public OnekgTsvWriter(DataSourceVersion version, string outputDirectory, GenomeAssembly genomeAssembly, ISequenceProvider sequenceProvider)
{
Console.WriteLine(version.ToString());
_onekgWriter = new SaTsvWriter(outputDirectory, version, genomeAssembly.ToString(),
SaTsvCommon.OneKgenSchemaVersion, InterimSaCommon.OneKgenTag, "AF1000G", true, sequenceProvider);
_refMinorWriter = new SaMiscTsvWriter(outputDirectory, version, genomeAssembly.ToString(), InterimSaCommon.RefMinorTag, sequenceProvider);
}
public GnomadTsvWriter(DataSourceVersion version, string outputDirectory, GenomeAssembly genomeAssembly, ISequenceProvider sequenceProvider, string sequencingDataType)
{
Console.WriteLine(version.ToString());
_writer = new SaTsvWriter(outputDirectory, version, genomeAssembly.ToString(),
SaTsvCommon.SchemaVersion, _jsonKeyDictionary[sequencingDataType], null, true, sequenceProvider);
}
public CosmicTsvWriter(DataSourceVersion version, string outputDirectory, GenomeAssembly genomeAssembly, ISequenceProvider sequenceProvider)
{
Console.WriteLine(version.ToString());
_writer = new SaTsvWriter(outputDirectory, version, genomeAssembly.ToString(),
SaTsvCommon.CosmicSchemaVersion, InterimSaCommon.CosmicTag, InterimSaCommon.CosmicVcfTag, false, sequenceProvider, true);
}
public TopMedTsvWriter(DataSourceVersion version, string outputFileName, GenomeAssembly genomeAssembly, ISequenceProvider sequenceProvider)
{
Console.WriteLine(version.ToString());
_writer = new SaTsvWriter(outputFileName, version, genomeAssembly.ToString(),
SaTsvCommon.SchemaVersion, InterimSaCommon.TopMedTag, null, true, sequenceProvider);
}
public CustomAnnoTsvWriter(DataSourceVersion version, string outputDirectory, GenomeAssembly genomeAssembly, bool isPositional, ISequenceProvider sequenceProvider)
{
Console.WriteLine(version.ToString());
_writer = new SaTsvWriter(outputDirectory, version, genomeAssembly.ToString(),
SaTsvCommon.CustomItemSchemaVersion, version.Name, null, !isPositional, sequenceProvider, true);
}
public ExacTsvWriter(DataSourceVersion version, string outputDirectory, GenomeAssembly genomeAssembly, ISequenceProvider sequenceProvider)
{
Console.WriteLine(version.ToString());
_writer = new SaTsvWriter(outputDirectory, version, genomeAssembly.ToString(),
SaTsvCommon.OneKgenSchemaVersion, InterimSaCommon.ExacTag, null, true, sequenceProvider);
}
private static ClinvarVariant GetClinvarVariant(XElement xElement, GenomeAssembly genomeAssembly, IDictionary <string, IChromosome> refChromDict, int?variantId)
{
if (xElement == null)
{
return(null);
}
//<SequenceLocation Assembly="GRCh38" Chr="17" Accession="NC_000017.11" start="43082402" stop="43082402" variantLength="1" referenceAllele="A" alternateAllele="C" />
if (genomeAssembly.ToString() != xElement.Attribute(AssemblyTag)?.Value &&
genomeAssembly != GenomeAssembly.Unknown)
{
return(null);
}
var chromosome = refChromDict.ContainsKey(xElement.Attribute(ChrTag)?.Value) ? refChromDict[xElement.Attribute(ChrTag)?.Value] : null;
int start = Convert.ToInt32(xElement.Attribute(StartTag)?.Value);
int stop = Convert.ToInt32(xElement.Attribute(StopTag)?.Value);
string referenceAllele = xElement.Attribute(RefAlleleTag)?.Value;
string altAllele = xElement.Attribute(AltAlleleTag)?.Value;
if (stop - start + 1 > MaxVariantLength)
{
return(null);
}
AdjustVariant(ref start, ref referenceAllele, ref altAllele);
return(new ClinvarVariant(chromosome, start, stop, variantId, referenceAllele, altAllele));
}
private static void AddFile(this ICollection <RemoteFile> files, GenomeAssembly genomeAssembly, string saDirectory, string path)
{
string filename = Path.GetFileName(path);
string remotePath = path;
string localPath = Path.Combine(saDirectory, genomeAssembly.ToString(), filename);
string description = $"{filename} ({genomeAssembly})";
files.Add(new RemoteFile(remotePath, localPath, description));
}
private static void AddCache(this ICollection <RemoteFile> files, GenomeAssembly genomeAssembly,
string remoteCacheDirectory, string cacheDirectory, string type)
{
string filename = $"Both.{type}.ndb";
string remotePath = $"{remoteCacheDirectory}/{CacheConstants.DataVersion}/{genomeAssembly}/{filename}";
string localPath = Path.Combine(cacheDirectory, genomeAssembly.ToString(), filename);
string description = $"{filename} ({genomeAssembly})";
files.Add(new RemoteFile(remotePath, localPath, description));
}
private void CreateSvTsv(string sourceName, string fileName)
