public override void SetProperty(T t, string value)
{
string[] proteins = reg.Split(value);
if (t.Peptides.Count != proteins.Length)
{
t.ClearPeptides();
for (int i = 0; i < proteins.Length; i++)
{
IIdentifiedPeptide mp = new IdentifiedPeptide(t);
string[] parts = proteins[i].Split(chars);
foreach (string part in parts)
{
mp.AddProtein(part);
}
}
}
else
{
for (int i = 0; i < proteins.Length; i++)
{
string[] parts = proteins[i].Split(chars);
t.Peptides[i].ClearProteins();
foreach (string part in parts)
{
t.Peptides[i].AddProtein(part);
}
}
}
}
private void ParseSearchHit(IIdentifiedSpectrum sph, XElement searchHit, PepXmlModifications ppmods)
{
var sp = new IdentifiedPeptide(sph);
var mod_info = searchHit.FindFirstDescendant("modification_info");
string seq = searchHit.Attribute("peptide").Value;
if (mod_info != null)
{
var modified_peptide = mod_info.Attribute("modified_peptide");
if (modified_peptide != null && !modReg.Match(modified_peptide.Value).Success)
{
seq = modified_peptide.Value;
}
else
{
var pureSeq = seq;
var modaas = PeptideProphetUtils.ParseModificationAminoacidMass(mod_info);
if (modaas != null && modaas.Count > 0)
{
modaas.Reverse();
foreach (var modaa in modaas)
{
string modchar = FindModificationChar(ppmods, modaa, pureSeq);
seq = seq.Insert(modaa.Position, modchar);
}
}
}
}
if (searchHit.Attribute("peptide_prev_aa") != null)
{
sp.Sequence = searchHit.Attribute("peptide_prev_aa").Value + "." +
seq + "." +
searchHit.Attribute("peptide_next_aa").Value;
}
else
{
sp.Sequence = seq;
}
sph.NumMissedCleavages = GetAttributeValue(searchHit, "num_missed_cleavages", 0);
sph.NumProteaseTermini = GetAttributeValue(searchHit, "num_tol_term", 2);
sp.AddProtein(searchHit.Attribute("protein").Value);
var NumTotalProteins = int.Parse(searchHit.Attribute("num_tot_proteins").Value);
if (NumTotalProteins > 1)
{
var alternative_proteins = searchHit.FindDescendants("alternative_protein");
foreach (var alternative_protein in alternative_proteins)
{
sp.AddProtein(alternative_protein.Attribute("protein").Value);
}
}
ParseScoreAndOtherInformation(sph, searchHit);
}
protected void ModifySequence(IdentifiedPeptide mp, Dictionary <int, string> modifications, PFindModification mm)
{
var positions = (from m in modifications
where !mm.StaticModification.ModificationMap.ContainsValue(m.Value)
orderby m.Key descending
select m.Key).ToList();
foreach (var pos in positions)
{
string mod = modifications[pos];
if (this.ModificationCharMap.ContainsKey(mod))
{
if (pos == mp.Sequence.Length)
{
mp.Sequence = mp.Sequence + this.ModificationCharMap[mod].ToString();
}
else
{
mp.Sequence = mp.Sequence.Insert(pos + 1, this.ModificationCharMap[mod].ToString());
}
}
else
{
throw new Exception(MyConvert.Format("Cannot find dynamic modification {0} definition", mod));
}
}
}
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 override void SetProperty(T t, string value)
{
if (string.IsNullOrEmpty(value))
{
return;
}
string[] siteProbs = reg.Split(value);
if (t.Peptides.Count != siteProbs.Length)
{
t.ClearPeptides();
for (int i = 0; i < siteProbs.Length; i++)
{
IIdentifiedPeptide mp = new IdentifiedPeptide(t);
mp.SiteProbability = siteProbs[i];
}
}
else
{
for (int i = 0; i < siteProbs.Length; i++)
{
t.Peptides[i].SiteProbability = siteProbs[i];
}
}
}
public void SetUp()
{
seqs = new Sequence[] { new Sequence("Test1", "ADFADJLFASRDLFKJWONNCKAOIWJEFLNC"), new Sequence("Test2", "WEUOIRJKJNCJKLSDTORWELSDJF") }.ToList();
identical = new IdentifiedPeptide(new IdentifiedSpectrum())
{
Sequence = "JWONNCK"
};
singlemutation = new IdentifiedPeptide(new IdentifiedSpectrum())
{
Sequence = "LSDAOR"
};
misscleavageIdentical = new IdentifiedPeptide(new IdentifiedSpectrum())
{
Sequence = "LFKJWONNCK"
};
misscleavageSingleMutation = new IdentifiedPeptide(new IdentifiedSpectrum())
{
Sequence = "JKLSDAOR"
};
nptIdentical = new IdentifiedPeptide(new IdentifiedSpectrum())
{
Sequence = "JWONNC"
};
nptSingleMutation = new IdentifiedPeptide(new IdentifiedSpectrum())
{
Sequence = "LSDAO"
};
//validator = new SnpDataValidator(null, null, null, new Protease("Trypsin", true, "KR", "P"));
}
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 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 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]);
}
/// <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);
}
public void TestSetSequence()
{
var pi = new IdentifiedPeptide(new IdentifiedSpectrum());
pi.Sequence = "-.MAS*ESETLNPSAR.I";
Assert.AreEqual("-.MAS*ESETLNPSAR.I", pi.Sequence);
Assert.AreEqual("MASESETLNPSAR", pi.PureSequence);
pi.Sequence = "MAS*ESETLNPSAR";
Assert.AreEqual("MAS*ESETLNPSAR", pi.Sequence);
Assert.AreEqual("MASESETLNPSAR", pi.PureSequence);
}
public void TestAddProtein()
{
var pi = new IdentifiedPeptide(new IdentifiedSpectrum());
pi.AddProtein("AAAAA\tBBBBB");
Assert.AreEqual(1, pi.Proteins.Count);
Assert.AreEqual("AAAAA BBBBB", pi.Proteins[0]);
pi.SetProtein(0, "CCCCC\tDDDDD");
Assert.AreEqual(1, pi.Proteins.Count);
Assert.AreEqual("CCCCC DDDDD", pi.Proteins[0]);
}
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 TestAddProtein()
{
var pi = new IdentifiedPeptide(new IdentifiedSpectrum());
pi.AddProtein("AAAAA\tBBBBB");
Assert.AreEqual(1, pi.Proteins.Count);
Assert.AreEqual("AAAAA BBBBB", pi.Proteins[0]);
pi.SetProtein(0, "CCCCC\tDDDDD");
Assert.AreEqual(1, pi.Proteins.Count);
Assert.AreEqual("CCCCC DDDDD", pi.Proteins[0]);
}
public void TestSetSequence()
{
var pi = new IdentifiedPeptide(new IdentifiedSpectrum());
