From 5b826f207b7db8cfeb11bd4358aaf570e5233599 Mon Sep 17 00:00:00 2001 From: Shilpa Nadimpalli Kobren Date: Wed, 21 Feb 2024 19:18:17 -0500 Subject: [PATCH] Add files via upload Expected output results when run on sample test data. --- .../output/test_comphet_cohort_recurrence.txt | 43 ++++++ test/output/test_comphet_individual_level.txt | 10 ++ .../test_comphet_mutational_targets.txt | 49 ++++++ test/output/test_comphet_variant_counts.txt | 19 +++ .../test_comphet_variant_distribution.txt | 58 ++++++++ ...t_comphet_variant_product_distribution.txt | 139 ++++++++++++++++++ test/output/test_denovo_cohort_recurrence.txt | 38 +++++ .../output/test_denovo_mutational_targets.txt | 39 +++++ test/output/test_denovo_variant_counts.txt | 6 + .../test_denovo_variant_distribution.txt | 17 +++ 10 files changed, 418 insertions(+) create mode 100644 test/output/test_comphet_cohort_recurrence.txt create mode 100644 test/output/test_comphet_individual_level.txt create mode 100644 test/output/test_comphet_mutational_targets.txt create mode 100644 test/output/test_comphet_variant_counts.txt create mode 100644 test/output/test_comphet_variant_distribution.txt create mode 100644 test/output/test_comphet_variant_product_distribution.txt create mode 100644 test/output/test_denovo_cohort_recurrence.txt create mode 100644 test/output/test_denovo_mutational_targets.txt create mode 100644 test/output/test_denovo_variant_counts.txt create mode 100644 test/output/test_denovo_variant_distribution.txt diff --git a/test/output/test_comphet_cohort_recurrence.txt b/test/output/test_comphet_cohort_recurrence.txt new file mode 100644 index 0000000..39188f1 --- /dev/null +++ b/test/output/test_comphet_cohort_recurrence.txt @@ -0,0 +1,43 @@ +file_names ensembl_gene_id gene_name P_val P_cond P_comphet poisson_lambda false_diagnosis_rate variant_info +test_patient5.tsv ENSG00000101220 C20orf27 2.148021806414702e-05 0.11168316306743772 0.0001923317487988463 0.00019235024692149588 0.0 chr20:G_3754424_A|CS|3.90395|P|test_patient5.tsv&chr20:G_3761023_C|IS|0.63|M|test_patient5.tsv +test_patient9.tsv ENSG00000080293 SCTR 2.6077297643100892e-05 0.021586685901861552 0.0012080269181501402 0.001208757170836845 0.0 chr2:G_119452036_A|CS|4.43205|P|test_patient9.tsv&chr2:G_119452036_A|CS|4.43205|M|test_patient9.tsv +test_patient4.tsv ENSG00000114656 CFAP92 7.393698802523214e-05 0.08658753589849612 0.0008538987425615874 0.0008542635217639556 0.0 chr3:C_128970364_G|IS|0.39|P|test_patient4.tsv&chr3:C_128970364_G|IS|0.39|M|test_patient4.tsv +test_patient8.tsv ENSG00000186806 VSIG10L 7.754000596163234e-05 0.048217443592192974 0.001608131833314097 0.001609426265241646 0.0 chr19:C_51341368_T|CS|3.94935|P|test_patient8.tsv&chr19:G_51338205_T|CS|3.82217|M|test_patient8.tsv +test_patient2.tsv ENSG00000010318 PHF7 0.00017873256409123487 0.5158461850227705 0.0003464842220037845 0.0003465442615306923 0.0 chr3:G_52422746_T|IS|0.2|P|test_patient2.tsv&chr3:T_52422267_A|CS|6.58568|M|test_patient2.tsv +test_patient8.tsv ENSG00000105219 CCNP 0.0002892059757170139 0.960945933319282 0.0003009596749299348 0.00030100497238165394 0.0 chr19:G_40222369_T|CS|1.55743|P|test_patient8.tsv&chr19:G_40223236_A|CS|3.52521|M|test_patient8.tsv +test_patient7.tsv ENSG00000103196 CRISPLD2 0.00033885834491722134 0.17979846729316812 0.0018846564713185243 0.0018864346708740724 0.0 chr16:G_84868866_A|CS|4.54509|P|test_patient7.tsv&chr16:C_84840821_T|IS|0.29|M|test_patient7.tsv +test_patient7.tsv ENSG00000145916 RMND5B 0.0003508884912207386 0.4550658789596972 0.000771071854525518 0.0007713692833304566 0.0 chr5:G_178138183_GGGCAGCACT|CI|2.645243|P|test_patient7.tsv&chr5:G_178146273_A|CS|2.96878|M|test_patient7.tsv +test_patient2.tsv ENSG00000218823 PAPOLB 0.0003692225120410811 0.5290512395424902 0.0006978955617992222 0.0006981392042714553 0.0 chr7:TGA_4860012_T|CI|4.095266|P|test_patient2.tsv&chr7:T_4861637_G|CS|2.29967|M|test_patient2.tsv +test_patient6.tsv ENSG00000159216 RUNX1 0.0003874263586071864 0.1696082940508568 0.002284241821871147 