/**********************************************************************
*
* MapLocToAnchor(annot, slp, anchor)
* map the current slp to a position on the anchor Bioseq
* annot: Seq-annot that may contain the alignment of the consistent markers
* slp: the current Bioseq
* anchor_id: the Seq-id for the anchor Bioseq, that is the sequece map
*
************************************************************************/
SeqLocPtr MapLocToAnchor(SeqAnnotPtr annot, SeqLocPtr slp, BioseqPtr anchor_bsp)
{
Int2 type;
Int4Ptr x_a, x;
Uint2 num;
SeqIdPtr anchor_id;
SeqLocPtr t_slp;
Int4 start, stop;
SeqAlignPtr align;
if(annot == NULL || slp == NULL || anchor_bsp == NULL)
return NULL;
if(slp->choice != SEQLOC_PNT && slp->choice != SEQLOC_INT)
return NULL;
anchor_id = SeqIdFindBest(anchor_bsp->id, SEQID_GI);
if(anchor_id == NULL)
anchor_id = anchor_bsp->id;
while(annot)
{
if(annot->type == 2)
{
type = GetEquivAlignType(annot);
if(type == 1) /*this is consistent*/
{
align = annot->data;
if(!get_anchor_coordinates(align, anchor_id, SeqLocId(slp), &x_a, &x, &num))
return NULL;
if(slp->choice == SEQLOC_INT)
{
start = find_this_position_by_anchor (x_a, x, num, SeqLocStart(slp), anchor_bsp->length);
if(SeqLocStart(slp) != SeqLocStop(slp))
stop = find_this_position_by_anchor (x_a, x, num, SeqLocStop(slp), anchor_bsp->length);
else
stop = start;
t_slp = SeqLocIntNew(start, stop, Seq_strand_plus, anchor_id);
}
else
{
start = SeqLocStart(slp);
start = find_this_position_by_anchor (x_a, x, num, start, anchor_bsp->length);
t_slp = SeqLocPntNew(start, Seq_strand_plus, anchor_id, FALSE);
}
MemFree(x_a);
MemFree(x);
return t_slp;
}
}
annot = annot->next;
}
return NULL;
}
extern SeqLocPtr CheckOverlap (SeqLocPtr slp, Int4 ctermsig)
{
SeqLocPtr slphead = NULL, slptmp;
Int4 start;
if (ctermsig == 0)
return slp;
while (slp != NULL)
{
start = SeqLocStop (slp);
if (start < ctermsig)
{
slptmp = slp->next;
slp->next = NULL;
SeqLocFree (slp);
slp = slptmp;
continue;
}
if (slphead == NULL)
slphead = slp;
slp = slp->next;
}
return slphead;
}
extern DustRegionPtr DustSeqLoc (SeqLocPtr slp,
DustDataPtr ddp)
{
BioseqPtr bsp;
Int4 start, end;
DustRegionPtr drp;
if (slp == NULL || ddp == NULL)
return NULL;
if (slp->choice != SEQLOC_INT)
{
ErrPostEx (SEV_ERROR, 2, 1,
"Will only dust a single SeqLoc interval");
ErrShow ();
return NULL;
}
if ((bsp = BioseqLockById (SeqLocId (slp))) == NULL)
{
ErrPostEx (SEV_ERROR, 2, 5, "Bioseq lock failure");
ErrShow ();
return NULL;
}
start = SeqLocStart (slp);
end = SeqLocStop (slp);
drp = DustBioseq (bsp, start, end, ddp);
BioseqUnlock (bsp);
return drp;
}
extern void RemoveInternalOrfs (SeqLocPtr PNTR slpFound)
{
SeqLocPtr slp1, slp2, slp = NULL;
SeqIdPtr id;
Int4 start1, stop1, start2, stop2;
Boolean flagInternal;
slp1 = *slpFound;
while (slp1 != NULL)
{
start1 = SeqLocStart (slp1);
stop1 = SeqLocStop (slp1);
flagInternal = FALSE;
slp2 = *slpFound;
while (slp2 != NULL)
{
start2 = SeqLocStart (slp2);
stop2 = SeqLocStop (slp2);
if ((start1 > start2 && start1 < stop2) &&
(stop1 > start2 && stop1 < stop2))
{
flagInternal = TRUE;
break;
}
slp2 = slp2->next;
}
if (!flagInternal)
SeqLocLink (&slp, SeqLocDup (slp1));
slp1 = slp1->next;
}
slp1 = *slpFound;
while (slp1 != NULL)
{
slp2 = slp1->next;
id = SeqLocId (slp1);
if (id != NULL)
id->next = SeqIdSetFree (id->next);
SeqLocFree (slp1);
slp1 = slp2;
}
*slpFound = slp;
return;
}
static Int4 FindNecessaryBioseqLength (SeqFeatPtr sfp)
{
Int4 len = 0;
while (sfp != NULL) {
len = MAX (SeqLocStop (sfp->location), len);
len = MAX (SeqLocStart (sfp->location), len);
sfp = sfp->next;
}
return len + 1;
}
extern Boolean SeqLocMatch (SeqLocPtr slplist, SeqLocPtr slpnew)
{
Int4 start1, stop1, start2, stop2;
if (slpnew == NULL || slplist == NULL)
{
return FALSE;
}
while (slplist != NULL)
{
start1 = SeqLocStart (slpnew);
stop1 = SeqLocStop (slpnew);
start2 = SeqLocStart (slplist);
stop2 = SeqLocStop (slplist);
if (start1 == start2 && stop1 == stop2)
return TRUE;
slplist = slplist->next;
}
return FALSE;
}
extern Int4 EndOfSig (SeqLocPtr slp)
{
Int4 stop, ctermsig = 0;
while (slp != NULL)
{
stop = SeqLocStop (slp);
if (stop > ctermsig)
ctermsig = stop;
slp = slp->next;
}
return ctermsig;
}
/****************************************************************************
*
* get_anchor_coordinates(h_align, anchor_id, sip, x_anchor_pos, x_pos, num)
*
* load the positions of framework marker of the current sequence and its
* corresponding positions in the anchor map (normally the NCBI sequence) into
* two arays to extrapolate the positions for map integration
* h_align: the alignment of consistent markers (a.k.a good alignment)
* anchor_id: the Seq-id for the anchor map (normally, the NCBI sequence map)
* sip: the Seq-id for the current sequence
* x_anchor_pos: the array to store the positions on the anchor map
* x_pos: the array to store the positions on the current map. each
* member of x_anchor_pos and x_pos is a matching pair
* both arrays are ordered
* num: the total number of framework markers in the current map.