pi.Sequence = "-.MAS*ESETLNPSAR.I";
Assert.AreEqual("-.MAS*ESETLNPSAR.I", pi.Sequence);
Assert.AreEqual("MASESETLNPSAR", pi.PureSequence);
pi.Sequence = "MAS*ESETLNPSAR";
Assert.AreEqual("MAS*ESETLNPSAR", pi.Sequence);
Assert.AreEqual("MASESETLNPSAR", pi.PureSequence);
}
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 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 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 SetUp()
{
seqs = new Sequence[] { new Sequence("Test1", "ADFADJLFASRDLFKJWONNCKAOIWJEFLNC"), new Sequence("Test2", "WEUOIRJKJNCJKLSDTORWELSDJF") }.ToList();
identical = new IdentifiedPeptide(new IdentifiedSpectrum()) { Sequence = "JWONNCK" };
singlemutation = new IdentifiedPeptide(new IdentifiedSpectrum()) { Sequence = "LSDAOR" };
misscleavageIdentical = new IdentifiedPeptide(new IdentifiedSpectrum()) { Sequence = "LFKJWONNCK" };
misscleavageSingleMutation = new IdentifiedPeptide(new IdentifiedSpectrum()) { Sequence = "JKLSDAOR" };
nptIdentical = new IdentifiedPeptide(new IdentifiedSpectrum()) { Sequence = "JWONNC" };
nptSingleMutation = new IdentifiedPeptide(new IdentifiedSpectrum()) { Sequence = "LSDAO" };
//validator = new SnpDataValidator(null, null, null, new Protease("Trypsin", true, "KR", "P"));
}
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 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;
}
}
}
// 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);
}
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);
}
protected bool ParseFromOutfileLineWithId(List <string> sLines, IdentifiedSpectrum entry)
{
if (sLines.Count < 12)
{
return(false);
}
//entry.Index = int.Parse(sLines[0].Substring(0, sLines[0].Length - 1));
entry.Rank = int.Parse(sLines[1]);
entry.SpRank = int.Parse(sLines[2]);
//entry.Id = int.Parse(sLines[3]);
entry.TheoreticalMH = MyConvert.ToDouble(sLines[4]);
entry.DeltaScore = MyConvert.ToDouble(sLines[5]);
entry.Score = MyConvert.ToDouble(sLines[6]);
entry.SpScore = MyConvert.ToDouble(sLines[7]);
entry.MatchedIonCount = int.Parse(sLines[8]);
entry.TheoreticalIonCount = int.Parse(sLines[9]);
entry.ClearPeptides();
string sequence;
if ('+' != sLines[11][0])
{
entry.DuplicatedCount = 0;
sequence = sLines[11];
}
else
{
entry.DuplicatedCount = int.Parse(sLines[11].Substring(1, sLines[11].Length - 1));
sequence = sLines[12];
}
CheckSequenceValid(ref sequence);
var sp = new IdentifiedPeptide(entry);
sp.Sequence = sequence;
sp.AddProtein(sLines[10]);
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 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 List <IIdentifiedSpectrum> ReadFromFile(string fileName)
{
var result = new List <IIdentifiedSpectrum>();
XElement root = XElement.Load(fileName);
var features = root.FindElement("featureDescriptions");
var descriptions = features.FindElements("featureDescription");
var missIndex = FindIndex(fileName, descriptions, "# Missed Cleavages");
var scans = root.FindElements("fragSpectrumScan");
foreach (var scan in scans)
{
var scanNumber = int.Parse(scan.FindAttribute("scanNumber").Value);
var psms = scan.FindElements("peptideSpectrumMatch");
foreach (var psm in psms)
{
IIdentifiedSpectrum spec = new IdentifiedSpectrum();
spec.Query.QueryId = scanNumber;
spec.Id = psm.FindAttribute("id").Value.StringAfter("decoy_");
spec.FromDecoy = psm.FindAttribute("isDecoy").Value.Equals("true");
spec.TheoreticalMH = double.Parse(psm.FindAttribute("calculatedMassToCharge").Value);
spec.ExperimentalMH = double.Parse(psm.FindAttribute("experimentalMassToCharge").Value);
spec.Query.Charge = int.Parse(psm.FindAttribute("chargeState").Value);
var pep = new IdentifiedPeptide(spec);
pep.Sequence = psm.FindElement("peptide").FindElement("peptideSequence").Value;
pep.AddProtein(psm.FindElement("occurence").FindAttribute("proteinId").Value);
var featureEles = psm.FindElement("features").FindElements("feature");
//The first one is the score.
spec.Score = double.Parse(featureEles[0].Value);
spec.NumMissedCleavages = int.Parse(featureEles[missIndex].Value);
result.Add(spec);
}
}
return(result);
}
public void TestNoredundant()
{
string header = "\t\"File, Scan(s)\"\tSequence\tMH+\tDiff(MH+)\tCharge\tRank\tScore\tDeltaScore\tExpectValue\tQuery\tIons\tReference\tDIFF_MODIFIED_CANDIDATE\tPI\tMissCleavage\tModification";
IPropertyConverter<IIdentifiedSpectrum> converter = IdentifiedSpectrumPropertyConverterFactory.GetInstance().GetConverters(header, '\t');
Assert.AreEqual(header, converter.Name);
IIdentifiedSpectrum mphit = new IdentifiedSpectrum();
mphit.Query.FileScan.ShortFileName = "AAA,1-2";
IdentifiedPeptide mp1 = new IdentifiedPeptide(mphit);
mp1.Sequence = "AAAAA";
mp1.AddProtein("PROTEIN1");
mp1.AddProtein("PROTEIN2");
IdentifiedPeptide mp2 = new IdentifiedPeptide(mphit);
mp2.Sequence = "BBBBB";
mp2.AddProtein("PROTEIN3");
mphit.TheoreticalMH = 1000.00102;
mphit.ExperimentalMH = 1000.0;
mphit.Query.Charge = 2;
mphit.Rank = 1;
mphit.Score = 100.2;
mphit.DeltaScore = 0.5;
mphit.ExpectValue = 1.1e-2;
mphit.Query.QueryId = 10;
mphit.NumMissedCleavages = 1;
mphit.Modifications = "O18(1)";
string expect = " AAA,1 - 2 AAAAA ! BBBBB 1000.00102 0.00102 2 1 100.2 0.5 1.10E-002 10 0|0 PROTEIN1/PROTEIN2 ! PROTEIN3 0.00 1 O18(1)";
Assert.AreEqual(expect, converter.GetProperty(mphit));
string expectNew = " BBB,2 - 3 BBBBB 1002.00783 -0.00200 3 2 200.2 0.6 1.20E-003 20 0|0 PROTEIN2/PROTEIN4 0.00 2 O18(2)";
converter.SetProperty(mphit, expectNew);
Assert.AreEqual(expectNew, converter.GetProperty(mphit));
}
