// ----------------------------------------------------------------------------
bool CSoMap::xMapNcRna(
const CSeq_feat& feature,
string& so_type)
// ----------------------------------------------------------------------------
{
map<string, string> mapNcRnaClassToSoType = {
{"lncRNA", "lnc_RNA"},
{"other", "ncRNA"},
};
string ncrna_class = feature.GetNamedQual("ncRNA_class");
if (ncrna_class.empty()) {
if (feature.IsSetData() &&
feature.GetData().IsRna() &&
feature.GetData().GetRna().IsSetExt() &&
feature.GetData().GetRna().GetExt().IsGen() &&
feature.GetData().GetRna().GetExt().GetGen().IsSetClass()) {
ncrna_class = feature.GetData().GetRna().GetExt().GetGen().GetClass();
if (ncrna_class == "classRNA") {
ncrna_class = "ncRNA";
}
}
}
if (ncrna_class.empty()) {
return false;
}
auto cit = mapNcRnaClassToSoType.find(ncrna_class);
if (cit == mapNcRnaClassToSoType.end()) {
so_type = ncrna_class;
return true;
}
so_type = cit->second;
return true;
}
// ----------------------------------------------------------------------------
bool CGffRecord::AssignType(
const CSeq_feat& feature )
// ----------------------------------------------------------------------------
{
m_strType = "region";
if ( feature.CanGetQual() ) {
const vector< CRef< CGb_qual > >& quals = feature.GetQual();
vector< CRef< CGb_qual > >::const_iterator it = quals.begin();
while ( it != quals.end() ) {
if ( (*it)->CanGetQual() && (*it)->CanGetVal() ) {
if ( (*it)->GetQual() == "standard_name" ) {
m_strType = (*it)->GetVal();
return true;
}
}
++it;
}
}
if ( ! feature.CanGetData() ) {
return true;
}
switch ( feature.GetData().GetSubtype() ) {
default:
m_strType = feature.GetData().GetKey();
break;
case CSeq_feat::TData::eSubtype_gene:
m_strType = "gene";
break;
case CSeq_feat::TData::eSubtype_cdregion:
m_strType = "CDS";
break;
case CSeq_feat::TData::eSubtype_mRNA:
m_strType = "mRNA";
break;
case CSeq_feat::TData::eSubtype_scRNA:
m_strType = "scRNA";
break;
case CSeq_feat::TData::eSubtype_exon:
m_strType = "exon";
break;
}
return true;
}
// ----------------------------------------------------------------------------
bool CGffRecord::AssignPhase(
const CSeq_feat& feature )
// ----------------------------------------------------------------------------
{
m_strPhase = ".";
if ( ! feature.CanGetData() ) {
return true;
}
const CSeq_feat::TData& data = feature.GetData();
if ( data.GetSubtype() != CSeq_feat::TData::eSubtype_cdregion ) {
return true;
}
const CCdregion& cdr = data.GetCdregion();
CCdregion::TFrame frame = cdr.GetFrame();
switch ( frame ) {
default:
break;
case CCdregion::eFrame_one:
m_strPhase = "0";
break;
case CCdregion::eFrame_two:
m_strPhase = "1";
break;
case CCdregion::eFrame_three:
m_strPhase = "2";
break;
}
return true;
}
// ----------------------------------------------------------------------------
bool CSoMap::FeatureToSoType(
const CSeq_feat& feature,
string& so_type)
// ----------------------------------------------------------------------------
{
auto subtype = feature.GetData().GetSubtype();
TYPEFUNCENTRY cit = mMapTypeFunc.find(subtype);
if (cit == mMapTypeFunc.end()) {
return false;
}
return (cit->second)(feature, so_type);
}
// ----------------------------------------------------------------------------
bool CSoMap::xMapRna(
const CSeq_feat& feature,
string& so_type)
// ----------------------------------------------------------------------------
{
static const map<CSeqFeatData::ESubtype, string> mapSubtypeStraight = {
{CSeqFeatData::eSubtype_misc_RNA, "transcript"},
{CSeqFeatData::eSubtype_rRNA, "rRNA"},
{CSeqFeatData::eSubtype_tRNA, "tRNA"},
};
static const map<CSeqFeatData::ESubtype, string> mapSubtypePseudo = {
{CSeqFeatData::eSubtype_misc_RNA, "pseudogenic_transcript"},
