private void MergePeptides(MascotResult result)
{
var peptideMap = new Dictionary <String, IIdentifiedPeptide>();
foreach (IIdentifiedProteinGroup group in result)
{
foreach (IIdentifiedProtein protein in group)
{
for (int i = 0; i < protein.Peptides.Count; i++)
{
String pepid = protein.Peptides[i].Spectrum.Query.QueryId + "_" + protein.Peptides[i].Sequence;
if (peptideMap.ContainsKey(pepid))
{
IIdentifiedPeptide old = peptideMap[pepid];
old.AddProtein(protein.Name);
protein.Peptides[i] = old;
}
else
{
peptideMap[pepid] = protein.Peptides[i];
}
}
}
}
}
private void RefineModification(MascotResult result)
{
var mods = new List <string>(this.modifications.Keys);
mods.Sort();
for (int i = 0; i < mods.Count; i++)
{
this.modifications[mods[i]] = ModificationConsts.MODIFICATION_CHAR[i + 1];
}
List <IIdentifiedSpectrum> spectra = result.GetSpectra();
foreach (IIdentifiedSpectrum spectrum in spectra)
{
foreach (IIdentifiedPeptide pep in spectrum.Peptides)
{
if (null == spectrum.Modifications)
{
continue;
}
string seq = pep.Sequence;
string mod = spectrum.Modifications;
string[] modStrs = mod.Split(new[] { ';' }, StringSplitOptions.RemoveEmptyEntries);
foreach (string modStr in modStrs)
{
Match m = this.modificationReg.Match(modStr.Trim());
char modChar = this.modifications[m.Groups[1].Value];
seq = seq.Replace("<u>" + m.Groups[2].Value + "</u>", m.Groups[2].Value + modChar);
seq = seq.Replace("<U>" + m.Groups[2].Value + "</U>", m.Groups[2].Value + modChar);
}
seq = seq.Replace("<u>", "");
seq = seq.Replace("</u>", "*");
seq = seq.Replace("<U>", "");
seq = seq.Replace("</U>", "*");
seq = seq.Replace(".*", ".");
pep.Sequence = seq;
}
}
}
public IIdentifiedResult ReadFromFile(string proteinFile)
{
if (!File.Exists(proteinFile))
{
throw new FileNotFoundException("File not exist : " + proteinFile);
}
var result = new MascotResult();
var peptideMap = new Dictionary <string, IIdentifiedSpectrum>();
using (var filein = new StreamReader(proteinFile))
{
string lastLine;
while ((lastLine = filein.ReadLine()) != null)
{
if (lastLine.StartsWith("Locus"))
{
this.proteinConverter = IdentifiedProteinPropertyConverterFactory.GetInstance().GetConverters(lastLine, '\t',
"Dtaselect");
}
if (lastLine.StartsWith("Unique"))
{
this.peptideConverter = IdentifiedSpectrumPropertyConverterFactory.GetInstance().GetConverters(lastLine,
'\t',
"Dtaselect");
break;
}
}
IIdentifiedProteinGroup group;
lastLine = null;
while ((group = ReadNextProteinGroup(filein, peptideMap, ref lastLine)) != null)
{
result.Add(group);
}
}
return(result);
}
public void TestGetAnnotationKeys()
{
string key1 = "TEST1";
string key2 = "TEST2";
var mph1 = new IdentifiedSpectrum();
mph1.Annotations.Add(key1, null);
mph1.Query.FileScan.Experimental = "EXP1";
new IdentifiedPeptide(mph1);
var mph2 = new IdentifiedSpectrum();
mph2.Annotations.Add(key2, null);
mph2.Query.FileScan.Experimental = "EXP2";
new IdentifiedPeptide(mph2);
mph1.Peptide.Sequence = "SEQ1";
mph2.Peptide.Sequence = "SEQ2";
var protein = new IdentifiedProtein();
protein.Peptides.Add(mph1.Peptide);
protein.Peptides.Add(mph2.Peptide);
var mpg = new IdentifiedProteinGroup();
mpg.Add(protein);
var mr = new MascotResult();
mr.Add(mpg);
List <string> annotationKeys = AnnotationUtils.GetAnnotationKeys(mr.GetSpectra());
Assert.AreEqual(2, annotationKeys.Count);
Assert.IsTrue(annotationKeys.Contains(key1));
Assert.IsTrue(annotationKeys.Contains(key2));
}
public MascotResult ParseContent(String fileContent)
{
var result = new MascotResult();
this.modifications = new Dictionary <string, char>();
Pair <int, double> pValueScore = ParsePValueScore(fileContent);
result.PValueScore = pValueScore.First;
result.PValue = pValueScore.Second;
var offsets = new List <Offset>();
try
{
result.PeakIsotopicType = ParsePeakIsotopicType(fileContent);
}
catch (ArgumentException)
{
}
try
{
result.PeakTolerance = ParsePeakTolerance(fileContent);
}
catch (ArgumentException)
{
}
var filters = new List <IFilter <IIdentifiedSpectrum> >();
if (this.filterByDefaultScoreAndPvalue)
{
filters.Add(new IdentifiedSpectrumScoreFilter(pValueScore.First));
filters.Add(new IdentifiedSpectrumExpectValueFilter(pValueScore.Second));
}
filters.Add(new IdentifiedSpectrumRankFilter(1));
if (null != this.defaultPeptideFilter)
{
filters.Add(this.defaultPeptideFilter);
}
this.currentPeptideFilter = new AndFilter <IIdentifiedSpectrum>(filters);
Match proteinMatch = GetProteinRegex().Match(fileContent);
while (proteinMatch.Success)
{
IdentifiedProtein protein = ParseProtein(proteinMatch.Groups[1].Value);
var group = new IdentifiedProteinGroup();
group.Add(protein);
result.Add(group);
offsets.Add(new Offset(proteinMatch.Index, proteinMatch.Index + proteinMatch.Length, group));
proteinMatch = proteinMatch.NextMatch();
}
int endIndex = fileContent.IndexOf("Peptide matches not assigned to protein hits");
if (-1 == endIndex)
{
endIndex = fileContent.Length - 1;
}
for (int i = 0; i < offsets.Count; i++)
{
int start = offsets[i].End;
int end = i == offsets.Count - 1 ? endIndex : offsets[i + 1].Start;
String redundant = fileContent.Substring(start, end - start + 1);
if (!redundant.Contains("Proteins matching the same set"))
{
continue;
}
List <IdentifiedProtein> sameMatchProteins = ParseSameMatchProteins(redundant);
foreach (IdentifiedProtein mp in sameMatchProteins)
{
mp.Peptides.AddRange(offsets[i].Mpg[0].Peptides);
offsets[i].Mpg.Add(mp);
}
}
for (int i = result.Count - 1; i >= 0; i--)
{
if (0 == result[i][0].Peptides.Count)
{
result.RemoveAt(i);
}
}
RefineModification(result);
MergePeptides(result);
result.InitUniquePeptideCount();
return(result);
}