public void TestBuild()
{
var pep1 = new IdentifiedPeptide(new IdentifiedSpectrum(new SequestFilename("A", 1, 1, 1, ".dta"))) { Sequence = "A" };
var pep2 = new IdentifiedPeptide(new IdentifiedSpectrum(new SequestFilename("B", 1, 1, 1, ".dta"))) { Sequence = "B" };
var pep3 = new IdentifiedPeptide(new IdentifiedSpectrum(new SequestFilename("C", 1, 1, 1, ".dta"))) { Sequence = "C" };
var pep4 = new IdentifiedPeptide(new IdentifiedSpectrum(new SequestFilename("D", 1, 1, 1, ".dta"))) { Sequence = "D" };
var pep5 = new IdentifiedPeptide(new IdentifiedSpectrum(new SequestFilename("E", 1, 1, 1, ".dta"))) { Sequence = "E" };
var pep6 = new IdentifiedPeptide(new IdentifiedSpectrum(new SequestFilename("F", 1, 1, 1, ".dta"))) { Sequence = "F" };
var protein1 = new IdentifiedProtein()
{
Peptides = new IIdentifiedPeptide[] { pep1, pep3, pep5, pep6 }.ToList()
};
var protein2 = new IdentifiedProtein()
{
Peptides = new IIdentifiedPeptide[] { pep2, pep3, pep4 }.ToList()
};
//should be removed from final result since all peptides has been included in protein1 and protein2, even one protein contains both peptides
var protein3 = new IdentifiedProtein()
{
Peptides = new IIdentifiedPeptide[] { pep1, pep2 }.ToList()
};
//should be removed from final result since all peptides has been included in protein1
var protein4 = new IdentifiedProtein()
{
Peptides = new IIdentifiedPeptide[] { pep1, pep5 }.ToList()
};
var actual = new IdentifiedProteinGroupBuilder().Build(new IIdentifiedProtein[] { protein1, protein2, protein3 }.ToList());
Assert.AreEqual(2, actual.Count);
Assert.AreSame(protein1, actual[0][0]);
Assert.AreSame(protein2, actual[1][0]);
}
public List <IIdentifiedSpectrum> ReadFromFile(string fileName)
{
var result = new List <IIdentifiedSpectrum>();
var anns = new AnnotationFormat().ReadFromFile(fileName);
foreach (var ann in anns)
{
var peptideId = ann.Annotations["PeptideId"] as string;
var sequence = peptideId.StringBefore("_");
var spec = new IdentifiedSpectrum();
var pep = new IdentifiedPeptide(spec);
pep.Sequence = sequence;
spec.Query.FileScan.Experimental = ann.Annotations["Sample"] as string;
spec.Query.FileScan.RetentionTime = double.Parse(ann.Annotations["PredictionRetentionTime"] as string);
spec.Query.FileScan.Charge = int.Parse(ann.Annotations["Charge"] as string);
spec.IsPrecursorMonoisotopic = true;
spec.TheoreticalMH = PrecursorUtils.MzToMH(double.Parse(ann.Annotations["TheoreticalMz"] as string), spec.Query.FileScan.Charge, true);
result.Add(spec);
}
return(result);
}
public List <IIdentifiedSpectrum> ReadFromFile(string fileName)
{
var result = new List <IIdentifiedSpectrum>();
XElement root = XElement.Load(fileName);
var peptides = root.FindElement("peptides").FindElements("peptide");
foreach (var peptide in peptides)
{
IIdentifiedSpectrum spec = new IdentifiedSpectrum();
var pep = new IdentifiedPeptide(spec);
pep.Sequence = peptide.FindAttribute("peptide_id").Value;
spec.FromDecoy = peptide.FindAttribute("decoy").Value.Equals("true");
spec.SpScore = double.Parse(peptide.FindElement("svm_score").Value);
spec.QValue = double.Parse(peptide.FindElement("q_value").Value);
spec.Score = double.Parse(peptide.FindElement("pep").Value);
spec.TheoreticalMass = double.Parse(peptide.FindElement("calc_mass").Value);
pep.AddProtein(peptide.FindElement("protein_id").Value);
spec.Probability = double.Parse(peptide.FindElement("p_value").Value);
result.Add(spec);
}
return(result);
}
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]);
}
/// <summary>
///
/// Get top one peptide list from xtandem xml file
///
/// </summary>
/// <param name="fileName">xtandem xml filename</param>
/// <returns>List of IIdentifiedSpectrum</returns>
public List <IIdentifiedSpectrum> ReadFromFile(string fileName)
{
string sourceFilename = GetSourceFile(fileName);
List <IIdentifiedSpectrum> result = new List <IIdentifiedSpectrum>();
XmlDocument doc = new XmlDocument();
doc.Load(fileName);
this.xmlHelper = new XmlHelper(doc);
XmlNode root = doc.DocumentElement;
Match mSource = Regex.Match(sourceFilename, @"(.+)\.(?:RAW)", RegexOptions.IgnoreCase);
if (mSource.Success)
{
sourceFilename = mSource.Groups[1].Value;
}
else
{
mSource = Regex.Match(sourceFilename, @"(.+?)\.");
if (mSource.Success)
{
sourceFilename = mSource.Groups[1].Value;
}
}
XmlNode parameters = xmlHelper.GetFirstChildByNameAndAttribute(root, "group", "label", "input parameters");
ParseParameters(parameters);
int pos = sourceFilename.LastIndexOfAny(new char[] { '/', '\\' });
string rawFileName;
if (pos > 0)
{
rawFileName = sourceFilename.Substring(pos + 1);
}
else
{
rawFileName = sourceFilename;
}
rawFileName = FileUtils.ChangeExtension(rawFileName, "");
List <XmlNode> groupNodes = xmlHelper.GetChildrenByNameAndAttribute(root, "group", "type", "model");
foreach (XmlNode groupNode in groupNodes)
{
Dictionary <string, IIdentifiedPeptide> pepmap = new Dictionary <string, IIdentifiedPeptide>();
IIdentifiedSpectrum spectrum = new IdentifiedSpectrum();
List <XmlNode> proteins = xmlHelper.GetChildren(groupNode, "protein");
foreach (XmlNode proteinNode in proteins)
{
XmlNode domainNode = xmlHelper.GetValidChild(xmlHelper.GetValidChild(proteinNode, "peptide"), "domain");
int numMissedCleavages = int.Parse(domainNode.Attributes["missed_cleavages"].Value);
string preSeq = domainNode.Attributes["pre"].Value;
if (preSeq.Equals("["))
{
preSeq = "-";
}
string postSeq = domainNode.Attributes["post"].Value;
if (postSeq.Equals("]"))
{
postSeq = "-";
}
