public Aminoacids GetAminoacids()
{
var mod = ModificationUtils.ParseFromOutFileLine(this.Modification);
var result = new Aminoacids();
mod.ForEach(m => result[m.Key].ResetMass(m.Value, m.Value));
return(result);
}
//(STY* +79.96633) (M# +15.99492) (ST@ -18.00000) C=160.16523 Enzyme:Trypsin(KR) (1)
public static Aminoacids ParseModificationFromOutFileLine(string line)
{
Dictionary <char, double> map = ModificationUtils.ParseFromOutFileLine(line);
var result = new Aminoacids();
foreach (char c in map.Keys)
{
result[c].ResetMass(map[c], map[c]);
}
return(result);
}
/// <summary>
/// Filter spectra by quantify mode
/// </summary>
/// <param name="isoSpectra"></param>
public void FilterSpectraByQuantifyMode(List <IIdentifiedSpectrum> isoSpectra)
{
if (QuantifyMode.qmModificationSite == options.Mode)
{
isoSpectra.RemoveAll(m => !ModificationUtils.IsModifiedSequence(m.GetMatchSequence(), options.ModifiedAminoacids));
if (isoSpectra.Any(m => m.Peptide.GetSiteProbabilities().Any(l => l.Probability > 0.0)))
{
isoSpectra.RemoveAll(m => m.Peptide.GetSiteProbabilities().Any(l => l.Probability < options.MinimumSiteProbability));
}
else
{
Progress.SetMessage("There is no site probability in spectra, cannot filter spectra by minimum site probability, filter ignored.");
}
}
else if (QuantifyMode.qmUnmodifiedPeptide == options.Mode)
{
isoSpectra.RemoveAll(m =>
{
return(ModificationUtils.IsModifiedSequence(m.GetMatchSequence(), options.ModifiedAminoacids));
});
}
}
public List <ModificationSiteProbability> GetSiteProbabilities()
{
return(ModificationUtils.ParseProbability(this.SiteProbability));
}
public virtual Dictionary <int, IIdentifiedPeptide> ParsePeptideMap(string fileName, bool isDecoy)
{
var suffix = isDecoy ? "_decoy" : "";
SQLiteDBHelper sqlite = new SQLiteDBHelper(fileName);
Dictionary <int, IIdentifiedPeptide> result = new Dictionary <int, IIdentifiedPeptide>();
var pniReader = sqlite.ExecuteReader(string.Format("select distinct(ProcessingNodeID) from peptidescores{0}", suffix), 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{0} as pep, PeptideScores{0} as ps where pep.PeptideID=ps.PeptideID and ps.ScoreID={1} order by pep.SpectrumID, pep.SearchEngineRank", suffix, scoreid);
var peptideReader = sqlite.ExecuteReader(sqlPeptide, null);
Progress.SetMessage("Parsing peptides{0} ...", suffix);
while (peptideReader.Read())
{
var specid = peptideReader.GetInt32(0);
if (!spectra.ContainsKey(specid))
{
throw new Exception(string.Format("Cannot find spectrum id {0}", specid));
}
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.Id = specid.ToString();
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;
spectrum.FromDecoy = isDecoy;
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;
}
var dscore = (spectrum.Score - score) / spectrum.Score;
if (dscore < spectrum.DeltaScore)
{
spectrum.DeltaScore = dscore;
}
}
}
//动态氨基酸修饰
var unexpectedModifications = new HashSet <int>();
var modMap = ParseModifications(fileName, unexpectedModifications);
string sqlPeptideMod = string.Format("select PeptideID, AminoAcidModificationID, Position from PeptidesAminoacidModifications{0} order by Position desc", suffix);
var pepModReader = sqlite.ExecuteReader(sqlPeptideMod, null);
Progress.SetMessage("Parsing peptide modifications{0} ...", suffix);
while (pepModReader.Read())
{
var pepid = pepModReader.GetInt32(0);
if (!result.ContainsKey(pepid))
{
//Some peptides ranked lower are ignored.
continue;
}
var modid = pepModReader.GetInt32(1);
if (unexpectedModifications.Contains(modid))
{
continue;
}
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 = string.Format("select PeptideID, TerminalModificationID from PeptidesTerminalModifications{0}", suffix);
var termModReader = sqlite.ExecuteReader(sqlTermMod, null);
Progress.SetMessage("Parsing terminal modifications{0} ...", suffix);
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
Progress.SetMessage("Parsing other scores{0} ...", suffix);
var dcReader = sqlite.ExecuteReader(string.Format("select ps.PeptideID, pns.ScoreName, ps.ScoreValue from PeptideScores{0} as ps, ProcessingNodeScores as pns where ps.ScoreID=pns.ScoreID and pns.IsMainScore=0", suffix), 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;
}
}
}
}
var pniProb = sqlite.ExecuteReader("select FieldId from CustomDataFields where DisplayName='phosphoRS Site Probabilities'", null);
if (!pniProb.Read())
{
Progress.SetMessage("Not phosphoylation data!");
return(result);
}
var fieldid = pniProb.GetInt32(0);
string sqlPhospho = string.Format("select PeptideID, FieldValue from CustomDataPeptides where FieldId={0}", fieldid);
var phosphoReader = sqlite.ExecuteReader(sqlPhospho, null);
Progress.SetMessage("Parsing peptide phosphoylation probability ...");
while (phosphoReader.Read())
{
var pepid = phosphoReader.GetInt32(0);
IIdentifiedPeptide peptide;
if (!result.TryGetValue(pepid, out peptide))
{
continue;
}
peptide.SiteProbability = ModificationUtils.FilterSiteProbability(peptide.Sequence, phosphoReader.GetString(1));
}
return(result);
}
