public static OccurrenceArray[] CreateFromFile(string fileName, DnaBwt bwt)
{
using (var file = File.OpenRead(fileName))
{
BinaryReader reader = new BinaryReader(file);
int[][] compressedOccs = new int[4][]
{
new int[bwt.Length/CompressFactor+1],
new int[bwt.Length/CompressFactor+1],
new int[bwt.Length/CompressFactor+1],
new int[bwt.Length/CompressFactor+1]
};
for (int i = 0; i < compressedOccs[0].Length; i++)
{
for (int dnaBase = 0; dnaBase < 4; dnaBase++)
{
var value = reader.ReadInt32();
compressedOccs[dnaBase][i] = value;
}
}
OccurrenceArray[] occs = new[]
{
new OccurrenceArray(bwt, 0, compressedOccs[0]),
new OccurrenceArray(bwt, 1, compressedOccs[1]),
new OccurrenceArray(bwt, 2, compressedOccs[2]),
new OccurrenceArray(bwt, 3, compressedOccs[3])
};
return occs;
}
}
protected OccurrenceArray(DnaBwt bwt, int dnaBase, int[] compressedOccurrences)
{
_compressedOcc = compressedOccurrences;
_bwt = bwt;
_length = _bwt.Length;
_dnaBase = dnaBase;
}
public CompressedSuffixArray(uint[] compressedSuffixArray, DnaBwt bwt, OccurrenceArray[] occ, uint[] c)
{
_baseArray = compressedSuffixArray;
_bwt = bwt;
_occ = occ;
_c = c;
Length = bwt.Length;
}
public static CompressedSuffixArray CreateFromFile(string fileName, DnaBwt bwt, OccurrenceArray[] occ, uint[] c)
{
var buffer = File.ReadAllBytes(fileName);
uint[] compressedSufArray = new uint[buffer.Length/4];
for (int i = 0; i < compressedSufArray.Length; i++)
{
compressedSufArray[i] = BitConverter.ToUInt32(buffer, i*4);
}
CompressedSuffixArray csa = new CompressedSuffixArray(compressedSufArray, bwt, occ, c);
return csa;
}
public static DnaBwt ReadFromFile(string fileName)
{
using (var file = File.OpenRead(fileName))
{
var reader = new BinaryReader(file);
var length = reader.ReadUInt32();
var sentinelIndex = reader.ReadUInt32();
byte[] bwt = reader.ReadBytes((int) (length/4 + (length%4 != 0 ? 1 : 0)));
DnaBwt dnaBwt = new DnaBwt(bwt, length, sentinelIndex);
return dnaBwt;
}
}
public static OccurrenceArray[] CreateOccurrenceArrays(DnaBwt bwt)
{
OccurrenceArray[] occArrays = new OccurrenceArray[4]
{
new OccurrenceArray(bwt, 0, new int[bwt.Length/CompressFactor+1]),
new OccurrenceArray(bwt, 1, new int[bwt.Length/CompressFactor+1]),
new OccurrenceArray(bwt, 2, new int[bwt.Length/CompressFactor+1]),
new OccurrenceArray(bwt, 3, new int[bwt.Length/CompressFactor+1])
};
int[] sums = new int[4];
for (long i = 0; i < bwt.Length; i++)
{
if (bwt[i] >= 0)
sums[bwt[i]]++;
if (i%CompressFactor == 0)
{
occArrays[0][i] = sums[0];
occArrays[1][i] = sums[1];
occArrays[2][i] = sums[2];
occArrays[3][i] = sums[3];
}
}
return occArrays;
}
public static void SavePrecomputedDataToFiles(string baseFileName, DnaSequence referenceGenome)
{
Level0String level0String = new Level0String(referenceGenome);
LongSuffixArray suffixArray = LongSuffixArray.CreateSuffixArray(level0String);
suffixArray.WriteToFile(baseFileName + ".csa", 32);
DnaBwt bwt = new DnaBwt(level0String, suffixArray);
bwt.WriteToFile(baseFileName + ".bwt");
WriteCToFile(baseFileName + ".c", bwt);
OccurrenceArray[] occs = OccurrenceArray.CreateOccurrenceArrays(bwt);
OccurrenceArray.WriteToFile(baseFileName + ".occ", occs);
}
public static void WriteCToFile(string fileName, DnaBwt bwt)
{
using (var file = File.Open(fileName, FileMode.Create))
{
uint[] c = new uint[4];
for (long i = 0; i < bwt.Length; i++)
{
if (bwt[i] < 0)
continue;
c[bwt[i]]++;
}
c[3] = c[0] + c[1] + c[2];
c[2] = c[0] + c[1];
c[1] = c[0];
c[0] = 0;
var writer = new BinaryWriter(file);
for (int i = 0; i < 4; i++)
{
writer.Write(c[i]);
}
}
}