OneKGPd

syntax = "proto3"; package org.dnaerys.cluster.grpc; option java_multiple_files = true; option java_outer_classname = "DnaerysProto"; service DnaerysService { rpc Health (HealthRequest) returns (HealthResponse) {} rpc ClusterNodes (ClusterNodesRequest) returns (ClusterNodesResponse) {} // dataset info rpc DatasetInfo (DatasetInfoRequest) returns (DatasetInfoResponse) {} // Variant selection // Beacon Service rpc Beacon (BeaconRequest) returns (BeaconResponse) {} // selects variants in all samples in a single region // returns stream of unique non-empty sets of unique variants rpc SelectVariantsInRegion (AllelesInRegionRequest) returns (stream AllelesResponse) {} // counts variants in all samples in a single region based on selection criteria // returns # of unique variants rpc CountVariantsInRegion (CountAllelesInRegionRequest) returns (CountAllelesResponse) {} // selects variants in provided samples in a single region // returns stream of unique non-empty sets of unique variants rpc SelectVariantsInRegionInSamples (AllelesInRegionInSamplesRequest) returns (stream AllelesResponse) {} // counts variants in provided samples in a single region based on selection criteria // returns # of unique variants rpc CountVariantsInRegionInSamples (CountAllelesInRegionInSamplesRequest) returns (CountAllelesResponse) {} // selects variants in provided samples in a single region // returns stream of unique non-empty sets of unique variants with VC stats rpc SelectVariantsInRegionInSamplesWithStats (AllelesInRegionInSamplesRequest) returns (stream AllelesWithStatsResponse) {} // Bracket Queries // selects variants in all samples in a single region // with hard requirements for alleles start and end positions // typical use case - SV // see GA4GH Beacon Bracket Queries // https://docs.genomebeacons.org/variant-queries/#beacon-bracket-queries // returns stream of unique non-empty sets of unique variants rpc SelectVariantsInBracket (AllelesInBracketRequest) returns (stream AllelesResponse) {} // Bracket Queries // counts variants in all samples in a single region // with hard requirements for alleles start and end positions // typical use case - SV // see GA4GH Beacon Bracket Queries // https://docs.genomebeacons.org/variant-queries/#beacon-bracket-queries // returns # of unique variants rpc CountVariantsInBracket (CountAllelesInBracketRequest) returns (CountAllelesResponse) {} // Bracket Queries // selects variants in provided samples in a single region // with hard requirements for alleles start and end positions // typical use case - SV // see GA4GH Beacon Bracket Queries // https://docs.genomebeacons.org/variant-queries/#beacon-bracket-queries // returns stream of unique non-empty sets of unique variants rpc SelectVariantsInBracketInSamples (AllelesInBracketInSamplesRequest) returns (stream AllelesResponse) {} // Bracket Queries // counts variants in provided samples in a single region // with hard requirements for alleles start and end positions // typical use case - SV // see GA4GH Beacon Bracket Queries // https://docs.genomebeacons.org/variant-queries/#beacon-bracket-queries // returns # of unique variants rpc CountVariantsInBracketInSamples (CountAllelesInBracketInSamplesRequest) returns (CountAllelesResponse) {} // selects variants in all samples in multiple regions // regions can intersect or duplicate, returned variants are still unique and skip & limit are still obeyed // returns stream of unique non-empty sets of unique variants rpc SelectVariantsInMultiRegions (AllelesInMultiRegionsRequest) returns (stream AllelesResponse) {} // counts variants in all samples in multiple regions // regions can intersect or duplicate // returns # of unique variants rpc CountVariantsInMultiRegions (CountAllelesInMultiRegionsRequest) returns (CountAllelesResponse) {} // selects variants in all samples in multiple regions // regions can intersect or duplicate, returned variants are still unique and skip & limit are still obeyed // returns stream of unique non-empty sets of unique variants with F-statistics rpc SelectVariantsInMultiRegionsWithStats (AllelesInMultiRegionsRequest) returns (stream AllelesWithStatsResponse) {} // selects variants in provided samples in multiple regions // regions can intersect or duplicate, returned variants are still unique and skip & limit are still obeyed // returns stream of unique non-empty sets of unique variants rpc SelectVariantsInMultiRegionsInSamples (AllelesInMultiRegionsInSamplesRequest) returns (stream AllelesResponse) {} // counts variants in provided samples in multiple regions // regions can intersect or duplicate // returns # of unique variants rpc CountVariantsInMultiRegionsInSamples (CountAllelesInMultiRegionsInSamplesRequest) returns (CountAllelesResponse) {} // selects variants in provided samples in multiple regions // regions can intersect or duplicate, returned variants are still unique and skip & limit are still obeyed // returns stream of unique non-empty sets of unique variants with VC stats rpc SelectVariantsInMultiRegionsInSamplesWithStats (AllelesInMultiRegionsInSamplesRequest) returns (stream AllelesWithStatsResponse) {} // selects all variants in all samples in a panel // returns stream of unique non-empty sets of unique variants rpc SelectVariantsInPanel (AllelesInPanelRequest) returns (stream AllelesResponse) {} // selects top N variants with the most significant p-value for Chi-squared test for deviation from // Hardy-Weinberg Equilibrium across all variants. // Autosomal + X chromosome outside PAR and biallelic SNVs only. // On X chromosome outside PAR calculated according to: // "Testing for Hardy-Weinberg equilibrium at biallelic genetic markers on the X chromosome" J Graffelman, BS Weir // https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4868269/ // selection order of variants with identical p-value is undefined rpc TopNHWE (TopNHWERequest) returns (AllelesWithStatsResponse) {} // selects top N variants with the most significant p-value in Pearson's chi-squared test // with provided samples as cases and the rest of cohort as controls // selection order of variants with identical p-value is undefined rpc TopNchi2 (TopNchi2Request) returns (AllelesWithStatsResponse) {} // Sample selection // selects samples with variants in a region rpc SelectSamplesInRegion (SamplesInRegionRequest) returns (SamplesResponse) {} // counts samples with variants in a region // returns # of unique samples rpc CountSamplesInRegion (SamplesInRegionRequest) returns (CountSamplesResponse) {} // selects samples with variants in regions rpc SelectSamplesInMultiRegions (SamplesInMultiRegionsRequest) returns (SamplesResponse) {} // counts samples with variants in regions // returns # of unique samples rpc CountSamplesInMultiRegions (SamplesInMultiRegionsRequest) returns (CountSamplesResponse) {} // Variant selection by inheritance model // naive implementation for de novo candidate variants in proband // entirely based on existing GT calls, no specialised de novo variant calling pipeline is used // returns stream of non-empty sets of unique variants rpc SelectDeNovo (DeNovoRequest) returns (stream AllelesResponse) {} // naive implementation for heterozygous dominant candidate variants in affected child // entirely based on existing GT calls // returns stream of non-empty sets of unique variants rpc SelectHetDominant (HetDominantRequest) returns (stream AllelesResponse) {} // naive implementation for homozygous recessive candidate variants in affected child // entirely based on existing GT calls // returns stream of non-empty sets of unique variants rpc SelectHomRecessive (HomRecessiveRequest) returns (stream AllelesResponse) {} // Polygenic risk scores // PRS implements same calculations as --score in Plink rpc Prs (PRSRequest) returns (PRSResponse) {} // "reported vs observed" sex mismatch check is based on F-statistics // for deviation from expected number of homozygous alleles performed // on biallelic SNVs on X chromosome outside PAR. The same method is // used in Hail 0.2 and Plink 1.7, parameters have similar meaning. rpc SexMismatchCheck (FstatXRequest) returns (SexMismatchResponse) {} // calculates F-statistics as in SexMismatchCheck for all samples in request, // so distribution and thresholds could be evaluated rpc FstatX (FstatXRequest) returns (FstatXResponse) {} // degrees of relatedness & kinship coefficients between samples in dataset // https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3025716 // returns all pairs or filtered by degree of relatedness // can be disabled at runtime by setting "DISABLE_KINSHIP=true" env var rpc Kinship (KinshipRequest) returns (KinshipResponse) {} // degrees of relatedness & kinship coefficients between 2 samples // https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3025716 // returns degree of relatedness // can be disabled at runtime by setting "DISABLE_KINSHIP=true" env var rpc KinshipDuo (KinshipDuoRequest) returns (KinshipResponse) {} // degrees of relatedness & kinship coefficients between samples in trio // https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3025716 // returns all pairs or filtered by degree of relatedness // can be disabled at runtime by setting "DISABLE_KINSHIP_TRIO=true" env var rpc KinshipTrio (KinshipTrioRequest) returns (KinshipResponse) {} // selects samples from dataset which genetically relate to provided // sample of interest up to a certain kinship degree; // sample of interest is provided as a vcf in request; // https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3025716 // @since 1.14.3 rpc SampleKinship (SampleKinshipRequest) returns (SampleKinshipResponse) {} } // Requesting Health Status message HealthRequest {} // The response message containing Health Status message HealthResponse { string status = 1; } // Requesting Active Nodes message ClusterNodesRequest {} // Cluster Nodes states message ClusterNodesResponse { repeated string active_nodes = 1; // active nodes repeated string inactive_nodes = 2; // all nodes in any other than "up" state int32 total_nodes = 3; // total number of nodes in cluster at time of request int64 elapsed_ms = 4; // time to execute, in ms; time from receiving request to sending response } // Dataset info message DatasetInfoRequest { bool return_samples_names = 1; // whether to return samples names for each cohort } message DatasetInfoResponse { repeated Cohort cohorts = 1; int32 samples_total = 2; // total number of samples in dataset int32 females_total = 3; // total number of female samples in dataset int32 males_total = 4; // total number of male samples in dataset int32 variants_total = 5; // total number of variants in dataset RefAssembly assembly = 6; // dataset's reference assembly bool rto = 7; // dataset is in runtime optimized mode repeated PRS prs = 8; // PRS string timestamp = 9; // dataset's creation timestamp int32 data_format = 10; // data format version string notes = 11; // notes int32 rings_total = 12; // dataset's total number of rings int64 elapsed_ms = 14; // time to execute, in ms; time from receiving request to sending response string node_id = 15; // node which responses } message Cohort { string cohort_name = 1; // cohort name int32 samples_count = 2; // total number of samples in cohort int32 female_count = 3; // number of female samples in cohort int32 male_count = 4; // number of male samples in cohort repeated string female_samples_names = 5; // female sample names repeated string male_samples_names = 6; // male sample names bool synthetic = 7; // is cohort synthetic } message PRS { string name = 1; // polygenic risk scores name string desc = 2; // polygenic risk scores description int32 cardinality = 3; // number of effect alleles } // Variant selection // GA4GH Beacon message BeaconRequest { Chromosome chr = 1; int32 pos = 2; // 1-based (!) VCF position string alt = 3; // alternative allele RefAssembly assembly = 4; // reference assembly, optional; default = GRCh38 } message BeaconResponse { bool exists = 1; // indicates whether allele exists in dataset double af = 2; // AF within a cohort float ac = 3; // AC is float due to uncertainty how to count het loci in sex chromosomes in males bool incomplete_cluster = 4; // indicates response from incomplete cluster with unreachable nodes bool affected = 5; // indicates that unreachable nodes could possibly affect completeness of response int64 elapsed_ms = 6; // time to execute, in ms; time from receiving request to sending response int64 elapsed_db_ms = 7; // processing time in database engine, in ms string node_id = 8; // node which responses } /* * When Annotations passed as a parameter for variant/sample selection: * relation between different annotation fields is AND; * relation between different values for the same annotation field is OR. */ message Annotations { // types repeated VariantType vtypes = 1; // Sequence Ontology Variant classes terms repeated FeatureType ftypes = 2; // VEP features repeated BioType btypes = 3; // VEP biotypes // consequences repeated Consequence consequences = 4; // Sequence Ontology variant consequences // AF float gnomad_af_lt = 5; // select variants with gnomAD AF < gnomad_af_lt, 0 is default & has no effect float gnomad_af_gt = 6; // select variants with gnomAD AF > gnomad_af_gt, 0 is default & has no effect // impacts repeated Impact impact = 7; // VEP impacts repeated SIFT sift = 8; // SIFT prediction terms repeated PolyPhen