public void Normalize()
{
// Find the best bandwidth without chrY
double[] gcsNoChrY = withoutChrY.Select(i => gcs[i]).ToArray();
double[] countsNoChrY = withoutChrY.Select(i => counts[i]).ToArray();
double bestBandwidth = findBestBandwith(0.3, 0.75, gcsNoChrY, countsNoChrY);
// Fit LOESS
double medianY = Utilities.Median(counts);
int minGC = (int)gcs.Min();
int maxGC = (int)gcs.Max();
LoessInterpolator loess = new LoessInterpolator(bestBandwidth, 0);
var model = loess.Train(gcs, counts, 1, computeFitted: false);
double[] fittedByGC = model.Predict(Enumerable.Range(minGC, maxGC).Select(i => (double)i));
// Smooth
foreach (GenomicBin bin in bins)
{
int i = Math.Min(fittedByGC.Length - 1, Math.Max(0, bin.GC - minGC));
double smoothed = countTransformer(bin.Count) - fittedByGC[i] + medianY;
bin.Count = invCountTransformer(smoothed);
}
}
/// <summary>
/// Perform GC normalization depending on the mode
/// </summary>
/// <param name="bins">Bins whose counts are to be normalized</param>
/// <param name="manifest"></param>
/// <param name="mode">GC normalization mode</param>
static void NormalizeByGC(List <SampleGenomicBin> bins, NexteraManifest manifest, CanvasGCNormalizationMode mode)
{
switch (mode)
{
case CanvasGCNormalizationMode.MedianByGC:
NormalizeByGC(bins, manifest: manifest);
break;
case CanvasGCNormalizationMode.LOESS:
var normalizer = new LoessGCNormalizer(bins, manifest, robustnessIter: 0,
countTransformer: x => (double)Math.Log(x),
invCountTransformer: x => (float)Math.Exp(x));
normalizer.Normalize();
break;
default:
throw new Illumina.Common.IlluminaException("Unsupported Canvas GC normalization mode: " + mode.ToString());
}
}