/*private*/
LineSequencer::Sequences*
LineSequencer::findSequences()
{
Sequences *sequences = new Sequences();
planargraph::algorithm::ConnectedSubgraphFinder csFinder(graph);
vector<planargraph::Subgraph*> subgraphs;
csFinder.getConnectedSubgraphs(subgraphs);
for (vector<planargraph::Subgraph*>::const_iterator
it=subgraphs.begin(), endIt=subgraphs.end();
it!=endIt;
++it )
{
planargraph::Subgraph* subgraph = *it;
if (hasSequence(*subgraph)) {
planargraph::DirectedEdge::NonConstList* seq=findSequence(*subgraph);
sequences->push_back(seq);
}
else {
// if any subgraph cannot be sequenced, abort
delete subgraph;
delAll(*sequences);
delete sequences;
return nullptr;
}
delete subgraph;
}
return sequences;
}
// la séquence initiale est lue et découpée en sous-séquences de
// longueur 20 ;
// chaque sous-séquence est terminée par une observation END pour que
// le HMM généré possède un état terminal
Sequences build_initial_sequences(const std::string& name)
{
Sequence sequence = read_initial_sequence(name, false);
Sequences sequences;
unsigned int length = sequence.size() / 20;
Sequence::const_iterator it = sequence.begin();
unsigned int added = 0;
unsigned int index = 0;
sequences.push_back(Sequence());
while (it != sequence.end()) {
if (added == length) {
sequences[index].push_back(Observation(0, END));
++index;
added = 0;
sequences.push_back(Sequence());
}
sequences[index].push_back(*it);
++added;
++it;
}
if (sequence.size() % 20 != 0) {
sequences[index].push_back(Observation(0, END));
}
return sequences;
}
int main(int argc, char** argv)
{
if (argc < 4)
{
std::cout << "Usage: get_TrieArray <fastafile> <matrix> <peptideLength> <outfile> " << std::endl;
return -1;
}
string fastafile(argv[1]);
string matrix(argv[2]);
cout << "test" << endl;
int peptideLength(atoi(argv[3]));
string outname(argv[4]);
//std::cout << fastafile << "\t" << outname << std::endl;
//----------------------------------------------------------------------------------------
cout << "Reading FASTA file..." << endl;
Sequences s(fastafile);
cout << "Read " << s.size() << " sequences." << endl;
cout << "Generating peptides..." << endl;
Sequences ninemers;
generateAllSubstrings(ninemers, s, peptideLength);
cout << "Generated " << ninemers.size() << " peptides." << endl;
s.clear();
//Matrix m("/abi-projects/dist2self/matrices/BLOSUM45_distance_normal.dat"); cout << "Initializing trie. " << endl; Trie t;
Matrix m(matrix); cout << "Initializing trie. " << endl; Trie t;
Matrix::IndexSequence indices;
for (size_t i = 0; i < ninemers.size(); ++i) {
m.translate(ninemers[i], indices); t.add(indices);
}
t.dump();
cout << "Converting to trie array." << endl;
TrieArray ta(t, peptideLength);
cout << "Done." << endl;
// std::ofstream ofs("test.trie");
std::ofstream ofs(outname.c_str());
boost::archive::text_oarchive oa(ofs);
ta.save(oa,1);
}
// fonction de sauvegarde de la liste des sous-séquences dans les
// fichiers .input
void save_sequences(const std::string& name, const Sequences& sequences)
{
std::ofstream f((boost::format("seq-%1%.input") %
name).str().c_str());
for (Sequences::const_iterator it = sequences.begin();
it != sequences.end(); ++it) {
for (Sequence::const_iterator it2 = it->begin();
it2 != it->end(); ++it2) {
f << it2->first << "|" << it2->second << " ";
}
f << std::endl;
}
f.close();
}
void generateAllSubstrings(Sequences& substrings, const Sequences& s, size_t len)
{
for (size_t i = 0; i < s.size(); ++i)
{
for (int j = 0; j <= ((int)s[i].size() - (int)len); ++j)
{
string sub(string(&(s[i][j]), len));
substrings.push_back(sub);
if (sub.size() != len)
cout << "generateAllSubstrings size: " << sub.size() << endl;
}
}
}
int main(int argc, char** argv)
{
if (argc < 2)
{
std::cout << "Usage: get_TrieArray <fastafile> <outfile> " << std::endl;
return -1;
}
ofstream myfile;
string fastafile(argv[1]);
const char* outname(argv[2]);
myfile.open(outname);
std::cout << fastafile << "\t" << outname << std::endl;
//----------------------------------------------------------------------------------------
cout << "Reading FASTA file..." << endl;
Sequences s(fastafile);
cout << "Read " << s.size() << " sequences." << endl;
cout << "Generating ninemers..." << endl;
Sequences ninemers;
generateAllSubstrings(ninemers, s, 9);
cout << "Generated " << ninemers.size() << " ninemers." << endl;
s.clear();
for (size_t i = 0; i < ninemers.size(); ++i) {
myfile << "> " << i << endl;
myfile << ninemers[i] << endl;
}
myfile.close();
cout << "Done." << endl;
}