From cd99ea84f04ee98fd13e857a87dcc17f726c648f Mon Sep 17 00:00:00 2001
From: naumenko-sa <evolgenomicslab@gmail.com>
Date: Mon, 20 Aug 2018 13:03:38 -0400
Subject: [PATCH] 	new file:   data/test.vcf

---
 data/test.vcf | 434 ++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 434 insertions(+)
 create mode 100644 data/test.vcf

diff --git a/data/test.vcf b/data/test.vcf
new file mode 100644
index 0000000..6a4e91f
--- /dev/null
+++ b/data/test.vcf
@@ -0,0 +1,434 @@
+##fileformat=VCFv4.2
+##FILTER=<ID=PASS,Description="All filters passed">
+##contig=<ID=1,length=249250621>
+##contig=<ID=2,length=243199373>
+##contig=<ID=3,length=198022430>
+##contig=<ID=4,length=191154276>
+##contig=<ID=5,length=180915260>
+##contig=<ID=6,length=171115067>
+##contig=<ID=7,length=159138663>
+##contig=<ID=8,length=146364022>
+##contig=<ID=9,length=141213431>
+##contig=<ID=10,length=135534747>
+##contig=<ID=11,length=135006516>
+##contig=<ID=12,length=133851895>
+##contig=<ID=13,length=115169878>
+##contig=<ID=14,length=107349540>
+##contig=<ID=15,length=102531392>
+##contig=<ID=16,length=90354753>
+##contig=<ID=17,length=81195210>
+##contig=<ID=18,length=78077248>
+##contig=<ID=19,length=59128983>
+##contig=<ID=20,length=63025520>
+##contig=<ID=21,length=48129895>
+##contig=<ID=22,length=51304566>
+##contig=<ID=X,length=155270560>
+##contig=<ID=Y,length=59373566>
+##contig=<ID=MT,length=16569>
+##contig=<ID=GL000207.1,length=4262>
+##contig=<ID=GL000226.1,length=15008>
+##contig=<ID=GL000229.1,length=19913>
+##contig=<ID=GL000231.1,length=27386>
+##contig=<ID=GL000210.1,length=27682>
+##contig=<ID=GL000239.1,length=33824>
+##contig=<ID=GL000235.1,length=34474>
+##contig=<ID=GL000201.1,length=36148>
+##contig=<ID=GL000247.1,length=36422>
+##contig=<ID=GL000245.1,length=36651>
+##contig=<ID=GL000197.1,length=37175>
+##contig=<ID=GL000203.1,length=37498>
+##contig=<ID=GL000246.1,length=38154>
+##contig=<ID=GL000249.1,length=38502>
+##contig=<ID=GL000196.1,length=38914>
+##contig=<ID=GL000248.1,length=39786>
+##contig=<ID=GL000244.1,length=39929>
+##contig=<ID=GL000238.1,length=39939>
+##contig=<ID=GL000202.1,length=40103>
+##contig=<ID=GL000234.1,length=40531>
+##contig=<ID=GL000232.1,length=40652>
+##contig=<ID=GL000206.1,length=41001>
+##contig=<ID=GL000240.1,length=41933>
+##contig=<ID=GL000236.1,length=41934>
+##contig=<ID=GL000241.1,length=42152>
+##contig=<ID=GL000243.1,length=43341>
+##contig=<ID=GL000242.1,length=43523>
+##contig=<ID=GL000230.1,length=43691>
+##contig=<ID=GL000237.1,length=45867>
+##contig=<ID=GL000233.1,length=45941>
+##contig=<ID=GL000204.1,length=81310>
+##contig=<ID=GL000198.1,length=90085>
+##contig=<ID=GL000208.1,length=92689>
+##contig=<ID=GL000191.1,length=106433>
+##contig=<ID=GL000227.1,length=128374>
+##contig=<ID=GL000228.1,length=129120>
+##contig=<ID=GL000214.1,length=137718>
+##contig=<ID=GL000221.1,length=155397>
+##contig=<ID=GL000209.1,length=159169>
+##contig=<ID=GL000218.1,length=161147>
+##contig=<ID=GL000220.1,length=161802>
+##contig=<ID=GL000213.1,length=164239>
+##contig=<ID=GL000211.1,length=166566>
+##contig=<ID=GL000199.1,length=169874>
+##contig=<ID=GL000217.1,length=172149>
+##contig=<ID=GL000216.1,length=172294>
+##contig=<ID=GL000215.1,length=172545>
+##contig=<ID=GL000205.1,length=174588>
+##contig=<ID=GL000219.1,length=179198>
+##contig=<ID=GL000224.1,length=179693>
+##contig=<ID=GL000223.1,length=180455>
+##contig=<ID=GL000195.1,length=182896>
+##contig=<ID=GL000212.1,length=186858>
+##contig=<ID=GL000222.1,length=186861>
+##contig=<ID=GL000200.1,length=187035>
+##contig=<ID=GL000193.1,length=189789>
+##contig=<ID=GL000194.1,length=191469>
+##contig=<ID=GL000225.1,length=211173>
+##contig=<ID=GL000192.1,length=547496>
+##FILTER=<ID=FBQualDepth,Description="Set if true: (AF[0] <= 0.5 && (DP < 4 || (DP < 13 && %QUAL < 10))) || (AF[0] > 0.5 && (DP < 4 && %QUAL < 50))">
+##FILTER=<ID=GATKCutoffIndel,Description="Set if true: TYPE=indel && (ReadPosRankSum < -20.0 || QD < 2.0 || FS > 200.0 || SOR > 10.0 || (QD < 10.0 && AD[0:1] / (AD[0:1] + AD[0:0]) < 0.25 && ReadPosRankSum < 0.0))">
+##FILTER=<ID=GATKCutoffSNP,Description="Set if true: TYPE=snp && (MQRankSum < -12.5 || ReadPosRankSum < -8.0 || QD < 2.0 || FS > 60.0 || (QD < 10.0 && AD[0:1] / (AD[0:1] + AD[0:0]) < 0.25 && ReadPosRankSum < 0.0) || MQ < 30.0)">
+##FILTER=<ID=GOF,Description="Variant fails goodness-of-fit test.">
+##FILTER=<ID=HapScore,Description="Too many haplotypes are supported by the data in this region.">
+##FILTER=<ID=LowQual,Description="Low quality">
+##FILTER=<ID=MQ,Description="Root-mean-square mapping quality across calling region is low.">
+##FILTER=<ID=PlatQualDepth,Description="Set if true: (FR[0] <= 0.5 && TC < 4 && %QUAL < 20) || (TC < 13 && %QUAL < 10) || (FR[0] > 0.5 && TC < 4 && %QUAL < 50)">
+##FILTER=<ID=Q20,Description="Variant quality is below 20.">
+##FILTER=<ID=QD,Description="Variants fail quality/depth filter.">
+##FILTER=<ID=QualDepth,Description="Variant quality/Read depth ratio is low.">
+##FILTER=<ID=REFCALL,Description="This line represents a homozygous reference call">
+##FILTER=<ID=SC,Description="Variants fail sequence-context filter. Surrounding sequence is low-complexity">
+##FILTER=<ID=alleleBias,Description="Variant frequency is lower than expected for het">
+##FILTER=<ID=badReads,Description="Variant supported only by reads with low quality bases close to variant position, and not present on both strands.">
+##FILTER=<ID=hp10,Description="Flanking sequence contains homopolymer of length 10 or greater">
+##FILTER=<ID=stQualDepth,Description="Set if true: ((AC[0] / AN) <= 0.5 && DP < 4 && %QUAL < 20) || (DP < 13 && %QUAL < 10) || ((AC[0] / AN) > 0.5 && DP < 4 && %QUAL < 50)">
+##FILTER=<ID=strandBias,Description="Variant fails strand-bias filter">
+##INFO=<ID=AB,Number=1,Type=Float,Description="Allele balance at heterozygous sites: a number between 0 and 1 representing the ratio of reads showing the reference allele to all reads, considering only reads from individuals called as heterozygous">
+##INFO=<ID=ABP,Number=1,Type=Float,Description="Allele balance probability at heterozygous sites: Phred-scaled upper-bounds estimate of the probability of observing the deviation between ABR and ABA given E(ABR/ABA) ~ 0.5, derived using Hoeffding's inequality">
+##INFO=<ID=AC,Number=1,Type=Integer,Description="Allele count in genotypes, for each ALT allele, in the same order as listed">
+##INFO=<ID=AF,Number=1,Type=Float,Description="Allele Frequency, for each ALT allele, in the same order as listed">
+##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">
+##INFO=<ID=AO,Number=1,Type=Integer,Description="Count of full observations of this alternate haplotype.">
+##INFO=<ID=AltaiNeandertal,Number=1,Type=String,Description="calculated by first of overlapping values in column 18 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=Ancestral_allele,Number=1,Type=String,Description="calculated by first of overlapping values in column 17 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=BQB,Number=1,Type=Float,Description="Mann-Whitney U test of Base Quality Bias (bigger is better)">
+##INFO=<ID=BRF,Number=1,Type=Float,Description="Fraction of reads around this variant that failed filters">
+##INFO=<ID=BaseQRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt Vs. Ref base qualities">
+##INFO=<ID=CADD_phred,Number=1,Type=String,Description="calculated by first of overlapping values in column 79 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=CADD_raw,Number=1,Type=String,Description="calculated by first of overlapping values in column 77 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=CADD_raw_rankscore,Number=1,Type=String,Description="calculated by first of overlapping values in column 78 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=CALLERS,Number=.,Type=String,Description="Individual caller support">
+##INFO=<ID=CIGAR,Number=1,Type=String,Description="The extended CIGAR representation of each alternate allele, with the exception that '=' is replaced by 'M' to ease VCF parsing.  Note that INDEL alleles do not have the first matched base (which is provided by default, per the spec) referred to by the CIGAR.">
