/// get the indel cigar and ref and indel strings used in the indel
/// summary line output
///
static
void
get_vcf_summary_strings(const indel_key& ik,
const indel_data& id,
const reference_contig_segment& ref,
std::string& vcf_indel_seq,
std::string& vcf_ref_seq) {
if (ik.is_breakpoint()) {
if (ik.type == INDEL::BP_LEFT) {
copy_ref_subseq(ref,ik.pos-1,ik.pos,vcf_ref_seq);
vcf_indel_seq = vcf_ref_seq + id.get_insert_seq() + '.';
} else if(ik.type == INDEL::BP_RIGHT) {
copy_ref_subseq(ref,ik.pos,ik.pos+1,vcf_ref_seq);
vcf_indel_seq = '.' + id.get_insert_seq() + vcf_ref_seq;
} else {
assert(0);
}
} else {
copy_ref_subseq(ref,ik.pos-1,ik.pos+ik.delete_length(),vcf_ref_seq);
copy_ref_subseq(ref,ik.pos-1,ik.pos,vcf_indel_seq);
vcf_indel_seq += id.get_insert_seq();
}
}
void
indel_digt_caller::
get_indel_digt_lhood(const starling_options& opt,
const starling_deriv_options& dopt,
const starling_sample_options& sample_opt,
const double indel_error_prob,
const double ref_error_prob,
const indel_key& ik,
const indel_data& id,
const bool is_het_bias,
const double het_bias,
const bool is_tier2_pass,
const bool is_use_alt_indel,
double* const lhood) {
static const double loghalf(-std::log(2.));
for (unsigned gt(0); gt<STAR_DIINDEL::SIZE; ++gt) lhood[gt] = 0.;
const bool is_breakpoint(ik.is_breakpoint());
const double indel_error_lnp(std::log(indel_error_prob));
const double indel_real_lnp(std::log(1.-indel_error_prob));
const double ref_error_lnp(std::log(ref_error_prob));
const double ref_real_lnp(std::log(1.-ref_error_prob));
// typedef read_path_scores::alt_indel_t::const_iterator aiter;
typedef indel_data::score_t::const_iterator siter;
siter it(id.read_path_lnp.begin()), it_end(id.read_path_lnp.end());
for (; it!=it_end; ++it) {
const read_path_scores& path_lnp(it->second);
// optionally skip tier2 data:
if ((! is_tier2_pass) && (! path_lnp.is_tier1_read)) continue;
// get alt path lnp:
double alt_path_lnp(path_lnp.ref);
#if 0
if (is_use_alt_indel && path_lnp.is_alt &&
(path_lnp.alt > alt_path_lnp)) {
alt_path_lnp=path_lnp.alt;
}
#else
if (is_use_alt_indel and (not path_lnp.alt_indel.empty()) ) {
typedef read_path_scores::alt_indel_t::const_iterator aiter;
aiter j(path_lnp.alt_indel.begin()), j_end(path_lnp.alt_indel.end());
for (; j!=j_end; ++j) {
if (j->second>alt_path_lnp) alt_path_lnp=j->second;
}
}
#endif
const double noindel_lnp(log_sum(alt_path_lnp+ref_real_lnp,path_lnp.indel+indel_error_lnp));
const double hom_lnp(log_sum(alt_path_lnp+ref_error_lnp,path_lnp.indel+indel_real_lnp));
// allele ratio convention is that the indel occurs at the
// het_allele ratio and the alternate allele occurs at
// (1-het_allele_ratio):
double log_ref_prob(loghalf);
double log_indel_prob(loghalf);
if (not is_breakpoint) {
static const double het_allele_ratio(0.5);
get_het_observed_allele_ratio(path_lnp.read_length,sample_opt.min_read_bp_flank,
ik,het_allele_ratio,log_ref_prob,log_indel_prob);
}
const double het_lnp(log_sum(noindel_lnp+log_ref_prob,hom_lnp+log_indel_prob));
lhood[STAR_DIINDEL::NOINDEL] += integrate_out_sites(dopt,path_lnp.nsite,noindel_lnp,is_tier2_pass);
lhood[STAR_DIINDEL::HOM] += integrate_out_sites(dopt,path_lnp.nsite,hom_lnp,is_tier2_pass);
lhood[STAR_DIINDEL::HET] += integrate_out_sites(dopt,path_lnp.nsite,het_lnp,is_tier2_pass);
#ifdef DEBUG_INDEL_CALL
//log_os << std::setprecision(8);