polyphen = 9; // PolyPhen prediction terms repeated ClinSignificance clnsgn = 10; // ClinVar Clinical Significance // CADD scores // https://cadd.gs.washington.edu float cadd_raw_lt = 11; // select variants with CADD raw < cadd_raw_lt, 0 is default & has no effect float cadd_raw_gt = 12; // select variants with CADD raw > cadd_raw_gt, 0 is default & has no effect float cadd_phred_lt = 13; // select variants with CADD phred < cadd_phred_lt, 0 is default & has no effect float cadd_phred_gt = 14; // select variants with CADD phred > cadd_phred_gt, 0 is default & has no effect // AlphaMissense class // https://www.science.org/doi/10.1126/science.adg7492 repeated AlphaMissense am_class = 15; bool biallelicOnly = 16; // select only biallelic variants, exclude multiallelic } // Selects variants in all samples in region message AllelesInRegionRequest { Chromosome chr = 1; int32 start = 2; // 1-based region start position, inclusive int32 end = 3; // 1-based region end position, inclusive string ref = 4; // reference allele, optional string alt = 5; // alternative allele, optional bool hom = 6; // select homozygous alleles; NB: empty/null/false == do not select bool het = 7; // select heterozygous alleles; NB: empty/null/false == do not select Annotations ann = 8; // select by annotations, optional int32 skip = 9; // skip first n variants from result from each node, <= 0 means no skip; optional int32 limit = 10; // limit result to n variants from each node, <= 0 means 2^31-1 limit; optional RefAssembly assembly = 11; // reference assembly, optional; default = GRCh38 int32 variantMinLength = 12; // minimal alt allele length; default = 0; optional int32 variantMaxLength = 13; // maximal alt allele length; >= 1; default = Int32.MaxValue; optional } // Selects variants in all samples in a bracket // see https://docs.genomebeacons.org/variant-queries/#beacon-bracket-queries message AllelesInBracketRequest { Chromosome chr = 1; int32 start_min = 2; // 1-based start min position, inclusive int32 start_max = 3; // 1-based start max position, inclusive int32 end_min = 4; // 1-based end min position, inclusive int32 end_max = 5; // 1-based end max position, inclusive string ref = 6; // reference allele, optional string alt = 7; // alternative allele, optional bool hom = 8; // select homozygous alleles; NB: empty/null/false == do not select bool het = 9; // select heterozygous alleles; NB: empty/null/false == do not select Annotations ann = 10; // select by annotations, optional int32 skip = 11; // skip first n variants from result from each node, <= 0 means no skip; optional int32 limit = 12; // limit result to n variants from each node, <= 0 means 2^31-1 limit; optional RefAssembly assembly = 13; // reference assembly, optional; default = GRCh38 int32 variantMinLength = 14; // minimal alt allele length; default = 0; optional int32 variantMaxLength = 15; // maximal alt allele length; >= 1; default = Int32.MaxValue; optional } // Selects variants in provided samples in a bracket // see https://docs.genomebeacons.org/variant-queries/#beacon-bracket-queries message AllelesInBracketInSamplesRequest { Chromosome chr = 1; int32 start_min = 2; // 1-based start min position, inclusive int32 start_max = 3; // 1-based start max position, inclusive int32 end_min = 4; // 1-based end min position, inclusive int32 end_max = 5; // 1-based end max position, inclusive string ref = 6; // reference allele, optional string alt = 7; // alternative allele, optional bool hom = 8; // select homozygous alleles; NB: empty/null/false == do not select bool het = 9; // select heterozygous alleles; NB: empty/null/false == do not select Annotations ann = 10; // select by annotations, optional int32 skip = 11; // skip first n variants from result from each node, <= 0 means no skip; optional int32 limit = 12; // limit result to n variants from each node, <= 0 means 2^31-1 limit; optional RefAssembly assembly = 13; // reference assembly, optional; default = GRCh38 int32 variantMinLength = 14; // minimal alt allele length; default = 0; optional int32 variantMaxLength = 15; // maximal alt allele length; >= 1; default = Int32.MaxValue; optional repeated string samples = 16; // samples names as provided during ETL } // Selects variants in provided samples in region message AllelesInRegionInSamplesRequest { Chromosome chr = 1; int32 start = 2; // 1-based region start position, inclusive int32 end = 3; // 1-based region end position, inclusive string ref = 4; // reference allele, optional string alt = 5; // alternative allele, optional bool hom = 6; // select homozygous alleles; NB: empty/null/false == do not select bool het = 7; // select heterozygous alleles; NB: empty/null/false == do not select Annotations ann = 8; // select by annotations, optional int32 skip = 9; // skip first n variants from result from each node, <= 0 means no skip; optional int32 limit = 10; // limit result to n variants from each node, <= 0 means 2^31-1 limit; optional RefAssembly assembly = 11; // reference assembly, optional; default = GRCh38 repeated string samples = 12; // samples names as provided during ETL int32 variantMinLength = 13; // minimal alt allele length; default = 0; optional int32 variantMaxLength = 14; // maximal alt allele length; >= 1; default = Int32.MaxValue; optional } // Selects variants in all samples in regions message AllelesInMultiRegionsRequest { repeated Chromosome chr = 1; repeated int32 start = 2; // 1-based regions start positions, inclusive repeated int32 end = 3; // 1-based regions end positions, inclusive repeated string ref = 4; // reference allele for each region, if at all; optional repeated string alt = 5; // alternative allele for each region, if at all; optional bool hom = 6; // select homozygous alleles; NB: empty/null/false == do not select bool het = 7; // select heterozygous alleles; NB: empty/null/false == do not select Annotations ann = 8; // select by annotations, optional int32 skip = 9; // skip first n variants from result from each node, <= 0 means no skip; optional int32 limit = 10; // limit result to n variants from each node, <= 0 means 2^31-1 limit; optional RefAssembly assembly = 11; // reference assembly, optional; default = GRCh38 int32 variantMinLength = 12; // minimal alt allele length; default = 0; optional int32 variantMaxLength = 13; // maximal alt allele length; >= 1; default = Int32.MaxValue; optional } // Selects variants in provided samples in regions message AllelesInMultiRegionsInSamplesRequest { repeated Chromosome chr = 1; repeated int32 start = 2; // 1-based regions start positions, inclusive repeated int32 end = 3; // 1-based regions end positions, inclusive repeated string ref = 4; // reference allele for each