+##INFO=<ID=CSQ,Number=.,Type=String,Description="Consequence annotations from Ensembl VEP. Format: Allele|Consequence|IMPACT|SYMBOL|Gene|Feature_type|Feature|BIOTYPE|EXON|INTRON|HGVSc|HGVSp|cDNA_position|CDS_position|Protein_position|Amino_acids|Codons|Existing_variation|ALLELE_NUM|DISTANCE|STRAND|FLAGS|VARIANT_CLASS|SYMBOL_SOURCE|HGNC_ID|CANONICAL|TSL|APPRIS|CCDS|ENSP|SWISSPROT|TREMBL|UNIPARC|REFSEQ_MATCH|SOURCE|GIVEN_REF|USED_REF|BAM_EDIT|GENE_PHENO|SIFT|PolyPhen|DOMAINS|HGVS_OFFSET|AF|AFR_AF|AMR_AF|EAS_AF|EUR_AF|SAS_AF|AA_AF|EA_AF|gnomAD_AF|gnomAD_AFR_AF|gnomAD_AMR_AF|gnomAD_ASJ_AF|gnomAD_EAS_AF|gnomAD_FIN_AF|gnomAD_NFE_AF|gnomAD_OTH_AF|gnomAD_SAS_AF|MAX_AF|MAX_AF_POPS|CLIN_SIG|SOMATIC|PHENO|PUBMED|MOTIF_NAME|MOTIF_POS|HIGH_INF_POS|MOTIF_SCORE_CHANGE|LoF|LoF_filter|LoF_flags|LoF_info|MaxEntScan_alt|MaxEntScan_diff|MaxEntScan_ref|SpliceRegion">
+##INFO=<ID=ClippingRankSum,Number=1,Type=Float,Description="Z-score From Wilcoxon rank sum test of Alt vs. Ref number of hard clipped bases">
+##INFO=<ID=DANN_rankscore,Number=1,Type=String,Description="calculated by first of overlapping values in column 81 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=DANN_score,Number=1,Type=String,Description="calculated by first of overlapping values in column 80 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=DECOMPOSED,Number=0,Type=Flag,Description="The allele was parsed using vcfallelicprimitives.">
+##INFO=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth; some reads may have been filtered">
+##INFO=<ID=DP4,Number=4,Type=Integer,Description="Number of high-quality ref-forward , ref-reverse, alt-forward and alt-reverse bases">
+##INFO=<ID=DPB,Number=1,Type=Float,Description="Total read depth per bp at the locus; bases in reads overlapping / bases in haplotype">
+##INFO=<ID=DPRA,Number=1,Type=Float,Description="Alternate allele depth ratio.  Ratio between depth in samples with each called alternate allele and those without.">
+##INFO=<ID=DS,Number=0,Type=Flag,Description="Were any of the samples downsampled?">
+##INFO=<ID=Denisova,Number=1,Type=String,Description="calculated by first of overlapping values in column 19 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=END,Number=1,Type=Integer,Description="Stop position of the interval">
+##INFO=<ID=EPP,Number=1,Type=Float,Description="End Placement Probability: Phred-scaled upper-bounds estimate of the probability of observing the deviation between EL and ER given E(EL/ER) ~ 0.5, derived using Hoeffding's inequality">
+##INFO=<ID=EPPR,Number=1,Type=Float,Description="End Placement Probability for reference observations: Phred-scaled upper-bounds estimate of the probability of observing the deviation between EL and ER given E(EL/ER) ~ 0.5, derived using Hoeffding's inequality">
+##INFO=<ID=Eigen-PC-phred,Number=1,Type=String,Description="calculated by first of overlapping values in column 90 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=Eigen-PC-raw,Number=1,Type=String,Description="calculated by first of overlapping values in column 89 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=Eigen-PC-raw_rankscore,Number=1,Type=String,Description="calculated by first of overlapping values in column 91 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=Eigen-phred,Number=1,Type=String,Description="calculated by first of overlapping values in column 88 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=Eigen-raw,Number=1,Type=String,Description="calculated by first of overlapping values in column 87 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=Eigen_coding_or_noncoding,Number=1,Type=String,Description="calculated by first of overlapping values in column 86 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=Ensembl_geneid,Number=1,Type=String,Description="calculated by first of overlapping values in column 20 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=Ensembl_proteinid,Number=1,Type=String,Description="calculated by first of overlapping values in column 22 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=Ensembl_transcriptid,Number=1,Type=String,Description="calculated by first of overlapping values in column 21 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=ExcessHet,Number=1,Type=Float,Description="Phred-scaled p-value for exact test of excess heterozygosity">
+##INFO=<ID=FATHMM_converted_rankscore,Number=1,Type=String,Description="calculated by first of overlapping values in column 51 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=FATHMM_pred,Number=1,Type=String,Description="calculated by first of overlapping values in column 52 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=FATHMM_score,Number=1,Type=String,Description="calculated by first of overlapping values in column 50 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=FR,Number=.,Type=Float,Description="Estimated population frequency of variant">
+##INFO=<ID=FS,Number=.,Type=Float,Description="Phred-scaled p-value using Fisher's exact test to detect strand bias">
+##INFO=<ID=GC,Number=1,Type=Float,Description="GC content around the variant (see docs for window size details)">
+##INFO=<ID=GERP++_NR,Number=1,Type=String,Description="calculated by first of overlapping values in column 106 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=GERP++_RS,Number=1,Type=String,Description="calculated by first of overlapping values in column 107 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=GERP++_RS_rankscore,Number=1,Type=String,Description="calculated by first of overlapping values in column 108 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=GM12878_confidence_value,Number=1,Type=String,Description="calculated by first of overlapping values in column 99 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=GM12878_fitCons_rankscore,Number=1,Type=String,Description="calculated by first of overlapping values in column 98 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=GM12878_fitCons_score,Number=1,Type=String,Description="calculated by first of overlapping values in column 97 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=GTEx_V6_gene,Number=1,Type=String,Description="calculated by first of overlapping values in column 193 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=GTEx_V6_tissue,Number=1,Type=String,Description="calculated by first of overlapping values in column 194 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=GTI,Number=1,Type=Integer,Description="Number of genotyping iterations required to reach convergence or bailout.">
+##INFO=<ID=GenoCanyon_score,Number=1,Type=String,Description="calculated by first of overlapping values in column 92 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=GenoCanyon_score_rankscore,Number=1,Type=String,Description="calculated by first of overlapping values in column 93 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=H1-hESC_confidence_value,Number=1,Type=String,Description="calculated by first of overlapping values in column 102 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=H1-hESC_fitCons_rankscore,Number=1,Type=String,Description="calculated by first of overlapping values in column 101 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=H1-hESC_fitCons_score,Number=1,Type=String,Description="calculated by first of overlapping values in column 100 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=HOB,Number=1,Type=Float,Description="Bias in the number of HOMs number (smaller is better)">
+##INFO=<ID=HP,Number=1,Type=Integer,Description="Homopolymer run length around variant locus">
+##INFO=<ID=HRun,Number=1,Type=Integer,Description="Largest Contiguous Homopolymer Run of Variant Allele In Either Direction">
+##INFO=<ID=HUVEC_confidence_value,Number=1,Type=String,Description="calculated by first of overlapping values in column 105 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=HUVEC_fitCons_rankscore,Number=1,Type=String,Description="calculated by first of overlapping values in column 104 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=HUVEC_fitCons_score,Number=1,Type=String,Description="calculated by first of overlapping values in column 103 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=HapScore,Number=.,Type=Integer,Description="Haplotype score measuring the number of haplotypes the variant is segregating into in a window">
+##INFO=<ID=HaplotypeScore,Number=1,Type=Float,Description="Consistency of the site with at most two segregating haplotypes">
+##INFO=<ID=ICB,Number=1,Type=Float,Description="Inbreeding Coefficient Binomial test (bigger is better)">
+##INFO=<ID=IDV,Number=1,Type=Integer,Description="Maximum number of reads supporting an indel">
+##INFO=<ID=IMF,Number=1,Type=Float,Description="Maximum fraction of reads supporting an indel">
+##INFO=<ID=INDEL,Number=0,Type=Flag,Description="Indicates that the variant is an INDEL.">