//log_os << "INDEL_CALL i,ref_lnp,indel_lnp,lhood(noindel),lhood(hom),lhood(het): " << i << " " << path_lnp.ref << " " << path_lnp.indel << " " << lhood[STAR_DIINDEL::NOINDEL] << " " << lhood[STAR_DIINDEL::HOM] << " " << lhood[STAR_DIINDEL::HET] << "\n";
#endif
}
if (is_het_bias) {
// loop is currently setup to assume a uniform het ratio subgenotype prior
const unsigned n_bias_steps(1+static_cast<unsigned>(het_bias/opt.het_bias_max_ratio_inc));
const double ratio_increment(het_bias/static_cast<double>(n_bias_steps));
for (unsigned step(0); step<n_bias_steps; ++step) {
const double het_ratio(0.5+(step+1)*ratio_increment);
increment_het_ratio_lhood(opt,dopt,sample_opt,
indel_error_lnp,indel_real_lnp,
ref_error_lnp,ref_real_lnp,
ik,id,het_ratio,is_tier2_pass,is_use_alt_indel,lhood);
}
const unsigned n_het_subgt(1+2*n_bias_steps);
const double subgt_log_prior(std::log(static_cast<double>(n_het_subgt)));
lhood[STAR_DIINDEL::HET] -= subgt_log_prior;
}
}
void
indel_digt_caller::
get_high_low_het_ratio_lhood(const starling_options& /*opt*/,
const starling_deriv_options& dopt,
const starling_sample_options& sample_opt,
const double indel_error_lnp,
const double indel_real_lnp,
const double ref_error_lnp,
const double ref_real_lnp,
const indel_key& ik,
const indel_data& id,
const double het_ratio,
const bool is_tier2_pass,
const bool is_use_alt_indel,
double& het_lhood_high,
double& het_lhood_low) {
// handle het ratio and its complement in one step:
const double chet_ratio(1.-het_ratio);
const double log_het_ratio(std::log(het_ratio));
const double log_chet_ratio(std::log(chet_ratio));
const bool is_breakpoint(ik.is_breakpoint());
het_lhood_high=0;
het_lhood_low=0;
// typedef read_path_scores::alt_indel_t::const_iterator aiter;
typedef indel_data::score_t::const_iterator siter;
siter i(id.read_path_lnp.begin()), i_end(id.read_path_lnp.end());
for (; i!=i_end; ++i) {
const read_path_scores& path_lnp(i->second);
// optionally skip tier2 data:
if ((! is_tier2_pass) && (! path_lnp.is_tier1_read)) continue;
// get alt path lnp:
double alt_path_lnp(path_lnp.ref);
#if 0
if (is_use_alt_indel && path_lnp.is_alt &&
(path_lnp.alt > alt_path_lnp)) {
alt_path_lnp=path_lnp.alt;
}
#else
if (is_use_alt_indel && (! path_lnp.alt_indel.empty()) ) {
typedef read_path_scores::alt_indel_t::const_iterator aiter;
aiter j(path_lnp.alt_indel.begin()), j_end(path_lnp.alt_indel.end());
for (; j!=j_end; ++j) {
if (j->second>alt_path_lnp) alt_path_lnp=j->second;
}
}
#endif
const double noindel_lnp(log_sum(alt_path_lnp+ref_real_lnp,path_lnp.indel+indel_error_lnp));
const double hom_lnp(log_sum(alt_path_lnp+ref_error_lnp,path_lnp.indel+indel_real_lnp));
// allele ratio convention is that the indel occurs at the
// het_allele ratio and the alternate allele occurs at
// (1-het_allele_ratio):
{
double log_ref_prob(log_chet_ratio);
double log_indel_prob(log_het_ratio);
if (! is_breakpoint) {
get_het_observed_allele_ratio(path_lnp.read_length,sample_opt.min_read_bp_flank,
ik,het_ratio,log_ref_prob,log_indel_prob);
}
const double het_lnp(log_sum(noindel_lnp+log_ref_prob,hom_lnp+log_indel_prob));
het_lhood_low += integrate_out_sites(dopt,path_lnp.nsite,het_lnp,is_tier2_pass);
}
{
double log_ref_prob(log_het_ratio);
double log_indel_prob(log_chet_ratio);
if (! is_breakpoint) {
get_het_observed_allele_ratio(path_lnp.read_length,sample_opt.min_read_bp_flank,
ik,chet_ratio,log_ref_prob,log_indel_prob);
}
const double het_lnp(log_sum(noindel_lnp+log_ref_prob,hom_lnp+log_indel_prob));
het_lhood_high += integrate_out_sites(dopt,path_lnp.nsite,het_lnp,is_tier2_pass);
}
}
}
