private static void GetBestLR2BinCount(string tumorBinnedPath, IEnumerable<string> normalBinnedPaths, string bestBinnedPath,
NexteraManifest manifest = null)
{
int bestNormalSampleIndex = 0;
int normalSampleCount = normalBinnedPaths.Count();
if (normalSampleCount > 1) // find the best normal
{
List<double[]> binCountsByNormalSample = new List<double[]>();
for (int normalSampleIndex = 0; normalSampleIndex < normalSampleCount; normalSampleIndex++)
{
string normalBinnedPath = normalBinnedPaths.ElementAt(normalSampleIndex);
var binCounts = new BinCounts(normalBinnedPath, manifest: manifest);
List<double> counts = binCounts.OnTargetCounts;
double median = binCounts.OnTargetMedianBinCount;
// If a manifest is available, get the median of bins overlapping the targeted regions only.
// For small panels, there could be a lot of bins with zero count and the median would be 0 if taken over all the bins, resulting in division by zero.
double weight = median > 0 ? 1.0 / median : 0;
binCountsByNormalSample.Add(counts.Select(cnt => cnt * weight).ToArray());
}
double[] tumorBinCounts;
{
var binCounts = new BinCounts(tumorBinnedPath, manifest: manifest);
List<double> counts = binCounts.OnTargetCounts;
double tumorMedian = binCounts.OnTargetMedianBinCount;
double tumorWeight = tumorMedian > 0 ? 1.0 / tumorMedian : 0;
tumorBinCounts = counts.Select(cnt => cnt * tumorWeight).ToArray();
}
// Find the best normal sample
bestNormalSampleIndex = -1;
double minMeanSquaredLogRatios = double.PositiveInfinity;
for (int normalSampleIndex = 0; normalSampleIndex < normalSampleCount; normalSampleIndex++)
{
// Get the sum of squared log ratios
var result = GetMeanSquaredLogRatios(tumorBinCounts, binCountsByNormalSample[normalSampleIndex]);
double meanSquaredLogRatios = result.Item1;
int ignoredBinCount = result.Item2;
// TODO: Skip a (bad) normal sample if too many bins were ignored.
// Donavan's script skips a normal sample if more than 100 log ratios is NA.
// The cut-off is likely panel-dependent.
if (meanSquaredLogRatios < minMeanSquaredLogRatios)
{
minMeanSquaredLogRatios = meanSquaredLogRatios;
bestNormalSampleIndex = normalSampleIndex;
}
}
}
// copy file
string srcBinnedPath = normalBinnedPaths.ElementAt(bestNormalSampleIndex);
if (File.Exists(srcBinnedPath))
{
if (File.Exists(bestBinnedPath)) { File.Delete(bestBinnedPath); }
File.Copy(srcBinnedPath, bestBinnedPath);
}
}