* This is also the size of x_anchor_pos and x_pos
*
* return TRUE for success and FALSE for fail
*
****************************************************************************/
Boolean get_anchor_coordinates(SeqAlignPtr h_align, SeqIdPtr anchor_id, SeqIdPtr sip, Int4Ptr PNTR x_anchor_pos, Int4Ptr PNTR x_pos, Uint2Ptr num)
{
StdSegPtr ssp;
SeqLocPtr slp;
SeqIdPtr id;
Int4 n, i, j;
Int4 a_pos, t_pos;
SeqAlignPtr align;
Int4Ptr anchor_pos, pos;
Boolean change;
Int4 temp;
*x_anchor_pos = NULL;
*x_pos = NULL;
*num = 0;
align = h_align;
if(align == NULL)
return FALSE;
/* count the number of the consistent markers for the
current sip */
n = 0;
while(align)
{
if(align->segtype == 3)
{ /*Std-segs*/
ssp = align->segs;
for(slp = ssp->loc; slp != NULL; slp = slp->next)
{
id = SeqLocId(slp);
if(SeqIdForSameBioseq(id, sip))
{
++n;
break;
}
}
}
align = align->next;
}
if(n == 0)
return FALSE;
anchor_pos = MemNew((size_t)n * sizeof(Int4));
pos = MemNew((size_t)n * sizeof(Int4));
/*load the data*/
n = 0;
align = h_align;
while(align)
{
if(align->segtype == 3)
{
ssp = align->segs;
a_pos = -1;
t_pos = -1;
for(slp = ssp->loc; slp != NULL; slp = slp->next)
{
id = SeqLocId(slp);
if(SeqIdForSameBioseq(id, sip))
t_pos = (SeqLocStart(slp) + SeqLocStop(slp))/2;
else if(SeqIdForSameBioseq(id, anchor_id))
a_pos = SeqLocStart(slp);
}
/*each time, load a matching pair*/
if(t_pos >= 0 && a_pos >=0)
{
anchor_pos[n] = a_pos;
pos[n] = t_pos;
++n;
}
}
align = align->next;
}
/*sort the array*/
change = TRUE;
for(i = 0; i<n-1 && change == TRUE; ++i)
{
change = FALSE;
for(j = 0; j<n-i-1; ++j)
{
if(anchor_pos[j] > anchor_pos[j+1])
{
change = TRUE;
temp = anchor_pos[j+1];
anchor_pos[j+1] = anchor_pos[j];
anchor_pos[j] = temp;
temp = pos[j+1];
pos[j+1] = pos[j];
pos[j] = temp;
}
}
}
/*check the linear relationship between anchor_pos and pos*/
temp = pos[0];
for(i = 1, j= 1; i<n; ++i)
{
if(pos[i] >= temp)
{
temp = pos[i];
pos[j] = temp;
anchor_pos[j] = anchor_pos[i];
++j;
}
}
*x_anchor_pos = anchor_pos;
*x_pos = pos;
*num = (Uint2)j;
return TRUE;
}
/******************************************************************
*
* aa_to_dnaloc(sfp, aa_start, aa_stop)
* map the amino acid sequence to a list of Seq-locs in the
* DNA sequence
*
******************************************************************/
NLM_EXTERN SeqLocPtr aa_to_dnaloc(SeqFeatPtr sfp, Int4 aa_start, Int4 aa_stop)
{
Int4 frame_offset, start_offset; /*for determine the reading frame*/
SeqLocPtr slp = NULL;
CdRegionPtr crp;
SeqLocPtr dna_loc, loc; /*for the dna location*/
Boolean is_end; /**is the end for process reached?**/
Int4 p_start=0, p_stop=0; /**protein start & stop in defined
corresponding CdRegion Seq-loc**/
Int4 cur_pos; /**current protein position in process**/
Int4 cd_len; /**length of the cDNA for the coding region**/
Boolean is_new; /**Is cur_pos at the begin of new exon?**/
Boolean end_partial; /*the end of aa is a partial codon*/
Int4 d_start, d_stop; /*the start and the stop of the DNA sequence*/
Int4 offset; /*offset from the start of the current exon*/
Int4 aa_len;
Uint1 strand;
if(sfp->data.choice !=3)
return NULL;
crp = sfp->data.value.ptrvalue;
if(!crp)
return NULL;
if(crp->frame>0)
frame_offset = crp->frame-1;
else
frame_offset = 0;
start_offset = frame_offset;
cur_pos= aa_start;
cd_len = 0;
is_end = FALSE;
p_start = 0;
slp = NULL;
dna_loc= NULL;
while(!is_end && ((slp = SeqLocFindNext(sfp->location, slp))!=NULL))
{
cd_len += SeqLocLen(slp);
end_partial = ((cd_len - start_offset)%3 != 0);
p_stop = (cd_len - start_offset)/3 -1;
if(end_partial)
++p_stop;
if(p_stop > aa_stop || (p_stop == aa_stop && !end_partial))
{
p_stop = aa_stop; /**check if the end is reached**/
is_end = TRUE;
}
if(p_stop >= cur_pos) /*get the exon*/
{
is_new = (p_start == cur_pos); /*start a new exon?*/
if(is_new) /**special case of the first partial**/
offset = 0;
else
{
if(frame_offset && p_start >0)
++p_start;
offset = 3*(cur_pos - p_start) + frame_offset;
}
strand = SeqLocStrand(slp);
if(strand == Seq_strand_minus)
d_start = SeqLocStop(slp) - offset;
else
d_start = SeqLocStart(slp) + offset;
d_stop = d_start;
aa_len = MIN(p_stop, aa_stop) - cur_pos +1;
if(strand == Seq_strand_minus)
{
d_stop -= 3*aa_len;
d_stop = MAX(d_stop, SeqLocStart(slp));
loc = SeqLocIntNew(d_stop, d_start, strand, SeqLocId(slp));
}
else
{
d_stop += 3*aa_len;
d_stop = MIN(d_stop, SeqLocStop(slp));
loc = SeqLocIntNew(d_start, d_stop, strand, SeqLocId(slp));
}
ValNodeLink(&dna_loc, loc);
if(end_partial)
cur_pos = p_stop;
else
cur_pos = p_stop+1;
}
if(end_partial)
p_start = p_stop;
else
p_start = p_stop +1;
frame_offset = (cd_len - start_offset)%3;
if(frame_offset >0)
frame_offset = 3-frame_offset;
}/**end of while(slp && !is_end) **/
return dna_loc;
}
/******************************************************************
*
* aa_to_codon(sfp, aa_start, aa_stop)
* generate a list of CodonVecotr to show the codons of an
* amino acid sequence
* sfp: the Seq-feat for cds
* aa_start: the start position of protein sequence
* aa_stop the stop position of protein sequence
*
******************************************************************/
NLM_EXTERN ValNodePtr aa_to_codon(SeqFeatPtr sfp, Int4 aa_start, Int4 aa_stop)
{
BioseqPtr bsp;
Int4 frame_offset, start_offset;
SeqLocPtr slp = NULL;
SeqLocPtr cdloc;
CdRegionPtr crp;
Uint1 frame;
Boolean is_end; /**is the end for process reached?**/
Int4 p_start=0, p_stop=0; /**protein start & stop in defined
corresponding CdRegion Seq-loc**/
Int4 line_len;
