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

Documentation fixes 

- Fix missing closing code block tag
	- SOR fix + minor fix to template
	- Minor typo fixes
	- Make no_cmdline_in_header arg visible in docs
	- Caveats for UG-only args that are difficult to move out of common collection
	- Reference -L and -XL in -gvcf documentation
	- Annotation doc fixes (dsde-docs#1289)
	- Unhide some ContEst args and make Advanced
	- Fix inputPrior error message
	- Update web urls
	- Add JEXL doc link
This commit is contained in:
Geraldine Van der Auwera 2016-06-04 02:14:49 -04:00
parent 66aa735817
commit b42dc1624b
30 changed files with 428 additions and 423 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

96
protected/gatk-tools-protected/src/main/java/org/broadinstitute/gatk/engine/arguments/GenotypeCalculationArgumentCollection.java
View File

@ -66,39 +66,23 @@ public class GenotypeCalculationArgumentCollection implements Cloneable{
public static final String MAX_ALTERNATE_ALLELES_SHORT_NAME = "maxAltAlleles";
/**
* Depending on the value of the --max_alternate_alleles argument, we may genotype only a fraction of the alleles being sent on for genotyping.
* Using this argument instructs the genotyper to annotate (in the INFO field) the number of alternate alleles that were originally discovered at the site.
* Depending on the value of the --max_alternate_alleles argument, we may genotype only a fraction of the alleles
* being sent on for genotyping. Using this argument instructs the genotyper to annotate (in the INFO field) the
* number of alternate alleles that were originally discovered (but not necessarily genotyped) at the site.
*/
@Argument(fullName = "annotateNDA", shortName = "nda", doc = "If provided, we will annotate records with the number of alternate alleles that were discovered (but not necessarily genotyped) at a given site", required = false)
@Argument(fullName = "annotateNDA", shortName = "nda", doc = "Annotate number of alleles observed", required = false)
public boolean ANNOTATE_NUMBER_OF_ALLELES_DISCOVERED = false;
/**
* Use the new allele frequency / QUAL score model
* This activates a model for calculating QUAL that was introduced in version 3.7 (November 2016). We expect this
* model will become the default in future versions.
*/
@Argument(fullName = "useNewAFCalculator", shortName = "newQual", doc = "If provided, we will use the new AF model instead of the so-called exact model", required = false)
@Argument(fullName = "useNewAFCalculator", shortName = "newQual", doc = "Use new AF model instead of the so-called exact model", required = false)
public boolean USE_NEW_AF_CALCULATOR = false;
/**
* The expected heterozygosity value used to compute prior probability that a locus is non-reference.
*
* From the heterozygosity we calculate the probability of N samples being hom-ref at a site as 1 - sum_i_2N (hets / i)
* where hets is this case is analogous to the parameter theta from population genetics. See https://en.wikipedia.org/wiki/Coalescent_theory for more details.
*
* Note that heterozygosity as used here is the population genetics concept. (See http://en.wikipedia.org/wiki/Zygosity#Heterozygosity_in_population_genetics.
* We also suggest the book "Population Genetics: A Concise Guide" by John H. Gillespie for further details on the theory.) That is, a hets value of 0.001
* implies that two randomly chosen chromosomes from the population of organisms would differ from each other at a rate of 1 in 1000 bp.
*
* The default priors provided for humans (hets = 1e-3)
*
* Also note that this quantity has nothing to do with the likelihood of any given sample having a heterozygous genotype,
* which in the GATK is purely determined by the probability of the observed data P(D | AB) under the model that there
* may be a AB het genotype. The posterior probability of this AB genotype would use the het prior, but the GATK
* only uses this posterior probability in determining the prob. that a site is polymorphic. So changing the
* het parameters only increases the chance that a site will be called non-reference across all samples, but
* doesn't actually change the output genotype likelihoods at all, as these aren't posterior probabilities at all.
*
* The quantity that changes whether the GATK considers the possibility of a het genotype at all is the ploidy,
* which determines how many chromosomes each individual in the species carries.
* The expected heterozygosity value used to compute prior probability that a locus is non-reference. See
* https://software.broadinstitute.org/gatk/documentation/article?id=8603 for more details.
*/
@Argument(fullName = "heterozygosity", shortName = "hets", doc = "Heterozygosity value used to compute prior likelihoods for any locus", required = false)
public Double snpHeterozygosity = HomoSapiensConstants.SNP_HETEROZYGOSITY;
@ -110,8 +94,8 @@ public class GenotypeCalculationArgumentCollection implements Cloneable{
public double indelHeterozygosity = HomoSapiensConstants.INDEL_HETEROZYGOSITY;
/**
* The standard deviation of the distribution of alt allele fractions. The above heterozygosity parameters give the
* *mean* of this distribution; this parameter gives its spread.
* The standard deviation of the distribution of alt allele fractions. The above heterozygosity parameters give
* the *mean* of this distribution; this parameter gives its spread.
*/
@Argument(fullName = "heterozygosity_stdev", shortName = "heterozygosityStandardDeviation", doc = "Standard deviation of eterozygosity for SNP and indel calling.", required = false)
public double heterozygosityStandardDeviation = 0.01;
@ -134,10 +118,11 @@ public class GenotypeCalculationArgumentCollection implements Cloneable{
public double STANDARD_CONFIDENCE_FOR_EMITTING = 30.0;
/**
* If there are more than this number of alternate alleles presented to the genotyper (either through discovery or GENOTYPE_GIVEN_ALLELES),
* then only this many alleles will be used. Note that genotyping sites with many alternate alleles is both CPU and memory intensive and it
* scales exponentially based on the number of alternate alleles. Unless there is a good reason to change the default value, we highly recommend
* that you not play around with this parameter.
* If there are more than this number of alternate alleles presented to the genotyper (either through discovery or
* GENOTYPE_GIVEN_ALLELES), then only this many alleles will be used. Note that genotyping sites with many
* alternate alleles is both CPU and memory intensive and it scales exponentially based on the number of alternate
* alleles. Unless there is a good reason to change the default value, we highly recommend that you not play around
* with this parameter.
*
* See also {@link #MAX_GENOTYPE_COUNT}.
*/
@ -146,19 +131,23 @@ public class GenotypeCalculationArgumentCollection implements Cloneable{
public int MAX_ALTERNATE_ALLELES = 6;
/**
* If there are more than this number of genotypes at a locus presented to the genotyper, then only this many genotypes will be used.
* The possible genotypes are simply different ways of partitioning alleles given a specific ploidy asumption.
* Therefore, we remove genotypes from consideration by removing alternate alleles that are the least well supported.
* The estimate of allele support is based on the ranking of the candidate haplotypes coming out of the graph building step.
* Note that the reference allele is always kept.
* If there are more than this number of genotypes at a locus presented to the genotyper, then only this many
* genotypes will be used. This is intended to deal with sites where the combination of high ploidy and high alt
* allele count can lead to an explosion in the number of possible genotypes, with extreme adverse effects on
* runtime performance.
*
* Note that genotyping sites with large genotype counts is both CPU and memory intensive.
* Unless there is a good reason to change the default value, we highly recommend that you not play around with this parameter.
* How does it work? The possible genotypes are simply different ways of partitioning alleles given a specific
* ploidy assumption. Therefore, we remove genotypes from consideration by removing alternate alleles that are the
* least well supported. The estimate of allele support is based on the ranking of the candidate haplotypes coming
* out of the graph building step. Note however that the reference allele is always kept.
*
* The maximum number of alternative alleles used in the genotyping step will be the lesser of the two:
* 1. the largest number of alt alleles, given ploidy, that yields a genotype count no higher than {@link #MAX_GENOTYPE_COUNT}
* 2. the value of {@link #MAX_ALTERNATE_ALLELES}
*
* As noted above, genotyping sites with large genotype counts is both CPU and memory intensive. Unless you have
* a good reason to change the default value, we highly recommend that you not play around with this parameter.
*
* See also {@link #MAX_ALTERNATE_ALLELES}.
*/
@Advanced
@ -175,23 +164,19 @@ public class GenotypeCalculationArgumentCollection implements Cloneable{
public int MAX_NUM_PL_VALUES = AFCalculator.MAX_NUM_PL_VALUES_DEFAULT;
/**
* By default, the prior specified with the argument --heterozygosity/-hets is used for variant discovery at a particular locus, using an infinite sites model,
* see e.g. Waterson (1975) or Tajima (1996).
* This model asserts that the probability of having a population of k variant sites in N chromosomes is proportional to theta/k, for 1=1:N
* By default, the prior specified with the argument --heterozygosity/-hets is used for variant discovery at a
* particular locus, using an infinite sites model (see e.g. Waterson, 1975 or Tajima, 1996). This model asserts that
* the probability of having a population of k variant sites in N chromosomes is proportional to theta/k, for 1=1:N.
* However, there are instances where using this prior might not be desirable, e.g. for population studies where prior
* might not be appropriate, as for example when the ancestral status of the reference allele is not known.
*
* There are instances where using this prior might not be desirable, e.g. for population studies where prior might not be appropriate,
* as for example when the ancestral status of the reference allele is not known.
* By using this argument, the user can manually specify a list of probabilities for each AC>1 to be used as priors for genotyping,
* with the following restrictions:
* a) User must specify 2N values, where N is the number of samples.
* b) Only diploid calls supported.
* c) Probability values are specified in Double format, in linear space (not log10 space or Phred-scale).
* d) No negative values allowed.
* e) Values will be added and Pr(AC=0) will be 1-sum, so that they sum up to one.
* f) If user-defined values add to more than one, an error will be produced.
* This argument allows you to manually specify a list of probabilities for each AC>1 to be used as
* priors for genotyping, with the following restrictions: only diploid calls are supported; you must specify 2 *
* N values where N is the number of samples; probability values must be positive and specified in Double format,
* in linear space (not log10 space nor Phred-scale); and all values must sume to 1.
*
* If user wants completely flat priors, then user should specify the same value (=1/(2*N+1)) 2*N times,e.g.
* -inputPrior 0.33 -inputPrior 0.33
* For completely flat priors, specify the same value (=1/(2*N+1)) 2*N times, e.g.
* -inputPrior 0.33 -inputPrior 0.33
* for the single-sample diploid case.
*/
@Advanced
@ -199,9 +184,10 @@ public class GenotypeCalculationArgumentCollection implements Cloneable{
public List<Double> inputPrior = Collections.emptyList();
/**
* Sample ploidy - equivalent to number of chromosomes per pool. In pooled experiments this should be = # of samples in pool * individual sample ploidy
* Sample ploidy - equivalent to number of chromosome copies per pool. For pooled experiments this should be set to
* the number of samples in pool multiplied by individual sample ploidy.
*/
@Argument(shortName="ploidy", fullName="sample_ploidy", doc="Ploidy (number of chromosomes) per sample. For pooled data, set to (Number of samples in each pool * Sample Ploidy).", required=false)
@Argument(shortName="ploidy", fullName="sample_ploidy", doc="Ploidy per sample. For pooled data, set to (Number of samples in each pool * Sample Ploidy).", required=false)
public int samplePloidy = HomoSapiensConstants.DEFAULT_PLOIDY;
/**