region, if at all; optional repeated string alt = 5; // alternative allele for each region, if at all; optional bool hom = 6; // select homozygous alleles; NB: empty/null/false == do not select bool het = 7; // select heterozygous alleles; NB: empty/null/false == do not select Annotations ann = 8; // select by annotations, optional int32 skip = 9; // skip first n variants from result from each node, <= 0 means no skip; optional int32 limit = 10; // limit result to n variants from each node, <= 0 means 2^31-1 limit; optional RefAssembly assembly = 11; // reference assembly, optional; default = GRCh38 repeated string samples = 12; // samples names as provided during ETL int32 variantMinLength = 13; // minimal alt allele length; default = 0; optional int32 variantMaxLength = 14; // maximal alt allele length; >= 1; default = Int32.MaxValue; optional } // Selects all variants in all samples in a panel // defined for GRCh37 only, mainly for performance testing message AllelesInPanelRequest { string panel = 1; // panel name, either one of 3 known panels, GRCh37 only: // "mito11" - mitochondrial liver disease genes, 11 nuclear genes // "mito374" - mitochondrial disorder, 374 nuclear genes // "cancer104" - solid tumours cancer susceptibility, 104 genes } // Set of variants in given region(s) message AllelesResponse { repeated Variant alleles = 1; bool incomplete_cluster = 2; // indicates response from incomplete cluster with unreachable nodes bool affected = 3; // indicates that unreachable nodes could possibly affect completeness of response int64 elapsed_ms = 4; // time to execute, in ms; time from receiving request to sending response int64 elapsed_db_ms = 5; // processing time in database engine, in ms string node_id = 6; // node which responses } message Variant { Chromosome chr = 1; // chromosome name in CHR_# format, e.g. CHR_2, CHR_11, CHR_X int32 start = 2; // 1-based, inclusive int32 end = 3; // 1-based, inclusive = start for SNVs string ref = 4; // reference allele, in CAPITALS string alt = 5; // alternate allele, in CAPITALS float af = 6; // allele frequency float ac = 7; // allele count. There is some degree of uncertainty how to count heterozygous loci // in sex chromosomes in males, since the true ones exist only in PAR. // To resolve this, it is counted as 1/2 of het alleles in data outside PAR. Hence float. int32 an = 8; // allele number. Doesn't count samples with missing genotypes in data, hence specific per variant. int32 homc = 9; // homozygous alleles count int32 hetc = 10; // heterozygous alleles count int32 misc = 11; // missing aka no-call alleles count int32 homfc = 12; // homozygous alleles count in females on sex chromosomes. males counts are in homc for sex chromosomes int32 hetfc = 13; // heterozygous alleles count in females on sex chromosomes. males counts are in hetc for sex chromosomes int32 misfc = 14; // missing alleles count in females on sex chromosomes. // NB: # of female samples with missing GT is not defined in Runtime Optimized mode float gnomad_af = 15; // gnomAD AF as defined in input VCFs, = 0 if VCFs are not annotated } // Set of variants in a given region(s) with stats // NB: stats is empty if dataset is in Runtime Optimized mode message AllelesWithStatsResponse { repeated VariantWithStats alleles = 1; bool incomplete_cluster = 2; // indicates response from incomplete cluster with unreachable nodes bool affected = 3; // indicates that unreachable nodes could possibly affect completeness of response int64 elapsed_ms = 4; // time to execute, in ms; time from receiving request to sending response int64 elapsed_db_ms = 5; // processing time in database engine, in ms string node_id = 6; // node which responses } message VariantWithStats { Variant allele = 1; // counters within virtual cohort (aka provided samples in req) // NB. virtual cohort counters are empty in Runtime Optimized mode float vaf = 2; float vac = 3; int32 van = 4; int32 vhomc = 5; int32 vhetc = 6; int32 vhomfc = 7; int32 vhetfc = 8; // Statistics // NB i. Calculated for the whole population = dataset, NOT just in sub-population = virtual cohort // NB ii. All stats are empty in Runtime Optimized mode and outside function domain float phwe = 9; // p-value for Chi-squared test for deviation from Hardy-Weinberg Equilibrium // Biallelic SNVs only on autosomal and X chromosomes. For all other variants p-value = 0. float pchi2 = 10; // p-value in Pearson's chi-squared test with provided samples as cases and the rest of cohort as controls float or = 11; // odds ratio in Pearson's chi-squared test above // F-statistics // https://en.wikipedia.org/wiki/F-statistics // For biallelic SNVs in Autosomal and PAR only // Empty for X & Y outside PAR, MT, non SNVs and in Runtime Optimized mode float ibc = 12; // F-statistics as for inbreeding coefficient } message TopNchi2Request { int32 n = 1; // top 'n' variants to select in each node repeated string samples = 2; // samples names as provided during ETL bool seq = 3; // calculate sequentially in a single thread to be gentle on CPU resources; // by default calculations are performed in MT and occupy all cores available on the nodes } message TopNHWERequest { int32 n = 1; // top 'n' variants to select in each node bool seq = 2; // calculate sequentially in a single thread to be gentle on CPU resources; // by default calculations are performed in MT and occupy all cores available on the nodes } // Sample selection // Samples with (specific) variants in a region message SamplesInRegionRequest { Chromosome chr = 1; int32 start = 2; // 1-based region start position, inclusive int32 end = 3; // 1-based region end position, inclusive string ref = 4; // reference allele, optional string alt = 5; // alternative allele, optional bool hom = 6; // select samples with homozygous alleles; NB: empty/null/false == do not select bool het = 7; // select samples with heterozygous alleles; NB: empty/null/false == do not select Annotations ann = 8; // select by annotations, optional int32 skip = 9; // skip first n samples from result from each node, <= 0 means no skip; optional int32 limit = 10; // limit result to n samples from each node, <= 0 means 2^31-1 limit; optional RefAssembly assembly = 11; // reference assembly, optional; default = GRCh38 int32 variantMinLength = 12; // minimal alt allele length; default = 0; optional int32 variantMaxLength = 13; // maximal alt allele length; >= 1; default = Int32.MaxValue; optional } // Selects samples with (specific) variants in region(s) message SamplesInMultiRegionsRequest { repeated Chromosome chr = 1; repeated int32 start = 2; // 1-based regions start positions, inclusive repeated int32 end = 3; // 1-based regions end positions, inclusive repeated