0.0022868546819159678 0.0 chr21:T_34834592_A|CS|3.95425|P|test_patient6.tsv&chr21:C_34880568_T|CS|4.44113|M|test_patient6.tsv +test_patient6.tsv ENSG00000135624 CCT7 0.00048381489440958486 0.47906344710519444 0.0010099182004661422 0.0010104285114624979 0.0 chr2:T_73249822_A|CS|3.71215|P|test_patient6.tsv&chr2:G_73252845_A|CS|3.31355|M|test_patient6.tsv +test_patient5.tsv ENSG00000215262 KCNU1 0.0006736184161919917 0.17597918613748567 0.00382783004613807 0.0038351749368891806 0.0 chr8:G_36787239_A|IS|0.3|P|test_patient5.tsv&chr8:G_36909360_T|CS|3.57366|M|test_patient5.tsv +test_patient9.tsv ENSG00000173193 PARP14 0.0006778168933768957 0.1991280256199051 0.0034039251444731855 0.0034097316780827337 0.0 chr3:G_122685319_A|IS|0.76|P|test_patient9.tsv&chr3:G_122713923_A|CS|3.39003|M|test_patient9.tsv +test_patient7.tsv ENSG00000114770 ABCC5 0.0008355608591900176 0.0903488168862666 0.009248166030130123 0.009291195820830676 0.0 chr3:A_183947367_T|CS|4.05246|P|test_patient7.tsv&chr3:G_183949816_C|CS|4.37386|M|test_patient7.tsv +test_patient9.tsv ENSG00000196591 HDAC2 0.0010749787719244038 0.8813883279187219 0.0012196426227504276 0.0012203869921186615 0.0 chr6:G_113956702_T|IS|0.16|P|test_patient9.tsv&chr6:G_113956702_T|IS|0.16|M|test_patient9.tsv +test_patient6.tsv ENSG00000164934 DCAF13 0.0012400247136536318 0.9028275735017219 0.0013734900772293113 0.0013744341793009898 0.0 chr8:G_103440560_C|IS|0.53|P|test_patient6.tsv&chr8:C_103415196_G|CS|1.54288|M|test_patient6.tsv +test_patient2.tsv ENSG00000188779 SKOR1 0.0018077912135076376 0.8131742975834898 0.0022231288161466134 0.002225603635588472 0.0 chr15:T_67826673_G|CS|2.05706|P|test_patient2.tsv&chr15:C_67828134_T|CS|2.45427|M|test_patient2.tsv +test_patient2.tsv ENSG00000132849 PATJ 0.002082539509081194 0.15600260121077092 0.013349389644263243 0.013439293752656746 0.0 chr1:C_62148357_T|CS|2.2905|P|test_patient2.tsv&chr1:T_62049551_C|IS|0.39|M|test_patient2.tsv +test_patient3.tsv ENSG00000008226 DLEC1 0.0029111329272343933 0.3254782805047925 0.008944169554783943 0.008984408756486378 0.0 chr3:G_38117210_A|IS|0.25|P|test_patient3.tsv&chr3:G_38116772_T|IS|0.81|M|test_patient3.tsv +test_patient4.tsv ENSG00000156395 SORCS3 0.0036769580983089336 0.38723714336655074 0.009495365207847328 0.009540733609499075 0.0 chr10:T_104977372_C|CS|3.11537|P|test_patient4.tsv&chr10:C_105139436_G|CS|3.10482|M|test_patient4.tsv +test_patient9.tsv ENSG00000131697 NPHP4 0.004316870930759805 0.328954205670853 0.01312301486450429 0.013209882437335925 0.0 chr1:G_5882861_A|IS|0.53|P|test_patient9.tsv&chr1:T_5875004_C|CS|1.76576|M|test_patient9.tsv +test_patient7.tsv ENSG00000068976 PYGM 0.004356407315695673 0.9463659674163782 0.0046033009065075126 0.004613928724029089 0.0 chr11:T_64752486_C|CS|1.88515|P|test_patient7.tsv&chr11:G_64759751_A|CS|5.66247|M|test_patient7.tsv +test_patient8.tsv ENSG00000055118 KCNH2 0.004674946956037011 0.5927731893790524 0.007886569500442753 0.00791783297253498 0.0 chr7:G_150958202_A|CS|2.53237|P|test_patient8.tsv&chr7:G_150958449_A|CS|3.27642|M|test_patient8.tsv +test_patient9.tsv ENSG00000138002 IFT172 0.005081900268301298 0.3823378389083952 0.01329164877536193 0.013380773361747637 0.0 chr2:A_27447624_G|CS|4.2879|P|test_patient9.tsv&chr2:G_27476652_C|CS|3.12065|M|test_patient9.tsv +test_patient1.tsv ENSG00000091428 RAPGEF4 0.0051108273997115755 0.6752798562588769 0.007568458250814869 0.007597244367287079 0.0 chr2:G_173014459_T|IS|0.28|P|test_patient1.tsv&chr2:G_173019594_C|IS|0.18|M|test_patient1.tsv +test_patient4.tsv ENSG00000197748 CFAP43 0.00536376184226492 0.7845712591639886 0.006836551530042478 0.006860027807488871 0.0 chr10:T_104143495_G|CS|1.99241|P|test_patient4.tsv&chr10:A_104147961_G|CS|3.87771|M|test_patient4.tsv +test_patient8.tsv ENSG00000121210 TMEM131L 0.006287812421651071 0.8485791169845791 0.007409812822161799 0.007437401856065239 0.0 chr4:A_153593821_T|CS|2.26947|P|test_patient8.tsv&chr4:A_153479364_G|IS|0.16|M|test_patient8.tsv +test_patient7.tsv ENSG00000187720 THSD4 0.0072071766087168435 