int main(int argc, char *argv[]) {
DBAdaptor *dba;
Slice *slice;
SliceAdaptor *sliceA;
SequenceAdaptor *seqA;
initEnsC(argc, argv);
dba = DBAdaptor_new("ensembldb.ensembl.org","anonymous",NULL,"homo_sapiens_core_70_37",5306,NULL);
//dba = DBAdaptor_new("ens-livemirror.internal.sanger.ac.uk","ensro",NULL,"homo_sapiens_core_70_37",3306,NULL);
//dba = DBAdaptor_new("genebuild2.internal.sanger.ac.uk","ensadmin","ensembl","steve_hs_testdb",3306,NULL);
sliceA = DBAdaptor_getSliceAdaptor(dba);
seqA = DBAdaptor_getSequenceAdaptor(dba);
//
// Test fetch_by_Slice_start_end_strand
//
slice = SliceAdaptor_fetchByRegion(sliceA,"chromosome",CHR,START,END,STRAND,NULL,0);
compareComplements(slice, seqA);
slice = SliceAdaptor_fetchByRegion(sliceA, "clone","AL031658.11", POS_UNDEF, POS_UNDEF, STRAND_UNDEF, NULL, 0);
compareComplements(slice, seqA);
slice = SliceAdaptor_fetchByRegion(sliceA, "supercontig","NT_028392", POS_UNDEF, POS_UNDEF, STRAND_UNDEF, NULL, 0);
compareComplements(slice, seqA);
slice = SliceAdaptor_fetchByRegion(sliceA, "contig", "AL031658.11.1.162976", POS_UNDEF, POS_UNDEF, STRAND_UNDEF, NULL, 0);
compareComplements(slice, seqA);
return 0;
}
int main(int argc, char *argv[]) {
DBAdaptor *dba;
DBAdaptor *writeDba;
ProteinAlignFeatureAdaptor *pafa;
Slice *slice;
Vector *features;
int i;
int failed;
initEnsC(argc, argv);
dba = Test_initROEnsDB();
writeDba = Test_initRWEnsDB();
slice = Test_getStandardSlice(dba);
ok(1, slice!=NULL);
pafa = DBAdaptor_getProteinAlignFeatureAdaptor(writeDba);
SliceAdaptor *sa = DBAdaptor_getSliceAdaptor(dba);
ok(2, pafa!=NULL);
//features = Slice_getAllDNAPepAlignFeatures(slice,NULL,NULL, NULL,NULL);
//Slice *slice3 = SliceAdaptor_fetchByRegion(sa,"chromosome","1",2,260000000,1,NULL,0);
Slice *slice2 = SliceAdaptor_fetchByRegion(sa,"chromosome","1",1000000,4000000,1,NULL,0);
features = Slice_getAllProteinAlignFeatures(slice2,NULL,NULL, NULL,NULL);
ok(3, features!=NULL);
ok(4, Vector_getNumElement(features)!=0);
ProteinAlignFeatureAdaptor_store((BaseFeatureAdaptor*)pafa, features);
return 0;
}
int main(int argc, char *argv[]) {
DBAdaptor * dba;
StatementHandle *sth;
ResultRow * row;
Vector * slices;
int nSlices;
htsFile * out;
int argNum = 1;
char *inFName = NULL;
char *outFName = NULL;
char *dbUser = "******";
char *dbPass = NULL;
int dbPort = 3306;
char *dbHost = "ens-staging.internal.sanger.ac.uk";
char *dbName = "homo_sapiens_core_71_37";
char *assName = "GRCh37";
char *chrName = "1";
int flags = 0;
int threads = 1;
initEnsC(argc, argv);
while (argNum < argc) {
char *arg = argv[argNum];
char *val;
// Ones without a val go here
if (!strcmp(arg, "-U") || !strcmp(arg,"--ucsc_naming")) {
flags |= M_UCSC_NAMING;
} else {
// Ones with a val go in this block
if (argNum == argc-1) {
Bamcov_usage();
}
val = argv[++argNum];
if (!strcmp(arg, "-i") || !strcmp(arg,"--in_file")) {
StrUtil_copyString(&inFName,val,0);
