bool SeqPath::check_if_correct(const string& str, const Config *config) const
{
const vector<mass_t>& aa2mass = config->get_aa2mass();
const char *path_str = seq_str.c_str();
const char *corr_str = str.c_str();
int len_path_str = strlen(path_str);
int len_corr_str = strlen(corr_str);
if (len_path_str>len_corr_str)
return false;
int i;
for (i=0; i<=len_corr_str-len_path_str; i++)
{
int j;
bool correct_seq = true;
for (j=0; j<len_path_str; j++)
if (! (path_str[j] == corr_str[i+j] ||
(path_str[j] == 'I' && corr_str[i+j]== 'L') ||
(path_str[j] == 'L' && corr_str[i+j]== 'I') ||
(path_str[j] == 'Q' && corr_str[i+j]== 'K') ||
(path_str[j] == 'K' && corr_str[i+j]== 'Q') ) )
{
correct_seq = false;
break;
}
if (correct_seq)
{
// check prefix mass
Peptide pep;
pep.parseFromString(config,corr_str);
const vector<int>& aas= pep.get_amino_acids();
mass_t mass=0;
int j;
if (n_term_mass == 0 && i==0)
return true;
for (j=0; j<aas.size(); j++)
{
mass+=aa2mass[aas[j]];
if (fabs(mass-this->n_term_mass)<6)
return true;
if (mass>n_term_mass)
break;
}
}
}
return false;
}
void AllScoreModels::predict_fragmentation( const char* input_file, size_t num_peaks)
{
FILE* stream = fopen(input_file,"r");
if (! stream)
{
cout << "Error: couldn't open file for reading: " << input_file << endl;
exit(1);
}
PeptideRankScorer *dnv_rank = (PeptideRankScorer *)get_rank_model_ptr(1);
PeakRankModel *prm = this->get_peak_prediction_model_ptr(3);
char buffer[128];
char pep_str[128];
while (fgets(buffer,128,stream))
{
int charge;
if (sscanf(buffer,"%s %d",pep_str,&charge) != 2)
continue;
cout << ">> " << pep_str << "\t" << charge << endl;
if (charge<1 || charge>=prm->get_size_thresholds().size())
{
cout << "Invalid charge!" << endl;
continue;
}
Peptide pep;
pep.parseFromString(&config_,static_cast<string>(pep_str));
PeptideSolution sol;
sol.pep = pep;
sol.reaches_n_terminal=true;
sol.reaches_c_terminal=true;
sol.charge = charge;
sol.pm_with_19 = pep.get_mass_with_19();
PeptidePeakPrediction ppp;
prm->calc_peptide_predicted_scores(sol, ppp);
const size_t num_frags = ppp.frag_idxs.size();
vector< vector<int> > predicted_ranks;
calc_combined_peak_ranks(ppp.rank_scores, predicted_ranks);
vector<PeakTuple> tuples;
for (size_t f=0; f<num_frags; f++)
for (size_t i=0; i<ppp.rank_scores[f].size(); i++)
if (predicted_ranks[f][i]<999)
{
PeakTuple pt;
pt.frag_idx = f;
pt.pos =i;
pt.rank = predicted_ranks[f][i];
pt.score = ppp.rank_scores[f][i];
tuples.push_back(pt);
}
sort(tuples.begin(),tuples.end());
if (tuples.size()<1)
continue;
const size_t num_aas = pep.get_num_aas();
vector<mass_t> breakage_masses;
pep.calc_expected_breakage_masses(&config_, breakage_masses);
cout << fixed << "Rank\tIon\tm/z\tScore" << endl;
for (size_t i=0; i<num_peaks && i<tuples.size(); i++)
{
PeakTuple pt = tuples[i];
cout << i+1 << "\t";
const FragmentType& ft = config_.get_fragment(ppp.frag_idxs[pt.frag_idx]);
cout << ft.label << ":" << (ft.orientation == PREFIX ? pt.pos : num_aas - pt.pos) << "\t";