2
protected/gatk-tools-protected/src/main/java/org/broadinstitute/gatk/tools/walkers/annotator/AS_BaseQualityRankSumTest.java
View File

@ -71,7 +71,7 @@ import java.util.List;
* <p>The ideal result is a value close to zero, which indicates there is little to no difference. A negative value indicates that the bases supporting the alternate allele have lower quality scores than those supporting the reference allele. Conversely, a positive value indicates that the bases supporting the alternate allele have higher quality scores than those supporting the reference allele. Finding a statistically significant difference either way suggests that the sequencing process may have been biased or affected by an artifact.</p>
*
* <h3>Statistical notes</h3>
* <p>The value output for this annotation is the u-based z-approximation from the Mann-Whitney-Wilcoxon Rank Sum Test for base qualities (bases supporting REF vs. bases supporting ALT). See the <a href="http://www.broadinstitute.org/gatk/guide/article?id=4732">method document on statistical tests</a> for a more detailed explanation of the ranksum test.</p>
* <p>The value output for this annotation is the u-based z-approximation from the Mann-Whitney-Wilcoxon Rank Sum Test for base qualities (bases supporting REF vs. bases supporting ALT). See the <a href="http://www.broadinstitute.org/gatk/guide/article?id=8031">method document on statistical tests</a> for a more detailed explanation of the ranksum test.</p>
*
* <h3>Caveats</h3>
* <ul>

16
protected/gatk-tools-protected/src/main/java/org/broadinstitute/gatk/tools/walkers/annotator/AS_InsertSizeRankSum.java
View File

@ -63,13 +63,19 @@ import java.util.List;
/**
* Allele specific Rank Sum Test for insert sizes of REF versus ALT reads
*
* <p>
* This annotation tests whether the insert sizes of reads supporting the REF allele and ALT allele are roughly equal.
* In case of multiple alternate alleles, each alternate allele is considered separately.
* <p>This variant-level annotation compares the insert sizes of reads supporting the reference allele with those supporting each alternate allele. To be clear, it does so separately for each alternate allele.</p>
*
* <p>The ideal result is a value close to zero, which indicates there is little to no difference. A negative value indicates that the reads supporting the alternate allele are associated with smaller insert sizes than those supporting the reference allele. Conversely, a positive value indicates that reads supporting the alternate allele are associated with larger insert sizes than those supporting the reference allele. Finding a statistically significant difference either way suggests that the sequencing process may have been biased or affected by an artifact.</p>
*
* </p>
* <h3>Statistical notes</h3>
* <p> See the <a href="http://www.broadinstitute.org/gatk/guide/article?id=4732">method document</a> for a more detailed explanation of the rank sum test. </p>
* <p>The value output for this annotation is the u-based z-approximation from the Mann-Whitney-Wilcoxon Rank Sum Test for insert sizes (insert sizes of reads supporting REF vs. insert sizes of reads supporting ALT). See the <a href="http://www.broadinstitute.org/gatk/guide/article?id=8031">method document on statistical tests</a> for a more detailed explanation of the ranksum test.</p>
*
* <h3>Caveats</h3>
* <ul>
* <li>Uninformative reads are not used in these calculations.</li>
* <li>The insert size rank sum test cannot be calculated for sites without a mixture of reads showing both the reference and alternate alleles.</li>
* <li>This is an experimental annotation and as such it is unsupported. Use at your own risk.</li>
* </ul>
*
* */

4
protected/gatk-tools-protected/src/main/java/org/broadinstitute/gatk/tools/walkers/annotator/AS_MQMateRankSumTest.java
View File

@ -75,7 +75,7 @@ import java.util.Map;
* <p>This annotation can be used to evaluate confidence in a variant call and could be used as a covariate for variant recalibration (VQSR). Finding a statistically significant difference in quality either way suggests that the sequencing and/or mapping process may have been biased or affected by an artifact. In practice, we only filter out low negative values when evaluating variant quality because the idea is to filter out variants for which the quality of the data supporting the alternate allele is comparatively low. The reverse case, where it is the quality of data supporting the reference allele that is lower (resulting in positive ranksum scores), is not really informative for filtering variants.</p>
*
* <h3>Statistical notes</h3>
* <p>The value output for this annotation is the u-based z-approximation from the Mann-Whitney-Wilcoxon Rank Sum Test for mapping qualities of the read's mate See the <a href="http://www.broadinstitute.org/gatk/guide/article?id=4732">method document on statistical tests</a> for a more detailed explanation of the ranksum test.</p>
* <p>The value output for this annotation is the u-based z-approximation from the Mann-Whitney-Wilcoxon Rank Sum Test for mapping qualities of the read's mate See the <a href="http://www.broadinstitute.org/gatk/guide/article?id=8031">method document on statistical tests</a> for a more detailed explanation of the ranksum test.</p>
*
* * <h3>Caveats</h3>
* <ul><li>The mapping quality rank sum test can not be calculated for sites without a mixture of reads showing both the reference and alternate alleles.</li>
@ -85,6 +85,8 @@ import java.util.Map;
* <h3>Related annotations</h3>
* <ul>
* <li><b><a href="https://www.broadinstitute.org/gatk/guide/tooldocs/org_broadinstitute_gatk_tools_walkers_annotator_AS_MappingQualityRankSumTest.php">AS_MappingQualityRankSumTest</a></b> outputs the same rank sum test on the mapping quality of the reads themselves rather than their mates.</li>
* <li><b><a href="https://www.broadinstitute.org/gatk/guide/tooldocs/org_broadinstitute_gatk_tools_walkers_annotator_MappingQualityRankSumTest.php">MappingQualityRankSumTest</a></b> outputs a version of the above mapping quality ranksum test annotation that includes all alternate alleles in a single calculation.</li>
* <li><b><a href="https://www.broadinstitute.org/gatk/guide/tooldocs/org_broadinstitute_gatk_tools_walkers_annotator_RMSMappingQuality.php">RMSMappingQuality</a></b> gives an estimation of the overall read mapping quality supporting a variant call.</li>
* </ul>
*/
public class AS_MQMateRankSumTest extends AS_RankSumTest implements BetaTestingAnnotation {

3
protected/gatk-tools-protected/src/main/java/org/broadinstitute/gatk/tools/walkers/annotator/AS_MappingQualityRankSumTest.java
View File

@ -76,7 +76,7 @@ import java.util.Map;
* <p>Finding a statistically significant difference in quality either way suggests that the sequencing and/or mapping process may have been biased or affected by an artifact. In practice, we only filter out low negative values when evaluating variant quality because the idea is to filter out variants for which the quality of the data supporting the alternate allele is comparatively low. The reverse case, where it is the quality of data supporting the reference allele that is lower (resulting in positive ranksum scores), is not really informative for filtering variants.
*
* <h3>Statistical notes</h3>
* <p>The value output for this annotation is the u-based z-approximation from the Mann-Whitney-Wilcoxon Rank Sum Test for mapping qualities (MAPQ of reads supporting REF vs. MAPQ of reads supporting ALT). See the <a href="http://www.broadinstitute.org/gatk/guide/article?id=4732">method document on statistical tests</a> for a more detailed explanation of the ranksum test.</p>
* <p>The value output for this annotation is the u-based z-approximation from the Mann-Whitney-Wilcoxon Rank Sum Test for mapping qualities (MAPQ of reads supporting REF vs. MAPQ of reads supporting ALT). See the <a href="http://www.broadinstitute.org/gatk/guide/article?id=8031">method document on statistical tests</a> for a more detailed explanation of the ranksum test.</p>
*
* <h3>Caveats</h3>
* <ul><li>The mapping quality rank sum test can not be calculated for sites without a mixture of reads showing both the reference and alternate alleles.</li>
@ -86,6 +86,7 @@ import java.util.Map;
* <h3>Related annotations</h3>
* <ul>
* <li><b><a href="https://www.broadinstitute.org/gatk/guide/tooldocs/org_broadinstitute_gatk_tools_walkers_annotator_MappingQualityRankSumTest.php">MappingQualityRankSumTest</a></b> outputs a version of this annotation that includes all alternate alleles in a single calculation.</li>
* <li><b><a href="https://www.broadinstitute.org/gatk/guide/tooldocs/org_broadinstitute_gatk_tools_walkers_annotator_AS_MQMateRankSumTest.php">AS_MQMateRankSumTest</a></b> outputs the same allele-specific rank sum test on the mapping quality of the reads' mates rather than the reads themselves.</li>
* <li><b><a href="https://www.broadinstitute.org/gatk/guide/tooldocs/org_broadinstitute_gatk_tools_walkers_annotator_RMSMappingQuality.php">RMSMappingQuality</a></b> gives an estimation of the overal read mapping quality supporting a variant call.</li>
* </ul>
*

