From 4450d66c647f949da89e9590d2c1e336e82da742 Mon Sep 17 00:00:00 2001 From: Eric Banks Date: Mon, 20 Aug 2012 15:10:24 -0400 Subject: [PATCH] Fixing the docs for DP and AD --- .../gatk/walkers/annotator/DepthOfCoverage.java | 17 ++++------------- .../annotator/DepthPerAlleleBySample.java | 12 ++++++------ 2 files changed, 10 insertions(+), 19 deletions(-) diff --git a/public/java/src/org/broadinstitute/sting/gatk/walkers/annotator/DepthOfCoverage.java b/public/java/src/org/broadinstitute/sting/gatk/walkers/annotator/DepthOfCoverage.java index 28ca77f18..39b5e84dc 100755 --- a/public/java/src/org/broadinstitute/sting/gatk/walkers/annotator/DepthOfCoverage.java +++ b/public/java/src/org/broadinstitute/sting/gatk/walkers/annotator/DepthOfCoverage.java @@ -22,19 +22,10 @@ import java.util.Map; /** * Total (unfiltered) depth over all samples. * - * This and AD are complementary fields that are two important ways of thinking about the depth of the data for this sample - * at this site. The DP field describe the total depth of reads that passed the Unified Genotypers internal - * quality control metrics (like MAPQ > 17, for example), whatever base was present in the read at this site. - * The AD values (one for each of REF and ALT fields) is the count of all reads that carried with them the - * REF and ALT alleles. The reason for this distinction is that the DP is in some sense reflective of the - * power I have to determine the genotype of the sample at this site, while the AD tells me how many times - * I saw each of the REF and ALT alleles in the reads, free of any bias potentially introduced by filtering - * the reads. If, for example, I believe there really is a an A/T polymorphism at a site, then I would like - * to know the counts of A and T bases in this sample, even for reads with poor mapping quality that would - * normally be excluded from the statistical calculations going into GQ and QUAL. - * - * Note that the DP is affected by downsampling (-dcov) though, so the max value one can obtain for N samples with - * -dcov D is N * D + * While the sample-level (FORMAT) DP field describes the total depth of reads that passed the Unified Genotyper's + * internal quality control metrics (like MAPQ > 17, for example), the INFO field DP represents the unfiltered depth + * over all samples. Note though that the DP is affected by downsampling (-dcov), so the max value one can obtain for + * N samples with -dcov D is N * D */ public class DepthOfCoverage extends InfoFieldAnnotation implements StandardAnnotation, ActiveRegionBasedAnnotation { diff --git a/public/java/src/org/broadinstitute/sting/gatk/walkers/annotator/DepthPerAlleleBySample.java b/public/java/src/org/broadinstitute/sting/gatk/walkers/annotator/DepthPerAlleleBySample.java index a9edab752..5d83ddd51 100755 --- a/public/java/src/org/broadinstitute/sting/gatk/walkers/annotator/DepthPerAlleleBySample.java +++ b/public/java/src/org/broadinstitute/sting/gatk/walkers/annotator/DepthPerAlleleBySample.java @@ -24,10 +24,10 @@ import java.util.List; /** * The depth of coverage of each VCF allele in this sample. * - * This and DP are complementary fields that are two important ways of thinking about the depth of the data for this sample - * at this site. The DP field describe the total depth of reads that passed the Unified Genotypers internal - * quality control metrics (like MAPQ > 17, for example), whatever base was present in the read at this site. - * The AD values (one for each of REF and ALT fields) is the count of all reads that carried with them the + * The AD and DP are complementary fields that are two important ways of thinking about the depth of the data for this + * sample at this site. While the sample-level (FORMAT) DP field describes the total depth of reads that passed the + * Unified Genotyper's internal quality control metrics (like MAPQ > 17, for example), the AD values (one for each of + * REF and ALT fields) is the unfiltered count of all reads that carried with them the * REF and ALT alleles. The reason for this distinction is that the DP is in some sense reflective of the * power I have to determine the genotype of the sample at this site, while the AD tells me how many times * I saw each of the REF and ALT alleles in the reads, free of any bias potentially introduced by filtering @@ -35,10 +35,10 @@ import java.util.List; * to know the counts of A and T bases in this sample, even for reads with poor mapping quality that would * normally be excluded from the statistical calculations going into GQ and QUAL. Please note, however, that * the AD isn't necessarily calculated exactly for indels (it counts as non-reference only those indels that - * are actually present and correctly left-aligned in the alignments themselves). Because of this fact and + * are unambiguously informative about the alternate allele). Because of this fact and * because the AD includes reads and bases that were filtered by the Unified Genotyper, one should not base * assumptions about the underlying genotype based on it; instead, the genotype likelihoods (PLs) are what - * determine the genotype calls (see below). + * determine the genotype calls. */ public class DepthPerAlleleBySample extends GenotypeAnnotation implements StandardAnnotation {