Sequence::Sequence(const CBioseq& bioseq) :
status(CAV_ERROR_SEQUENCES), bioseqASN(&bioseq), seqIDs(bioseq.GetId()), mmdbLink(NOT_SET)
{
// try to get description from title or compound
if (bioseq.IsSetDescr()) {
CSeq_descr::Tdata::const_iterator d, de = bioseq.GetDescr().Get().end();
for (d=bioseq.GetDescr().Get().begin(); d!=de; ++d) {
if (d->GetObject().IsTitle()) {
description = d->GetObject().GetTitle();
break;
} else if (d->GetObject().IsPdb() && d->GetObject().GetPdb().GetCompound().size() > 0) {
description = d->GetObject().GetPdb().GetCompound().front();
break;
}
}
}
// get link to MMDB id - mainly for CDD's where Biostrucs have to be loaded separately
if (bioseq.IsSetAnnot()) {
CBioseq::TAnnot::const_iterator a, ae = bioseq.GetAnnot().end();
for (a=bioseq.GetAnnot().begin(); a!=ae; ++a) {
if (a->GetObject().GetData().IsIds()) {
CSeq_annot::C_Data::TIds::const_iterator i, ie = a->GetObject().GetData().GetIds().end();
for (i=a->GetObject().GetData().GetIds().begin(); i!=ie; ++i) {
if (i->GetObject().IsGeneral() &&
i->GetObject().GetGeneral().GetDb() == "mmdb" &&
i->GetObject().GetGeneral().GetTag().IsId()) {
mmdbLink = i->GetObject().GetGeneral().GetTag().GetId();
break;
}
}
if (i != ie) break;
}
}
}
if (mmdbLink != NOT_SET)
ERR_POST_X(3, Info << "sequence " << GetTitle() << " is from MMDB id " << mmdbLink);
// get sequence string
if (bioseq.GetInst().GetRepr() == CSeq_inst::eRepr_raw && bioseq.GetInst().IsSetSeq_data()) {
// protein formats
if (bioseq.GetInst().GetSeq_data().IsNcbieaa()) {
sequenceString = bioseq.GetInst().GetSeq_data().GetNcbieaa().Get();
} else if (bioseq.GetInst().GetSeq_data().IsIupacaa()) {
sequenceString = bioseq.GetInst().GetSeq_data().GetIupacaa().Get();
} else if (bioseq.GetInst().GetSeq_data().IsNcbistdaa()) {
StringFromStdaa(bioseq.GetInst().GetSeq_data().GetNcbistdaa().Get(), &sequenceString);
}
// nucleotide formats
else if (bioseq.GetInst().GetSeq_data().IsIupacna()) {
sequenceString = bioseq.GetInst().GetSeq_data().GetIupacna().Get();
} else if (bioseq.GetInst().GetSeq_data().IsNcbi4na()) {
StringFrom4na(bioseq.GetInst().GetSeq_data().GetNcbi4na().Get(), &sequenceString,
(bioseq.GetInst().GetMol() == CSeq_inst::eMol_dna));
} else if (bioseq.GetInst().GetSeq_data().IsNcbi8na()) { // same repr. for non-X as 4na
StringFrom4na(bioseq.GetInst().GetSeq_data().GetNcbi8na().Get(), &sequenceString,
(bioseq.GetInst().GetMol() == CSeq_inst::eMol_dna));
} else if (bioseq.GetInst().GetSeq_data().IsNcbi2na()) {
StringFrom2na(bioseq.GetInst().GetSeq_data().GetNcbi2na().Get(), &sequenceString,
(bioseq.GetInst().GetMol() == CSeq_inst::eMol_dna));
if (bioseq.GetInst().IsSetLength() && bioseq.GetInst().GetLength() < sequenceString.length())
sequenceString.resize(bioseq.GetInst().GetLength());
}
else {
ERR_POST_X(4, Critical << "Sequence::Sequence() - sequence " << GetTitle()
<< ": confused by sequence string format");
return;
}
if (bioseq.GetInst().IsSetLength() && bioseq.GetInst().GetLength() != sequenceString.length()) {
ERR_POST_X(5, Critical << "Sequence::Sequence() - sequence string length mismatch");
return;
}
} else {
ERR_POST_X(6, Critical << "Sequence::Sequence() - sequence " << GetTitle()
<< ": confused by sequence representation");
return;
}
status = CAV_SUCCESS;
}
Sequence::Sequence(SequenceSet *parent, ncbi::objects::CBioseq& bioseq) :
StructureBase(parent), bioseqASN(&bioseq), identifier(NULL), molecule(NULL), isProtein(false)
{
if (bioseq.IsSetDescr()) {
string defline, taxid;
CSeq_descr::Tdata::const_iterator d, de = bioseq.GetDescr().Get().end();
for (d=bioseq.GetDescr().Get().begin(); d!=de; ++d) {
// get "defline" from title or compound
if ((*d)->IsTitle()) { // prefer title over compound
defline = (*d)->GetTitle();
} else if (defline.size() == 0 && (*d)->IsPdb() && (*d)->GetPdb().GetCompound().size() > 0) {