0.7015622436312373 0.010273039454650523 0.010326171321546436 0.0 chr15:G_71771107_A|CS|3.5644|P|test_patient7.tsv&chr15:G_71531803_T|IS|0.17|M|test_patient7.tsv +test_patient5.tsv ENSG00000184347 SLIT3 0.009314903287505708 0.4073172360516191 0.022868915093799846 0.023134465104041144 0.0 chr5:T_169077795_C|IS|0.2|P|test_patient5.tsv&chr5:A_168806478_C|CS|2.61546|M|test_patient5.tsv +test_patient5.tsv ENSG00000112159 MDN1 0.011009974667099773 0.1505575139656002 0.07312803178734317 0.07593983707286883 1.0 chr6:T_89654004_C|IS|0.49|P|test_patient5.tsv&chr6:C_89758288_T|CS|3.7985|M|test_patient5.tsv +test_patient1.tsv ENSG00000103197 TSC2 0.011309728968291386 0.3737345208652806 0.030261397695098613 0.03072872596144594 0.0 chr16:G_2062557_A|CS|3.33142|P|test_patient1.tsv&chr16:C_2056759_G|CS|3.4387|M|test_patient1.tsv +test_patient5.tsv ENSG00000166833 NAV2 0.012477089676526937 0.400135242513416 0.03118218129988537 0.03167869436479569 0.0 chr11:T_19718559_G|IS|0.2|P|test_patient5.tsv&chr11:C_19934094_T|CS|3.41417|M|test_patient5.tsv +test_patient1.tsv,test_patient9.tsv ENSG00000164199 ADGRV1 0.013552668541129229 0.16161873948379835 0.08385579905161822 0.08758150208182405 1.0 chr5:C_90629537_A|CS|2.02571|P|test_patient1.tsv&chr5:A_90778464_G|CS|3.70419|M|test_patient1.tsv,chr5:G_90763365_T|CS|3.01374|P|test_patient9.tsv&chr5:C_90855803_A|CS|3.95323|M|test_patient9.tsv +test_patient5.tsv ENSG00000131149 GSE1 0.017789435898676934 0.926884726113861 0.01919271663183242 0.019379287881425098 0.0 chr16:C_85654404_G|CS|1.72958|P|test_patient5.tsv&chr16:A_85616904_G|IS|0.24|M|test_patient5.tsv +test_patient9.tsv ENSG00000164061 BSN 0.02189216610667306 0.5997223022790761 0.03650383856574624 0.03718677511670675 0.0 chr3:G_49656797_A|CS|3.88631|P|test_patient9.tsv&chr3:C_49661891_T|CS|2.49044|M|test_patient9.tsv +test_patient3.tsv ENSG00000149256 TENM4 0.02695407659716365 0.6879857864620426 0.03917824630618405 0.03996636724263877 0.0 chr11:C_79116852_T|IS|0.38|P|test_patient3.tsv&chr11:G_79064959_T|CS|2.62637|M|test_patient3.tsv +test_patient6.tsv ENSG00000163359 COL6A3 0.02865347639163457 0.8514638607999415 0.03365201708586307 0.034231278877165476 0.0 chr2:A_237324784_G|CS|1.87558|P|test_patient6.tsv&chr2:C_237327211_A|IS|0.26|M|test_patient6.tsv +test_patient2.tsv ENSG00000054654 SYNE2 0.028854977229636012 0.3899308411757089 0.07400024358840984 0.0768813073904305 1.0 chr14:G_64224488_A|CS|2.91873|P|test_patient2.tsv&chr14:C_64209453_G|CS|3.1526|M|test_patient2.tsv +test_patient7.tsv ENSG00000130702 LAMA5 0.03897947849007256 0.5829504926342018 0.06686584707036514 0.06920630183697957 1.0 chr20:A_62311050_C|CS|3.41239|P|test_patient7.tsv&chr20:G_62312300_A|CS|2.50571|M|test_patient7.tsv +test_patient4.tsv ENSG00000142798 HSPG2 0.07929217469578631 0.6766589144682678 0.1171818962262482 0.12463609758989856 1.0 chr1:C_21833508_T|CS|3.21122|P|test_patient4.tsv&chr1:C_21880484_T|CS|2.52561|M|test_patient4.tsv +test_patient1.tsv,test_patient4.tsv,test_patient5.tsv,test_patient7.tsv ENSG00000155657 TTN 0.14721405202170884 0.16050998305858694 0.9171644605306262 2.490898089035142 5.0 chr2:A_178573986_G|CS|3.52354|P|test_patient1.tsv&chr2:C_178782896_T|CS|3.22483|M|test_patient1.tsv,chr2:C_178728283_A|CS|2.79666|P|test_patient4.tsv&chr2:T_178597640_C|CS|1.70749|M|test_patient4.tsv,chr2:G_178586727_A|CS|3.72524|P|test_patient5.tsv&chr2:G_178630241_A|CS|3.13464|M|test_patient5.tsv,chr2:G_178532670_A|CS|16.7948|P|test_patient7.tsv&chr2:C_178718186_T|CS|2.65789|M|test_patient7.tsv +test_patient2.tsv ENSG00000154358 OBSCN 0.23368614253709996 0.9604412719396987 0.2433112251258731 0.2788032397063109 1.0 chr1:G_228280211_T|CS|3.41403|P|test_patient2.tsv&chr1:C_228309111_G|CS|1.6097|M|test_patient2.tsv diff --git a/test/output/test_comphet_individual_level.txt b/test/output/test_comphet_individual_level.txt new file mode 100644 index 0000000..4b10772 --- /dev/null +++ b/test/output/test_comphet_individual_level.txt @@ -0,0 +1,10 @@ +file_name ensembl_gene_id gene_name P_val P_cond y_stat