SeqType
read_fasta(const std::string& filename, const std::string& name)
{
std::string line, begin_contig=">"+name;
SeqType sequence;
// open file
std::ifstream fastafile ( filename.c_str() , std::ifstream::in );
if (!fastafile.is_open()) {
std::stringstream ss;
ss<< "Fasta file "<< filename << " cannot be opened.";
throw std::domain_error(ss.str().c_str());
}
// find contig in multifasta
do {
getline(fastafile, line);
if (fastafile.eof()) {
std::stringstream s;
s << "Sequence of \"" << name << "\" not found.";
throw std::invalid_argument(s.str());
}
} while (line!=begin_contig);
/*
// get first contig line
getline(fastafile, line);
// while we do not reach a new contig
while ((!fastafile.eof())&&(line.substr(0,1) != ">")) {
// move read bases into sequence
unsigned int filled_until=sequence.size();
sequence.resize(sequence.size()+line.size());
for (unsigned int i=0; i<line.size(); i++) {
sequence[i+filled_until]=line[i];
}
// read a new line
getline(fastafile, line);
}
*/
sequence=read_sequence(fastafile);
fastafile.close();
return sequence;
}
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);
}
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;
}
fasta::FastaData fasta::parse_fasta(std::string const& filename,
int codon_length)
{
fs::path p(filename);
if (!fs::exists(p)) {
throw std::invalid_argument("File not found: " + filename);
}
std::ifstream fastafile(filename.c_str());
std::string line;
std::string header;
std::string seq_line;
auto in_sequence_section = true;
fasta::FastaData fd;
while (std::getline(fastafile, line)) {
if (line.substr(0, 1) == ">") {
if (!seq_line.empty()) {
auto sequence = fasta::make_sequence(
header, seq_line, codon_length
);
fd.sequences.push_back(sequence);
seq_line = "";
}
in_sequence_section = true;
// Parse header
line.erase(std::remove(line.begin(), line.end(), '\r'), line.end());
header = line;
continue;
}
if (line.substr(0, 1) == "#") {
assert(!seq_line.empty());
auto sequence = fasta::make_sequence(header, seq_line, codon_length);
fd.sequences.push_back(sequence);
in_sequence_section = false;
continue;
}
if (in_sequence_section) {
line.erase(std::remove(line.begin(), line.end(), '\r'), line.end());
seq_line += line;
} else {
std::vector<std::string> result;
boost::split(result, line, boost::is_any_of("\t "));
if (result.size() != 2) {
throw std::runtime_error("Invalid probability format: " + line);
}
fd.probabilities["m_" + result[0]] = std::stod(result[1]);
}
}
// If the file doesn't have a probability section, add the last sequence that
// was being processed.
if (in_sequence_section) {
auto sequence = fasta::make_sequence(header, seq_line, codon_length);
fd.sequences.push_back(sequence);
}
return fd;
}