4
protected/gatk-tools-protected/src/main/java/org/broadinstitute/gatk/tools/walkers/annotator/AS_RankSumTest.java
View File

@ -72,7 +72,9 @@ import org.broadinstitute.gatk.utils.variant.GATKVCFHeaderLines;
import java.util.*;
/**
* Allele-specific implementation of rank sum test annotations
* Allele-specific implementation of rank sum test annotations.
* The RankSumTest concept is documented at https://software.broadinstitute.org/gatk/documentation/article?id=8031
*
*/
public abstract class AS_RankSumTest extends RankSumTest implements ReducibleAnnotation {
private final static Logger logger = Logger.getLogger(AS_RMSAnnotation.class);

2
protected/gatk-tools-protected/src/main/java/org/broadinstitute/gatk/tools/walkers/annotator/AS_ReadPosRankSumTest.java
View File

@ -74,7 +74,7 @@ import java.util.List;
* <p>This annotation can be used to evaluate confidence in a variant call and is a recommended covariate for variant recalibration (VQSR). Finding a statistically significant difference in relative position either way suggests that the sequencing process may have been biased or affected by an artifact. In practice, we only filter out low negative values when evaluating variant quality because the idea is to filter out variants for which the quality of the data supporting the alternate allele is comparatively low. The reverse case, where it is the quality of data supporting the reference allele that is lower (resulting in positive ranksum scores), is not really informative for filtering variants.</p>
*
* <h3>Statistical notes</h3>
* <p>The value output for this annotation is the u-based z-approximation from the Mann-Whitney-Wilcoxon Rank Sum Test for site position within reads (position within reads supporting REF vs. position within reads supporting ALT). See the <a href="http://www.broadinstitute.org/gatk/guide/article?id=4732">method document on statistical tests</a> for a more detailed explanation of the ranksum test.</p>
* <p>The value output for this annotation is the u-based z-approximation from the Mann-Whitney-Wilcoxon Rank Sum Test for site position within reads (position within reads supporting REF vs. position within reads supporting ALT). See the <a href="http://www.broadinstitute.org/gatk/guide/article?id=8031">method document on statistical tests</a> for a more detailed explanation of the ranksum test.</p>
*
* <h3>Caveat</h3>
* <ul>

2
protected/gatk-tools-protected/src/main/java/org/broadinstitute/gatk/tools/walkers/annotator/BaseQualityRankSumTest.java
View File

@ -70,7 +70,7 @@ import java.util.*;
* <p>The ideal result is a value close to zero, which indicates there is little to no difference. A negative value indicates that the bases supporting the alternate allele have lower quality scores than those supporting the reference allele. Conversely, a positive value indicates that the bases supporting the alternate allele have higher quality scores than those supporting the reference allele. Finding a statistically significant difference either way suggests that the sequencing process may have been biased or affected by an artifact.</p>
*
* <h3>Statistical notes</h3>
* <p>The value output for this annotation is the u-based z-approximation from the Mann-Whitney-Wilcoxon Rank Sum Test for base qualities (bases supporting REF vs. bases supporting ALT). See the <a href="http://www.broadinstitute.org/gatk/guide/article?id=4732">method document on statistical tests</a> for a more detailed explanation of the ranksum test.</p>
* <p>The value output for this annotation is the u-based z-approximation from the Mann-Whitney-Wilcoxon Rank Sum Test for base qualities (bases supporting REF vs. bases supporting ALT). See the <a href="http://www.broadinstitute.org/gatk/guide/article?id=8031">method document on statistical tests</a> for a more detailed explanation of the ranksum test.</p>
*
* <h3>Caveats</h3>
* <ul>

2
protected/gatk-tools-protected/src/main/java/org/broadinstitute/gatk/tools/walkers/annotator/ClippingRankSumTest.java
View File

@ -66,7 +66,7 @@ import java.util.*;
* <p>This variant-level annotation tests whether the data supporting the reference allele shows more or less base clipping (hard clips) than those supporting the alternate allele. The ideal result is a value close to zero, which indicates there is little to no difference. A negative value indicates that the reads supporting the alternate allele have more hard-clipped bases than those supporting the reference allele. Conversely, a positive value indicates that the reads supporting the alternate allele have fewer hard-clipped bases than those supporting the reference allele. Finding a statistically significant difference either way suggests that the sequencing and/or mapping process may have been biased or affected by an artifact.</p>
*
* <h3>Statistical notes</h3>
* <p>The value output for this annotation is the u-based z-approximation from the Mann-Whitney-Wilcoxon Rank Sum Test applied to base clips (number of hard-clipped bases on reads supporting REF vs. number of hard-clipped bases on reads supporting ALT). See the <a href="http://www.broadinstitute.org/gatk/guide/article?id=">method document on statistical tests</a> for a more detailed explanation of the ranksum test.</p>
* <p>The value output for this annotation is the u-based z-approximation from the Mann-Whitney-Wilcoxon Rank Sum Test applied to base clips (number of hard-clipped bases on reads supporting REF vs. number of hard-clipped bases on reads supporting ALT). See the <a href="http://www.broadinstitute.org/gatk/guide/article?id=8031">method document on statistical tests</a> for a more detailed explanation of the ranksum test.</p>
*
* <h3>Caveat</h3>
* <p>The clipping rank sum test cannot be calculated for sites without a mixture of reads showing both the reference and alternate alleles.</p>

2
protected/gatk-tools-protected/src/main/java/org/broadinstitute/gatk/tools/walkers/annotator/FisherStrand.java
View File

@ -75,7 +75,7 @@ import java.util.*;
* <p>The output is a Phred-scaled p-value. The higher the output value, the more likely there is to be bias. More bias is indicative of false positive calls.</p>
*
* <h3>Statistical notes</h3>
* <p>See the <a href="http://www.broadinstitute.org/gatk/guide/article?id=4732">method document on statistical tests</a> for a more detailed explanation of this application of Fisher's Exact Test.</p>
* <p>See the <a href="http://www.broadinstitute.org/gatk/guide/article?id=8056">method document on statistical tests</a> for a more detailed explanation of this application of Fisher's Exact Test.</p>
*
* <h3>Caveats</h3>
* <ul>

2
protected/gatk-tools-protected/src/main/java/org/broadinstitute/gatk/tools/walkers/annotator/InbreedingCoeff.java
View File

@ -76,7 +76,7 @@ import java.util.*;
* <p>This annotation estimates whether there is evidence of inbreeding in a population. The higher the score, the higher the chance that there is inbreeding.</p>
*
* <h3>Statistical notes</h3>
* <p>The calculation is a continuous generalization of the Hardy-Weinberg test for disequilibrium that works well with limited coverage per sample. The output is the F statistic from running the HW test for disequilibrium with PL values. See the <a href="http://www.broadinstitute.org/gatk/guide/article?id=4732">method document on statistical tests</a> for a more detailed explanation of this statistical test.</p>
* <p>The calculation is a continuous generalization of the Hardy-Weinberg test for disequilibrium that works well with limited coverage per sample. The output is the F statistic from running the HW test for disequilibrium with PL values. See the <a href="http://www.broadinstitute.org/gatk/guide/article?id=8032">method document on statistical tests</a> for a more detailed explanation of this statistical test.</p>
*
* <h3>Caveats</h3>
* <ul>

2
protected/gatk-tools-protected/src/main/java/org/broadinstitute/gatk/tools/walkers/annotator/LikelihoodRankSumTest.java
View File

@ -66,7 +66,7 @@ import java.util.List;
* <p>This variant-level annotation compares the likelihoods of reads to their best haplotype match, between reads that support the reference allele and those that support the alternate allele. The ideal result is a value close to zero, which indicates there is little to no difference. A negative value indicates that the reads supporting the alternate allele have lower likelihoods to their best haplotype match than those supporting the reference allele. Conversely, a positive value indicates that the reads supporting the alternate allele have higher likelihoods to their best haplotype match than those supporting the reference allele. Finding a statistically significant difference either way suggests that the sequencing and/or mapping process may have been biased or affected by an artifact.</p>
*
* <h3>Statistical notes</h3>
* <p>The value output for this annotation is the u-based z-approximation from the Mann-Whitney-Wilcoxon Rank Sum Test for per-read likelihoods to the best haplotype match (likelihoods of reads supporting REF vs. likelihoods of reads supporting ALT). See the <a href="http://www.broadinstitute.org/gatk/guide/article?id=4732">method document on statistical tests</a> for a more detailed explanation of the ranksum test.</p>
* <p>The value output for this annotation is the u-based z-approximation from the Mann-Whitney-Wilcoxon Rank Sum Test for per-read likelihoods to the best haplotype match (likelihoods of reads supporting REF vs. likelihoods of reads supporting ALT). See the <a href="http://www.broadinstitute.org/gatk/guide/article?id=8031">method document on statistical tests</a> for a more detailed explanation of the ranksum test.</p>
*
* <h3>Caveat</h3>
* <p>The read position rank sum test can not be calculated for sites without a mixture of reads showing both the reference and alternate alleles.</p>

3
protected/gatk-tools-protected/src/main/java/org/broadinstitute/gatk/tools/walkers/annotator/MappingQualityRankSumTest.java
View File

