IdentifiedSpectrum() { Score = 2.0, Charge = 2 };
other.AddPeptide(new IdentifiedPeptide(other) { Sequence = "B1" });
spectra.Add(other);
List<IIdentifiedSpectrum> filtered = UniquePeptideDistiller.KeepMaxScorePeptideOnly(spectra);
Assert.AreEqual(2, filtered.Count);
Assert.AreEqual(3.0, filtered[0].Score);
Assert.AreEqual("A1", filtered[0].Sequence);
Assert.AreEqual(2.0, filtered[1].Score);
Assert.AreEqual("B1", filtered[1].Sequence);
}
