public static string GetAlphabet(AlphabetType type)
{
switch (type)
{
case AlphabetType.EN:
return(ALPHABET_EN);
case AlphabetType.PL:
return(ALPHABET_PL);
case AlphabetType.EN_Digits:
return(ALPHABET_EN + DIGITS);
case AlphabetType.PL_Digits:
return(ALPHABET_PL + DIGITS);
case AlphabetType.EN_Digits_Extended:
return(ALPHABET_EN + DIGITS + PUNCTUATION);
case AlphabetType.PL_Digits_Extended:
return(ALPHABET_PL + DIGITS + PUNCTUATION);
default:
throw new ArgumentOutOfRangeException(nameof(type), type, null);
}
}
/// <summary>
/// Creates a course from json using a given AlphabetType.
/// </summary>
private static Course CreateCourse(AlphabetType alphabetType)
{
//determine resource id
string resourceId = $"Alphabets.Resources.Database.{alphabetType}.Course.json";
//get json string
string json = FileHelper.TextResourceToString(resourceId);
//deserialize json data
CourseImport courseImport = JsonConvert.DeserializeObject <CourseImport>(json);
//create lessons
List <Lesson> lessons = new List <Lesson>();
foreach (LessonImport lessonImport in courseImport.Lessons)
{
//create lesson parts
List <LessonPart> lessonParts = new List <LessonPart>();
foreach (LessonPartImport lessonPartImport in lessonImport.LessonParts)
{
lessonParts.Add(new LessonPart(lessonPartType: lessonPartImport.LessonPartType, letter: lessonPartImport.Letter));
}
lessons.Add(new Lesson(cumulativeLetters: lessonImport.CumulativeLetters, lessonParts: lessonParts.ToArray()));
}
//create course
return(new Course(alphabetType: AlphabetType.Georgian, lessons: lessons.ToArray()));
}
protected NucleotideSequence(string sequence, AlphabetType alphabet, GeneticCode geneticCode = GeneticCode.Standard, IEnumerable <string> tags = null)
: this(sequence, alphabet, geneticCode)
{
if (tags != null)
{
_tags = new HashSet <string>(tags);
}
}
internal override char[] ConvertPhonemes(char[] phones, AlphabetType alphabet)
{
if (alphabet == AlphabetType.Ipa)
{
return(phones);
}
return(_alphabetConverter.SapiToIpa(phones));
}
public void ProcessPhoneme(ref FragmentState fragmentState, AlphabetType alphabet, string ph, char[] phoneIds)
{
_writer.WriteStartElement("phoneme");
if (alphabet != AlphabetType.Ipa)
{
_writer.WriteAttributeString("alphabet", (alphabet == AlphabetType.Sapi) ? "x-microsoft-sapi" : "x-microsoft-ups");
}
_writer.WriteAttributeString("ph", ph);
}
public void ProcessPhoneme(ref FragmentState fragmentState, AlphabetType alphabet, string ph, char[] phoneIds)
{
_writer.WriteStartElement("phoneme");
if (alphabet != AlphabetType.Ipa)
{
_writer.WriteAttributeString("alphabet", alphabet == AlphabetType.Sapi ? "x-microsoft-sapi" : "x-microsoft-ups");
System.Diagnostics.Debug.Assert(alphabet == AlphabetType.Ups || alphabet == AlphabetType.Sapi);
}
_writer.WriteAttributeString("ph", ph);
}
public void GenerateFastaSequenceTests(string rawSequence, AlphabetType sequenceAlphabet, ISequence expected)
{
var parser = new FastaParser(rawSequence, sequenceAlphabet);
var actual = parser.Parse().First();
Assert.AreEqual(expected.GetType(), actual.GetType());
CollectionAssert.AreEquivalent(expected.Tags, actual.Tags);
Assert.AreEqual(expected.Sequence, actual.Sequence);
Assert.AreEqual(expected.ActiveAlphabet, actual.ActiveAlphabet);
}
protected NucleotideSequence(string sequence, AlphabetType alphabet, GeneticCode geneticCode, Dictionary <Nucleotide, long> symbolCounts, IEnumerable <string> tags)
{
NucleotideAlphabet = new NucleotideAlphabet(alphabet, geneticCode);
ActiveAlphabet = alphabet;
GeneticCode = geneticCode;