@ -68,7 +68,7 @@ import java.util.*;
* <p>This annotation can be used to evaluate confidence in a variant call and is a recommended covariate for variant recalibration (VQSR). Finding a statistically significant difference in quality either way suggests that the sequencing and/or mapping process may have been biased or affected by an artifact. In practice, we only filter out low negative values when evaluating variant quality because the idea is to filter out variants for which the quality of the data supporting the alternate allele is comparatively low. The reverse case, where it is the quality of data supporting the reference allele that is lower (resulting in positive ranksum scores), is not really informative for filtering variants.
*
* <h3>Statistical notes</h3>
* <p>The value output for this annotation is the u-based z-approximation from the Mann-Whitney-Wilcoxon Rank Sum Test for mapping qualities (MAPQ of reads supporting REF vs. MAPQ of reads supporting ALT). See the <a href="http://www.broadinstitute.org/gatk/guide/article?id=4732">method document on statistical tests</a> for a more detailed explanation of the ranksum test.</p>
* <p>The value output for this annotation is the u-based z-approximation from the Mann-Whitney-Wilcoxon Rank Sum Test for mapping qualities (MAPQ of reads supporting REF vs. MAPQ of reads supporting ALT). See the <a href="http://www.broadinstitute.org/gatk/guide/article?id=8031">method document on statistical tests</a> for a more detailed explanation of the ranksum test.</p>
*
* <h3>Caveats</h3>
* <ul><li>The mapping quality rank sum test can not be calculated for sites without a mixture of reads showing both the reference and alternate alleles.</li>
@ -78,6 +78,7 @@ import java.util.*;
* <h3>Related annotations</h3>
* <ul>
* <li><b><a href="https://www.broadinstitute.org/gatk/guide/tooldocs/org_broadinstitute_gatk_tools_walkers_annotator_AS_MappingQualityRankSumTest.php">AS_MappingQualityRankSumTest</a></b> outputs an allele-specific version of this annotation.</li>
* <li><b><a href="https://www.broadinstitute.org/gatk/guide/tooldocs/org_broadinstitute_gatk_tools_walkers_annotator_AS_MQMateRankSumTest.php">AS_MQMateRankSumTest</a></b> outputs the allele-specific rank sum test on the mapping quality of the reads' mates rather than the reads themselves.</li>
* <li><b><a href="https://www.broadinstitute.org/gatk/guide/tooldocs/org_broadinstitute_gatk_tools_walkers_annotator_RMSMappingQuality.php">RMSMappingQuality</a></b> gives an estimation of the overal read mapping quality supporting a variant call.</li>
* </ul>
*

3
protected/gatk-tools-protected/src/main/java/org/broadinstitute/gatk/tools/walkers/annotator/RankSumTest.java
View File

@ -71,7 +71,8 @@ import java.util.*;
/**
* Abstract root for all RankSum-based annotations
* Abstract root for all RankSum-based annotations.
* The RankSumTest concept is documented at https://software.broadinstitute.org/gatk/documentation/article?id=8031
*/
//TODO: will eventually implement ReducibleAnnotation in order to preserve accuracy for CombineGVCFs and GenotypeGVCFs -- see RMSAnnotation.java for an example of an abstract ReducibleAnnotation
public abstract class RankSumTest extends InfoFieldAnnotation implements ActiveRegionBasedAnnotation {

2
protected/gatk-tools-protected/src/main/java/org/broadinstitute/gatk/tools/walkers/annotator/ReadPosRankSumTest.java
View File

@ -74,7 +74,7 @@ import java.util.*;
* <p>This annotation can be used to evaluate confidence in a variant call and is a recommended covariate for variant recalibration (VQSR). Finding a statistically significant difference in relative position either way suggests that the sequencing process may have been biased or affected by an artifact. In practice, we only filter out low negative values when evaluating variant quality because the idea is to filter out variants for which the quality of the data supporting the alternate allele is comparatively low. The reverse case, where it is the quality of data supporting the reference allele that is lower (resulting in positive ranksum scores), is not really informative for filtering variants.</p>
*
* <h3>Statistical notes</h3>
* <p>The value output for this annotation is the u-based z-approximation from the Mann-Whitney-Wilcoxon Rank Sum Test for site position within reads (position within reads supporting REF vs. position within reads supporting ALT). See the <a href="http://www.broadinstitute.org/gatk/guide/article?id=4732">method document on statistical tests</a> for a more detailed explanation of the ranksum test.</p>
* <p>The value output for this annotation is the u-based z-approximation from the Mann-Whitney-Wilcoxon Rank Sum Test for site position within reads (position within reads supporting REF vs. position within reads supporting ALT). See the <a href="http://www.broadinstitute.org/gatk/guide/article?id=8031">method document on statistical tests</a> for a more detailed explanation of the ranksum test.</p>
*
* <h3>Caveat</h3>
* <ul>

10
protected/gatk-tools-protected/src/main/java/org/broadinstitute/gatk/tools/walkers/annotator/StrandOddsRatio.java
View File

@ -77,24 +77,22 @@ import java.util.*;
*
* <p>and its inverse:</p>
*
* <table>
* <table class='table table-striped'>
* <tr><td>&nbsp;</td><td>+ strand </td><td>- strand</td></tr>
* <tr><td>REF;</td><td>X[0][0]</td><td>X[0][1]</td></tr>
* <tr><td>ALT;</td><td>X[1][0]</td><td>X[1][1]</td></tr>
* </table>
*
* <br />
* <p>The sum R + 1/R is used to detect a difference in strand bias for REF and for ALT (the sum makes it symmetric). A high value is indicative of large difference where one entry is very small compared to the others. A scale factor of refRatio/altRatio where</p>
*
* $$ refRatio = \frac{max(X[0][0], X[0][1])}{min(X[0][0], X[0][1} $$
* $$ refRatio = \frac{min(X[0][0], X[0][1])}{max(X[0][0], X[0][1} $$
*
* <p>and </p>
*
* $$ altRatio = \frac{max(X[1][0], X[1][1])}{min(X[1][0], X[1][1]} $$
* $$ altRatio = \frac{min(X[1][0], X[1][1])}{max(X[1][0], X[1][1]} $$
*
* <p>ensures that the annotation value is large only. </p>
*
* <p>See the <a href="http://www.broadinstitute.org/gatk/guide/article?id=4732">method document on statistical tests</a> for a more detailed explanation of this statistical test.</p>
*
* <h3>Caveat</h3>
* <p>
* The name SOR is not entirely appropriate because the implementation was changed somewhere between the start of development and release of this annotation. Now SOR isn't really an odds ratio anymore. The goal was to separate certain cases of data without penalizing variants that occur at the ends of exons because they tend to only be covered by reads in one direction (depending on which end of the exon they're on), so if a variant has 10 ref reads in the + direction, 1 ref read in the - direction, 9 alt reads in the + direction and 2 alt reads in the - direction, it's actually not strand biased, but the FS score is pretty bad. The implementation that resulted derived in part from empirically testing some read count tables of various sizes with various ratios and deciding from there.</p>

14
protected/gatk-tools-protected/src/main/java/org/broadinstitute/gatk/tools/walkers/cancer/contamination/ContEst.java
View File

@ -197,29 +197,29 @@ public class ContEst extends RodWalker<Map<String, Map<String, ContaminationStat
public SeqGenotypeMode genotypeMode = SeqGenotypeMode.HARD_THRESHOLD;
// ------------------------------------------------------------------------------------------------------------------------------------------------------
// hidden arguments
// advanced arguments
// ------------------------------------------------------------------------------------------------------------------------------------------------------
@Hidden
@Advanced
@Argument(fullName = "trim_interval", doc = "progressively trim from 0 to TRIM_FRACTION by this interval", required = false)
public double TRIM_INTERVAL = 0;
@Hidden
@Advanced
@Argument(fullName = "min_site_depth", required = false, doc = "minimum depth at a site to consider in calculation")
public int MIN_SITE_DEPTH = 0;
@Hidden
@Advanced
@Argument(fullName = "fixed_epsilon_qscore", required = false, doc = "use a constant epsilon (phred scale) for calculation")
public Byte FIXED_EPSILON = null;
@Hidden
@Advanced
@Argument(fullName = "min_genotype_depth", required = false, doc = "what minimum depth is required to call a site in seq genotype mode")
public int MIN_GENOTYPE_DEPTH_FOR_SEQ = 50;
@Hidden
@Advanced
@Argument(fullName = "min_genotype_ratio", required = false, doc = "the ratio of alt to other bases to call a site a hom non-ref variant")
public double MIN_GENOTYPE_RATIO = 0.80;
@Hidden
@Advanced
@Argument(fullName = "min_genotype_llh", required = false, doc = "the min log likelihood for UG to call a genotype")
public double MIN_UG_LOG_LIKELIHOOD = 5;
// ------------------------------------------------------------------------------------------------------------------------------------------------------

38
protected/gatk-tools-protected/src/main/java/org/broadinstitute/gatk/tools/walkers/cancer/m2/MuTect2.java
View File