+##INFO=<ID=InbreedingCoeff,Number=1,Type=Float,Description="Inbreeding coefficient as estimated from the genotype likelihoods per-sample when compared against the Hardy-Weinberg expectation">
+##INFO=<ID=Interpro_domain,Number=1,Type=String,Description="calculated by first of overlapping values in column 192 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=LEN,Number=1,Type=Integer,Description="allele length">
+##INFO=<ID=LRT_Omega,Number=1,Type=String,Description="calculated by first of overlapping values in column 39 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=LRT_converted_rankscore,Number=1,Type=String,Description="calculated by first of overlapping values in column 37 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=LRT_pred,Number=1,Type=String,Description="calculated by first of overlapping values in column 38 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=LRT_score,Number=1,Type=String,Description="calculated by first of overlapping values in column 36 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=M-CAP_pred,Number=1,Type=String,Description="calculated by first of overlapping values in column 69 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=M-CAP_rankscore,Number=1,Type=String,Description="calculated by first of overlapping values in column 68 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=M-CAP_score,Number=1,Type=String,Description="calculated by first of overlapping values in column 67 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=MEANALT,Number=1,Type=Float,Description="Mean number of unique non-reference allele observations per sample with the corresponding alternate alleles.">
+##INFO=<ID=MGOF,Number=.,Type=Integer,Description="Worst goodness-of-fit value reported across all samples">
+##INFO=<ID=MIN_DP,Number=1,Type=Integer,Description="Minimum depth in gVCF output block.">
+##INFO=<ID=MLEAC,Number=1,Type=Integer,Description="Maximum likelihood expectation (MLE) for the allele counts (not necessarily the same as the AC), for each ALT allele, in the same order as listed">
+##INFO=<ID=MLEAF,Number=1,Type=Float,Description="Maximum likelihood expectation (MLE) for the allele frequency (not necessarily the same as the AF), for each ALT allele, in the same order as listed">
+##INFO=<ID=MMLQ,Number=1,Type=Float,Description="Median minimum base quality for bases around variant">
+##INFO=<ID=MQ,Number=1,Type=Float,Description="RMS Mapping Quality">
+##INFO=<ID=MQ0,Number=1,Type=Integer,Description="Total Mapping Quality Zero Reads">
+##INFO=<ID=MQ0F,Number=1,Type=Float,Description="Fraction of MQ0 reads (smaller is better)">
+##INFO=<ID=MQB,Number=1,Type=Float,Description="Mann-Whitney U test of Mapping Quality Bias (bigger is better)">
+##INFO=<ID=MQM,Number=1,Type=Float,Description="Mean mapping quality of observed alternate alleles">
+##INFO=<ID=MQMR,Number=1,Type=Float,Description="Mean mapping quality of observed reference alleles">
+##INFO=<ID=MQRankSum,Number=1,Type=Float,Description="Z-score From Wilcoxon rank sum test of Alt vs. Ref read mapping qualities">
+##INFO=<ID=MQSB,Number=1,Type=Float,Description="Mann-Whitney U test of Mapping Quality vs Strand Bias (bigger is better)">
+##INFO=<ID=MetaLR_pred,Number=1,Type=String,Description="calculated by first of overlapping values in column 65 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=MetaLR_rankscore,Number=1,Type=String,Description="calculated by first of overlapping values in column 64 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=MetaLR_score,Number=1,Type=String,Description="calculated by first of overlapping values in column 63 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=MetaSVM_pred,Number=1,Type=String,Description="calculated by first of overlapping values in column 62 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=MetaSVM_rankscore,Number=1,Type=String,Description="calculated by first of overlapping values in column 61 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=MetaSVM_score,Number=1,Type=String,Description="calculated by first of overlapping values in column 60 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=MutPred_AAchange,Number=1,Type=String,Description="calculated by first of overlapping values in column 75 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=MutPred_Top5features,Number=1,Type=String,Description="calculated by first of overlapping values in column 76 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=MutPred_protID,Number=1,Type=String,Description="calculated by first of overlapping values in column 74 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=MutPred_rankscore,Number=1,Type=String,Description="calculated by first of overlapping values in column 73 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=MutPred_score,Number=1,Type=String,Description="calculated by first of overlapping values in column 72 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=MutationAssessor_UniprotID,Number=1,Type=String,Description="calculated by first of overlapping values in column 45 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=MutationAssessor_pred,Number=1,Type=String,Description="calculated by first of overlapping values in column 49 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=MutationAssessor_rankscore,Number=1,Type=String,Description="calculated by first of overlapping values in column 48 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=MutationAssessor_score,Number=1,Type=String,Description="calculated by first of overlapping values in column 47 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=MutationAssessor_variant,Number=1,Type=String,Description="calculated by first of overlapping values in column 46 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=MutationTaster_AAE,Number=1,Type=String,Description="calculated by first of overlapping values in column 44 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=MutationTaster_converted_rankscore,Number=1,Type=String,Description="calculated by first of overlapping values in column 41 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=MutationTaster_model,Number=1,Type=String,Description="calculated by first of overlapping values in column 43 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=MutationTaster_pred,Number=1,Type=String,Description="calculated by first of overlapping values in column 42 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=MutationTaster_score,Number=1,Type=String,Description="calculated by first of overlapping values in column 40 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=NF,Number=.,Type=Integer,Description="Total number of forward reads containing this variant">
+##INFO=<ID=NR,Number=.,Type=Integer,Description="Total number of reverse reads containing this variant">
+##INFO=<ID=NS,Number=1,Type=Integer,Description="Number of samples with data">
+##INFO=<ID=NUMALT,Number=1,Type=Integer,Description="Number of unique non-reference alleles in called genotypes at this position.">
+##INFO=<ID=ODDS,Number=1,Type=Float,Description="The log odds ratio of the best genotype combination to the second-best.">
+##INFO=<ID=OLD_MULTIALLELIC,Number=1,Type=String,Description="Original chr:pos:ref:alt encoding">
+##INFO=<ID=OLD_VARIANT,Number=.,Type=String,Description="Original chr:pos:ref:alt encoding">
+##INFO=<ID=PAIRED,Number=1,Type=Float,Description="Proportion of observed alternate alleles which are supported by properly paired read fragments">
+##INFO=<ID=PAIREDR,Number=1,Type=Float,Description="Proportion of observed reference alleles which are supported by properly paired read fragments">
+##INFO=<ID=PAO,Number=1,Type=Float,Description="Alternate allele observations, with partial observations recorded fractionally">
+##INFO=<ID=PP,Number=.,Type=Float,Description="Posterior probability (phred scaled) that this variant segregates">
+##INFO=<ID=PQA,Number=1,Type=Float,Description="Alternate allele quality sum in phred for partial observations">
+##INFO=<ID=PQR,Number=1,Type=Float,Description="Reference allele quality sum in phred for partial observations">
+##INFO=<ID=PRO,Number=1,Type=Float,Description="Reference allele observation count, with partial observations recorded fractionally">
