public IEnumerable <DigestedPeptide> Digest(Protein protein)
{
Regex regex = new Regex(Regex);
int begin = 0;
int len = protein.Sequence.Length;
while (begin < len)
{
int end = begin;
int endFirst = begin;
int missed = 0;
do
{
string sequence = protein.Sequence;
Match m = regex.Match(sequence, end);
end = (m.Success ? m.Index + 1 : len);
// Save the end of the first cleavage
if (missed == 0)
{
endFirst = end;
}
// TODO(nicksh)
//// Deal with 'ragged ends', or cleavages one amino acid apart
//// i.e. KR, RR, etc. for trypsin
//if (settings.ExcludeRaggedEnds && end < len)
//{
// Match mNext = regex.Match(sequence, end);
// if (mNext.Success && mNext.Index == end)
// {
// // If there are no missed cleavages, then move the
// // begin index to the next cleavage point that is
// // not part of a run.
// if (missed == 0)
// endFirst = GetDiscontiguousCleavageIndex(regex, mNext, sequence);
// break;
// }
//}
// Single amino acid peptides have no fragment ions.
int count = end - begin;
if (count > 1 && sequence.IndexOfAny(new[] { '*', '-' }, begin, count) == -1) // Not L10N
{
DigestedPeptide peptide = new DigestedPeptide
{
Index = begin,
Sequence = sequence.Substring(begin, end - begin)
};
yield return(peptide);
}
// Increment missed cleavages for next loop.
missed++;
}while (end < len);
begin = endFirst;
}
}
public IEnumerable<DigestedPeptide> Digest(Protein protein)
{
Regex regex = new Regex(Regex);
int begin = 0;
int len = protein.Sequence.Length;
while (begin < len)
{
int end = begin;
int endFirst = begin;
int missed = 0;
do
{
string sequence = protein.Sequence;
Match m = regex.Match(sequence, end);
end = (m.Success ? m.Index + 1 : len);
// Save the end of the first cleavage
if (missed == 0)
endFirst = end;
// TODO(nicksh)
//// Deal with 'ragged ends', or cleavages one amino acid apart
//// i.e. KR, RR, etc. for trypsin
//if (settings.ExcludeRaggedEnds && end < len)
//{
// Match mNext = regex.Match(sequence, end);
// if (mNext.Success && mNext.Index == end)
// {
// // If there are no missed cleavages, then move the
// // begin index to the next cleavage point that is
// // not part of a run.
// if (missed == 0)
// endFirst = GetDiscontiguousCleavageIndex(regex, mNext, sequence);
// break;
// }
//}
// Single amino acid peptides have no fragment ions.
int count = end - begin;
if (count > 1 && sequence.IndexOfAny(new[] { '*', '-' }, begin, count) == -1) // Not L10N
{
DigestedPeptide peptide = new DigestedPeptide
{
Index = begin,
Sequence = sequence.Substring(begin, end - begin)
};
yield return peptide;
}
// Increment missed cleavages for next loop.
missed++;
}
while (end < len);
begin = endFirst;
}
}
public IEnumerable<DigestedPeptide> Digest(Protein protein)
{
if (string.IsNullOrEmpty(protein.Sequence))
{
yield break;
}
FastaSequence fastaSequence;
try
{
fastaSequence = new FastaSequence("name", "description", new List<ProteinMetadata>(), protein.Sequence); // Not L10N
}
catch (InvalidDataException)
{
// It's possible that the peptide sequence in the fasta file was bogus, in which case we just don't digest it.
yield break;
}
DigestSettings digestSettings = new DigestSettings(6, false);
foreach (var digest in _enzyme.Digest(fastaSequence, digestSettings))
{
var digestedPeptide = new DigestedPeptide
{
Index = digest.Begin ?? 0,
Sequence = digest.Sequence
};
yield return digestedPeptide;
}
}
