int main (int argc, const char * argv[]){
struct timeval start, end;
gettimeofday(&start, NULL);
// general parameters
size_t maxSeqLen = 50000;
int seqType = Sequence::AMINO_ACIDS;
// parameter for the prefiltering
int kmerSize = 6;
int alphabetSize = 21;
size_t maxResListLen = 100;
int split = 0;
int skip = 0;
bool aaBiasCorrection = true;
float zscoreThr = 50.0f;
float sensitivity = 4.0;
// parameters for the alignment
double evalThr = 0.001;
double covThr = 0.8;
int maxAlnNum = 10;
std::string lastSeqDB = "";
std::string currentSeqDB = "";
std::string cluDB = "";
std::string outDB = "";
std::string tmpDir = "";
// get the path of the scoring matrix
char* mmdir = getenv ("MMDIR");
if (mmdir == 0){
std::cerr << "Please set the environment variable $MMDIR to your MMSEQS installation directory.\n";
exit(1);
}
std::string scoringMatrixFile(mmdir);
scoringMatrixFile = scoringMatrixFile + "/data/blosum62.out";
parseArgs(argc, argv, &lastSeqDB, ¤tSeqDB, &cluDB, &outDB, &tmpDir, &scoringMatrixFile, &maxSeqLen);
std::string lastSeqDBIndex = lastSeqDB + ".index";
std::string currentSeqDBIndex = currentSeqDB + ".index";
std::string cluDBIndex = cluDB + ".index";
std::string outDBIndex = outDB + ".index";
std::list<std::string>* tmpFiles = new std::list<std::string>();
std::string AIndex = tmpDir + "/A.index";
std::string BIndex = tmpDir + "/B.index";
tmpFiles->push_back(AIndex);
tmpFiles->push_back(BIndex);
std::string Brest_indexFile = tmpDir + "/Brest.index";
tmpFiles->push_back(Brest_indexFile);
std::string BB_clu = tmpDir + "/BB_clu";
std::string BB_clu_index = BB_clu + ".index";
tmpFiles->push_back(BB_clu);
tmpFiles->push_back(BB_clu_index);
std::cout << "////////////////////////////////////////////////////////////////////////\n";
std::cout << "/////// Init /////////////\n";
std::cout << "////////////////////////////////////////////////////////////////////////\n";
// extract three indexes:
// - A: last database version without deleted sequences
// - B: sequences which are new in the database
writeIndexes(AIndex, BIndex, lastSeqDBIndex, currentSeqDBIndex);
std::cout << "////////////////////////////////////////////////////////////////////////\n";
std::cout << "/////// Calculating B->A scores /////////////\n";
std::cout << "////////////////////////////////////////////////////////////////////////\n";
// calculate score for the updating
// B->A scores
std::string BA_base = runScoresCalculation(currentSeqDB, BIndex,
currentSeqDB, AIndex,
tmpDir,
scoringMatrixFile, maxSeqLen, seqType,
kmerSize, alphabetSize, maxResListLen, split, skip, aaBiasCorrection, zscoreThr, sensitivity,
evalThr, covThr, maxAlnNum, "BA", tmpFiles);
std::cout << "////////////////////////////////////////////////////////////////////////\n";
std::cout << "/////// Adding sequences to existing clusters /////////////\n";
std::cout << "////////////////////////////////////////////////////////////////////////\n";
// update the clustering
DBReader* currSeqDbr = new DBReader(currentSeqDB.c_str(), currentSeqDBIndex.c_str());
currSeqDbr->open(DBReader::NOSORT);
// data structures for the clustering
int seqDBSize = currSeqDbr->getSize();
unsigned int* id2rep = new unsigned int[seqDBSize];
char** rep2cluName = new char*[seqDBSize];
for (int i = 0; i < seqDBSize; i++)
rep2cluName[i] = new char[FFINDEX_MAX_ENTRY_NAME_LENTH];
cluster_t* clusters = new cluster_t[seqDBSize];
for (int i = 0; i < seqDBSize; i++){
clusters[i].clu_size = 0;
clusters[i].first = 0;
clusters[i].last = 0;
}
std::cout << "Read the existing clustering...\n";
// Read the existing clustering
readClustering(currSeqDbr, cluDB, id2rep, rep2cluName, clusters);
std::cout << "Append new sequences to the existing clustering...\n";
// append sequences from the new database to the existing clustering based on the B->A alignment scores
// write sequences without a match to a separate index (they will be clustered separately)
appendToClustering(currSeqDbr, BIndex, BA_base, id2rep, clusters, Brest_indexFile);
if (seqsWithoutMatches > 0){
std::cout << "////////////////////////////////////////////////////////////////////////\n";
std::cout << "/////// Calculating B->B scores /////////////\n";
std::cout << "////////////////////////////////////////////////////////////////////////\n";
// B->B scores
std::string BB_base = runScoresCalculation(currentSeqDB, Brest_indexFile,
currentSeqDB, Brest_indexFile,
tmpDir,
scoringMatrixFile, maxSeqLen, seqType,
kmerSize, alphabetSize, maxResListLen, split, skip, aaBiasCorrection, zscoreThr, sensitivity,
evalThr, covThr, maxAlnNum, "BB", tmpFiles);
std::cout << "////////////////////////////////////////////////////////////////////////\n";
std::cout << "/////// Appending new clusters /////////////\n";
std::cout << "////////////////////////////////////////////////////////////////////////\n";
std::cout << "Cluster new sequences without a match to the existing clusters...\n";
// cluster sequences without a match to the existing clusters separately
// use the index generated in the previous step
Clustering* clu = new Clustering(currentSeqDB, currentSeqDBIndex,
BB_base, BB_base + ".index",
BB_clu, BB_clu_index,
0.0, 0, maxResListLen);
clu->run(Clustering::SET_COVER);
std::cout << "Append generated clusters to the complete clustering...\n";
// append B->B clusters to the clustering
newClus = readClustering(currSeqDbr, BB_clu, id2rep, rep2cluName, clusters);
}
// write new clustering
std::cout << "Write clustering results...\n";
writeResults(clusters, rep2cluName, currSeqDbr, seqDBSize, outDB);
std::cout << "done.\n";
currSeqDbr->close();
std::cout << "////////////////////////////////////////////////////////////////////////\n";
std::cout << "/////// Statistics ////////\n";
std::cout << "////////////////////////////////////////////////////////////////////////\n";
std::cout << "\nPrevios database version: " << oldDBSize << " entries.\n";
std::cout << "New database vesion : " << newDBSize << " entries.\n";
std::cout << deletedSeqs << " entries were deleted,\n";
std::cout << newSeqs << " entries are new,\n";
std::cout << sharedSeqs << " entries are shared.\n\n";
std::cout << seqsWithMatches << " new sequences had matches to the previous database version.\n";
std::cout << "Remaining " << seqsWithoutMatches << " were grouped into " << newClus << " new clusters.\n";
gettimeofday(&end, NULL);
int sec = end.tv_sec - start.tv_sec;
std::cout << "\nTime for updating: " << (sec / 3600) << " h " << (sec % 3600 / 60) << " m " << (sec % 60) << "s\n\n";
deleteTmpFiles(tmpFiles);
delete tmpFiles;
}
