Skip to content

Commit

Permalink
test gvcf_norm examples
Browse files Browse the repository at this point in the history
  • Loading branch information
@mlin
mlin committed Aug 11, 2021
1 parent 82e9cb1 commit 68e25e5
Show file tree
Hide file tree
Showing 2 changed files with 160 additions and 0 deletions.
154 changes: 154 additions & 0 deletions test/data/gvcf_test_cases/deepvariant_norm.yml
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,154 @@
readme: |
DeepVariant+gvcf_norm
input:
header : |-
##fileformat=VCFv4.2
##FILTER=<ID=PASS,Description="All filters passed">
##FILTER=<ID=RefCall,Description="Genotyping model thinks this site is reference.">
##FILTER=<ID=LowQual,Description="Confidence in this variant being real is below calling threshold."
##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">
##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Read depth of all passing filters reads.">
##FORMAT=<ID=MIN_DP,Number=1,Type=Integer,Description="Minimum DP observed within the GVCF block.">
##FORMAT=<ID=AD,Number=R,Type=Integer,Description="Read depth of all passing filters reads for each
##FORMAT=<ID=VAF,Number=A,Type=Float,Description="Variant allele fractions.">
##FORMAT=<ID=GL,Number=G,Type=Float,Description="Genotype likelihoods, log10 encoded">
##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Genotype likelihoods, Phred encoded">
##INFO=<ID=END,Number=1,Type=Integer,Description="Stop position of the interval">
##contig=<ID=chr21,length=48129895>
##contig=<ID=chr22,length=51304566>
##INFO=<ID=gvcf_norm_originalPOS,Number=1,Type=Integer,Description="POS before gvcf_norm left-aligned the variant">
#CHROM POS ID REF ALT QUAL FILTER INFO FORMAT
body:
- NA12878.gvcf: |
NA12878
chr21 26193733 . T <*> 0 . END=26193733 GT:GQ:MIN_DP:PL 0/0:39:33:0,39,869
chr21 26193734 . G T,<*> 29 PASS . GT:GQ:DP:AD:VAF:PL 0/1:29:33:21,12,0:0.363636,0:29,0,48,990,990,990
chr21 26193735 . T <*> 0 . END=26193740 GT:GQ:MIN_DP:PL 0/0:50:32:0,69,929
chr21 26193741 . TTTTTT T,<*> 29.1 PASS . GT:GQ:DP:AD:VAF:PL 0/1:29:32:22,8,0:0.25,0:29,0,55,990,990,990
chr21 26193747 . T <*> 0 . END=26193751 GT:GQ:MIN_DP:PL 0/0:50:22:0,66,659
chr21 29848774 . T <*> 0 . END=29848778 GT:GQ:MIN_DP:PL 0/0:50:30:0,99,989
chr21 29848779 . AT ATATATTT,T,<*> 40.3 PASS . GT:GQ:DP:AD:VAF:PL 1/2:16:32:1,11,12,0:0.34375,0.375,0:40,19,47,19,0,57,990,990,990,990
chr21 29848781 . T <*> 0 . END=29848791 GT:GQ:MIN_DP:PL 0/0:50:19:0,57,569
- NA12878_norm.gvcf: |
NA12878_norm
chr21 26193733 . T <*> 0 . END=26193733 GT:GQ:MIN_DP:PL 0/0:39:33:0,39,869
chr21 26193734 . G T,<*> 29 PASS . GT:GQ:DP:AD:VAF:PL 0/1:29:33:21,12,0:0.363636,0:29,0,48,990,990,990
chr21 26193734 . GTTTTT G,<*> 29.1 PASS gvcf_norm_originalPOS=26193741 GT:GQ:DP:AD:VAF:PL 0/1:29:32:22,8,0:0.25,0:29,0,55,990,990,990
chr21 26193735 . T <*> 0 . END=26193740 GT:GQ:MIN_DP:PL 0/0:50:32:0,69,929
chr21 26193747 . T <*> 0 . END=26193751 GT:GQ:MIN_DP:PL 0/0:50:22:0,66,659
chr21 29848774 . T <*> 0 . END=29848778 GT:GQ:MIN_DP:PL 0/0:50:30:0,99,989
chr21 29848778 . TA TATATATT,T,<*> 40.3 PASS gvcf_norm_originalPOS=29848779 GT:GQ:DP:AD:VAF:PL 1/2:16:32:1,11,12,0:0.34375,0.375,0:40,19,47,19,0,57,990,990,990,990
chr21 29848781 . T <*> 0 . END=29848791 GT:GQ:MIN_DP:PL 0/0:50:19:0,57,569
unifier_config:
min_AQ1: 0
min_AQ2: 0
min_GQ: 0
monoallelic_sites_for_lost_alleles: true

