/// <summary>
/// Write all data from the specified SnpCollection into the SnpCollection
/// file having the specified filename (which may include a path). Any
/// existing contents of the file will be overwritten.
/// </summary>
/// <param name="snps">The SnpCollection containing the data to be written.</param>
/// <param name="filename">The path and filename of the SnpCollection file.</param>
public static void Write(SnpCollection snps, string filename) {
if (snps == null) throw new ArgumentNullException("The SnpCollection cannot be null.");
if (filename == null) throw new ArgumentNullException("filename cannot be null.");
if (String.IsNullOrWhiteSpace(filename)) throw new ArgumentOutOfRangeException("filename cannot be empty.");
Write(snps, filename, new CancellationToken(false), null);
}
public void Read(SnpCollection snps, CancellationToken cancel, Progress progress) {
if (this.filename == null) throw new ArgumentNullException("filename cannot be null.");
if (String.IsNullOrWhiteSpace(filename)) throw new ArgumentOutOfRangeException("filename cannot be empty.");
string ext = Path.GetExtension(filename);
if (ext.EndsWith("csv", StringComparison.InvariantCultureIgnoreCase)) {
try {
Read(Genome.GenomeType.Ftdna, snps, cancel, progress);
return;
}
catch (Exception) { }
genome.Clear();
try {
Read(Genome.GenomeType.MeAnd23v2, snps, cancel, progress);
return;
}
catch (Exception) { }
} else {
try {
Read(Genome.GenomeType.MeAnd23v2, snps, cancel, progress);
return;
}
catch (Exception) { }
genome.Clear();
try {
Read(Genome.GenomeType.Ftdna, snps, cancel, progress);
return;
}
catch (Exception) { }
}
throw new ApplicationException("Could not read as either format.");
}
/// <summary>
/// Read data into the specified SnpCollection from the SnpCollection
/// file having the specified filename (which may include a path).
/// The specified CancellationToken can be used to abort the read.
/// The progress parameter will be updated by this method with a
/// value of 0-100 to reflect the percent progress of the read.
/// </summary>
/// <param name="snps">The SnpCollection to receive the read data.</param>
/// <param name="filename">The path and filename of the SnpCollection file.</param>
/// <param name="cancel">The CancellationToken that can be used to abort the read.</param>
/// <param name="progress">The progress parameter that will be updated to reflect
/// the percent progress of the read.</param>
public static void Read(SnpCollection snps, string filename, CancellationToken cancel, Progress progress) {
if (snps == null) throw new ArgumentNullException("The SnpCollection cannot be null.");
if (filename == null) throw new ArgumentNullException("filename cannot be null.");
if (String.IsNullOrWhiteSpace(filename)) throw new ArgumentOutOfRangeException("filename cannot be empty.");
using (StreamReader reader = new StreamReader(filename)) {
long length = 0;
if (progress != null) length = reader.BaseStream.Length;
string[] columns = new string[6];
string line;
while ((line = reader.ReadLine()) != null) {
cancel.ThrowIfCancellationRequested();
line.FastSplit(',', columns);
byte chr = Convert.ToByte(columns[2]);
if (chr == 0) chr = 23; // handles legacy use of 0 for X
Snp snp;
if ((!String.IsNullOrWhiteSpace(columns[3]) && Char.IsDigit(columns[3][0]))) {
// new format snp file
snp = new Snp(columns[0], chr, Convert.ToInt32(columns[3]), Convert.ToSingle(columns[4]), columns[1], columns[5]);
} else {
// old SnpMap format snp file
snp = new Snp(columns[0], chr, -1, -1, columns[1], columns[3]);
}
snps.Add(snp);
if (progress != null) progress.Set(reader.BaseStream.Position, length);
}
}
}
static PhasedGenomeFile SimplePhase(string filename, GenomeFile gfile, SnpCollection refSnps) {
Console.Write("Creating simple phased genome...");
PhasedGenome phased = new PhasedGenome(gfile.Genome);
Console.WriteLine("completed");
PhasedGenomeFile pfile = new PhasedGenomeFile(GetPhasedFilename(filename));
pfile.SetStandardComments();
pfile.AddComment("## history");
pfile.AddComment("## " + DateTime.Now.ToString() + " SimplePhase of " + phased.Count.ToString("#,##0")
+ " homozygous SNPs (of " + gfile.Genome.Count.ToString("#,##0") + " total).");
pfile.PhasedGenome = phased;
return pfile;
}
