void PosteriorEstimator::estimatePEP(
vector<pair<double, bool> >& combined,
double pi0, vector<double>& peps,
bool include_negative) {
// Logistic regression on the data
size_t nTargets = 0, nDecoys = 0;
LogisticRegression lr;
estimate(combined, lr);
vector<double> xvals(0);
vector<pair<double, bool> >::const_iterator elem = combined.begin();
for (; elem != combined.end(); ++elem)
if (elem->second) {
xvals.push_back(elem->first);
++nTargets;
} else {
if (include_negative) {
xvals.push_back(elem->first);
}
++nDecoys;
}
lr.predict(xvals, peps);
#define OUTPUT_DEBUG_FILES
#undef OUTPUT_DEBUG_FILES
#ifdef OUTPUT_DEBUG_FILES
ofstream drFile("decoyRate.all", ios::out), xvalFile("xvals.all", ios::out);
ostream_iterator<double> drIt(drFile, "\n"), xvalIt(xvalFile, "\n");
copy(peps.begin(), peps.end(), drIt);
copy(xvals.begin(), xvals.end(), xvalIt);
#endif
double factor = pi0 * ((double)nTargets / (double)nDecoys);
double top = min(1.0, factor
* exp(*max_element(peps.begin(), peps.end())));
vector<double>::iterator pep = peps.begin();
bool crap = false;
for (; pep != peps.end(); ++pep) {
if (crap) {
*pep = top;
continue;
}
*pep = factor * exp(*pep);
if (*pep >= top) {
*pep = top;
crap = true;
}
}
partial_sum(peps.rbegin(), peps.rend(), peps.rbegin(), mymin);
}
void PosteriorEstimator::estimatePEPGeneralized(
vector<pair<double, bool> >& combined,
vector<double>& peps,
bool include_negative) {
// Logistic regression on the data
size_t nTargets = 0, nDecoys = 0;
LogisticRegression lr;
estimate(combined, lr);
vector<double> xvals(0);
vector<pair<double, bool> >::const_iterator elem = combined.begin();
for (; elem != combined.end(); ++elem) {
xvals.push_back(elem->first);
if (elem->second) {
++nTargets;
} else {
if (include_negative) {
xvals.push_back(elem->first);
}
++nDecoys;
}
}
lr.predict(xvals, peps);
#ifdef OUTPUT_DEBUG_FILES
ofstream drFile("decoyRate.all", ios::out), xvalFile("xvals.all", ios::out);
ostream_iterator<double> drIt(drFile, "\n"), xvalIt(xvalFile, "\n");
copy(peps.begin(), peps.end(), drIt);
copy(xvals.begin(), xvals.end(), xvalIt);
#endif
double top = exp(*max_element(peps.begin(), peps.end()));
top = top/(1+top);
bool crap = false;
vector<double>::iterator pep = peps.begin();
for (; pep != peps.end(); ++pep) {
if (crap) {
*pep = top;
continue;
}
// eg = p/(1-p)
// eg - egp = p
// p = eg/(1+eg)
double eg = exp(*pep);
*pep = eg/(1+eg);
if (*pep >= top) {
*pep = top;
crap = true;
}
}
partial_sum(peps.rbegin(), peps.rend(), peps.rbegin(), mymin);
double high = *max_element(peps.begin(), peps.end());
double low = *min_element(peps.begin(), peps.end());
assert(high>low);
if (VERB > 2) {
cerr << "Highest generalized decoy rate =" << high
<< ", low rate = " << low << endl;
}
pep = peps.begin();
for (; pep != peps.end(); ++pep) {
*pep = (*pep - low)/(high-low);
}
}