static void checkSequence(string seq) {
Normalizer n;
bool ok = n.check(seq);
if (!ok) {
cerr << "Sequence can contain only numbers 0-9 and lowercase a-z" << endl;
exit(1);
}
}
int main()
{
Model model;
model.AddVariable("X0");
model.AddParam("gfi");
Normalizer normalizer;
normalizer.PutRmCoor("X0", 0.156, 0.5465, 0.41541, 0.214);
return 0;
}
std::string sequenceToPattern(std::string seq) {
checkSequence(seq);
Normalizer n;
std::string sub = "";
if (seq.length()>10) {
sub = seq.substr(0,seq.length()-10);
seq = seq.substr(seq.length()-10,seq.length());
}
string pat = n.denorm(submain(n.norm(seq)));
pat = sub + pat;
return pat;
}
void testNormalize() {
BOOST_LOG(rdInfoLog) << "-----------------------\n test normalize"
<< std::endl;
Normalizer normalizer;
// Test sulfoxide normalization.
std::string smi1 = "CS(C)=O";
std::shared_ptr<ROMol> m1(SmilesToMol(smi1));
ROMOL_SPTR normalized(normalizer.normalize(*m1));
TEST_ASSERT(MolToSmiles(*normalized) == "C[S+](C)[O-]");
// normalize sulfone.
std::string smi2 = "C[S+2]([O-])([O-])C";
std::shared_ptr<ROMol> m2(SmilesToMol(smi2));
ROMOL_SPTR normalized2(normalizer.normalize(*m2));
TEST_ASSERT(MolToSmiles(*normalized2) == "CS(C)(=O)=O");
BOOST_LOG(rdInfoLog) << "Finished" << std::endl;
}
/*
operates on normalized and localized sequences and patterns only
alphabet can be modified
*/
list<string> extendSequence(const list<string>& seq,
string pat) {
list<string> results;
std::string result;
boost::regex_constants::syntax_option_type flags =
boost::regex_constants::perl;
boost::regex re;
boost::smatch what;
pat = "^" + pat;
re.assign(pat, flags);
for (list<string>::const_iterator it = seq.begin(); it!=seq.end(); it++) {
string activeSeq = *it;
Normalizer n;
n.norm(activeSeq);
string input = n.getInput() + "z";
for (int i=0; i<input.length(); i++) {
string ref = activeSeq+input[i]+"~~~~~~~~~~~~~~~~~~";
DBG cout << "pattern " << pat << " against " << ref << endl;
try {
if (regex_search(ref,what,re)) {
string m = what[0];
if (m.length()>activeSeq.length()) {
string bit;
bit += input[i];
string ext = activeSeq + n.norm(bit);
DBG cout << " got something " << ext << endl;
results.push_back(string(ext));
}
}
} catch(boost::regex_error& regErr) {
cerr << "regular expression failed: " << regErr.what() << endl;
}
}
}
return results;
}
ExitCodes main_(int, const char **)
{
//-------------------------------------------------------------
// parameter handling
//-------------------------------------------------------------
//input/output files
String in(getStringOption_("in"));
String out(getStringOption_("out"));
//-------------------------------------------------------------
// loading input
//-------------------------------------------------------------
MSExperiment<> exp;
MzMLFile f;
f.setLogType(log_type_);
f.load(in, exp);
//-------------------------------------------------------------
// filter
//-------------------------------------------------------------
Param filter_param = getParam_().copy("algorithm:", true);
writeDebug_("Used filter parameters", filter_param, 3);
Normalizer filter;
filter.setParameters(filter_param);
filter.filterPeakMap(exp);
//-------------------------------------------------------------
// writing output
//-------------------------------------------------------------
//annotate output with data processing info
addDataProcessing_(exp, getProcessingInfo_(DataProcessing::FILTERING));
f.store(out, exp);
return EXECUTION_OK;
}
int main()
{
cout << ">> TEST DATA SET (k=3)" << endl;
rowvec inX = randu<rowvec>(4);
mat dataSet = randu<mat>(4, 4);
ucolvec labels;
labels << 1 << endr << 3 << endr << 2 << endr << 3 << endr;
inX.print("inX");
dataSet.print("dataSet:");
labels.print("labels:");
cout << "answer: " << knn(inX, dataSet, labels, 3) << endl << endl;
cout << ">> RAND DATA SET (k=10)" << endl;
srand ( time(NULL) );
inX = randu<rowvec>(100);
dataSet = randu<mat>(1000000, 100);
labels = arma::conv_to<ucolvec>::from(4 * randu<colvec>(1000000));
cout << "0s: " << count(labels.begin(), labels.end(), 0) << endl;
cout << "1s: " << count(labels.begin(), labels.end(), 1) << endl;
cout << "2s: " << count(labels.begin(), labels.end(), 2) << endl;
cout << "3s: " << count(labels.begin(), labels.end(), 3) << endl;
cout << "answer: " << knn(inX, dataSet, labels, 10) << endl << endl;
cout << ">> FILE-BASED DATA SET (k=10)" << endl;
mat data;
data.load("datingTestSet2.txt");
dataSet = data.submat(0, 0, data.n_rows-1, data.n_cols-2);
Normalizer <double> normalizer;
dataSet = normalizer.normalize(dataSet);
labels = arma::conv_to<ucolvec>::from(data.submat(0, data.n_cols-1, data.n_rows-1, data.n_cols-1));
