int main(int argc, char** argv) {
if (argc < 3) {
cerr << "usage: " << argv[0] << " <vcf file> [FIELD1] [FIELD2] ..." << endl
<< "outputs each record in the vcf file, removing INFO fields not listed on the command line" << endl;
return 1;
}
string filename = argv[1];
set<string> fieldsToKeep;
for (int i = 2; i < argc; ++i) {
fieldsToKeep.insert(argv[i]);
}
VariantCallFile variantFile;
if (filename == "-") {
variantFile.open(std::cin);
} else {
variantFile.open(filename);
}
if (!variantFile.is_open()) {
return 1;
}
Variant var(variantFile);
vector<string> fieldsToErase;
vector<string> infoIds = variantFile.infoIds();
for (vector<string>::iterator i = infoIds.begin(); i != infoIds.end(); ++i) {
if (!fieldsToKeep.count(*i)) {
fieldsToErase.push_back(*i);
variantFile.removeInfoHeaderLine(*i);
}
}
// write the header
cout << variantFile.header << endl;
// print the records, filtering is done via the setting of varA's output sample names
while (variantFile.getNextVariant(var)) {
for (vector<string>::iterator f = fieldsToErase.begin(); f != fieldsToErase.end(); ++f) {
var.info.erase(*f);
var.infoFlags.erase(*f);
}
cout << var << endl;
}
return 0;
}
int main(int argc, char** argv) {
if (argc > 1 && (argv[1] == "-h" || argv[1] == "--help")) {
cerr << "usage: " << argv[0] << " <vcf file>" << endl
<< "outputs a VCF stream where AC and NS have been generated for each record using sample genotypes" << endl;
return 1;
}
VariantCallFile variantFile;
if (argc == 1 || (argc == 2 && argv[1] == "-")) {
variantFile.open(std::cin);
if (!variantFile.is_open()) {
cerr << "vcffixup: could not open stdin" << endl;
return 1;
}
} else {
string filename = argv[1];
variantFile.open(filename);
if (!variantFile.is_open()) {
cerr << "vcffixup: could not open " << filename << endl;
return 1;
}
}
Variant var(variantFile);
// remove header lines we're going to add
variantFile.removeInfoHeaderLine("AC");
variantFile.removeInfoHeaderLine("AF");
variantFile.removeInfoHeaderLine("NS");
variantFile.removeInfoHeaderLine("AN");
// and add them back, so as not to duplicate them if they are already there
variantFile.addHeaderLine("##INFO=<ID=AC,Number=A,Type=Integer,Description=\"Total number of alternate alleles in called genotypes\">");
variantFile.addHeaderLine("##INFO=<ID=AF,Number=A,Type=Float,Description=\"Estimated allele frequency in the range (0,1]\">");
variantFile.addHeaderLine("##INFO=<ID=NS,Number=1,Type=Integer,Description=\"Number of samples with data\">");
variantFile.addHeaderLine("##INFO=<ID=AN,Number=1,Type=Integer,Description=\"Total number of alleles in called genotypes\">");
// write the new header
cout << variantFile.header << endl;
// print the records, filtering is done via the setting of varA's output sample names
while (variantFile.getNextVariant(var)) {
stringstream ns;
ns << var.samples.size();
var.info["NS"].clear();
var.info["NS"].push_back(ns.str());
var.info["AC"].clear();
var.info["AF"].clear();
var.info["AN"].clear();
int allelecount = countAlleles(var);
stringstream an;
an << allelecount;
var.info["AN"].push_back(an.str());
for (vector<string>::iterator a = var.alt.begin(); a != var.alt.end(); ++a) {
string& allele = *a;
int altcount = countAlts(var, var.getAltAlleleIndex(allele) + 1);
stringstream ac;
ac << altcount;
var.info["AC"].push_back(ac.str());
stringstream af;
af << (double) altcount / (double) allelecount;
var.info["AF"].push_back(af.str());
}
cout << var << endl;
}
return 0;
}