string ref = 4; // reference allele for each region, if at all; optional repeated string alt = 5; // alternative allele for each region, if at all; optional bool hom = 6; // select samples with homozygous alleles; NB: empty/null/false == do not select bool het = 7; // select samples with heterozygous alleles; NB: empty/null/false == do not select Annotations ann = 8; // select by annotations, optional int32 skip = 9; // skip first n samples from result from each node, <= 0 means no skip; optional int32 limit = 10; // limit result to n samples from each node, <= 0 means 2^31-1 limit; optional RefAssembly assembly = 11; // reference assembly, optional; default = GRCh38 int32 variantMinLength = 12; // minimal alt allele length; default = 0; optional int32 variantMaxLength = 13; // maximal alt allele length; >= 1; default = Int32.MaxValue; optional } // Set of samples with variants in given region(s) message SamplesResponse { repeated string samples = 1; // sample names as provided during ETL bool incomplete_cluster = 2; // indicates response from incomplete cluster with unreachable nodes bool affected = 3; // indicates that unreachable nodes could possibly affect completeness of response int64 elapsed_ms = 4; // time to execute, in ms; time from receiving request to sending response int64 elapsed_db_ms = 5; // processing time in database engine, in ms string node_id = 6; // node which responses } // De Novo Request message DeNovoRequest { string parent1 = 1; // unaffected parent, sample name as provided during ETL; required string parent2 = 2; // unaffected parent, sample name as provided during ETL; required string proband = 3; // affected child, sample name as provided during ETL; required Chromosome chr = 4; // required int32 start = 5; // 1-based region start position, inclusive; required int32 end = 6; // 1-based region end position, inclusive; required string ref = 7; // reference allele, optional string alt = 8; // alternative allele, optional int32 variantMinLength = 9; // minimal alt allele length; default = 0; optional int32 variantMaxLength = 10; // maximal alt allele length; >= 1; default = Int32.MaxValue; optional Annotations ann = 11; // select by annotations, optional RefAssembly assembly = 12; // reference assembly, optional; default = GRCh38 int32 skip = 13; // skip first n variants from result from each node, <= 0 means no skip; optional int32 limit = 14; // limit result to n variants from each node, <= 0 means 2^31-1 limit; optional } // Heterozygous Dominant Request message HetDominantRequest { string affected_parent = 1; // affected parent, sample name as provided during ETL; required string unaffected_parent = 2; // unaffected parent, sample name as provided during ETL; required string affected_child = 3; // affected child, sample name as provided during ETL; required Chromosome chr = 4; // required int32 start = 5; // 1-based region start position, inclusive; required int32 end = 6; // 1-based region end position, inclusive; required string ref = 7; // reference allele, optional string alt = 8; // alternative allele, optional int32 variantMinLength = 9; // minimal alt allele length; default = 0; optional int32 variantMaxLength = 10; // maximal alt allele length; >= 1; default = Int32.MaxValue; optional Annotations ann = 11; // select by annotations, optional RefAssembly assembly = 12; // reference assembly, optional; default = GRCh38 int32 skip = 13; // skip first n variants from result from each node, <= 0 means no skip; optional int32 limit = 14; // limit result to n variants from each node, <= 0 means 2^31-1 limit; optional } // Homozygous Recessive Request message HomRecessiveRequest { string unaffected_parent1 = 1;// unaffected parent, sample name as provided during ETL; required string unaffected_parent2 = 2;// unaffected parent, sample name as provided during ETL; required string affected_child = 3; // affected child, sample name as provided during ETL; required Chromosome chr = 4; // required int32 start = 5; // 1-based region start position, inclusive; required int32 end = 6; // 1-based region end position, inclusive; required string ref = 7; // reference allele, optional string alt = 8; // alternative allele, optional int32 variantMinLength = 9; // minimal alt allele length; default = 0; optional int32 variantMaxLength = 10; // maximal alt allele length; >= 1; default = Int32.MaxValue; optional Annotations ann = 11; // select by annotations, optional RefAssembly assembly = 12; // reference assembly, optional; default = GRCh38 int32 skip = 13; // skip first n variants from result from each node, <= 0 means no skip; optional int32 limit = 14; // limit result to n variants from each node, <= 0 means 2^31-1 limit; optional } // PRS for Samples Request message PRSRequest { string prs_name = 1; // PRS name as loaded to dataset // either 'cohort_name', 'samples' or both should be provided string cohort_name = 2; // calculate PRS for all samples in cohort repeated string samples = 3; // calculate PRS for sample names as provided during ETL bool dominant = 4; // same as 'dominant' in plink 2.* bool recessive = 5; // same as 'recessive' in plink 2.* } // PRS for Sample Response message PRSResponse { string prs_name = 1; // PRS name as loaded to dataset repeated SampleScore sample_scores = 2; // PRS scores for samples bool dominant = 3; // indicates whether 'dominant' option was used in scores calculations bool recessive = 4; // indicates whether 'recessive' option was used in scores calculations int32 prs_cardinality = 5; // number of effect variants in PRS bool incomplete_cluster = 6; // indicates response from incomplete cluster with unreachable nodes int64 elapsed_ms = 7; // time to execute, in ms; time from receiving request to sending response int64 elapsed_db_ms = 8; // processing time in database engine, in ms string node_id = 9; // node which responses } message SampleScore { string sample = 1; // sample name as provided during ETL float scores_sum = 2; // summary of scores in sample, equals to 'sum' mode in plink's '--score' int32 hethom_cardinality = 3; // number of effect alleles contributed to scores_sum in this sample // = number of effect alleles in sample with het or hom genotypes int32 ref_cardinality = 4; // number of effect alleles in sample with ref genotypes; // for datasets in optimized mode it's < 0 as they miss ref/missing gt data // and for them the metric just reflects the number of nodes replied. // see https://dnaerys.org/#doc/#runtime-optimization int32 mis_cardinality = 5; // number of effect alleles in sample with missing genotypes // for datasets in optimized mode it's = 0 as they miss ref/missing gt data float imputed_sum = 6; // summary of imputed