rowvec inX1, inX2, inX3;
inX1 << 58732 << 2.454285 << 0.222380 << endr;
inX2 << 6121 << 8.339588 << 1.443357 << endr;
inX3 << 36800 << 12.45 << 0.64 << endr;
cout << "example from the 1st class:" << inX1 << "answer: " << knn(normalizer.normalize(inX1), dataSet, labels, 10) << endl << endl;
cout << "example from the 2nd class:" << inX2 << "answer: " << knn(normalizer.normalize(inX2), dataSet, labels, 10) << endl << endl;
cout << "example from the 3rd class:" << inX3 << "answer: " << knn(normalizer.normalize(inX3), dataSet, labels, 10) << endl << endl;
return 0;
}
vector<int> extendSequence(const vector<int>& seq,
int ct) {
vector<int> result;
Normalizer n;
int at = 0;
map<int,char> lower;
map<char,int> revLower;
for (vector<int>::const_iterator it = seq.begin();
it!=seq.end(); it++) {
int v = *it;
if (lower.find(v)==lower.end()) {
char ch = n.toChar(at);
if (ch==-1) {
printf("Too many units in symbolic sequence\n");
}
lower[v] = ch;
revLower[ch] = v;
at++;
}
}
if (at>10) {
// alternate mode: just look for best prior
int hist = seq.size()-1;
for (int i=0; i<ct; i++) {
int bestHits = -1;
int bestAt = 0;
for (int j=0; j<seq.size(); j++) {
int hits = 0;
for (int k=0; k<=hist; k++) {
if (j-k-1<0) {
break;
}
if (seq[j-k-1]!=seq[hist-k]) {
break;
}
hits++;
}
if (hits>bestHits) {
bestAt = j;
bestHits = hits;
}
}
hist = bestAt;
result.push_back(seq[hist]);
}
cerr << "Did alternative search" << endl;
cerr << "Got: ";
for (int i=0; i<result.size(); i++) {
cerr << result[i] << " ";
}
cerr << endl;
return result;
}
string strSeq;
for (vector<int>::const_iterator it = seq.begin();
it!=seq.end(); it++) {
strSeq += lower[*it];
}
string pat = sequenceToPattern(strSeq);
string ext = extendSequence(strSeq,pat,ct);
map<char,int> novel;
int novelAt = 1;
for (int i=0; i<ext.length(); i++) {
char ch = ext[i];
int v = 0;
if (revLower.find(ch)==revLower.end()) {
if (novel.find(ch)==novel.end()) {
novel[ch] = novelAt;
novelAt++;
}
v = -novel[ch];
} else {
v = revLower[ch];
}
result.push_back(v);
}
return result;
}
std::string extendSequence(std::string seq, std::string pattern, int len) {
srand (std::time(0));
checkSequence(seq);
Normalizer n;
int pruneLen = 100;
seq = n.norm(seq);
pattern = n.norm(pattern);
string refPattern = pattern;
pattern = localizePattern(pattern);
DBG cout << "extend " << seq << " with " << pattern << endl;
n.add("ABCDEFGHIJKLMNOPQRSTUVWXYZ");
list<string> lst;
lst.push_back(seq);
for (int k=0; k<len; k++) {
lst = extendSequence(lst,pattern);
list<string> lst2;
for (list<string>::const_iterator it = lst.begin(); it!=lst.end();
it++) {
string nextSeq = *it;
string nextPat = refPattern;
if (nextSeq.length()<=10) {
nextPat = sequenceToPattern(nextSeq);
}
if (nextPat==refPattern) {
lst2.push_back(nextSeq);
} else {
DBG cout << nextSeq << ": " << "mismatch " << nextPat << " versus " << refPattern << endl;
}
}
if (lst2.size()>0) {
lst = lst2;
}
if (lst.size()>pruneLen) {
DBG cout << "NEED TO PRUNE" << endl;
vector<string> v(lst.begin(),lst.end());
random_shuffle(v.begin(),v.end());
lst.clear();
lst = list<string>(v.begin(),v.begin()+pruneLen);
//lst.erase((++(++(lst.begin()))),lst.end());
}
DBG {
cout << "possibilities: " << endl;
for (list<string>::const_iterator it = lst.begin(); it!=lst.end();
it++) {
cout << " -- " << n.denorm(*it) << endl;
}
}
}
for (list<string>::const_iterator it = lst.begin(); it!=lst.end();
it++) {
DBG cout << " final possibility " << n.denorm(*it) << endl;
}
vector<string> v(lst.begin(),lst.end());
random_shuffle(v.begin(),v.end());
if (v.size()>0) {
string result = n.denorm(v[0]);
result = result.substr(seq.length(),result.length());
return result;
}
return "";
}
void CompNovoIdentificationCID::getIdentification(PeptideIdentification & id, const PeakSpectrum & CID_spec)
{
//if (CID_spec.getPrecursors().begin()->getMZ() > 1000.0)
//{
//cerr << "Weight of precursor has been estimated to exceed 2000.0 Da which is the current limit" << endl;
//return;
//}
PeakSpectrum new_CID_spec(CID_spec);
windowMower_(new_CID_spec, 0.3, 1);
Param zhang_param;
zhang_param = zhang_.getParameters();
zhang_param.setValue("tolerance", fragment_mass_tolerance_);
zhang_param.setValue("use_gaussian_factor", "true");
zhang_param.setValue("use_linear_factor", "false");
zhang_.setParameters(zhang_param);
Normalizer normalizer;
Param n_param(normalizer.getParameters());
n_param.setValue("method", "to_one");
normalizer.setParameters(n_param);
normalizer.filterSpectrum(new_CID_spec);
Size charge(2);
double precursor_weight(0); // [M+H]+
if (!CID_spec.getPrecursors().empty())
{
// believe charge of spectrum?
