int main( int argc, const char * argv[] )
{
args_t args = args_t( argc, argv );
coverage_t::const_iterator cit;
coverage_t coverage;
vector< pair< int, int > > data;
bam1_t * const in_bam = bam_init1();
while ( args.bamin->next( in_bam ) ) {
aligned_t read( in_bam );
coverage.include( read );
}
for ( cit = coverage.begin(); cit != coverage.end(); ++cit ) {
map< elem_t, int >::const_iterator it;
if ( cit->op != MATCH )
continue;
it = cit->obs.begin();
if ( it == cit->obs.end() )
continue;
int cov = it->second;
int max = it->second;
for ( ++it; it != cit->obs.end(); ++it ) {
cov += it->second;
if ( it->second > max )
max = it->second;
}
for ( it = cit->obs.begin(); it != cit->obs.end(); ++it )
if ( it->second && it->second != max )
data.push_back( make_pair( cov, cov - it->second ) );
}
rateclass_t rc( data, 3 );
double lg_L, aicc;
vector< pair< double, double > > params;
rc( lg_L, aicc, params );
const double bg = weighted_harmonic_mean( params );
const double lg_bg = log( bg );
const double lg_invbg = log( 1.0 - bg );
params_json_dump( stderr, lg_L, aicc, params, bg );
for ( cit = coverage.begin(); cit != coverage.end(); ++cit ) {
map< elem_t, int >::const_iterator it;
if ( cit->op != MATCH )
continue;
it = cit->obs.begin();
if ( it == cit->obs.end() )
continue;
int cov = it->second;
int max = it->second;
for ( ++it; it != cit->obs.end(); ++it ) {
cov += it->second;
if ( it->second > max )
max = it->second;
}
string css;
for ( it = cit->obs.begin(); it != cit->obs.end(); ++it )
if ( it->second == max ) {
string elem;
it->first.get_seq( elem );
css.append( elem );
css.push_back( '/' );
}
// erase the trailing slash, in a compatible way
css.erase( --css.end() );
for ( it = cit->obs.begin(); it != cit->obs.end(); ++it ) {
string elem;
if ( !it->second || it->second == max )
continue;
const double prob = prob_background( lg_bg, lg_invbg, cov, it->second );
if ( prob >= args.cutoff )
continue;
fprintf( stdout, "%d\t%s\t%d\t", cit->col + 1, css.c_str(), cov );
it->first.get_seq( elem );
fprintf( stdout, "%s", elem.c_str() );
fprintf( stdout, ":%d:%.3e\n", it->second, prob );
}
fflush( stdout );
}
bam_destroy1( in_bam );
return 0;
}
int main( int argc, const char * argv[] )
{
args_t args = args_t( argc, argv );
coverage_t coverage;
vector< cov_t > variants;
vector< pair< int, int > > data;
// accumulate the data at each position in a linked list
{
cov_citer cit;
bam1_t * in_bam = bam_init1();
while ( args.bamin->next( in_bam ) ) {
aligned_t read( in_bam );
coverage.include( read );
}
for ( cit = coverage.begin(); cit != coverage.end(); ++cit ) {
int cov = 0;
for ( obs_citer it = cit->obs.begin(); it != cit->obs.end(); ++it )
cov += it->second;
for ( obs_citer it = cit->obs.begin(); it != cit->obs.end(); ++it )
if ( it->second )
data.push_back( make_pair( cov, it->second ) );
#if 0
obs_citer it = cit->obs.begin();
int cov = 0, maj;
if ( it == cit->obs.end() )
continue;
maj = it->second;
cov += maj;
for ( ++it; it != cit->obs.end(); ++it ) {
if ( it->second > maj )
maj = it->second;
cov += it->second;
}
data.push_back( make_pair( cov, maj ) );
#endif
}
bam_destroy1( in_bam );
}
// learn a joint multi-binomial model for the mutation rate classes
{
cov_iter cit;
double lg_L, aicc, bg, lg_bg, lg_invbg;
rateclass_t rc( data );
vector< pair< double, double > > params;
rc( lg_L, aicc, params );
bg = params[ 0 ].second;
lg_bg = log( bg );
lg_invbg = log( 1.0 - bg );
params_json_dump( stderr, lg_L, aicc, params );
// cerr << "background: " << bg << endl;
// determine which variants are above background and those which are not
for ( cit = coverage.begin(); cit != coverage.end(); ++cit ) {
if ( cit->op == INS )
continue;
int cov = 0;
for ( obs_citer it = cit->obs.begin(); it != cit->obs.end(); ++it )
cov += it->second;
for ( obs_iter it = cit->obs.begin(); it != cit->obs.end(); ++it ) {
const double p = prob_background( lg_bg, lg_invbg, cov, it->second );
if ( p < args.cutoff ) {
cout << cit->col << "\t" << cov << "\t" << it->second;
for ( unsigned i = 0; i < it->first.size(); ++i )
cout << bits2nuc( it->first[ i ] );
cout << ":" << p << endl;
it->second = 1;
}
else {
it->second = 0;
}
}
#if 0
variants.push_back( *cit );
#endif
}
}
return 0;
// write out the input reads, but only with "real" variants this time
{
bam1_t * const in_bam = bam_init1();
if ( !args.bamin->seek0() ) {
cerr << "unable to seek( 0 )" << endl;
exit( 1 );
}
if ( !args.bamout->write_header( args.bamin->hdr ) ) {
cerr << "error writing out BAM header" << endl;
exit( 1 );
}
while ( args.bamin->next( in_bam ) ) {
aligned_t read( in_bam );
bam1_t * const out_bam = punchout_read( in_bam, variants, read );
if ( !out_bam->core.l_qseq )
continue;
if ( !args.bamout->write( out_bam ) ) {
cerr << "error writing out read" << endl;
exit( 1 );
}
bam_destroy1( out_bam );
}
bam_destroy1( in_bam );
}
return 0;
}