+##INFO=<ID=PROVEAN_converted_rankscore,Number=1,Type=String,Description="calculated by first of overlapping values in column 54 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=PROVEAN_pred,Number=1,Type=String,Description="calculated by first of overlapping values in column 55 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=PROVEAN_score,Number=1,Type=String,Description="calculated by first of overlapping values in column 53 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=QA,Number=1,Type=Integer,Description="Alternate allele quality sum in phred">
+##INFO=<ID=QD,Number=1,Type=Float,Description="Variant Confidence/Quality by Depth">
+##INFO=<ID=QR,Number=1,Type=Integer,Description="Reference allele quality sum in phred">
+##INFO=<ID=REVEL_rankscore,Number=1,Type=String,Description="calculated by first of overlapping values in column 71 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=REVEL_score,Number=1,Type=String,Description="calculated by first of overlapping values in column 70 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=RO,Number=1,Type=Integer,Description="Count of full observations of the reference haplotype.">
+##INFO=<ID=RPB,Number=1,Type=Float,Description="Mann-Whitney U test of Read Position Bias (bigger is better)">
+##INFO=<ID=RPL,Number=1,Type=Float,Description="Reads Placed Left: number of reads supporting the alternate balanced to the left (5') of the alternate allele">
+##INFO=<ID=RPP,Number=1,Type=Float,Description="Read Placement Probability: Phred-scaled upper-bounds estimate of the probability of observing the deviation between RPL and RPR given E(RPL/RPR) ~ 0.5, derived using Hoeffding's inequality">
+##INFO=<ID=RPPR,Number=1,Type=Float,Description="Read Placement Probability for reference observations: Phred-scaled upper-bounds estimate of the probability of observing the deviation between RPL and RPR given E(RPL/RPR) ~ 0.5, derived using Hoeffding's inequality">
+##INFO=<ID=RPR,Number=1,Type=Float,Description="Reads Placed Right: number of reads supporting the alternate balanced to the right (3') of the alternate allele">
+##INFO=<ID=RUN,Number=1,Type=Integer,Description="Run length: the number of consecutive repeats of the alternate allele in the reference genome">
+##INFO=<ID=ReadPosRankSum,Number=.,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt vs. Ref read position bias">
+##INFO=<ID=Reliability_index,Number=1,Type=String,Description="calculated by first of overlapping values in column 66 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=SAF,Number=1,Type=Integer,Description="Number of alternate observations on the forward strand">
+##INFO=<ID=SAP,Number=1,Type=Float,Description="Strand balance probability for the alternate allele: Phred-scaled upper-bounds estimate of the probability of observing the deviation between SAF and SAR given E(SAF/SAR) ~ 0.5, derived using Hoeffding's inequality">
+##INFO=<ID=SAR,Number=1,Type=Integer,Description="Number of alternate observations on the reverse strand">
+##INFO=<ID=SC,Number=1,Type=String,Description="Genomic sequence 10 bases either side of variant position">
+##INFO=<ID=SGB,Number=1,Type=Float,Description="Segregation based metric.">
+##INFO=<ID=SOR,Number=1,Type=Float,Description="Symmetric Odds Ratio of 2x2 contingency table to detect strand bias">
+##INFO=<ID=SRF,Number=1,Type=Integer,Description="Number of reference observations on the forward strand">
+##INFO=<ID=SRP,Number=1,Type=Float,Description="Strand balance probability for the reference allele: Phred-scaled upper-bounds estimate of the probability of observing the deviation between SRF and SRR given E(SRF/SRR) ~ 0.5, derived using Hoeffding's inequality">
+##INFO=<ID=SRR,Number=1,Type=Integer,Description="Number of reference observations on the reverse strand">
+##INFO=<ID=START,Number=.,Type=Integer,Description="Start position of reference call block">
+##INFO=<ID=SbPval,Number=.,Type=Float,Description="Binomial P-value for strand bias test">
+##INFO=<ID=SiPhy_29way_logOdds,Number=1,Type=String,Description="calculated by first of overlapping values in column 118 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=SiPhy_29way_logOdds_rankscore,Number=1,Type=String,Description="calculated by first of overlapping values in column 119 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=SiPhy_29way_pi,Number=1,Type=String,Description="calculated by first of overlapping values in column 117 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=Size,Number=.,Type=Integer,Description="Size of reference call block">
+##INFO=<ID=Source,Number=.,Type=String,Description="Was this variant suggested by Playtypus, Assembler, or from a VCF?">
+##INFO=<ID=TC,Number=1,Type=Integer,Description="Total coverage at this locus">
+##INFO=<ID=TCF,Number=1,Type=Integer,Description="Total forward strand coverage at this locus">
+##INFO=<ID=TCR,Number=1,Type=Integer,Description="Total reverse strand coverage at this locus">
+##INFO=<ID=TR,Number=.,Type=Integer,Description="Total number of reads containing this variant">
+##INFO=<ID=TYPE,Number=1,Type=String,Description="The type of allele, either snp, mnp, ins, del, or complex.">
+##INFO=<ID=Transcript_id_VEST3,Number=1,Type=String,Description="calculated by first of overlapping values in column 56 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=Transcript_var_VEST3,Number=1,Type=String,Description="calculated by first of overlapping values in column 57 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=VDB,Number=1,Type=Float,Description="Variant Distance Bias for filtering splice-site artefacts in RNA-seq data (bigger is better)">
+##INFO=<ID=VEST3_rankscore,Number=1,Type=String,Description="calculated by first of overlapping values in column 59 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=VEST3_score,Number=1,Type=String,Description="calculated by first of overlapping values in column 58 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=WE,Number=1,Type=Integer,Description="End position of calling window">
+##INFO=<ID=WS,Number=1,Type=Integer,Description="Starting position of calling window">
+##INFO=<ID=ac_adj_exac_afr,Number=1,Type=Float,Description="calculated by max of overlapping values in field AC_AFR from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/ExAC.r0.3.sites.vep.tidy.vcf.gz">
+##INFO=<ID=ac_adj_exac_amr,Number=1,Type=Float,Description="calculated by max of overlapping values in field AC_AMR from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/ExAC.r0.3.sites.vep.tidy.vcf.gz">
+##INFO=<ID=ac_adj_exac_eas,Number=1,Type=Float,Description="calculated by max of overlapping values in field AC_EAS from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/ExAC.r0.3.sites.vep.tidy.vcf.gz">
+##INFO=<ID=ac_adj_exac_fin,Number=1,Type=Float,Description="calculated by max of overlapping values in field AC_FIN from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/ExAC.r0.3.sites.vep.tidy.vcf.gz">
+##INFO=<ID=ac_adj_exac_nfe,Number=1,Type=Float,Description="calculated by max of overlapping values in field AC_NFE from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/ExAC.r0.3.sites.vep.tidy.vcf.gz">
+##INFO=<ID=ac_adj_exac_oth,Number=1,Type=Float,Description="calculated by max of overlapping values in field AC_OTH from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/ExAC.r0.3.sites.vep.tidy.vcf.gz">
+##INFO=<ID=ac_adj_exac_sas,Number=1,Type=Float,Description="calculated by max of overlapping values in field AC_SAS from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/ExAC.r0.3.sites.vep.tidy.vcf.gz">
+##INFO=<ID=ac_exac_all,Number=1,Type=Float,Description="calculated by max of overlapping values in field AC_Adj from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/ExAC.r0.3.sites.vep.tidy.vcf.gz">
+##INFO=<ID=af_1kg,Number=1,Type=Float,Description="calculated field: af_1kg">
+##INFO=<ID=af_1kg_afr,Number=1,Type=Float,Description="calculated by max of overlapping values in field AFR_AF from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/ALL.wgs.phase3_shapeit2_mvncall_integrated_v5a.20130502.sites.tidy.vcf.gz">
+##INFO=<ID=af_1kg_all,Number=1,Type=Float,Description="calculated by max of overlapping values in field AF from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/ALL.wgs.phase3_shapeit2_mvncall_integrated_v5a.20130502.sites.tidy.vcf.gz">
+##INFO=<ID=af_1kg_amr,Number=1,Type=Float,Description="calculated by max of overlapping values in field AMR_AF from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/ALL.wgs.phase3_shapeit2_mvncall_integrated_v5a.20130502.sites.tidy.vcf.gz">
+##INFO=<ID=af_1kg_eas,Number=1,Type=Float,Description="calculated by max of overlapping values in field EAS_AF from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/ALL.wgs.phase3_shapeit2_mvncall_integrated_v5a.20130502.sites.tidy.vcf.gz">