poisson_lambda variant_info +test_patient1.tsv ENSG00000103197 TSC2 0.8805262468318172 0.9037104556163108 0.5800264118709461 3.663037625547644 chr16:G_2062557_A|CS|3.33142|P|test_patient1.tsv&chr16:C_2056759_G|CS|3.4387|M|test_patient1.tsv +test_patient2.tsv ENSG00000010318 PHF7 0.16085670053023618 0.16175438590073787 0.033764592462501825 5.194014687316723 chr3:G_52422746_T|IS|0.2|P|test_patient2.tsv&chr3:T_52422267_A|CS|6.58568|M|test_patient2.tsv +test_patient3.tsv ENSG00000008226 DLEC1 0.8562956915370973 0.8623243118350665 0.3908831825752294 4.963113253481458 chr3:G_38117210_A|IS|0.25|P|test_patient3.tsv&chr3:G_38116772_T|IS|0.81|M|test_patient3.tsv +test_patient4.tsv ENSG00000114656 CFAP92 0.2646588887467117 0.2671156302705057 0.06556427892050695 4.6888457487416195 chr3:C_128970364_G|IS|0.39|P|test_patient4.tsv&chr3:C_128970364_G|IS|0.39|M|test_patient4.tsv +test_patient5.tsv ENSG00000101220 C20orf27 0.021496499411909818 0.021732007478409074 0.004802628289345945 4.524796286270406 chr20:G_3754424_A|CS|3.90395|P|test_patient5.tsv&chr20:G_3761023_C|IS|0.63|M|test_patient5.tsv +test_patient6.tsv ENSG00000159216 RUNX1 0.24523827437376353 0.2474227340920225 0.05948609868786205 4.729729818341644 chr21:T_34834592_A|CS|3.95425|P|test_patient6.tsv&chr21:C_34880568_T|CS|4.44113|M|test_patient6.tsv +test_patient7.tsv ENSG00000145916 RMND5B 0.2638358237441326 0.26720706926225035 0.07004807174401698 4.372741632103667 chr5:G_178138183_GGGCAGCACT|CI|2.645243|P|test_patient7.tsv&chr5:G_178146273_A|CS|2.96878|M|test_patient7.tsv +test_patient8.tsv ENSG00000186806 VSIG10L 0.08110054269891298 0.08178160020462166 0.017664103261028106 4.788160815292933 chr19:C_51341368_T|CS|3.94935|P|test_patient8.tsv&chr19:G_51338205_T|CS|3.82217|M|test_patient8.tsv +test_patient9.tsv ENSG00000080293 SCTR 0.010189456342487475 0.01029704494587668 0.002245353255283013 4.561297508934969 chr2:G_119452036_A|CS|4.43205|P|test_patient9.tsv&chr2:G_119452036_A|CS|4.43205|M|test_patient9.tsv diff --git a/test/output/test_comphet_mutational_targets.txt b/test/output/test_comphet_mutational_targets.txt new file mode 100644 index 0000000..159cbe3 --- /dev/null +++ b/test/output/test_comphet_mutational_targets.txt @@ -0,0 +1,49 @@ +# Compound heterozygous mutational targets computed for processed variant files in test/input/ +# variant types are in the format paternal_variant_type,maternal_variant_type +variant_type ensembl_gene_id per_patient_mutational_targets +IS,CS ENSG00000131697 0.3260042015110388 +CS,CS ENSG00000142798 0.6592794640361354 +CS,IS ENSG00000132849 0.152720854388882 +CS,CS ENSG00000154358 0.954520885815634 +CS,CS ENSG00000138002 0.3794763008048035 +CS,CS ENSG00000135624 0.47886894650201167 +CS,CS ENSG00000080293 0.021284615867876524 +IS,IS ENSG00000091428 0.6742448592678627 +CS,CS ENSG00000155657 0.18437758707551505 +CS,CS ENSG00000155657 0.9409320231226761 +CS,CS ENSG00000155657 0.2346752253595933 +CS,CS ENSG00000155657 0.4300563552308008 +CS,IS ENSG00000163359 0.8490873358262157 +IS,IS ENSG00000008226 0.3234678521264028 +CS,CS ENSG00000164061 0.5937237755612464 +IS,CS ENSG00000010318 0.5157826182381667 +IS,CS ENSG00000173193 0.19830912689664312 +IS,IS ENSG00000114656 0.08637555828441287 +CS,CS ENSG00000114770 0.08804346711580001 +CS,IS ENSG00000121210 0.8480575778847543 +CS,CS ENSG00000164199 0.7609341566695156 +CS,CS ENSG00000164199 0.3792004097206957 +IS,CS ENSG00000184347 0.4024764882783488 +CI,CS ENSG00000145916 0.454913048644159 +IS,CS ENSG00000112159 0.1318848358182284 +IS,IS ENSG00000196591 0.8813204679326655 +CI,CS ENSG00000218823 0.5289256198347109 +CS,CS ENSG00000055118 0.5914872257725904 +IS,CS ENSG00000215262 0.1750497641754769 +IS,CS ENSG00000164934 0.9027643280397302 +CS,CS ENSG00000197748 0.7839107511680166 +CS,CS ENSG00000156395 0.3852068743568498 +IS,CS ENSG00000166833 0.3934525283906666 +CS,CS ENSG00000068976 0.9462453823413233 +IS,CS ENSG00000149256 0.6826743975891878 +CS,CS ENSG00000054654 0.3734526220921216 +CS,CS ENSG00000188779 0.8129857043998733 +CS,IS