Int4 cur_pos; /**current protein position in process**/
Int4 cd_len; /**length of the cDNA for the coding region**/
Int2 i, j;
Int2 k, n;
CharPtr PNTR buf;
Boolean is_new; /**Is cur_pos at the begin of new Seq-loc?**/
CharPtr temp;
SeqPortPtr spp;
Uint1 residue;
Boolean end_partial;
Int4 d_start, seq_pos;
Int2 pos;
ValNodePtr head= NULL;
CodonVectorPtr cvp;
Boolean prt_stop_codon;
Uint2 exon;
if(sfp->data.choice !=3)
return NULL;
crp = sfp->data.value.ptrvalue;
if(!crp)
return NULL;
frame = crp->frame;
cdloc = sfp->location;
if(cdloc == NULL )
return NULL;
if(frame>0)
frame_offset = frame-1;
else
frame_offset = 0;
start_offset = frame_offset;
prt_stop_codon = (aa_stop == SeqLocStop(sfp->product));
line_len = (aa_stop - aa_start + 1) + 1;
/* +1 for the possible partial start codon*/
if(prt_stop_codon)/*can be either as a stop codon or partial stop*/
++line_len;
buf = MemNew((size_t)3 * sizeof(CharPtr));
for(i =0; i<3; ++i)
buf[i] = MemNew((size_t)(line_len + 1) * sizeof (Char));
cur_pos= aa_start;
cd_len = 0;
is_end = FALSE;
p_start = 0;
slp = NULL;
exon = 0;
while(!is_end && ((slp = SeqLocFindNext(cdloc, slp))!=NULL))
{
++exon;
cd_len += SeqLocLen(slp);
end_partial = ((cd_len - start_offset)%3 != 0);
p_stop = (cd_len - start_offset)/3 -1;
if(end_partial)
++p_stop;
if(p_stop > aa_stop || (p_stop == aa_stop && !end_partial))
{
p_stop = aa_stop; /**check if the end is reached**/
is_end = TRUE;
}
if(p_stop >= cur_pos) /*get the exon*/
{
bsp = BioseqLockById(SeqLocId(slp));
if(bsp)
{
is_new = (p_start == cur_pos); /*start a new exon?*/
cvp = MemNew(sizeof(CodonVector));
cvp->sip = SeqIdDup(find_sip(bsp->id));
cvp->strand = SeqLocStrand(slp);
cvp->exonCount = exon;
if(is_new)
{
if(frame_offset == 0)
cvp->frame = 0;
else
cvp->frame = 3- (Uint1)frame_offset;
}
else
cvp->frame = 0;
if(cur_pos==0 && frame_offset > 0) /*partial start codon*/
cvp->aa_index = 0;
else
cvp->aa_index = 1;
if(is_new) /**special case of the first partial**/
d_start = SeqLocStart(slp);
else
{
if(frame_offset && p_start >0)
++p_start;
d_start = SeqLocStart(slp) + 3*(cur_pos - p_start) + frame_offset;
}
/**p_start is the start position of aa in the current Seq-loc
cur_pos is the current aa that is in process. The offset will
help to located the position on the DNA Seq-loc for translation
d_start is the position of the starting DNA in the coordinates
of DNA segment, used for mark the sequence
**/
seq_pos = d_start - SeqLocStart(slp); /**the pos in spp**/
if(SeqLocStrand(slp)== Seq_strand_minus)
d_start = SeqLocStop(slp) - seq_pos;
cvp->dna_pos = d_start;
n = (Int2)cur_pos - (Int2)aa_start + cvp->aa_index; /*position in buffer*/
for(i =0; i<3; ++i)
make_empty(buf[i], (Int2)line_len);
spp = SeqPortNewByLoc(slp, Seq_code_iupacna);
SeqPortSeek(spp, seq_pos, SEEK_SET);
/**store the partial codons**/
if(is_new && frame_offset > 0)
{
k = (Int2)frame_offset;
while(k > 0)
{
residue = SeqPortGetResidue(spp);
temp = buf[3-k]; /**the position**/
pos = n;
temp[pos] = TO_LOWER(residue);
--k;
}
++n;
if(cur_pos!=0)
++cur_pos;
}
/**load the codons**/
k =0;
while((residue = SeqPortGetResidue(spp)) != SEQPORT_EOF && cur_pos <= p_stop)
{
j= (Uint1)k%3;
temp = buf[j];
temp[n] = TO_LOWER(residue);
if(j ==2)
{ /**the last base**/
++n;
if(!prt_stop_codon|| !is_end) /*for the last codon*/
/**prt_end controls to print the whole loc**/
++cur_pos;
}
++k;
} /**end of while**/
SeqPortFree(spp);
for(i =0; i<3; ++i)
cvp->buf[i] = StringSave(buf[i]);
ValNodeAddPointer(&head, 0, (Pointer)cvp);
BioseqUnlock(bsp);
}/*end of if(bsp)*/
}/**end of if for matched intervals**/
if(end_partial)
p_start = p_stop;
else
p_start = p_stop +1;
frame_offset = (cd_len - start_offset)%3;
if(frame_offset >0)
frame_offset = 3-frame_offset;
}/**end of while(slp && !is_end) **/
for(i=0; i<3; ++i)
MemFree(buf[i]);
MemFree(buf);
return head;
}
static void ConsignProc (ButtoN b)
{
XOSPtr xosp;
XISPtr xisp;
ComPatPtr cpp, cpph;
ValNodePtr orflist;
SeqLocPtr slp, slpn;
Int4 start, stop;
Uint1 strand;
SeqPortPtr spp;
Uint1Ptr aaseq;
Int4 ntpos, aapos;
Uint1 cdn[3];
SeqAlignPtr sap, sapn;
FloatHi probcut;
Int4 clustmin, findmin;
Int4 i, n, endpos, XLength, XScale, shift;
Int4 iframe, frame, top, orftop[6];
FloatHiPtr score, expandscore;
FloatHi maxscore;
Int4Ptr tableGlobal;
SeqGraphPtr sgp, sgpn;
WindoW w;
VieweR v;
GrouP g;
SegmenT seg;
GraphSentPtr gsp;
Char numberbuffer[32];
if ((xosp = (XOSPtr) GetObjectExtra (b)) == NULL)
return;
if (xosp->bsp == NULL)
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 101, "No Bioseq");
ErrShow ();
return;
}
WatchCursor ();
cpph = cpp = ReadPrositePattern (xosp->pattern_file, TRUE, -1, NULL, NULL);
if (cpph == NULL)
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 101,
"read failed %s", xosp->pattern_file);
ErrShow ();
ArrowCursor ();
return;
}
xosp->orflist = GetOrfList (xosp->bsp, (Int2) (xosp->orfcut));
xosp->orflist = ClearNonMetOrfs (xosp->orflist);
orflist = xosp->orflist;
while (orflist != NULL)
{
slp = (SeqLocPtr) orflist->data.ptrvalue;
if (slp->choice == 0)
{
orflist = orflist->next;
continue;
}
if (slp->choice == SEQLOC_MIX)
slp = (SeqLocPtr) slp->data.ptrvalue;
start = SeqLocStart (slp);
stop = SeqLocStop (slp);
strand = SeqLocStrand (slp);
if (strand != Seq_strand_both)
strand = Seq_strand_both;
if (stop - start + 1 >= xosp->minimumseed)
{
spp = SeqPortNew (xosp->bsp, start, stop, strand, Seq_code_ncbi4na);
aaseq = (Uint1Ptr) MemNew ((size_t)
(sizeof (Uint1) * (((stop-start)/3)+2)));
ntpos = start;
aapos = 0;
while (ntpos < start+3)
{
cdn[0] = SeqPortGetResidue (spp);
