// readFromCurFile - reads one .ms2 file
void SpectraSTMs2LibImporter::readFromFile(string& impFileName) {
ifstream fin;
if (!myFileOpen(fin, impFileName)) {
g_log->error("CREATE", "Cannot open .ms2 file \"" + impFileName + "\" for reading. File skipped.");
return;
}
g_log->log("MS2 IMPORT", "Importing .ms2 file \"" + impFileName + "\".");
if (g_verbose) {
cout << "\nImporting spectra from .ms2 library file..." << endl;
}
// start the progress count
ProgressCount pc(!g_quiet && !g_verbose, 500, 0);
pc.start("\nImporting spectra from .ms2 library file");
string line("");
unsigned int scan1 = 0;
unsigned int scan2 = 0;
double precursorMz = 0.0;
int charge = 1;
double mw = 0.0;
string dummy("");
string seq("");
string modifiedSeq("");
SpectraSTPeakList* peakList = NULL;
// looks like their cysteines are actually C[160]'s
// Peptide::addModTokenToTables("C", "Carbamidomethyl");
while (nextLine(fin, line)) {
if (line.empty()) continue;
string::size_type pos = 0;
if (line[0] == 'H') {
continue;
} else if (line[0] == 'S') {
if (peakList) {
if (peakList->getNumPeaks() == 0 || seq.empty()) {
delete peakList;
} else {
pc.increment();
if (!(modifiedSeq.empty())) seq = modifiedSeq;
Peptide* pep = new Peptide(seq, charge);
// check legality of peptide and mod strings -- will not insert later if illegal (parsing will continue anyway)
if (pep->hasUnknownMod) {
g_log->error("MS2 IMPORT", "Peptide ID with unknown modification: \"" + seq + "\". Entry skipped.");
}
if (pep->illegalPeptideStr && !pep->hasUnknownMod) {
g_log->error("MS2 IMPORT", "Illegal peptide ID string: \"" + seq + "\". Entry skipped.");
}
stringstream commentss;
commentss << "Fullname=X." << seq << ".X/" << charge;
commentss << " ScanNum=" << scan1 << '.' << scan2;
commentss << " Spec=Raw";
SpectraSTLibEntry* entry = new SpectraSTLibEntry(pep, commentss.str(), "Normal", peakList);
if (g_verbose) {
cout << "Importing record " << m_count << ": " << pep->interactStyleWithCharge() << endl;
}
m_count++;
if (passAllFilters(entry)) {
entry->annotatePeaks();
m_lib->insertEntry(entry);
}
delete (entry);
}
}
seq = "";
modifiedSeq = "";
peakList = NULL;
scan1 = atoi(nextToken(line, 1, pos, " \t\r\n", " \t\r\n").c_str());
scan2 = atoi(nextToken(line, pos, pos, " \t\r\n", " \t\r\n").c_str());
precursorMz = atof(nextToken(line, pos, pos, " \t\r\n", " \t\r\n").c_str());
} else if (line[0] == 'Z') {
charge = atoi(nextToken(line, 1, pos, " \t\r\n", " \t\r\n").c_str());
mw = atof(nextToken(line, pos, pos, " \t\r\n", " \t\r\n").c_str());
} else if (line[0] == 'D') {
dummy = nextToken(line, 1, pos, "\t\r\n", " \t\r\n");
if (dummy == "seq") {
seq = nextToken(line, pos, pos, "\r\n", " \t\r\n");
} else if (dummy == "modified seq") {
modifiedSeq = nextToken(line, pos, pos, "\r\n", " \t\r\n");
}
} else {
// should be a peak
if (!peakList) {
peakList = new SpectraSTPeakList(precursorMz, 0);
}
double mz = atof(nextToken(line, 0, pos, " \t\r\n", " \t\r\n").c_str());
float intensity = atof(nextToken(line, pos, pos, " \t\r\n", " \t\r\n").c_str());
peakList->insert(mz, intensity, "", "");
}
}
// finish last record
if (peakList) {
if (peakList->getNumPeaks() == 0 || seq.empty()) {
delete peakList;
} else {
pc.increment();
if (!(modifiedSeq.empty())) seq = modifiedSeq;
Peptide* pep = new Peptide(seq, charge);
if (pep->hasUnknownMod) {
g_log->error("MS2 IMPORT", "Peptide ID with unknown modification: \"" + seq + "\". Entry skipped.");
}
if (pep->illegalPeptideStr && !pep->hasUnknownMod) {
g_log->error("MS2 IMPORT", "Illegal peptide ID string: \"" + seq + "\". Entry skipped.");
}
stringstream commentss;
commentss << "Fullname=X." << seq << ".X/" << charge;
commentss << " ScanNum=" << scan1 << '.' << scan2;
commentss << " Spec=Raw";
SpectraSTLibEntry* entry = new SpectraSTLibEntry(pep, commentss.str(), "Normal", peakList);
if (g_verbose) {
cout << "Importing record " << m_count << ": " << pep->interactStyleWithCharge() << endl;
}
m_count++;
if (passAllFilters(entry)) {
entry->annotatePeaks();
m_lib->insertEntry(entry);
}
delete (entry);
}
}
pc.done();
}