} else if (!strcmp(arg, "-o") || !strcmp(arg,"--out_file")) {
StrUtil_copyString(&outFName,val,0);
} else if (!strcmp(arg, "-h") || !strcmp(arg,"--host")) {
StrUtil_copyString(&dbHost,val,0);
} else if (!strcmp(arg, "-p") || !strcmp(arg,"--password")) {
StrUtil_copyString(&dbPass,val,0);
} else if (!strcmp(arg, "-P") || !strcmp(arg,"--port")) {
dbPort = atoi(val);
} else if (!strcmp(arg, "-n") || !strcmp(arg,"--name")) {
StrUtil_copyString(&dbName,val,0);
} else if (!strcmp(arg, "-u") || !strcmp(arg,"--user")) {
StrUtil_copyString(&dbUser,val,0);
} else if (!strcmp(arg, "-t") || !strcmp(arg,"--threads")) {
threads = atoi(val);
} else if (!strcmp(arg, "-a") || !strcmp(arg,"--assembly")) {
StrUtil_copyString(&assName,val,0);
} else if (!strcmp(arg, "-v") || !strcmp(arg,"--verbosity")) {
verbosity = atoi(val);
// Temporary
} else if (!strcmp(arg, "-c") || !strcmp(arg,"--chromosome")) {
StrUtil_copyString(&chrName,val,0);
} else {
fprintf(stderr,"Error in command line at %s\n\n",arg);
Bamcov_usage();
}
}
argNum++;
}
if (verbosity > 0) {
printf("Program for calculating read coverage in a BAM file \n"
"Steve M.J. Searle. [email protected] Last update April 2013.\n");
}
if (!inFName || !outFName) {
Bamcov_usage();
}
dba = DBAdaptor_new(dbHost,dbUser,dbPass,dbName,dbPort,NULL);
//nSlices = getSlices(dba, destName);
nSlices = 1;
slices = Vector_new();
SliceAdaptor *sa = DBAdaptor_getSliceAdaptor(dba);
Slice *slice = SliceAdaptor_fetchByRegion(sa,NULL,chrName,POS_UNDEF,POS_UNDEF,1,NULL, 0);
Vector_addElement(slices,slice);
if (Vector_getNumElement(slices) == 0) {
fprintf(stderr, "Error: No slices.\n");
exit(1);
}
htsFile *in = hts_open(inFName, "rb");
if (in == 0) {
fprintf(stderr, "Fail to open BAM file %s\n", inFName);
return 1;
}
hts_set_threads(in, threads);
hts_idx_t *idx;
idx = bam_index_load(inFName); // load BAM index
if (idx == 0) {
fprintf(stderr, "BAM index file is not available.\n");
return 1;
}
int i;
for (i=0; i<Vector_getNumElement(slices); i++) {
Slice *slice = Vector_getElementAt(slices,i);
if (verbosity > 0) printf("Working on '%s'\n",Slice_getName(slice));
// if (verbosity > 0) printf("Stage 1 - retrieving annotation from database\n");
// Vector *genes = getGenes(slice, flags);
if (verbosity > 0) printf("Stage 1 - calculating coverage\n");
calcCoverage(inFName, slice, in, idx, flags);
}
hts_idx_destroy(idx);
hts_close(in);
if (verbosity > 0) printf("Done\n");
return 0;
}
Vector *PredictionTranscriptAdaptor_fetchAllBySlice(PredictionTranscriptAdaptor *pta, Slice *slice, char *logicName, int loadExons) {
//my $transcripts = $self->SUPER::fetch_all_by_Slice($slice,$logic_name);
Vector *transcripts = BaseFeatureAdaptor_fetchAllBySlice((BaseFeatureAdaptor *)pta, slice, logicName);
// if there are 0 or 1 transcripts still do lazy-loading
if ( ! loadExons || Vector_getNumElement(transcripts) < 2 ) {
return transcripts;
}
