void compareComplements(Slice *slice, SequenceAdaptor *seqA) {
char *seq = SequenceAdaptor_fetchBySliceStartEndStrand(seqA, slice,1,POS_UNDEF,1);
fprintf(stderr,"FORWARD STRAND SLICE SEQ for %s\n", Slice_getName(slice));
//fprintf(stderr,"%s\n", seq);
char *invertedSeq = SequenceAdaptor_fetchBySliceStartEndStrand(seqA, slice,1,POS_UNDEF,-1);
fprintf(stderr,"REVERSE STRAND SLICE SEQ for %s\n", Slice_getName(slice));
//fprintf(stderr,"%s\n", invertedSeq);
ok(nTest++, strlen(seq) == Slice_getLength(slice)); //sequence is correct length
SeqUtil_reverseComplement(seq, Slice_getLength(slice)); //reverse complement seq
//fprintf(stderr,"%s\n", seq);
ok(nTest++, !strcmp(seq, invertedSeq)); //revcom same as seq on inverted slice
}
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;
}
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;
}