ntpos++;
cdn[1] = SeqPortGetResidue (spp);
ntpos++;
cdn[2] = SeqPortGetResidue (spp);
ntpos++;
aaseq[aapos] = AAForCodon (cdn, xosp->gcdi);
aapos++;
}
while (ntpos <= stop)
{
cdn[0] = SeqPortGetResidue (spp);
ntpos++;
cdn[1] = SeqPortGetResidue (spp);
ntpos++;
cdn[2] = SeqPortGetResidue (spp);
ntpos++;
aaseq[aapos] = AAForCodon (cdn, xosp->gcd);
aapos++;
}
SeqPortFree (spp);
aaseq[aapos] = 0;
cpp = cpph;
while (cpp != NULL)
{
sap = PatternMatch (aaseq, 0, Seq_strand_plus, SeqLocId (slp),
cpp, 0, Seq_strand_unknown, FALSE);
if (sap != NULL)
break;
cpp = cpp->nextpattern;
}
MemFree (aaseq);
if (sap != NULL)
{
SeqLocLink (&(xosp->slps), SeqLocDup (slp));
}
while (sap != NULL)
{
sapn = sap->next;
SeqAlignFree (sap);
sap = sapn;
}
}
orflist = orflist->next;
}
ComPatFree (cpph);
orflist = xosp->orflist;
while (orflist != NULL)
{
slp = (SeqLocPtr) orflist->data.ptrvalue;
if (slp->choice > 0)
SeqLocLink (&(xosp->slpa), SeqLocDup (slp));
while (slp != NULL)
{
slpn = slp->next;
SeqLocFree (slp);
slp = slpn;
}
orflist->data.ptrvalue = NULL;
orflist = orflist->next;
}
xosp->orflist = ValNodeFree (xosp->orflist);
probcut = xosp->probcut;
clustmin = xosp->clustmin;
findmin = xosp->findmin;
xosp->slpb = FindSimilarBiasOrfs (xosp->sep, probcut, clustmin, findmin,
xosp->slps, xosp->slpa);
tableGlobal = CodonTableFromSeqLoc (xosp->bsp, xosp->slpb);
seg = NULL;
top = 0;
xisp = (XISPtr) MemNew (sizeof (XIS));
frame = 0;
for (iframe = 0; iframe < 6; iframe++)
{
endpos = (xosp->bsp->length + 3 - frame - xosp->window) / 3;
if (iframe < 3)
score = BiasScoreBioseq (xosp->bsp, tableGlobal, xosp->window,
frame, Seq_strand_plus);
else
score = BiasScoreBioseq (xosp->bsp, tableGlobal, xosp->window,
frame, Seq_strand_minus);
maxscore = 0.0;
for (i = 0; i < endpos; i++)
if (score[i] > maxscore)
maxscore = score[i];
expandscore = (FloatHiPtr) MemNew (sizeof (FloatHi) * xosp->bsp->length);
for (i = 0; i < xosp->window/2; i++)
expandscore[i] = maxscore;
n = 0;
while (i < xosp->bsp->length)
{
if (n < endpos)
expandscore[i] = score[n];
else
expandscore[i] = maxscore;
i++;
if (i%3 == 0)
n++;
}
MemFree (score);
score = expandscore;
sgp = SeqGraphNew ();
if (xisp->sgp == NULL)
{
xisp->sgp = sgp;
}
else
{
sgpn = xisp->sgp;
while (sgpn->next != NULL)
sgpn = sgpn->next;
sgpn->next = sgp;
}
XLength = xosp->bsp->length;
if (XLength > 1200)
XLength = 1200;
XScale = xosp->bsp->length / XLength;
if (xosp->bsp->length % XLength != 0)
XScale++;
sgp->loc = SeqLocIntNew (0, xosp->bsp->length-1, xosp->bsp->strand,
xosp->bsp->id);
sgp->flags[2] = 1;
sgp->numval = xosp->bsp->length;
sgp->values = (Pointer) score;
sgp->max.realvalue = maxscore;
sgp->min.realvalue = 0.0;
sgp->flags[1] = 1;
sgp->a = 4.0;
sgp->b = 0.0;
if (seg == NULL)
seg = CreatePicture ();
if ((gsp = AddGraphSentinelToPicture (sgp, xosp->bsp, seg, 0,
top, 0, NULL)) != NULL)
{
sprintf (numberbuffer, "%ld", 1L);
AddLabel (seg, gsp->box.left, gsp->bottom-20,
numberbuffer, SMALL_TEXT, 0, MIDDLE_CENTER, 0);
sprintf (numberbuffer, "%ld", (long) xosp->bsp->length);
AddLabel (seg, gsp->box.left+xosp->bsp->length, gsp->bottom-20,
numberbuffer, SMALL_TEXT, 0, MIDDLE_CENTER, 0);
}
shift = (Int4) (maxscore*sgp->a);
orftop[iframe] = top - shift - 38;
top -= (shift+56);
frame++;
if (frame == 3)
{
top -= 24;
frame = 0;
}
}
frame = 0;
for (iframe = 0; iframe < 6; iframe++)
{
if (iframe < 3)
strand = Seq_strand_plus;
else
strand = Seq_strand_minus;
shift = 0;
if (xosp->slpa != NULL)
{
AddOrfClass (xosp->slpa, seg, orftop, iframe, frame,
shift, strand, YELLOW_COLOR, 5);
shift += 4;
}
if (xosp->slpk != NULL)
{
AddOrfClass (xosp->slpk, seg, orftop, iframe, frame,
shift, strand, GREEN_COLOR, 5);
shift += 4;
}
if (xosp->slpb != NULL)
{
AddOrfClass (xosp->slpb, seg, orftop, iframe, frame,
shift, strand, BLUE_COLOR, 5);
shift += 4;
}
if (xosp->slps != NULL)
{
AddOrfClass (xosp->slps, seg, orftop, iframe, frame,
shift, strand, RED_COLOR, 5);
}
frame++;
if (frame == 3)
frame = 0;
}
MemFree (tableGlobal);
start = 20;
stop = 20 + (50*XScale);
top = orftop[5] - 40;
if (xosp->slpa != NULL)
{
top -= 12;
AddAttribute (seg, (COLOR_ATT|STYLE_ATT|SHADING_ATT|WIDTH_ATT),
YELLOW_COLOR, SOLID_LINE, SOLID_SHADING, 5,
0);
AddLine (seg, start, top, stop, top, FALSE, 0);
AddAttribute (seg, (COLOR_ATT|STYLE_ATT|SHADING_ATT|WIDTH_ATT),
BLACK_COLOR, SOLID_LINE, SOLID_SHADING, STD_PEN_WIDTH,
0);
AddLabel (seg, stop+(20*XScale), top,
"All Met-init'd ORFs equal to or greater than 50 codons",
SMALL_TEXT, 0, MIDDLE_RIGHT, 0);
}
if (xosp->slpk != NULL)
{
top -= 12;
AddAttribute (seg, (COLOR_ATT|STYLE_ATT|SHADING_ATT|WIDTH_ATT),
GREEN_COLOR, SOLID_LINE, SOLID_SHADING, 5,
0);
AddLine (seg, start, top, stop, top, FALSE, 0);
AddAttribute (seg, (COLOR_ATT|STYLE_ATT|SHADING_ATT|WIDTH_ATT),
BLACK_COLOR, SOLID_LINE, SOLID_SHADING, STD_PEN_WIDTH,
0);
AddLabel (seg, stop+(20*XScale), top, "Annotated (reported) ORFs",
SMALL_TEXT, 0, MIDDLE_RIGHT, 0);
}
if (xosp->slpb != NULL)
{
top -= 12;
AddAttribute (seg, (COLOR_ATT|STYLE_ATT|SHADING_ATT|WIDTH_ATT),
BLUE_COLOR, SOLID_LINE, SOLID_SHADING, 5,
0);
AddLine (seg, start, top, stop, top, FALSE, 0);
AddAttribute (seg, (COLOR_ATT|STYLE_ATT|SHADING_ATT|WIDTH_ATT),
BLACK_COLOR, SOLID_LINE, SOLID_SHADING, STD_PEN_WIDTH,
0);
AddLabel (seg, stop+(20*XScale), top, "Similar codon usage bias ORFs to seed ORFs",
SMALL_TEXT, 0, MIDDLE_RIGHT, 0);
}
if (xosp->slps != NULL)
{
top -= 12;
AddAttribute (seg, (COLOR_ATT|STYLE_ATT|SHADING_ATT|WIDTH_ATT),
RED_COLOR, SOLID_LINE, SOLID_SHADING, 5,
0);