scores for missing alleles in sample, i.e. SNP scores * estimated weights // with estimated gt weights = gnomAD AF * 2 // equals to default mode in plink's '--score' when combined with 'scores_sum'; // for datasets in optimized mode it's = 0 as they miss ref/missing gt data } message FstatXRequest { // either 'cohort_name', 'samples' or both should be provided string cohort_name = 1; // report sample sex mismatch for all samples in cohort repeated string samples = 2; // report sample sex mismatch for given sample names // optional float aaf_threshold = 3; // [0,1] consider only alleles with 'aaf_threshold < aaf < 1 - aaf_threshold'; default = 0 float female_threshold = 4; // samples called females if F < female_threshold; default = 0.7; ignored in FstatX calls float male_threshold = 5; // samples called males if F > male_threshold; default = 0.7; ignored in FstatX calls bool include_par = 6; // PAR are excluded by default, this option includes them when true bool seq = 7; // calculate sequentially in a single thread to be gentle on CPU resources; // by default calculations are performed in MT and occupy all cores available on the nodes with X data } message SexMismatchResponse { repeated SampleStat mismatch_males = 1; // samples with reported male sex (reported during ETL) and observed female sex repeated SampleStat mismatch_females = 2; // samples with reported female sex (reported during ETL) and observed male sex bool incomplete_cluster = 3; // indicates response from incomplete cluster with unreachable nodes int64 elapsed_ms = 4; // time to execute, in ms; time from receiving request to sending response int64 elapsed_db_ms = 5; // processing time in database engine, in ms string node_id = 6; // node which responses } message SampleStat { string sample = 1; // sample name as provided during ETL string reported_sex = 2; // sample sex as provided during ETL string observed_sex = 3; // sample sex as observed float f_stat = 4; // F value } message FstatXResponse { repeated SampleStat males = 1; // F-stats for samples with reported male sex (reported during ETL) repeated SampleStat females = 2; // F-stats for samples with reported female sex (reported during ETL) bool incomplete_cluster = 3; // indicates response from incomplete cluster with unreachable nodes int64 elapsed_ms = 4; // time to execute, in ms; time from receiving request to sending response int64 elapsed_db_ms = 5; // processing time in database engine, in ms string node_id = 6; // node which responses } // Degrees of relatedness & kinship coefficients for all pairs(!) of samples // returns all pairs or filtered by degree of relatedness message KinshipRequest { // either 'cohort_name', 'samples' or both should be provided // Achtung: number of pairs in n samples = O(n^2)! string cohort_name = 1; // report kinship coefficients for all possible pairs in cohort repeated string samples = 2; // report kinship coefficients for all possible pairs in provided samples // filtering by degree: either 'degree' or 'threshold' (or none) should be provided, but not both KinshipDegree degree = 3; // report all pairs with relatedness closer or equal to 'degree' float threshold = 4; // [0,0.5) report pairs with relatedness closer than threshold, // i.e. with kinship coefficient > threshold; default = 0 = return all pairs bool seq = 5; // calculate sequentially in a single thread to be gentle on CPU resources; // by default calculations are performed in MT and occupy all cores available on the nodes } // Degree of relatedness & kinship coefficient between samples in duo // returns degree of relatedness message KinshipDuoRequest { string sample1 = 1; string sample2 = 2; bool seq = 3; // calculate sequentially in a single thread to be gentle on CPU resources; // by default calculations are performed in MT and occupy all cores available on the nodes } // Degrees of relatedness & kinship coefficients for all pairs of samples in trio // returns all pairs or filtered by degree of relatedness message KinshipTrioRequest { string sample1 = 1; string sample2 = 2; string sample3 = 3; // filtering by degree: either 'degree' or 'threshold' (or none) should be provided, but not both KinshipDegree degree = 4; // report all pairs with relatedness closer or equal to 'degree' float threshold = 5; // [0,0.5) report pairs with relatedness closer than threshold, // i.e. with kinship coefficient > threshold; default = 0 = return all pairs bool seq = 6; // calculate sequentially in a single thread to be gentle on CPU resources; // by default calculations are performed in MT and occupy all cores available on the nodes } message KinshipResponse { repeated Relatedness rel = 1; // relatedness for pairs of samples bool incomplete_cluster = 2; // indicates response from incomplete cluster with unreachable nodes int64 elapsed_ms = 3; // time to execute, in ms; time from receiving request to sending response int64 elapsed_db_ms = 4; // processing time in database engine, in ms string node_id = 5; // node which responses } message Relatedness { string sampleA = 1; // sample name string sampleB = 2; // sample name KinshipDegree degree = 3; // phi_bwf thresholds: > 0.354, (0.177, 0.354), (0.0884, 0.177), (0.0442, 0.0884), < 0.0442 float phi_bwf = 4; // "between-family" KING robust estimator for kinship coefficient, based on: // https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3025716 // https://www.kingrelatedness.com } message SampleKinshipRequest { string sample_vcf = 1; // external sample of interest as a single sample vcf (v4.2) in a multi line text // if multi sample vcf is provided, the first sample is used // only autosomal biallelics SNVs counted (and truly diploid, i.e no missing calls on any strand) // variants are assumed to be aligned to the dataset build and be in a minimal representation // returns INVALID_ARGUMENT if none found string cohort_name = 2; // search for related samples in provided cohort; // search in the whole dataset if cohort_name is not specified // filtering by degree: either 'degree' or 'threshold' (or none) should be provided, but not both // if none provided, default degree = THIRD_DEGREE is used KinshipDegree degree = 3; // report all pairs with relatedness closer or equal to 'degree' float threshold = 4; // [0,0.5) report pairs with relatedness closer than threshold, // i.e. with kinship coefficient > threshold; bool seq = 5; // calculate sequentially in a single thread to be gentle on CPU resources; // by default calculations are performed in MT and occupy all cores available on the nodes } message SampleKinshipResponse { repeated RelatednessPerSample rel = 1; // relatedness wrt sample of interest int32 accepted_snvs = 2; // # of accepted valid autosomal