if (CID_spec.getPrecursors().begin()->getCharge() != 0)
{
charge = CID_spec.getPrecursors().begin()->getCharge();
}
else
{
// TODO estimate charge state
}
precursor_weight = CID_spec.getPrecursors().begin()->getMZ() * charge - ((charge - 1) * Constants::PROTON_MASS_U);
}
//cerr << "charge=" << charge << ", [M+H]=" << precursor_weight << endl;
// now delete all peaks that are right of the estimated precursor weight
Size peak_counter(0);
for (PeakSpectrum::ConstIterator it = new_CID_spec.begin(); it != new_CID_spec.end(); ++it, ++peak_counter)
{
if (it->getPosition()[0] > precursor_weight)
{
break;
}
}
if (peak_counter < new_CID_spec.size())
{
new_CID_spec.resize(peak_counter);
}
static double oxonium_mass = EmpiricalFormula("H2O+").getMonoWeight();
Peak1D p;
p.setIntensity(1);
p.setPosition(oxonium_mass);
new_CID_spec.push_back(p);
p.setPosition(precursor_weight);
new_CID_spec.push_back(p);
// add complement to spectrum
/*
for (PeakSpectrum::ConstIterator it1 = CID_spec.begin(); it1 != CID_spec.end(); ++it1)
{
// get m/z of complement
double mz_comp = precursor_weight - it1->getPosition()[0] + Constants::PROTON_MASS_U;
// search if peaks are available that have similar m/z values
Size count(0);
bool found(false);
for (PeakSpectrum::ConstIterator it2 = CID_spec.begin(); it2 != CID_spec.end(); ++it2, ++count)
{
if (fabs(mz_comp - it2->getPosition()[0]) < fragment_mass_tolerance)
{
// add peak intensity to corresponding peak in new_CID_spec
new_CID_spec[count].setIntensity(new_CID_spec[count].getIntensity());
}
}
if (!found)
{
// infer this peak
Peak1D p;
p.setIntensity(it1->getIntensity());
p.setPosition(mz_comp);
new_CID_spec.push_back(p);
}
}*/
CompNovoIonScoringCID ion_scoring;
Param ion_scoring_param(ion_scoring.getParameters());
ion_scoring_param.setValue("fragment_mass_tolerance", fragment_mass_tolerance_);
ion_scoring_param.setValue("precursor_mass_tolerance", precursor_mass_tolerance_);
ion_scoring_param.setValue("decomp_weights_precision", decomp_weights_precision_);
ion_scoring_param.setValue("double_charged_iso_threshold", (double)param_.getValue("double_charged_iso_threshold"));
ion_scoring_param.setValue("max_isotope_to_score", param_.getValue("max_isotope_to_score"));
ion_scoring_param.setValue("max_isotope", max_isotope_);
ion_scoring.setParameters(ion_scoring_param);
Map<double, IonScore> ion_scores;
ion_scoring.scoreSpectrum(ion_scores, new_CID_spec, precursor_weight, charge);
new_CID_spec.sortByPosition();
/*
cerr << "Size of ion_scores " << ion_scores.size() << endl;
for (Map<double, IonScore>::const_iterator it = ion_scores.begin(); it != ion_scores.end(); ++it)
{
cerr << it->first << " " << it->second.score << endl;
}*/
#ifdef WRITE_SCORED_SPEC
PeakSpectrum filtered_spec(new_CID_spec);
filtered_spec.clear();
for (Map<double, CompNovoIonScoringCID::IonScore>::const_iterator it = ion_scores.begin(); it != ion_scores.end(); ++it)
{
Peak1D p;
p.setIntensity(it->second.score);
p.setPosition(it->first);
filtered_spec.push_back(p);
}
DTAFile().store("spec_scored.dta", filtered_spec);
#endif
set<String> sequences;
getDecompositionsDAC_(sequences, 0, new_CID_spec.size() - 1, precursor_weight, new_CID_spec, ion_scores);
#ifdef SPIKE_IN
sequences.insert("AFCVDGEGR");
sequences.insert("APEFAAPWPDFVPR");
sequences.insert("AVKQFEESQGR");
sequences.insert("CCTESLVNR");
sequences.insert("DAFLGSFLYEYSR");
sequences.insert("DAIPENLPPLTADFAEDK");
sequences.insert("DDNKVEDIWSFLSK");
sequences.insert("DDPHACYSTVFDK");
sequences.insert("DEYELLCLDGSR");
sequences.insert("DGAESYKELSVLLPNR");
sequences.insert("DGASCWCVDADGR");
sequences.insert("DLFIPTCLETGEFAR");
sequences.insert("DTHKSEIAHR");
sequences.insert("DVCKNYQEAK");
sequences.insert("EACFAVEGPK");
sequences.insert("ECCHGDLLECADDR");
sequences.insert("EFLGDKFYTVISSLK");
sequences.insert("EFTPVLQADFQK");
sequences.insert("ELFLDSGIFQPMLQGR");
sequences.insert("ETYGDMADCCEK");
sequences.insert("EVGCPSSSVQEMVSCLR");
sequences.insert("EYEATLEECCAK");
sequences.insert("FADLIQSGTFQLHLDSK");
sequences.insert("FFSASCVPGATIEQK");
sequences.insert("FLANVSTVLTSK");
sequences.insert("FLSGSDYAIR");
sequences.insert("FTASCPPSIK");
sequences.insert("GAIEWEGIESGSVEQAVAK");
sequences.insert("GDVAFIQHSTVEENTGGK");
sequences.insert("GEPPSCAEDQSCPSER");
sequences.insert("GEYVPTSLTAR");
sequences.insert("GQEFTITGQKR");
sequences.insert("GTFAALSELHCDK");
sequences.insert("HLVDEPQNLIK");
sequences.insert("HQDCLVTTLQTQPGAVR");
sequences.insert("HTTVNENAPDQK");
sequences.insert("ILDCGSPDTEVR");
sequences.insert("KCPSPCQLQAER");
sequences.insert("KGTEFTVNDLQGK");
sequences.insert("KQTALVELLK");
sequences.insert("KVPQVSTPTLVEVSR");
sequences.insert("LALQFTTNAKR");
sequences.insert("LCVLHEKTPVSEK");
sequences.insert("LFTFHADICTLPDTEK");
sequences.insert("LGEYGFQNALIVR");
sequences.insert("LHVDPENFK");
sequences.insert("LKECCDKPLLEK");
sequences.insert("LKHLVDEPQNLIK");
sequences.insert("LKPDPNTLCDEFK");
sequences.insert("LLGNVLVVVLAR");
sequences.insert("LLVVYPWTQR");
sequences.insert("LRVDPVNFK");