StringBuilder pepSeqSB = new StringBuilder(domainNode.Attributes["seq"].Value);
int start = int.Parse(domainNode.Attributes["start"].Value);
int end = int.Parse(domainNode.Attributes["end"].Value);
List <XmlNode> modifications = xmlHelper.GetChildren(domainNode, "aa");
if (modifications.Count > 0)
{
List <ModificationItem> items = new List <ModificationItem>();
foreach (XmlNode modification in modifications)
{
int at = int.Parse(modification.Attributes["at"].Value);
if (at < start || at > end)
{
continue;
}
ModificationItem item = new ModificationItem();
item.Type = modification.Attributes["type"].Value;
item.At = at;
item.Modified = MyConvert.ToDouble(modification.Attributes["modified"].Value);
if (!staticModifications.ContainsKey(item.Type[0]))
{
items.Add(item);
}
}
spectrum.Modifications = "";
if (items.Count > 0)
{
items.Sort((m1, m2) => m1.At - m2.At);
var mod = "";
foreach (ModificationItem item in items)
{
mod = mod + MyConvert.Format(",{0}({1:0.0000})", item.Type, item.Modified);
}
spectrum.Modifications = mod.Substring(1);
items.Sort((m1, m2) => m2.At - m1.At);
foreach (ModificationItem item in items)
{
var key = GetModifiedKey(item.Modified);
if (!dynamicModificationChars.ContainsKey(key))
{
AddDynamicModificationChar(key);
}
char modificationChar = dynamicModificationChars[key];
pepSeqSB.Insert(item.At - start + 1, modificationChar.ToString());
}
spectrum.Modifications = mod.Substring(1);
}
}
StringBuilder sb = new StringBuilder();
sb.Append(preSeq.Substring(preSeq.Length - 1));
sb.Append(".");
sb.Append(pepSeqSB.ToString());
sb.Append(".");
sb.Append(postSeq[0]);
string pepSeq = sb.ToString();
if (!pepmap.ContainsKey(pepSeq))
{
IdentifiedPeptide pep = new IdentifiedPeptide(spectrum);
pep.Sequence = pepSeq;
pepmap[pepSeq] = pep;
spectrum.TheoreticalMH = MyConvert.ToDouble(domainNode.Attributes["mh"].Value);
spectrum.Score = MyConvert.ToDouble(domainNode.Attributes["hyperscore"].Value);
double nextScore = MyConvert.ToDouble(domainNode.Attributes["nextscore"].Value);
spectrum.DeltaScore = (spectrum.Score - nextScore) / spectrum.Score;
spectrum.NumMissedCleavages = int.Parse(domainNode.Attributes["missed_cleavages"].Value);
}
var noteNode = xmlHelper.GetValidChild(proteinNode, "note");
string proteinName = noteNode.InnerText.StringBefore(" ").StringBefore("\t");
pepmap[pepSeq].AddProtein(proteinName);
}
if (spectrum.Peptides.Count > 0)
{
spectrum.DigestProtease = protease;
result.Add(spectrum);
spectrum.Query.QueryId = int.Parse(groupNode.Attributes["id"].Value);
spectrum.ExperimentalMH = MyConvert.ToDouble(groupNode.Attributes["mh"].Value);
spectrum.ExpectValue = MyConvert.ToDouble(groupNode.Attributes["expect"].Value);
XmlNode spectrumNode = xmlHelper.GetFirstChildByNameAndAttribute(groupNode, "group", "label", "fragment ion mass spectrum");
XmlNode labelNode = xmlHelper.GetFirstChildByNameAndAttribute(spectrumNode, "note", "label", "Description");
string title = labelNode.InnerText.Trim();
if (title.StartsWith("RTINSECONDS"))
{
var rtvalue = title.StringAfter("=").StringBefore(" ").StringBefore("-");
spectrum.Query.FileScan.RetentionTime = double.Parse(rtvalue);
title = title.StringAfter(" ").Trim();
}
SequestFilename sf = this.TitleParser.GetValue(title);
if (sf.Experimental == null || sf.Experimental.Length == 0)
{
sf.Experimental = sourceFilename;
}
spectrum.Query.FileScan.LongFileName = sf.LongFileName;
if (sf.RetentionTime > 0 && spectrum.Query.FileScan.RetentionTime == 0)
{
spectrum.Query.FileScan.RetentionTime = sf.RetentionTime;
}
spectrum.Query.Charge = int.Parse(groupNode.Attributes["z"].Value);
spectrum.Query.Title = title;
}
}
return(result);
}
/// <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 = 10, double minScore = 0.0)
{
var result = new List <IIdentifiedSpectrum>();
SequestFilename sf = null;
int curIndex = 0;
using (var sr = new StreamReader(filename))
{
string line;
while ((line = sr.ReadLine()) != null)
{
if (string.IsNullOrWhiteSpace(line))
{
continue;
}
if (line.StartsWith("S"))
{
var title = line.StringAfter("\t");
sf = this.parser.GetValue(title);
curIndex = 0;
continue;
}
var parts = line.Split('\t');
var score = MyConvert.ToDouble(parts[2]);
if (score < minScore)
{
continue;
}
curIndex++;
IIdentifiedSpectrum curSpectrum;
if (curIndex == 1)
{
curSpectrum = new IdentifiedSpectrum();
curSpectrum.Query.FileScan = sf;
curSpectrum.Query.Charge = sf.Charge;
curSpectrum.Score = score;
curSpectrum.Rank = curIndex;
result.Add(curSpectrum);
}
else if (score == result.Last().Score)
{
curSpectrum = result.Last();
}
else if (curIndex > maxRank)
{
continue;
}
else
{
curSpectrum = new IdentifiedSpectrum();
curSpectrum.Query.FileScan = sf;
curSpectrum.Query.Charge = sf.Charge;
curSpectrum.Score = score;
curSpectrum.Rank = curIndex;
result.Add(curSpectrum);
}
IdentifiedPeptide pep = new IdentifiedPeptide(curSpectrum);
pep.Sequence = ModifySequence(parts[1]);
}
}
return(result);
}
public bool Equals(TargetPeptide obj)
{
if (!PeptideMass.Equals(obj.PeptideMass) || !PeptideSequence.Equals(obj.PeptideSequence) || !Modifications.Count.Equals(obj.Modifications.Count) || !IdentifiedPeptide.Equals(obj.IdentifiedPeptide))
{
return(false);
}
foreach (string key in obj.Modifications.Keys)
{
if (obj.Modifications[key] != Modifications[key])
{
return(false);
}
}
return(true);
}
public List <IIdentifiedSpectrum> ReadFromFile(string fileName)
{
XElement root = XElement.Load(fileName);
var name = root.FindElement("AnalysisSoftwareList").
FindElement("AnalysisSoftware").
FindElement("SoftwareName").