{CSeqFeatData::eSubtype_rRNA, "pseudogenic_rRNA"},
{CSeqFeatData::eSubtype_tRNA, "pseudogenic_tRNA"},
};
auto subtype = feature.GetData().GetSubtype();
if (feature.IsSetPseudo() && feature.GetPseudo()) {
auto cit = mapSubtypePseudo.find(subtype);
if (cit == mapSubtypePseudo.end()) {
return false;
}
so_type = cit->second;
return true;
}
if (feature.IsSetPseudo() && !feature.GetPseudo()) {
auto cit = mapSubtypeStraight.find(subtype);
if (cit == mapSubtypeStraight.end()) {
return false;
}
so_type = cit->second;
return true;
}
for (auto qual: feature.GetQual()) {
if (qual->GetQual() == "pseudo" || qual->GetQual() == "pseudogene") {
auto cit = mapSubtypePseudo.find(subtype);
if (cit == mapSubtypePseudo.end()) {
return false;
}
so_type = cit->second;
return true;
}
}
auto cit = mapSubtypeStraight.find(subtype);
if (cit == mapSubtypeStraight.end()) {
return false;
}
so_type = cit->second;
return true;
}
// Corresponds to SortFeatItemListByPos from the C toolkit
int CSeq_feat::CompareNonLocation(const CSeq_feat& f2,
const CSeq_loc& loc1,
const CSeq_loc& loc2) const
{
const CSeqFeatData& data1 = GetData();
const CSeqFeatData& data2 = f2.GetData();
CSeqFeatData::E_Choice type1 = data1.Which();
CSeqFeatData::E_Choice type2 = data2.Which();
// operon first
if ( int diff = s_IsOperon(data2) - s_IsOperon(data1) ) {
return diff;
}
if ( type1 != type2 ) {
// order by feature type
int order1 = GetTypeSortingOrder(type1);
int order2 = GetTypeSortingOrder(type2);
int diff = order1 - order2;
if ( diff != 0 )
return diff;
}
// minus strand last
ENa_strand strand1 = loc1.GetStrand();
ENa_strand strand2 = loc2.GetStrand();
if ( int diff = IsReverse(strand1) - IsReverse(strand2) ) {
return diff;
}
if ( int diff = loc1.CompareSubLoc(loc2, strand1) ) {
return diff;
}
{{ // compare subtypes
CSeqFeatData::ESubtype subtype1 = data1.GetSubtype();
CSeqFeatData::ESubtype subtype2 = data2.GetSubtype();
int diff = subtype1 - subtype2;
if ( diff != 0 )
return diff;
}}
// subtypes are equal, types must be equal too
_ASSERT(type1 == type2);
// type dependent comparison
if ( type1 == CSeqFeatData::e_Cdregion ) {
// compare frames of identical CDS ranges
if ( int diff = s_GetCdregionOrder(data1)-s_GetCdregionOrder(data2) ) {
return diff;
}
}
else if ( type1 == CSeqFeatData::e_Imp ) {
// compare labels of imp features
int diff = NStr::CompareNocase(data1.GetImp().GetKey(),
data2.GetImp().GetKey());
if ( diff != 0 )
return diff;
}
// XXX - should compare parent seq-annots
// XXX 1. parent Seq-annot idx.itemID
// XXX 2. features itemID
return 0; // unknown
}
// ----------------------------------------------------------------------------
bool CSoMap::xMapGeneric(
const CSeq_feat& feature,
string& so_type)
// ----------------------------------------------------------------------------
{
static const map<CSeqFeatData::ESubtype, string> mapSubtypeToSoType = {
{CSeqFeatData::eSubtype_3UTR, "three_prime_UTR"},
{CSeqFeatData::eSubtype_5UTR, "five_prime_UTR"},
{CSeqFeatData::eSubtype_assembly_gap, "assemply_gap"},
{CSeqFeatData::eSubtype_C_region, "C_gene_segment"},
{CSeqFeatData::eSubtype_centromere, "centromere"},
{CSeqFeatData::eSubtype_D_loop, "D_loop"},
{CSeqFeatData::eSubtype_D_segment, "D_gene_segment"},
{CSeqFeatData::eSubtype_exon, "exon"},
{CSeqFeatData::eSubtype_enhancer, "enhancer"},
{CSeqFeatData::eSubtype_gap, "gap"},
{CSeqFeatData::eSubtype_iDNA, "iDNA"},
{CSeqFeatData::eSubtype_intron, "intron"},
{CSeqFeatData::eSubtype_J_segment, "J_gene_segment"},
{CSeqFeatData::eSubtype_LTR, "long_terminal_repeat"},
{CSeqFeatData::eSubtype_mat_peptide, "mature_protein_region"},
{CSeqFeatData::eSubtype_misc_binding, "binding_site"},
