proteinSequenceConsequence-ex1.yaml

id: civic.mpid:33
type: CategoricalVariant
name: EGFR L858R
description: >-
  EGFR L858R has long been recognized as a functionally significant mutation in cancer,
  and is one of the most prevalent single mutations in lung cancer. Best described in
  non-small cell lung cancer (NSCLC), the mutation seems to confer sensitivity to first
  and second generation TKI's like gefitinib and neratinib. NSCLC patients with this
  mutation treated with TKI's show increased overall and progression-free survival, as
  compared to chemotherapy alone. Third generation TKI's are currently in clinical trials
  that specifically focus on mutant forms of EGFR, a few of which have shown efficacy in
  treating patients that failed to respond to earlier generation TKI therapies.
aliases:
  - LEU858ARG
  - rs121434568
  - L813R
  - LEU813ARG
  - NC_000007.13:g.55259515T>G
  - NM_005228.4:c.2573T>G
  - ENST00000275493.2:c.2573T>G
  - ENST00000275493.7:c.2573T>G
  - NP_005219.2:p.Leu858Arg
extensions:
  - name: CIViC Representative Variant Coordinates
    value:
      chromosome: '7'
      start: 55259515
      stop: 55259515
      reference_bases: T
      variant_bases: G
      representative_transcript: ENST00000275493.2
      ensembl_version: 75
      reference_build: GRCh37
  - name: CIViC Variant Type
    value:
      name: missense_variant
      system: http://www.sequenceontology.org/browser/
      systemVersion: release_2.5.3
      code: SO:0001583
      iris:
        - http://www.sequenceontology.org/browser/release_2.5.3/term/SO:0001583
  - name: CIViC Molecular Profile Score
    value: 379
  - name: hgvs list
    value:
      - nucleotideExpression:
          syntax: hgvs.g
          value: NC_000007.13:g.55259515T>G
        nucleotideType: genomic
      - nucleotideExpression:
          syntax: hgvs.c
          value: NM_005228.5:c.2573T>G
        nucleotideType: coding
      - nucleotideExpression:
          syntax: hgvs.c
          value: ENST00000275493.2:c.2573T>G
        nucleotideType: coding
      - nucleotideExpression:
          syntax: hgvs.c
          value: ENST00000275493.7:c.2573T>G
        nucleotideType: coding
        maneSelect: true
        proteinExpression:
          syntax: hgvs.p
          value: NP_005219.2:p.Leu858Arg
        molecularConsequence:
          name: missense_variant
          system: http://www.sequenceontology.org/browser/
          systemVersion: release_2.5.3
          code: SO:0001583
          iris:
            - http://www.sequenceontology.org/browser/release_2.5.3/term/SO:0001583
constraints:
  - type: DefiningAlleleConstraint
    allele:
      id: ga4gh:VA.S41CcMJT2bcd8R4-qXZWH1PoHWNtG2PZ
      type: Allele
      name: NP_005219.2:p.Leu858Arg
      description: VRS variation of NP_005219.2:p.Leu858Arg, generated with the VICC Variation Normalizer (https://github.com/cancervariants/variation-normalization).
      digest: S41CcMJT2bcd8R4-qXZWH1PoHWNtG2PZ
      expressions:
        - syntax: hgvs.p
          value: NP_005219.2:p.Leu858Arg
      location:
        id: ga4gh:SL.v0_edynH98OIu-0QPVT5anCSOriAFSDQ
        description: Amino acid position 858 within the EGFR protein (refseq:NP_005219.2), which is the protein product of the MANE Select (GRCh38) coding transcript for EGFR (refseq:NM_005228.5), corresponding to leucine in the reference sequence.
        type: SequenceLocation
        digest: v0_edynH98OIu-0QPVT5anCSOriAFSDQ
        sequenceReference:
          id: refseq:NP_005219.2
          name: NP_005219.2
          description: The protein product of the MANE Select (GRCh38) coding transcript for EGFR (refseq:NM_005228.5), corresponding to the RefSeq protein accession NP_005219.2.
