bool CPeptideDatabase::readMascot(char* mascotFile, char* dataFile){
MSReader r;
MascotParser p;
Spectrum s;
MascotLite m;
int i;
int percent=0;
p.clear();
p.readText(mascotFile);
if(p.isDistiller()){
cout << mascotFile << "\t" << p.size() << " peptides from Distiller, no need for RT lookup." << endl;
} else if(p.hasRTime()){
cout << mascotFile << "\t" << p.size() << " peptides have RT already, no need for lookup." << endl;
} else {
cout << mascotFile << "\tLooking up retention times for " << p.size() << " Mascot peptides..." << endl;
cout << percent;
r.readFile(dataFile,s);
}
for(i=0;i<p.size();i++){
if(p.isDistiller()||p.hasRTime()){
m.rTime=p[i].rTime;
} else {
if( (int)i*100/p.size() > percent){
percent=(int)i*100/p.size();
cout << "\b\b\b" << percent;
}
r.readFile(NULL,s,p[i].scanNum);
if(s.getScanNumber()==0){
cout << "Scan not found. Please check that correct data file is used. Stopping Mascot parsing." << endl;
return false;
}
m.rTime=s.getRTime();
}
m.charge=p[i].charge;
m.fileID=fileID;
m.monoMass=p[i].zeroMass;
m.scanNum=p[i].scanNum;
strcpy(m.peptide,p[i].sequence_Long);
strcpy(m.protein,p[i].gene);
mascot.push_back(m);
}
cout << " Done!" << endl;
fileID++;
return true;
}
//#ifdef _MSC_VER
//#ifndef MSSINGLESCAN_MAIN
//int mssinglescan_main(int argc, char * argv[] ) {
//#else
//int main(int argc, char *argv[]){
//#endif
//#else
int main(int argc, char *argv[]){
//#endif
//Here are all the variable we are going to need
MSReader r;
Spectrum s;
int j;
if(argc==1){
printf("DESCRIPTION: Reads an MS/MS spectrum from any MSToolkit supported file type and outputs to screen in MS2 format.\n\n");
printf("USAGE: MSSingleScan [scan number] [file]\n");
exit(0);
};
r.readFile(argv[2],s,atoi(argv[1]));
if(s.getScanNumber()==0) exit(-1);
printf("S\t%d\t%d\t%.*f\n",s.getScanNumber(),s.getScanNumber(),2,s.getMZ());
if(s.getRTime()>0) printf("I\tRTime\t%.*f\n",4,s.getRTime());
for(j=0;j<s.sizeZ();j++){
printf("Z\t%d\t%.*f\n",s.atZ(j).z,2,s.atZ(j).mz);
};
for(j=0;j<s.size();j++){
printf("%.4f %.4f\n",s.at(j).mz,s.at(j).intensity);
};
return 0;
};
bool CNoiseReduction::ScanAverage(Spectrum& sp, char* file, int width, float cutoff){
Spectrum ts;
Spectrum ps=sp;
MSReader r;
int i;
int j;
int k;
int widthCount=0;
int numScans=1;
double dif;
double prec;
double dt;
double c=CParam(ps,3);
bool bLeft=true;
int posLeft=ps.getScanNumber()-1;
int posRight=ps.getScanNumber()+1;
char cFilter1[256];
char cFilter2[256];
ps.getRawFilter(cFilter1,256);
while(widthCount<(width*2)){
//Alternate looking left and right
if(bLeft){
bLeft=false;
widthCount++;
while(posLeft>0){
r.readFile(file,ts,posLeft);
if(ts.getScanNumber()==0) break;
ts.getRawFilter(cFilter2,256);
if(strcmp(cFilter1,cFilter2)==0) break;
posLeft--;
}
} else {
bLeft=true;
widthCount++;
while(true){
r.readFile(file,ts,posRight);
if(ts.getScanNumber()==0) break;
ts.getRawFilter(cFilter2,256);
if(strcmp(cFilter1,cFilter2)==0) break;
posRight++;
}
}
if(ts.getScanNumber()==0) continue;
numScans++;
//Match peaks between pivot scan and temp scan
k=0;
for(i=0;i<ps.size();i++){
dif=100000.0;
prec = c * ps.at(i).mz * ps.at(i).mz / 2;
for(j=k;j<ts.size();j++){
dt=fabs(ps.at(i).mz-ts.at(j).mz);
if(dt<=dif) {
if(dt<prec) {
ps.at(i).intensity+=ts.at(j).intensity;
ts.at(j).mz=-1.0;
k=j+1;
break;
}
dif=dt;
} else {
k=j-1;
break;
}
}
}
//Add unmatched peaks from temp scan
for(i=0;i<ts.size();i++){
if(ts.at(i).mz>-1.0) ps.add(ts.at(i));
}
//Sort pivot scan peaks for fast traversal against next temp scan
ps.sortMZ();
}
//Average points and apply cutoff
sp.clear();
for(i=0;i<ps.size();i++) {
ps.at(i).intensity/=numScans;
if(ps.at(i).intensity>=cutoff) sp.add(ps.at(i));
}
sp.setScanNumber(ps.getScanNumber());
sp.setScanNumber(ps.getScanNumber(true),true);
sp.setRTime(ps.getRTime());
return true;
}
// Function reads in the spectra from the data stored for each PSMClass object
void PepXMLClass::readInSpectra() {
string curSpectrumFilePath;
deque<PSMClass>::iterator curPSM;
SpecStruct *spec = NULL;
bool status;
string spectrumFileName;
int scanNum;
int ctr = 0;
int N = (signed) PSMvec->size();
if(g_ext == "mgf") {
parseMGF();
return;
}
// mstoolkit to read MS2 spectra
MSReader *reader = new MSReader();
reader->setFilter(MS2);
// mstoolkit spectrum object
Spectrum *S = NULL;
// Extract from each PSM, it's parent spectrum file and scan number
for(curPSM = PSMvec->begin(); curPSM != PSMvec->end(); curPSM++) {
spectrumFileName = curPSM->getSpectrumFileName();
scanNum = curPSM->getScanNumber();
// code to get the full path to the input spectrum file
filesystem::path curFile( spectrumFileName.c_str() );
filesystem::path spectral_dir( g_srcDir.c_str() );
filesystem::path curFilePath( spectral_dir/curFile );
curSpectrumFilePath = curFilePath.file_string();
// if the source file is not located, drop the spectrum
if( !boost::filesystem::exists(curSpectrumFilePath) ) {
curPSM = PSMvec->erase(curPSM);
continue;
}
// Read the spectrum for 'scanNum' into 'S'
S = new Spectrum();
status = reader->readFile(curSpectrumFilePath.c_str(), *S, scanNum);
if(S->getScanNumber() == 0) {
cerr << "Failed to get " << curSpectrumFilePath.c_str() << " scan#: " << scanNum << endl;
exit(0);
}
spec = new SpecStruct();
for(int j = 0; j < S->size(); j++) {
spec->mz.push_back( S->at(j).mz );
spec->intensity.push_back( S->at(j).intensity );
}
delete(S); S = NULL;
// Assign the data in 'S' to curPSM
curPSM->recordSpectrum(*spec);
delete(spec); spec = NULL;
ctr++;
printProgress("Reading in spectra (please be patient)...", ctr, N);
}
delete(reader); reader = NULL;
cerr << endl; // prettier stderr
}