public void AddData(Peptide peptide, double[] quant, bool ismissingChannel = false)
{
PSMs++;
UniquePeptides.Add(peptide);
Peptides.Add(peptide);
QuantData.Add(new Tuple <Peptide, double[], bool>(peptide, quant, ismissingChannel));
}
public override string ToString()
{
var sb = new StringBuilder();
// list of protein accession numbers
sb.Append(ProteinGroupName);
sb.Append("\t");
// genes
sb.Append(GlobalVariables.CheckLengthOfOutput(string.Join("|", ListOfProteinsOrderedByAccession.Select(p => p.GeneNames.Select(x => x.Item2).FirstOrDefault()))));
sb.Append("\t");
// organisms
sb.Append(GlobalVariables.CheckLengthOfOutput(string.Join("|", ListOfProteinsOrderedByAccession.Select(p => p.Organism).Distinct())));
sb.Append("\t");
// list of protein names
sb.Append(GlobalVariables.CheckLengthOfOutput(string.Join("|", ListOfProteinsOrderedByAccession.Select(p => p.FullName).Distinct())));
sb.Append("\t");
// list of masses
var sequences = ListOfProteinsOrderedByAccession.Select(p => p.BaseSequence).Distinct();
List <double> masses = new List <double>();
foreach (var sequence in sequences)
{
try
{
masses.Add(new Proteomics.AminoAcidPolymer.Peptide(sequence).MonoisotopicMass);
}
catch (System.Exception)
{
masses.Add(double.NaN);
}
}
sb.Append(GlobalVariables.CheckLengthOfOutput(string.Join("|", masses)));
sb.Append("\t");
// number of proteins in group
sb.Append("" + Proteins.Count);
sb.Append("\t");
// list of unique peptides
if (!DisplayModsOnPeptides)
{
sb.Append(GlobalVariables.CheckLengthOfOutput(string.Join("|", UniquePeptides.Select(p => p.BaseSequence).Distinct())));
}
else
{
sb.Append(GlobalVariables.CheckLengthOfOutput(string.Join("|", UniquePeptides.Select(p => p.Sequence).Distinct())));
}
sb.Append("\t");
// list of shared peptides
var SharedPeptides = AllPeptides.Except(UniquePeptides);
if (!DisplayModsOnPeptides)
{
sb.Append(GlobalVariables.CheckLengthOfOutput(string.Join("|", SharedPeptides.Select(p => p.BaseSequence).Distinct())));
}
else
{
sb.Append(GlobalVariables.CheckLengthOfOutput(string.Join("|", SharedPeptides.Select(p => p.Sequence).Distinct())));
}
sb.Append("\t");
// number of peptides
if (!DisplayModsOnPeptides)
{
sb.Append("" + AllPeptides.Select(p => p.BaseSequence).Distinct().Count());
}
else
{
sb.Append("" + AllPeptides.Select(p => p.Sequence).Distinct().Count());
}
sb.Append("\t");
// number of unique peptides
if (!DisplayModsOnPeptides)
{
sb.Append("" + UniquePeptides.Select(p => p.BaseSequence).Distinct().Count());
}
else
{
sb.Append("" + UniquePeptides.Select(p => p.Sequence).Distinct().Count());
}
sb.Append("\t");
// sequence coverage percent
sb.Append(GlobalVariables.CheckLengthOfOutput(string.Join("|", SequenceCoveragePercent.Select(p => string.Format("{0:0}" + "%", (p * 100))))));
sb.Append("\t");
// sequence coverage
sb.Append(GlobalVariables.CheckLengthOfOutput(string.Join("|", SequenceCoverageDisplayList)));
sb.Append("\t");
// sequence coverage with mods
sb.Append(GlobalVariables.CheckLengthOfOutput(string.Join("|", SequenceCoverageDisplayListWithMods)));
sb.Append("\t");
//Detailed mods information list
sb.Append(GlobalVariables.CheckLengthOfOutput(string.Join("|", ModsInfo)));
sb.Append("\t");
// MS1 intensity (retrieved from FlashLFQ in the SearchTask)
if (IntensitiesByFile != null && FilesForQuantification != null)
{
foreach (var file in FilesForQuantification)
{
if (IntensitiesByFile[file] > 0)
{
sb.Append(IntensitiesByFile[file]);
}
else
{
sb.Append("");
}
sb.Append("\t");
}
}
// number of PSMs for listed peptides
sb.Append("" + AllPsmsBelowOnePercentFDR.Count);
sb.Append("\t");
// isDecoy