public void Read(Genome.GenomeType genomeType, SnpCollection snps, CancellationToken cancel, Progress progress) {
if (snps == null) throw new ArgumentNullException("The SnpCollection cannot be null.");
if (this.filename == null) throw new ArgumentNullException("filename cannot be null.");
if (String.IsNullOrWhiteSpace(filename)) throw new ArgumentOutOfRangeException("filename cannot be empty.");
this.comments.Clear();
if (this.genome == null) {
this.genome = new Genome(1, 23);
} else {
this.genome.Clear();
}
if (genomeType == Dna.Genome.GenomeType.Ftdna) {
ReadFtdnaGenome(snps, cancel, progress);
} else {
Read23AndMeGenome(snps, cancel, progress);
}
if (String.IsNullOrWhiteSpace(this.genome.Name)) this.genome.Name = Path.GetFileNameWithoutExtension(this.filename);
}
public void Read(SnpCollection snps, CancellationToken cancel, Progress progress) {
if (snps == null) throw new ArgumentNullException("The SnpCollection cannot be null.");
if (this.filename == null) throw new ArgumentNullException("filename cannot be null.");
if (String.IsNullOrWhiteSpace(filename)) throw new ArgumentOutOfRangeException("filename cannot be empty.");
if (this.genome == null) {
this.genome = new PhasedGenome(1, 23);
} else {
this.genome.Clear();
}
this.comments.Clear();
using (StreamReader reader = new StreamReader(this.filename)) {
long length = 0;
if (progress != null) length = reader.BaseStream.Length;
string line;
string[] columns = new string[4];
while ((line = reader.ReadLine()) != null) {
cancel.ThrowIfCancellationRequested();
if ((line.Length > 0) && (line[0] != '#')) {
int colCount = line.FastSplit('\t', columns);
if ((colCount != 2) && (colCount != 4)) throw new ApplicationException("Not phased genome format.");
string rsId = columns[0];
Snp snp = snps[rsId];
if (snp != null) {
var alleles = columns[colCount - 1];
var phased = new PhasedGenome.Phasing(alleles[0].ToAllele(), alleles[1].ToAllele());
this.genome.Add(snp, phased);
}
} else if ((line.Length > 0) && (genome.Count == 0) && (line != header)) {
this.comments.Add(line);
}
if (progress != null) progress.Set(reader.BaseStream.Position, length);
}
}
if (String.IsNullOrWhiteSpace(genome.Name)) this.genome.Name = Path.GetFileNameWithoutExtension(filename);
}
public static GenomeFile ReadGenome(SnpCollection refSnps, string filename) {
GenomeFile result = new GenomeFile(filename);
result.Genome = new Genome(1, 23);
Console.Write("Reading genome " + result.Name + "...");
result.Read(refSnps, new System.Threading.CancellationToken(), null);
Console.WriteLine("completed");
return result;
}
public static SnpCollection ReadRefSnps() {
SnpCollection refSnps = new SnpCollection(1, 23);
Console.Write("Reading reference SNPs...");
SnpFile.Read(refSnps, "RefSnps.csv");
Console.WriteLine("completed");
return refSnps;
}
public static void UpdateCentimorgans(string[] args) {
SnpCollection snps = new SnpCollection(1, 23);
string filename = args[1];
SnpFile.ReadRutgers(snps, filename, new System.Threading.CancellationToken(), null);
for (int i = 1; i <= 23; i++) snps.Add(new Snp("fake" + i, (byte) i, 0, 0, null, null));
SnpCollection refSnps = new SnpCollection(1, 23);
SnpFile.Read(refSnps, "RefSnps.csv");
Snp prevSnp = null;
foreach(Snp snp in refSnps) {
Snp rutgerSnp = null;
if (snps.Contains(snp.RsId)) {
rutgerSnp = snps[snp.RsId];
//if ((rutgerSnp.Chromosome != snp.Chromosome) || (Math.Abs(rutgerSnp.Position-snp.Position) > 10)) {
// Console.WriteLine("mismatched pos for " + snp.RsId + " - " + snp.Chromosome + ":" + snp.Position + " vs. " + rutgerSnp.Chromosome + ":" + rutgerSnp.Position);
// snp.cM = snps.ExtrapolateCentiMorganPosition(snp.Chromosome, snp.Position);
//} else {
// snp.cM = snps[snp.RsId].cM;
//}
snp.Chromosome = rutgerSnp.Chromosome;
snp.Position = rutgerSnp.Position;
}
if ((rutgerSnp != null) && (rutgerSnp.cM > 0)) {
snp.cM = rutgerSnp.cM;
} else {
snp.cM = snps.ExtrapolateCentiMorganPosition(snp.Chromosome, snp.Position);
}
if ((prevSnp != null) && (prevSnp.Chromosome == snp.Chromosome)
&& (prevSnp.cM > snp.cM)) {
Console.WriteLine("cM out of sequence " + prevSnp.RsId + "-" + snp.RsId);
}
prevSnp = snp;
}
SnpFile.Write(refSnps, "RefSnps2.csv");
}
// FTDNA files are are made available by the Family Tree DNA testing
// service to their customers.
