diff --git a/test/config/config-noalt-uncalled.json b/test/config/config-noalt-uncalled.json new file mode 100644 index 0000000000000000000000000000000000000000..c4dc9dad06763e3bb8637155c4157f4acbd68422 --- /dev/null +++ b/test/config/config-noalt-uncalled.json @@ -0,0 +1,9 @@ +{ + "samples": { + "16699289": { + "disease_code": "TEST", + "gvcf": "test/data/16699289_chrM.g.vcf", + "vcf": "test/data/16699289_chrM_noalt_uncalled.vcf" + } + } +} diff --git a/test/data/16699289_chrM_noalt_uncalled.vcf b/test/data/16699289_chrM_noalt_uncalled.vcf new file mode 100644 index 0000000000000000000000000000000000000000..fc48c78ea837cfcf5e72e9be9c7b4f4c8e702c3a --- /dev/null +++ b/test/data/16699289_chrM_noalt_uncalled.vcf @@ -0,0 +1,40 @@ +##fileformat=VCFv4.2 +##ALT=<ID=NON_REF,Description="Represents any possible alternative allele at this location"> +##FILTER=<ID=LowQual,Description="Low quality"> +##FORMAT=<ID=AD,Number=R,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed"> +##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth (reads with MQ=255 or with bad mates are filtered)"> +##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 DP observed within the GVCF block"> +##FORMAT=<ID=PGT,Number=1,Type=String,Description="Physical phasing haplotype information, describing how the alternate alleles are phased in relation to one another"> +##FORMAT=<ID=PID,Number=1,Type=String,Description="Physical phasing ID information, where each unique ID within a given sample (but not across samples) connects records within a phasing group"> +##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Normalized, Phred-scaled likelihoods for genotypes as defined in the VCF specification"> +##FORMAT=<ID=RGQ,Number=1,Type=Integer,Description="Unconditional reference genotype confidence, encoded as a phred quality -10*log10 p(genotype call is wrong)"> +##FORMAT=<ID=SB,Number=4,Type=Integer,Description="Per-sample component statistics which comprise the Fisher's Exact Test to detect strand bias."> +##INFO=<ID=AC,Number=A,Type=Integer,Description="Allele count in genotypes, for each ALT allele, in the same order as listed"> +##INFO=<ID=AF,Number=A,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=BaseQRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt Vs. Ref base qualities"> +##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=DB,Number=0,Type=Flag,Description="dbSNP Membership"> +##INFO=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth; some reads may have been filtered"> +##INFO=<ID=DS,Number=0,Type=Flag,Description="Were any of the samples downsampled?"> +##INFO=<ID=END,Number=1,Type=Integer,Description="Stop position of the interval"> +##INFO=<ID=ExcessHet,Number=1,Type=Float,Description="Phred-scaled p-value for exact test of excess heterozygosity"> +##INFO=<ID=FS,Number=1,Type=Float,Description="Phred-scaled p-value using Fisher's exact test to detect strand bias"> +##INFO=<ID=HaplotypeScore,Number=1,Type=Float,Description="Consistency of the site with at most two segregating haplotypes"> +##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=MLEAC,Number=A,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=A,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=MQ,Number=1,Type=Float,Description="RMS Mapping Quality"> +##INFO=<ID=MQRankSum,Number=1,Type=Float,Description="Z-score From Wilcoxon rank sum test of Alt vs. Ref read mapping qualities"> +##INFO=<ID=QD,Number=1,Type=Float,Description="Variant Confidence/Quality by Depth"> +##INFO=<ID=RAW_MQ,Number=1,Type=Float,Description="Raw data for RMS Mapping Quality"> +##INFO=<ID=ReadPosRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt vs. Ref read position bias"> +##INFO=<ID=SOR,Number=1,Type=Float,Description="Symmetric Odds Ratio of 2x2 contingency table to detect strand bias"> +##contig=<ID=chrM,length=16571,assembly=hg19> +#CHROM POS ID REF ALT QUAL FILTER INFO FORMAT 16699289 +chrM 73 . G A 4062.77 . AC=2;AF=1.00;AN=2;DP=131;ExcessHet=3.0103;FS=0.000;MLEAC=2;MLEAF=1.00;MQ=58.26;QD=32.24;SOR=0.791 GT:AD:DP:GQ:PL 1/1:0,126:126:99:4091,378,0 +chrM 150 . T C 5149.77 . AC=2;AF=1.00;AN=2;DP=130;ExcessHet=3.0103;FS=0.000;MLEAC=2;MLEAF=1.00;MQ=60.00;QD=34.24;SOR=0.710 GT:AD:DP:GQ:PGT:PID:PL 0/0:0,117:117:99:1|1:150_T_C:5178,352,0 +chrM 152 . T C 5149.77 . AC=2;AF=1.00;AN=2;DP=126;ExcessHet=3.0103;FS=0.000;MLEAC=2;MLEAF=1.00;MQ=60.00;QD=30.63;SOR=0.711 GT:AD:DP:GQ:PGT:PID:PL ./.:0,113:113:99:1|1:150_T_C:5178,352,0 +chrM 195 . C T 2959.77 . AC=2;AF=1.00;AN=2;DP=98;ExcessHet=3.0103;FS=0.000;MLEAC=2;MLEAF=1.00;MQ=60.00;QD=29.09;SOR=0.961 GT:AD:DP:GQ:PL 1/1:0,82:82:99:2988,246,0 diff --git a/test/test-integration.yml b/test/test-integration.yml index b4af988d67256ae33b1f80d0f3e58e4f79c92931..29151c00e72c6542fc686b8de458522edad8b342 100644 --- a/test/test-integration.yml +++ b/test/test-integration.yml @@ -12,3 +12,24 @@ - path: 16699289_coverage.varda - path: 16699289_variants.varda +- name: test-trim-alt-exclude-uncalled + tags: + - integration + command: > + snakemake + --configfile test/config/config-noalt-uncalled.json + --use-singularity + --singularity-args ' --containall --bind /tmp' + --notemp + --cores 1 + 16699289_trimmed.vcf + files: + - path: 16699289_trimmed.vcf + must_not_contain: + - "chrM\t150\t.\tT\tC" + - "chrM\t152\t.\tT\tC" + contains: + - "chrM\t73\t.\tG\tA" + - "chrM\t150\t.\tT\t." + - "chrM\t152\t.\tT\t." + - "chrM\t195\t.\tC\tT"