// preload all of the exons now, instead of lazy loading later
// faster than 1 query per transcript
// get extent of region spanned by transcripts
long minStart = 2000000000;
long maxEnd = -2000000000;
int i;
for (i=0; i<Vector_getNumElement(transcripts); i++) {
PredictionTranscript *t = Vector_getElementAt(transcripts, i);
if (PredictionTranscript_getSeqRegionStart((SeqFeature*)t) < minStart) {
minStart = PredictionTranscript_getSeqRegionStart((SeqFeature*)t);
}
if (PredictionTranscript_getSeqRegionEnd((SeqFeature*)t) > maxEnd) {
maxEnd = PredictionTranscript_getSeqRegionEnd((SeqFeature*)t);
}
}
Slice *extSlice;
if (minStart >= Slice_getStart(slice) && maxEnd <= Slice_getEnd(slice)) {
extSlice = slice;
} else {
SliceAdaptor *sa = DBAdaptor_getSliceAdaptor(pta->dba);
extSlice = SliceAdaptor_fetchByRegion(sa, Slice_getCoordSystemName(slice), Slice_getSeqRegionName(slice),
minStart, maxEnd, Slice_getStrand(slice), CoordSystem_getVersion(Slice_getCoordSystem(slice)), 0);
}
// associate exon identifiers with transcripts
IDHash *trHash = IDHash_new(IDHASH_MEDIUM);
for (i=0; i<Vector_getNumElement(transcripts); i++) {
PredictionTranscript *t = Vector_getElementAt(transcripts, i);
if ( ! IDHash_contains(trHash, PredictionTranscript_getDbID(t))) {
IDHash_add(trHash, PredictionTranscript_getDbID(t), t);
}
}
IDType *uniqueIds = IDHash_getKeys(trHash);
char tmpStr[1024];
char *qStr = NULL;
if ((qStr = (char *)calloc(655500,sizeof(char))) == NULL) {
fprintf(stderr,"Failed allocating qStr\n");
return transcripts;
}
int lenNum;
int endPoint = sprintf(qStr, "SELECT prediction_transcript_id, prediction_exon_id, exon_rank FROM prediction_exon WHERE prediction_transcript_id IN (");
for (i=0; i<IDHash_getNumValues(trHash); i++) {
if (i!=0) {
qStr[endPoint++] = ',';
qStr[endPoint++] = ' ';
}
lenNum = sprintf(tmpStr,IDFMTSTR,uniqueIds[i]);
memcpy(&(qStr[endPoint]), tmpStr, lenNum);
endPoint+=lenNum;
}
qStr[endPoint++] = ')';
qStr[endPoint] = '\0';
free(uniqueIds);
StatementHandle *sth = pta->prepare((BaseAdaptor *)pta,qStr,strlen(qStr));
sth->execute(sth);
IDHash *exTrHash = IDHash_new(IDHASH_MEDIUM);
ResultRow *row;
while ((row = sth->fetchRow(sth))) {
IDType trId = row->getLongLongAt(row,0);
IDType exId = row->getLongLongAt(row,1);
int rank = row->getIntAt(row,2);
if (! IDHash_contains(exTrHash, exId)) {
Vector *vec = Vector_new();
Vector_setFreeFunc(vec, PredictionTranscriptRankPair_free);
IDHash_add(exTrHash, exId, vec);
}
Vector *exVec = IDHash_getValue(exTrHash, exId);
PredictionTranscriptRankPair *trp = PredictionTranscriptRankPair_new(IDHash_getValue(trHash, trId), rank);
Vector_addElement(exVec, trp);
}
IDHash_free(trHash, NULL);
sth->finish(sth);
PredictionExonAdaptor *pea = DBAdaptor_getPredictionExonAdaptor(pta->dba);
Vector *exons = PredictionExonAdaptor_fetchAllBySlice(pea, extSlice);
// move exons onto transcript slice, and add them to transcripts
