// 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 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");
}
// 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;
}
}
