public static IIdentifiedResult DoBuildGroupByPeptide(List <IIdentifiedSpectrum> spectra, Func <IIdentifiedPeptide, string> func)
{
IdentifiedResult result = new IdentifiedResult();
var singlePeptides = (from s in spectra
where s.Peptides.Count == 1
select s).GroupBy(m => func(m.Peptide));
var multiplePeptides = (from s in spectra
where s.Peptides.Count > 1
select s).ToList();
Dictionary <string, List <IIdentifiedPeptide> > dic = new Dictionary <string, List <IIdentifiedPeptide> >();
foreach (var g in singlePeptides)
{
dic[g.Key] = new List <IIdentifiedPeptide>(from s in g
select s.Peptide);
}
foreach (var o in multiplePeptides)
{
var pc = (from p in o.Peptides
let c = dic.ContainsKey(func(p)) ? dic[func(p)].Count : 0
orderby c descending
select p).First();
if (!dic.ContainsKey(func(pc)))
{
dic[func(pc)] = new List <IIdentifiedPeptide>();
}
dic[func(pc)].Add(pc);
}
var keys = new List <string>(dic.Keys);
keys.Sort();
foreach (var key in keys)
{
IdentifiedProtein protein = new IdentifiedProtein(key);
protein.Peptides.AddRange(dic[key]);
protein.UniquePeptideCount = 1;
protein.Description = dic[key][0].Proteins.Merge('/');
IdentifiedProteinGroup group = new IdentifiedProteinGroup();
group.Add(protein);
result.Add(group);
}
result.BuildGroupIndex();
//result.Sort();
return(result);
}
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 TestFilter()
{
var pro1 = new IdentifiedProtein("P1");
pro1.Peptides.Add(new IdentifiedPeptide(new IdentifiedSpectrum()
{
Charge = 1
}));
pro1.Peptides.Add(new IdentifiedPeptide(new IdentifiedSpectrum()
{
Charge = 2
}));
var pro2 = new IdentifiedProtein("P2");
pro2.Peptides.Add(new IdentifiedPeptide(new IdentifiedSpectrum()
{
Charge = 3
}));
var g1 = new IdentifiedProteinGroup();
g1.Add(pro1);
var g2 = new IdentifiedProteinGroup();
g2.Add(pro2);
IdentifiedResult ir = new IdentifiedResult();
ir.Add(g1);
ir.Add(g2);
Assert.AreEqual(2, ir.Count);
Assert.AreEqual(3, ir.GetSpectra().Count);
ir.Filter(m => { return(m.Spectrum.Query.Charge > 1); });
Assert.AreEqual(2, ir.Count);
Assert.AreEqual(2, ir.GetSpectra().Count);
ir.GetSpectra().All(m => { return(m.Charge > 1); });
ir.Filter(m => { return(m.Spectrum.Query.Charge > 2); });
Assert.AreEqual(1, ir.Count);
Assert.AreEqual(1, ir.GetSpectra().Count);
ir.GetSpectra().All(m => { return(m.Charge > 2); });
Assert.AreEqual("P2", ir[0][0].Name);
}
public IIdentifiedResult Build(List <IIdentifiedProteinGroup> groups)
{
IdentifiedResult result = new IdentifiedResult();
result.AddRange(groups);
result.Sort();
result.BuildGroupIndex();
if (FillSequence(result))
{
AveragePeptideMassCalculator massCalc = new AveragePeptideMassCalculator(new Aminoacids(), Atom.H.AverageMass, Atom.H.AverageMass + Atom.O.AverageMass);
Progress.SetMessage("Calculating coverage and mass weight ...");
foreach (IIdentifiedProteinGroup group in result)
{
foreach (IIdentifiedProtein protein in group)
{
if (!string.IsNullOrEmpty(protein.Sequence))
{
try
{
protein.CalculateCoverage();
protein.MolecularWeight = massCalc.GetMass(protein.Sequence);
}
catch (Exception ex)
{
var error = "Calculating coverage and mass weight error:" + ex.Message;
Progress.SetMessage(error);
Console.Error.WriteLine(error);
}
}
}
}
}
return(result);
}