ENSG00000187720 0.7002481468833333 +CS,CS ENSG00000103197 0.36709691817894835 +CS,IS ENSG00000103196 0.17934202598203886 +CS,IS ENSG00000131149 0.9261983632213022 +CS,CS ENSG00000105219 0.9609401849054968 +CS,CS ENSG00000186806 0.047815981254394596 +CS,IS ENSG00000101220 0.11163568005357706 +CS,CS ENSG00000130702 0.571369914575868 +CS,CS ENSG00000159216 0.16905291400653366 diff --git a/test/output/test_comphet_variant_counts.txt b/test/output/test_comphet_variant_counts.txt new file mode 100644 index 0000000..9e0632b --- /dev/null +++ b/test/output/test_comphet_variant_counts.txt @@ -0,0 +1,19 @@ +# Sum (across cohort) of all products of (# paternally-inherited variants)x(# maternally-inherited variants) for each variant type pair +# Variant input files processed from: test/input/ +paternal_variant_type maternal_variant_type total_product_of_variant_counts +CS CS 155313 +CS CI 6949 +CS IS 55883 +CS II 3968 +CI CS 8876 +CI CI 414 +CI IS 3309 +CI II 220 +IS CS 60783 +IS CI 2727 +IS IS 21945 +IS II 1484 +II CS 2405 +II CI 112 +II IS 886 +II II 64 diff --git a/test/output/test_comphet_variant_distribution.txt b/test/output/test_comphet_variant_distribution.txt new file mode 100644 index 0000000..6e88777 --- /dev/null +++ b/test/output/test_comphet_variant_distribution.txt @@ -0,0 +1,58 @@ +# Variant count distribution computed from input variant files in test/input/ +# variant_annotations: CI +# CADD_threshold: 1.5 +# SpliceAI_threshold: 0.15 +inheritance variant_type variant_count number_samples +P CS 103 1 +P CS 116 1 +P CS 129 1 +P CS 130 1 +P CS 133 1 +P CS 136 2 +P CS 140 1 +P CS 142 1 +P CI 3 1 +P CI 5 2 +P CI 7 1 +P CI 8 1 +P CI 9 1 +P CI 10 3 +P IS 41 1 +P IS 43 1 +P IS 45 1 +P IS 46 1 +P IS 50 1 +P IS 52 2 +P IS 61 1 +P IS 68 1 +P II 1 4 +P II 2 3 +P II 3 1 +P II 5 1 +M CS 121 2 +M CS 124 1 +M CS 125 1 +M CS 129 1 +M CS 130 1 +M CS 146 2 +M CS 158 1 +M CI 2 1 +M CI 4 1 +M CI 5 3 +M CI 6 1 +M CI 8 2 +M CI 10 1 +M IS 36 1 +M IS 42 2 +M IS 47 1 +M IS 48 1 +M IS 49 1 +M IS 53 1 +M IS 56 1 +M IS 60 1 +M II 1 1 +M II 2 2 +M II 3 2 +M II 4 2 +M II 5 1 +M II 6 1 diff --git a/test/output/test_comphet_variant_product_distribution.txt b/test/output/test_comphet_variant_product_distribution.txt new file mode 100644 index 0000000..832e3b4 --- /dev/null +++ b/test/output/test_comphet_variant_product_distribution.txt @@ -0,0 +1,139 @@ +# Number of input variant files with specific (paternal_variant_count)x(maternal_variant_count) values +# Variant input files processed from: test/input/ +paternal_variant_type maternal_variant_type product_of_variant_counts number_samples +CS CS 12463 1 +CS CS 16120 1 +CS CS 16456 1 +CS CS 16770 1 +CS CS 17000 1 +CS CS 18318 1 +CS CS 18328 1 +CS CS 19418 1 +CS CS 20440 1 +CS CI 272 1 +CS CI 412 1 +CS CI 580 1 +CS CI 645 1 +CS CI 700 1 +CS CI 816 1 +CS CI 1040 1 +CS CI 1064 1 +CS CI 1420 1 +CS IS 4896 1 +CS IS 5047 1 +CS IS 5568 1 +CS IS 5880 1 +CS IS 5964 1 +CS IS 6063 1 +CS IS 7049 1 +CS IS 7616 1 +CS IS 7800 1 +CS II 116 1 +CS II 258 1 +CS II 260 1 +CS II 309 1 +CS II 408 1 +CS II 544 1 +CS II 568 1 +CS II 665 1 +CS II 840 1 +CI CS 375 1 +CI CS 730 1 +CI CS 790 1 +CI CS 847 1 +CI CS 968 1 +CI CS 1116 1 +CI CS 1290 1 +CI CS 1300 1 +CI CS 1460 1 +CI CI 16 1 +CI CI 18 1 +CI CI 25 2 +CI CI 28 1 +CI CI 50 1 +CI CI 72 1 +CI CI 80 1 +CI CI 100 1 +CI IS 108 1 +CI IS 210 1 +CI IS 240 1 +CI IS 343 1 +CI IS 420 1 +CI IS 448 1 +CI IS 470 1 +CI IS 530 1 +CI IS 540 1 +CI II 5 1 +CI II 12 1 +CI II 18 1 +CI II 20 1 +CI II 21 1 +CI II 24 1 +CI II 30 1 +CI II 40 1 +CI II 50 1 +IS CS 5203 1 +IS CS 5934 1 +IS CS 5986 1 +IS CS 6050 1 +IS CS 6570 1 +IS CS 6760 1 +IS CS 7564 1 +IS CS 8216 1 +IS CS 8500 1 +IS CI 86 1 +IS CI 200 1 +IS CI 205 1 +IS CI 260 2 +IS CI 360 1 +IS CI 408 1 +IS CI 460 1 +IS CI 488 1 +IS IS 1722 1 +IS IS 1932 1 +IS IS 2385 1 +IS IS 2408 1 +IS IS 2444 1 +IS IS 2448 1 +IS IS 2450 1 +IS IS 2496 1 +IS IS 3660 1 +IS II 52 1 +IS II 104 1 +IS II 122 1 +IS II 129 1 +IS II 150 1 +IS II 184 1 +IS II 225 1 +IS II 246 1 +IS II 272 1 +II