/// <summary>
/// Read data into the specified Genome from an individual's
/// FTDNA personal genome file, using the specified filename (which
/// may include a path). The specified SnpCollection does not need
/// to contain all the SNPs that may be present in the genome file.
/// The SnpCollection is used as the source of physical and cM
/// positional information. Centimorgan values for SNPs present in
/// the genome but not in the SnpCollection are extrapolated.
/// The specified CancellationToken can be used to abort the read.
/// The progress parameter will be updated by this method with a
/// value of 0-100 to reflect the percent progress of the read.
/// </summary>
/// <param name="genome">The Genome to receive the read data.</param>
/// <param name="snps">The SnpCollection containing reference SNP positional data.</param>
/// <param name="filename">The path and filename of the FTDNA genome file.</param>
/// <param name="cancel">The CancellationToken that can be used to abort the read.</param>
/// <param name="progress">The progress parameter that will be updated to reflect
/// the percent progress of the read.</param>
private void ReadFtdnaGenome(SnpCollection snps, CancellationToken cancel, Progress progress) {
using (StreamReader reader = new StreamReader(this.filename)) {
long length = 0;
if (progress != null) length = reader.BaseStream.Length;
string[] columns = new string[4];
string line;
bool started = false;
while ((line = reader.ReadLine()) != null) {
cancel.ThrowIfCancellationRequested();
if ((line.Length > 0) && (line[0] != '#') && (line[0] != '-')
&& (started || !line.StartsWith("RSID,", StringComparison.Ordinal))) {
started = true;
line.Replace("\"", "").FastSplit(',', columns);
string rsId = columns[0];
Snp snp = snps[rsId];
if (snp == null) {
byte chr = Snp.ChromosomeToByte(columns[1]).Value;
if (chr > 23) continue;
int position = Convert.ToInt32(columns[2]);
snp = new Snp(rsId, chr, position, snps.ExtrapolateCentiMorganPosition(chr, position), null, "");
}
var alleles = columns[3];
if ((snp.Chromosome == 23) && (alleles.Length == 1)) alleles += alleles;
this.genome.Add(snp, Allele.ToAlleles(alleles));
} else if ((line.Length > 0) && (this.genome.Count == 0) && !line.StartsWith("# rsid\t")) {
this.comments.Add(line);
}
if (progress != null) progress.Set(reader.BaseStream.Position, length);
}
}
}
public void Read(PhasedGenome genome, SnpCollection snps, CancellationToken cancel, Progress progress) {
this.PhasedGenome = genome;
Read(snps, cancel, progress);
}
public static void ReadMatchWeights(SnpMap<MatchWeight> matchWeights, SnpCollection snps, string filename,
CancellationToken cancel, Progress progress) {
if (matchWeights == null) throw new ArgumentNullException("The MatchWeights cannot be null.");
if (snps == null) throw new ArgumentNullException("The SnpCollection cannot be null.");
if (filename == null) throw new ArgumentNullException("filename cannot be null.");
if (String.IsNullOrWhiteSpace(filename)) throw new ArgumentOutOfRangeException("filename cannot be empty.");
using (StreamReader reader = new StreamReader(filename)) {
long length = 0;
if (progress != null) length = reader.BaseStream.Length;
string line;
string[] columns = new string[5];
while ((line = reader.ReadLine()) != null) {
cancel.ThrowIfCancellationRequested();
if (line.Length > 0) {
line.FastSplit('\t', columns);
string rsId = columns[0];
string majorAllele = columns[1];
double majorWeight, minorWeight;
double.TryParse(columns[2], out majorWeight);
double.TryParse(columns[4], out minorWeight);
if (snps.Contains(rsId)) {
Snp snp = snps[rsId];
MatchWeight matchWeight = new MatchWeight(Convert.ToInt32(10*majorWeight), Convert.ToInt32(10*minorWeight));
matchWeights.Add(snp, matchWeight);
}
}
if (progress != null) progress.Set(reader.BaseStream.Position, length);
}
}
}
/// <summary>
/// Read data into the specified SnpCollection from the Rutgers SNP
/// map file having the specified filename (which may include a path).