{
if (string.IsNullOrEmpty(fileName))
{
return;
}
var benchMark = new Benchmark();
//Console.WriteLine($"Creating TSV from {fileName}");
var dataSource = "";
var version = DataSourceVersionReader.GetSourceVersion(fileName);
switch (sourceName)
{
case InterimSaCommon.DgvTag:
dataSource = "DGV";
using (var writer = new IntervalTsvWriter(_outputDirectory, version,
_genomeAssembly.ToString(), SaTsvCommon.DgvSchemaVersion, InterimSaCommon.DgvTag, ReportFor.StructuralVariants))
{
var reader = new DgvReader(new FileInfo(fileName), _refNamesDictionary);
CreateSvTsv(reader.GetDgvItems(), writer);
}
break;
case InterimSaCommon.ClinGenTag:
dataSource = "ClinGen";
using (var writer = new IntervalTsvWriter(_outputDirectory, version,
_genomeAssembly.ToString(), SaTsvCommon.ClinGenSchemaVersion, InterimSaCommon.ClinGenTag,
ReportFor.StructuralVariants))
{
var reader = new ClinGenReader(new FileInfo(fileName), _refNamesDictionary);
CreateSvTsv(reader.GetClinGenItems(), writer);
}
break;
case InterimSaCommon.OnekSvTag:
dataSource = "OnekSv";
using (var writer = new IntervalTsvWriter(_outputDirectory, version,
_genomeAssembly.ToString(), SaTsvCommon.OneKgenSchemaVersion, InterimSaCommon.OnekSvTag,
ReportFor.StructuralVariants))
{
var reader = new OneKGenSvReader(new FileInfo(fileName), _refNamesDictionary);
CreateSvTsv(reader.GetOneKGenSvItems(), writer);
}
break;
default:
Console.WriteLine("invalid source name");
break;
}
var timeSpan = Benchmark.ToHumanReadable(benchMark.GetElapsedTime());
TsvWriterUtilities.WriteCompleteInfo(dataSource, version.Version, timeSpan);
}
private static ClinvarVariant GetClinvarVariant(LiteXmlElement xmlElement, GenomeAssembly genomeAssembly)
{
if (xmlElement.Children == null)
{
return(null);
}
//<SequenceLocation Assembly="GRCh38" Chr="17" Accession="NC_000017.11" start="43082402" stop="43082402" variantLength="1" referenceAllele="A" alternateAllele="C" />
string chromosome = null, referenceAllele = null, altAllele = null;
int start = 0, stop = 0;
foreach (var attribute in xmlElement.Attributes)
{
switch (attribute.Key)
{
case "Assembly":
if (attribute.Value != genomeAssembly.ToString() &&
genomeAssembly != GenomeAssembly.Unknown)
{
return(null);
}
break;
case "Chr":
chromosome = attribute.Value;
break;
case "display_start":
start = Convert.ToInt32(attribute.Value);
break;
case "display_stop":
stop = Convert.ToInt32(attribute.Value);
break;
case "referenceAllele":
referenceAllele = attribute.Value;
break;
case "alternateAllele":
altAllele = attribute.Value;
break;
}
}
AdjustVariant(ref start, ref stop, ref referenceAllele, ref altAllele);
return(new ClinvarVariant(chromosome, start, stop, referenceAllele, altAllele));
}
public void CreateTsv()
{
var benchMark = new Benchmark();
const string dataSource = "COSMIC";
if (_cnvStream != null)
{
using (var writer = new IntervalTsvWriter(_outputDirectory, _version,
_genomeAssembly.ToString(), SaTsvCommon.CosmicSvSchemaVersion, InterimSaCommon.CosmicCnvTag, ReportFor.StructuralVariants))
using (var cnvReader = new CosmicCnvReader(_cnvStream, _refNameToChorm, _genomeAssembly))
{
foreach (var cnvEntry in cnvReader.GetEntries())
{
writer.AddEntry(cnvEntry.Chromosome.EnsemblName, cnvEntry.Start, cnvEntry.End, cnvEntry.GetJsonString());
}
}
}
var timeSpan = Benchmark.ToHumanReadable(benchMark.GetElapsedTime());
TsvWriterUtilities.WriteCompleteInfo(dataSource, _version.Version, timeSpan);
}
public static string GetCachePathPrefix(GenomeAssembly genomeAssembly, string baseUrl = null)
{
return(LambdaUrlHelper.GetCacheFolder(baseUrl).UrlCombine(genomeAssembly.ToString())
.UrlCombine(LambdaUrlHelper.DefaultCacheSource));
}
public ClinvarTsvWriter(DataSourceVersion version, string outputDirectory, GenomeAssembly genomeAssembly, ISequenceProvider sequenceProvider) : this(new SaTsvWriter(outputDirectory, version, genomeAssembly.ToString(),
SaTsvCommon.ClinvarSchemaVersion, InterimSaCommon.ClinvarTag, InterimSaCommon.ClinvarVcfTag, false, sequenceProvider, true))
{
Console.WriteLine(version.ToString());
}
public EvsTsvWriter(DataSourceVersion version, string outputDirectory, GenomeAssembly genomeAssembly, ISequenceProvider sequenceProvider) : this(new SaTsvWriter(outputDirectory, version, genomeAssembly.ToString(),
SaTsvCommon.OneKgenSchemaVersion, InterimSaCommon.EvsTag, InterimSaCommon.EvsVcfTag, true, sequenceProvider))
{
Console.WriteLine(version.ToString());
}