boolean getWormGeneDna(char *name, DNA **retDna, boolean upcExons)
/* Get the DNA associated with a gene. Optionally upper case exons. */
{
struct gdfGene *g;
struct slName *syn = NULL;
long lstart, lend;
int start, end;
int dnaSize;
DNA *dna;
struct wormGdfCache *gdfCache;
/* Translate biologist type name to cosmid.N name */
if (wormIsGeneName(name))
{
syn = wormGeneToOrfNames(name);
if (syn != NULL)
name = syn->name;
}
if (strncmp(name, "g-", 2) == 0)
gdfCache = &wormGenieGdfCache;
else
gdfCache = &wormSangerGdfCache;
if ((g = wormGetSomeGdfGene(name, gdfCache)) == NULL)
return FALSE;
gdfGeneExtents(g, &lstart, &lend);
start = lstart;
end = lend;
/* wormClipRangeToChrom(chromIds[g->chromIx], &start, &end); */
dnaSize = end-start;
*retDna = dna = wormChromPart(chromIds[g->chromIx], start, dnaSize);
gdfOffsetGene(g, -start);
if (g->strand == '-')
{
reverseComplement(dna, dnaSize);
gdfRcGene(g, dnaSize);
}
if (upcExons)
{
int i;
struct gdfDataPoint *pt = g->dataPoints;
for (i=0; i<g->dataCount; i += 2)
{
toUpperN(dna + pt[i].start, pt[i+1].start - pt[i].start);
}
}
gdfFreeGene(g);
return TRUE;
}
boolean getWormGeneExonDna(char *name, DNA **retDna)
/* Get the DNA associated with a gene, without introns. */
{
struct gdfGene *g;
struct slName *syn = NULL;
long lstart, lend;
int start, end;
int dnaSize;
DNA *dna;
int i;
struct gdfDataPoint *pt = NULL;
struct wormGdfCache *gdfCache;
struct dyString *dy = newDyString(1000);
/* Translate biologist type name to cosmid.N name */
if (wormIsGeneName(name))
{
syn = wormGeneToOrfNames(name);
if (syn != NULL)
name = syn->name;
}
if (strncmp(name, "g-", 2) == 0)
gdfCache = &wormGenieGdfCache;
else
gdfCache = &wormSangerGdfCache;
if ((g = wormGetSomeGdfGene(name, gdfCache)) == NULL)
return FALSE;
gdfGeneExtents(g, &lstart, &lend);
start = lstart;
end = lend;
/*wormClipRangeToChrom(chromIds[g->chromIx], &start, &end);*/
dnaSize = end-start;
dna = wormChromPart(chromIds[g->chromIx], start, dnaSize);
gdfOffsetGene(g, -start);
if (g->strand == '-')
{
reverseComplement(dna, dnaSize);
gdfRcGene(g, dnaSize);
}
pt = g->dataPoints;
for (i=0; i<g->dataCount; i += 2)
{
dyStringAppendN(dy, (dna+pt[i].start), (pt[i+1].start - pt[i].start));
}
*retDna = cloneString(dy->string);
dyStringFree(&dy);
gdfFreeGene(g);
return TRUE;
}
void gdfUpcExons(struct gdfGene *gene, int geneOffset, DNA *dna, int dnaSize, int dnaOffset)
/* Uppercase exons in DNA. */
{
struct gdfDataPoint *dp = gene->dataPoints;
int count = gene->dataCount;
int start, end;
long gffStart, gffEnd;
int combinedOffset;
int i;
gdfGeneExtents(gene, &gffStart, &gffEnd);
combinedOffset = -gffStart + geneOffset - dnaOffset;
for (i=0; i<count; i += 2)
{
start = dp[i].start + combinedOffset;
end = dp[i+1].start + combinedOffset;
if (end <= 0 || start >= dnaSize)
continue;
if (start < 0) start = 0;
if (end > dnaSize) end = dnaSize;
toUpperN(dna+start, end-start);
}
}