AlleleAttributes alleleAttributes(Allele & main_allele, Allele & reference_allele) {
assert(!(main_allele.seq().empty()));
assert(!(reference_allele.seq().empty()));
assert(!(reference_allele.isMissing()));
if (main_allele.isMissing()) {
return AlleleAttributes(Type::Missing, 0, 0, 0);
}
if (main_allele == reference_allele) {
return AlleleAttributes(Type::Reference, main_allele.seq().size(), count(main_allele.seq().begin(), main_allele.seq().end(), 'N'), 0);
}
Allele trimmed_main_allele = main_allele;
Allele trimmed_reference_allele = reference_allele;
fullTrimAllelePair(&trimmed_main_allele, &trimmed_reference_allele);
assert(!(trimmed_main_allele.seq().empty()) or !(trimmed_reference_allele.seq().empty()));
uint trimmed_main_allele_length = trimmed_main_allele.seq().size();
uint trimmed_reference_allele_length = trimmed_reference_allele.seq().size();
uint trimmed_main_allele_num_ambiguous = count(trimmed_main_allele.seq().begin(), trimmed_main_allele.seq().end(), 'N');
if (trimmed_main_allele_length == trimmed_reference_allele_length) {
auto allele_type = Type::Complex;
if (trimmed_main_allele_length == 1) {
allele_type = Type::SNP;
} else if (isInversion(trimmed_main_allele, trimmed_reference_allele, 0.95, 10)) {
allele_type = Type::Inversion;
}
return AlleleAttributes(allele_type, trimmed_main_allele_length, trimmed_main_allele_num_ambiguous, 0);
} else {
auto allele_type = Type::Complex;
if (trimmed_main_allele_length == 0) {
allele_type = Type::Deletion;
} else if (trimmed_reference_allele_length == 0) {
allele_type = Type::Insertion;
}
return AlleleAttributes(allele_type, trimmed_main_allele_length, trimmed_main_allele_num_ambiguous, trimmed_main_allele_length - trimmed_reference_allele_length);
}
}
bool hasAmbiguous(Allele & allele) {
if (allele.seq().find_first_of("N") != string::npos) {
return true;
} else {
return false;
}
}
bool isInversion(Allele & main_allele, Allele & reference_allele, const float min_match_fraction, const uint min_size) {
if (main_allele.seq().size() != reference_allele.seq().size()) {
return false;
}
if (main_allele.seq().size() < min_size) {
return false;
}
string main_allele_rv = reverseComplementSequence(main_allele.seq());
assert(main_allele_rv.size() == reference_allele.seq().size());
auto main_rv_it = main_allele_rv.begin();
auto reference_rit = reference_allele.seq().begin();
uint num_correct_bases = 0;
while (main_rv_it != main_allele_rv.end()) {
if ((*main_rv_it == *reference_rit) and (*main_rv_it != 'N')) {
num_correct_bases++;
}
main_rv_it++;
reference_rit++;
}
assert(num_correct_bases <= main_allele_rv.size());
assert(reference_rit == reference_allele.seq().end());
if ((static_cast<float>(num_correct_bases)/main_allele_rv.size()) < min_match_fraction) {
return false;
} else {
return true;
}
}