braf-v600.annotated.yaml

# Categorical Variants are described using the Cat-VRS data model, here:
# https://cat-vrs.readthedocs.io/en/latest/concepts/catvrs_model.html

# While Categorical Variants can be defined using any combination of constraints, the Cat-VRS development team
# is generating common types of Categorical Variants, named "recipes", and these can be found here:
# https://cat-vrs.readthedocs.io/en/latest/concepts/recipes.html

# Here, we describe the Protein Sequence Consequence Categorical Variant for BRAF V600 variants,
# referenced from CIViC: https://civicdb.org/variants/17/summary

# id: The ‘logical’ identifier of the Entity in the system of record, e.g. a UUID.
# This ‘id’ is unique within a given system, but may or may not be globally unique outside the system.
# Within these examples, we are using the nomenclature {originating resource}:{identifier that they are using}
# Given the URL https://civicdb.org/variants/17/summary, we will use the id of civic.vid:17
id: civic.vid:17

# type: All Categorical Variants must be of type 'CategoricalVariant'. This specifies the data type of the object.
type: CategoricalVariant

# name: A primary name for the entity. This is intended to be human-readable.
name: BRAF V600 (annotated)

# description: A free-text description of the entity
description: >-
  BRAF V600 variants are missense amino acid substitutions that result in Valine changed.
  V600E is the most common substitution, but V600K, V600M, V600R, and V600G have also been observed.

# aliases: Alternative names of the Categorical Variant. For most examples, we have filled in hgvs representations
# within aliases but hgvs requires an alternate allele to be specified, which we cannot do here. Thus we've just added
# a version of the name with the MANE Select transcript specified.
aliases:
  - NM_004333.6(BRAF) V600
  - NM_004333.6 V600

# extensions: A list of extensions to the Entity, that allow for capture of information not directly
# supported by elements defined in the model.
# The decision of how to structure extensions are left to implementers, though we recommend documenting an
# implementation's use of extensions in the Standard Operating Procedure to promote ease of use.
extensions:
  - name: CIViC Representative Variant Coordinates
    value:
      chromosome: '7'
      start: 140453136
      stop: 140453137
      reference_bases: ''
      variant_bases: ''
      representative_transcript:  ENST00000288602.6
      ensembl_version: 75
      reference_build: GRCh37

# constraints: A rule or set of rules that must be satisfied for a Categorical Variant to be considered valid.
# The currently implemented constraints can be viewed online, here:
# https://cat-vrs.readthedocs.io/en/latest/concepts/catvrs_model.html#constraint
# They also can be viewed within the source yaml file, located at schema/cat-vrs/cat-vrs-source.yaml, within this
# GitHub repository.
# For each categorical variant there may be 0 to n constraints.
constraints:
  # The DefiningLocationConstraint describes variation relative to a VRS location
  # The VRS location can be transcribed in full, or abbreviated with the notation vrs.json#/ga4gh:VA...
  - type: DefiningLocationConstraint
    location:
      id: ga4gh:SL.1ReS370wzmC9PGTn13XrnG8Ot7UAKYuw
      description: Amino acid position 600 within the BRAF protein (refseq:NP_004324.2), which is the protein product of the MANE Select (GRCh38) coding transcript for BRAF (refseq:NM_004333.6), corresponding to valine in the reference sequence.
      type: SequenceLocation
      digest: 1ReS370wzmC9PGTn13XrnG8Ot7UAKYuw
      sequenceReference:
        id: refseq:NP_004324.2
        name: NP_004324.2
        description: The protein product of the MANE Select (GRCh38) coding transcript for BRAF (refseq:NM_004333.6), corresponding to the Refseq protein accession NP_004324.2.
        aliases:
          - ensembl:ENSP00000288602.6
          - ga4gh:SQ.cQvw4UsHHRRlogxbWCB8W-mKD4AraM9y
        type: SequenceReference
        refgetAccession: SQ.cQvw4UsHHRRlogxbWCB8W-mKD4AraM9y
        residueAlphabet: aa
      start: 599
      end: 600
      sequence: V
    relations:
      - primaryCoding:
          code: translation_of
          system: http://www.sequenceontology.org
          iris:
            - http://www.sequenceontology.org/browser/current_release/term/translation_of
    matchCharacteristic:
      primaryCoding:
        code: is_within
        system: ga4gh-gks-term:location-match

