/// <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);
}
}
}
/// <summary>
/// Create a new SegmentMatch struct with the specified values.
/// </summary>
/// <param name="startSnp">The Snp that is the start of the segment.</param>
/// <param name="endSnp">The Snp that is the end of the segment (inclusive).</param>
/// <param name="snpCount">The number of matching Snps within the segment.</param>
/// <param name="halvesMatched">The number of halves matched; either 1 for a half
/// matching segment, or 2 for a full matching segment.</param>
public SegmentMatch(Snp startSnp, Snp endSnp, int snpCount, int phasedSnpCount, int score,
PhasedGenome.Phasing.MatchKind matchKind, int halvesMatched) {
this.startSnp = startSnp;
this.endSnp = endSnp;
this.snpCount = snpCount;
this.phasedSnpCount = phasedSnpCount;
this.score = score;
this.matchKind = matchKind;
this.halvesMatched = halvesMatched;
}
/// <summary>
/// Determines whether the specified Snp is equal to this Snp.
/// </summary>
/// <param name="other">The Snp to compare with this Snp.</param>
/// <returns>true if the specified Snp is equal to this Snp; otherwise, false.</returns>
public bool Equals(Snp other) {
return ((other != null) && (this.Chromosome == other.Chromosome)
&& (this.Position == other.Position) && (this.Id == other.Id));
}
// 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);
}
}
}
// 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>
/// 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>
/// Determines whether the specified Snp is contained in this Genome.
/// </summary>
/// <param name="snp">The Snp to find.</param>
/// <returns>true if this Genome contains the specified Snp, otherwise false.</returns>
public bool ContainsKey(Snp snp) {
return this.genotypes.ContainsKey(snp);
}
/// <summary>
/// Adds the specified byte Alleles value for the specified Snp to this Genome.
/// </summary>
/// <param name="snp">The Snp being added.</param>
/// <param name="alleles">The byte Alleles value to add for the specified Snp.</param>
public virtual void Add(Snp snp, byte alleles) {
if (snp == null) throw new ArgumentNullException("Snp cannot be null.");
this.genotypes.Add(snp, alleles);
}
/// <summary>
/// Gets the byte Alleles value for the specified Snp.
/// </summary>
/// <param name="snp">The Snp whose alleles value is desired.</param>
/// <returns>The byte Alleles value for the specified Snp.</returns>
public byte this[Snp snp] {
get {
if (snp == null) throw new ArgumentNullException("Snp cannot be null.");
return this.genotypes[snp];
}
}
/// <summary>
/// Create a new SegmentMatch struct with the specified values.
/// </summary>
/// <param name="startSnp">The Snp that is the start of the segment.</param>
/// <param name="endSnp">The Snp that is the end of the segment (inclusive).</param>
/// <param name="snpCount">The number of matching Snps within the segment.</param>
/// <param name="halvesMatched">The number of halves matched; either 1 for a half
/// matching segment, or 2 for a full matching segment.</param>
public SegmentMatch(Snp startSnp, Snp endSnp, int snpCount, int hoHoSnpCount, int halvesMatched) {
this.startSnp = startSnp;
this.endSnp = endSnp;
this.snpCount = snpCount;
this.hoHoSnpCount = hoHoSnpCount;
this.halvesMatched = halvesMatched;
}