          aliases:
            - ensembl:ENSP00000275493.2
            - ga4gh:SQ.vyo55F6mA6n2LgN4cagcdRzOuh38V4mE
          type: SequenceReference
          refgetAccession: SQ.vyo55F6mA6n2LgN4cagcdRzOuh38V4mE
          residueAlphabet: aa
        start: 857
        end: 858
        sequence: L
      state:
        type: LiteralSequenceExpression
        sequence: R
    relations:
      - primaryCoding:
          code: translation_of
          system: http://www.sequenceontology.org
          iris:
            - http://www.sequenceontology.org/browser/current_release/term/translation_of
mappings:
  - coding:
      system: https://civicdb.org/variants/
      code: '33'
      iris:
        - https://civicdb.org/variants/33/summary
    relation: exactMatch
  - coding:
      system: https://civicdb.org/molecular-profiles/
      code: '33'
      iris:
        - https://civicdb.org/molecular-profiles/33/summary
    relation: relatedMatch
  - coding:
      system: https://reg.clinicalgenome.org/
      code: CA126713
      iris:
        - https://reg.genome.network/redmine/projects/registry/genboree_registry/by_caid?caid=CA126713
    relation: relatedMatch
  - coding:
      system: https://www.ncbi.nlm.nih.gov/clinvar/variation/
      code: '16609'
      iris:
        - https://www.ncbi.nlm.nih.gov/clinvar/variation/16609/
    relation: relatedMatch
  - coding:
      system: https://www.ncbi.nlm.nih.gov/clinvar/variation/
      code: '376282'
      iris:
        - https://www.ncbi.nlm.nih.gov/clinvar/variation/376282/
    relation: relatedMatch
  - coding:
      system: https://www.ncbi.nlm.nih.gov/clinvar/variation/
      code: '376280'
      iris:
        - https://www.ncbi.nlm.nih.gov/clinvar/variation/376280/
    relation: relatedMatch
  - coding:
      system: https://www.ncbi.nlm.nih.gov/snp/
      code: rs121434568
      iris:
        - https://www.ncbi.nlm.nih.gov/snp/rs121434568
    relation: relatedMatch
members:
  - id: ga4gh:VA.7WF8GDGgqy8ksDf9KV-qrWS_2_q8fiEO
    type: Allele
    name: NC_000007.13:g.55259515T>G
    description: VRS variation of NC_000007.13:g.55259515T>G, generated with the VICC Variation Normalizer (https://github.com/cancervariants/variation-normalization).
    digest: 7WF8GDGgqy8ksDf9KV-qrWS_2_q8fiEO
    expressions:
      - syntax: hgvs.g
        value: NC_000007.13:g.55259515T>G
      - syntax: hgvs.c
        value: NM_005228.5:c.2573T>G
      - syntax: hgvs.p
        value: NP_005219.2:p.Leu858Arg
    location:
      id: ga4gh:SL.FYIfdQ3NyatgqPT_kKMfeIbt00559Izo
      description: Genomic position 55,259,515 on chromosome 1 (refseq:NC_000007.13, GRCh38).
      extensions:
        - name: GRCh38 1-based, genomic position
          value: chr7:55259515
          description: Genomic position 55,259,515 on chromosome 1 (refseq:NC_000007.13, GRCh38).
        - name: GRCh38 1-based, inclusive interval notation
          value: chr1:55259515-55259515
          description: Genomic positions 55,259,515 to 55,259,515 on chromosome 1 (refseq:NC_000007.13, GRCh38); 1-based, inclusive interval notation.
        - name: GRCh38 0-based, half-open interval notation
          value: chr1:55259514-55259515
          description: Genomic positions 55,259,514 to 55,259,515 on chromosome 1 (refseq:NC_000007.13, GRCh38); 0-based, half-open interval notation.
      type: SequenceLocation
      digest: FYIfdQ3NyatgqPT_kKMfeIbt00559Izo
      sequenceReference:
        id: refseq:NC_000007.13
        name: NC_000007.13
        description: Reference sequence for GRCh38 chromosome 7.
        aliases:
          - GRCh38:7
          - GRCh38:chr7
          - ga4gh:SQ.IW78mgV5Cqf6M24hy52hPjyyo5tCCd86
        type: SequenceReference
        refgetAccession: SQ.IW78mgV5Cqf6M24hy52hPjyyo5tCCd86
        residueAlphabet: na
      start: 55259514
      end: 55259515
      sequence: AT
    state:
      type: LiteralSequenceExpression
      sequence: G
  - id: ga4gh:VA.gV7_dnvF8SQSeUdvgDFhU65zK_csc6VE
    type: Allele
    name: NM_005228.5:c.2573T>G
    description: VRS variation of NM_005228.5:c.2573T>G, generated with the VICC Variation Normalizer (https://github.com/cancervariants/variation-normalization).