# mappings: A list of mappings to concepts in terminologies or code systems.
# Each mapping should include a coding and a relation.
# Usually, this is intended to describe relations to concepts in other websites or systems
# For example, linking out to clinvar or dbSNP. These mappings are taken from
mappings:
  - coding:
      system: https://www.ncbi.nlm.nih.gov/clinvar/variation/
      code: '13961'
      name: NM_004333.6(BRAF):c.1799T>A (p.Val600Glu)
      iris:
        - https://www.ncbi.nlm.nih.gov/clinvar/variation/13961
    relation: relatedMatch
  - coding:
      system: https://www.ncbi.nlm.nih.gov/clinvar/variation/
      code: '375940'
      name: NM_004333.6(BRAF):c.1798_1799delinsAG (p.Val600Arg)
      iris:
        - https://www.ncbi.nlm.nih.gov/clinvar/variation/375940
    relation: relatedMatch
  - coding:
      system: https://www.ncbi.nlm.nih.gov/clinvar/variation/
      code: '375941'
      name: NM_004333.6(BRAF):c.1798_1799delinsAA (p.Val600Lys)
      iris:
        - https://www.ncbi.nlm.nih.gov/clinvar/variation/375941
    relation: relatedMatch
  - coding:
      system: https://www.ncbi.nlm.nih.gov/clinvar/variation/
      code: '40389'
      name: NM_004333.6(BRAF):c.1799T>G (p.Val600Gly)
      iris:
        - https://www.ncbi.nlm.nih.gov/clinvar/variation/40389
    relation: relatedMatch
  - coding:
      system: https://www.ncbi.nlm.nih.gov/clinvar/variation/
      code: '44815'
      name: NM_004333.6(BRAF):c.1798G>A (p.Val600Met)
      iris:
        - https://www.ncbi.nlm.nih.gov/clinvar/variation/44815
    relation: relatedMatch

