public void CompactId_IO_EndToEnd()
{
const string expectedResults = "ENSP00000334393.3";
var id = CompactId.Convert("ENSP00000334393", 3);
ICompactId observedId;
using (var ms = new MemoryStream())
{
using (var writer = new ExtendedBinaryWriter(ms, Encoding.UTF8, true))
{
id.Write(writer);
}
ms.Position = 0;
using (var reader = new BufferedBinaryReader(ms))
{
observedId = CompactId.Read(reader);
}
}
Assert.NotNull(observedId);
Assert.Equal(expectedResults, observedId.WithVersion);
}
public static ITranslation Read(ExtendedBinaryReader reader, string[] peptideSeqs)
{
var codingRegion = DataStructures.CodingRegion.Read(reader);
var proteinId = CompactId.Read(reader);
var peptideIndex = reader.ReadOptInt32();
var peptideSeq = peptideIndex == -1 ? null : peptideSeqs[peptideIndex];
return(new Translation(codingRegion, proteinId, peptideSeq));
}
public static IRegulatoryRegion Read(IBufferedBinaryReader reader, IDictionary <ushort, IChromosome> chromosomeIndexDictionary)
{
var refIndex = reader.ReadOptUInt16();
int start = reader.ReadOptInt32();
int end = reader.ReadOptInt32();
var type = (RegulatoryRegionType)reader.ReadByte();
var id = CompactId.Read(reader);
return(new RegulatoryRegion(chromosomeIndexDictionary[refIndex], start, end, id, type));
}
public static IGene Read(IBufferedBinaryReader reader, IDictionary <ushort, IChromosome> indexToChromosome)
{
ushort referenceIndex = reader.ReadOptUInt16();
int start = reader.ReadOptInt32();
int end = reader.ReadOptInt32();
bool onReverseStrand = reader.ReadBoolean();
string symbol = reader.ReadAsciiString();
int hgncId = reader.ReadOptInt32();
var entrezId = CompactId.Read(reader);
var ensemblId = CompactId.Read(reader);
return(new Gene(indexToChromosome[referenceIndex], start, end, onReverseStrand, symbol, hgncId, entrezId, ensemblId));
}
public static ITranscript Read(BufferedBinaryReader reader,
IDictionary <ushort, IChromosome> chromosomeIndexDictionary, IGene[] cacheGenes,
ITranscriptRegion[] cacheTranscriptRegions, IInterval[] cacheMirnas, string[] cachePeptideSeqs)
{
// transcript
var referenceIndex = reader.ReadOptUInt16();
var start = reader.ReadOptInt32();
var end = reader.ReadOptInt32();
var id = CompactId.Read(reader);
// gene
var geneIndex = reader.ReadOptInt32();
var gene = cacheGenes[geneIndex];
// encoded data
var encoded = EncodedTranscriptData.Read(reader);
// transcript regions
var transcriptRegions = encoded.HasTranscriptRegions ? ReadIndices(reader, cacheTranscriptRegions) : null;
ushort numExons = reader.ReadOptUInt16();
// protein function predictions
int siftIndex = encoded.HasSift ? reader.ReadOptInt32() : -1;
int polyphenIndex = encoded.HasPolyPhen ? reader.ReadOptInt32() : -1;
// translation
var translation = encoded.HasTranslation ? DataStructures.Translation.Read(reader, cachePeptideSeqs) : null;
// attributes
var mirnas = encoded.HasMirnas ? ReadIndices(reader, cacheMirnas) : null;
var rnaEdits = encoded.HasRnaEdits ? ReadItems(reader, RnaEdit.Read) : null;
var selenocysteines = encoded.HasSelenocysteines ? ReadItems(reader, x => x.ReadOptInt32()) : null;
return(new Transcript(chromosomeIndexDictionary[referenceIndex], start, end, id, translation,
encoded.BioType, gene, ExonUtilities.GetTotalExonLength(transcriptRegions), encoded.StartExonPhase,
encoded.IsCanonical, transcriptRegions, numExons, mirnas, siftIndex, polyphenIndex,
encoded.TranscriptSource, encoded.CdsStartNotFound, encoded.CdsEndNotFound, selenocysteines, rnaEdits));
}