FindElement("cvParam").Attribute("name").Value;
var defaultExp = Path.GetFileNameWithoutExtension(fileName);
foreach (var ext in extensions)
{
if (defaultExp.ToLower().EndsWith(ext))
{
defaultExp = defaultExp.Substring(0, defaultExp.Length - ext.Length);
}
}
//parsing identification protocol first
var protocols = root.FindElement("AnalysisProtocolCollection");
var sip = protocols.FindElement("SpectrumIdentificationProtocol");
var modMap = ParseSearchModificationMap(sip.FindElement("ModificationParams"));
var proteases = ParseEnzymes(sip.FindElement("Enzymes"));
var protease = proteases.FirstOrDefault();
//parsing sequence collection, including protein<->peptide map
var seqs = root.FindElement("SequenceCollection");
var proteinMap = (from ele in seqs.FindElements("DBSequence")
let id = ele.Attribute("id").Value
let accession = ParseAccession(ele.Attribute("accession").Value)
let db = ele.Attribute("searchDatabase_ref").Value
select new { Id = id, Accession = accession, DB = db }).ToDictionary(m => m.Id);
var peptideMap = (from ele in seqs.FindElements("Peptide")
let id = ele.Attribute("id").Value
let seq = ele.FindElement("PeptideSequence").Value
let mods = (from modEle in ele.FindElements("Modification")
let mod = ParseModification(modEle, modMap)
where mod != null
orderby mod.Location descending
select mod).ToArray()
let numMiss = protease == null ? 0 : protease.GetMissCleavageSiteCount(seq)
select new MzIdentPeptideItem()
{
Id = id,
PureSequence = seq,
Modifications = mods,
Sequence = GetModifiedSequence(seq, mods),
NumMissCleavage = numMiss
}).ToDictionary(m => m.Id);
var peptideEvidenceMap = (from g in
(from ele in seqs.FindElements("PeptideEvidence")
select new MzIdentPeptideEvidenceItem()
{
Id = ele.Attribute("id").Value,
PeptideRef = ele.Attribute("peptide_ref").Value,
DbRef = ele.Attribute("dBSequence_ref").Value,
Pre = ele.Attribute("pre").Value,
Post = ele.Attribute("post").Value
}).GroupBy(m => m.Id)
select g.First()).ToDictionary(m => m.Id);
//now parsing data
var data = root.FindElement("DataCollection");
var result = new List <IIdentifiedSpectrum>();
var analysisData = data.FindElement("AnalysisData");
var idList = analysisData.FindElement("SpectrumIdentificationList");
foreach (var sir in idList.FindElements("SpectrumIdentificationResult"))
{
var items = FilterItems(sir.FindElements("SpectrumIdentificationItem"), peptideMap, peptideEvidenceMap);
if (items.Count == 0)
{
continue;
}
var spectrum = new IdentifiedSpectrum();
result.Add(spectrum);
var spectrumId = sir.Attribute("spectrumID").Value;
var sirCvParams = GetCvParams(sir);
string value;
if (sirCvParams.TryGetValue("MS:1000796", out value))
{
spectrum.Query.FileScan = TitleParser.GetValue(value);
}
else
{
if (spectrumId.StartsWith("index=") || spectrumId.StartsWith("scan="))
{
spectrum.Query.FileScan.Experimental = defaultExp;
spectrum.Query.FileScan.FirstScan = int.Parse(spectrumId.StringAfter("="));
spectrum.Query.FileScan.LastScan = spectrum.Query.FileScan.FirstScan;
}
else
{
spectrum.Query.FileScan.Experimental = spectrumId;
}
}
if (sirCvParams.TryGetValue("MS:1001115", out value))
{
spectrum.Query.FileScan.FirstScan = int.Parse(value);
}
if (spectrum.Query.FileScan.FirstScan == 0)
{
throw new Exception(string.Format("Cannot find scan information in file {0}", fileName));
}
bool bFirst = true;
foreach (var sit in items)
{
if (bFirst) //only parse score once
{
spectrum.Id = sit.Attribute("id").Value;
spectrum.Charge = int.Parse(sit.Attribute("chargeState").Value);
spectrum.TheoreticalMH = PrecursorUtils.MzToMH(double.Parse(sit.Attribute("calculatedMassToCharge").Value), spectrum.Charge, true);
spectrum.ExperimentalMH = PrecursorUtils.MzToMH(double.Parse(sit.Attribute("experimentalMassToCharge").Value), spectrum.Charge, true);
var cvParams = GetCvParams(sit);
if (cvParams.TryGetValue("MS:1001121", out value))
{
spectrum.MatchedIonCount = int.Parse(value);
}
if (cvParams.TryGetValue("MS:1001362", out value))
{
spectrum.TheoreticalIonCount = int.Parse(value) + spectrum.MatchedIonCount;
}
ParseScore(spectrum, cvParams);
var userParams = GetUserParams(sit);
ParseUserParams(spectrum, userParams);
bFirst = false;
}
var peptide = new IdentifiedPeptide(spectrum);
var pep_ref = sit.Attribute("peptide_ref").Value;
var pep = peptideMap[pep_ref];
spectrum.Modifications = (from m in pep.Modifications
select string.Format("{0}:{1}", m.Location, m.Item.Name)).Reverse().Merge(",");
spectrum.NumMissedCleavages = pep.NumMissCleavage;
foreach (var per in sit.FindElements("PeptideEvidenceRef"))
{
var pe_ref = per.Attribute("peptideEvidence_ref").Value;
var pe = peptideEvidenceMap[pe_ref];
peptide.Sequence = pe.Pre + "." + pep.Sequence + "." + pe.Post;
var protein = proteinMap[pe.DbRef];
peptide.AddProtein(protein.Accession);
}
}
}
return(result);
}
public Dictionary <int, IIdentifiedPeptide> ParsePeptideMap(string fileName)
{
SQLiteDBHelper sqlite = new SQLiteDBHelper(fileName);
Dictionary <int, IIdentifiedPeptide> result = new Dictionary <int, IIdentifiedPeptide>();
var pniReader = sqlite.ExecuteReader("select distinct(ProcessingNodeID) from peptidescores", null);
if (!pniReader.Read())
{
return(result);
}
var nodeid = pniReader.GetInt32(0);
var pniScore = sqlite.ExecuteReader(string.Format("select scoreid from processingnodescores where processingnodeid={0} and ismainscore=1", nodeid), null);
if (!pniScore.Read())
{
return(result);
}
var scoreid = pniScore.GetInt32(0);
Dictionary <int, IIdentifiedSpectrum> spectra = ParseSpectrumMap(fileName);
var aas = ParseAminoacids(fileName);
//读取肽段列表
string sqlPeptide = string.Format("select pep.SpectrumID, pep.PeptideID, pep.TotalIonsCount, pep.MatchedIonsCount, pep.ConfidenceLevel, pep.Sequence, pep.MissedCleavages, ps.ScoreValue from Peptides as pep, PeptideScores as ps where pep.PeptideID=ps.PeptideID and ps.ScoreID={0} order by pep.SpectrumID, pep.SearchEngineRank", scoreid);
var peptideReader = sqlite.ExecuteReader(sqlPeptide, null);
Progress.SetMessage("Parsing peptides ...");
while (peptideReader.Read())
{
var specid = peptideReader.GetInt32(0);
if (!spectra.ContainsKey(specid))
{
continue;
}
var pepid = peptideReader.GetInt32(1);
