zzh
/
gatk-3.8
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Improvements and bugfixes to IndelSummary 

-- Now properly includes both bi and multi-allelic variants.  These are actually counted as well, and emitted as counts and % of sites with multiple alleles
-- Bug fix for gold standard rate
This commit is contained in:
Mark DePristo 2012-04-09 15:51:34 -04:00
parent bfa966a4e9
commit e6d5cb46d2
1 changed files with 6 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
public/java/src/org/broadinstitute/sting/gatk/walkers/varianteval/evaluators/IndelSummary.java
View File

@ -62,8 +62,8 @@ public class IndelSummary extends VariantEvaluator implements StandardEval {
@DataPoint(description = "Percent of indels overlapping gold standard sites")
public String gold_standard_matching_rate;
// counts 1 for each site where the number of alleles > 2
public int nMultiIndelSites = 0;
@DataPoint(description = "Number of sites with where the number of alleles is greater than 2")
public int n_multiallelic_indel_sites = 0;
@DataPoint(description = "Percent of indel sites that are multi-allelic")
public String percent_of_sites_with_more_than_2_alleles;
@ -158,10 +158,9 @@ public class IndelSummary extends VariantEvaluator implements StandardEval {
break;
case INDEL:
final VariantContext gold = getWalker().goldStandard == null ? null : tracker.getFirstValue(getWalker().goldStandard);
if ( eval.isComplexIndel() ) break; // don't count complex substitutions
nIndelSites++;
if ( ! eval.isBiallelic() ) nMultiIndelSites++;
if ( ! eval.isBiallelic() ) n_multiallelic_indel_sites++;
// collect information about het / hom ratio
for ( final Genotype g : eval.getGenotypes() ) {
@ -216,11 +215,11 @@ public class IndelSummary extends VariantEvaluator implements StandardEval {
}
public void finalizeEvaluation() {
percent_of_sites_with_more_than_2_alleles = Utils.formattedRatio(nMultiIndelSites, nIndelSites);
percent_of_sites_with_more_than_2_alleles = Utils.formattedRatio(n_multiallelic_indel_sites, nIndelSites);
SNP_to_indel_ratio = Utils.formattedRatio(n_SNPs, n_indels);
SNP_to_indel_ratio_for_singletons = Utils.formattedRatio(n_singleton_SNPs, n_singleton_indels);
gold_standard_matching_rate = Utils.formattedNoveltyRate(n_indels_matching_gold_standard, n_indels);
gold_standard_matching_rate = Utils.formattedPercent(n_indels_matching_gold_standard, n_indels);
indel_novelty_rate = Utils.formattedNoveltyRate(nKnownIndels, n_indels);
frameshift_rate_for_coding_indels = Utils.formattedPercent(n_coding_indels_frameshifting, n_coding_indels_in_frame + n_coding_indels_frameshifting);