private void CalculateBasicFDR(IList <InputFile> csvFiles, bool isBatched = false)
{
string msg = "Calculating first order FDR threshold";
if (isBatched)
{
msg += " in batch...";
Log(msg);
// Calculate global threshold
double threshold = FalseDiscoveryRate <Peptide, double> .CalculateThreshold(_allPeptides, _maximumFalseDiscoveryRate);
foreach (InputFile csvFile in csvFiles)
{
csvFile.ScoreThreshold = threshold;
}
}
else
{
msg += " separately...";
Log(msg);
// Calculate each file separately
foreach (InputFile csvFile in csvFiles)
{
csvFile.ScoreThreshold = FalseDiscoveryRate <Peptide, double> .CalculateThreshold(csvFile.Peptides, _maximumFalseDiscoveryRate);
}
}
foreach (InputFile csvFile in csvFiles)
{
double threshold = csvFile.ScoreThreshold;
List <Peptide> passingPeptides = csvFile.Peptides.Where(peptide => peptide.FdrScoreMetric <= threshold).ToList();
csvFile.FdrFilteredPeptides = passingPeptides;
List <PSM> passingPsms = csvFile.PeptideSpectralMatches.Where(psm => psm.FdrScoreMetric <= threshold).ToList();
csvFile.FdrFilteredPSMs = passingPsms;
int total = csvFile.FdrFilteredPeptides.Count;
int decoys = csvFile.FdrFilteredPeptides.Count(peptide => peptide.IsDecoy);
int targets = total - decoys;
Log(
string.Format(
"{0:N0} peptides ({1:N0} decoys FDR = {2:F4}) pass the e-value threshold of {3:G4} for {4}",
targets, decoys, 100.0 * decoys / (double)targets, csvFile.ScoreThreshold, csvFile.Name));
}
}
private Tuple <double, double> CalculateBestPPMError(IEnumerable <Peptide> inputPeptides, double maximumFalseDisoveryRate = 0.01, int steps = 10, double minimumIncrement = 0.05)
{
List <Peptide> peptides = inputPeptides.OrderBy(pep => pep.CorrectedPrecursorErrorPPM).ToList();
double[] precursorPPMs = peptides.Select(pep => pep.CorrectedPrecursorErrorPPM).ToArray();
double bestppmError = 0;
double max = peptides[peptides.Count - 1].CorrectedPrecursorErrorPPM;
double maxPrecursorError = Math.Min(max, _maximumPPMError);
double minPrecursorError = 0;
double increment = (maxPrecursorError - minPrecursorError) / steps;
increment = Math.Max(increment, minimumIncrement);
double bestCount = 0;
for (double ppmError = minPrecursorError; ppmError <= maxPrecursorError; ppmError += increment)
{
int index = Array.BinarySearch(precursorPPMs, ppmError);
if (index < 0)
{
index = ~index;
}
int count = FalseDiscoveryRate <Peptide, double> .Count(peptides.Take(index).ToList(), maximumFalseDisoveryRate);
if (count <= bestCount)
{
continue;
}
bestCount = count;
bestppmError = ppmError;
}
List <Peptide> filteredPeptides = new List <Peptide>(peptides.Where(pep => pep.CorrectedPrecursorErrorPPM <= bestppmError));
// Calculate the e-value threshold for those filtered peptides
double threshold = FalseDiscoveryRate <Peptide, double> .CalculateThreshold(filteredPeptides, maximumFalseDisoveryRate);
return(new Tuple <double, double>(bestppmError, threshold));
}