public void WriteCanvasPartitionResults(string outPath, GenomeSegmentationResults segmentationResults)
{
Dictionary <string, bool> starts = new Dictionary <string, bool>();
Dictionary <string, bool> stops = new Dictionary <string, bool>();
foreach (string chr in segmentationResults.SegmentByChr.Keys)
{
for (int segmentIndex = 0; segmentIndex < segmentationResults.SegmentByChr[chr].Length; segmentIndex++)
{
Segmentation.Segment segment = segmentationResults.SegmentByChr[chr][segmentIndex];
starts[chr + ":" + segment.start] = true;
stops[chr + ":" + segment.end] = true;
}
}
Dictionary <string, List <SampleGenomicBin> > excludedIntervals = new Dictionary <string, List <SampleGenomicBin> >();
if (!string.IsNullOrEmpty(ForbiddenIntervalBedPath))
{
excludedIntervals = CanvasCommon.Utilities.LoadBedFile(ForbiddenIntervalBedPath);
}
using (GzipWriter writer = new GzipWriter(outPath))
{
int segmentNum = -1;
foreach (string chr in StartByChr.Keys)
{
List <SampleGenomicBin> excludeIntervals = null;
if (excludedIntervals.ContainsKey(chr))
{
excludeIntervals = excludedIntervals[chr];
}
int excludeIndex = 0; // Points to the first interval which *doesn't* end before our current position
uint previousBinEnd = 0;
for (int pos = 0; pos < StartByChr[chr].Length; pos++)
{
uint start = StartByChr[chr][pos];
uint end = EndByChr[chr][pos];
string key = chr + ":" + start;
bool newSegment = IsNewSegment(starts, key, excludeIntervals, previousBinEnd, end, start, ref excludeIndex);
if (newSegment)
{
segmentNum++;
}
writer.WriteLine(string.Format($"{chr}\t{start}\t{end}\t{ScoreByChr[chr][pos]}\t{segmentNum}"));
previousBinEnd = end;
}
}
}
}
public static Segmentation.Segment[] DeriveSegments(List <int> breakpoints, int sizeScoreByChr, uint[] startByChr, uint[] endByChr)
{
List <int> startBreakpointsPos = new List <int>();
List <int> endBreakpointPos = new List <int>();
List <int> lengthSeg = new List <int>();
if (breakpoints.Count() >= 2 && sizeScoreByChr > 10)
{
startBreakpointsPos.Add(breakpoints[0]);
endBreakpointPos.Add(breakpoints[1] - 1);
lengthSeg.Add(breakpoints[1] - 1);
for (int i = 1; i < breakpoints.Count - 1; i++)
{
startBreakpointsPos.Add(breakpoints[i] - 1);
endBreakpointPos.Add(breakpoints[i + 1]);
lengthSeg.Add(breakpoints[i + 1] - 1 - breakpoints[i]);
}
startBreakpointsPos.Add(breakpoints[breakpoints.Count - 1]);
endBreakpointPos.Add(sizeScoreByChr - 1);
lengthSeg.Add(sizeScoreByChr - breakpoints[breakpoints.Count - 1] - 1);
}
else
{
startBreakpointsPos.Add(0);
endBreakpointPos.Add(sizeScoreByChr - 1);
lengthSeg.Add(sizeScoreByChr - 1);
}
Segmentation.Segment[] segments = new Segmentation.Segment[startBreakpointsPos.Count];
for (int i = 0; i < startBreakpointsPos.Count; i++)
{
int start = startBreakpointsPos[i];
int end = endBreakpointPos[i];
segments[i] = new Segmentation.Segment
{
start = startByChr[start],
end = endByChr[end]
};
// Genomic start
// Genomic end
}
return(segments);
}
/// <summary>
/// CBS: circular binary segmentation porting the R function segment in DNAcopy
/// </summary>
/// <param name="alpha">Now in this.Alpha</param>
/// <param name="nPerm"></param>
/// <param name="pMethod">"hybrid" or "perm"</param>
/// <param name="minWidth"></param>
/// <param name="kMax"></param>
/// <param name="nMin"></param>
/// <param name="eta"></param>
/// <param name="sbdry"></param>
/// <param name="trim"></param>
/// <param name="undoSplit">"none" or "prune" or "sdundo"; now in this.UndoMethod</param>
/// <param name="undoPrune"></param>
/// <param name="undoSD"></param>
