* Tables pertaining to different coverage summaries. Suffix on the table files declares the contents: + *
* - no suffix: per locus coverage + *
* - _summary: total, mean, median, quartiles, and threshold proportions, aggregated over all bases + *
* - _statistics: coverage histograms (# locus with X coverage), aggregated over all bases + *
* - _interval_summary: total, mean, median, quartiles, and threshold proportions, aggregated per interval + *
* - _interval_statistics: 2x2 table of # of intervals covered to >= X depth in >=Y samples + *
* - _gene_summary: total, mean, median, quartiles, and threshold proportions, aggregated per gene + *
* - _gene_statistics: 2x2 table of # of genes covered to >= X depth in >= Y samples + *
* - _cumulative_coverage_counts: coverage histograms (# locus with >= X coverage), aggregated over all bases + *
* - _cumulative_coverage_proportions: proprotions of loci with >= X coverage, aggregated over all bases *
* diff --git a/public/java/src/org/broadinstitute/sting/gatk/walkers/fasta/FastaAlternateReferenceWalker.java b/public/java/src/org/broadinstitute/sting/gatk/walkers/fasta/FastaAlternateReferenceWalker.java index fd912334f..4e2c17bf6 100755 --- a/public/java/src/org/broadinstitute/sting/gatk/walkers/fasta/FastaAlternateReferenceWalker.java +++ b/public/java/src/org/broadinstitute/sting/gatk/walkers/fasta/FastaAlternateReferenceWalker.java @@ -43,8 +43,10 @@ import java.util.List; * Generates an alternative reference sequence over the specified interval. * *- * Given variant ROD tracks, it replaces the reference bases at variation sites with the bases supplied by the ROD(s). - * Additionally, allows for a "snpmask" ROD to set overlapping bases to 'N'. + * Given variant tracks, it replaces the reference bases at variation sites with the bases supplied by the ROD(s). + * Additionally, allows for one or more "snpmask" VCFs to set overlapping bases to 'N'. + * Note that if there are multiple variants at a site, it takes the first one seen. + * Reference bases for each interval will be output as a separate fasta sequence (named numerically in order). * *
diff --git a/public/java/src/org/broadinstitute/sting/gatk/walkers/fasta/FastaReferenceWalker.java b/public/java/src/org/broadinstitute/sting/gatk/walkers/fasta/FastaReferenceWalker.java index 5f3b37cc8..7ae5c5c75 100755 --- a/public/java/src/org/broadinstitute/sting/gatk/walkers/fasta/FastaReferenceWalker.java +++ b/public/java/src/org/broadinstitute/sting/gatk/walkers/fasta/FastaReferenceWalker.java @@ -42,6 +42,9 @@ import java.io.PrintStream; * *
* The output format can be partially controlled using the provided command-line arguments. + * Specify intervals with the usual -L argument to output only the reference bases within your intervals. + * Overlapping intervals are automatically merged; reference bases for each disjoint interval will be output as a + * separate fasta sequence (named numerically in order). * *
diff --git a/public/java/src/org/broadinstitute/sting/gatk/walkers/genotyper/ExactAFCalculationModel.java b/public/java/src/org/broadinstitute/sting/gatk/walkers/genotyper/ExactAFCalculationModel.java
index cd006a3cf..6ae437b27 100755
--- a/public/java/src/org/broadinstitute/sting/gatk/walkers/genotyper/ExactAFCalculationModel.java
+++ b/public/java/src/org/broadinstitute/sting/gatk/walkers/genotyper/ExactAFCalculationModel.java
@@ -63,7 +63,7 @@ public class ExactAFCalculationModel extends AlleleFrequencyCalculationModel {
private boolean SIMPLE_GREEDY_GENOTYPER = false;
-
+ private final static double SUM_GL_THRESH_NOCALL = -0.001; // if sum(gl) is bigger than this threshold, we treat GL's as non-informative and will force a no-call.
final private ExactCalculation calcToUse;
protected ExactAFCalculationModel(UnifiedArgumentCollection UAC, int N, Logger logger, PrintStream verboseWriter) {
@@ -178,22 +178,25 @@ public class ExactAFCalculationModel extends AlleleFrequencyCalculationModel {
}
- private static final double[][] getGLs(Map
+ * Tumor and normal bam files (or single sample bam file(s) in --unpaired mode).