/// The specified CancellationToken can be used to abort the read.
/// The progress parameter will be updated by this method with a
/// value of 0-100 to reflect the percent progress of the read.
/// </summary>
/// </summary>
/// <remarks>See http://compgen.rutgers.edu/RutgersMap/AffymetrixIllumina.aspx </remarks>
/// <param name="snps">The SnpCollection to receive the read data.</param>
/// <param name="filename">The path and filename of the Rutgers SNP map file.</param>
/// <param name="cancel">The CancellationToken that can be used to abort the read.</param>
/// <param name="progress">The progress parameter that will be updated to reflect
/// the percent progress of the read.</param>
public static void ReadRutgers(SnpCollection snps, string filename, CancellationToken cancel, Progress progress) {
if (snps == null) throw new ArgumentNullException("The SnpCollection cannot be null.");
if (filename == null) throw new ArgumentNullException("filename cannot be null.");
if (String.IsNullOrWhiteSpace(filename)) throw new ArgumentOutOfRangeException("filename cannot be empty.");
using (StreamReader reader = new StreamReader(filename)) {
long length = 0;
if (progress != null) length = reader.BaseStream.Length;
string[] columns = new string[4];
string line;
reader.ReadLine(); // skip header
while ((line = reader.ReadLine()) != null) {
cancel.ThrowIfCancellationRequested();
line.FastSplit(',', columns);
byte? chr = Snp.ChromosomeToByte(columns[1]);
if (chr.HasValue && (chr.Value >= 1) && (chr.Value <= 23)) {
float cM;
Snp snp;
if (float.TryParse(columns[3], out cM)) {
snp = new Snp(columns[0], chr.Value, Convert.ToInt32(columns[2]), cM, null, null);
} else {
snp = new Snp(columns[0], chr.Value, Convert.ToInt32(columns[2]));
}
snps.Add(snp);
}
if (progress != null) progress.Set(reader.BaseStream.Position, length);
}
}
}
/// <summary>
/// Write all data from the specified SnpCollection into the SnpCollection
/// file having the specified filename (which may include a path). Any
/// existing contents of the file will be overwritten.
/// The specified CancellationToken can be used to abort the read.
/// The progress parameter will be updated by this method with a
/// value of 0-100 to reflect the percent progress of the read.
/// </summary>
/// <param name="snps">The SnpCollection containing the data to be written.</param>
/// <param name="filename">The path and filename of the SnpCollection file.</param>
/// <param name="cancel">The CancellationToken that can be used to abort the write.</param>
/// <param name="progress">The progress parameter that will be updated to reflect
/// the percent progress of the write.</param>
public static void Write(SnpCollection snps, string filename, CancellationToken cancel, Progress progress) {
if (snps == null) throw new ArgumentNullException("The SnpCollection cannot be null.");
if (filename == null) throw new ArgumentNullException("filename cannot be null.");
if (String.IsNullOrWhiteSpace(filename)) throw new ArgumentOutOfRangeException("filename cannot be empty.");
using (StreamWriter writer = new StreamWriter(filename)) {
int count = 0;
foreach (var snp in snps) {
string rsid = snp.RsId;
cancel.ThrowIfCancellationRequested();
writer.WriteLine(rsid + "," + snp.AlfredId + "," + Snp.ChromosomeToString(snp.Chromosome)
+ "," + snp.Position + "," + snp.cM.ToString("0.######") + "," + snp.Alleles.ToAllelesString());
count++;
if (progress != null) progress.Set(count, snps.Count);
}
}
}
public static PhasedGenomeFile ReadPhasedGenome(SnpCollection refSnps, string filename) {
string phasedFilename = GetPhasedFilename(filename);
if (!File.Exists(phasedFilename)) return null;
PhasedGenomeFile result = new PhasedGenomeFile(phasedFilename);
result.PhasedGenome = new PhasedGenome(1, 23);
Console.Write("Reading phased genome " + result.Name + "...");
result.Read(refSnps, new System.Threading.CancellationToken(), null);
Console.WriteLine("completed");
return result;
}
// 23AndMe files are are made available by the 23AndMe DNA testing service to
// their customers.