@ -109,26 +109,19 @@ import static java.lang.Math.pow;
/**
* Call somatic SNPs and indels via local re-assembly of haplotypes
*
* <p>MuTect2 is a somatic SNP and indel caller that combines the DREAM challenge-winning somatic genotyping engine of the original MuTect (<a href='http://www.nature.com/nbt/journal/v31/n3/full/nbt.2514.html'>Cibulskis et al., 2013</a>) with the assembly-based machinery of HaplotypeCaller.</p>
*
* <p>The basic operation of MuTect2 proceeds similarly to that of the <a href="https://www.broadinstitute.org/gatk/guide/tooldocs/org_broadinstitute_gatk_tools_walkers_haplotypecaller_HaplotypeCaller.php">HaplotypeCaller</a> </p>
* <p>MuTect2 is a somatic SNP and indel caller that combines the DREAM challenge-winning somatic genotyping engine of the original MuTect (<a href='http://www.nature.com/nbt/journal/v31/n3/full/nbt.2514.html'>Cibulskis et al., 2013</a>) with the assembly-based machinery of HaplotypeCaller. The basic operation of MuTect2 proceeds similarly to that of the <a href="https://www.broadinstitute.org/gatk/guide/tooldocs/org_broadinstitute_gatk_tools_walkers_haplotypecaller_HaplotypeCaller.php">HaplotypeCaller</a>.</p>
*
* <h3>Differences from HaplotypeCaller</h3>
* <p>While the HaplotypeCaller relies on a ploidy assumption (diploid by default) to inform its genotype likelihood and
* variant quality calculations, MuTect2 allows for a varying allelic fraction for each variant, as is often seen in tumors with purity less
* than 100%, multiple subclones, and/or copy number variation (either local or aneuploidy). MuTect2 also differs from the HaplotypeCaller in that it does apply some hard filters
* to variants before producing output.</p>
* <p>While the HaplotypeCaller relies on a ploidy assumption (diploid by default) to inform its genotype likelihood and variant quality calculations, MuTect2 allows for a varying allelic fraction for each variant, as is often seen in tumors with purity less than 100%, multiple subclones, and/or copy number variation (either local or aneuploidy). MuTect2 also differs from the HaplotypeCaller in that it does apply some hard filters to variants before producing output.</p>
* <p>Note that the GVCF generation capabilities of HaplotypeCaller are NOT available in MuTect2, even though some of the relevant arguments are listed below. There are currently no plans to make GVCF calling available in MuTect2.</p>
*
* <h3>Usage examples</h3>
* <p>These are example commands that show how to run MuTect2 for typical use cases. Square brackets ("[ ]")
* indicate optional arguments. Note that parameter values shown here may not be the latest recommended; see the
* Best Practices documentation for detailed recommendations. </p>
* <p>These are example commands that show how to run MuTect2 for typical use cases. Square brackets ("[ ]") indicate optional arguments. Note that parameter values shown here may not be the latest recommended; see the Best Practices documentation for detailed recommendations. </p>
*
* <br />
* <h4>Tumor/Normal variant calling</h4>
* <pre>
* java
* -jar GenomeAnalysisTK.jar \
* java -jar GenomeAnalysisTK.jar \
* -T MuTect2 \
* -R reference.fasta \
* -I:tumor tumor.bam \
@ -141,10 +134,9 @@ import static java.lang.Math.pow;
*
* <h4>Normal-only calling for panel of normals creation</h4>
* <pre>
* java
* -jar GenomeAnalysisTK.jar
* -T MuTect2
* -R reference.fasta
* java -jar GenomeAnalysisTK.jar \
* -T MuTect2 \
* -R reference.fasta \
* -I:tumor normal1.bam \
* [--dbsnp dbSNP.vcf] \
* [--cosmic COSMIC.vcf] \
@ -153,12 +145,11 @@ import static java.lang.Math.pow;
* -o output.normal1.vcf
* </pre>
* <br />
* For full PON creation, call each of your normals separately in artifact detection mode. Then use CombineVariants to
* output only sites where a variant was seen in at least two samples:
* For full PON creation, call each of your normals separately in artifact detection mode as shown above. Then use CombineVariants to output only sites where a variant was seen in at least two samples:
* <pre>
* java -jar GenomeAnalysisTK.jar
* -T CombineVariants
* -R reference.fasta
* java -jar GenomeAnalysisTK.jar \
* -T CombineVariants \
* -R reference.fasta \
* -V output.normal1.vcf -V output.normal2.vcf [-V output.normal2.vcf ...] \
* -minN 2 \
* --setKey "null" \
@ -170,7 +161,10 @@ import static java.lang.Math.pow;
*
* <h3>Caveats</h3>
* <ul>
* <li>MuTect2 currently only supports the calling of a single tumor-normal pair at a time</li>
* <li>As noted in several places in the documentation, MuTect2 is currently released under BETA status; it is NOT recommended for production work and is NOT available for commercial/for-profit licensing.</li>
* <li>MuTect2 currently only supports the calling of a single tumor-normal pair at a time.</li>
* <li>Tumor-only variant calling is possible but it is NOT supported and we will not answer any questions about it until it becomes a supported feature.</li>
* <li>Some of the arguments listed below are not functional; they are exclusive to HaplotypeCaller and are listed here due to technical entanglements in the code. This will be resolved in the upcoming GATK 4 release.</li>
* </ul>
*
*/

2
protected/gatk-tools-protected/src/main/java/org/broadinstitute/gatk/tools/walkers/genotyper/GenotypingEngine.java
View File

@ -631,7 +631,7 @@ public abstract class GenotypingEngine<Config extends StandardCallerArgumentColl
if (!inputPriors.isEmpty()) {
// user-specified priors
if (inputPriors.size() != N)
throw new UserException.BadArgumentValue("inputPrior","Invalid length of inputPrior vector: vector length must be equal to # samples +1 ");
throw new UserException.BadArgumentValue("inputPrior","Invalid length of inputPrior vector: vector length must be equal to # samples * ploidy");
for (final Double prior : inputPriors) {
if (prior <= 0 || prior >= 1) throw new UserException.BadArgumentValue("inputPrior","inputPrior vector values must be greater than 0 and less than 1");
}

42
protected/gatk-tools-protected/src/main/java/org/broadinstitute/gatk/tools/walkers/genotyper/StandardCallerArgumentCollection.java
View File

@ -81,26 +81,30 @@ public class StandardCallerArgumentCollection implements Cloneable {
public GenotypingOutputMode genotypingOutputMode = GenotypingOutputMode.DISCOVERY;
/**
* When the UnifiedGenotyper is put into GENOTYPE_GIVEN_ALLELES mode it will genotype the samples using only the alleles provide in this rod binding
* When --genotyping_mode is set to GENOTYPE_GIVEN_ALLELES mode, the caller will genotype the samples using only the alleles provide in this callset. Note that this is not well tested in HaplotypeCaller, and is definitely not suitable for use with HaplotypeCaller in -ERC GVCF mode. In addition, it does not apply to MuTect2 at all.
*/
@Input(fullName="alleles", shortName = "alleles", doc="The set of alleles at which to genotype when --genotyping_mode is GENOTYPE_GIVEN_ALLELES", required=false)
@Input(fullName="alleles", shortName = "alleles", doc="Set of alleles to use in genotyping", required=false)
public RodBinding<VariantContext> alleles;
/**
* If this fraction is greater is than zero, the caller will aggressively attempt to remove contamination through biased down-sampling of reads.
* Basically, it will ignore the contamination fraction of reads for each alternate allele. So if the pileup contains N total bases, then we
* will try to remove (N * contamination fraction) bases for each alternate allele.
* If this fraction is greater is than zero, the caller will aggressively attempt to remove
* contamination through biased down-sampling of reads (for all samples). Basically, it will ignore the
* contamination fraction of reads for each alternate allele. So if the pileup contains N
* total bases, then we will try to remove (N * contamination fraction) bases for each alternate
* allele.
*/
@Argument(fullName = "contamination_fraction_to_filter", shortName = "contamination", doc = "Fraction of contamination in sequencing data (for all samples) to aggressively remove", required = false)
@Argument(fullName = "contamination_fraction_to_filter", shortName = "contamination", doc = "Fraction of contamination to aggressively remove", required = false)
public double CONTAMINATION_FRACTION = DEFAULT_CONTAMINATION_FRACTION;
public static final double DEFAULT_CONTAMINATION_FRACTION = 0.0;
/**
* This argument specifies a file with two columns "sample" and "contamination" specifying the contamination level for those samples.
* Samples that do not appear in this file will be processed with CONTAMINATION_FRACTION.
* This argument specifies a file with two columns "sample" and "contamination" (separated by a tab)
* specifying the contamination level for those samples (where contamination is given as a
* decimal number, not an integer) per line. There should be no header. Samples that do not appear
* in this file will be processed with CONTAMINATION_FRACTION.
**/
@Advanced
@Argument(fullName = "contamination_fraction_per_sample_file", shortName = "contaminationFile", doc = "Tab-separated File containing fraction of contamination in sequencing data (per sample) to aggressively remove. Format should be \"<SampleID><TAB><Contamination>\" (Contamination is double) per line; No header.", required = false)
@Argument(fullName = "contamination_fraction_per_sample_file", shortName = "contaminationFile", doc = "Contamination per sample", required = false)
public File CONTAMINATION_FRACTION_FILE = null;
/**
@ -148,23 +152,33 @@ public class StandardCallerArgumentCollection implements Cloneable {
* Controls the model used to calculate the probability that a site is variant plus the various sample genotypes in the data at a given locus.
*/
@Hidden
@Argument(fullName = "p_nonref_model", shortName = "pnrm", doc = "Non-reference probability calculation model to employ", required = false)
@Argument(fullName = "p_nonref_model", shortName = "pnrm", doc = "Non-reference probability calculation model", required = false)
public AFCalculatorImplementation requestedAlleleFrequencyCalculationModel;
@Hidden
@Argument(shortName = "logExactCalls", doc="x", required=false)
public File exactCallsLog = null;
@Argument(fullName = "output_mode", shortName = "out_mode", doc = "Specifies which type of calls we should output", required = false)
/**
* Experimental argument FOR USE WITH UnifiedGenotyper ONLY. When using HaplotypeCaller, use -ERC
* instead. When using GenotypeGVCFs, see -allSites.
*/
@Advanced
@Argument(fullName = "output_mode", shortName = "out_mode", doc = "Which type of calls we should output", required = false)
public OutputMode outputMode = OutputMode.EMIT_VARIANTS_ONLY;
/**
* Advanced, experimental argument: if SNP likelihood model is specified, and if EMIT_ALL_SITES output mode is set, when we set this argument then we will also emit PLs at all sites.
* This will give a measure of reference confidence and a measure of which alt alleles are more plausible (if any).
* Experimental argument FOR USE WITH UnifiedGenotyper ONLY: if SNP likelihood model
* is specified, and if EMIT_ALL_SITES output mode is set, when we set this argument then we
* will also emit PLs at all sites. This will give a measure of reference confidence and a
* measure of which alt alleles are more plausible (if any).
* WARNINGS:
* - This feature will inflate VCF file size considerably.
* - All SNP ALT alleles will be emitted with corresponding 10 PL values.
* - An error will be emitted if EMIT_ALL_SITES is not set, or if anything other than diploid SNP model is used
* - An error will be emitted if EMIT_ALL_SITES is not set, or if anything other than diploid
* SNP model is used
* - THIS WILL NOT WORK WITH HaplotypeCaller, GenotypeGVCFs or MuTect2! Use HaplotypeCaller with
* -ERC GVCF then GenotypeGVCFs instead. See the Best Practices documentation for more information.
*/
@Advanced
@Argument(fullName = "allSitePLs", shortName = "allSitePLs", doc = "Annotate all sites with PLs", required = false)

