int main(int argc, char *argv[])
/* The program */
{
struct psl *pslList = NULL, *psl;
struct hash *queryHash, *targetHash;
struct lineFile *vulg;
aaSeq *querySeqs;
struct dnaSeq *targetSeqs;
if (argc != 5)
usage();
/* Load up everything at beginning */
vulg = lineFileOpen(argv[1], TRUE);
querySeqs = dnaLoadAll(argv[2]);
targetSeqs = dnaLoadAll(argv[3]);
queryHash = seqHash(querySeqs);
targetHash = seqHash(targetSeqs);
/* Main business */
pslList = vulgarToPsl(vulg, queryHash, targetHash);
pslWriteAll(pslList, argv[4], FALSE);
/* Free up everything */
freeDnaSeqList(&querySeqs);
freeDnaSeqList(&targetSeqs);
freeHash(&targetHash);
freeHash(&queryHash);
pslFreeList(&pslList);
lineFileClose(&vulg);
return 0;
}
void pslRecalcMatch(char *inName, char *targetName, char *queryName,
char *outName)
/* pslRecalcMatch - Recalculate match,mismatch,repMatch columns in psl file.
* This can be useful if the psl went through pslMap, or if you've added
* lower-case repeat masking after the fact. */
{
struct nibTwoCache *tCache = nibTwoCacheNew(targetName);
struct dnaSeq *qSeqList = dnaLoadAll(queryName);
struct hash *qHash = dnaSeqHash(qSeqList);
struct psl *psl;
struct lineFile *lf = pslFileOpen(inName);
FILE *f = mustOpen(outName, "w");
while ((psl = pslNext(lf)) != NULL)
{
int tSize;
struct dnaSeq *tSeqPart = nibTwoCacheSeqPart(tCache,
psl->tName, psl->tStart, psl->tEnd - psl->tStart, &tSize);
struct dnaSeq *qSeq = hashMustFindVal(qHash, getQName(psl->qName));
recalcMatches(psl, tSeqPart, psl->tStart, qSeq);
pslTabOut(psl, f);
dnaSeqFree(&tSeqPart);
}
carefulClose(&f);
lineFileClose(&lf);
}
int main(int argc, char *argv[])
/* The program */
{
struct bed *bedList = NULL;
struct dnaSeq *targets = NULL, *target;
struct dnaSeq *queries = NULL, *query;
if (argc != 4)
usage();
targets = dnaLoadAll(argv[2]);
queries = dnaLoadAll(argv[1]);
for (target = targets; target != NULL; target = target->next)
for (query = queries; query != NULL; query = query->next)
{
struct bed *oneList = oligoMatch(target, query);
bedList = slCat(bedList, oneList);
}
outputBed6(bedList, argv[3]);
bedFreeList(&bedList);
dnaSeqFreeList(&targets);
dnaSeqFreeList(&queries);
return 0;
}
void findCutters(char *gcgFile, char *genome, char *outputFile)
/* findCutters - Find REBASE restriction enzymes using their GCG file. */
{
struct cutter *cutters = readGcg(gcgFile);
struct dnaSeq *seqs = dnaLoadAll(genome);
struct slName *whiteList = NULL;
if (justThis)
whiteList = newSlName(justThis);
if (justThese)
{
struct slName *listFromJustThese = getWhiteListFromFile();
whiteList = slCat(whiteList, listFromJustThese);
}
if (justThese || justThis)
cullCutters(&cutters, TRUE, whiteList, 0);
if (countsOnly)
findCounts(cutters, seqs, outputFile);
else
findBeds(cutters, seqs, outputFile);
cutterFreeList(&cutters);
freeDnaSeqList(&seqs);
slNameFreeList(&whiteList);
}