# members: A non-exhaustive list of VRS variation Constraints that satisfy the constraints of this categorical variant.
# Here, we are describing VRS alleles that satisfy BRAF V600
# The VariantNormalizer is a useful API tool to retrieve VRS Alleles based on HGVS representation
# https://normalize.cancervariants.org/variation
members:
  - id: ga4gh:VA.W6xsV-aFm9yT2Bic5cFAV2j0rll6KK5R
    type: Allele
    name: NM_004333.6:c.1799T>A
    description: VRS variation of NM_004333.6:c.1799T>A, generated with the VICC Variation Normalizer (https://github.com/cancervariants/variation-normalization).
    digest: W6xsV-aFm9yT2Bic5cFAV2j0rll6KK5R
    expressions:
      - syntax: hgvs.c
        value: NM_004333.6:c.1799T>A
    location:
      id: ga4gh:SL.8HBKs9fzlT3tKWlM03REjkg_0Om6Y33U
      description: Coding DNA (cDNA) position 1799 of the BRAF MANE Select coding transcript (refseq:NM_004333.6), corresponding to genomic position 140753336 on chromosome 7 (refseq:NC_000007.14, GRCh38).
      extensions:
        - name: GRCh38 1-based, genomic position
          value: chr7:140753336
          description: Genomic position 140,753,336 on chromosome 7 (refseq:NC_000007.14, GRCh38).
        - name: GRCh38 1-based, inclusive interval
          value: chr7:140753336-140753336
          description: Genomic positions 140,753,336 to 140,753,336 on chromosome 7 (refseq:NC_000007.14, GRCh38); 1-based, inclusive interval notation.
        - name: GRCh38 0-based, half-open interval
          value: chr7:140753335-140753337
          description: Genomic positions 140,753,335 to 140,753,336 on chromosome 7 (refseq:NC_000007.14, GRCh38); 0-based, half-open interval notation.
      type: SequenceLocation
      digest: 8HBKs9fzlT3tKWlM03REjkg_0Om6Y33U
      sequenceReference:
        id: refseq:NM_004333.6
        name: NM_004333.6
        description: The MANE Select (GRCh38) coding transcript for BRAF.
        aliases:
          - ga4gh:SQ.aKMPEJgmlZXt_F6gRY5cUG3THH2n-GUa
        type: SequenceReference
        refgetAccession: SQ.aKMPEJgmlZXt_F6gRY5cUG3THH2n-GUa
        residueAlphabet: na
      start: 2024
      end: 2025
      sequence: T
    state:
      type: LiteralSequenceExpression
      sequence: A
  - id: ga4gh:VA.GIOeMJX8rJ-q9ZGqmFRIUOGnXQ5NARht
    type: Allele
    name: NM_004333.6:c.1798_1799delinsAA
    description: VRS variation of NM_004333.6:c.1798_1799delinsAA, generated with the VICC Variation Normalizer (https://github.com/cancervariants/variation-normalization).
    digest: GIOeMJX8rJ-q9ZGqmFRIUOGnXQ5NARht
    expressions:
      - syntax: hgvs.c
        value: NM_004333.6:c.1798_1799delinsAA
    location:
      id: ga4gh:SL.SXY8ShFrBAfSvtO_sXLMQKN3Ozc5awgh
      description: Coding DNA (cDNA) positions 1798 to 1799 of the BRAF MANE Select coding transcript (refseq:NM_004333.6), corresponding to genomic positions 140753336 to 140753337 on chromosome 7 (refseq:NC_000007.14, GRCh38).
      extensions:
        - name: GRCh38 1-based, inclusive interval
          value: chr7:140753336-140753337
          description: Genomic positions 140,753,336 to 140,753,337 on chromosome 7 (refseq:NC_000007.14, GRCh38); 1-based, inclusive interval notation.
        - name: GRCh38 0-based, half-open interval
          value: chr7:140753335-140753337
          description: Genomic positions 140,753,335 to 140,753,337 on chromosome 7 (refseq:NC_000007.14, GRCh38); 0-based, half-open interval notation.
      type: SequenceLocation
      digest: SXY8ShFrBAfSvtO_sXLMQKN3Ozc5awgh
      sequenceReference:
        id: refseq:NM_004333.6
        name: NM_004333.6
        description: The MANE Select (GRCh38) coding transcript for BRAF.
        aliases:
          - ga4gh:SQ.aKMPEJgmlZXt_F6gRY5cUG3THH2n-GUa
        type: SequenceReference
        refgetAccession: SQ.aKMPEJgmlZXt_F6gRY5cUG3THH2n-GUa
        residueAlphabet: na
      start: 2023
      end: 2025
      sequence: GT
    state:
      type: LiteralSequenceExpression
      sequence: AA
  - id: ga4gh:VA.PEphL_4Hx5JYuJPMzgu0pRQIUcz_J9p0
    type: Allele
    name: NM_004333.6:c.1799T>G
    description: VRS variation of NM_004333.6:c.1799T>G, generated with the VICC Variation Normalizer (https://github.com/cancervariants/variation-normalization).
    digest: PEphL_4Hx5JYuJPMzgu0pRQIUcz_J9p0
    expressions:
      - syntax: hgvs.c
        value: NM_004333.6:c.1799T>G
    location:
      id: ga4gh:SL.8HBKs9fzlT3tKWlM03REjkg_0Om6Y33U
      description: Coding DNA (cDNA) positions 1799 of the BRAF MANE Select coding transcript (refseq:NM_004333.6), corresponding to genomic position 140753336 on chromosome 7 (refseq:NC_000007.14, GRCh38).
      extensions:
        - name: GRCh38 1-based, genomic position
          value: chr7:140753336