biallelics SNVs in 'sample_vcf' bool incomplete_cluster = 3; // indicates response from incomplete cluster with unreachable nodes int64 elapsed_ms = 4; // time to execute, in ms; time from receiving request to sending response int64 elapsed_db_ms = 5; // processing time in database engine, in ms string node_id = 6; // node which responses } message RelatednessPerSample { string sample_name = 1; // sample from dataset KinshipDegree degree = 2; // phi_bwf thresholds: > 0.354, (0.177, 0.354), (0.0884, 0.177), (0.0442, 0.0884), < 0.0442 float phi_bwf = 3; // "between-family" KING robust estimator for kinship coefficient, based on: // https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3025716 // https://www.kingrelatedness.com int32 common_loci = 4; // # of common autosomal biallelics SNV loci between 'sample_vcf' and 'sample_name'; // these are the loci based on which kinship coefficient is calculated for this sample. // GTs with "no call" on any strand are ignored. // GT counters used in phi_bwf calculation for this pair of samples int32 nHetS1 = 5; // # Heterozygous Alt GTs in 'sample_vcf' in common loci int32 nHetS2 = 6; // # Heterozygous Alt GTs in dataset sample in common loci int32 nHetS1S2 = 7; // # loci where both samples are Heterozygous int32 nHomOp = 8; // # loci where samples are opposite Homozygous } // Count selected variants in all samples in region message CountAllelesInRegionRequest { Chromosome chr = 1; int32 start = 2; // 1-based region start position, inclusive int32 end = 3; // 1-based region end position, inclusive string ref = 4; // reference allele, optional string alt = 5; // alternative allele, optional bool hom = 6; // count homozygous alleles; NB: empty/null/false == do not include bool het = 7; // count heterozygous alleles; NB: empty/null/false == do not include Annotations ann = 8; // select by annotations, optional RefAssembly assembly = 9; // reference assembly, optional; default = GRCh38 int32 variantMinLength = 10; // minimal alt allele length; default = 0; optional int32 variantMaxLength = 11; // maximal alt allele length; >= 1; default = Int32.MaxValue; optional } // Counts selected variants in provided samples in region message CountAllelesInRegionInSamplesRequest { Chromosome chr = 1; int32 start = 2; // 1-based region start position, inclusive int32 end = 3; // 1-based region end position, inclusive string ref = 4; // reference allele, optional string alt = 5; // alternative allele, optional bool hom = 6; // count homozygous alleles; NB: empty/null/false == do not select bool het = 7; // count heterozygous alleles; NB: empty/null/false == do not select Annotations ann = 8; // select by annotations, optional RefAssembly assembly = 9; // reference assembly, optional; default = GRCh38 repeated string samples = 10; // samples names as provided during ETL int32 variantMinLength = 11; // minimal alt allele length; default = 0; optional int32 variantMaxLength = 12; // maximal alt allele length; >= 1; default = Int32.MaxValue; optional } // Counts unique variants in all samples in a bracket // see https://docs.genomebeacons.org/variant-queries/#beacon-bracket-queries message CountAllelesInBracketRequest { Chromosome chr = 1; int32 start_min = 2; // 1-based start min position, inclusive int32 start_max = 3; // 1-based start max position, inclusive int32 end_min = 4; // 1-based end min position, inclusive int32 end_max = 5; // 1-based end max position, inclusive string ref = 6; // reference allele, optional string alt = 7; // alternative allele, optional bool hom = 8; // count homozygous alleles; NB: empty/null/false == do not select bool het = 9; // count heterozygous alleles; NB: empty/null/false == do not select Annotations ann = 10; // select by annotations, optional RefAssembly assembly = 11; // reference assembly, optional; default = GRCh38 int32 variantMinLength = 12; // minimal alt allele length; default = 0; optional int32 variantMaxLength = 13; // maximal alt allele length; >= 1; default = Int32.MaxValue; optional } // Counts variants in provided samples in a bracket // see https://docs.genomebeacons.org/variant-queries/#beacon-bracket-queries message CountAllelesInBracketInSamplesRequest { Chromosome chr = 1; int32 start_min = 2; // 1-based start min position, inclusive int32 start_max = 3; // 1-based start max position, inclusive int32 end_min = 4; // 1-based end min position, inclusive int32 end_max = 5; // 1-based end max position, inclusive string ref = 6; // reference allele, optional string alt = 7; // alternative allele, optional bool hom = 8; // select homozygous alleles; NB: empty/null/false == do not select bool het = 9; // select heterozygous alleles; NB: empty/null/false == do not select Annotations ann = 10; // select by annotations, optional RefAssembly assembly = 11; // reference assembly, optional; default = GRCh38 int32 variantMinLength = 12; // minimal alt allele length; default = 0; optional int32 variantMaxLength = 13; // maximal alt allele length; >= 1; default = Int32.MaxValue; optional repeated string samples = 14; // samples names as provided during ETL } // Counts variants in all samples in regions message CountAllelesInMultiRegionsRequest { repeated Chromosome chr = 1; repeated int32 start = 2; // 1-based regions start positions, inclusive repeated int32 end = 3; // 1-based regions end positions, inclusive repeated string ref = 4; // reference allele for each region, if at all; optional repeated string alt = 5; // alternative allele for each region, if at all; optional bool hom = 6; // select homozygous alleles; NB: empty/null/false == do not select bool het = 7; // select heterozygous alleles; NB: empty/null/false == do not select Annotations ann = 8; // select by annotations, optional RefAssembly assembly = 9; // reference assembly, optional; default = GRCh38 int32 variantMinLength = 10; // minimal alt allele length; default = 0; optional int32 variantMaxLength = 11; // maximal alt allele length; >= 1; default = Int32.MaxValue; optional } // Counts variants in provided samples in regions message CountAllelesInMultiRegionsInSamplesRequest { repeated Chromosome chr = 1; repeated int32 start = 2; // 1-based regions start positions, inclusive repeated int32 end = 3; // 1-based regions end positions, inclusive repeated string ref = 4; // reference allele for each region, if at all; optional repeated string alt = 5; // alternative allele for each region, if at all; optional bool hom = 6; // select homozygous alleles; NB: empty/null/false == do not select bool het = 7; // select heterozygous alleles; NB: empty/null/false == do not select Annotations ann = 8; // select by annotations, optional RefAssembly assembly = 9; // reference