2
protected/gatk-tools-protected/src/main/java/org/broadinstitute/gatk/tools/walkers/phasing/PhaseByTransmission.java
View File

@ -140,7 +140,7 @@ import java.util.*;
* </pre>
*
*/
@DocumentedGATKFeature( groupName = HelpConstants.DOCS_CAT_VARDISC, extraDocs = {CommandLineGATK.class} )
@DocumentedGATKFeature( groupName = HelpConstants.DOCS_CAT_VARMANIP, extraDocs = {CommandLineGATK.class} )
public class PhaseByTransmission extends RodWalker<HashMap<Byte,Integer>, HashMap<Byte,Integer>> {
@ArgumentCollection

2
protected/gatk-tools-protected/src/main/java/org/broadinstitute/gatk/tools/walkers/phasing/ReadBackedPhasing.java
View File

@ -124,7 +124,7 @@ import static org.broadinstitute.gatk.engine.GATKVCFUtils.getVCFHeadersFromRods;
* reverse order between these two genotypes.</p>
* <p>In an old notation that RBP used to output in much earlier versions, the genotypes would have been: 0/1 and 1|0,
* respectively. This was changed because depending on the case it caused ambiguity, incompleteness, and possible
* inconsistency with trio-based phasing. In contrast, the HP tag is much more explicitl for linking alleles, especially
* inconsistency with trio-based phasing. In contrast, the HP tag is much more explicit for linking alleles, especially
* if the genotypes are non-consecutive.</p>
*
* <h3>Usage example</h3>

3
protected/gatk-tools-protected/src/main/java/org/broadinstitute/gatk/tools/walkers/rnaseq/SplitNCigarReads.java
View File

@ -108,7 +108,8 @@ import java.util.ArrayList;
* -I input.bam \
* -o output.bam \
* -U ALLOW_N_CIGARS
*
* </pre>
*
* <h3>Note</h3>
* <p>When this tool is used as part of the RNAseq best practices, the command should include mapping quality
* reassignment. See the Best Practices documentation for details.</p>

5
public/gatk-engine/src/main/java/org/broadinstitute/gatk/engine/arguments/GATKArgumentCollection.java
View File

@ -416,10 +416,9 @@ public class GATKArgumentCollection {
public boolean disableAutoIndexCreationAndLockingWhenReadingRods = false;
/**
* FOR DEBUGGING PURPOSES ONLY. This option is required in order to pass integration tests.
* This option is intended to be used FOR DEBUGGING PURPOSES ONLY. Note to developers: it is required in order to pass integration tests.
*/
@Hidden
@Argument(fullName = "no_cmdline_in_header", shortName = "no_cmdline_in_header", doc = "Don't include the command line in the VCF header",
@Argument(fullName = "no_cmdline_in_header", shortName = "no_cmdline_in_header", doc = "Don't include the command line in output VCF headers",
required = false)
public boolean disableCommandLineInVCF = false;

9
public/gatk-engine/src/main/java/org/broadinstitute/gatk/engine/filters/NotPrimaryAlignmentFilter.java
View File

@ -28,11 +28,10 @@ package org.broadinstitute.gatk.engine.filters;
import htsjdk.samtools.SAMRecord;
/**
* Filter out reads that are non-primary alignments
* Filter out read records that are secondary alignments
*
* <p>This filter recognizes the SAM flag that identifies secondary and supplementary alignments, i.e. non-primary alignments.
* It is intended to ensure that only reads that are likely to be mapped in the right place, and therefore to be
* informative, will be used in analysis.</p>
* <p>This filter recognizes the SAM flag that identifies secondary alignments. It is intended to ensure that only records that are likely to be mapped in the right place, and therefore to be
* informative, will be used in analysis. To be clear, it does NOT filter out read records that are supplementary alignments.</p>
*
* <h3>Usage example</h3>
*
@ -45,8 +44,6 @@ import htsjdk.samtools.SAMRecord;
* -rf NotPrimaryAlignment
* </pre>
*
* @author rpoplin
* @since Dec 9, 2009
*/
public class NotPrimaryAlignmentFilter extends ReadFilter {

16
public/gatk-tools-public/src/main/java/org/broadinstitute/gatk/tools/walkers/annotator/VariantAnnotator.java
View File

@ -54,9 +54,7 @@ import java.util.*;
*
* <p>
* This tool is designed to annotate variant calls based on their context (as opposed to functional annotation).
* Various annotation modules are available; see the
* <a href="https://www.broadinstitute.org/gatk/guide/tooldocs/org_broadinstitute_gatk_tools_walkers_annotator_VariantAnnotator.php#VariantAnnotations">documentation</a>
* for a complete list.
* Various annotation modules are available; see the "Annotation Modules" page linked in the Tool Documentation sidebar for a complete list.
*
* <h3>Input</h3>
* <p>
@ -77,9 +75,9 @@ import java.util.*;
* -R reference.fasta \
* -T VariantAnnotator \
* -I input.bam \
* -V input.vcf \
* -o output.vcf \
* -A Coverage \
* -V input.vcf \
* -L input.vcf \
* --dbsnp dbsnp.vcf
* </pre>
@ -90,11 +88,11 @@ import java.util.*;
* -R reference.fasta \
* -T VariantAnnotator \
* -I input.bam \
* -o output.vcf \
* -V input.vcf \
* -o output.vcf \
* -L input.vcf \
* --resource:foo resource.vcf
* -E foo.AF
* --resource:foo resource.vcf \
* -E foo.AF \
* --resourceAlleleConcordance
* </pre>
*
@ -103,11 +101,11 @@ import java.util.*;
* java -jar GenomeAnalysisTK.jar \
* -R reference.fasta \
* -T VariantAnnotator \
* -V input.vcf \
* -o output.vcf \
* --resource:foo resource.vcf \
* --expression foo.AF \
* --expression foo.FILTER \
* -V input.vcf \
* --expression foo.FILTER
* </pre>
*
*/

2
public/gatk-tools-public/src/main/java/org/broadinstitute/gatk/tools/walkers/filters/VariantFiltration.java
View File

@ -119,7 +119,7 @@ public class VariantFiltration extends RodWalker<Integer, Integer> implements Tr
protected VariantContextWriter writer = null;
/**
* VariantFiltration accepts any number of JEXL expressions (so you can have two named filters by using
* VariantFiltration accepts any number of <a href='https://software.broadinstitute.org/gatk/guide/article?id=1255'>JEXL expressions</a> (so you can have two named filters by using
* {@code --filterName One --filterExpression "X < 1" --filterName Two --filterExpression "X > 2"}).
*/
@Argument(fullName="filterExpression", shortName="filter", doc="One or more expression used with INFO fields to filter", required=false)

17
public/gatk-tools-public/src/main/java/org/broadinstitute/gatk/tools/walkers/variantutils/ValidateVariants.java
View File

@ -194,10 +194,11 @@ public class ValidateVariants extends RodWalker<GenomeLoc, GenomeLocSortedSet> {
protected Boolean WARN_ON_ERROR = false;
/**
* Validate this file as a gvcf. In particular, every variant must include a <NON_REF> allele, and that
* every base in the territory under consideration is covered by a variant (or a reference block).
* If you specifed intervals (using -L or -XL) to restrict analysis to a subset of genomic regions,
* those intervals will need to be covered in a valid gvcf.
* This validation option REQUIRES that the input GVCF satisfies the following conditions:
* (1) every variant record must feature an allele in the list of ALT alleles, and
* (2) every position in the genomic territory under consideration must covered by a record, whether a single-position record or a reference block record.
* If the analysis that produced the file was restricted to a subset of genomic regions (for example using the -L or -XL arguments), the same intervals must be provided for validation.
* Otherwise, the validation tool will find positions that are not covered by records and will fail.
*/
@Argument(fullName = "validateGVCF", shortName = "gvcf", doc = "Validate this file as a GVCF", required = false, exclusiveOf = "DO_NOT_VALIDATE_FILTERED")
protected Boolean VALIDATE_GVCF = false;
@ -270,9 +271,11 @@ public class ValidateVariants extends RodWalker<GenomeLoc, GenomeLocSortedSet> {
final GenomeLocSortedSet uncoveredIntervals = traversalIntervals.subtractRegions(result);
if (traversalIntervals.subtractRegions(result).coveredSize() > 0) {
final UserException e = new UserException.FailsStrictValidation(file, "A GVCF must cover the entire region. Found " + uncoveredIntervals.coveredSize() +
" loci with no VariantContext covering it. The first uncovered segment is:" +
uncoveredIntervals.iterator().next());
final UserException e = new UserException.FailsStrictValidation(file, "Found " + uncoveredIntervals.coveredSize() +
" positions not covered by a VariantContext record. The first uncovered segment is: " + uncoveredIntervals.iterator().next() +
". As noted in the documentation for the --validateGVCF/-gvcf argument, GVCF validation requires that all positions to validate " +
"be covered by records. Use -L or --XL to specify what intervals are covered in the GVCF. These should be the same intervals used " +
"to generate the GVCF or a subset thereof.");
if (WARN_ON_ERROR) {
numErrors++;

6
public/gatk-utils/src/main/java/org/broadinstitute/gatk/utils/help/HelpConstants.java
View File