sequences.insert("LTDEELAFPPLSPSR");
sequences.insert("LVNELTEFAK");
sequences.insert("MFLSFPTTK");
sequences.insert("MPCTEDYLSLILNR");
sequences.insert("NAPYSGYSGAFHCLK");
sequences.insert("NECFLSHKDDSPDLPK");
sequences.insert("NEPNKVPACPGSCEEVK");
sequences.insert("NLQMDDFELLCTDGR");
sequences.insert("QAGVQAEPSPK");
sequences.insert("RAPEFAAPWPDFVPR");
sequences.insert("RHPEYAVSVLLR");
sequences.insert("RPCFSALTPDETYVPK");
sequences.insert("RSLLLAPEEGPVSQR");
sequences.insert("SAFPPEPLLCSVQR");
sequences.insert("SAGWNIPIGTLLHR");
sequences.insert("SCWCVDEAGQK");
sequences.insert("SGNPNYPHEFSR");
sequences.insert("SHCIAEVEK");
sequences.insert("SISSGFFECER");
sequences.insert("SKYLASASTMDHAR");
sequences.insert("SLHTLFGDELCK");
sequences.insert("SLLLAPEEGPVSQR");
sequences.insert("SPPQCSPDGAFRPVQCK");
sequences.insert("SREGDPLAVYLK");
sequences.insert("SRQIPQCPTSCER");
sequences.insert("TAGTPVSIPVCDDSSVK");
sequences.insert("TCVADESHAGCEK");
sequences.insert("TQFGCLEGFGR");
sequences.insert("TVMENFVAFVDK");
sequences.insert("TYFPHFDLSHGSAQVK");
sequences.insert("TYMLAFDVNDEK");
sequences.insert("VDEVGGEALGR");
sequences.insert("VDLLIGSSQDDGLINR");
sequences.insert("VEDIWSFLSK");
sequences.insert("VGGHAAEYGAEALER");
sequences.insert("VGTRCCTKPESER");
sequences.insert("VKVDEVGGEALGR");
sequences.insert("VKVDLLIGSSQDDGLINR");
sequences.insert("VLDSFSNGMK");
sequences.insert("VLSAADKGNVK");
sequences.insert("VPQVSTPTLVEVSR");
sequences.insert("VTKCCTESLVNR");
sequences.insert("VVAASDASQDALGCVK");
sequences.insert("VVAGVANALAHR");
sequences.insert("YICDNQDTISSK");
sequences.insert("YLASASTMDHAR");
sequences.insert("YNGVFQECCQAEDK");
#endif
SpectrumAlignmentScore spectra_zhang;
spectra_zhang.setParameters(zhang_param);
vector<PeptideHit> hits;
Size missed_cleavages = param_.getValue("missed_cleavages");
for (set<String>::const_iterator it = sequences.begin(); it != sequences.end(); ++it)
{
Size num_missed = countMissedCleavagesTryptic_(*it);
if (missed_cleavages < num_missed)
{
//cerr << "Two many missed cleavages: " << *it << ", found " << num_missed << ", allowed " << missed_cleavages << endl;
continue;
}
PeakSpectrum CID_sim_spec;
getCIDSpectrum_(CID_sim_spec, *it, charge);
//normalizer.filterSpectrum(CID_sim_spec);
double cid_score = zhang_(CID_sim_spec, CID_spec);
PeptideHit hit;
hit.setScore(cid_score);
hit.setSequence(getModifiedAASequence_(*it));
hit.setCharge((Int)charge); //TODO unify charge interface: int or size?
hits.push_back(hit);
//cerr << getModifiedAASequence_(*it) << " " << cid_score << " " << endl;
}
// rescore the top hits
id.setHits(hits);
id.assignRanks();
hits = id.getHits();
SpectrumAlignmentScore alignment_score;
Param align_param(alignment_score.getParameters());
align_param.setValue("tolerance", fragment_mass_tolerance_);
align_param.setValue("use_linear_factor", "true");
alignment_score.setParameters(align_param);
for (vector<PeptideHit>::iterator it = hits.begin(); it != hits.end(); ++it)
{
//cerr << "Pre: " << it->getRank() << " " << it->getSequence() << " " << it->getScore() << " " << endl;
}
Size number_of_prescoring_hits = param_.getValue("number_of_prescoring_hits");
if (hits.size() > number_of_prescoring_hits)
{
hits.resize(number_of_prescoring_hits);
}
for (vector<PeptideHit>::iterator it = hits.begin(); it != hits.end(); ++it)
{
PeakSpectrum CID_sim_spec;
getCIDSpectrum_(CID_sim_spec, getModifiedStringFromAASequence_(it->getSequence()), charge);
normalizer.filterSpectrum(CID_sim_spec);
//DTAFile().store("sim_specs/" + it->getSequence().toUnmodifiedString() + "_sim_CID.dta", CID_sim_spec);
//double cid_score = spectra_zhang(CID_sim_spec, CID_spec);
double cid_score = alignment_score(CID_sim_spec, CID_spec);
//cerr << "Final: " << it->getSequence() << " " << cid_score << endl;
it->setScore(cid_score);
}
id.setHits(hits);
id.assignRanks();
hits = id.getHits();
for (vector<PeptideHit>::iterator it = hits.begin(); it != hits.end(); ++it)
{
//cerr << "Fin: " << it->getRank() << " " << it->getSequence() << " " << it->getScore() << " " << endl;
}
Size number_of_hits = param_.getValue("number_of_hits");
if (id.getHits().size() > number_of_hits)
{
hits.resize(number_of_hits);
}
id.setHits(hits);
id.assignRanks();
return;
}
int main(int /*argc*/, char ** /*argv*/) {
Normalizer *normalizer = new Normalizer();
DOMDocument *doc = normalizer->createDocument();
bool *tmpTrue = new bool(true);
bool *tmpFalse = new bool(false);
DOMElement* docFirstElement = doc->createElementNS(X("http://www.test.com"),X("docEle"));
doc->appendChild(docFirstElement);
DOMElement* docFirstElementChild = doc->createElementNS(X("http://www.test2.com"),X("docEleChild"));
docFirstElement->appendChild(docFirstElementChild);
//create default ns
doc->normalizeDocument();
normalizer->serializeNode(doc);
XERCES_STD_QUALIFIER cout << "\n\n";
//add in binding
docFirstElement->setPrefix(X("po"));
doc->normalizeDocument();
normalizer->serializeNode(doc);
XERCES_STD_QUALIFIER cout << "\n\n";
//use default
DOMElement* docFirstElementChildChild = doc->createElementNS(X("http://www.test2.com"),X("docEleChildChild"));