Sequence = sequence;
SymbolCounts = symbolCounts;
if (tags != null)
{
_tags = new HashSet <string>(tags);
}
}
protected NucleotideSequence(string sequence, AlphabetType alphabet, GeneticCode geneticCode)
{
NucleotideAlphabet = new NucleotideAlphabet(alphabet, geneticCode);
ActiveAlphabet = alphabet;
GeneticCode = geneticCode;
var trimmedSequence = sequence.Trim();
VerifyAndInitializeNucleotides(trimmedSequence);
Sequence = trimmedSequence;
}
public NucleotideAlphabet(AlphabetType nucleotideAlphabet, GeneticCode geneticCode)
{
if (nucleotideAlphabet == AlphabetType.ExtendedProtein || nucleotideAlphabet == AlphabetType.StandardProtein)
{
throw new ArgumentException(String.Format(AlphabetDataProvider.InvalidNucleotideAlphabet, nucleotideAlphabet));
}
GeneticCode = geneticCode;
AllowedSymbols = AlphabetDataProvider.GetAllowedNucleotideSymbols(nucleotideAlphabet);
ComplementTable = AlphabetDataProvider.GetComplementTable(nucleotideAlphabet);
TranscriptionTable = AlphabetDataProvider.GetTranscriptionTable(nucleotideAlphabet);
TranslationTable = AlphabetDataProvider.GetTranslationTable(geneticCode, nucleotideAlphabet);
GcContentSymbols = AlphabetDataProvider.GcContentSymbols(nucleotideAlphabet);
}
public static ISet <AminoAcid> GetAllowedProteinSymbols(AlphabetType alphabet)
{
switch (alphabet)
{
case AlphabetType.ExtendedProtein:
return(ExtendedProtein);
case AlphabetType.StandardProtein:
return(StandardProtein);
default:
throw new ArgumentException(String.Format(ProteinAlphabet.InvalidProteinAlphabet, alphabet));
}
}
public RnaSequence(string rawBasePairs, AlphabetType alphabet, GeneticCode geneticCode = GeneticCode.Standard, IEnumerable <string> tags = null)
: base(rawBasePairs, alphabet, geneticCode, tags)
{
switch (alphabet)
{
case AlphabetType.AmbiguousRna:
break;
case AlphabetType.StrictRna:
break;
default:
throw new ArgumentException(String.Format(InvalidAlphabetForSequenceType, alphabet, GetType()));
}
}
public ProteinAlphabet(AlphabetType proteinAlphabet, GeneticCode geneticCode = GeneticCode.Standard)
{
switch (proteinAlphabet)
{
case AlphabetType.ExtendedProtein:
break;
case AlphabetType.StandardProtein:
break;
default:
throw new ArgumentException(String.Format(InvalidProteinAlphabet, proteinAlphabet));
}
_activeAlphabet = proteinAlphabet;
_geneticCode = geneticCode;
}
public static char[] Create(AlphabetType alphabetType)
{
switch (alphabetType)
{
case AlphabetType.None:
throw new NotSupportedException();
case AlphabetType.English:
return("ABCDEFGHIJKLMNOPQRSTUVWXYZ".ToArray());
case AlphabetType.Russian:
return("ABCDEFGHIJKLMNOPQRSTUVWXYZ".ToArray());
case AlphabetType.Count:
throw new NotSupportedException();
}
throw new NotSupportedException();
}
/// <summary>
/// Returns the proper complement table for the given nucleotide alphabet
/// </summary>
/// <param name="alphabet"></param>
/// <returns></returns>
public static IDictionary <Nucleotide, Nucleotide> GetComplementTable(AlphabetType alphabet)
{
switch (alphabet)
{
case AlphabetType.StrictDna:
return(StrictDnaComplements);
case AlphabetType.AmbiguousDna:
return(AmbiguousDnaComplements);
case AlphabetType.StrictRna:
return(StrictRnaComplements);
case AlphabetType.AmbiguousRna:
return(AmbiguousRnaComplements);
default:
throw new ArgumentException(String.Format(InvalidNucleotideAlphabet, alphabet));
}
}
/// <summary>
/// Returns the transcription table for DNA to RNA conversions, or the back transcription table for RNA to DNA conversion. An RNA alphabet will return
/// a DNA alphabet.
