int main (int argn, char** argv) {
// 1. parse cmd
parse_cmd_line(argn, argv);
// 2. input DNA sequence file
int numSeq = 0;
SequenceSet allSeqs (0, Sequence());
parse_seqs_file(allSeqs, numSeq, trainFname);
vector<int> lenSeqs (numSeq, 0);
for (int n = 0; n < numSeq; n ++)
lenSeqs[n] = allSeqs[n].size();
// pre-info
cout << "#########################################################" << endl;
cout << "ScoreMatch: " << C_M;
cout << ", ScoreInsertion: " << C_I;
cout << ", ScoreDeletion: " << C_D;
cout << ", ScoreMismatch: " << C_MM << endl;
for (int n = 0; n < numSeq; n ++)
sequence_dump(allSeqs, n);
// 3. relaxed convex program: ADMM-based algorithm
string dir_path = string(trainFname)+".trace/";
//system((string("rm -rf ")+dir_path).c_str());
//system((string("mkdir ")+dir_path).c_str());
// omp_set_num_threads(NUM_THREADS);
int T2 = get_init_model_length (lenSeqs) + LENGTH_OFFSET; // model_seq_length
time_t begin = time(NULL);
vector<Tensor4D> W = CVX_ADMM_MSA (allSeqs, lenSeqs, T2, dir_path);
time_t end = time(NULL);
// 4. output the result
// a. tuple view
cout << ">>>>>>>>>>>>>>>>>>>>>>>TupleView<<<<<<<<<<<<<<<<<<<<<<<<" << endl;
for (int n = 0; n < numSeq; n ++) {
cout << "n = " << n << endl;
tensor4D_dump(W[n]);
}
// b. sequence view
cout << ">>>>>>>>>>>>>>>>>>>>>>>SequenceView<<<<<<<<<<<<<<<<<<<<<<<<" << endl;
int T2m = T2;
Tensor tensor (T2m, Matrix (NUM_DNA_TYPE, vector<double>(NUM_DNA_TYPE, 0.0)));
Matrix mat_insertion (T2m, vector<double> (NUM_DNA_TYPE, 0.0));
for (int n = 0; n < numSeq; n ++) {
int T1 = W[n].size();
for (int i = 0; i < T1; i ++) {
for (int j = 0; j < T2m; j ++) {
for (int d = 0; d < NUM_DNA_TYPE; d ++) {
for (int m = 0; m < NUM_MOVEMENT; m ++) {
if (m == DELETION_A or m == MATCH_A)
tensor[j][d][dna2T3idx('A')] += max(0.0, W[n][i][j][d][m]);
else if (m == DELETION_T or m == MATCH_T)
tensor[j][d][dna2T3idx('T')] += max(0.0, W[n][i][j][d][m]);
else if (m == DELETION_C or m == MATCH_C)
tensor[j][d][dna2T3idx('C')] += max(0.0, W[n][i][j][d][m]);
else if (m == DELETION_G or m == MATCH_G)
tensor[j][d][dna2T3idx('G')] += max(0.0, W[n][i][j][d][m]);
else if (m == DELETION_START or m == MATCH_START)
tensor[j][d][dna2T3idx('*')] += max(0.0, W[n][i][j][d][m]);
else if (m == DELETION_END or m == MATCH_END)
tensor[j][d][dna2T3idx('#')] += max(0.0, W[n][i][j][d][m]);
else if (m == INSERTION)
mat_insertion[j][d] += max(0.0, W[n][i][j][d][m]);
}
}
}
}
}
Trace trace (0, Cell(2)); // 1d: j, 2d: ATCG
refined_viterbi_algo (trace, tensor, mat_insertion);
// for (int i = 0; i < trace.size(); i ++)
// cout << trace[i].toString() << endl;
for (int n = 0; n < numSeq; n ++) {
char buffer [50];
sprintf (buffer, "Seq%5d", n);
cout << buffer << ": ";
for (int j = 0; j < allSeqs[n].size(); j ++)
cout << allSeqs[n][j];
cout << endl;
}
Sequence recSeq;