@ -27,9 +27,9 @@ package org.broadinstitute.gatk.utils.help;
public class HelpConstants {
public final static String BASE_GATK_URL = "https://www.broadinstitute.org/gatk";
public final static String GATK_DOCS_URL = BASE_GATK_URL + "/guide/tooldocs/";
public final static String GATK_ARTICLE_URL = BASE_GATK_URL + "/guide/article";
public final static String BASE_GATK_URL = "https://software.broadinstitute.org/gatk";
public final static String GATK_DOCS_URL = BASE_GATK_URL + "/documentation/tooldocs/";
public final static String GATK_ARTICLE_URL = BASE_GATK_URL + "/documentation/article";
public final static String GATK_FORUM_URL = "http://gatkforums.broadinstitute.org/";
public final static String GATK_FORUM_API_URL = "https://gatkforums.broadinstitute.org/api/v1/";

538
settings/helpTemplates/generic.template.html
View File

@ -8,289 +8,291 @@
<div class='row-fluid' id="top">
<#include "common.html"/>
<#include "common.html"/>
<#macro argumentlist name myargs>
<#if myargs?size != 0>
<tr>
<th colspan="4" id="row-divider">${name}</th>
</tr>
<#list myargs as arg>
<tr>
<td><a href="#${arg.name}">${arg.name}</a><br />
<#if arg.synonyms != "NA">
<#if arg.name[2..] != arg.synonyms[1..]>
&nbsp;<em>${arg.synonyms}</em>
</#if>
</#if>
</td>
<!--<td>${arg.type}</td> -->
<td>${arg.defaultValue!"NA"}</td>
<td>${arg.summary}</td>
</tr>
</#list>
</#if>
</#macro>
<#macro argumentDetails arg>
<hr style="border-bottom: dotted 1px #C0C0C0;" />
<h3><a name="${arg.name}">${arg.name} </a>
<#if arg.synonyms??> / <small>${arg.synonyms}</small></#if>
</h3>
<p class="args">
<b>${arg.summary}</b><br />
${arg.fulltext}
</p>
<#if arg.rodTypes != "NA">
<p>This argument supports reference-ordered data (ROD) files in the following formats: ${arg.rodTypes}</p>
</#if>
<#if arg.otherArgumentRequired != "NA">
<p><b>Dependency:</b> This argument requires that you also specify <code>${arg.otherArgumentRequired}</code>.</p>
</#if>
<#if arg.exclusiveOf != "NA">
<p><b>Exclusion:</b> This argument cannot be used at the same time as <code>${arg.exclusiveOf}</code>.</p>
</#if>
<#if arg.options?has_content>
<p>
The ${arg.name} argument is an enumerated type (${arg.type}), which can have one of the following values:
<dl class="enum">
<#list arg.options as option>
<dt class="enum">${option.name}</dt>
<dd class="enum">${option.summary}</dd>
<#macro argumentlist name myargs>
<#if myargs?size != 0>
<tr>
<th colspan="4" id="row-divider">${name}</th>
</tr>
<#list myargs as arg>
<tr>
<td><a href="#${arg.name}">${arg.name}</a><br />
<#if arg.synonyms != "NA">
<#if arg.name[2..] != arg.synonyms[1..]>
&nbsp;<em>${arg.synonyms}</em>
</#if>
</#if>
</td>
<!--<td>${arg.type}</td> -->
<td>${arg.defaultValue!"NA"}</td>
<td>${arg.summary}</td>
</tr>
</#list>
</dl>
</#if>
</#macro>
<#macro argumentDetails arg>
<hr style="border-bottom: dotted 1px #C0C0C0;" />
<h3><a name="${arg.name}">${arg.name} </a>
<#if arg.synonyms??> / <small>${arg.synonyms}</small></#if>
</h3>
<p class="args">
<b>${arg.summary}</b><br />
${arg.fulltext}
</p>
</#if>
<p><#if arg.required != "NA">
<#if arg.required == "yes">
<span class="badge badge-important">R</span>
</#if>
<#if arg.rodTypes != "NA">
<p>This argument supports reference-ordered data (ROD) files in the following formats: ${arg.rodTypes}</p>
</#if>
<span class="label label-info ">${arg.type}</span>
<#if arg.defaultValue?has_content>
&nbsp;<span class="label">${arg.defaultValue}</span>
<#if arg.otherArgumentRequired != "NA">
<p><b>Dependency:</b> This argument requires that you also specify <code>${arg.otherArgumentRequired}</code>.</p>
</#if>
<#if arg.minValue?is_number>
&nbsp;<span class="label label-warning">[ [ ${arg.minValue}</span>
<#if arg.exclusiveOf != "NA">
<p><b>Exclusion:</b> This argument cannot be used at the same time as <code>${arg.exclusiveOf}</code>.</p>
</#if>
<#if arg.minRecValue?is_number>
&nbsp;<span class="label label-success">[ ${arg.minRecValue}</span>
</#if>
<#if arg.maxRecValue?is_number>
&nbsp;<span class="label label-success">${arg.maxRecValue} ]</span>
</#if>
<#if arg.maxValue?is_number>
&nbsp;<span class="label label-warning">${arg.maxValue} ] ]</span>
</#if>
</p>
</#macro>
<#macro relatedByType name type>
<#list relatedDocs as relatedDoc>
<#if relatedDoc.relation == type>
<h3>${name}</h3>
<ul>
<#list relatedDocs as relatedDoc>
<#if relatedDoc.relation == type>
<li><a href="${relatedDoc.filename}">${relatedDoc.name}</a> is a ${relatedDoc.relation}</li>
</#if>
</#list>
</ul>
<#break>
</#if>
</#list>
</#macro>
<?php $group = '${group}'; ?>
<section class="span4">
<aside class="well">
<a href="index"><h4><i class='fa fa-chevron-left'></i> Back to Tool Docs Index</h4></a>
</aside>
<aside class="well">
<h2>Categories</h2>
<@getCategories groups=groups />
</aside>
<?php getForumPosts( '${name}' ) ?>
</section>
<div class="span8">
<h1>${name}</h1>
<p class="lead">${summary}</p>
<#if group?? >
<h3>Category
<small> ${group}</small>
</h3>
</#if>
<#if walkertype != "">
<h3>Traversal
<small>${walkertype}</small>
</h3>
</#if>
<#if walkertype != "">
<h3>PartitionBy
<small>${partitiontype}</small>
</h3>
</#if>
<#if annotfield != "" >
<h3>VCF Field
<small>${annotfield}</small>
</h3>
</#if>
<#if annotinfo != "" >
<h3>Type
<small>${annotinfo}</small>
</h3>
</#if>
<#if annotdescript?has_content >
<h3>Header definition line <br />
<small>
<#list annotdescript as line>
<li><pre>${line}</pre></li>
</#list>
</small>
</h3>
</#if>
<hr>
<h2>Overview</h2>
${description}
<#-- Create references to additional capabilities if appropriate -->
<#if readfilters?size != 0 || parallel?size != 0>
<hr>
<h2>Additional Information</h2>
<p></p>
</#if>
<#if readfilters?size != 0>
<h3>Read filters</h3>
<#if readfilters?size = 1>
<p>This Read Filter is automatically applied to the data by the Engine before processing by ${name}.</p>
</#if>
<#if (readfilters?size > 1) >
<p>These Read Filters are automatically applied to the data by the Engine before processing by ${name}.</p>
</#if>
<ul>
<#list readfilters as filter>
<li><a href="${filter.filename}">${filter.name}</a></li>
<#if arg.options?has_content>
<p>
The ${arg.name} argument is an enumerated type (${arg.type}), which can have one of the following values:
<dl class="enum">
<#list arg.options as option>
<dt class="enum">${option.name}</dt>
<dd class="enum">${option.summary}</dd>
</#list>
</ul>
</dl>
</p>
</#if>
<#if parallel?size != 0>
<h3>Parallelism options</h3>
<#if parallel?size == 1>
<p>This tool can be run in multi-threaded mode using this option.</p>
<p><#if arg.required != "NA">
<#if arg.required == "yes">
<span class="badge badge-important">R</span>
</#if>
</#if>
<#if (parallel?size > 1)>
<p>This tool can be run in multi-threaded mode using these options.</p>
<span class="label label-info ">${arg.type}</span>
<#if arg.defaultValue?has_content>
&nbsp;<span class="label">${arg.defaultValue}</span>
</#if>
<ul>
<#list parallel as option>
<li><a href="${option.link}">${option.name} (${option.arg})</a></li>
</#list>
</ul>
</#if>
<#if downsampling?size != 0>
<h3>Downsampling settings</h3>
<#if downsampling.by == "NONE">
<p>This tool does not apply any downsampling by default.</p>
<#if arg.minValue?is_number>
&nbsp;<span class="label label-warning">[ [ ${arg.minValue}</span>
</#if>
<#if downsampling.by != "NONE">
<p>This tool applies the following downsampling settings by default.</p>
<#if arg.minRecValue?is_number>
&nbsp;<span class="label label-success">[ ${arg.minRecValue}</span>
</#if>
<#if arg.maxRecValue?is_number>
&nbsp;<span class="label label-success">${arg.maxRecValue} ]</span>
</#if>
<#if arg.maxValue?is_number>
&nbsp;<span class="label label-warning">${arg.maxValue} ] ]</span>
</#if>
</p>
</#macro>
<#macro relatedByType name type>
<#list relatedDocs as relatedDoc>
<#if relatedDoc.relation == type>
<h3>${name}</h3>
<ul>
<li>Mode: <b>${downsampling.by}</b></li>
<li>To coverage: <b>${downsampling.to_cov}</b></li>
<#list relatedDocs as relatedDoc>
<#if relatedDoc.relation == type>
<li><a href="${relatedDoc.filename}">${relatedDoc.name}</a> is a ${relatedDoc.relation}</li>
</#if>
</#list>
</ul>
<#break>
</#if>
</#list>
</#macro>
<?php $group = '${group}'; ?>
<section class="span4">
<aside class="well">
<a href="index"><h4><i class='fa fa-chevron-left'></i> Back to Tool Docs Index</h4></a>
</aside>
<aside class="well">
<h2>Categories</h2>
<@getCategories groups=groups />
</aside>
<?php getForumPosts( '${name}' ) ?>
</section>
<div class="span8">
<h1>${name}</h1>
<p class="lead">${summary}</p>
<#if group?? >
<h3>Category
<small> ${group}</small>
</h3>
</#if>
<#if walkertype != "">
<h3>Traversal
<small>${walkertype}</small>
</h3>
</#if>
<#if walkertype != "">
<h3>PartitionBy
<small>${partitiontype}</small>