CS 121 1 +II CS 129 1 +II CS 146 1 +II CS 158 1 +II CS 248 1 +II CS 250 1 +II CS 260 1 +II CS 363 1 +II CS 730 1 +II CI 2 1 +II CI 5 2 +II CI 10 2 +II CI 12 2 +II CI 16 1 +II CI 40 1 +II IS 42 2 +II IS 48 1 +II IS 56 1 +II IS 72 1 +II IS 94 1 +II IS 120 1 +II IS 147 1 +II IS 265 1 +II II 1 1 +II II 3 1 +II II 4 3 +II II 6 1 +II II 8 1 +II II 9 1 +II II 25 1 diff --git a/test/output/test_denovo_cohort_recurrence.txt b/test/output/test_denovo_cohort_recurrence.txt new file mode 100644 index 0000000..46a3e32 --- /dev/null +++ b/test/output/test_denovo_cohort_recurrence.txt @@ -0,0 +1,38 @@ +file_names ensembl_gene_id gene_name Q_val P_val P_cond P_dnv poisson_lambda false_diag_rate s_het_weight variant_info FDR_0.05 FDR_0.1 +test_patient3.tsv ENSG00000164442 CITED2 1.1225213362877478e-05 3.7704660704731225e-05 0.07297088915531116 0.0005167082536774448 0.000516841793389824 0.0 3.358925971903842 chr6:T_139373244_G|CS|4.501419|DN|test_patient3.tsv False False +test_patient7.tsv ENSG00000111481 COPZ1 1.7100473064177582e-05 5.743922310710815e-05 0.05878967962409223 0.0009770290206441157 0.00097750662461168 0.0 3.358925971903842 chr12:T_54340617_C|IS|0.78|DN|test_patient7.tsv False False +test_patient6.tsv ENSG00000124766 SOX4 2.5556239973986446e-05 2.5556239973986446e-05 0.021380074670386093 0.001195329781021992 0.001196044757476558 0.0 1.0 chr6:C_21595574_A|CS|6.901804|DN|test_patient6.tsv False False +test_patient5.tsv ENSG00000183576 SETD3 7.746559227189386e-05 7.787924242602353e-05 0.025176757289436493 0.0030932991699729184 0.00309809330887371 0.0 1.0053397920547462 chr14:G_99405350_A|CS|7.900505|DN|test_patient5.tsv False False +test_patient7.tsv ENSG00000124151 NCOA3 8.132195528660304e-05 8.175619761731887e-05 0.020685092166728595 0.003952421239332038 0.003960252698453242 0.0 1.0053397920547462 chr20:C_47652438_T|CS|7.96412|DN|test_patient7.tsv False False +test_patient9.tsv ENSG00000171136 RLN3 0.0001442615473181361 6.62941093235379e-05 0.11430042693822379 0.0005799987900252379 0.0005801670543887152 0.0 0.45954109432461093 chr19:C_14030829_T|CS|5.620277|DN|test_patient9.tsv False False +test_patient6.tsv ENSG00000059588 TARBP1 0.00015945486665924394 7.087397016200158e-05 0.013871657381356636 0.0051092647557209325 0.005122361678368999 0.0 0.44447668263057594 chr1:C_234463846_A|CS|8.807564|DN|test_patient6.tsv False False +test_patient7.tsv ENSG00000165269 AQP7 0.0002045181780989752 9.414758054934992e-05 0.5035196654696817 0.0001869789543602618 0.00018699643710422004 0.0 0.46033844729336393 chr9:C_33387008_T|CS|3.379604|DN|test_patient7.tsv False False +test_patient1.tsv ENSG00000196453 ZNF777 0.00030027718432374496 0.001008608833195184 0.4312495530939381 0.0023388055151803977 0.0023415447927244413 0.0 3.358925971903842 chr7:T_149435944_C|IS|0.09|DN|test_patient1.tsv False False +test_patient1.tsv ENSG00000132463 GRSF1 0.0003240999548749789 0.00014405487278354998 0.09190799511412717 0.0015673812991423564 0.0015686109262417558 0.0 0.44447668263057594 chr4:T_70833298_C|IS|0.85|DN|test_patient1.tsv False False +test_patient3.tsv ENSG00000118503 TNFAIP3 0.0003696444452180436 0.0012416083274128737 0.579426746397738 0.002142821909985826 0.0021451210378563117 0.0 3.358925971903842 chr6:C_137874865_G|CS|2.903065|DN|test_patient3.tsv False False +test_patient8.tsv ENSG00000204688 OR2H1 0.00043541154277197203 0.0004377365498686106 0.8546225994666515 0.0005121986595507666 0.0005123298780927682 0.0 1.0053397920547462 chr6:G_29462672_T|CS|1.10432|DN|test_patient8.tsv False False +test_patient4.tsv ENSG00000001629 ANKIB1 0.0004432950873817894 0.0014889953822240754 0.46352464541422117 0.0032123327140317626 0.0032175033308949903 0.0 3.358925971903842 chr7:A_92322367_C|IS|0.12|DN|test_patient4.tsv False False +test_patient3.tsv ENSG00000154845 PPP4R1 0.0004908406641759278 0.0008071349489513891 0.23080580192160985 0.003497030586889327 0.0035031594911677693 0.0 1.6443929932058252 chr18:G_9595069_A|CS|4.221749|DN|test_patient3.tsv False False +test_patient1.tsv ENSG00000183807 