+ *
+ * Indel calls with associated metrics.
+ *
* A recalibration table file in CSV format that is used by the TableRecalibration walker.
+ * It is a comma-separated text file relating the desired covariates to the number of such bases and their rate of mismatch in the genome, and its implied empirical quality score.
+ *
+ * The first 20 lines of such a file is shown below.
+ * * The file begins with a series of comment lines describing:
+ * ** The number of counted loci
+ * ** The number of counted bases
+ * ** The number of skipped loci and the fraction skipped, due to presence in dbSNP or bad reference bases
+ *
+ * * After the comments appears a header line indicating which covariates were used as well as the ordering of elements in the subsequent records.
+ *
+ * * After the header, data records occur one per line until the end of the file. The first several items on a line are the values of the individual covariates and will change
+ * depending on which covariates were specified at runtime. The last three items are the data- that is, number of observations for this combination of covariates, number of
+ * reference mismatches, and the raw empirical quality score calculated by phred-scaling the mismatch rate.
+ *
+ * Input
+ * Output
+ * Examples
+ *
+ * java -Xmx2g -jar GenomeAnalysisTK.jar \
+ * -R ref.fasta \
+ * -T SomaticIndelDetector \
+ * -o indels.vcf \
+ * -verbose indels.txt
+ * -I:normal normal.bam \
+ * -I:tumor tumor.bam
+ *
*
*/
+
@ReadFilters({Platform454Filter.class, MappingQualityZeroFilter.class, PlatformUnitFilter.class})
public class SomaticIndelDetectorWalker extends ReadWalkerOutput
*
+ * # Counted Sites 19451059
+ * # Counted Bases 56582018
+ * # Skipped Sites 82666
+ * # Fraction Skipped 1 / 235 bp
+ * ReadGroup,QualityScore,Cycle,Dinuc,nObservations,nMismatches,Qempirical
+ * SRR006446,11,65,CA,9,1,10
+ * SRR006446,11,48,TA,10,0,40
+ * SRR006446,11,67,AA,27,0,40
+ * SRR006446,11,61,GA,11,1,10
+ * SRR006446,12,34,CA,47,1,17
+ * SRR006446,12,30,GA,52,1,17
+ * SRR006446,12,36,AA,352,1,25
+ * SRR006446,12,17,TA,182,11,12
+ * SRR006446,11,48,TG,2,0,40
+ * SRR006446,11,67,AG,1,0,40
+ * SRR006446,12,34,CG,9,0,40
+ * SRR006446,12,30,GG,43,0,40
+ * ERR001876,4,31,AG,1,0,40
+ * ERR001876,4,31,AT,2,2,1
+ * ERR001876,4,31,CA,1,0,40
+ *
*
* Valid // amplicon is valid
* SITE_IS_FILTERED=1 // validation site is not marked 'PASS' or '.' in its filter field ("you are trying to validate a filtered variant")
* VARIANT_TOO_NEAR_PROBE=1 // there is a variant too near to the variant to be validated, potentially shifting the mass-spec peak
@@ -72,10 +72,10 @@ import java.util.List;
* END_TOO_CLOSE, // variant is too close to the end of the amplicon region to give sequenom a good chance to find a suitable primer
* NO_VARIANTS_FOUND, // no variants found within the amplicon region
* INDEL_OVERLAPS_VALIDATION_SITE, // an insertion or deletion interferes directly with the site to be validated (i.e. insertion directly preceding or postceding, or a deletion that spans the site itself)
- *
+ *
*
*