static void gtfToGenePred(char *gtfFile, char *gpFile, char *infoFile)
/* gtfToGenePred - convert a GTF file to a genePred.. */
{
struct gffFile *gtf = gffRead(gtfFile);
FILE *gpFh, *infoFh = NULL;
struct gffGroup *group;
if (!gtf->isGtf)
errAbort("%s doesn't appear to be a GTF file (GFF not supported by this program)", gtfFile);
gffGroupLines(gtf);
gpFh = mustOpen(gpFile, "w");
if (infoFile != NULL)
{
infoFh = mustOpen(infoFile, "w");
fputs(infoHeader, infoFh);
}
if (!doSimple)
for (group = gtf->groupList; group != NULL; group = group->next)
if (inclGroup(group))
gtfGroupToGenePred(gtf, group, gpFh, infoFh);
carefulClose(&gpFh);
gffFileFree(>f);
}
void gffToBed(char *inGff, char *outBed)
/* gffToBed - Convert a gff file (gff1 or gff2) to bed. Not tested with gff3 */
{
struct gffFile *gff = gffRead(inGff);
FILE *f = mustOpen(outBed, "w");
char *exonFeature = bestExonFeature(gff);
gffGroupLines(gff);
separateGroupsByChromosome(gff);
struct gffGroup *group;
for (group = gff->groupList; group != NULL; group = group->next)
{
struct genePred *gp;
if (gff->isGtf)
gp = genePredFromGroupedGtf(gff, group, group->name, FALSE, FALSE);
else
gp = genePredFromGroupedGff(gff, group, group->name, exonFeature, FALSE, FALSE);
if (gp != NULL)
{
assert(gp->txStart == gp->exonStarts[0]);
struct bed *bed = bedFromGenePred(gp);
bedTabOutN(bed, 12, f);
bedFree(&bed);
}
}
carefulClose(&f);
}
void ldGencodeIntron(char *database, char *table,
int gtfCount, char *gtfNames[])
/* Load Gencode intron status table from GTF files with
* intron_id and intron_status keywords */
{
struct gffFile *gff, *gffList = NULL;
struct gffLine *gffLine;
struct gencodeIntron *intron, *intronList = NULL;
struct sqlConnection *conn;
FILE *f;
int i;
int introns = 0;
for (i=0; i<gtfCount; i++)
{
verbose(1, "Reading %s\n", gtfNames[i]);
gff = gffRead(gtfNames[i]);
for (gffLine = gff->lineList; gffLine != NULL; gffLine = gffLine->next)
{
if (sameWord(gffLine->feature, "intron"))
{
AllocVar(intron);
intron->chrom = gffLine->seq;
intron->chromStart = gffLine->start;
intron->chromEnd = gffLine->end;
intron->name = gffLine->intronId;
intron->strand[0] = gffLine->strand;
intron->strand[1] = 0;
intron->status = gffLine->intronStatus;
intron->transcript = gffLine->group;
intron->geneId = gffLine->geneId;
slAddHead(&intronList, intron);
verbose(2, "%s %s\n", intron->chrom, intron->name);
introns++;
}
}
}
slSort(&intronList, bedCmp);
f = hgCreateTabFile(".", table);
for (intron = intronList; intron != NULL; intron = intron->next)
gencodeIntronTabOut(intron, f);
carefulClose(&f);
verbose(1, "%d introns in %d files\n", introns, gtfCount);
hSetDb(database);
conn = sqlConnect(database);
gencodeIntronTableCreate(conn, table, hGetMinIndexLength());
hgLoadTabFile(conn, ".", table, &f);
sqlDisconnect(&conn);
}