assembly, optional; default = GRCh38 repeated string samples = 10; // samples names as provided during ETL int32 variantMinLength = 11; // minimal alt allele length; default = 0; optional int32 variantMaxLength = 12; // maximal alt allele length; >= 1; default = Int32.MaxValue; optional } message CountAllelesResponse { int64 count = 1; // number of selected alleles bool incomplete_cluster = 2; // indicates response from incomplete cluster with unreachable nodes bool affected = 3; // indicates that unreachable nodes could possibly affect completeness of response int64 elapsed_ms = 4; // time to execute, in ms; time from receiving request to sending response int64 elapsed_db_ms = 5; // processing time in database engine, in ms string node_id = 6; // node which responses } message CountSamplesResponse { int32 count = 1; // number of selected samples bool incomplete_cluster = 2; // indicates response from incomplete cluster with unreachable nodes bool affected = 3; // indicates that unreachable nodes could possibly affect completeness of response int64 elapsed_ms = 4; // time to execute, in ms; time from receiving request to sending response int64 elapsed_db_ms = 5; // processing time in database engine, in ms string node_id = 6; // node which responses } /* ------------------------------------------------------------------------------------------------------------------ */ /* enums */ enum RefAssembly { ASSEMBLY_UNSPECIFIED = 0; // equals default GRCh38 GRCh37 = 1; GRCh38 = 2; // default assembly } enum Chromosome { CHROMOSOME_UNSPECIFIED = 0; CHR_1 = 1; CHR_2 = 2; CHR_3 = 3; CHR_4 = 4; CHR_5 = 5; CHR_6 = 6; CHR_7 = 7; CHR_8 = 8; CHR_9 = 9; CHR_10 = 10; CHR_11 = 11; CHR_12 = 12; CHR_13 = 13; CHR_14 = 14; CHR_15 = 15; CHR_16 = 16; CHR_17 = 17; CHR_18 = 18; CHR_19 = 19; CHR_20 = 20; CHR_21 = 21; CHR_22 = 22; CHR_X = 23; CHR_Y = 24; CHR_MT = 25; } /* Annotations enums */ // Sequence Ontology Variant classes terms as defined at // https://asia.ensembl.org/info/genome/variation/prediction/classification.html#classes enum VariantType { VARIANTTYPE_UNSPECIFIED = 0; SNV = 1; INSERTION = 2; DELETION = 3; INDEL = 4; SUBSTITUTION = 5; // SV INVERSION = 6; TRANSLOCATION = 7; DUPLICATION = 8; ALU_INSERTION = 9; COMPLEX_STRUCTURAL_ALTERATION = 10; COMPLEX_SUBSTITUTION = 11; COPY_NUMBER_GAIN = 12; COPY_NUMBER_LOSS = 13; COPY_NUMBER_VARIATION = 14; INTERCHROMOSOMAL_BREAKPOINT = 15; INTERCHROMOSOMAL_TRANSLOCATION = 16; INTRACHROMOSOMAL_BREAKPOINT = 17; INTRACHROMOSOMAL_TRANSLOCATION = 18; LOSS_OF_HETEROZYGOSITY = 19; MOBILE_ELEMENT_DELETION = 20; MOBILE_ELEMENT_INSERTION = 21; NOVEL_SEQUENCE_INSERTION = 22; SHORT_TANDEM_REPEAT_VARIATION = 23; TANDEM_DUPLICATION = 24; PROBE = 25; ALU_DELETION = 26; HERV_DELETION = 27; HERV_INSERTION = 28; LINE1_DELETION = 29; LINE1_INSERTION = 30; SVA_DELETION = 31; SVA_INSERTION = 32; COMPLEX_CHROMOSOMAL_REARRANGEMENT = 33; SEQUENCE_ALTERATION = 34; } // VEP type of feature enum FeatureType { FEATURETYPE_UNSPECIFIED = 0; TRANSCRIPT = 1; REGULATORYFEATURE = 2; MOTIFFEATURE = 3; } // VEP Biotypes // https://asia.ensembl.org/info/genome/genebuild/biotypes.html enum BioType { BIOTYPE_UNSPECIFIED = 0; PROCESSED_TRANSCRIPT = 1; LNCRNA = 2; ANTISENSE = 3; MACRO_LNCRNA = 4; NON_CODING = 5; RETAINED_INTRON = 6; SENSE_INTRONIC = 7; SENSE_OVERLAPPING = 8; LINCRNA = 9; NCRNA = 10; MIRNA = 11; MISCRNA = 12; PIRNA = 13; RRNA = 14; SIRNA = 15; SNRNA = 16; SNORNA = 17; TRNA = 18; VAULTRNA = 19; PROTEIN_CODING = 20; PSEUDOGENE = 21; IG_PSEUDOGENE = 22; POLYMORPHIC_PSEUDOGENE = 23; PROCESSED_PSEUDOGENE = 24; TRANSCRIBED_PSEUDOGENE = 25; TRANSLATED_PSEUDOGENE = 26; UNITARY_PSEUDOGENE = 27; UNPROCESSED_PSEUDOGENE = 28; READTHROUGH = 29; STOP_CODON_READTHROUGH = 30; TEC = 31; TR_GENE = 32; TR_C_GENE = 33; TR_D_GENE = 34; TR_J_GENE = 35; TR_V_GENE = 36; IG_GENE = 37; IG_C_GENE = 38; IG_D_GENE = 39; IG_J_GENE = 40; IG_V_GENE = 41; NONSENSE_MEDIATED_DECAY = 42; } // Sequence Ontology variant consequences // https://asia.ensembl.org/info/genome/variation/prediction/predicted_data.html#consequences enum Consequence { CONSEQUENCE_UNSPECIFIED = 0; TRANSCRIPT_ABLATION = 1; SPLICE_ACCEPTOR_VARIANT = 2; SPLICE_DONOR_VARIANT = 3; STOP_GAINED = 4; FRAMESHIFT_VARIANT = 5; STOP_LOST = 6; START_LOST = 7; TRANSCRIPT_AMPLIFICATION = 8; INFRAME_INSERTION = 9; INFRAME_DELETION = 10; MISSENSE_VARIANT = 11; PROTEIN_ALTERING_VARIANT = 12; SPLICE_REGION_VARIANT = 13; INCOMPLETE_TERMINAL_CODON_VARIANT = 14; START_RETAINED_VARIANT = 15; STOP_RETAINED_VARIANT = 16; SYNONYMOUS_VARIANT = 17; CODING_SEQUENCE_VARIANT = 18; MATURE_MIRNA_VARIANT = 19; FIVE_PRIME_UTR_VARIANT = 20; THREE_PRIME_UTR_VARIANT = 21; NON_CODING_TRANSCRIPT_EXON_VARIANT = 22; INTRON_VARIANT = 23; NMD_TRANSCRIPT_VARIANT = 24; NON_CODING_TRANSCRIPT_VARIANT = 25; UPSTREAM_GENE_VARIANT = 26; DOWNSTREAM_GENE_VARIANT = 27; TFBS_ABLATION = 28; TFBS_AMPLIFICATION = 29; TF_BINDING_SITE_VARIANT = 30; REGULATORY_REGION_ABLATION = 31; REGULATORY_REGION_AMPLIFICATION = 32; FEATURE_ELONGATION = 33; REGULATORY_REGION_VARIANT = 34; FEATURE_TRUNCATION = 35; INTERGENIC_VARIANT = 36; SPLICE_POLYPYRIMIDINE_TRACT_VARIANT = 37; SPLICE_DONOR_5TH_BASE_VARIANT = 38; SPLICE_DONOR_REGION_VARIANT = 39; CODING_TRANSCRIPT_VARIANT = 40; SEQUENCE_VARIANT = 41; } // VEP impact of consequence type // https://asia.ensembl.org/info/genome/variation/prediction/predicted_data.html#consequences enum Impact { IMPACT_UNSPECIFIED = 0; HIGH = 1; MODERATE = 2; LOW = 3; MODIFIER = 4; } // SIFT prediction terms // https://sift.bii.a-star.edu.sg/ enum SIFT { SIFT_UNSPECIFIED = 0; TOLERATED = 1; DELETERIOUS = 2; } // PolyPhen prediction terms enum PolyPhen { POLYPHEN_UNSPECIFIED = 0; BENIGN = 1; POSSIBLY_DAMAGING = 2; PROBABLY_DAMAGING = 3; UNKNOWN = 4; } // ClinVar Clinical Significance // https://www.ncbi.nlm.nih.gov/clinvar/docs/clinsig/ enum ClinSignificance { CLNSIG_UNSPECIFIED = 0; CLNSIG_BENIGN = 1; LIKELY_BENIGN = 2; UNCERTAIN_SIGNIFICANCE = 3; LIKELY_PATHOGENIC = 4; PATHOGENIC = 5; DRUG_RESPONSE = 6; ASSOCIATION = 7; RISK_FACTOR = 8; PROTECTIVE = 9; AFFECTS = 10; CONFERS_SENSITIVITY = 11; CONFLICTING_INTERPRETATIONS = 12; NOT_PROVIDED = 13; OTHER = 14; LIKELY_PATHOGENIC_LOW_PENETRANCE = 15; PATHOGENIC_LOW_PENETRANCE = 16; UNCERTAIN_RISK_ALLELE = 17; LIKELY_RISK_ALLELE = 18; ESTABLISHED_RISK_ALLELE = 19; } // AlphaMissense class // https://www.science.org/doi/10.1126/science.adg7492 enum AlphaMissense { AM_UNSPECIFIED = 0; AM_LIKELY_BENIGN = 1; // alphamissense_pathogenicity < 0.34 AM_LIKELY_PATHOGENIC = 2; // alphamissense_pathogenicity > 0.564 AM_AMBIGUOUS = 3; // otherwise } enum KinshipDegree { KINSHIP_UNSPECIFIED = 0; TWINS_MONOZYGOTIC = 1; FIRST_DEGREE = 2; SECOND_DEGREE = 3; THIRD_DEGREE = 4; UNRELATED = 5; }