AddLine (seg, start, top, stop, top, FALSE, 0);
AddAttribute (seg, (COLOR_ATT|STYLE_ATT|SHADING_ATT|WIDTH_ATT),
BLACK_COLOR, SOLID_LINE, SOLID_SHADING, STD_PEN_WIDTH,
0);
AddLabel (seg, stop+(20*XScale), top, "Pattern match seed ORFs",
SMALL_TEXT, 0, MIDDLE_RIGHT, 0);
}
xisp->picture = seg;
w = FixedWindow (10, 10, 640, 720, "Consign", CloseGraphWindowProc);
SetObjectExtra (w, xisp, CleanUpGraphWindow);
g = HiddenGroup (w, -1, 0, NULL);
v = CreateViewer (g, 560, 640, TRUE, TRUE);
AttachPicture (v, seg, INT4_MIN, INT4_MAX, UPPER_LEFT, XScale, 1, NULL);
PushButton (g, "Close", CloseGraphWindowButton);
RealizeWindow (w);
ArrowCursor ();
Show (w);
return;
}
static void AddOrfClass (SeqLocPtr slp, SegmenT seg,
Int4Ptr orftop, Int4 iframe,
Int4 frame, Int4 shift, Uint1 strand,
Uint1Ptr orfcolor, Uint1 orfwidth)
{
SeqLocPtr slpThis, slpHead;
Uint1 strandThis;
Int4 start, stop, startorig, startthis, stopthis;
Int4 len, runlen, extraframe;
Int4 top, topold, startold, stopold;
Int4 framethis;
Boolean flagRTL;
while (slp != NULL)
{
if (slp->choice == SEQLOC_MIX)
slpThis = (SeqLocPtr) slp->data.ptrvalue;
else
slpThis = slp;
strandThis = SeqLocStrand (slpThis);
if (strandThis == strand ||
(strandThis == Seq_strand_unknown && strand == Seq_strand_plus))
{
flagRTL = TRUE;
runlen = 0;
startold = -1;
stopold = -1;
topold = -1;
slpHead = slpThis;
if (strandThis != Seq_strand_plus &&
strandThis != Seq_strand_unknown)
{
if (slp->choice == SEQLOC_MIX)
{
if (slpHead->next != NULL)
{
if (SeqLocStart (slpHead->next) > SeqLocStart (slpHead))
{
flagRTL = FALSE;
while (slpHead->next != NULL)
slpHead = slpHead->next;
}
}
}
}
if (strandThis != Seq_strand_plus &&
strandThis != Seq_strand_unknown)
startorig = SeqLocStop (slpHead) - 2;
else
startorig = SeqLocStart (slpHead);
if (startorig > 0 && startorig%3 == frame)
{
while (slpThis != NULL)
{
start = SeqLocStart (slpThis);
stop = SeqLocStop (slpThis);
if (strandThis != Seq_strand_plus &&
strandThis != Seq_strand_unknown)
{
startthis = SeqLocStop (slpThis) - 2;
stopthis = SeqLocStart (slpThis) - 2;
}
else
{
startthis = SeqLocStart (slpThis);
stopthis = SeqLocStop (slpThis);
}
framethis = startthis % 3;
extraframe = runlen % 3;
framethis += extraframe;
framethis %= 3;
if (iframe > 2)
framethis = 3 + framethis;
top = orftop[framethis] - shift;
len = stopthis - startthis;
if (len < 0)
len *= -1;
len += 1;
runlen += len;
if (stopold >= 0)
{
AddAttribute (seg, (COLOR_ATT|STYLE_ATT|SHADING_ATT|WIDTH_ATT),
orfcolor, SOLID_LINE, SOLID_SHADING,
STD_PEN_WIDTH, 0);
if (strand == Seq_strand_minus && flagRTL)
AddLine (seg, startold, topold, stop, top, FALSE, 0);
else
AddLine (seg, stopold, topold, start, top, FALSE, 0);
}
AddAttribute (seg, (COLOR_ATT|STYLE_ATT|SHADING_ATT|WIDTH_ATT),
orfcolor, SOLID_LINE, SOLID_SHADING,
orfwidth, 0);
AddLine (seg, start, top, stop, top, FALSE, 0);
AddAttribute (seg, (COLOR_ATT|STYLE_ATT|SHADING_ATT|WIDTH_ATT),
BLACK_COLOR, SOLID_LINE, SOLID_SHADING,
STD_PEN_WIDTH, 0);
startold = start;
stopold = stop;
topold = top;
if (slp->choice != SEQLOC_MIX)
break;
slpThis = slpThis->next;
}
}
}
slp = slp->next;
}
return;
}
static int LIBCALLBACK
MegaBlastPrintEndpoints(VoidPtr ptr)
{
BlastSearchBlkPtr search = (BlastSearchBlkPtr) ptr;
CharPtr subject_descr;
SeqIdPtr sip, query_id;
CharPtr query_buffer, title;
CharPtr subject_buffer;
Int4 query_length, q_start, q_end, q_shift=0, s_shift=0;
Int4 subject_end;
Int4 hsp_index;
Boolean numeric_sip_type = FALSE;
BLAST_HSPPtr hsp;
Int2 context;
Char context_sign;
Int4 subject_gi, score;
FILE *fp = (FILE *) search->output;
if (search->current_hitlist == NULL || search->current_hitlist->hspcnt <= 0) {
search->subject_info = BLASTSubjectInfoDestruct(search->subject_info);
return 0;
}
if (search->rdfp)
readdb_get_descriptor(search->rdfp, search->subject_id, &sip,
&subject_descr);
else
sip = SeqIdSetDup(search->subject_info->sip);
if (sip->choice != SEQID_GENERAL ||
StringCmp(((DbtagPtr)sip->data.ptrvalue)->db, "BL_ORD_ID")) {
if (search->pbp->mb_params->full_seqids) {
subject_buffer = (CharPtr) Malloc(BUFFER_LENGTH + 1);
SeqIdWrite(sip, subject_buffer, PRINTID_FASTA_LONG, BUFFER_LENGTH);
} else
numeric_sip_type = GetAccessionFromSeqId(SeqIdFindBest(sip, SEQID_GI),
&subject_gi, &subject_buffer);
} else {
DbtagPtr db_tag = (DbtagPtr) sip->data.ptrvalue;
if (db_tag->db &&
(!StringCmp(db_tag->db, "THC") ||
!StringICmp(db_tag->db, "TI")) &&
db_tag->tag->id != 0) {
subject_buffer = (CharPtr) Malloc(16);
sprintf(subject_buffer, "%ld", (long) db_tag->tag->id);
} else {
subject_buffer = StringTokMT(subject_descr, " \t", &subject_descr);
subject_descr = subject_buffer;
}
}
search->current_hitlist->hspcnt_max = search->current_hitlist->hspcnt;
/* Only for the two sequences case, get offset shift if subject
is a subsequence */
if (!search->rdfp && search->query_slp->next) {
s_shift = SeqLocStart(search->query_slp->next);
subject_end = SeqLocStop(search->query_slp->next);
} else {
s_shift = 0;
subject_end =
readdb_get_sequence_length(search->rdfp, search->subject_id);
}
/* Get offset shift if query is a subsequence */
q_shift = SeqLocStart(search->query_slp);
for (hsp_index=0; hsp_index<search->current_hitlist->hspcnt; hsp_index++) {
hsp = search->current_hitlist->hsp_array[hsp_index];
if (hsp==NULL || (search->pbp->cutoff_e > 0 &&
hsp->evalue > search->pbp->cutoff_e))
continue;
/* Correct query context is already found in BlastGetNonSumStatsEvalue */
context = hsp->context;
query_id = search->qid_array[context/2];
if (query_id == NULL) /* Bad hsp, something wrong */