FAM162B 0.0005241531369291328 0.00026944769161210214 0.36366178154895157 0.0007409293615194823 0.0007412039853384816 0.0 0.5140629190749885 chr6:C_116752685_T|CS|3.091688|DN|test_patient1.tsv False False +test_patient3.tsv ENSG00000155621 C9orf85 0.0005765689573410236 0.0002654168585799206 0.2348165207082366 0.0011303159495736903 0.001130955238424308 0.0 0.46033844729336393 chr9:T_71918407_A|IS|0.21|DN|test_patient3.tsv False False +test_patient2.tsv ENSG00000155463 OXA1L 0.0007728259776332096 0.0003435031267891407 0.24604612792282798 0.0013960923900289135 0.0013970678349895806 0.0 0.44447668263057594 chr14:G_22771094_A|CS|3.97604|DN|test_patient2.tsv False False +test_patient8.tsv ENSG00000147526 TACC1 0.0009390626877079542 0.0005128824774566592 0.18737475420524657 0.002737201602382666 0.0027409545887065287 0.0 0.5461642595006012 chr8:G_38846799_C|CS|4.306055|DN|test_patient8.tsv False False +test_patient6.tsv ENSG00000124659 TBCC 0.0010142003473439791 0.0005213627910825131 0.8348159312306526 0.0006245242472959767 0.0006247193437963093 0.0 0.5140629190749885 chr6:C_42745605_A|CS|1.502626|DN|test_patient6.tsv False False +test_patient5.tsv ENSG00000111012 CYP27B1 0.0011857530924368833 0.0006095516960002989 0.4399322763014761 0.0013855580252597477 0.0013865187983542414 0.0 0.5140629190749885 chr12:G_57765517_C|IS|0.12|DN|test_patient5.tsv False False +test_patient1.tsv ENSG00000173482 PTPRM 0.001229886759803811 0.0020224171702580025 0.17452812662863215 0.011587915422717976 0.011655578538860494 0.0 1.6443929932058252 chr18:G_8377224_A|IS|0.21|DN|test_patient1.tsv False False +test_patient4.tsv ENSG00000172428 COPS9 0.0014326045170556824 0.0008480320205112429 0.8542226862849067 0.000992752866584956 0.0009932459720936036 0.0 0.5919512401469564 chr2:A_240133860_G|IS|0.06|DN|test_patient4.tsv False False +test_patient3.tsv ENSG00000132704 FCRL2 0.001433836913804302 0.0006589069844526518 0.43752752947016255 0.0015059783443811536 0.0015071134695604732 0.0 0.45954109432461093 chr1:G_157768617_A|CS|1.923312|DN|test_patient3.tsv False False +test_patient5.tsv ENSG00000187912 CLEC17A 0.0018656802815210111 0.0009590770515793373 0.8368785043893019 0.0011460170700395844 0.0011466742497427658 0.0 0.5140629190749885 chr19:G_14586841_A|IS|0.06|DN|test_patient5.tsv False False +test_patient5.tsv ENSG00000136842 TMOD1 0.0018672527956897144 0.001877223537332341 0.9936487721645217 0.0018892224193495233 0.0018910092508605551 0.0 1.0053397920547462 chr9:A_97564120_G|CS|1.013321|DN|test_patient5.tsv False False +test_patient4.tsv ENSG00000277363 SRCIN1 0.0018782118230699185 0.006308774473246413 0.9999999894580844 0.0063087745397529815 0.0063287589536283936 0.0 3.358925971903842 chr17:C_38540521_T|IS|0.05|DN|test_patient4.tsv False False +test_patient9.tsv ENSG00000138593 SECISBP2L 0.0018881277889329475 0.001117679586214789 0.3649439180667603 0.0030626064194617664 0.0030673057958483362 0.0 0.5919512401469564 chr15:G_48999940_C|CS|3.886618|DN|test_patient9.tsv False False +test_patient5.tsv ENSG00000169925 BRD3 0.0023357161519041293 0.00227537634733935 0.6671410001641104 0.0034106378513382163 0.0034164673352278284 0.0 0.9741664651693277 chr9:GCTTCTC_134040146_G|CI|1.925244|DN|test_patient5.tsv False False +test_patient2.tsv ENSG00000065526 SPEN 0.0024307447961973423 0.008164691827017364 0.8870583254891697 0.009204233354683788 0.009246854039245524 0.0 3.358925971903842 chr1:A_15930310_G|CS|1.514843|DN|test_patient2.tsv False False +test_patient7.tsv ENSG00000146592 CREB5 0.0032520420816577254 0.0031680303392704087 0.6735079005848893 0.004703776060413278 0.004714873629020252 0.0 0.9741664651693277 chr7:T_28736872_A|IS|0.07|DN|test_patient7.tsv False False +test_patient7.tsv ENSG00000101246 ARFRP1 0.0037865958427979966 0.0016830535586695834 0.99999952729133 0.0016830543542639687 0.0016844722814326803 0.0 0.44447668263057594 chr20:T_63706789_A|IS|0.05|DN|test_patient7.tsv False False +test_patient6.tsv ENSG00000018280 SLC11A1 0.003908611007437514 0.0017961673796470555 