/// <param name="verbose"></param>
public Dictionary <string, Segmentation.Segment[]> Run(Segmentation segmentation, uint nPerm = 10000, string pMethod = "hybrid", int minWidth = 2, int kMax = 25,
uint nMin = 200, double eta = 0.05, uint[] sbdry = null, double trim = 0.025,
double undoPrune = 0.05, double undoSD = 3, int verbose = 1)
{
if (minWidth < 2 || minWidth > 5)
{
Console.Error.WriteLine("Minimum segment width should be between 2 and 5");
Environment.Exit(1);
}
if (nMin < 4 * kMax)
{
Console.Error.WriteLine("nMin should be >= 4 * kMax");
Environment.Exit(1);
}
if (sbdry == null)
{
GetBoundary.ComputeBoundary(nPerm, this._alpha, eta, out sbdry);
}
Dictionary <string, int[]> inaByChr = new Dictionary <string, int[]>();
Dictionary <string, double[]> finiteScoresByChr = new Dictionary <string, double[]>();
List <ThreadStart> tasks = new List <ThreadStart>();
foreach (KeyValuePair <string, double[]> scoreByChrKVP in segmentation.ScoreByChr)
{
tasks.Add(new ThreadStart(() =>
{
string chr = scoreByChrKVP.Key;
int[] ina;
Helper.GetFiniteIndices(scoreByChrKVP.Value, out ina); // not NaN, -Inf, Inf
double[] scores;
if (ina.Length == scoreByChrKVP.Value.Length)
{
scores = scoreByChrKVP.Value;
}
else
{
Helper.ExtractValues <double>(scoreByChrKVP.Value, ina, out scores);
}
lock (finiteScoresByChr)
{
finiteScoresByChr[chr] = scores;
inaByChr[chr] = ina;
}
}));
}
Parallel.ForEach(tasks, task => task.Invoke());
// Quick sanity-check: If we don't have any segments, then return a dummy result.
int n = 0;
foreach (var list in finiteScoresByChr.Values)
{
n += list.Length;
}
if (n == 0)
{
return(new Dictionary <string, Segmentation.Segment[]>());
}
double trimmedSD = Math.Sqrt(ChangePoint.TrimmedVariance(finiteScoresByChr, trim: trim));
Dictionary <string, Segmentation.Segment[]> segmentByChr = new Dictionary <string, Segmentation.Segment[]>();
// when parallelizing we need an RNG for each chromosome to get deterministic results
Random seedGenerator = new MersenneTwister(0);
Dictionary <string, Random> perChromosomeRandom = new Dictionary <string, Random>();
foreach (string chr in segmentation.ScoreByChr.Keys)
{
perChromosomeRandom[chr] = new MersenneTwister(seedGenerator.NextFullRangeInt32(), true);
}
tasks = new List <ThreadStart>();
foreach (string chr in segmentation.ScoreByChr.Keys)
{
tasks.Add(new ThreadStart(() =>
{
int[] ina = inaByChr[chr];
int[] lengthSeg;
double[] segmentMeans;
ChangePoint.ChangePoints(segmentation.ScoreByChr[chr], sbdry, out lengthSeg, out segmentMeans, perChromosomeRandom[chr],
dataType: "logratio", alpha: this._alpha, nPerm: nPerm,
pMethod: pMethod, minWidth: minWidth, kMax: kMax, nMin: nMin, trimmedSD: trimmedSD,
undoSplits: this._undoMethod, undoPrune: undoPrune, undoSD: undoSD, verbose: verbose);
Segmentation.Segment[] segments = new Segmentation.Segment[lengthSeg.Length];
int cs1 = 0, cs2 = -1; // cumulative sum
for (int i = 0; i < lengthSeg.Length; i++)
{
cs2 += lengthSeg[i];
int start = ina[cs1];
int end = ina[cs2];
segments[i] = new Segmentation.Segment();
segments[i].start = segmentation.StartByChr[chr][start]; // Genomic start
segments[i].end = segmentation.EndByChr[chr][end]; // Genomic end
cs1 += lengthSeg[i];
}
lock (segmentByChr)
{
segmentByChr[chr] = segments;
}
}));
}
Parallel.ForEach(tasks, task => task.Invoke());
// segmentation.SegmentationResults = new Segmentation.GenomeSegmentationResults(segmentByChr);
Console.WriteLine("{0} Completed CBS tasks", DateTime.Now);
Console.WriteLine("{0} Segmentation results complete", DateTime.Now);
return(segmentByChr);
}