+##INFO=<ID=af_1kg_eur,Number=1,Type=Float,Description="calculated by max of overlapping values in field EUR_AF from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/ALL.wgs.phase3_shapeit2_mvncall_integrated_v5a.20130502.sites.tidy.vcf.gz">
+##INFO=<ID=af_1kg_sas,Number=1,Type=Float,Description="calculated by max of overlapping values in field SAS_AF from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/ALL.wgs.phase3_shapeit2_mvncall_integrated_v5a.20130502.sites.tidy.vcf.gz">
+##INFO=<ID=af_adj_exac_afr,Number=1,Type=Float,Description="calculated field: af_adj_exac_afr">
+##INFO=<ID=af_adj_exac_amr,Number=1,Type=Float,Description="calculated field: af_adj_exac_amr">
+##INFO=<ID=af_adj_exac_eas,Number=1,Type=Float,Description="calculated field: af_adj_exac_eas">
+##INFO=<ID=af_adj_exac_fin,Number=1,Type=Float,Description="calculated field: af_adj_exac_fin">
+##INFO=<ID=af_adj_exac_nfe,Number=1,Type=Float,Description="calculated field: af_adj_exac_nfe">
+##INFO=<ID=af_adj_exac_oth,Number=1,Type=Float,Description="calculated field: af_adj_exac_oth">
+##INFO=<ID=af_adj_exac_sas,Number=1,Type=Float,Description="calculated field: af_adj_exac_sas">
+##INFO=<ID=af_esp_aa,Number=1,Type=Float,Description="calculated by lua:ratio(vals) of overlapping values in field AA_AC from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/ESP6500SI.all.snps_indels.tidy.v2.vcf.gz">
+##INFO=<ID=af_esp_all,Number=1,Type=Float,Description="calculated by lua:ratio(vals) of overlapping values in field TAC from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/ESP6500SI.all.snps_indels.tidy.v2.vcf.gz">
+##INFO=<ID=af_esp_ea,Number=1,Type=Float,Description="calculated by lua:ratio(vals) of overlapping values in field EA_AC from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/ESP6500SI.all.snps_indels.tidy.v2.vcf.gz">
+##INFO=<ID=af_exac_all,Number=1,Type=Float,Description="calculated field: af_exac_all">
+##INFO=<ID=an_adj_exac_afr,Number=1,Type=Integer,Description="African/African American Chromosome Count (from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/ExAC.r0.3.sites.vep.tidy.vcf.gz)">
+##INFO=<ID=an_adj_exac_amr,Number=1,Type=Integer,Description="American Chromosome Count (from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/ExAC.r0.3.sites.vep.tidy.vcf.gz)">
+##INFO=<ID=an_adj_exac_eas,Number=1,Type=Integer,Description="East Asian Chromosome Count (from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/ExAC.r0.3.sites.vep.tidy.vcf.gz)">
+##INFO=<ID=an_adj_exac_fin,Number=1,Type=Integer,Description="Finnish Chromosome Count (from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/ExAC.r0.3.sites.vep.tidy.vcf.gz)">
+##INFO=<ID=an_adj_exac_nfe,Number=1,Type=Integer,Description="Non-Finnish European Chromosome Count (from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/ExAC.r0.3.sites.vep.tidy.vcf.gz)">
+##INFO=<ID=an_adj_exac_oth,Number=1,Type=Integer,Description="Other Chromosome Count (from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/ExAC.r0.3.sites.vep.tidy.vcf.gz)">
+##INFO=<ID=an_adj_exac_sas,Number=1,Type=Integer,Description="South Asian Chromosome Count (from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/ExAC.r0.3.sites.vep.tidy.vcf.gz)">
+##INFO=<ID=an_exac_all,Number=1,Type=Integer,Description="Adjusted Chromosome Count (from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/ExAC.r0.3.sites.vep.tidy.vcf.gz)">
+##INFO=<ID=cds_strand,Number=1,Type=String,Description="calculated by first of overlapping values in column 13 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=clinvar_disease_name,Number=.,Type=String,Description="Variant disease name (from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/clinvar_20170130.tidy.vcf.gz)">
+##INFO=<ID=clinvar_pathogenic,Number=.,Type=String,Description="Variant Clinical Significance, 0 - Uncertain significance, 1 - not provided, 2 - Benign, 3 - Likely benign, 4 - Likely pathogenic, 5 - Pathogenic, 6 - drug response, 7 - histocompatibility, 255 - other (from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/clinvar_20170130.tidy.vcf.gz)">
+##INFO=<ID=clinvar_sig,Number=.,Type=String,Description="calculated field: clinvar_sig">
+##INFO=<ID=codon_degeneracy,Number=1,Type=String,Description="calculated by first of overlapping values in column 16 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=codonpos,Number=1,Type=String,Description="calculated by first of overlapping values in column 15 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=common_pathogenic,Number=0,Type=Flag,Description="calculated field: common_pathogenic">
+##INFO=<ID=cosmic_ids,Number=.,Type=String,Description="calculated by uniq of overlapping values in field ID from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/cosmic-v68-GRCh37.tidy.vcf.gz">
+##INFO=<ID=cpg_island,Number=0,Type=Flag,Description="calculated by flag of overlapping values in column 2 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/hg19.CpG.bed.gz">
+##INFO=<ID=cse-hiseq,Number=0,Type=Flag,Description="calculated by flag of overlapping values in column 2 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/cse-hiseq-8_4-2013-02-20.bed.gz">
+##INFO=<ID=dgv,Number=.,Type=String,Description="calculated by uniq of overlapping values in column 4 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/hg19.dgv.bed.gz">
+##INFO=<ID=encode_consensus_gm12878,Number=.,Type=String,Description="calculated by concat of overlapping values in column 4 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/encode.6celltypes.consensus.bedg.gz">
+##INFO=<ID=encode_consensus_h1hesc,Number=.,Type=String,Description="calculated by concat of overlapping values in column 5 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/encode.6celltypes.consensus.bedg.gz">
+##INFO=<ID=encode_consensus_helas3,Number=.,Type=String,Description="calculated by concat of overlapping values in column 6 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/encode.6celltypes.consensus.bedg.gz">
+##INFO=<ID=encode_consensus_hepg2,Number=.,Type=String,Description="calculated by concat of overlapping values in column 7 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/encode.6celltypes.consensus.bedg.gz">
+##INFO=<ID=encode_consensus_huvec,Number=.,Type=String,Description="calculated by concat of overlapping values in column 8 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/encode.6celltypes.consensus.bedg.gz">
+##INFO=<ID=encode_consensus_k562,Number=.,Type=String,Description="calculated by concat of overlapping values in column 9 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/encode.6celltypes.consensus.bedg.gz">
+##INFO=<ID=evs_af,Number=R,Type=String,Description="calculated by lua:ratio(vals) of overlapping values in field TAC from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/ESP6500SI.all.snps_indels.tidy.v2.vcf.gz">
+##INFO=<ID=evs_af_aa,Number=R,Type=String,Description="calculated by lua:ratio(vals) of overlapping values in field AA_AC from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/ESP6500SI.all.snps_indels.tidy.v2.vcf.gz">
+##INFO=<ID=evs_af_ea,Number=R,Type=String,Description="calculated by lua:ratio(vals) of overlapping values in field EA_AC from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/ESP6500SI.all.snps_indels.tidy.v2.vcf.gz">
+##INFO=<ID=fathmm-MKL_coding_group,Number=1,Type=String,Description="calculated by first of overlapping values in column 85 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=fathmm-MKL_coding_pred,Number=1,Type=String,Description="calculated by first of overlapping values in column 84 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=fathmm-MKL_coding_rankscore,Number=1,Type=String,Description="calculated by first of overlapping values in column 83 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=fathmm-MKL_coding_score,Number=1,Type=String,Description="calculated by first of overlapping values in column 82 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=fitcons,Number=1,Type=Float,Description="calculated by mean of overlapping values in column 4 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/hg19_fitcons_fc-i6-0_V1-01.bed.gz">
+##INFO=<ID=gerp_elements,Number=1,Type=Float,Description="calculated by mean of overlapping values in column 4 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/hg19.gerp.elements.bed.gz">