docFirstElementChild->appendChild(docFirstElementChildChild);
doc->normalizeDocument();
normalizer->serializeNode(doc);
XERCES_STD_QUALIFIER cout << "\n\n";
// this block is needed to destroy the XMLBuffer
{
//use a binding
XMLBuffer buf;
buf.set(XMLUni::fgXMLNSString);
buf.append(chColon);
buf.append(X("po2"));
docFirstElementChild->removeAttributeNS(XMLUni::fgXMLNSURIName, XMLUni::fgXMLNSString);
docFirstElement->removeAttributeNS(XMLUni::fgXMLNSURIName, XMLUni::fgXMLNSString);
docFirstElement->setAttributeNS(XMLUni::fgXMLNSURIName, buf.getRawBuffer(), X("http://www.test2.com"));
docFirstElementChild->setPrefix(X("po2"));
doc->normalizeDocument();
normalizer->serializeNode(doc);
XERCES_STD_QUALIFIER cout << "\n\n";
}
//some siblngs to ensure the scope stacks are working
docFirstElementChildChild = doc->createElementNS(X("http://www.test3.com"),X("docEleChildChild2"));
docFirstElementChild->appendChild(docFirstElementChildChild);
docFirstElementChildChild = doc->createElementNS(X("http://www.test4.com"),X("po4:docEleChildChild3"));
docFirstElementChild->appendChild(docFirstElementChildChild);
docFirstElementChildChild = doc->createElementNS(X("http://www.test4.com"),X("po4:docEleChildChild4"));
docFirstElementChild->appendChild(docFirstElementChildChild);
doc->normalizeDocument();
normalizer->serializeNode(doc);
XERCES_STD_QUALIFIER cout << "\n\n";
//conflicting prefix
docFirstElementChildChild->setAttributeNS(XMLUni::fgXMLNSURIName, X("po4"), X("conflict"));
doc->normalizeDocument();
normalizer->serializeNode(doc);
XERCES_STD_QUALIFIER cout << "\n\n";
//conflicting default
docFirstElementChildChild = doc->createElementNS(X("http://www.test4.com"),X("docEleChildChild5"));
docFirstElementChild->appendChild(docFirstElementChildChild);
docFirstElementChildChild->setAttributeNS(XMLUni::fgXMLNSURIName, XMLUni::fgXMLNSString, X("conflict"));
doc->normalizeDocument();
normalizer->serializeNode(doc);
XERCES_STD_QUALIFIER cout << "\n\n";
//set the xmlns to ""
DOMElement *noNamespaceEle = doc->createElementNS(X(""),X("noNamespace"));
docFirstElementChildChild->appendChild(noNamespaceEle);
doc->normalizeDocument();
normalizer->serializeNode(doc);
XERCES_STD_QUALIFIER cout << "\n\n";
//now lets do a bit off attribute testing on the doc ele
docFirstElement->setAttributeNS(X("http://testattr.com"), X("attr1"), X("value"));
docFirstElement->setAttributeNS(X("http://testattr.com"), X("attr2"), X("value"));
docFirstElement->setAttributeNS(X("http://testattr2.com"), X("attr3"), X("value"));
docFirstElement->setAttributeNS(X("http://www.test.com"), X("attr4"), X("value"));
docFirstElement->setAttributeNS(X("http://testattr2.com"), X("po:attr5"), X("value"));
docFirstElement->setAttributeNS(X("http://testattr2.com"), X("poFake:attr6"), X("value"));
docFirstElement->setAttributeNS(X("http://testattr3.com"), X("po3:attr7"), X("value"));
doc->normalizeDocument();
normalizer->serializeNode(doc);
XERCES_STD_QUALIFIER cout << "\n\n";
//and now on one of its children
docFirstElementChildChild->setAttributeNS(X("http://testattr.com"), X("attr1"), X("value"));
docFirstElementChildChild->setAttributeNS(X("http://testattr.com"), X("attr2"), X("value"));
docFirstElementChildChild->setAttributeNS(X("http://testattr2.com"), X("attr3"), X("value"));
docFirstElementChildChild->setAttributeNS(X("http://www.test.com"), X("attr4"), X("value"));
docFirstElementChildChild->setAttributeNS(X("http://testattr2.com"), X("po:attr5"), X("value"));
docFirstElementChildChild->setAttributeNS(X("http://testattr2.com"), X("poFake:attr6"), X("value"));
docFirstElementChildChild->setAttributeNS(X("http://testattr3.com"), X("po3:attr7"), X("value"));
docFirstElementChildChild->setAttributeNS(X("http://testattr4.com"), X("po4:attr8"), X("value"));
//test for a clash with our NSx attrs
docFirstElementChildChild->setAttributeNS(X("http://testclash.com"), X("NS1:attr9"), X("value"));
docFirstElementChildChild->setAttributeNS(XMLUni::fgXMLNSURIName, X("xmlns:NS1"), X("http://testclash.com"));
//clash with standard prefix
docFirstElementChildChild->setAttributeNS(X("http://testattr5.com"), X("po:attr10"), X("value"));
doc->normalizeDocument();
normalizer->serializeNode(doc);
XERCES_STD_QUALIFIER cout << "\n\n";
//2 prefix with the same uri
docFirstElementChildChild = doc->createElementNS(X("http://www.uri1.com"),X("docEleChildChild6"));
docFirstElementChild->appendChild(docFirstElementChildChild);
docFirstElementChildChild->setAttributeNS(XMLUni::fgXMLNSURIName, X("xmlns:uri1"), X("http://www.uri1.com"));
docFirstElementChildChild->setAttributeNS(XMLUni::fgXMLNSURIName, X("xmlns:uri1b"), X("http://www.uri1.com"));
docFirstElementChildChild->setAttributeNS(X("http://www.uri1.com"), X("uri1:attr1"), X("value"));
docFirstElementChildChild->setAttributeNS(X("http://www.uri1.com"), X("uri1b:attr2"), X("value"));
doc->normalizeDocument();
normalizer->serializeNode(doc);
XERCES_STD_QUALIFIER cout << "\n\n";
//check to see we use the nearest binding and for more inheritence