/// <summary>
/// Read data into the specified Genome from an individual's
/// 23AndMe personal genome file, using the specified filename (which
/// may include a path). The specified SnpCollection does not need
/// to contain all the SNPs that may be present in the genome file.
/// The SnpCollection is used as the source of physical and cM
/// positional information. Centimorgan values for SNPs present in
/// the genome but not in the SnpCollection are extrapolated.
/// The specified CancellationToken can be used to abort the read.
/// The progress parameter will be updated by this method with a
/// value of 0-100 to reflect the percent progress of the read.
/// </summary>
/// <param name="genome">The Genome to receive the read data.</param>
/// <param name="snps">The SnpCollection containing reference SNP positional data.</param>
/// <param name="filename">The path and filename of the 23AndMe genome file.</param>
/// <param name="cancel">The CancellationToken that can be used to abort the read.</param>
/// <param name="progress">The progress parameter that will be updated to reflect
/// the percent progress of the read.</param>
private void Read23AndMeGenome(SnpCollection snps, CancellationToken cancel, Progress progress) {
using (StreamReader reader = new StreamReader(this.filename)) {
long length = 0;
if (progress != null) length = reader.BaseStream.Length;
string line;
string[] columns = new string[4];
while ((line = reader.ReadLine()) != null) {
cancel.ThrowIfCancellationRequested();
if ((line.Length > 0) && (line[0] != '#') && (line[0] != '-')) {
int colCount = line.FastSplit('\t', columns);
if (colCount <= 1) throw new ApplicationException("Not 23andMe format.");
string rsId = columns[0];
Snp snp = snps[rsId];
if ((snp == null) && (colCount == 4)) {
byte chr = Snp.ChromosomeToByte(columns[1]).Value;
if (chr <= 23) {
int position = Convert.ToInt32(columns[2]);
snp = new Snp(rsId, chr, position, snps.ExtrapolateCentiMorganPosition(chr, position), null, "");
}
}
if (snp != null) {
var alleles = columns[colCount - 1];
if ((alleles != null) && (snp.Chromosome == 23) && (alleles.Length == 1)) alleles += alleles;
this.genome.Add(snp, Allele.ToAlleles(alleles));
}
} else if ((line.Length > 0) && (genome.Count == 0) && !line.StartsWith("# rsid\t")) {
this.comments.Add(line);
}
if (progress != null) progress.Set(reader.BaseStream.Position, length);
}
}
if (this.genome.Count < 700000) {
this.genome.GenomeTestType = Genome.GenomeType.MeAnd23v2;
} else {
this.genome.GenomeTestType = Genome.GenomeType.MeAnd23v3;
}
}
/// <summary>
/// Gets an SnpCollection of the SNPs contained in this Genome.
/// </summary>
/// <returns>An SnpCollection.</returns>
protected SnpCollection GetSnps() {
lock (lockObj) {
if (this.snps == null) {
var looseSnps = this.genotypes.Keys.ToArray<Snp>();
//Array.Sort(looseSnps);
ushort minChr = ushort.MaxValue;
ushort maxChr = ushort.MinValue;
foreach (var snp in looseSnps) {
if (snp.Chromosome < minChr) minChr = snp.Chromosome;
if (snp.Chromosome > maxChr) maxChr = snp.Chromosome;
}
snps = new SnpCollection(minChr, maxChr);
foreach (var snp in looseSnps) snps.Add(snp);
}
return this.snps;
}
}