var seq = peptideReader.GetString(5);
var missedCleavage = peptideReader.GetInt32(6);
var score = peptideReader.GetDouble(7);
IIdentifiedSpectrum spectrum = spectra[specid];
if (spectrum.Peptides.Count == 0)
{
spectrum.TheoreticalIonCount = peptideReader.GetInt32(2);
spectrum.MatchedIonCount = peptideReader.GetInt32(3);
IdentifiedPeptide peptide = new IdentifiedPeptide(spectrum);
peptide.ConfidenceLevel = peptideReader.GetInt32(4);
peptide.Sequence = seq;
spectrum.NumMissedCleavages = missedCleavage;
spectrum.Score = score;
spectrum.TheoreticalMass = aas.MonoPeptideMass(peptide.Sequence);
spectrum.Rank = 1;
spectrum.DeltaScore = 1.0;
result[pepid] = peptide;
continue;
}
else
{
if (score == spectrum.Score)
{
IIdentifiedPeptide peptide = new IdentifiedPeptide(spectrum);
peptide.ConfidenceLevel = peptideReader.GetInt32(4);
peptide.Sequence = seq;
result[pepid] = peptide;
continue;
}
if (seq == spectrum.Peptide.Sequence)
{
continue;
}
spectrum.DeltaScore = (spectrum.Score - score) / spectrum.Score;
}
}
//动态氨基酸修饰
var modMap = ParseModifications(fileName);
string sqlPeptideMod = "select PeptideID, AminoAcidModificationID, Position from PeptidesAminoacidModifications order by Position desc";
var pepModReader = sqlite.ExecuteReader(sqlPeptideMod, null);
Progress.SetMessage("Parsing peptide modifications ...");
while (pepModReader.Read())
{
var pepid = pepModReader.GetInt32(0);
if (!result.ContainsKey(pepid))
{
continue;
}
var modid = pepModReader.GetInt32(1);
var position = pepModReader.GetInt32(2);
var mod = modMap[modid];
var peptide = result[pepid];
var aminoacid = peptide.Sequence[position];
if (peptide.IsTopOne())
{
var modStr = string.Format("{0} ({1})", mod.SignStr, aminoacid);
if (string.IsNullOrEmpty(peptide.Spectrum.Modifications))
{
peptide.Spectrum.Modifications = modStr;
}
else
{
peptide.Spectrum.Modifications = peptide.Spectrum.Modifications + "; " + modStr;
}
peptide.Spectrum.TheoreticalMass += mod.DeltaMass;
}
var modchar = mod.SignChar;
var seq = peptide.Sequence;
peptide.Sequence = seq.Insert(position + 1, modchar.ToString());
}
//动态末端修饰
string sqlTermMod = "select PeptideID, TerminalModificationID from PeptidesTerminalModifications";
var termModReader = sqlite.ExecuteReader(sqlTermMod, null);
Progress.SetMessage("Parsing terminal modifications ...");
while (termModReader.Read())
{
var pepid = termModReader.GetInt32(0);
if (result.ContainsKey(pepid))
{
var modid = termModReader.GetInt32(1);
var peptide = result[pepid];
var mod = modMap[modid];
if (peptide.IsTopOne())
{
if (string.IsNullOrEmpty(peptide.Spectrum.Modifications))
{
peptide.Spectrum.Modifications = mod.SignStr;
}
else if (mod.PositionType == 1)
{
peptide.Spectrum.Modifications = mod.SignStr + "; " + peptide.Spectrum.Modifications;
}
else
{
peptide.Spectrum.Modifications = peptide.Spectrum.Modifications + "; " + mod.SignStr;
}
peptide.Spectrum.TheoreticalMass += mod.DeltaMass;
}
var modchar = mod.SignChar;
var seq = peptide.Sequence;
if (mod.PositionType == 1)
{
seq = modchar.ToString() + seq;
}
else
{
seq = seq + modchar.ToString();
}
peptide.Sequence = seq;
}
}
//其他Score
var dcReader = sqlite.ExecuteReader("select ps.PeptideID, pns.ScoreName, ps.ScoreValue from PeptideScores as ps, ProcessingNodeScores as pns where ps.ScoreID=pns.ScoreID and pns.IsMainScore=0", null);
while (dcReader.Read())
{
var pepid = dcReader.GetInt32(0);
if (result.ContainsKey(pepid))
{
var pep = result[pepid];
if (pep.IsTopOne())
{
var name = dcReader.GetString(1);
var value = dcReader.GetDouble(2);
if (name.Equals("SpScore"))
{
pep.Spectrum.SpScore = value;
}
else if (name.Equals("ProbabilityScore"))
{
pep.Spectrum.Probability = value;
}
}
}
}
return(result);
}
public override List <IIdentifiedProtein> ParseProteins(string fileName)
{
Dictionary <string, IIdentifiedProtein> proteinMap = new Dictionary <string, IIdentifiedProtein>();
Application xApp = new Application();
//得到WorkBook对象, 可以用两种方式之一: 下面的是打开已有的文件
Workbook xBook = xApp.Workbooks._Open(fileName,
Missing.Value, Missing.Value, Missing.Value, Missing.Value
, Missing.Value, Missing.Value, Missing.Value, Missing.Value
, Missing.Value, Missing.Value, Missing.Value, Missing.Value);
try
{
Worksheet xSheet = (Worksheet)xBook.Sheets[1];
int fromRow = 2;
int endRow = fromRow;
for (; endRow <= xSheet.Rows.Count; endRow++)
{
string b = xSheet.Value('B', endRow);
if (null == b)
{
break;
}
}
endRow--;
Progress.SetRange(fromRow, endRow);
Progress.SetMessage("Parsing file ...");
for (int i = fromRow; i <= endRow; i++)
{
Progress.SetPosition(i);
string seq = xSheet.Value('A', i);
if (null == seq)//蛋白质信息
{
continue;
}
string deltaCn = xSheet.Value('I', i);
if (null == deltaCn)//rank > 1
{
continue;
}
string protein = xSheet.Value('B', i);
if (!proteinMap.ContainsKey(protein))
{
var p = new IdentifiedProtein(protein);
p.Coverage = MyConvert.ToDouble(xSheet.Value('C', i + 2));
p.MolecularWeight = MyConvert.ToDouble(xSheet.Value('F', i + 2)) * 1000;
p.IsoelectricPoint = MyConvert.ToDouble(xSheet.Value('G', i + 2));
p.Score = MyConvert.ToDouble(xSheet.Value('H', i + 2));
p.Description = xSheet.Value('I', i + 2);
proteinMap[protein] = p;
}
var pro = proteinMap[protein];
IdentifiedSpectrum spectrum = new IdentifiedSpectrum();
IdentifiedPeptide peptide = new IdentifiedPeptide(spectrum);
peptide.Sequence = seq.ToUpper();
peptide.AddProtein(protein);
spectrum.Modifications = xSheet.Value('F', i);
spectrum.DeltaScore = MyConvert.ToDouble(deltaCn);
spectrum.Charge = Convert.ToInt32(xSheet.Value('K', i));
spectrum.ObservedMz = MyConvert.ToDouble(xSheet.Value('L', i));
spectrum.TheoreticalMH = MyConvert.ToDouble(xSheet.Value('M', i));
spectrum.Ions = xSheet.Value('S', i);
spectrum.Query.FileScan.FirstScan = Convert.ToInt32(xSheet.Value('P', i));
spectrum.Query.FileScan.LastScan = Convert.ToInt32(xSheet.Value('Q', i));
spectrum.Query.FileScan.Experimental = FileUtils.RemoveAllExtension(xSheet.Value('T', i));
pro.Peptides.Add(peptide);
}
}
finally
{
xBook.Close(false, Type.Missing, Type.Missing);
}
var proteins = proteinMap.Values.ToList();
return(proteins);
}
/// <summary>
///
/// Get the query/peptide map from mascot dat file.
