bool EnzymaticDigestionLogModel::isCleavageSite_(
const AASequence& protein, const AASequence::ConstIterator& iterator) const
{
if (enzyme_.getName() != "Trypsin") // no cleavage
{
throw Exception::InvalidParameter(__FILE__, __LINE__, __PRETTY_FUNCTION__, String("EnzymaticDigestionLogModel: enzyme '") + enzyme_.getName() + " does not support logModel!");
}
else
{
if ((!enzyme_.getRegEx().hasSubstring(iterator->getOneLetterCode())) || *iterator == 'P') // wait for R or K
{
return false;
}
SignedSize pos = distance(AASequence::ConstIterator(protein.begin()),
iterator) - 4; // start position in sequence
double score_cleave = 0, score_missed = 0;
for (SignedSize i = 0; i < 9; ++i)
{
if ((pos + i >= 0) && (pos + i < (SignedSize)protein.size()))
{
BindingSite_ bs(i, protein[pos + i].getOneLetterCode());
Map<BindingSite_, CleavageModel_>::const_iterator pos_it =
model_data_.find(bs);
if (pos_it != model_data_.end()) // no data for non-std. amino acids
{
score_cleave += pos_it->second.p_cleave;
score_missed += pos_it->second.p_miss;
}
}
}
return score_missed - score_cleave > log_model_threshold_;
}
}
String CompNovoIdentificationBase::getModifiedStringFromAASequence_(const AASequence & sequence)
{
String seq;
for (AASequence::ConstIterator it = sequence.begin(); it != sequence.end(); ++it)
{
if (residue_to_name_.has(&*it))
{
seq += residue_to_name_[&*it];
}
else
{
seq += it->getOneLetterCode();
}
}
return seq;
}
String SILACLabeler::getUnmodifiedSequence_(const Feature& feature, const String& arginine_label, const String& lysine_label) const
{
String unmodified_sequence = "";
for (AASequence::ConstIterator residue = feature.getPeptideIdentifications()[0].getHits()[0].getSequence().begin();
residue != feature.getPeptideIdentifications()[0].getHits()[0].getSequence().end();
++residue)
{
if (*residue == 'R' && residue->getModification() == arginine_label)
{
unmodified_sequence.append("R");
}
else if (*residue == 'K' && residue->getModification() == lysine_label)
{
unmodified_sequence.append("K");
}
else
{
unmodified_sequence.append(residue->getOneLetterCode());
}
}
return unmodified_sequence;
}
bool ModificationDefinitionsSet::isCompatible(const AASequence & peptide) const
{
set<String> var_names(getVariableModificationNames()), fixed_names(getFixedModificationNames());
// no modifications present and needed
if (fixed_names.empty() && !peptide.isModified())
{
return true;
}
// check whether the fixed modifications are fulfilled
if (!fixed_names.empty())
{
for (set<String>::const_iterator it1 = fixed_names.begin(); it1 != fixed_names.end(); ++it1)
{
String origin = ModificationsDB::getInstance()->getModification(*it1).getOrigin();
// only single 1lc amino acids are allowed
if (origin.size() != 1)
{
continue;
}
for (AASequence::ConstIterator it2 = peptide.begin(); it2 != peptide.end(); ++it2)
{
if (origin == it2->getOneLetterCode())
{
// check whether the residue is modified (has to be)
if (!it2->isModified())
{
return false;
}
// check whether the modification is the same
if (ModificationsDB::getInstance()->getModification(*it1).getId() != it2->getModification())
{
return false;
}
}
}
}
}
// check wether other modifications than the variable are present
for (AASequence::ConstIterator it = peptide.begin(); it != peptide.end(); ++it)
{
if (it->isModified())
{
String mod = ModificationsDB::getInstance()->getModification(it->getOneLetterCode(), it->getModification(), ResidueModification::ANYWHERE).getFullId();
if (var_names.find(mod) == var_names.end() &&
fixed_names.find(mod) == fixed_names.end())
{
return false;
}
}
}
if (peptide.hasNTerminalModification())
{
String mod = ModificationsDB::getInstance()->getTerminalModification(peptide.getNTerminalModification(), ResidueModification::N_TERM).getFullId();
if (var_names.find(mod) == var_names.end() &&
fixed_names.find(mod) == fixed_names.end())
{
return false;
}
}
if (peptide.hasCTerminalModification())
{
String mod = ModificationsDB::getInstance()->getTerminalModification(peptide.getCTerminalModification(), ResidueModification::C_TERM).getFullId();
if (var_names.find(mod) == var_names.end() &&
fixed_names.find(mod) == fixed_names.end())
{
return false;
}
}
return true;
}