cout << "SeqRecov: ";
for (int i = 0; i < trace.size(); i ++)
if (trace[i].action != INSERTION) {
cout << trace[i].acidB;
recSeq.push_back(trace[i].acidB);
if (trace[i].acidB == '#') break;
}
cout << endl;
cout << ">>>>>>>>>>>>>>>>>>>>>>>MatchingView<<<<<<<<<<<<<<<<<<<<<<<<" << endl;
// NOTE: rounding scheme
SequenceSet allModelSeqs, allDataSeqs;
for (int n = 0; n < numSeq; n ++) {
Sequence model_seq = recSeq, data_seq = allSeqs[n];
data_seq.erase(data_seq.begin());
model_seq.erase(model_seq.begin());
data_seq.erase(data_seq.end()-1);
model_seq.erase(model_seq.end()-1);
// align sequences locally
Plane plane (data_seq.size()+1, Trace(model_seq.size()+1, Cell(2)));
Trace trace (0, Cell(2));
smith_waterman (model_seq, data_seq, plane, trace);
// 4. output the result
model_seq.clear(); data_seq.clear();
for (int i = 0; i < trace.size(); i ++)
model_seq.push_back(trace[i].acidA);
for (int i = 0; i < trace.size(); i ++)
data_seq.push_back(trace[i].acidB);
allModelSeqs.push_back(model_seq);
allDataSeqs.push_back(data_seq);
for (int i = 0; i < model_seq.size(); i ++) cout << model_seq[i];
cout << endl;
for (int i = 0; i < data_seq.size(); i ++) cout << data_seq[i];
cout << endl;
}
cout << ">>>>>>>>>>>>>>>>>>>>>ClustalOmegaView<<<<<<<<<<<<<<<<<<<<<<" << endl;
writeClusterView(string(trainFname)+".co", allModelSeqs, allDataSeqs);
cout << "#########################################################" << endl;
cout << "Time Spent: " << end - begin << " seconds" << endl;
return 0;
}
void main (int argc, char* argv[])
{
int pos = 0;
int length = 0;
sequence s = sequence_create();
srand(time(NULL));
// while(length < 20000)
// {
// char * c = malloc(sizeof(char));
// *c = getc(stdin);
// if(*c == '\n') continue;
// pos = (int) (length * (rand() / (RAND_MAX + 1.0)));
// // system("clear");
// // printf("try to insert \033[01;35m%s\033[00m at pos \033[01;35m%d\033[00m...\n",c,pos);
// sequence_insert(s,c,pos);
// length++;
// // sequence_dump(s);
// }
// while(length > 0)
// {
// pos = (int) (length * (rand() / (RAND_MAX + 1.0)));
// // printf("try to delete at pos \033[01;35m%d\033[00m...\n",pos);
// sequence_delete(s,pos);
// length--;
// // sequence_dump(s);
// }
/******************************************/
char * c = malloc(sizeof(char));
*c = 'A';
while(length < 20)
{
pos = (int) (length * (rand() / (RAND_MAX + 1.0)));
printf("## ");
// for (int i = 0; i < 20; ++i)
// {
printf("try to insert \033[01;35mA\033[00m at pos \033[01;35m%d\033[00m...\n",pos);
sequence_insert(s,c,pos);
length++;
pos++;
sequence_dump(s);
// }
}
while(length > 0)
{
pos = (int) (length * (rand() / (RAND_MAX + 1.0)));
printf(" ## ");
for (int i = 0; i < 5; ++i)
{
printf("try to delete at pos \033[01;35m%d\033[00m...\n",pos);
sequence_delete(s,pos);
length--;
pos--;
sequence_dump(s);
}
}
sequence_destroy(s);
}