internal ProteinSequence(NucleotideSequence seq)
{
if (seq.ActiveAlphabet == AlphabetType.StrictDna || seq.ActiveAlphabet == AlphabetType.StrictRna)
{
if (seq.Sequence.Length % 3 != 0)
{
throw new ArgumentException("Sequence length is not evenly divisible by three, which means it cannot be translated because you are using a strict nucleotide alphabet");
}
}
AlphabetType alphabet;
var allowedSymbols = new HashSet <AminoAcid> {
AminoAcid.Stop, AminoAcid.Gap
};
switch (seq.ActiveAlphabet)
{
case AlphabetType.AmbiguousDna:
alphabet = AlphabetType.ExtendedProtein;
allowedSymbols.UnionWith(AlphabetDataProvider.ExtendedProtein);
break;
case AlphabetType.AmbiguousRna:
alphabet = AlphabetType.ExtendedProtein;
allowedSymbols.UnionWith(AlphabetDataProvider.ExtendedProtein);
break;
default:
alphabet = AlphabetType.StandardProtein;
allowedSymbols.UnionWith(AlphabetDataProvider.StandardProtein);
break;
}
var translationTable = new Dictionary <string, AminoAcid>(AlphabetDataProvider.GetTranslationTable(seq.GeneticCode, seq.ActiveAlphabet));
//string safeSequence, AlphabetType alphabet, GeneticCode geneticCode, Dictionary<Nucleotide, long> symbolCounts
ActiveAlphabet = seq.ActiveAlphabet;
_proteinAlphabet = new ProteinAlphabet(alphabet, seq.GeneticCode);
var proteinBlob = Translate(seq.Sequence, translationTable);
Sequence = proteinBlob.Sequence;
_aminoCounts = proteinBlob.AminoCounts;
}
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;
}
