void GffLoader::load(GList<GenomicSeqData>& seqdata, GFValidateFunc* gf_validate,
bool doCluster, bool doCollapseRedundant,
bool matchAllIntrons, bool fuzzSpan, bool forceExons) {
GffReader* gffr=new GffReader(f, this->transcriptsOnly, false); //not only mRNA features, not sorted
gffr->showWarnings(this->showWarnings);
// keepAttrs mergeCloseExons noExonAttr
gffr->readAll(this->fullAttributes, this->mergeCloseExons, this->noExonAttrs);
GVec<int> pseudoAttrIds;
GVec<int> pseudoFeatureIds;
if (this->noPseudo) {
GffNameList& fnames = gffr->names->feats;
for (int i=0;i<fnames.Count();i++) {
char* n=fnames[i]->name;
if (startsWith(n, "pseudo")) {
pseudoFeatureIds.Add(fnames[i]->idx);
}
}
GffNameList& attrnames = gffr->names->attrs;
for (int i=0;i<attrnames.Count();i++) {
char* n=attrnames[i]->name;
char* p=strifind(n, "pseudo");
if (p==n || (p==n+2 && tolower(n[0])=='i' && tolower(n[1])=='s')) {
pseudoAttrIds.Add(attrnames[i]->idx);
}
}
}
//int redundant=0; //redundant annotation discarded
if (verbose) GMessage(" .. loaded %d genomic features from %s\n", gffr->gflst.Count(), fname.chars());
//int rna_deleted=0;
//add to GenomicSeqData, adding to existing loci and identifying intron-chain duplicates
for (int k=0;k<gffr->gflst.Count();k++) {
GffObj* m=gffr->gflst[k];
if (strcmp(m->getFeatureName(), "locus")==0 &&
m->getAttr("transcripts")!=NULL) {
continue; //discard locus meta-features
}
if (this->noPseudo) {
bool is_pseudo=false;
for (int i=0;i<pseudoFeatureIds.Count();++i) {
if (pseudoFeatureIds[i]==m->ftype_id) {
is_pseudo=true;
break;
}
}
if (is_pseudo) continue;
for (int i=0;i<pseudoAttrIds.Count();++i) {
char* attrv=NULL;
if (m->attrs!=NULL) attrv=m->attrs->getAttr(pseudoAttrIds[i]);
if (attrv!=NULL) {
char fc=tolower(attrv[0]);
if (fc=='t' || fc=='y' || fc=='1') {
is_pseudo=true;
break;
}
}
}
if (is_pseudo) continue;
//last resort:
// scan all the attribute values for "pseudogene" keyword (NCBI does that for "product" attr)
/*
if (m->attrs!=NULL) {
for (int i=0;i<m->attrs->Count();++i) {
GffAttr& a=*(m->attrs->Get(i));
if (strifind(a.attr_val, "pseudogene")) {
is_pseudo=true;
break;
}
}
}
if (is_pseudo) continue;
*/
} //pseudogene detection requested
char* rloc=m->getAttr("locus");
if (rloc!=NULL && startsWith(rloc, "RLOC_")) {
m->removeAttr("locus", rloc);
}
/*
if (m->exons.Count()==0 && m->children.Count()==0) {
//a non-mRNA feature with no subfeatures
//add a dummy exon just to have the generic exon checking work
m->addExon(m->start,m->end);
}
*/
if (forceExons) { // && m->children.Count()==0) {
m->exon_ftype_id=gff_fid_exon;
}
//GList<GffObj> gfadd(false,false); -- for gf_validate()?
if (gf_validate!=NULL && !(*gf_validate)(m, NULL)) {
continue;
}
m->isUsed(true); //so the gffreader won't destroy it
int i=-1;
GenomicSeqData f(m->gseq_id);
GenomicSeqData* gdata=NULL;
if (seqdata.Found(&f,i)) gdata=seqdata[i];
else { //entry not created yet for this genomic seq
gdata=new GenomicSeqData(m->gseq_id);
seqdata.Add(gdata);
}
/*
for (int k=0;k<gfadd.Count();k++) {
bool keep=placeGf(gfadd[k], gdata, doCluster, doCollapseRedundant, matchAllIntrons, fuzzSpan);
if (!keep) {
gfadd[k]->isUsed(false);
//DEBUG
GMessage("Feature %s(%d-%d) is going to be discarded..\n",gfadd[k]->getID(), gfadd[k]->start, gfadd[k]->end);
}
}
*/
bool keep=placeGf(m, gdata, doCluster, doCollapseRedundant, matchAllIntrons, fuzzSpan);
if (!keep) {
m->isUsed(false);
//DEBUG
//GMessage("Feature %s(%d-%d) is going to be discarded..\n",m->getID(), m->start, m->end);
}
} //for each read gffObj
//if (verbose) GMessage(" .. %d records from %s clustered into loci.\n", gffr->gflst.Count(), fname.chars());
if (f!=stdin) { fclose(f); f=NULL; }
delete gffr;
}