+##INFO=<ID=gnomAD_AF,Number=1,Type=Float,Description="Allele Frequency among genotypes, for each ALT allele, in the same order as listed (from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/gnomad_genome.vcf.gz)">
+##INFO=<ID=gnomAD_AFR_AF,Number=1,Type=Float,Description="Allele Frequency among African/African American genotypes, for each ALT allele, in the same order as listed (from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/gnomad_genome.vcf.gz)">
+##INFO=<ID=gnomAD_AMR_AF,Number=1,Type=Float,Description="Allele Frequency among Admixed American genotypes, for each ALT allele, in the same order as listed (from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/gnomad_genome.vcf.gz)">
+##INFO=<ID=gnomAD_ASJ_AF,Number=1,Type=Float,Description="Allele Frequency among Ashkenazi Jewish genotypes, for each ALT allele, in the same order as listed (from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/gnomad_genome.vcf.gz)">
+##INFO=<ID=gnomAD_EAS_AF,Number=1,Type=Float,Description="Allele Frequency among East Asian genotypes, for each ALT allele, in the same order as listed (from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/gnomad_genome.vcf.gz)">
+##INFO=<ID=gnomAD_FIN_AF,Number=1,Type=Float,Description="Allele Frequency among Finnish genotypes, for each ALT allele, in the same order as listed (from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/gnomad_genome.vcf.gz)">
+##INFO=<ID=gnomAD_NFE_AF,Number=1,Type=Float,Description="Allele Frequency among Non-Finnish European genotypes, for each ALT allele, in the same order as listed (from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/gnomad_genome.vcf.gz)">
+##INFO=<ID=gnomAD_OTH_AF,Number=1,Type=Float,Description="Allele Frequency among Other (population not assigned) genotypes, for each ALT allele, in the same order as listed (from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/gnomad_genome.vcf.gz)">
+##INFO=<ID=gnomAD_SAS_AF,Number=1,Type=String,Description="calculated by self of overlapping values in field AF_SAS from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/gnomad_genome.vcf.gz">
+##INFO=<ID=gnomad_ac_es,Number=1,Type=Integer,Description="Allele count in genotypes, for each ALT allele, in the same order as listed (from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/gnomad.exomes.r2.0.1.sites.no-VEP.nohist.tidy.vcf.gz)">
+##INFO=<ID=gnomad_ac_gs,Number=1,Type=Integer,Description="Allele count in genotypes, for each ALT allele, in the same order as listed (from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/gnomad_genome.vcf.gz)">
+##INFO=<ID=gnomad_af_afr,Number=1,Type=Float,Description="Allele Frequency among African/African American genotypes, for each ALT allele, in the same order as listed (from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/gnomad.exomes.r2.0.1.sites.no-VEP.nohist.tidy.vcf.gz)">
+##INFO=<ID=gnomad_af_amr,Number=1,Type=Float,Description="Allele Frequency among Admixed American genotypes, for each ALT allele, in the same order as listed (from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/gnomad.exomes.r2.0.1.sites.no-VEP.nohist.tidy.vcf.gz)">
+##INFO=<ID=gnomad_af_asj,Number=1,Type=Float,Description="Allele Frequency among Ashkenazi Jewish genotypes, for each ALT allele, in the same order as listed (from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/gnomad.exomes.r2.0.1.sites.no-VEP.nohist.tidy.vcf.gz)">
+##INFO=<ID=gnomad_af_eas,Number=1,Type=Float,Description="Allele Frequency among East Asian genotypes, for each ALT allele, in the same order as listed (from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/gnomad.exomes.r2.0.1.sites.no-VEP.nohist.tidy.vcf.gz)">
+##INFO=<ID=gnomad_af_es,Number=1,Type=Float,Description="calculated field: gnomad_af_es">
+##INFO=<ID=gnomad_af_fin,Number=1,Type=Float,Description="Allele Frequency among Finnish genotypes, for each ALT allele, in the same order as listed (from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/gnomad.exomes.r2.0.1.sites.no-VEP.nohist.tidy.vcf.gz)">
+##INFO=<ID=gnomad_af_gs,Number=1,Type=Float,Description="Maximum Allele Frequency across populations (excluding OTH) (from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/gnomad_genome.vcf.gz)">
+##INFO=<ID=gnomad_af_nfe,Number=1,Type=Float,Description="Allele Frequency among Non-Finnish European genotypes, for each ALT allele, in the same order as listed (from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/gnomad.exomes.r2.0.1.sites.no-VEP.nohist.tidy.vcf.gz)">
+##INFO=<ID=gnomad_af_oth,Number=1,Type=Float,Description="Allele Frequency among Other (population not assigned) genotypes, for each ALT allele, in the same order as listed (from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/gnomad.exomes.r2.0.1.sites.no-VEP.nohist.tidy.vcf.gz)">
+##INFO=<ID=gnomad_af_sas,Number=1,Type=Float,Description="Allele Frequency among South Asian genotypes, for each ALT allele, in the same order as listed (from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/gnomad.exomes.r2.0.1.sites.no-VEP.nohist.tidy.vcf.gz)">
+##INFO=<ID=gnomad_hom_es,Number=1,Type=Integer,Description="Count of homozygous individuals (from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/gnomad.exomes.r2.0.1.sites.no-VEP.nohist.tidy.vcf.gz)">
+##INFO=<ID=gnomad_hom_gs,Number=1,Type=Integer,Description="Count of homozygous individuals (from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/gnomad_genome.vcf.gz)">
+##INFO=<ID=gwas_pubmed_trait,Number=.,Type=String,Description="calculated by uniq of overlapping values in column 4 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/hg19.gwas.bed.gz">
+##INFO=<ID=hapmap1,Number=1,Type=Float,Description="calculated by mean of overlapping values in column 4 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/genetic_map_HapMapII_GRCh37.gz">
+##INFO=<ID=hapmap2,Number=1,Type=Float,Description="calculated by mean of overlapping values in column 5 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/genetic_map_HapMapII_GRCh37.gz">
+##INFO=<ID=integrated_confidence_value,Number=1,Type=String,Description="calculated by first of overlapping values in column 96 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=integrated_fitCons_rankscore,Number=1,Type=String,Description="calculated by first of overlapping values in column 95 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=integrated_fitCons_score,Number=1,Type=String,Description="calculated by first of overlapping values in column 94 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=max_aaf_all,Number=1,Type=Float,Description="calculated field: max_aaf_all">
+##INFO=<ID=max_af,Number=1,Type=Float,Description="calculated field: max_af">
+##INFO=<ID=num_exac_Het,Number=1,Type=Integer,Description="Adjusted Heterozygous Counts (from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/ExAC.r0.3.sites.vep.tidy.vcf.gz)">
+##INFO=<ID=num_exac_Hom,Number=1,Type=Integer,Description="Adjusted Homozygous Counts (from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/ExAC.r0.3.sites.vep.tidy.vcf.gz)">
+##INFO=<ID=phastCons100way_vertebrate,Number=1,Type=String,Description="calculated by first of overlapping values in column 113 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=phastCons100way_vertebrate_rankscore,Number=1,Type=String,Description="calculated by first of overlapping values in column 114 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=phastCons20way_mammalian,Number=1,Type=String,Description="calculated by first of overlapping values in column 115 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=phastCons20way_mammalian_rankscore,Number=1,Type=String,Description="calculated by first of overlapping values in column 116 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=phyloP100way_vertebrate,Number=1,Type=String,Description="calculated by first of overlapping values in column 109 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=phyloP100way_vertebrate_rankscore,Number=1,Type=String,Description="calculated by first of overlapping values in column 110 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=phyloP20way_mammalian,Number=1,Type=String,Description="calculated by first of overlapping values in column 111 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=phyloP20way_mammalian_rankscore,Number=1,Type=String,Description="calculated by first of overlapping values in column 112 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=refcodon,Number=1,Type=String,Description="calculated by first of overlapping values in column 14 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/variation/dbNSFP.txt.gz">