          description: Genomic position 140,753,336 on chromosome 7 (refseq:NC_000007.14, GRCh38).
        - name: GRCh38 1-based, inclusive interval
          value: chr7:140753336-140753336
          description: Genomic positions 140,753,336 to 140,753,336 on chromosome 7 (refseq:NC_000007.14, GRCh38); 1-based, inclusive interval notation.
        - name: GRCh38 0-based, half-open interval
          value: chr7:140753335-140753336
          description: Genomic positions 140,753,335 to 140,753,336 on chromosome 7 (refseq:NC_000007.14, GRCh38); 0-based, half-open interval notation.
      type: SequenceLocation
      digest: 8HBKs9fzlT3tKWlM03REjkg_0Om6Y33U
      sequenceReference:
        id: refseq:NM_004333.6
        name: NM_004333.6
        description: The MANE Select (GRCh38) coding transcript for BRAF.
        aliases:
          - ga4gh:SQ.aKMPEJgmlZXt_F6gRY5cUG3THH2n-GUa
        type: SequenceReference
        refgetAccession: SQ.aKMPEJgmlZXt_F6gRY5cUG3THH2n-GUa
        residueAlphabet: na
      start: 2024
      end: 2025
      sequence: T
    state:
      type: LiteralSequenceExpression
      sequence: G
  - id: ga4gh:VA.O3Wd-kD48Dl1ihRUuf4vVybLaXYKFXnk
    name: NM_004333.6:c.1798G>A
    description: VRS variation of NM_004333.6:c.1799T>A, generated with the VICC Variation Normalizer (https://github.com/cancervariants/variation-normalization).
    digest: O3Wd-kD48Dl1ihRUuf4vVybLaXYKFXnk
    expressions:
      - syntax: hgvs.c
        value: NM_004333.6:c.1798G>A
    type: Allele
    location:
      id: ga4gh:SL.1ReS370wzmC9PGTn13XrnG8Ot7UAKYuw
      description: Coding DNA (cDNA) position 1798 of the BRAF MANE Select coding transcript (refseq:NM_004333.6), corresponding to genomic position 140753337 on chromosome 7 (refseq:NC_000007.14, GRCh38).
      extensions:
        - name: GRCh38 1-based, genomic position
          value: chr7:140753337
          description: Genomic position 140,753,337 on chromosome 7 (refseq:NC_000007.14, GRCh38).
        - name: GRCh38 1-based, inclusive interval
          value: chr7:140753337-140753337
          description: Genomic positions 140,753,337 to 140,753,337 on chromosome 7 (refseq:NC_000007.14, GRCh38); 1-based, inclusive interval notation.
        - name: GRCh38 0-based, half-open interval
          value: chr7:140753336-140753337
          description: Genomic positions 140,753,336 to 140,753,337 on chromosome 7 (refseq:NC_000007.14, GRCh38); 0-based, half-open interval notation.
      type: SequenceLocation
      digest: 1ReS370wzmC9PGTn13XrnG8Ot7UAKYuw
      sequenceReference:
        id: refseq:NM_004333.6
        name: NM_004333.6
        description: The MANE Select (GRCh38) coding transcript for BRAF.
        aliases:
          - ga4gh:SQ.aKMPEJgmlZXt_F6gRY5cUG3THH2n-GUa
        type: SequenceReference
        refgetAccession: SQ.aKMPEJgmlZXt_F6gRY5cUG3THH2n-GUa
        residueAlphabet: na
      start: 2024
      end: 2025
      sequence: G
    state:
      type: LiteralSequenceExpression
      sequence: A
  - id: ga4gh:VA.t97D17VsbiAa2U-znA-Qfx6DVInBd-_-
    type: Allele
    name: NM_004333.6:c.1798_1799delinsAG
    description: VRS variation of NM_004333.6:c.1799T>A, generated with the VICC Variation Normalizer (https://github.com/cancervariants/variation-normalization).
    digest: t97D17VsbiAa2U-znA-Qfx6DVInBd-_-
    expressions:
      - syntax: hgvs.c
        value: NM_004333.6:c.1798_1799delinsAG
    location:
      id: ga4gh:SL.SXY8ShFrBAfSvtO_sXLMQKN3Ozc5awgh
      description: Coding DNA (cDNA) positions 1798 to 1799 of the BRAF MANE Select coding transcript (refseq:NM_004333.6), corresponding to genomic positions 140753336 to 140753337 on chromosome 7 (refseq:NC_000007.14, GRCh38).
      extensions:
        - name: GRCh38 1-based, inclusive interval
          value: chr7:140753336-140753337
          description: Genomic positions 140,753,336 to 140,753,337 on chromosome 7 (refseq:NC_000007.14, GRCh38); 1-based, inclusive interval notation.
        - name: GRCh38 0-based, half-open interval
          value: chr7:140753335-140753337
          description: Genomic positions 140,753,335 to 140,753,337 on chromosome 7 (refseq:NC_000007.14, GRCh38); 0-based, half-open interval notation.
      type: SequenceLocation
      digest: SXY8ShFrBAfSvtO_sXLMQKN3Ozc5awgh
      sequenceReference:
        id: refseq:NM_004333.6
        name: NM_004333.6
        description: The MANE Select (GRCh38) coding transcript for BRAF.
        aliases:
          - ga4gh:SQ.aKMPEJgmlZXt_F6gRY5cUG3THH2n-GUa
        type: SequenceReference
        refgetAccession: SQ.aKMPEJgmlZXt_F6gRY5cUG3THH2n-GUa
        residueAlphabet: na
      start: 2023
      end: 2025
      sequence: GT
    state:
      type: LiteralSequenceExpression
      sequence: AG