0.6178998538231351 0.0029068907664140387 0.0029111239790260883 0.0 0.45954109432461093 chr2:A_218394153_T|CS|3.225004|DN|test_patient6.tsv False False +test_patient2.tsv ENSG00000081052 COL4A4 0.004137324696080427 0.0022596588789483164 0.3996983617679566 0.005653410409172888 0.005669451419980639 0.0 0.5461642595006012 chr2:G_227089988_C|IS|0.13|DN|test_patient2.tsv False False +test_patient6.tsv ENSG00000092445 TYRO3 0.00422104266598715 0.0023053826419893154 0.8620093029320408 0.0026744289581884795 0.0026780116324788793 0.0 0.5461642595006012 chr15:G_41569017_A|CS|1.878325|DN|test_patient6.tsv False False +test_patient8.tsv ENSG00000038295 TLL1 0.0053321400412987665 0.0053606125603260875 0.9999999935400137 0.005360612594955572 0.005375032233803562 0.0 1.0053397920547462 chr4:A_166001171_G|IS|0.05|DN|test_patient8.tsv False False +test_patient5.tsv ENSG00000181215 C4orf50 0.005891841707786448 0.002712241263460695 0.8366235874156552 0.0032418895477700493 0.0032471558566313347 0.0 0.46033844729336393 chr4:A_6131852_G|IS|0.06|DN|test_patient5.tsv False False +test_patient2.tsv ENSG00000116117 PARD3B 0.011808969694697578 0.006449637188769544 0.5126066671744778 0.012582039215994545 0.012661863345085345 0.0 0.5461642595006012 chr2:T_205370483_G|IS|0.09|DN|test_patient2.tsv False False diff --git a/test/output/test_denovo_mutational_targets.txt b/test/output/test_denovo_mutational_targets.txt new file mode 100644 index 0000000..6690c7c --- /dev/null +++ b/test/output/test_denovo_mutational_targets.txt @@ -0,0 +1,39 @@ +# Mutational targets computed from input variant files located in: test/input/ +variant_type ensembl_gene_id per_patient_mutational_targets +CS ENSG00000065526 0.11343568252678941 +CS ENSG00000132704 0.562776827353471 +CS ENSG00000059588 0.9874090605678529 +CS ENSG00000018280 0.38255033557047136 +CS ENSG00000124766 0.9789188209326051 +CS ENSG00000204688 0.14541189547932318 +CS ENSG00000124659 0.1652313473733675 +CS ENSG00000183807 0.636498942198312 +CS ENSG00000118503 0.4209296375656072 +CS ENSG00000164442 0.9271575992471726 +CS ENSG00000147526 0.8132865944571146 +CS ENSG00000165269 0.4965152266874578 +CS ENSG00000136842 0.006356621367645126 +CS ENSG00000155463 0.7542820439623226 +CS ENSG00000183576 0.9755974174076331 +CS ENSG00000092445 0.1381628510141465 +CS ENSG00000138593 0.6357210595449088 +CS ENSG00000154845 0.7700236325844929 +CS ENSG00000171136 0.8858426767313413 +CS ENSG00000124151 0.9803047762882531 +CI ENSG00000169925 0.33333333333333326 +IS ENSG00000116117 0.4897322455825549 +IS ENSG00000081052 0.601493553187644 +IS ENSG00000172428 0.1458442878676341 +IS ENSG00000181215 0.1636202186820383 +IS ENSG00000132463 0.9084808891779244 +IS ENSG00000038295 0.0 +IS ENSG00000146592 0.327136824324322 +IS ENSG00000001629 0.5371072409239045 +IS ENSG00000196453 0.5692271390714053 +IS ENSG00000155621 0.765450462609335 +IS ENSG00000111481 0.941453868100257 +IS ENSG00000111012 0.5603470170701385 +IS ENSG00000277363 0.0 +IS ENSG00000173482 0.8282999168274087 +IS ENSG00000187912 0.16320719989783108 +IS ENSG00000101246 0.0 diff --git a/test/output/test_denovo_variant_counts.txt b/test/output/test_denovo_variant_counts.txt new file mode 100644 index 0000000..eb056b5 --- /dev/null +++ b/test/output/test_denovo_variant_counts.txt @@ -0,0 +1,6 @@ +# De novo mutation count by variant type across cohort +inheritance variant_type denovo_mutation_count +DN CS 20 +DN CI 1 +DN IS 16 +DN II 0 diff --git a/test/output/test_denovo_variant_distribution.txt b/test/output/test_denovo_variant_distribution.txt new file mode 100644 index 0000000..35c1ded --- /dev/null +++ b/test/output/test_denovo_variant_distribution.txt @@ -0,0 +1,17 @@ +# Variant count distribution computed from input variant files in test/input/ +# variant_annotations: CI +# CADD_threshold: 0.5 +# SpliceAI_threshold: 0.05 +inheritance variant_type variant_count number_samples +DN CS 0 1 +DN CS 1 1 +DN CS 2 5 +DN CS 4 1 +DN CS 5 1 +DN CI 0 8 +DN CI 1 1 +DN IS 0 2 +DN IS 1 2 +DN IS 2 1 +DN IS 3 4 +DN II 0 9