/// </summary>
/// <param name="nucleotideAlphabet"></param>
/// <returns></returns>
public static IDictionary <Nucleotide, Nucleotide> GetTranscriptionTable(AlphabetType nucleotideAlphabet)
{
switch (nucleotideAlphabet)
{
case AlphabetType.AmbiguousDna:
return(AmbiguousDnaTranscriptionTable);
case AlphabetType.StrictDna:
return(UnambiguousDnaTranscriptionTable);
case AlphabetType.AmbiguousRna:
return(AmbiguousRnaTranscriptionTable);
case AlphabetType.StrictRna:
return(UnambiguousRnaTranslationTable);
default:
throw new ArgumentException(String.Format(InvalidNucleotideAlphabet, nucleotideAlphabet));
}
}
/// <summary>
/// Returns the set of symbols that are used to compute the GC content given an alphabet type
/// </summary>
/// <param name="alphabetType"></param>
/// <returns></returns>
public static ISet <Nucleotide> GcContentSymbols(AlphabetType alphabetType)
{
switch (alphabetType)
{
case AlphabetType.AmbiguousDna:
return(AmbiguousAlphabetGcSymbols);
case AlphabetType.AmbiguousRna:
return(AmbiguousAlphabetGcSymbols);
case AlphabetType.StrictDna:
return(UnambiguousAlphabetGcSymbols);
case AlphabetType.StrictRna:
return(UnambiguousAlphabetGcSymbols);
default:
throw new ArgumentException(String.Format(InvalidNucleotideAlphabet, alphabetType));
}
}
/// <summary>
/// Returns the set of allowed symbols for a given nucleotide alphabet
/// </summary>
/// <param name="alphabet"></param>
/// <returns></returns>
public static ISet <Nucleotide> GetAllowedNucleotideSymbols(AlphabetType alphabet)
{
switch (alphabet)
{
case AlphabetType.StrictDna:
return(StrictDna);
case AlphabetType.AmbiguousDna:
return(AmbiguousDna);
case AlphabetType.StrictRna:
return(StrictRna);
case AlphabetType.AmbiguousRna:
return(AmbiguousRna);
default:
throw new ArgumentException(String.Format(InvalidNucleotideAlphabet, alphabet));
}
}
/// <summary>
/// Creates an alphabet from json using a given AlphabetType.