continue;
hsp->context = context & 1;
query_length = search->query_context_offsets[context+1] -
search->query_context_offsets[context] - 1;
hsp->subject.end = hsp->subject.offset + hsp->subject.length;
if (hsp->context) {
hsp->query.end = query_length - hsp->query.offset;
hsp->query.offset =
hsp->query.end - hsp->query.length + 1;
context_sign = '-';
} else {
hsp->query.end = (++hsp->query.offset) + hsp->query.length - 1;
if (hsp->query.end > query_length) {
hsp->subject.end -= (hsp->query.end - query_length);
hsp->query.end = query_length;
}
context_sign = '+';
}
if (hsp->subject.end > subject_end) {
hsp->query.end -= (hsp->subject.end - subject_end);
hsp->subject.end = subject_end;
}
hsp->subject.offset++;
query_buffer = NULL;
if (query_id->choice == SEQID_LOCAL &&
search->pbp->mb_params->full_seqids) {
BioseqPtr query_bsp = BioseqLockById(query_id);
title = StringSave(BioseqGetTitle(query_bsp));
if (title)
query_buffer = StringTokMT(title, " ", &title);
else {
Int4 query_gi;
GetAccessionFromSeqId(query_bsp->id, &query_gi,
&query_buffer);
}
BioseqUnlock(query_bsp);
} else {
query_buffer = (CharPtr) Malloc(BUFFER_LENGTH + 1);
if (!search->pbp->mb_params->full_seqids)
SeqIdWrite(query_id, query_buffer, PRINTID_TEXTID_ACCESSION,
BUFFER_LENGTH);
else
SeqIdWrite(query_id, query_buffer, PRINTID_FASTA_LONG,
BUFFER_LENGTH);
}
if (search->pbp->gap_open==0 && search->pbp->gap_extend==0)
score = ((hsp->subject.length + hsp->query.length)*
search->sbp->reward / 2 - hsp->score) /
(search->sbp->reward - search->sbp->penalty);
else
score = hsp->score;
if (context_sign == '+') {
q_start = hsp->query.offset;
q_end = hsp->query.end;
} else {
q_start = hsp->query.end;
q_end = hsp->query.offset;
}
/* Adjust offsets if query is a subsequence, only for first query */
if (context < 2) {
q_start += q_shift;
q_end += q_shift;
}
hsp->subject.offset += s_shift;
hsp->subject.end += s_shift;
if (numeric_sip_type)
fprintf(fp, "'%ld'=='%c%s' (%d %d %d %d) %d\n", (long) subject_gi,
context_sign, query_buffer, hsp->subject.offset, q_start,
hsp->subject.end, q_end, score);
else
fprintf(fp, "'%s'=='%c%s' (%d %d %d %d) %d\n",
subject_buffer, context_sign, query_buffer,
hsp->subject.offset, q_start,
hsp->subject.end, q_end, score);
MemFree(query_buffer);
}
if (!numeric_sip_type && subject_buffer != subject_descr)
MemFree(subject_buffer);
MemFree(subject_descr);
sip = SeqIdSetFree(sip);
return 0;
}
Int2 Main (void)
{
Int2 argcount;
Boolean flagHaveNet;
Int4 gi;
SeqEntryPtr sep;
ComPatPtr cpp, cpph = NULL;
SeqAlignPtr sap, sapn;
StdSegPtr ssp;
SeqLocPtr slp, slpn;
Int4 start, stop;
FILE *fiop;
Char fastafile[256], namesfile[256];
CharPtr title;
CharPtr taxon;
FloatHi mw;
ValNodePtr namelist = NULL;
static CharPtr pattern_file = "ncbipros.dat";
static CharPtr protease_file = "ncbiendo.dat";
static CharPtr names_file = "ncbipnam.dat";
static GatherScope gs;
GatherScopePtr gsp;
static Gather_PBS gpbs;
Gather_PBSPtr gpbsp;
#ifndef NO_TAX_NET
Int4 i;
static Char taxdata[8];
static Gather_TaxId gti;
Gather_TaxIdPtr gtip;
#endif
#ifndef NO_TAX_NET
Int2 ia=4, ib=5, ic=6, id=7, ie=8, ig=9, ih=10, ii=11;
#else
Int2 ib=4, ic=5, id=6, ie=7, ig=8, ih=9, ii=10;
#endif
argcount = sizeof (myargs) / sizeof (Args);
if (!GetArgs ("ProSiteSearch", argcount, myargs))
return 1;
if (myargs[0].intvalue == 0 && myargs[1].strvalue == NULL)
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 100,
"No gi or FastA file given :: for help : srchaa -");
ErrShow ();
exit (1);
}
gsp = &gs;
#ifndef NO_TAX_NET
gtip = >i;
#endif
gpbsp = &gpbs;
MemSet ((Pointer) gsp, 0, sizeof (GatherScope));
MemSet ((Pointer) gsp->ignore, (int) (TRUE),
(size_t) (OBJ_MAX * sizeof (Boolean)));
gsp->ignore[OBJ_SEQDESC] = TRUE;
gsp->ignore[OBJ_BIOSEQ] = FALSE;
gpbsp->bsp = NULL;
gi = myargs[0].intvalue;
if (myargs[1].strvalue != NULL)
StrCpy (fastafile, myargs[1].strvalue);
else
fastafile[0] = '\0';
if (gi > 0)
{
if (!EntrezInit ("srchaa", FALSE, &flagHaveNet))
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 102,
"Entrez init failed");
ErrShow ();
exit (1);
}
}
#ifndef NO_TAX_NET
if (myargs[ia].intvalue)
{
if (!TaxArchInit ())
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 103,
"Taxonomy init failed");
ErrShow ();
exit (1);
}
}
#endif
fiop = NULL;
if (gi > 0)
{
sep = EntrezSeqEntryGet (gi, SEQENTRY_READ_BIOSEQ);
}
else
{
if ((fiop = FileOpen (fastafile, "r")) == NULL)
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 103,
"Failed to open FastA file: %s", fastafile);
ErrShow ();
exit (1);
}
sep = FastaToSeqEntry (fiop, FALSE);
}
if (sep == NULL)
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 104,
"No seqentry found");
ErrShow ();
exit (1);
}
while (sep != NULL)
{
gsp->ignore[OBJ_SEQDESC] = TRUE;
gsp->ignore[OBJ_BIOSEQ] = FALSE;
gpbsp->bsp = NULL;
gpbsp->gi = gi;
GatherSeqEntry (sep, (Pointer) gpbsp, GetBioseq, (Pointer) gsp);
taxon = NULL;
#ifndef NO_TAX_NET
if (myargs[ia].intvalue)
{
for (i = 0; i < 8; i++)
taxdata[i] = '-';
taxon = taxdata;
gsp->ignore[OBJ_SEQDESC] = FALSE;
gsp->ignore[OBJ_BIOSEQ] = TRUE;
gtip->taxid = 0;
GatherSeqEntry (sep, (Pointer) gtip, GetTaxId, (Pointer) gsp);
if (gtip->taxid != 0)
WhatOrg (gtip->taxid, taxon);
else
taxon = NULL;
}
#endif
if (gpbsp->bsp != NULL)
{
if (ISA_aa (gpbsp->bsp->mol))
{
if (cpph == NULL)
{
namesfile[0] = '\0';
if (myargs[id].intvalue)
StrCpy (namesfile, names_file);
if (myargs[ie].strvalue != NULL)
StrCpy (namesfile, myargs[ie].strvalue);
if (myargs[ig].strvalue != NULL)
{