for (i=0; i<Vector_getNumElement(exons); i++) {
PredictionExon *ex = Vector_getElementAt(exons, i);
// Perl didn't have this line - it was in GeneAdaptor version so I think I'm going to keep it
if (!IDHash_contains(exTrHash, PredictionExon_getDbID(ex))) continue;
PredictionExon *newEx;
if (slice != extSlice) {
newEx = (PredictionExon*)PredictionExon_transfer((SeqFeature*)ex, slice);
if (newEx == NULL) {
fprintf(stderr, "Unexpected. Exon could not be transferred onto PredictionTranscript slice.\n");
exit(1);
}
} else {
newEx = ex;
}
Vector *exVec = IDHash_getValue(exTrHash, PredictionExon_getDbID(newEx));
int j;
for (j=0; j<Vector_getNumElement(exVec); j++) {
PredictionTranscriptRankPair *trp = Vector_getElementAt(exVec, j);
PredictionTranscript_addExon(trp->transcript, newEx, &trp->rank);
}
}
IDHash_free(exTrHash, Vector_free);
free(qStr);
return transcripts;
}
int main(int argc, char *argv[]) {
DBAdaptor *dba;
GeneAdaptor *ga;
Slice *slice = NULL;
Vector *genes = NULL;
int i = 0;
int failed = 0;
initEnsC(argc, argv);
// ProcUtil_showBacktrace(EnsC_progName);
dba = Test_initROEnsDB();
slice = Test_getStandardSlice(dba);
// DBAdaptor *seqdba = DBAdaptor_new("genebuild6.internal.sanger.ac.uk","ensadmin","ensembl","steve_chicken_rnaseq_missing_reference",3306,NULL);
// dba = DBAdaptor_new("genebuild1.internal.sanger.ac.uk","ensadmin","ensembl","steve_chicken_rnaseq_missing_refined",3306,seqdba);
ok(1, slice!=NULL);
ga = DBAdaptor_getGeneAdaptor(dba);
SliceAdaptor *sa = DBAdaptor_getSliceAdaptor(dba);
ok(2, ga!=NULL);
slice = SliceAdaptor_fetchByRegion(sa,"chromosome","20",10000000,50000000,1,NULL,0);
// slice = SliceAdaptor_fetchByRegion(sa,"chromosome","17",1000000,5000000,1,NULL,0);
// slice = SliceAdaptor_fetchByRegion(sa,"chromosome","17",1,5000000,1,NULL,0);
// Has a seleno
// slice = SliceAdaptor_fetchByRegion(sa,"chromosome","1",1000000,27000000,1,NULL,0);
// slice = SliceAdaptor_fetchByRegion(sa,"chromosome","MT",1,17000,1,NULL,0);
genes = Slice_getAllGenes(slice, NULL, NULL, 1, NULL, NULL);
fprintf(stdout, "Have %d genes\n", Vector_getNumElement(genes));
ok(3, genes!=NULL);
ok(4, Vector_getNumElement(genes)!=0);
failed = dumpGenes(genes, 1);
ok(5, !failed);
//Vector *toplevelSlices = SliceAdaptor_fetchAll(sa, "toplevel", NULL, 0);
Vector *toplevelSlices = SliceAdaptor_fetchAll(sa, "chromosome", NULL, 0);
for (i=0;i<Vector_getNumElement(toplevelSlices) && !failed;i++) {
Slice *tlSlice = Vector_getElementAt(toplevelSlices, i);
fprintf(stderr, "Slice %s\n", Slice_getName(tlSlice));
genes = Slice_getAllGenes(tlSlice, NULL, NULL, 1, NULL, NULL);
fprintf(stderr, "Got %d genes on %s\n", Vector_getNumElement(genes), Slice_getName(tlSlice));
failed = dumpGenes(genes, 0);
}
//tc_malloc_stats();
fprintf(stderr,"\nEcostring table stats:\n");
EcoString_getInfo(ecoSTable);
fprintf(stderr,"\n");
ProcUtil_timeInfo("at end of GeneTest");
return 0;
}