mass_t mz = ft.calc_expected_mass(breakage_masses[pt.pos],pep.get_mass_with_19());
cout << setprecision(2);
if (mz<100)
cout << " ";
if (mz<1000)
cout << " ";
cout << mz << "\t";
cout << setprecision(3) << pt.score << endl;
}
cout << endl;
}
fclose(stream);
}
bool InspectResultsLine::parse_from_fields(Config *config,
const vector<string>& fields)
{
if (fields.size() < 20)
{
cout<< "Error: inspect results line has " << fields.size() << ", expecting 20-22" << endl;
exit(1);
}
SpectrumFile = fields[0];
if (sscanf(fields[1].c_str(),"%d",&scan) != 1 ||
scan<0 || scan>100000000)
error("scan");
Annotation = fields[2];
Protein = fields[3];
if (sscanf(fields[4].c_str(),"%d",&Charge) != 1 ||
Charge<0 || Charge>20)
error("Charge");
if (sscanf(fields[5].c_str(),"%f",&MQScore) != 1 ||
MQScore<NEG_INF || MQScore>POS_INF)
error("MQScore");
if (sscanf(fields[6].c_str(),"%d",&Length) != 1 ||
Length<1 || Length>POS_INF)
error("Length");
if (sscanf(fields[7].c_str(),"%f",&TotalPRMScore) != 1 ||
TotalPRMScore<NEG_INF || TotalPRMScore>POS_INF)
error("TotalPRMScore");
if (sscanf(fields[8].c_str(),"%f",&MedianPRMScore) != 1 ||
MedianPRMScore<NEG_INF || MedianPRMScore>POS_INF)
error("MedianPRMScore");
if (sscanf(fields[9].c_str(),"%f",&FractionY) != 1 ||
FractionY<0 || FractionY>1000)
error("FractionY");
if (sscanf(fields[10].c_str(),"%f",&FractionB) != 1 ||
FractionB<0 || FractionB>1000)
error("FractionB");
if (sscanf(fields[11].c_str(),"%f",&Intensity) != 1 ||
Intensity<0)
error("Intensity");
if (sscanf(fields[12].c_str(),"%d",&NTT) != 1 ||
NTT<0 || NTT>3)
error("NTT");
if (sscanf(fields[13].c_str(),"%f",&p_value) != 1)
error("p_value");
if (sscanf(fields[14].c_str(),"%f",&F_Score) != 1)
error("F_Score");
if (sscanf(fields[15].c_str(),"%f",&DeltaScore) != 1)
error("DeltaScore");
if (sscanf(fields[16].c_str(),"%f",&DeltaScoreOther) != 1)
error("DeltaScoreOther");
if (sscanf(fields[17].c_str(),"%d",&RecordNumber) != 1)
error("RecordNumber");
if (sscanf(fields[18].c_str(),"%d",&DBFilePos) != 1)
error("DBFilePos");
if (sscanf(fields[19].c_str(),"%d",&SpecFilePos) != 1)
error("SpecFilePos");
if (fields.size()>20 && sscanf(fields[20].c_str(),"%f",&PrecursorMz) != 1)
error("SpecFilePos");
if (fields.size()>21 && sscanf(fields[21].c_str(),"%f",&PrecursorError) != 1)
error("SpecFilePos");
Score = MQScore;
const vector<int>& char2aa = config->get_char2aa();
const int ann_length = Annotation.length();
if ((Annotation[1] != '.') || (Annotation[ann_length-2] != '.'))
{
cout << "Error: bad annotation format: " << Annotation << endl;
cout << "Expecting X.XXXXXXXXX.X" << endl;
cout << "Ann1 : " << Annotation[1] << endl;
cout << "Ann n-2: " << Annotation[ann_length-2] << endl;
exit(1);
}
// cout << "|" << Annotation << "|" << endl;
aaBefore = char2aa[Annotation[0]];
aaAfter = char2aa[Annotation[ann_length-1]];
pep.parseFromString(config,Annotation.substr(2,ann_length-4));
return true;
}