public void TestBuildNonredundantProteinGroup()
{
List <IIdentifiedProtein> proteins = InitProteins();
List <IIdentifiedProteinGroup> mpgs = MascotUtils.BuildNonredundantProteinGroups(proteins);
Assert.AreEqual(1, mpgs.Count);
Assert.AreEqual("Protein1", mpgs[0][0].Name);
}
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 TestParseTitle()
{
SequestFilename sf = MascotUtils.ParseTitle(" Cmpd. 6612. 6612. 1. dta", 1);
Assert.AreEqual("Cmpd.6612.6612.1.dta", sf.LongFileName);
sf = MascotUtils.ParseTitle(" FIT_PPN_SAX_Online_1mg_060909_01, Cmpd 7736, +MSn(600.4082), 51.88 min", 1);
Assert.AreEqual("FIT_PPN_SAX_Online_1mg_060909_01.7736.7736.1.dta", sf.LongFileName);
sf =
MascotUtils.ParseTitle(
"spectrumId=6085 Polarity=Positive ScanMode=ProductIon TimeInMinutes=61.875 acqNumber=3712494", 1);
Assert.AreEqual(".6085.6085.1.dta", sf.LongFileName);
sf =
MascotUtils.ParseTitle(
"Elution from: 40.798 to 40.798 period: 0 experiment: 1 cycles: 1 precIntensity: 355220.0 FinneganScanNumber: 6070 MStype: enumIsNormalMS rawFile: KR_mix_lc_090115.raw",
1);
Assert.AreEqual("KR_mix_lc_090115.6070.6070.1.dta", sf.LongFileName);
}
public void TestParseTitleException()
{
MascotUtils.ParseTitle("dfajdskfjalsdjfa", 1);
}
protected IdentifiedProtein ParseProtein(String proteinContent)
{
IdentifiedProtein result = GetProtein(proteinContent);
List <String> peptideInfoContentList = GetPeptideInfoContentList(proteinContent);
foreach (String peptideInfoContent in peptideInfoContentList)
{
List <String> peptideInfo = GetPeptideInfo(peptideInfoContent);
if (0 == peptideInfo.Count)
{
continue;
}
IIdentifiedSpectrum mphit = new IdentifiedSpectrum();
// Group 0 : peptide mass from observed m/z
double experimentalPeptideMass = MyConvert.ToDouble(peptideInfo[0]);
mphit.ExperimentalMass = experimentalPeptideMass;
// Group 1 : observed m/z
double observed = MyConvert.ToDouble(peptideInfo[1]);
mphit.Query.ObservedMz = observed;
// Group 2 : charge
int charge = int.Parse(peptideInfo[2]);
mphit.Query.Charge = charge;
// Group 3 : title
String title = Uri.UnescapeDataString(peptideInfo[3]).Trim();
mphit.Query.Title = title;
SequestFilename sf = MascotUtils.ParseTitle(title, charge);
if (sf != null)
{
mphit.Query.FileScan.LongFileName = sf.LongFileName;
}
// Group 4 : query
mphit.Query.QueryId = int.Parse(peptideInfo[4]);
// Group 5 equals Group 1
// Group 6 equals Group 0
// Group 7 : calculated peptide mass
mphit.TheoreticalMass = MyConvert.ToDouble(peptideInfo[7]);
// Group 8 : different between observed peptide mass and calculated
// peptide mass
// Group 9 : miss cleavage
mphit.NumMissedCleavages = int.Parse(peptideInfo[9]);
// Group 10: score
mphit.Score = int.Parse(peptideInfo[10]);
// Group 11: expect p value
mphit.ExpectValue = MyConvert.ToDouble(peptideInfo[11]);
// Group 12: rank
mphit.Rank = int.Parse(peptideInfo[12]);
// Group 13: peptide sequence
// K.YEINVLR<u>.</u>N + Label:18O(2) (C-term)
String seq = peptideInfo[13].Replace(" ", "");
var mpep = new IdentifiedPeptide(mphit);
string[] parts = Regex.Split(seq, "\\+");
if (parts.Length > 1)
{
seq = parts[0].Trim();
mphit.Modifications = parts[1].Trim();
string[] mods = parts[1].Trim().Split(new[] { ';' }, StringSplitOptions.RemoveEmptyEntries);
foreach (string mod in mods)
{
Match m = this.modificationReg.Match(mod.Trim());
if (!this.modifications.ContainsKey(m.Groups[1].Value))
{
this.modifications[m.Groups[1].Value] = ' ';
}
}
}
mpep.Sequence = seq;
if (GetPeptideFilter().Accept(mphit))
{
mpep.AddProtein(result.Name);
result.Peptides.Add(mpep);
}
}
return(result);
}