    digest: gV7_dnvF8SQSeUdvgDFhU65zK_csc6VE
    expressions:
      - syntax: hgvs.g
        value: NC_000007.13:g.55259515T>G
      - syntax: hgvs.c
        value: NM_005228.5:c.2573T>G
      - syntax: hgvs.p
        value: NP_005219.2:p.Leu858Arg
    location:
      id: ga4gh:SL.LREsUiEYvOrRhwXW1rG72kXFPegvkNzI
      description: Coding DNA (cDNA) position 2573 of the EGFR MANE Select coding transcript (refseq:NM_005228.5), corresponding to genomic position 55259515 on chromosome 7 (refseq:NC_000007.13, GRCh38).
      extensions:
        - name: GRCh38 1-based, genomic position
          value: chr7:55259515
          description: Genomic position 55,259,515 on chromosome 1 (refseq:NC_000007.13, GRCh38).
        - name: GRCh38 1-based, inclusive interval notation
          value: chr7:55259515-55259515
          description: Genomic positions 55,259,515 to 55,259,515 on chromosome 1 (refseq:NC_000007.13, GRCh38); 1-based, inclusive interval notation.
        - name: GRCh38 0-based, half-open interval notation
          value: chr7:55259514-55259515
          description: Genomic positions 55,259,514 to 55,259,515 on chromosome 1 (refseq:NC_000007.13, GRCh38); 0-based, half-open interval notation.
      type: SequenceLocation
      digest: LREsUiEYvOrRhwXW1rG72kXFPegvkNzI
      sequenceReference:
        id: refseq:NM_005228.5
        name: NM_005228.5
        description: The MANE Select (GRCh38) coding transcript for EGFR.
        aliases:
          - ensembl:ENST00000275493.7
          - ga4gh:SQ.d_QsP29RWJi6bac7GOC9cJ9AO7s_HUMN
        type: SequenceReference
        refgetAccession: SQ.d_QsP29RWJi6bac7GOC9cJ9AO7s_HUMN
        residueAlphabet: na
      start: 2833
      end: 2834
      sequence: T
    state:
      type: LiteralSequenceExpression
      sequence: G
  - id: ga4gh:VA.S41CcMJT2bcd8R4-qXZWH1PoHWNtG2PZ
    type: Allele
    name: NP_005219.2:p.Leu858Arg
    description: VRS variation of NP_005219.2:p.Leu858Arg, generated with the VICC Variation Normalizer (https://github.com/cancervariants/variation-normalization).
    digest: S41CcMJT2bcd8R4-qXZWH1PoHWNtG2PZ
    expressions:
      - syntax: hgvs.g
        value: NC_000007.13:g.55259515T>G
      - syntax: hgvs.c
        value: NM_005228.5:c.2573T>G
      - syntax: hgvs.p
        value: NP_005219.2:p.Leu858Arg
    location:
      id: ga4gh:SL.v0_edynH98OIu-0QPVT5anCSOriAFSDQ
      description: Amino acid position 858 of the RefSeq protein NP_005219.2, which is the protein product of the MANE Select (GRCh38) coding transcript for EGFR (refseq:NM_005228.5).
      type: SequenceLocation
      digest: v0_edynH98OIu-0QPVT5anCSOriAFSDQ
      sequenceReference:
        id: refseq:NP_005219.2
        name: NP_005219.2
        description: The protein product of the MANE Select (GRCh38) coding transcript for EGFR (refseq:NM_005228.5), corresponding to the RefSeq protein accession NP_005219.2.
        aliases:
          - ensembl:ENSP00000275493.2
          - ga4gh:SQ.vyo55F6mA6n2LgN4cagcdRzOuh38V4mE
        type: SequenceReference
        refgetAccession: SQ.vyo55F6mA6n2LgN4cagcdRzOuh38V4mE
        residueAlphabet: aa
      start: 857
      end: 858
      sequence: L
    state:
      type: LiteralSequenceExpression
      sequence: R