genotyper_config:
required_dp: 0
revise_genotypes: true
snv_prior_calibration: 0.375
indel_prior_calibration: 0.375
allow_partial_data: true
more_PL: true
trim_uncalled_alleles: true
liftover_fields:
- orig_names: [MIN_DP, DP]
name: DP
description: '##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth (reads with MQ=255 or with bad mates are filtered)">'
type: int
combi_method: min
number: basic
count: 1
ignore_non_variants: true
- orig_names: [AD]
name: AD
description: '##FORMAT=<ID=AD,Number=R,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed">'
type: int
number: alleles
combi_method: min
default_type: zero
count: 0
- orig_names: [GQ]
name: GQ
description: '##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">'
type: int
number: basic
combi_method: min
count: 1
ignore_non_variants: true
- orig_names: [PL]
name: PL
description: '##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Phred-scaled genotype Likelihoods">'
type: int
number: genotype
combi_method: missing
count: 0
ignore_non_variants: true

truth_unified_sites:
- range: {ref: chr21, beg: 26193734, end: 26193739}
in_target: {ref: chr21, beg: 1, end: 1000000000}
alleles:
- dna: GTTTTT
- dna: TTTTTT
normalized:
range: {beg: 26193734, end: 26193734}
dna: T
quality: 29
frequency: 0.5
- dna: G
quality: 29
frequency: 0.25
quality: 29
- range: {ref: chr21, beg: 26193741, end: 26193746}
in_target: {ref: chr21, beg: 1, end: 1000000000}
alleles:
- dna: TTTTTT
- dna: T
quality: 29
frequency: 0.25
quality: 29
- range: {ref: chr21, beg: 29848778, end: 29848779}
in_target: {ref: chr21, beg: 1, end: 1000000000}
alleles:
- dna: TA
- dna: T
quality: 19
frequency: 0.5
- dna: TATATATT
normalized:
range: {beg: 29848779, end: 29848779}
dna: ATATATT
quality: 19
frequency: 0.5
quality: 19
unification:
- range: {beg: 29848779, end: 29848780}
dna: T
to: 1
- range: {beg: 29848779, end: 29848780}
dna: ATATATTT
to: 2

truth_output_vcf:
- truth.vcf: |
##fileformat=VCFv4.2
##INFO=<ID=AF,Number=A,Type=Float,Description="Allele Frequency estimate for each alternate allele">
##INFO=<ID=AQ,Number=A,Type=Integer,Description="Allele Quality score reflecting evidence from all samples (Phred scale)">
##FILTER=<ID=PASS,Description="All filters passed">
##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">
##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Genotype likelihoods, Phred encoded">
##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth (reads with MQ=255 or with bad mates are filtered)">
##FORMAT=<ID=AD,Number=.,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed">
##FORMAT=<ID=RNC,Number=G,Type=Character,Description="Reason for No Call in GT: . = n/a, M = Missing data, P = Partial data, D = insufficient Depth of coverage, - = unrepresentable overlapping deletion, L = Lost/unrepresentable allele (other than deletion), U = multiple Unphased variants present, O = multiple Overlapping variants present">
##contig=<ID=21,length=48129895>
#CHROM POS ID REF ALT QUAL FILTER INFO FORMAT NA12878 NA12878_norm
chr21 26193734 . GTTTTT TTTTTT,G 29 . AF=0.5,0.25;AQ=29,29 GT:DP:AD:GQ:PL:RNC 0/1:33:21,12,0:29:29,0,48,990,990,990:.. 1/2:32:.,12,8:29:0,0,0,0,0,0:..
chr21 26193741 . TTTTTT T 29 . AF=0.25;AQ=29 GT:DP:AD:GQ:PL:RNC 0/1:32:22,8:29:29,0,55:.. ./.:.:.:.:0,0,0:MM
chr21 29848778 . TA T,TATATATT 19 . AF=0.5,0.5;AQ=19,19 GT:DP:AD:GQ:PL:RNC 1/2:32:1,12,11:16:40,19,57,19,0,47:.. 1/2:32:1,12,11:16:40,19,57,19,0,47:..
6 changes: 6 additions & 0 deletions test/gvcf_test_cases.cc
View file
Original file line number Diff line number Diff line change
Expand Up @@ -852,6 +852,12 @@ TEST_CASE("DeepVariant2") {
GVCFTestCase("deepvariant2", v_formats, v_infos, false).perform_gvcf_test();
}

TEST_CASE("DeepVariant_norm") {
vector<string> v_formats = {"DP", "GT", "GQ", "PL", "AD", "RNC"};
vector<string> v_infos = {"ANR","AF","AQ"};
GVCFTestCase("deepvariant_norm", v_formats, v_infos, false).perform_gvcf_test();
}

TEST_CASE("dv_1000G_chr21_5583275") {
vector<string> v_formats = {"DP", "GT", "GQ", "PL", "AD", "RNC"};
vector<string> v_infos = {"ANR","AF","AQ"};
Expand Down

0 comments on commit 68e25e5

Please sign in to comment.