+##INFO=<ID=rmsk,Number=.,Type=String,Description="calculated by uniq of overlapping values in column 4 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/hg19.rmsk.bed.gz">
+##INFO=<ID=rs_ids,Number=.,Type=String,Description="calculated by concat of overlapping values in field ID from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/dbsnp.b147.20160601.tidy.vcf.gz">
+##INFO=<ID=stam_mean,Number=1,Type=Float,Description="calculated by mean of overlapping values in column 5 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/stam.125cells.dnaseI.hg19.bed.gz">
+##INFO=<ID=stam_names,Number=.,Type=String,Description="calculated by uniq of overlapping values in column 6 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/stam.125cells.dnaseI.hg19.bed.gz">
+##INFO=<ID=technology.illumina,Number=1,Type=Float,Description="Fraction of observations supporting the alternate observed in reads from illumina">
+##INFO=<ID=tfbs,Number=.,Type=String,Description="calculated by uniq of overlapping values in column 4 from /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/gemini_data/wgEncodeRegTfbsClusteredV2.cell_count.20130213.bed.gz">
+##FORMAT=<ID=AD,Number=R,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed">
+##FORMAT=<ID=AO,Number=1,Type=Integer,Description="Alternate allele observation count">
+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth (reads with MQ=255 or with bad mates are filtered)">
+##FORMAT=<ID=GL,Number=.,Type=Float,Description="Genotype log10-likelihoods for AA,AB and BB genotypes, where A = ref and B = variant. Only applicable for bi-allelic sites">
+##FORMAT=<ID=GOF,Number=.,Type=Float,Description="Goodness of fit value">
+##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=MIN_DP,Number=1,Type=Integer,Description="Minimum depth in gVCF output block.">
+##FORMAT=<ID=NR,Number=.,Type=Integer,Description="Number of reads covering variant location in this sample">
+##FORMAT=<ID=NV,Number=.,Type=Integer,Description="Number of reads containing variant in this sample">
+##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Normalized, Phred-scaled likelihoods for genotypes as defined in the VCF specification">
+##FORMAT=<ID=QA,Number=1,Type=Integer,Description="Sum of quality of the alternate observations">
+##FORMAT=<ID=QR,Number=1,Type=Integer,Description="Sum of quality of the reference observations">
+##FORMAT=<ID=RO,Number=1,Type=Integer,Description="Reference allele observation count">
+##ALT=<ID=*,Description="Represents allele(s) other than observed.">
+##GATKCommandLine.HaplotypeCaller=<ID=HaplotypeCaller,Version=3.8-0-ge9d806836,Date="Thu Aug 02 05:54:20 EDT 2018",Epoch=1533203660430,CommandLineOptions="analysis_type=HaplotypeCaller input_file=[/hpf/largeprojects/ccmbio/naumenko/project_cheo/1171R/work/prealign/1171R_595742/1171R_595742-prealign.bam] showFullBamList=false read_buffer_size=null read_filter=[BadCigar, NotPrimaryAlignment] disable_read_filter=[] intervals=[/hpf/largeprojects/ccmbio/naumenko/project_cheo/1171R/work/gatk-haplotype/1/1171R-1_0_15509579-regions.bed] excludeIntervals=null interval_set_rule=INTERSECTION interval_merging=ALL interval_padding=0 reference_sequence=/hpf/largeprojects/ccmbio/naumenko/tools/bcbio/genomes/Hsapiens/GRCh37/seq/GRCh37.fa nonDeterministicRandomSeed=false disableDithering=false maxRuntime=-1 maxRuntimeUnits=MINUTES downsampling_type=BY_SAMPLE downsample_to_fraction=null downsample_to_coverage=500 baq=OFF baqGapOpenPenalty=40.0 refactor_NDN_cigar_string=false fix_misencoded_quality_scores=false allow_potentially_misencoded_quality_scores=false useOriginalQualities=false defaultBaseQualities=-1 performanceLog=null BQSR=null quantize_quals=0 static_quantized_quals=null round_down_quantized=false disable_indel_quals=false emit_original_quals=false preserve_qscores_less_than=6 globalQScorePrior=-1.0 secondsBetweenProgressUpdates=10 validation_strictness=SILENT remove_program_records=false keep_program_records=false sample_rename_mapping_file=null unsafe=LENIENT_VCF_PROCESSING use_jdk_deflater=false use_jdk_inflater=false disable_auto_index_creation_and_locking_when_reading_rods=false no_cmdline_in_header=false sites_only=false never_trim_vcf_format_field=false bcf=false bam_compression=null simplifyBAM=false disable_bam_indexing=false generate_md5=false num_threads=1 num_cpu_threads_per_data_thread=1 num_io_threads=0 monitorThreadEfficiency=false num_bam_file_handles=null read_group_black_list=null pedigree=[] pedigreeString=[] pedigreeValidationType=STRICT allow_intervals_with_unindexed_bam=false generateShadowBCF=false variant_index_type=DYNAMIC_SEEK variant_index_parameter=-1 reference_window_stop=0 phone_home= gatk_key=null tag=NA logging_level=INFO log_to_file=null help=false version=false out=/hpf/largeprojects/ccmbio/naumenko/project_cheo/1171R/work/bcbiotx/tmpdo686i/1171R-1_0_15509579.vcf.gz likelihoodCalculationEngine=PairHMM heterogeneousKmerSizeResolution=COMBO_MIN dbsnp=(RodBinding name= source=UNBOUND) dontTrimActiveRegions=false maxDiscARExtension=25 maxGGAARExtension=300 paddingAroundIndels=150 paddingAroundSNPs=20 comp=[] annotation=[MappingQualityRankSumTest, MappingQualityZero, QualByDepth, ReadPosRankSumTest, RMSMappingQuality, BaseQualityRankSumTest, FisherStrand, GCContent, HaplotypeScore, HomopolymerRun, DepthPerAlleleBySample, Coverage, ClippingRankSumTest, DepthPerSampleHC] excludeAnnotation=[] group=[StandardAnnotation, StandardHCAnnotation] debug=false useFilteredReadsForAnnotations=false emitRefConfidence=NONE bamOutput=null bamWriterType=CALLED_HAPLOTYPES emitDroppedReads=false disableOptimizations=false annotateNDA=false useNewAFCalculator=false heterozygosity=0.001 indel_heterozygosity=1.25E-4 heterozygosity_stdev=0.01 standard_min_confidence_threshold_for_calling=10.0 standard_min_confidence_threshold_for_emitting=30.0 max_alternate_alleles=6 max_genotype_count=1024 max_num_PL_values=100 input_prior=[] sample_ploidy=2 genotyping_mode=DISCOVERY alleles=(RodBinding name= source=UNBOUND) contamination_fraction_to_filter=0.0 contamination_fraction_per_sample_file=null p_nonref_model=null exactcallslog=null output_mode=EMIT_VARIANTS_ONLY allSitePLs=false gcpHMM=10 pair_hmm_implementation=VECTOR_LOGLESS_CACHING phredScaledGlobalReadMismappingRate=45 noFpga=false nativePairHmmThreads=1 useDoublePrecision=false sample_name=null kmerSize=[10, 25] dontIncreaseKmerSizesForCycles=false allowNonUniqueKmersInRef=false numPruningSamples=1 recoverDanglingHeads=false doNotRecoverDanglingBranches=false minDanglingBranchLength=4 consensus=false maxNumHaplotypesInPopulation=128 errorCorrectKmers=false minPruning=2 debugGraphTransformations=false allowCyclesInKmerGraphToGeneratePaths=false graphOutput=null kmerLengthForReadErrorCorrection=25 minObservationsForKmerToBeSolid=20 GVCFGQBands=[1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 70, 80, 90, 99] indelSizeToEliminateInRefModel=10 min_base_quality_score=10 includeUmappedReads=false useAllelesTrigger=false doNotRunPhysicalPhasing=true keepRG=null justDetermineActiveRegions=false dontGenotype=false dontUseSoftClippedBases=false captureAssemblyFailureBAM=false errorCorrectReads=false pcr_indel_model=CONSERVATIVE maxReadsInRegionPerSample=10000 minReadsPerAlignmentStart=10 mergeVariantsViaLD=false activityProfileOut=null activeRegionOut=null activeRegionIn=null activeRegionExtension=null forceActive=false activeRegionMaxSize=null bandPassSigma=null maxReadsInMemoryPerSample=30000 maxTotalReadsInMemory=10000000 maxProbPropagationDistance=50 activeProbabilityThreshold=0.002 min_mapping_quality_score=20 filter_reads_with_N_cigar=false filter_mismatching_base_and_quals=false filter_bases_not_stored=false">
+##LoF=Loss-of-function annotation (HC = High Confidence; LC = Low Confidence)
+##LoF_filter=Reason for LoF not being HC
+##LoF_flags=Possible warning flags for LoF
+##LoF_info=Info used for LoF annotation
+##MaxEntScan_alt=MaxEntScan alternate sequence score
+##MaxEntScan_diff=MaxEntScan score difference
+##MaxEntScan_ref=MaxEntScan reference sequence score
+##SpliceRegion=SpliceRegion predictions
+##bcftools_annotateCommand=annotate -x INFO/CSQ; Date=Fri Aug  3 23:31:36 2018
+##bcftools_annotateVersion=1.7+htslib-1.7
+##bcftools_callCommand=call -v -m -; Date=Thu Aug  2 00:01:03 2018
+##bcftools_callVersion=1.7+htslib-1.7