DOMElement *docFirstElementChildChildChild = doc->createElementNS(X("http://www.uri1.com"),X("docEleChildChildChild"));
docFirstElementChildChild->appendChild(docFirstElementChildChildChild);
docFirstElementChildChild->setAttributeNS(XMLUni::fgXMLNSURIName, X("xmlns:nearerThanPo"), X("http://www.test.com"));
docFirstElementChildChildChild->setAttributeNS(X("http://testattr.com"), X("attr2"), X("value"));
docFirstElementChildChildChild->setAttributeNS(X("http://www.test.com"), X("attr1"), X("value"));
doc->normalizeDocument();
normalizer->serializeNode(doc);
XERCES_STD_QUALIFIER cout << "\n\n";
//NS1.1 stuff
//test creating default prefix when NS1 has been set to ""
noNamespaceEle->setAttributeNS(XMLUni::fgXMLNSURIName, X("xmlns:NS1"), X(""));
DOMElement *noNamespaceChild = doc->createElementNS(X("http://testclash.com"),X("testing1.1Stuff"));
noNamespaceEle->appendChild(noNamespaceChild);
doc->normalizeDocument();
normalizer->serializeNode(doc);
noNamespaceChild = doc->createElementNS(X("http://testclash.com"),X("NS1:testing1.1Stuff"));
noNamespaceEle->appendChild(noNamespaceChild);
noNamespaceChild->setAttributeNS(X("http://www.someRandomUri.com"), X("attr"), X("value"));
doc->normalizeDocument();
normalizer->serializeNode(doc);
//check error conditions
XERCES_STD_QUALIFIER cout << "error conditions" << XERCES_STD_QUALIFIER endl;
DOMConfiguration *conf = doc->getDOMConfig();
conf->setParameter(XMLUni::fgDOMErrorHandler, normalizer);
conf->setParameter(XMLUni::fgDOMNamespaces, true);
DOMElement *level1Node = doc->createElement(X("level1Node"));
docFirstElement->appendChild(level1Node);
doc->normalizeDocument();
docFirstElement->removeChild(level1Node);
docFirstElement->setAttribute(X("level1Attr"), X("level1"));
doc->normalizeDocument();
docFirstElement->removeAttribute(X("level1Attr"));
//cant check this as Xerces does not let us do it
// noNamespaceChild->setAttributeNS(X("http://www.someRandomUri.com"), X("xmlns"), X("value"));
// doc->normalizeDocument();
//lets do a sanity test on a comment
DOMComment *comment = doc->createComment(X("some comment"));
docFirstElement->appendChild(comment);
doc->normalizeDocument();
normalizer->serializeNode(doc);
conf->setParameter(XMLUni::fgDOMComments, false);
docFirstElement->appendChild(comment);
doc->normalizeDocument();
normalizer->serializeNode(doc);
//and on a CDATA
DOMCDATASection *cData = doc->createCDATASection(X("some cdata"));
docFirstElement->appendChild(cData);
doc->normalizeDocument();
normalizer->serializeNode(doc);
conf->setParameter(XMLUni::fgDOMCDATASections, false);
docFirstElement->appendChild(cData);
doc->normalizeDocument();
normalizer->serializeNode(doc);
delete normalizer;
delete tmpTrue;
delete tmpFalse;
return 0;
}
ExitCodes main_(int, const char **)
{
//-------------------------------------------------------------
// parsing parameters
//-------------------------------------------------------------
StringList id_in(getStringList_("id_in"));
StringList in_raw(getStringList_("in"));
Size number_of_bins((UInt)getIntOption_("number_of_bins"));
bool precursor_error_ppm(getFlag_("precursor_error_ppm"));
bool fragment_error_ppm(getFlag_("fragment_error_ppm"));
bool generate_gnuplot_scripts(DataValue(getStringOption_("generate_gnuplot_scripts")).toBool());
if (in_raw.size() != id_in.size())
{
writeLog_("Number of spectrum files and identification files differs...");
return ILLEGAL_PARAMETERS;
}
//-------------------------------------------------------------
// reading input
//-------------------------------------------------------------
vector<vector<PeptideIdentification> > pep_ids;
vector<vector<ProteinIdentification> > prot_ids;
pep_ids.resize(id_in.size());
prot_ids.resize(id_in.size());
IdXMLFile idxmlfile;
for (Size i = 0; i != id_in.size(); ++i)
{
String doc_id;
idxmlfile.load(id_in[i], prot_ids[i], pep_ids[i], doc_id);
}
// read mzML files
vector<RichPeakMap> maps_raw;
maps_raw.resize(in_raw.size());
MzMLFile mzml_file;
for (Size i = 0; i != in_raw.size(); ++i)
{
mzml_file.load(in_raw[i], maps_raw[i]);
}
//-------------------------------------------------------------
// calculations
//-------------------------------------------------------------
// mapping ids
IDMapper mapper;
for (Size i = 0; i != maps_raw.size(); ++i)
{
mapper.annotate(maps_raw[i], pep_ids[i], prot_ids[i]);
}
// normalize the spectra
Normalizer normalizer;
for (vector<RichPeakMap>::iterator it1 = maps_raw.begin(); it1 != maps_raw.end(); ++it1)
{
for (RichPeakMap::Iterator it2 = it1->begin(); it2 != it1->end(); ++it2)
{
normalizer.filterSpectrum(*it2);
}
}
// generate precursor statistics
vector<MassDifference> precursor_diffs;
if (getStringOption_("precursor_out") != "")
{
for (Size i = 0; i != maps_raw.size(); ++i)
{
for (Size j = 0; j != maps_raw[i].size(); ++j)
{
if (maps_raw[i][j].getPeptideIdentifications().empty())
{
continue;
}
for (vector<PeptideIdentification>::const_iterator it = maps_raw[i][j].getPeptideIdentifications().begin(); it != maps_raw[i][j].getPeptideIdentifications().end(); ++it)