if ((cpph = CompilePattern (myargs[ig].strvalue, 1)) != NULL)
StrCpy (cpph->name, "User Pattern");
}
else
{
namelist = ReadPatternNames (namesfile);
if (myargs[ib].intvalue)
cpph = ReadPrositePattern (protease_file,
(Boolean) myargs[2].intvalue,
myargs[3].intvalue,
taxon, NULL);
else
cpph = ReadPrositePattern (pattern_file,
(Boolean) myargs[2].intvalue,
myargs[3].intvalue,
taxon, namelist);
}
}
if (!(Boolean) myargs[ih].intvalue)
{
title = FastaTitle (gpbsp->bsp, ">", NULL);
printf ("%s\n", title);
MemFree (title);
}
cpp = cpph;
while (cpp != NULL)
{
sap = PatternMatchBioseq (gpbsp->bsp, cpp,
(Int4)myargs[ii].intvalue);
if (myargs[ib].intvalue)
{
printf (">%s\n", cpp->name);
if (sap != NULL)
printf (" Start Stop M.W.\n");
}
if (myargs[ib].intvalue)
{
EmbedMolecularWeightInfo (sap, gpbsp->bsp);
if (myargs[ic].intvalue)
URK_SeqAlignSortByMolWt (&sap);
while (sap != NULL)
{
ssp = (StdSegPtr) sap->segs;
slp = ssp->loc;
start = SeqLocStart (slp);
stop = SeqLocStop (slp);
mw = ssp->scores->value.realvalue;
printf ("%8ld %8ld %9.2f\n",
(long) start+1, (long) stop+1, mw);
sapn = sap->next;
SeqAlignFree (sap);
sap = sapn;
}
}
else
{
slp = MatchSa2Sl (&sap);
if (myargs[ih].intvalue && slp != NULL)
{
title = FastaTitle (gpbsp->bsp, ">", NULL);
printf ("%s\n", title);
MemFree (title);
}
while (slp != NULL)
{
start = SeqLocStart (slp);
stop = SeqLocStop (slp);
printf ("%8ld %8ld %s\n",
(long) start+1, (long) stop+1, cpp->name);
slpn = slp->next;
SeqLocFree (slp);
slp = slpn;
}
}
cpp = cpp->nextpattern;
}
}
else
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 106,
"Not a protein bioseq");
ErrShow ();
exit (1);
}
}
else
{
ErrPostEx (SEV_ERROR, TOP_ERROR, 105,
"No bioseq found");
ErrShow ();
exit (1);
}
SeqEntryFree (sep);
sep = NULL;
if (fiop != NULL)
sep = FastaToSeqEntry (fiop, FALSE);
}
ComPatFree (cpph);
ValNodeFreeData (namelist);
FileClose (fiop);
if (gi > 0)
EntrezFini ();
#ifndef NO_TAX_NET
if (myargs[ia].intvalue)
TaxArchFini ();
#endif
return 0;
}
static Int2 LIBCALLBACK FilterMsgFunc (OMMsgStructPtr ommsp)
{
OMUserDataPtr omudp;
GraphViewFormPtr gvp;
SeqGraphPtr sgp;
VieweR v;
PoinT pt;
PntInfo pw;
Uint2 segID, primID, primCt, start, end, i;
SegmenT s;
PrimitivE p;
FloatHi fval;
Int4 pos;
FloatHi maxVal, minVal;
if ((omudp = (OMUserDataPtr) (ommsp->omuserdata)) == NULL)
return OM_MSG_RET_ERROR;
if ((gvp = (GraphViewFormPtr) (omudp->userdata.ptrvalue)) == NULL)
return OM_MSG_RET_ERROR;
switch (ommsp->message)
{
case OM_MSG_SELECT:
if (ommsp->itemtype == OBJ_BIOSEQ)
{
if (ommsp->regiontype == OM_REGION_SEQLOC)
{
if ((sgp = gvp->sgp) == NULL)
return OM_MSG_RET_ERROR;
switch (sgp->flags[2])
{
default:
case 1:
maxVal = sgp->max.realvalue;
minVal = sgp->min.realvalue;
break;
case 2:
case 3:
maxVal = (FloatHi) sgp->max.intvalue;
minVal = (FloatHi) sgp->min.intvalue;
break;
}
if (gvp->slp != NULL)
{
v = gvp->viewer;
pt.x = 0;
pt.y = 0;
s = FindSegment (v, pt, &segID, &primID, &primCt);
ExploreSegment (s, v, UnHLSeg);
/*
ObjMgrDeSelectAll ();
gvp->slp = NULL;
*/
}
pos = SeqLocStart ((SeqLocPtr) ommsp->region);
pos /= gvp->zoom;
pw.x = (Int2) pos;
v = gvp->viewer;
primID = 0;
fval = minVal - 1;
while (primID < 1 && fval < maxVal)
{
fval++;
pw.y = (Int2) (gvp->margin + ((Int4) (fval * sgp->a)) +
(Int4) sgp->b);
MapWorldToViewer (v, pw, &pt);
s = FindSegment (v, pt, &segID, &primID, &primCt);
}
if (primCt == 0 && fval == maxVal)
return OM_MSG_RET_ERROR;
if (s == NULL)
return OM_MSG_RET_ERROR;
start = primCt;
pos = SeqLocStop ((SeqLocPtr) ommsp->region);
pos /= gvp->zoom;
pw.x = (Int2) pos;
primID = 0;
fval = minVal - 1;
while (primID < 1 && fval < maxVal)
{
fval++;
pw.y = (Int2) (gvp->margin + ((Int4) (fval * sgp->a)) +
(Int4) sgp->b);
MapWorldToViewer (v, pw, &pt);
s = FindSegment (v, pt, &segID, &primID, &primCt);
}
if (primCt == 0 || fval == maxVal)
return OM_MSG_RET_ERROR;
if (s == NULL)
return OM_MSG_RET_ERROR;
end = primCt;
if (start > end)
return OM_MSG_RET_ERROR;
WatchCursor ();
ExploreSegment (s, v, UnHLSeg);
ArrowCursor ();
for (i = start; i < end; i++)
{
p = GetPrimitive (s, i);
HighlightPrimitive (v, s, p, FRAME_PRIMITIVE);
}
/* DUP/memcp and delta id
gvp->slp = (Pointer) (ommsp->region);
*/
/*
ObjMgrSelect (gvp->entityID, gvp->itemID, OBJ_BIOSEQ, OM_REGION_SEQLOC,
gvp->slp);
*/
}
}
break;
case OM_MSG_DESELECT:
if (ommsp->itemtype == OBJ_BIOSEQ)
{
if (ommsp->regiontype == OM_REGION_SEQLOC)
{
if (gvp->slp != NULL)
{
/*
v = gvp->viewer;
pt.x = 0;
pt.y = 0;
s = FindSegment (v, pt, &segID, &primID, &primCt);
ExploreSegment (s, v, UnHLSeg);
ObjMgrDeSelectAll ();
gvp->slp = NULL;
*/
}
}
}
break;
case OM_MSG_DEL:
case OM_MSG_CREATE:
case OM_MSG_UPDATE:
case OM_MSG_CACHED:
case OM_MSG_UNCACHED:
case OM_MSG_TO_CLIPBOARD:
break;
default:
break;
}
return OM_MSG_RET_OK;
}
SeqLocPtr SeqLocDust (SeqLocPtr this_slp,
Int2 level, Int2 window, Int2 minwin, Int2 linker)
{
SeqLocPtr next_slp, slp = NULL;
ValNodePtr vnp = NULL;
SeqIdPtr id;
BioseqPtr bsp;
SeqPortPtr spp;
DREGION PNTR reg, PNTR regold;
Int4 nreg;
Int4 start, end, l;
Int2 loopDustMax = 0;
/* error msg stuff */
ErrSetOptFlags (EO_MSG_CODES);
if (!this_slp)
{
ErrPostEx (SEV_ERROR, 2, 1,
"no sequence location given for dusting");
ErrShow ();
return slp;
}
/* place for dusted regions */
regold = reg = MemNew (sizeof (DREGION));
if (!reg)
{
ErrPostEx (SEV_FATAL, 2, 2,
"memory allocation error");
ErrShow ();
return slp;
}
reg->from = 0;
reg->to = 0;
reg->next = NULL;
/* count seqlocs */
next_slp = NULL;
while ((next_slp = SeqLocFindNext (this_slp, next_slp)) != NULL)