+##bcftools_filterCommand=filter -O v --soft-filter GATKCutoffIndel -e 'TYPE="indel" && (ReadPosRankSum < -20.0 || QD < 2.0 || FS > 200.0 || SOR > 10.0 || (QD < 10.0 && AD[0:1] / (AD[0:1] + AD[0:0]) < 0.25 && ReadPosRankSum < 0.0))' -m + /hpf/largeprojects/ccmbio/naumenko/project_cheo/1171R/work/gatk-haplotype/1171R-vepeffects-annotated-filterSNP.vcf.gz; Date=Fri Aug  3 22:57:22 2018
+##bcftools_filterVersion=1.7+htslib-1.7
+##bcftools_viewCommand=view -f PASS,. -O z -o /hpf/largeprojects/ccmbio/naumenko/project_cheo/1171R/work/bcbiotx/tmpkxC5NW/1171R-ensemble-work/txtmp4004832469508254059/1171R-vepeffects-annotated-filterSNP-filterINDEL-noeff-nomultiallelic-nofilter.vcf.gz /hpf/largeprojects/ccmbio/naumenko/project_cheo/1171R/work/gatk-haplotype/1171R-vepeffects-annotated-filterSNP-filterINDEL-noeff-nomultiallelic.vcf.gz; Date=Fri Aug  3 23:32:49 2018
+##bcftools_viewVersion=1.7+htslib-1.7
+##commandline="/hpf/largeprojects/ccmbio/naumenko/tools/bcbio/anaconda/bin/freebayes -f /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/genomes/Hsapiens/GRCh37/seq/GRCh37.fa --genotype-qualities --strict-vcf --ploidy 2 --targets /hpf/largeprojects/ccmbio/naumenko/project_cheo/1171R/work/freebayes/1/1171R-1_0_15509579-regions.bed --min-repeat-entropy 1 --no-partial-observations -b /hpf/largeprojects/ccmbio/naumenko/project_cheo/1171R/work/prealign/1171R_595742/1171R_595742-prealign.bam"
+##fileDate=2018-08-02
+##phasing=none
+##platypusOptions={'assemblyRegionSize': 1500, 'trimReadFlank': 0, 'assembleBadReads': 1, 'bamFiles': ['/hpf/largeprojects/ccmbio/naumenko/project_cheo/1171R/work/prealign/1171R_595742/1171R_595742-prealign.bam'], 'minVarDist': 9, 'trimSoftClipped': 1, 'minReads': 2, 'qualBinSize': 1, 'refFile': '/hpf/largeprojects/ccmbio/naumenko/tools/bcbio/genomes/Hsapiens/GRCh37/seq/GRCh37.fa', 'maxHaplotypes': 50, 'filterVarsByCoverage': 1, 'maxSize': 1500, 'originalMaxHaplotypes': 50, 'skipDifficultWindows': 0, 'parseNCBI': 0, 'skipRegionsFile': None, 'noCycles': 0, 'trimAdapter': 1, 'minPosterior': 5, 'assembleAll': 1, 'trimOverlapping': 1, 'filterDuplicates': 0, 'abThreshold': 0.001, 'minFlank': 10, 'bufferSize': 100000, 'fileCaching': 0, 'useEMLikelihoods': 0, 'coverageSamplingLevel': 30, 'calculateFlankScore': 0, 'logFileName': '/dev/null', 'nCPU': 1, 'filterReadsWithUnmappedMates': 1, 'qdThreshold': 10, 'maxVariants': 8, 'scThreshold': 0.95, 'filterReadsWithDistantMates': 1, 'maxReads': 5000000, 'badReadsWindow': 11, 'genIndels': 1, 'largeWindows': 0, 'minMapQual': 20, 'maxVarDist': 15, 'maxGOF': 30, 'rlen': 150, 'minGoodQualBases': 20, 'refCallBlockSize': 1000, 'countOnlyExactIndelMatches': 0, 'longHaps': 0, 'HLATyping': 0, 'filterReadPairsWithSmallInserts': 1, 'minBaseQual': 20, 'getVariantsFromBAMs': 1, 'genSNPs': 1, 'assemble': 0, 'assemblerKmerSize': 15, 'minVarFreq': 0.05, 'alignScoreFile': '', 'verbosity': 1, 'sourceFile': None, 'compressReads': 0, 'rmsmqThreshold': 40, 'filteredReadsFrac': 0.7, 'outputRefCalls': 0, 'badReadsThreshold': 15, 'hapScoreThreshold': 4, 'regions': ['/hpf/largeprojects/ccmbio/naumenko/project_cheo/1171R/work/platypus/1/1171R-1_0_15509579-regions.bed'], 'sbThreshold': 0.001, 'output': '-', 'assembleBrokenPairs': 0, 'mergeClusteredVariants': 1, 'maxGenotypes': 1275, 'nInd': 1}
+##reference=file:///hpf/largeprojects/ccmbio/naumenko/tools/bcbio/genomes/Hsapiens/GRCh37/seq/GRCh37.fa
+##samtoolsCommand=samtools mpileup -f /hpf/largeprojects/ccmbio/naumenko/tools/bcbio/genomes/Hsapiens/GRCh37/seq/GRCh37.fa -t DP -u -g -l /hpf/largeprojects/ccmbio/naumenko/project_cheo/1171R/work/samtools/1/1171R-1_0_15509579-regions.bed /hpf/largeprojects/ccmbio/naumenko/project_cheo/1171R/work/prealign/1171R_595742/1171R_595742-prealign.bam
+##samtoolsVersion=1.7+htslib-1.7
+##source=Platypus_Version_0.8.1.1
+##bcftools_viewCommand=view -f PASS,.; Date=Sun Aug  5 20:18:16 2018
+##bcftools_viewCommand=view -f PASS,.; Date=Thu Aug 16 23:29:37 2018
+##VEP="v92" time="2018-08-16 23:31:46" cache="/hpf/largeprojects/ccmbio/naumenko/tools/bcbio/genomes/Hsapiens/GRCh37/vep/homo_sapiens_merged/92_GRCh37" ensembl-variation=92.77a06cf ensembl=92.98e8548 ensembl-funcgen=92.cd2ca86 ensembl-io=92.39280bd 1000genomes="phase3" COSMIC="81" ClinVar="201706" ESP="20141103" HGMD-PUBLIC="20164" assembly="GRCh37.p13" dbSNP="150" gencode="GENCODE 19" genebuild="2011-04" gnomAD="170228" polyphen="2.2.2" refseq="01_2015" regbuild="1.0" sift="sift5.2.2"
+##bcftools_viewCommand=view 1171R-ensemble-annotated-decomposed.vcf.gz 1:14464; Date=Mon Aug 20 13:02:28 2018
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	1171R_595742
+1	14464	rs546169444	A	T	72.8	PASS	AC=1;AF=0.5;AN=2;BaseQRankSum=0.674;CALLERS=gatk-haplotype,samtools,freebayes;ClippingRankSum=0;DP=4;ExcessHet=3.0103;FS=0;MLEAC=1;MLEAF=0.5;MQ=34.53;MQ0=0;MQRankSum=0.319;QD=18.2;ReadPosRankSum=-0.319;SOR=1.609;CSQ=T|non_coding_transcript_exon_variant|MODIFIER|WASH7P|ENSG00000227232|Transcript|ENST00000423562|unprocessed_pseudogene|10/10||ENST00000423562.1:n.1568T>A||1568/1669|||||rs546169444|1||-1||SNV|HGNC|38034||||||||||Ensembl|A|A|||||||0.0958|0.0144|0.1138|0.005|0.1859|0.1943||||||||||||0.1943|SAS||||||||||||||||,T|non_coding_transcript_exon_variant|MODIFIER|WASH7P|ENSG00000227232|Transcript|ENST00000438504|unprocessed_pseudogene|12/12||ENST00000438504.2:n.1682T>A||1682/1783|||||rs546169444|1||-1||SNV|HGNC|38034|YES|||||||||Ensembl|A|A|||||||0.0958|0.0144|0.1138|0.005|0.1859|0.1943||||||||||||0.1943|SAS||||||||||||||||,T|downstream_gene_variant|MODIFIER|DDX11L1|ENSG00000223972|Transcript|ENST00000450305|transcribed_unprocessed_pseudogene||||||||||rs546169444|1|794|1||SNV|HGNC|37102||||||||||Ensembl|A|A|||||||0.0958|0.0144|0.1138|0.005|0.1859|0.1943||||||||||||0.1943|SAS||||||||||||||||,T|downstream_gene_variant|MODIFIER|DDX11L1|ENSG00000223972|Transcript|ENST00000456328|processed_transcript||||||||||rs546169444|1|55|1||SNV|HGNC|37102|YES|||||||||Ensembl|A|A|||||||0.0958|0.0144|0.1138|0.005|0.1859|0.1943||||||||||||0.1943|SAS||||||||||||||||,T|non_coding_transcript_exon_variant|MODIFIER|WASH7P|ENSG00000227232|Transcript|ENST00000488147|unprocessed_pseudogene|11/11||ENST00000488147.1:n.1291T>A||1291/1351|||||rs546169444|1||-1||SNV|HGNC|38034||||||||||Ensembl|A|A|||||||0.0958|0.0144|0.1138|0.005|0.1859|0.1943||||||||||||0.1943|SAS||||||||||||||||,T|downstream_gene_variant|MODIFIER|DDX11L1|ENSG00000223972|Transcript|ENST00000515242|transcribed_unprocessed_pseudogene||||||||||rs546169444|1|52|1||SNV|HGNC|37102||||||||||Ensembl|A|A|||||||0.0958|0.0144|0.1138|0.005|0.1859|0.1943||||||||||||0.1943|SAS||||||||||||||||,T|downstream_gene_variant|MODIFIER|DDX11L1|ENSG00000223972|Transcript|ENST00000518655|transcribed_unprocessed_pseudogene||||||||||rs546169444|1|55|1||SNV|HGNC|37102||||||||||Ensembl|A|A|||||||0.0958|0.0144|0.1138|0.005|0.1859|0.1943||||||||||||0.1943|SAS||||||||||||||||,T|non_coding_transcript_exon_variant|MODIFIER|WASH7P|ENSG00000227232|Transcript|ENST00000538476|unprocessed_pseudogene|13/13||ENST00000538476.1:n.1530T>A||1530/1583|||||rs546169444|1||-1||SNV|HGNC|38034||||||||||Ensembl|A|A|||||||0.0958|0.0144|0.1138|0.005|0.1859|0.1943||||||||||||0.1943|SAS||||||||||||||||,T|non_coding_transcript_exon_variant|MODIFIER|WASH7P|ENSG00000227232|Transcript|ENST00000541675|unprocessed_pseudogene|9/9||ENST00000541675.1:n.1315T>A||1315/1416|||||rs546169444|1||-1||SNV|HGNC|38034||||||||||Ensembl|A|A|||||||0.0958|0.0144|0.1138|0.005|0.1859|0.1943||||||||||||0.1943|SAS||||||||||||||||,T|non_coding_transcript_exon_variant|MODIFIER|WASH7P|653635|Transcript|NR_024540.1|pseudogene|11/11||NR_024540.1:n.1667T>A||1667/1769|||||rs546169444|1||-1||SNV|EntrezGene|38034|YES|||||||||RefSeq|A|A|OK||||||0.0958|0.0144|0.1138|0.005|0.1859|0.1943||||||||||||0.1943|SAS||||||||||||||||,T|downstream_gene_variant|MODIFIER|DDX11L1|100287102|Transcript|NR_046018.2|pseudogene||||||||||rs546169444|1|55|1||SNV|EntrezGene|37102|YES|||||||||RefSeq|A|A|||||||0.0958|0.0144|0.1138|0.005|0.1859|0.1943||||||||||||0.1943|SAS||||||||||||||||,T|downstream_gene_variant|MODIFIER|MIR6859-1|102466751|Transcript|NR_106918.1|miRNA||||||||||rs546169444|1|2905|-1||SNV|EntrezGene||YES|||||||||RefSeq|A|A|||||||0.0958|0.0144|0.1138|0.005|0.1859|0.1943||||||||||||0.1943|SAS||||||||||||||||,T|regulatory_region_variant|MODIFIER|||RegulatoryFeature|ENSR00000000002|open_chromatin_region||||||||||rs546169444|1||||SNV|||||||||||||||||||||0.0958|0.0144|0.1138|0.005|0.1859|0.1943||||||||||||0.1943|SAS||||||||||||||||;gnomad_ac_gs=5015;gnomad_af_gs=0.3152;af_1kg_amr=0.1138;af_1kg_eas=0.005;af_1kg_sas=0.1943;af_1kg_afr=0.0144;af_1kg_eur=0.1859;af_1kg_all=0.0958;rs_ids=rs546169444;af_1kg=0.1943;max_af=0.3152	GT:AD:DP:GQ:PL	0/1:1,3:4:22:101,0,22