{
if (it->getHits().size() > 0)
{
PeptideHit hit = *it->getHits().begin();
MassDifference md;
Int charge = hit.getCharge();
if (charge == 0)
{
charge = 1;
}
md.exp_mz = it->getMZ();
md.theo_mz = (hit.getSequence().getMonoWeight() + (double)charge * Constants::PROTON_MASS_U) / (double)charge;
md.charge = charge;
precursor_diffs.push_back(md);
}
}
}
}
}
// generate fragment ions statistics
vector<MassDifference> fragment_diffs;
TheoreticalSpectrumGenerator tsg;
SpectrumAlignment sa;
double fragment_mass_tolerance(getDoubleOption_("fragment_mass_tolerance"));
Param sa_param(sa.getParameters());
sa_param.setValue("tolerance", fragment_mass_tolerance);
sa.setParameters(sa_param);
if (getStringOption_("fragment_out") != "")
{
for (Size i = 0; i != maps_raw.size(); ++i)
{
for (Size j = 0; j != maps_raw[i].size(); ++j)
{
if (maps_raw[i][j].getPeptideIdentifications().empty())
{
continue;
}
for (vector<PeptideIdentification>::const_iterator it = maps_raw[i][j].getPeptideIdentifications().begin(); it != maps_raw[i][j].getPeptideIdentifications().end(); ++it)
{
if (it->getHits().size() > 0)
{
PeptideHit hit = *it->getHits().begin();
RichPeakSpectrum theo_spec;
tsg.addPeaks(theo_spec, hit.getSequence(), Residue::YIon);
tsg.addPeaks(theo_spec, hit.getSequence(), Residue::BIon);
vector<pair<Size, Size> > pairs;
sa.getSpectrumAlignment(pairs, theo_spec, maps_raw[i][j]);
//cerr << hit.getSequence() << " " << hit.getSequence().getSuffix(1).getFormula() << " " << hit.getSequence().getSuffix(1).getFormula().getMonoWeight() << endl;
for (vector<pair<Size, Size> >::const_iterator pit = pairs.begin(); pit != pairs.end(); ++pit)
{
MassDifference md;
md.exp_mz = maps_raw[i][j][pit->second].getMZ();
md.theo_mz = theo_spec[pit->first].getMZ();
//cerr.precision(15);
//cerr << md.exp_mz << " " << md.theo_mz << " " << md.exp_mz - md.theo_mz << endl;
md.intensity = maps_raw[i][j][pit->second].getIntensity();
md.charge = hit.getCharge();
fragment_diffs.push_back(md);
}
}
}
}
}
}
//-------------------------------------------------------------
// writing output
//-------------------------------------------------------------
String precursor_out_file(getStringOption_("precursor_out"));
if (precursor_out_file != "")
{
vector<double> errors;
ofstream precursor_out(precursor_out_file.c_str());
double min_diff(numeric_limits<double>::max()), max_diff(numeric_limits<double>::min());
for (Size i = 0; i != precursor_diffs.size(); ++i)
{
double diff = getMassDifference(precursor_diffs[i].theo_mz, precursor_diffs[i].exp_mz, precursor_error_ppm);
precursor_out << diff << "\n";
errors.push_back(diff);
if (diff > max_diff)
{
max_diff = diff;
}
if (diff < min_diff)
{
min_diff = diff;
}
}
precursor_out.close();
// fill histogram with the collected values
double bin_size = (max_diff - min_diff) / (double)number_of_bins;
Histogram<double, double> hist(min_diff, max_diff, bin_size);
for (Size i = 0; i != errors.size(); ++i)
{
hist.inc(errors[i], 1.0);
}
writeDebug_("min_diff=" + String(min_diff) + ", max_diff=" + String(max_diff) + ", number_of_bins=" + String(number_of_bins), 1);
// transform the histogram into a vector<DPosition<2> > for the fitting
vector<DPosition<2> > values;
for (Size i = 0; i != hist.size(); ++i)
{
DPosition<2> p;
p.setX((double)i / (double)number_of_bins * (max_diff - min_diff) + min_diff);
p.setY(hist[i]);
values.push_back(p);
}
double mean = Math::mean(errors.begin(), errors.end());
double abs_dev = Math::absdev(errors.begin(), errors.end(), mean);
double sdv = Math::sd(errors.begin(), errors.end(), mean);
sort(errors.begin(), errors.end());
double median = errors[(Size)(errors.size() / 2.0)];
writeDebug_("Precursor mean error: " + String(mean), 1);
writeDebug_("Precursor abs. dev.: " + String(abs_dev), 1);
writeDebug_("Precursor std. dev.: " + String(sdv), 1);
writeDebug_("Precursor median error: " + String(median), 1);
// calculate histogram for gauss fitting
GaussFitter gf;
GaussFitter::GaussFitResult init_param (hist.maxValue(), median, sdv/500.0);
gf.setInitialParameters(init_param);
try
{
gf.fit(values);
// write gnuplot scripts
if (generate_gnuplot_scripts)
{
ofstream out(String(precursor_out_file + "_gnuplot.dat").c_str());
for (vector<DPosition<2> >::const_iterator it = values.begin(); it != values.end(); ++it)
{
out << it->getX() << " " << it->getY() << endl;
}
out.close();
ofstream gpl_out(String(precursor_out_file + "_gnuplot.gpl").c_str());
gpl_out << "set terminal png" << endl;
gpl_out << "set output \"" << precursor_out_file << "_gnuplot.png\"" << endl;
if (precursor_error_ppm)
{
gpl_out << "set xlabel \"error in ppm\"" << endl;
}
else
{
gpl_out << "set xlabel \"error in Da\"" << endl;
}
gpl_out << "set ylabel \"frequency\"" << endl;
gpl_out << "plot '" << precursor_out_file << "_gnuplot.dat' title 'Precursor mass error distribution' w boxes, f(x) w lp title 'Gaussian fit of the error distribution'" << endl;
gpl_out.close();
}
}
catch (Exception::UnableToFit)
{
writeLog_("Unable to fit a Gaussian distribution to the precursor mass errors");
}
}