defline = (*d)->GetPdb().GetCompound().front();
}
// get taxonomy
if ((*d)->IsSource()) {
if ((*d)->GetSource().GetOrg().IsSetTaxname())
taxid = (*d)->GetSource().GetOrg().GetTaxname();
else if ((*d)->GetSource().GetOrg().IsSetCommon())
taxid = (*d)->GetSource().GetOrg().GetCommon();
}
}
if (taxid.size() > 0)
taxonomy = string("[") + taxid + ']';
if (defline.size() > 0) {
title = defline;
// remove taxonomy repeated at end of title
if (taxonomy.size() > 0 && NStr::EndsWith(title, taxonomy, NStr::eNocase))
title = title.substr(0, title.size() - taxonomy.size());
if (title[title.size() - 1] == ' ')
title = title.substr(0, title.size() - 1);
}
}
// get link to MMDB id - mainly for CDD's where Biostrucs have to be loaded separately
int mmdbID = MoleculeIdentifier::VALUE_NOT_SET;
if (bioseq.IsSetAnnot()) {
CBioseq::TAnnot::const_iterator a, ae = bioseq.GetAnnot().end();
for (a=bioseq.GetAnnot().begin(); a!=ae; ++a) {
if (a->GetObject().GetData().IsIds()) {
CSeq_annot::C_Data::TIds::const_iterator i, ie = a->GetObject().GetData().GetIds().end();
for (i=a->GetObject().GetData().GetIds().begin(); i!=ie; ++i) {
if (i->GetObject().IsGeneral() &&
i->GetObject().GetGeneral().GetDb() == "mmdb" &&
i->GetObject().GetGeneral().GetTag().IsId()) {
mmdbID = i->GetObject().GetGeneral().GetTag().GetId();
break;
}
}
if (i != ie) break;
}
}
}
// get sequence string
if (bioseq.GetInst().GetRepr() == CSeq_inst::eRepr_raw && bioseq.GetInst().IsSetSeq_data()) {
// protein formats
if (bioseq.GetInst().GetSeq_data().IsNcbieaa()) {
sequenceString = bioseq.GetInst().GetSeq_data().GetNcbieaa().Get();
isProtein = true;
} else if (bioseq.GetInst().GetSeq_data().IsIupacaa()) {
sequenceString = bioseq.GetInst().GetSeq_data().GetIupacaa().Get();
isProtein = true;
} else if (bioseq.GetInst().GetSeq_data().IsNcbistdaa()) {
StringFromStdaa(bioseq.GetInst().GetSeq_data().GetNcbistdaa().Get(), &sequenceString);
isProtein = true;
}
// nucleotide formats
else if (bioseq.GetInst().GetSeq_data().IsIupacna()) {
sequenceString = bioseq.GetInst().GetSeq_data().GetIupacna().Get();
// convert 'T' to 'U' for RNA
if (bioseq.GetInst().GetMol() == CSeq_inst::eMol_rna) {
for (unsigned int i=0; i<sequenceString.size(); ++i) {
if (sequenceString[i] == 'T')
sequenceString[i] = 'U';
}
}
} else if (bioseq.GetInst().GetSeq_data().IsNcbi4na()) {
StringFrom4na(bioseq.GetInst().GetSeq_data().GetNcbi4na().Get(), &sequenceString,
(bioseq.GetInst().GetMol() == CSeq_inst::eMol_dna));
} else if (bioseq.GetInst().GetSeq_data().IsNcbi8na()) { // same repr. for non-X as 4na
StringFrom4na(bioseq.GetInst().GetSeq_data().GetNcbi8na().Get(), &sequenceString,
(bioseq.GetInst().GetMol() == CSeq_inst::eMol_dna));
} else if (bioseq.GetInst().GetSeq_data().IsNcbi2na()) {
StringFrom2na(bioseq.GetInst().GetSeq_data().GetNcbi2na().Get(), &sequenceString,
(bioseq.GetInst().GetMol() == CSeq_inst::eMol_dna));
if (bioseq.GetInst().IsSetLength() && bioseq.GetInst().GetLength() < sequenceString.length())
sequenceString.resize(bioseq.GetInst().GetLength());
}
else {
ERRORMSG("Sequence::Sequence() - sequence " << bioseq.GetId().front()->GetSeqIdString()
<< ": confused by sequence string format");
return;
}
// check length
if (bioseq.GetInst().IsSetLength() && bioseq.GetInst().GetLength() != sequenceString.length()) {
ERRORMSG("Sequence::Sequence() - sequence string length mismatch");
return;
}
// force uppercase
for (unsigned int i=0; i<sequenceString.length(); ++i)
sequenceString[i] = toupper((unsigned char) sequenceString[i]);
} else {
ERRORMSG("Sequence::Sequence() - sequence " << bioseq.GetId().front()->GetSeqIdString() << ": confused by sequence representation");
return;
}
// get identifier (may be NULL if there's a problem!)
identifier = MoleculeIdentifier::GetIdentifier(this, mmdbID, bioseq.GetId());
}