{CSeqFeatData::eSubtype_misc_difference, "sequence_difference"},
{CSeqFeatData::eSubtype_misc_structure, "sequence_secondary_structure"},
{CSeqFeatData::eSubtype_mobile_element, "mobile_genetic_element"},
{CSeqFeatData::eSubtype_modified_base, "modified_DNA_base"},
{CSeqFeatData::eSubtype_mRNA, "mRNA"},
{CSeqFeatData::eSubtype_N_region, "N_region"},
{CSeqFeatData::eSubtype_operon, "operon"},
{CSeqFeatData::eSubtype_oriT, "oriT"},
{CSeqFeatData::eSubtype_otherRNA, "transcript"},
{CSeqFeatData::eSubtype_polyA_site, "polyA_site"},
{CSeqFeatData::eSubtype_precursor_RNA, "primary_transcript"},
{CSeqFeatData::eSubtype_preRNA, "primary_transcript"},
{CSeqFeatData::eSubtype_prim_transcript, "primary_transcript"},
{CSeqFeatData::eSubtype_primer_bind, "primer_binding_site"},
{CSeqFeatData::eSubtype_promoter, "promoter"},
{CSeqFeatData::eSubtype_propeptide, "propeptide"},
{CSeqFeatData::eSubtype_protein_bind, "protein_binding_site"},
{CSeqFeatData::eSubtype_rep_origin, "origin_of_replication"},
{CSeqFeatData::eSubtype_S_region, "S_region"},
{CSeqFeatData::eSubtype_sig_peptide, "signal_peptide"},
{CSeqFeatData::eSubtype_source, "region"},
{CSeqFeatData::eSubtype_stem_loop, "stem_loop"},
{CSeqFeatData::eSubtype_STS, "STS"},
{CSeqFeatData::eSubtype_telomere, "telomere"},
{CSeqFeatData::eSubtype_terminator, "terminator"},
{CSeqFeatData::eSubtype_tmRNA, "tmRNA"},
{CSeqFeatData::eSubtype_transit_peptide, "transit_peptide"},
{CSeqFeatData::eSubtype_unsure, "sequence_uncertainty"},
{CSeqFeatData::eSubtype_V_region, "V_region"},
{CSeqFeatData::eSubtype_V_segment, "V_gene_segment"},
{CSeqFeatData::eSubtype_variation, "sequence_alteration"},
//{CSeqFeatData::eSubtype_attenuator, "attenuator"},
};
auto subtype = feature.GetData().GetSubtype();
auto cit = mapSubtypeToSoType.find(subtype);
if (cit != mapSubtypeToSoType.end()) {
so_type = cit->second;
return true;
}
return false;
}
// ----------------------------------------------------------------------------
bool CGffRecord::AssignAttributesCore(
const CSeq_annot& annot,
const CSeq_feat& feature )
// ----------------------------------------------------------------------------
{
m_strAttributes = "";
// If feature ids are present then they are likely used to show parent/child
// relationships, via corresponding xrefs. Thus, any feature ids override
// gb ID tags (feature ids and ID tags should agree in the first place, but
// if not, feature ids must trump ID tags).
//
bool bIdAssigned = false;
if ( feature.CanGetId() ) {
const CSeq_feat::TId& id = feature.GetId();
string value = CGffRecord::FeatIdString( id );
AddAttribute( "ID", value );
bIdAssigned = true;
}
if ( feature.CanGetXref() ) {
const CSeq_feat::TXref& xref = feature.GetXref();
string value;
for ( size_t i=0; i < xref.size(); ++i ) {
// const CSeqFeatXref& ref = *xref[i];
if ( xref[i]->CanGetId() && xref[i]->CanGetData() ) {
const CSeqFeatXref::TId& id = xref[i]->GetId();
CSeq_feat::TData::ESubtype other_type = GetSubtypeOf( annot, id );
if ( ! IsParentOf( other_type, feature.GetData().GetSubtype() ) ) {
continue;
}
if ( ! value.empty() ) {
value += ",";
}
value += CGffRecord::FeatIdString( id );
}
}
if ( ! value.empty() ) {
AddAttribute( "Parent", value );
}
}
if ( feature.CanGetQual() ) {
const vector< CRef< CGb_qual > >& quals = feature.GetQual();
vector< CRef< CGb_qual > >::const_iterator it = quals.begin();
while ( it != quals.end() ) {
if ( (*it)->CanGetQual() && (*it)->CanGetVal() ) {
if ( (*it)->GetQual() == "ID" ) {
if ( ! bIdAssigned ) {
AddAttribute( "ID", (*it)->GetVal() );
}
}
if ( (*it)->GetQual() == "Name" ) {
AddAttribute( "Name", (*it)->GetVal() );
}
if ( (*it)->GetQual() == "Var_type" ) {
AddAttribute( "Var_type", (*it)->GetVal() );
}
}
++it;
}
}
return true;
}