if (IsDecoy)
{
sb.Append("D");
}
else if (IsContaminant)
{
sb.Append("C");
}
else
{
sb.Append("T");
}
sb.Append("\t");
// cumulative target
sb.Append(CumulativeTarget);
sb.Append("\t");
// cumulative decoy
sb.Append(CumulativeDecoy);
sb.Append("\t");
// q value
sb.Append(QValue);
sb.Append("\t");
// best peptide score
sb.Append(BestPeptideScore);
sb.Append("\t");
// best peptide q value
sb.Append(BestPeptideQValue);
sb.Append("\t");
return(sb.ToString());
}
public ProteinGroup ConstructSubsetProteinGroup(string fullFilePath)
{
var allPsmsForThisFile = new HashSet <PeptideSpectralMatch>(AllPsmsBelowOnePercentFDR.Where(p => p.FullFilePath.Equals(fullFilePath)));
var allPeptidesForThisFile = new HashSet <PeptideWithSetModifications>(allPsmsForThisFile.SelectMany(p => p.BestMatchingPeptides.Select(v => v.Peptide)));
var allUniquePeptidesForThisFile = new HashSet <PeptideWithSetModifications>(UniquePeptides.Intersect(allPeptidesForThisFile));
ProteinGroup subsetPg = new ProteinGroup(Proteins, allPeptidesForThisFile, allUniquePeptidesForThisFile)
{
AllPsmsBelowOnePercentFDR = allPsmsForThisFile,
DisplayModsOnPeptides = DisplayModsOnPeptides
};
SpectraFileInfo spectraFileInfo = null;
if (FilesForQuantification != null)
{
spectraFileInfo = FilesForQuantification.Where(p => p.FullFilePathWithExtension == fullFilePath).First();
subsetPg.FilesForQuantification = new List <SpectraFileInfo> {
spectraFileInfo
};
}
if (IntensitiesByFile == null)
{
subsetPg.IntensitiesByFile = null;
}
else
{
subsetPg.IntensitiesByFile = new Dictionary <SpectraFileInfo, double> {
{ spectraFileInfo, IntensitiesByFile[spectraFileInfo] }
};
}
return(subsetPg);
}
public override string ToString()
{
var sb = new StringBuilder();
// list of protein accession numbers
sb.Append(ProteinGroupName);
sb.Append("\t");
// genes
sb.Append(GlobalVariables.CheckLengthOfOutput(string.Join("|", ListOfProteinsOrderedByAccession.Select(p => p.GeneNames.Select(x => x.Item2).FirstOrDefault()))));
sb.Append("\t");
// organisms
sb.Append(GlobalVariables.CheckLengthOfOutput(string.Join("|", ListOfProteinsOrderedByAccession.Select(p => p.Organism).Distinct())));
sb.Append("\t");
// list of protein names
sb.Append(GlobalVariables.CheckLengthOfOutput(string.Join("|", ListOfProteinsOrderedByAccession.Select(p => p.FullName).Distinct())));
sb.Append("\t");
// list of masses
var sequences = ListOfProteinsOrderedByAccession.Select(p => p.BaseSequence).Distinct();
List <double> masses = new List <double>();
foreach (var sequence in sequences)
{
try
{
masses.Add(new Proteomics.AminoAcidPolymer.Peptide(sequence).MonoisotopicMass);
}
catch (System.Exception)
{
masses.Add(double.NaN);
}
}
sb.Append(GlobalVariables.CheckLengthOfOutput(string.Join("|", masses)));
sb.Append("\t");
// number of proteins in group
sb.Append("" + Proteins.Count);
sb.Append("\t");
// list of unique peptides
if (UniquePeptidesOutput != null)
{
sb.Append(GlobalVariables.CheckLengthOfOutput(UniquePeptidesOutput));
}
sb.Append("\t");
// list of shared peptides
if (SharedPeptidesOutput != null)
{
sb.Append(GlobalVariables.CheckLengthOfOutput(SharedPeptidesOutput));
}
sb.Append("\t");
// number of peptides
if (!DisplayModsOnPeptides)
{
sb.Append("" + AllPeptides.Select(p => p.BaseSequence).Distinct().Count());
}
else
{
sb.Append("" + AllPeptides.Select(p => p.FullSequence).Distinct().Count());
}
sb.Append("\t");
// number of unique peptides
if (!DisplayModsOnPeptides)
{
sb.Append("" + UniquePeptides.Select(p => p.BaseSequence).Distinct().Count());
}
else
{
sb.Append("" + UniquePeptides.Select(p => p.FullSequence).Distinct().Count());
}