///
/// </summary>
/// <param name="filename">pFind 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 Dictionary <int, List <IIdentifiedSpectrum> > ParsePeptides(string filename, int minRank, double minScore)
{
var result = new Dictionary <int, List <IIdentifiedSpectrum> >();
var sourceDir = GetSourceFile(filename);
using (var sr = new StreamReader(filename))
{
var parameters = ParseSection(sr, "Search");
var mm = ParseModification(parameters);
foreach (var mod in mm.DynamicModification)
{
if (!this.ModificationCharMap.ContainsKey(mod.Modification))
{
this.ModificationCharMap[mod.Modification] = ModificationConsts.MODIFICATION_CHAR[this.ModificationCharMap.Count + 1];
}
}
var headers = ParseSection(sr, "Total");
var queryCount = int.Parse(headers["Spectra"]);
Progress.SetRange(1, queryCount);
for (int queryId = 1; queryId <= queryCount; queryId++)
{
if (Progress.IsCancellationPending())
{
throw new UserTerminatedException();
}
Progress.SetPosition(queryId);
var speName = MyConvert.Format("Spectrum{0}", queryId);
var peptideSection = ParseSection(sr, speName);
int candidateCount = int.Parse(peptideSection["ValidCandidate"]);
if (candidateCount == 0)
{
continue;
}
var expMH = MyConvert.ToDouble(peptideSection["MH"]);
var expMz = MyConvert.ToDouble(peptideSection["MZ"]);
var charge = int.Parse(peptideSection["Charge"]);
var iPeps = new List <IIdentifiedSpectrum>();
result[queryId] = iPeps;
IIdentifiedSpectrum lastHit = null;
int rank = 0;
for (int k = 1; k <= candidateCount; k++)
{
string key = "NO" + k.ToString();
var scoreKey = key + "_Score";
if (!peptideSection.ContainsKey(scoreKey))
{
if (null != lastHit)
{
lastHit.DeltaScore = 1.0;
}
break;
}
double score = MyConvert.ToDouble(peptideSection[scoreKey]);
if (score < minScore || score == 0.0)
{
if (null != lastHit)
{
lastHit.DeltaScore = 1.0 - score / lastHit.Score;
}
break;
}
bool bSameRank = null != lastHit && score == lastHit.Score;
if (!bSameRank)
{
if (null != lastHit)
{
lastHit.DeltaScore = 1.0 - score / lastHit.Score;
}
rank++;
if (rank > minRank)
{
break;
}
}
IIdentifiedSpectrum mphit;
if (bSameRank)
{
mphit = lastHit;
}
else
{
mphit = new IdentifiedSpectrum();
mphit.Rank = rank;
mphit.Score = score;
mphit.ExpectValue = MyConvert.ToDouble(peptideSection[key + "_EValue"]);
var mhkey = key + "_MH";
if (peptideSection.ContainsKey(mhkey))
{
mphit.TheoreticalMH = MyConvert.ToDouble(peptideSection[mhkey]);
}
else
{
mphit.TheoreticalMH = MyConvert.ToDouble(peptideSection[key + "_Mass"]);
}
var micKey = key + "_Matched_Peaks";
if (peptideSection.ContainsKey(micKey))
{
mphit.MatchedIonCount = int.Parse(peptideSection[micKey]);
mphit.MatchedTIC = MyConvert.ToDouble(peptideSection[key + "_Matched_Intensity"]);
}
var misKey = key + "_MissCleave";
if (peptideSection.ContainsKey(misKey))
{
mphit.NumMissedCleavages = int.Parse(peptideSection[misKey]);
}
mphit.ExperimentalMH = expMH;
mphit.DeltaScore = 1.0;
mphit.Query.QueryId = queryId;
mphit.Query.ObservedMz = expMz;
mphit.Query.Charge = charge;
//mphit.Query.MatchCount = queryItem.MatchCount;
lastHit = mphit;
}
var mp = new IdentifiedPeptide(mphit);
mp.Sequence = peptideSection[key + "_SQ"];
string modificationPos = peptideSection[key + "_Modify_Pos"];
string modificationName = peptideSection[key + "_Modify_Name"];
Dictionary <int, string> modifications = GetModifications(modificationPos, modificationName);
ModifySequence(mp, modifications, mm);
AssignModification(mphit, modifications, mm);
string proteins = peptideSection[key + "_Proteins"];
var parts = proteins.Split(',');
for (int i = 1; i < parts.Count(); i++)
{
mp.AddProtein(parts[i]);
}
if (!bSameRank)
{
iPeps.Add(mphit);
}
}
var title = new FileInfo(peptideSection["Input"]).Name;
SequestFilename sf = this.TitleParser.GetValue(title);
sf.Charge = charge;
if (sf.Experimental == null || sf.Experimental.Length == 0)
{
sf.Experimental = sourceDir;
}
foreach (IIdentifiedSpectrum mp in iPeps)
{
mp.Query.Title = title;
mp.Query.FileScan.LongFileName = sf.LongFileName;
}
}
}
return(result);
}
public List <IIdentifiedSpectrum> ReadFromFile(string fileName)
{
XElement root = XElement.Load(fileName);
XElement request = root.FindElement("MSSearch_request");
//parsing identification protocol first
var modMap = ParseSearchModificationMap(request.FindFirstDescendant("MSSearchSettings_variable"));
var protease = ParseProtease(request.FindFirstDescendant("MSSearchSettings_enzyme"));
Func <string, int> missCalc;
if (protease == null)
{
missCalc = m => 0;
}
else
{
missCalc = m => protease.GetMissCleavageSiteCount(m);
}
//parsing sequence collection, including protein<->peptide map
var result = new List <IIdentifiedSpectrum>();
var response = root.FindElement("MSSearch_response");
var scale = double.Parse(response.FindFirstDescendant("MSResponse_scale").Value);
var idList = response.FindFirstDescendant("MSResponse_hitsets");
