-
Function: Build a recalibration model to score variant quality for filtering purposes
Usage: java -Xmx4g -jar GenomeAnalysisTK.jar -T VariantRecalibrator -R reference.fasta -input raw_variants.vcf -resource:hapmap,known=false,training=true,truth=true,prior=15.0 hapmap_3.3.b37.sites.vcf -resource:omni,known=false,training=true,truth=false,prior=12.0 1000G_omni2.5.b37.sites.vcf -resource:1000G,known=false,training=true,truth=false,prior=10.0 1000G_phase1.snps.high_confidence.vcf -resource:dbsnp,known=true,training=false,truth=false,prior=2.0 dbsnp_135.b37.vcf -an QD -an MQ -an MQRankSum -an ReadPosRankSum -an FS -an SOR -an InbreedingCoeff -mode SNP -recalFile output.recal -tranchesFile output.tranches -rscriptFile output.plots.R
-
Function: Select a subset of variants from a larger callset
Usage: java -Xmx2g -jar GenomeAnalysisTK.jar -R ref.fasta -T SelectVariants --variant input.vcf -o output.vcf --selectTypeToExclude INDEL
-
Function: Calculate read counts per allele for allele-specific expression analysis
Usage: java -jar GenomeAnalysisTK.jar -R reference.fasta -T ASEReadCounter -o file_name.csv -I input.bam -sites sites.vcf -U ALLOW_N_CIGAR_READS [-minDepth 10] [--minMappingQuality 10] [--minBaseQuality 2] [-drf DuplicateRead]
-
Function: Selects headers from a VCF source
Usage: java -jar GenomeAnalysisTK.jar -T SelectHeaders -R reference.fasta -V input.vcf -o output.vcf -hn FILTER -hn FORMAT -hn INFO -he '.*SnpEff.*'
-
Function: Read clipping based on quality, position or sequence matching
Usage: java -jar GenomeAnalysisTK.jar -T ClipReads -R reference.fasta -I original.bam -o clipped.bam -XF seqsToClip.fasta -X CCCCC -CT "1-5,11-15" -QT 10
-
Function: Annotate physical phasing information
Usage: java -jar GenomeAnalysisTK.jar -T ReadBackedPhasing -R reference.fasta -I reads.bam --variant SNPs.vcf -L SNPs.vcf -o phased_SNPs.vcf --phaseQualityThresh 20.0
-
Function: Set the mapping quality of reads with a given value to another given value
Usage: java -jar GenomeAnalysisTK.jar -T PrintReads -R reference.fasta -I input.bam -o output.file -rf ReassignOneMappingQuality -RMQF 255 -RMQT 60
-
Function: Select a subset of variants from a larger callset
Usage: java -jar GenomeAnalysisTK.jar -T SelectVariants -R reference.fasta -V hapmap.vcf --discordance myCalls.vcf -o output.vcf -sn mySample
-
Function: Calculate genotype posterior likelihoods given panel data
Usage: java -jar GenomeAnalysisTK.jar -T CalculateGenotypePosteriors -R reference.fasta -V input.vcf -o output.withPosteriors.vcf
-
Function: Extract specific fields from a VCF file to a tab-delimited table
Usage: java -jar GenomeAnalysisTK.jar -R reference.fasta -T VariantsToTable -V file.vcf -F CHROM -F POS -F ID -F QUAL -F AC -o results.table
-
Function: General-purpose tool for variant evaluation (% in dbSNP, genotype concordance, Ti/Tv ratios, and a lot more)
Usage: Java -jar GenomeAnalysisTK.jar -T VariantEval -R reference.fasta -o output.MVs.byFamily.table --eval multiFamilyCallset.vcf -noEV -noST -ST Family -EV MendelianViolationEvaluator
-
Function: Select a subset of variants from a larger callset
Usage: java -jar GenomeAnalysisTK.jar -R ref.fasta -T SelectVariants --variant input.vcf -o output.vcf -se 'SAMPLE.+PARC' -select "QD > 10.0" -invertSelect
-
Function: Annotate variant calls with context information
Usage: java -jar GenomeAnalysisTK.jar -R reference.fasta -T VariantAnnotator -I input.bam -V input.vcf -o output.vcf -L input.vcf --resource:foo resource.vcf -E foo.AF --resourceAlleleConcordance
-
Function: Combine variant records from different sources
Usage: java -jar GenomeAnalysisTK.jar -T CombineVariants -R reference.fasta --variant input1.vcf --variant input2.vcf -o output.vcf -genotypeMergeOptions UNIQUIFY
-
Function: Perform joint genotyping on gVCF files produced by HaplotypeCaller
Usage: java -jar GenomeAnalysisTK.jar -T GenotypeGVCFs -R reference.fasta --variant sample1.g.vcf --variant sample2.g.vcf -o output.vcf