String fragment_out_file(getStringOption_("fragment_out"));
if (fragment_out_file != "")
{
vector<double> errors;
ofstream fragment_out(fragment_out_file.c_str());
double min_diff(numeric_limits<double>::max()), max_diff(numeric_limits<double>::min());
for (Size i = 0; i != fragment_diffs.size(); ++i)
{
double diff = getMassDifference(fragment_diffs[i].theo_mz, fragment_diffs[i].exp_mz, fragment_error_ppm);
fragment_out << diff << endl;
errors.push_back(diff);
if (diff > max_diff)
{
max_diff = diff;
}
if (diff < min_diff)
{
min_diff = diff;
}
}
fragment_out.close();
// fill histogram with the collected values
// here we use the intensities to scale the error
// low intensity peaks are likely to be random matches
double bin_size = (max_diff - min_diff) / (double)number_of_bins;
Histogram<double, double> hist(min_diff, max_diff, bin_size);
for (Size i = 0; i != fragment_diffs.size(); ++i)
{
double diff = getMassDifference(fragment_diffs[i].theo_mz, fragment_diffs[i].exp_mz, fragment_error_ppm);
hist.inc(diff, fragment_diffs[i].intensity);
}
writeDebug_("min_diff=" + String(min_diff) + ", max_diff=" + String(max_diff) + ", number_of_bins=" + String(number_of_bins), 1);
// transform the histogram into a vector<DPosition<2> > for the fitting
vector<DPosition<2> > values;
for (Size i = 0; i != hist.size(); ++i)
{
DPosition<2> p;
p.setX((double)i / (double)number_of_bins * (max_diff - min_diff) + min_diff);
p.setY(hist[i]);
values.push_back(p);
}
double mean = Math::mean(errors.begin(), errors.end());
double abs_dev = Math::absdev(errors.begin(), errors.end(), mean);
double sdv = Math::sd(errors.begin(), errors.end(), mean);
sort(errors.begin(), errors.end());
double median = errors[(Size)(errors.size() / 2.0)];
writeDebug_("Fragment mean error: " + String(mean), 1);
writeDebug_("Fragment abs. dev.: " + String(abs_dev), 1);
writeDebug_("Fragment std. dev.: " + String(sdv), 1);
writeDebug_("Fragment median error: " + String(median), 1);
// calculate histogram for gauss fitting
GaussFitter gf;
GaussFitter::GaussFitResult init_param (hist.maxValue(), median, sdv / 100.0);
gf.setInitialParameters(init_param);
try
{
gf.fit(values);
// write gnuplot script
if (generate_gnuplot_scripts)
{
ofstream out(String(fragment_out_file + "_gnuplot.dat").c_str());
for (vector<DPosition<2> >::const_iterator it = values.begin(); it != values.end(); ++it)
{
out << it->getX() << " " << it->getY() << endl;
}
out.close();
ofstream gpl_out(String(fragment_out_file + "_gnuplot.gpl").c_str());
gpl_out << "set terminal png" << endl;
gpl_out << "set output \"" << fragment_out_file << "_gnuplot.png\"" << endl;
if (fragment_error_ppm)
{
gpl_out << "set xlabel \"error in ppm\"" << endl;
}
else
{
gpl_out << "set xlabel \"error in Da\"" << endl;
}
gpl_out << "set ylabel \"frequency\"" << endl;
gpl_out << "plot '" << fragment_out_file << "_gnuplot.dat' title 'Fragment mass error distribution' w boxes, f(x) w lp title 'Gaussian fit of the error distribution'" << endl;
gpl_out.close();
}
}
catch (Exception::UnableToFit)
{
writeLog_("Unable to fit a Gaussian distribution to the fragment mass errors");
}
}
return EXECUTION_OK;
}
Normalizer* e_ptr = 0;
Normalizer* e_nullPointer = 0;
START_SECTION((Normalizer()))
e_ptr = new Normalizer;
TEST_NOT_EQUAL(e_ptr, e_nullPointer)
END_SECTION
START_SECTION((~Normalizer()))
delete e_ptr;
END_SECTION
e_ptr = new Normalizer();
START_SECTION((Normalizer(const Normalizer& source)))
Normalizer copy(*e_ptr);
TEST_EQUAL(copy.getParameters(), e_ptr->getParameters())
TEST_EQUAL(copy.getName(), e_ptr->getName())
END_SECTION
START_SECTION((Normalizer& operator = (const Normalizer& source)))
Normalizer copy;
copy = *e_ptr;
TEST_EQUAL(copy.getParameters(), e_ptr->getParameters())
TEST_EQUAL(copy.getName(), e_ptr->getName())
END_SECTION
START_SECTION((template<typename SpectrumType> void filterSpectrum(SpectrumType& spectrum)))
DTAFile dta_file;
PeakSpectrum spec;
dta_file.load(OPENMS_GET_TEST_DATA_PATH("Transformers_tests.dta"), spec);
TEST_EQUAL(copy.getName(), ptr->getName());
TEST_EQUAL(copy.getParameters(), ptr->getParameters());
END_SECTION
START_SECTION(ZhangSimilarityScore& operator = (const ZhangSimilarityScore& source))
ZhangSimilarityScore copy;
copy = *ptr;
TEST_EQUAL(copy.getName(), ptr->getName());
TEST_EQUAL(copy.getParameters(), ptr->getParameters());
END_SECTION
START_SECTION(double operator () (const PeakSpectrum& spec) const)
PeakSpectrum s1;
DTAFile().load(OPENMS_GET_TEST_DATA_PATH("PILISSequenceDB_DFPIANGER_1.dta"), s1);
Normalizer normalizer;
Param p(normalizer.getParameters());
p.setValue("method", "to_one");
normalizer.setParameters(p);
normalizer.filterSpectrum(s1);
double score = (*ptr)(s1);
TEST_REAL_SIMILAR(score, 1.82682);
END_SECTION
START_SECTION(double operator () (const PeakSpectrum& spec1, const PeakSpectrum& spec2) const)
PeakSpectrum s1, s2;
DTAFile().load(OPENMS_GET_TEST_DATA_PATH("PILISSequenceDB_DFPIANGER_1.dta"), s1);
DTAFile().load(OPENMS_GET_TEST_DATA_PATH("PILISSequenceDB_DFPIANGER_1.dta"), s2);
Normalizer normalizer;