loopDustMax++;
if (!loopDustMax)
{
ErrPostEx (SEV_ERROR, 2, 3,
"can not find next seq loc");
ErrShow ();
}
/* loop for dusting as needed */
next_slp = NULL;
while ((next_slp = SeqLocFindNext (this_slp, next_slp)) != NULL)
{
/* offsets into actual sequence */
start = SeqLocStart (next_slp);
end = SeqLocStop (next_slp);
/* if all goes okay should get a seqport pointer */
id = SeqLocId (next_slp);
if (!id)
{
ErrPostEx (SEV_ERROR, 2, 4,
"no bioseq id");
ErrShow ();
continue;
}
bsp = BioseqLockById (id);
if (!bsp)
{
ErrPostEx (SEV_ERROR, 2, 5,
"no bioseq");
ErrShow ();
continue;
}
if (!ISA_na (bsp->mol))
{
ErrPostEx (SEV_WARNING, 2, 6,
"not nucleic acid");
ErrShow ();
BioseqUnlock (bsp);
continue;
}
spp = SeqPortNew (bsp, start, end, 0, Seq_code_ncbi2na);
BioseqUnlock (bsp);
if (!spp)
{
ErrPostEx (SEV_ERROR, 2, 7,
"sequence port open failed");
ErrShow ();
continue;
}
l = spp->totlen;
nreg = dust_segs (l, spp, start, reg,
(Int4)level, (Int4)window, (Int4)minwin, (Int4)linker);
slp = slpDust (spp, slp, id, &vnp,
reg, nreg, loopDustMax);
/* find tail - this way avoids referencing the pointer */
while (reg->next) reg = reg->next;
SeqPortFree (spp);
}
/* clean up memory */
reg = regold;
while (reg)
{
regold = reg;
reg = reg->next;
MemFree (regold);
}
return slp;
}
static Int2 LIBCALLBACK MatrixMsgFunc (OMMsgStructPtr ommsp)
{
OMUserDataPtr omudp;
GraphViewFormPtr gvp;
SeqGraphPtr sgp;
VieweR v;
PoinT pt;
PntInfo pw;
Uint2 segID, primID, primCt;
SegmenT s;
PrimitivE p;
Int4 pos;
FloatHi maxVal;
if ((omudp = (OMUserDataPtr) (ommsp->omuserdata)) == NULL)
return OM_MSG_RET_ERROR;
if ((gvp = (GraphViewFormPtr) (omudp->userdata.ptrvalue)) == NULL)
return OM_MSG_RET_ERROR;
switch (ommsp->message)
{
case OM_MSG_SELECT:
if (ommsp->itemtype == OBJ_BIOSEQ)
{
if (ommsp->regiontype == OM_REGION_SEQLOC)
{
if ((sgp = gvp->sgp) == NULL)
return OM_MSG_RET_ERROR;
switch (sgp->flags[2])
{
default:
case 1:
maxVal = sgp->max.realvalue;
break;
case 2:
case 3:
maxVal = (FloatHi) sgp->max.intvalue;
break;
}
if (gvp->slp != NULL)
{
v = gvp->viewer;
pt.x = 0;
pt.y = 0;
s = FindSegment (v, pt, &segID, &primID, &primCt);
ExploreSegment (s, v, UnHLSeg);
/*
ObjMgrDeSelectAll ();
gvp->slp = NULL;
*/
}
pos = SeqLocStart ((SeqLocPtr) ommsp->region);
pos += SeqLocStop ((SeqLocPtr) ommsp->region);
pos /= 2;
pos /= gvp->zoom;
pw.x = (Int2) pos;
if (SeqLocStrand ((SeqLocPtr) ommsp->region) == Seq_strand_plus)
{
pw.y = (Int2) (gvp->margin + ((Int4) (1.0 +
(maxVal/2)) * sgp->a) +
(Int4) sgp->b);
}
else
{
pw.y = (Int2) (gvp->margin + ((Int4) (maxVal - 1.0 -
(maxVal/2)) * sgp->a) +
(Int4) sgp->b);
}
v = gvp->viewer;
primID = 0;
MapWorldToViewer (v, pw, &pt);
s = FindSegment (v, pt, &segID, &primID, &primCt);
if (primID < 1 || s == NULL)
return OM_MSG_RET_ERROR;
p = GetPrimitive (s, primCt);
WatchCursor ();
ExploreSegment (s, v, UnHLSeg);
ArrowCursor ();
HighlightPrimitive (v, s, p, FRAME_PRIMITIVE);
/* DUP/memcp and delta id
gvp->slp = (Pointer) (ommsp->region);
*/
/*
ObjMgrSelect (gvp->entityID, gvp->itemID, OBJ_BIOSEQ, OM_REGION_SEQLOC,
gvp->slp);
*/
}
}
break;
case OM_MSG_DESELECT:
if (ommsp->itemtype == OBJ_BIOSEQ)
{
if (ommsp->regiontype == OM_REGION_SEQLOC)
{
if (gvp->slp != NULL)
{
/*
v = gvp->viewer;
pt.x = 0;
pt.y = 0;
s = FindSegment (v, pt, &segID, &primID, &primCt);
ExploreSegment (s, v, UnHLSeg);
ObjMgrDeSelectAll ();
gvp->slp = NULL;
*/
}
}
}
break;
case OM_MSG_DEL:
case OM_MSG_CREATE:
case OM_MSG_UPDATE:
case OM_MSG_CACHED:
case OM_MSG_UNCACHED:
case OM_MSG_TO_CLIPBOARD:
break;
default:
break;
}
return OM_MSG_RET_OK;
}
extern SeqLocPtr FilterSigSeq (BioseqPtr bsp,
ComProfPtr pppl, ComProfPtr pppc,
FloatHi leadcutoff, FloatHi cutcutoff,
Int4 range, SeqIdPtr sip,
Boolean flagBoundaryCondition,
Boolean flagReportIfAllFuzzyOnly)
{
Int4 lstart, lstop, cstart, cstop;
FloatHi score;
SeqAlignPtr sap1h, sap1, sap2h, sap2;
StdSegPtr ssp1, ssp2;
SeqLocPtr slp1, slp2;
SeqLocPtr slp, slpt, slph = NULL;
if (bsp == NULL || pppl == NULL || pppc == NULL)
return NULL;
sap1h = sap1 = ProfileMatchBioseq (bsp, pppl, NULL, leadcutoff,
flagBoundaryCondition);
sap2h = sap2 = ProfileMatchBioseq (bsp, pppc, NULL, cutcutoff,
flagBoundaryCondition);
if (flagReportIfAllFuzzyOnly)
{
score = leadcutoff * 0.9;
score = leadcutoff + (leadcutoff - score);
while (sap1 != NULL)
{
if (sap1->score->value.realvalue > score)
{
while (sap1h != NULL)
{
sap1 = sap1h->next;
SeqAlignFree (sap1h);
sap1h = sap1;
}
break;
}
sap1 = sap1->next;
}
score = cutcutoff * 0.9;
score = cutcutoff + (cutcutoff - score);
while (sap2 != NULL)
{
if (sap2->score->value.realvalue > score)
{
while (sap2h != NULL)
{
sap2 = sap2h->next;
SeqAlignFree (sap2h);
sap2h = sap2;
}
break;
}
sap2 = sap2->next;
}
}
sap1 = sap1h;
sap2 = sap2h;
while (sap1 != NULL)
{
ssp1 = (StdSegPtr) sap1->segs;
slp1 = ssp1->loc;
lstart = SeqLocStart (slp1);
lstop = SeqLocStop (slp1);
if (range < 0 || lstop < range)
{
sap2 = sap2h;
while (sap2 != NULL)
{
ssp2 = (StdSegPtr) sap2->segs;
slp2 = ssp2->loc;
cstart = SeqLocStart (slp2);
cstop = SeqLocStop (slp2);
if (cstart - lstop > 0 && cstart - lstop < 8)
{
slpt = slph;
while (slpt != NULL)
{
if (cstop == SeqLocStop (slpt))
break;
slpt = slpt->next;
}
if (slpt == NULL)
{
slp = SeqLocIntNew (lstart, cstop, Seq_strand_unknown, sip);
ValNodeLink (&slph, slp);
}
}
sap2 = sap2->next;
}
}
sap1 = sap1->next;
}
while (sap1h != NULL)
{
sap1 = sap1h->next;
SeqAlignFree (sap1h);
sap1h = sap1;
}
while (sap2h != NULL)
{
sap2 = sap2h->next;
SeqAlignFree (sap2h);
sap2h = sap2;
}
return slph;
}