sb.Append("\t");
// sequence coverage percent
sb.Append(GlobalVariables.CheckLengthOfOutput(string.Join("|", SequenceCoverageFraction.Select(p => string.Format("{0:0.#####}", p)))));
sb.Append("\t");
// sequence coverage
sb.Append(GlobalVariables.CheckLengthOfOutput(string.Join("|", SequenceCoverageDisplayList)));
sb.Append("\t");
// sequence coverage with mods
sb.Append(GlobalVariables.CheckLengthOfOutput(string.Join("|", SequenceCoverageDisplayListWithMods)));
sb.Append("\t");
//Detailed mods information list
sb.Append(GlobalVariables.CheckLengthOfOutput(string.Join("|", ModsInfo)));
sb.Append("\t");
// MS1 intensity (retrieved from FlashLFQ in the SearchTask)
if (IntensitiesByFile != null && FilesForQuantification != null)
{
foreach (var sampleGroup in FilesForQuantification.GroupBy(p => p.Condition))
{
foreach (var sample in sampleGroup.GroupBy(p => p.BiologicalReplicate).OrderBy(p => p.Key))
{
// if the samples are fractionated, the protein will only have 1 intensity in the first fraction
// and the other fractions will be zero. we could find the first/only fraction with an intensity,
// but simply summing the fractions is easier than finding the single non-zero value
double summedIntensity = sample.Sum(file => IntensitiesByFile[file]);
if (summedIntensity > 0)
{
sb.Append(summedIntensity);
}
sb.Append("\t");
}
}
}
// number of PSMs for listed peptides
sb.Append("" + AllPsmsBelowOnePercentFDR.Count);
sb.Append("\t");
// isDecoy
if (IsDecoy)
{
sb.Append("D");
}
else if (IsContaminant)
{
sb.Append("C");
}
else
{
sb.Append("T");
}
sb.Append("\t");
// cumulative target
sb.Append(CumulativeTarget);
sb.Append("\t");
// cumulative decoy
sb.Append(CumulativeDecoy);
sb.Append("\t");
// q value
sb.Append(QValue);
sb.Append("\t");
// best peptide score
sb.Append(BestPeptideScore);
sb.Append("\t");
// best peptide q value
sb.Append(BestPeptideQValue);
sb.Append("\t");
return(sb.ToString());
}
//Get unique and identified peptides for output
//Convert the output if it's a SILAC experiment
public void GetIdentifiedPeptidesOutput(List <SilacLabel> labels)
{
var SharedPeptides = AllPeptides.Except(UniquePeptides);
if (labels == null)
{
//TODO add unit test with displaymodsonpeptides
if (!DisplayModsOnPeptides)
{
UniquePeptidesOutput = GlobalVariables.CheckLengthOfOutput(string.Join("|", UniquePeptides.Select(p => p.BaseSequence).Distinct()));
SharedPeptidesOutput = GlobalVariables.CheckLengthOfOutput(string.Join("|", SharedPeptides.Select(p => p.BaseSequence).Distinct()));
}
else
{
UniquePeptidesOutput = GlobalVariables.CheckLengthOfOutput(string.Join("|", UniquePeptides.Select(p => p.FullSequence).Distinct()));
SharedPeptidesOutput = GlobalVariables.CheckLengthOfOutput(string.Join("|", SharedPeptides.Select(p => p.FullSequence).Distinct()));
}
}
else
{
if (!DisplayModsOnPeptides)
{
UniquePeptidesOutput = GlobalVariables.CheckLengthOfOutput(string.Join("|", UniquePeptides.Select(p => SilacConversions.GetAmbiguousLightSequence(p.BaseSequence, labels, true)).Distinct()));
SharedPeptidesOutput = GlobalVariables.CheckLengthOfOutput(string.Join("|", SharedPeptides.Select(p => SilacConversions.GetAmbiguousLightSequence(p.BaseSequence, labels, true)).Distinct()));
}
else
{
UniquePeptidesOutput = GlobalVariables.CheckLengthOfOutput(string.Join("|", UniquePeptides.Select(p => SilacConversions.GetAmbiguousLightSequence(p.FullSequence, labels, false)).Distinct()));
SharedPeptidesOutput = GlobalVariables.CheckLengthOfOutput(string.Join("|", SharedPeptides.Select(p => SilacConversions.GetAmbiguousLightSequence(p.FullSequence, labels, false)).Distinct()));
}
}
}