</h3>
</#if>
<#if annotfield != "" >
<h3>VCF Field
<small>${annotfield}</small>
</h3>
</#if>
<#if annotinfo != "" >
<h3>Type
<small>${annotinfo}</small>
</h3>
</#if>
<#if annotdescript?has_content >
<h3>Header definition line <br />
<small>
<#list annotdescript as line>
<li><pre>${line}</pre></li>
</#list>
</small>
</h3>
</#if>
<hr>
<h2>Overview</h2>
${description}
<#-- Create references to additional capabilities if appropriate -->
<#if readfilters?size != 0 || parallel?size != 0>
<hr>
<h2>Additional Information</h2>
<p></p>
</#if>
<#if readfilters?size != 0>
<h3>Read filters</h3>
<#if readfilters?size = 1>
<p>This Read Filter is automatically applied to the data by the Engine before processing by ${name}.</p>
</#if>
<#if (readfilters?size > 1) >
<p>These Read Filters are automatically applied to the data by the Engine before processing by ${name}.</p>
</#if>
<ul>
<#list readfilters as filter>
<li><a href="${filter.filename}">${filter.name}</a></li>
</#list>
</ul>
</#if>
</#if>
<#if refwindow?size != 0>
<h3>Window size</h3>
<p>This tool uses a sliding window on the reference.</p>
<ul>
<li>Window start: <b>${refwindow.start}</b> bp before the locus</li>
<li>Window stop: <b>${refwindow.stop}</b> bp after the locus</li>
</ul>
</#if>
<#if activeregion?size != 0>
<h3>ActiveRegion settings</h3>
<p>This tool uses ActiveRegions on the reference.</p>
<ul>
<li>Minimum region size: <b>${activeregion.min}</b> bp</li>
<li>Maximum region size: <b>${activeregion.max}</b> bp</li>
<li>Extension increments: <b>${activeregion.ext}</b> bp</li>
</ul>
</#if>
<#if extradocs?size != 0 || arguments.all?size != 0>
<hr>
<h2>Command-line Arguments</h2>
<p></p>
</#if>
<#if extradocs?size != 0>
<h3>Engine arguments</h3>
<p>All tools inherit arguments from the GATK Engine' "CommandLineGATK" argument collection, which can be
used to modify various aspects of the tool's function. For example, the -L argument directs the GATK
engine to restrict processing to specific genomic intervals; or the -rf argument allows you to apply
certain read filters to exclude some of the data from the analysis.</p>
<ul>
<#list extradocs as extradoc>
<li><a href="${extradoc.filename}">${extradoc.name}</a></li>
</#list>
</ul>
</#if>
<#-- This class is related to other documented classes via sub/super relationships -->
<#if relatedDocs?? && relatedDocs?size != 0>
<h3>Related capabilities</h3>
<@relatedByType name="Superclasses" type="superclass"/>
<@relatedByType name="Subclasses" type="subclass"/>
</#if>
<#-- Create the argument summary -->
<#if arguments.all?size != 0>
<h3>${name} specific arguments</h3>
<p>This table summarizes the command-line arguments that are specific to this tool. For more details on each argument, see the list further down below the table or click on an argument name to jump directly to that entry in the list.</p>
<table class="table table-striped table-bordered table-condensed">
<thead>
<tr>
<th>Argument name(s)</th>
<th>Default value</th>
<th>Summary</th>
</tr>
</thead>
<tbody>
<@argumentlist name="Required Inputs" myargs=arguments.required_in/>
<@argumentlist name="Required Outputs" myargs=arguments.required_out/>
<@argumentlist name="Required Parameters" myargs=arguments.required_param/>
<@argumentlist name="Required Flags" myargs=arguments.required_flag/>
<@argumentlist name="Optional Inputs" myargs=arguments.optional_in/>
<@argumentlist name="Optional Outputs" myargs=arguments.optional_out/>
<@argumentlist name="Optional Parameters" myargs=arguments.optional_param/>
<@argumentlist name="Optional Flags" myargs=arguments.optional_flag/>
<@argumentlist name="Advanced Inputs" myargs=arguments.advanced_in/>
<@argumentlist name="Advanced Outputs" myargs=arguments.advanced_out/>
<@argumentlist name="Advanced Parameters" myargs=arguments.advanced_param/>
<@argumentlist name="Advanced Flags" myargs=arguments.advanced_flag/>
<@argumentlist name="Hidden" myargs=arguments.hidden/>
<@argumentlist name="Deprecated" myargs=arguments.deprecated/>
</tbody>
</table>
</#if>
<#-- List all of the things -->
<#if arguments.all?size != 0>
<#-- Create the argument details -->
<h3>Argument details</h3>
<p>Arguments in this list are specific to this tool. Keep in mind that other arguments are available that are shared with other tools (e.g. command-line GATK arguments); see Inherited arguments above.</p>
<#list arguments.all as arg>
<@argumentDetails arg=arg/>
</#list>
<#if parallel?size != 0>
<h3>Parallelism options</h3>
<#if parallel?size == 1>
<p>This tool can be run in multi-threaded mode using this option.</p>
</#if>
<@footerInfo />
<@footerClose />
<#if (parallel?size > 1)>
<p>This tool can be run in multi-threaded mode using these options.</p>
</#if>
<ul>
<#list parallel as option>
<li><a href="${option.link}">${option.name} (${option.arg})</a></li>
</#list>
</ul>
</#if>
<#if downsampling?size != 0>
<h3>Downsampling settings</h3>
<#if downsampling.by == "NONE">
<p>This tool does not apply any downsampling by default.</p>
</#if>
<#if downsampling.by != "NONE">
<p>This tool applies the following downsampling settings by default.</p>
<ul>
<li>Mode: <b>${downsampling.by}</b></li>
<li>To coverage: <b>${downsampling.to_cov}</b></li>
</ul>
</#if>
</#if>
<#if refwindow?size != 0>
<h3>Window size</h3>
<p>This tool uses a sliding window on the reference.</p>
<ul>
<li>Window start: <b>${refwindow.start}</b> bp before the locus</li>
<li>Window stop: <b>${refwindow.stop}</b> bp after the locus</li>
</ul>
</#if>
<#if activeregion?size != 0>
<h3>ActiveRegion settings</h3>
<p>This tool uses ActiveRegions on the reference.</p>
<ul>
<li>Minimum region size: <b>${activeregion.min}</b> bp</li>
<li>Maximum region size: <b>${activeregion.max}</b> bp</li>
<li>Extension increments: <b>${activeregion.ext}</b> bp</li>
</ul>
</#if>
<#if extradocs?size != 0 || arguments.all?size != 0>
<hr>
<h2>Command-line Arguments</h2>
<p></p>
</#if>
<#if extradocs?size != 0>
<h3>Engine arguments</h3>
<p>All tools inherit arguments from the GATK Engine' "CommandLineGATK" argument collection, which can be
used to modify various aspects of the tool's function. For example, the -L argument directs the GATK
engine to restrict processing to specific genomic intervals; or the -rf argument allows you to apply
certain read filters to exclude some of the data from the analysis.</p>
<ul>
<#list extradocs as extradoc>
<li><a href="${extradoc.filename}">${extradoc.name}</a></li>
</#list>
</ul>
</#if>
<#-- This class is related to other documented classes via sub/super relationships -->
<#if relatedDocs?? && relatedDocs?size != 0>
<h3>Related capabilities</h3>
<@relatedByType name="Superclasses" type="superclass"/>
<@relatedByType name="Subclasses" type="subclass"/>
</#if>
<#-- Create the argument summary -->
<#if arguments.all?size != 0>
<h3>${name} specific arguments</h3>
<p>This table summarizes the command-line arguments that are specific to this tool. For more details on each argument, see the list further down below the table or click on an argument name to jump directly to that entry in the list.</p>
<table class="table table-striped table-bordered table-condensed">
<thead>
<tr>
<th>Argument name(s)</th>
<th>Default value</th>
<th>Summary</th>
</tr>
</thead>
<tbody>
<@argumentlist name="Required Inputs" myargs=arguments.required_in/>
<@argumentlist name="Required Outputs" myargs=arguments.required_out/>
<@argumentlist name="Required Parameters" myargs=arguments.required_param/>
<@argumentlist name="Required Flags" myargs=arguments.required_flag/>
<@argumentlist name="Optional Inputs" myargs=arguments.optional_in/>
<@argumentlist name="Optional Outputs" myargs=arguments.optional_out/>
<@argumentlist name="Optional Parameters" myargs=arguments.optional_param/>
<@argumentlist name="Optional Flags" myargs=arguments.optional_flag/>
<@argumentlist name="Advanced Inputs" myargs=arguments.advanced_in/>
<@argumentlist name="Advanced Outputs" myargs=arguments.advanced_out/>
<@argumentlist name="Advanced Parameters" myargs=arguments.advanced_param/>
<@argumentlist name="Advanced Flags" myargs=arguments.advanced_flag/>
<@argumentlist name="Hidden" myargs=arguments.hidden/>
<@argumentlist name="Deprecated" myargs=arguments.deprecated/>
</tbody>
</table>
</#if>
<#-- List all of the things -->
<#if arguments.all?size != 0>
<#-- Create the argument details -->
<h3>Argument details</h3>
<p>Arguments in this list are specific to this tool. Keep in mind that other arguments are available that are shared with other tools (e.g. command-line GATK arguments); see Inherited arguments above.</p>
<#list arguments.all as arg>
<@argumentDetails arg=arg/>
</#list>
</#if>
<@footerInfo />
<@footerClose />
</div>
</div>