foreach (var sir in idList.FindElements("MSHitSet"))
{
var hits = sir.FindElement("MSHitSet_hits");
if (hits == null)
{
continue;
}
var spectrum = new IdentifiedSpectrum();
result.Add(spectrum);
var title = sir.FindElement("MSHitSet_ids").FindElement("MSHitSet_ids_E").Value;
spectrum.Query.FileScan = this.TitleParser.GetValue(title);
foreach (var hit in hits.FindElements("MSHits"))
{
var evalue = double.Parse(hit.FindElement("MSHits_evalue").Value);
if (spectrum.Peptides.Count > 0)
{
if (evalue > spectrum.ExpectValue)
{
continue;
}
if (evalue < spectrum.ExpectValue)
{
spectrum.ClearPeptides();
}
}
spectrum.ExpectValue = evalue;
spectrum.Score = -Math.Log(spectrum.ExpectValue);
if (spectrum.Query.Charge == 0) // trust the charge from title
{
spectrum.Query.Charge = int.Parse(hit.FindElement("MSHits_charge").Value);
}
spectrum.ExperimentalMass = double.Parse(hit.FindElement("MSHits_mass").Value) / scale;
spectrum.TheoreticalMass = double.Parse(hit.FindElement("MSHits_theomass").Value) / scale;
var peptide = new IdentifiedPeptide(spectrum);
var seq = hit.FindElement("MSHits_pepstring").Value;
spectrum.NumMissedCleavages = missCalc(seq);
var mods = hit.FindElement("MSHits_mods");
if (mods != null)
{
var modsloc = (from ele in mods.FindElements("MSModHit")
let loc = int.Parse(ele.FindElement("MSModHit_site").Value)
let modtype = ele.FindElement("MSModHit_modtype").FindElement("MSMod").Value
orderby loc descending
select new { Location = loc, ModType = modtype }).ToList();
foreach (var modloc in modsloc)
{
seq = seq.Insert(modloc.Location + 1, modMap[modloc.ModType]);
}
}
peptide.Sequence = hit.FindElement("MSHits_pepstart").Value + "." + seq + "." + hit.FindElement("MSHits_pepstop").Value;
foreach (var pep in hit.FindElement("MSHits_pephits").FindElements("MSPepHit"))
{
var proteinName = pep.FindElement("MSPepHit_defline").Value.StringBefore(" ").StringBefore("\t");
peptide.AddProtein(proteinName);
}
}
}
return(result);
}
public override List <IIdentifiedProtein> ParseProteins(string fileName)
{
Dictionary <string, IIdentifiedProtein> proteinMap = new Dictionary <string, IIdentifiedProtein>();
using (StreamReader sr = new StreamReader(fileName))
{
string line = sr.ReadLine();
string[] headerParts = line.Split('\t');
int seqIndex = Array.FindIndex(headerParts, (m => m == "Sequence"));
int proIndex = Array.FindIndex(headerParts, (m => m == "Protein Accessions"));
int modIndex = Array.FindIndex(headerParts, (m => m == "Modifications"));
int xcIndex = Array.FindIndex(headerParts, (m => m == "XCorr"));
int deltaIndex = Array.FindIndex(headerParts, (m => m.EndsWith(" Score")));
int chargeIndex = Array.FindIndex(headerParts, (m => m == "Charge"));
int obsIndex = Array.FindIndex(headerParts, (m => m == "m/z [Da]"));
int mhIndex = Array.FindIndex(headerParts, (m => m == "MH+ [Da]"));
int fscanIndex = Array.FindIndex(headerParts, (m => m == "First Scan"));
int lscanIndex = Array.FindIndex(headerParts, (m => m == "Last Scan"));
int ionIndex = Array.FindIndex(headerParts, (m => m == "Ions Matched"));
int fileIndex = Array.FindIndex(headerParts, (m => m == "Spectrum File"));
Progress.SetRange(0, sr.BaseStream.Length);
Progress.SetMessage("Parsing file ...");
while ((line = sr.ReadLine()) != null)
{
if (line.Trim().Length == 0)
{
break;
}
string[] parts = line.Split('\t');
if (parts[0].Length == 0)
{
continue;
}
Progress.SetPosition(sr.BaseStream.Position);
string seq = parts[seqIndex];
string deltaCn = parts[deltaIndex];
if (deltaCn.Length == 0)//rank > 1
{
continue;
}
string protein = parts[proIndex];
if (!proteinMap.ContainsKey(protein))
{
sr.ReadLine();
string proLine = sr.ReadLine();
string[] proParts = proLine.Split('\t');
var p = new IdentifiedProtein(protein);
p.Coverage = MyConvert.ToDouble(proParts[2]);
p.MolecularWeight = MyConvert.ToDouble(proParts[5]) * 1000;
p.IsoelectricPoint = MyConvert.ToDouble(proParts[6]);
p.Score = MyConvert.ToDouble(proParts[7]);
p.Description = proParts[8];
proteinMap[protein] = p;
}
var pro = proteinMap[protein];
IdentifiedSpectrum spectrum = new IdentifiedSpectrum();
IdentifiedPeptide peptide = new IdentifiedPeptide(spectrum);
peptide.Sequence = seq.ToUpper();
peptide.AddProtein(protein);
spectrum.Modifications = parts[modIndex];
spectrum.DeltaScore = MyConvert.ToDouble(deltaCn);
spectrum.Charge = Convert.ToInt32(parts[chargeIndex]);
spectrum.ObservedMz = MyConvert.ToDouble(parts[obsIndex]);
spectrum.TheoreticalMH = MyConvert.ToDouble(parts[mhIndex]);
spectrum.Ions = parts[ionIndex];
spectrum.Query.FileScan.FirstScan = Convert.ToInt32(parts[fscanIndex]);
spectrum.Query.FileScan.LastScan = Convert.ToInt32(parts[lscanIndex]);
spectrum.Query.FileScan.Experimental = FileUtils.RemoveAllExtension(parts[fileIndex]);
pro.Peptides.Add(peptide);
}
}
var proteins = proteinMap.Values.ToList();
return(proteins);
}