/// </summary>
private static Alphabet CreateAlphabet(AlphabetType alphabetType)
{
//determine resource id
string resourceId = $"Alphabets.Resources.Database.{alphabetType}.Alphabet.json";
//get json string
string json = FileHelper.TextResourceToString(resourceId);
//deserialize json data
AlphabetImport alphabetImport = JsonConvert.DeserializeObject <AlphabetImport>(json);
//create letters
List <Letter> letters = new List <Letter>();
foreach (LetterImport letterImport in alphabetImport.Letters)
{
letters.Add(new Letter(cases: letterImport.Cases, transCases: letterImport.TransCases, pronounciationTips: letterImport.PronounciationTips, resourceId: letterImport.ResourceId));
}
//create alphabet
return(new Alphabet(name: alphabetImport.Name, letters: letters.ToArray()));
}
public ProteinSequence(string rawSequence, AlphabetType desiredProteinAlphabet, GeneticCode geneticCode = GeneticCode.Standard)
{
switch (desiredProteinAlphabet)
{
case AlphabetType.ExtendedProtein:
break;
case AlphabetType.StandardProtein:
break;
default:
throw new ArgumentException(String.Format(ProteinAlphabet.InvalidProteinAlphabet, desiredProteinAlphabet));
}
_proteinAlphabet = new ProteinAlphabet(desiredProteinAlphabet, geneticCode);
ActiveAlphabet = desiredProteinAlphabet;
AllowedSymbols = AlphabetDataProvider.GetAllowedProteinSymbols(ActiveAlphabet);
_aminoCounts = new Dictionary <AminoAcid, long>(AllowedSymbols.Count);
foreach (var symbol in AllowedSymbols)
{
_aminoCounts.Add(symbol, 0);
}
var trimmedRaw = rawSequence.Trim();
foreach (var aminoCharacter in trimmedRaw)
{
var typedAmino = (AminoAcid)Char.ToUpperInvariant(aminoCharacter);
if (!AllowedSymbols.Contains(typedAmino))
{
throw new ArgumentException(String.Format(_invalidAminoAcidCharacter, aminoCharacter, _proteinAlphabet));
}
_aminoCounts[typedAmino]++;
}
Sequence = trimmedRaw;
}
public void RnaSequenceConstructor_TestCases(string nucleotides, AlphabetType alphabet)
{
var rna = new RnaSequence(nucleotides, alphabet);
Assert.IsInstanceOf <RnaSequence>(rna);
}
public void DnaSequenceConstructor_Tests(string nucleotides, AlphabetType alphabet)
{
var dna = new DnaSequence(nucleotides, alphabet);
Assert.IsInstanceOf <DnaSequence>(dna);
}
public void ProcessPhoneme(ref FragmentState fragmentState, AlphabetType alphabet, string ph, char[] phoneIds)
{
fragmentState.Action = TtsEngineAction.Pronounce;
fragmentState.Phoneme = _speakInfo.Voice.TtsEngine.ConvertPhonemes(phoneIds, alphabet);
}
internal RnaSequence(string safeSequence, AlphabetType alphabet, GeneticCode geneticCode, Dictionary <Nucleotide, long> symbolCounts, IEnumerable <string> tags = null)
: base(safeSequence, alphabet, geneticCode, symbolCounts, tags)
{
}
internal static RnaSequence FastRnaSequence(string safeSequence, AlphabetType alphabet, GeneticCode geneticCode, Dictionary <Nucleotide, long> symbolCounts, IEnumerable <string> tags = null)
{
return(new RnaSequence(safeSequence, alphabet, geneticCode, symbolCounts, tags));
}
public FastaParser(string fastaTextBlob, AlphabetType alphabet, GeneticCode geneticCode = GeneticCode.Standard) :
this(alphabet, geneticCode)
{
_lines = Regex.Split(fastaTextBlob, Constants.CrossPlatformNewlines).ToList();
}
public FastaParser(IEnumerable <string> fastaText, AlphabetType alphabet, GeneticCode geneticCode = GeneticCode.Standard) :
this(alphabet, geneticCode)
{
_lines.AddRange(fastaText);
}
public FastaParser(Uri pathToFasta, AlphabetType alphabet, GeneticCode geneticCode = GeneticCode.Standard) :
this(alphabet, geneticCode)
{
_dataPath = pathToFasta;
}
private FastaParser(AlphabetType alphabet, GeneticCode geneticCode)
{
_geneticCode = geneticCode;
_alphabet = alphabet;
}
public int Constructor_Tests(string sequence, AlphabetType alphabet)
{
var protein = new ProteinSequence(sequence, alphabet, GeneticCode.Standard);
return(protein.Sequence.Length);
}
