snapshot_type: uniprot_record_evidence_extract
archive:
  repository: https://github.com/ai4curation/uniprot-orphan-analysis
  commit: f6a331cb47f61256ad070bbaa75567094ef64e8a
extraction: Original source line ranges with two context lines; not complete records. Structured fields
  are selected from the same archived snapshots. Sequence values are replaced by lengths and SHA-256 digests.
sources:
- url: https://rest.uniprot.org/uniprotkb/F7J0M4.json
  retrieved_at: '2026-10-18T23:38:56.253174+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/uniprotkb/F7J0M6.json
  retrieved_at: '2026-10-18T23:38:56.417350+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/proteomes/UP000059680.json
  retrieved_at: '2026-10-18T23:38:56.578089+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/F7J0M4?format=txt&versions=17
  retrieved_at: '2026-10-18T23:39:00.435303+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/F7J0M4?format=txt&versions=38
  retrieved_at: '2026-10-18T23:39:01.143621+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/F7J0M4?format=txt&versions=48
  retrieved_at: '2026-10-18T23:39:02.446326+00:00'
  uniprot_release: '2026_03'
observations:
  primary_accession: F7J0M4
  alternative_accession: F7J0M6
  sequence_identical: false
  primary_sequence_length: 996
  alternative_sequence_length: 1014
  shared_uniparc_id: null
  same_taxon: true
  reference_proteome: UP000059680
  proteome_is_reference: true
  proteome_taxon_matches: true
  primary_in_reference_proteome: false
  alternative_in_reference_proteome: true
  searched_reference_proteomes:
  - UP000059680
  primary_in_any_reference_proteome: false
  sampled_history_versions:
  - 17
  - 38
  - 48
  sampled_versions_with_proteome_links: []
current_records:
- primaryAccession: F7J0M4
  entryType: UniProtKB reviewed (Swiss-Prot)
  entryAudit:
    firstPublicDate: '2018-07-18'
    lastAnnotationUpdateDate: '2026-09-02'
    lastSequenceUpdateDate: '2011-09-21'
    entryVersion: 53
    sequenceVersion: 1
  genes:
  - geneName:
      evidences:
      - evidenceCode: ECO:0000303
        source: PubMed
        id: '21251109'
      value: RGA4
    synonyms:
    - evidences:
      - evidenceCode: ECO:0000303
        source: PubMed
        id: '21251109'
      value: PIA
  organism:
    scientificName: Oryza sativa subsp. japonica
    taxonId: 39947
  sequence:
    length: 996
    sha256: 7208c821f7e4518dbb9216779120a9efc2bda360cece05692dd79c65fb952379
  uniProtKBCrossReferences: []
- primaryAccession: F7J0M6
  entryType: UniProtKB reviewed (Swiss-Prot)
  entryAudit:
    firstPublicDate: '2018-07-18'
    lastAnnotationUpdateDate: '2026-09-02'
    lastSequenceUpdateDate: '2011-09-21'
    entryVersion: 66
    sequenceVersion: 1
  genes:
  - geneName:
      evidences:
      - evidenceCode: ECO:0000303
        source: PubMed
        id: '21251109'
      value: RGA4
    orderedLocusNames:
    - evidences:
      - evidenceCode: ECO:0000312
        source: EMBL
        id: BAT13283.1
      value: Os11g0225100
    - evidences:
      - evidenceCode: ECO:0000312
        source: EMBL
        id: ABA92206.2
      value: LOC_Os11g11790
  organism:
    scientificName: Oryza sativa subsp. japonica
    taxonId: 39947
  sequence:
    length: 1014
    sha256: aa3fb4d0e26115c21c3da7b0f042a7ba973313f24b43bd4b148ec8bff29da94c
  uniProtKBCrossReferences:
  - database: Gramene
    id: Os11t0225100-01
    properties:
    - key: ProteinId
      value: Os11t0225100-01
    - key: GeneId
      value: Os11g0225100
  - database: Proteomes
    id: UP000059680
    properties:
    - key: Component
      value: Chromosome 11
reference_proteomes:
- id: UP000059680
  proteomeType: Reference proteome
  taxonomy:
    scientificName: Oryza sativa subsp. japonica
    commonName: Rice
    taxonId: 39947
    mnemonic: ORYSJ
unisave_records:
- entry_version: 17
  url: https://rest.uniprot.org/unisave/F7J0M4?format=txt&versions=17
  entry_date: 09-DEC-2015, entry version 17.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 38
  url: https://rest.uniprot.org/unisave/F7J0M4?format=txt&versions=38
  entry_date: 12-AUG-2020, entry version 38.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 48
  url: https://rest.uniprot.org/unisave/F7J0M4?format=txt&versions=48
  entry_date: 27-NOV-2024, entry version 48.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
archived_sources:
- path: genes/ORYSJ/RGA4/RGA4-record-evidence.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/ORYSJ/RGA4/RGA4-record-evidence.yaml
  sha256: 016729cc5fc734c209d12f1a5f2fcb0107d7b123500e593320981f421118ec4c
  excerpts:
  - start_line: 26
    end_line: 38
    text: |2
        alternative_sequence_length: 1014
        shared_uniparc_id: null
        same_taxon: true
        reference_proteome: UP000059680
        proteome_is_reference: true
        proteome_taxon_matches: true
        primary_in_reference_proteome: false
        alternative_in_reference_proteome: true
        searched_reference_proteomes:
        - UP000059680
        primary_in_any_reference_proteome: false
        sampled_history_versions:
        - 17
  - start_line: 946
    end_line: 955
    text: |2
              source: EMBL
              id: BAT13283.1
            value: Os11g0225100
          - evidences:
            - evidenceCode: ECO:0000312
              source: EMBL
              id: ABA92206.2
            value: LOC_Os11g11790
        comments:
        - texts:
  - start_line: 961
    end_line: 965
    text: |2
              an appropriate avirulence protein via an indirect interaction with this avirulence protein. That triggers
              a defense system including the hypersensitive response, which restricts the pathogen growth. At the opposite
              of cultivars Aichi asahi and Sasanishiki, the cultivars Nipponbare, Mokoto and Hitomebore don't recognize
              the effector avirulence protein AVR-Pia from M.oryzae
          commentType: FUNCTION
  - start_line: 1456
    end_line: 1460
    text: |2
            value: Os11t0225100-01
          - key: GeneId
            value: Os11g0225100
        - database: Gramene
          id: Os11t0225100-01
  - start_line: 1463
    end_line: 1467
    text: |2
            value: Os11t0225100-01
          - key: GeneId
            value: Os11g0225100
        - database: KEGG
          id: dosa:Os11g0225100
  - start_line: 2100
    end_line: 2105
    text: |
      - entry_version: 17
        url: https://rest.uniprot.org/unisave/F7J0M4?format=txt&versions=17
        entry_date: 09-DEC-2015, entry version 17.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 2171
    end_line: 2176
    text: |
      - entry_version: 38
        url: https://rest.uniprot.org/unisave/F7J0M4?format=txt&versions=38
        entry_date: 12-AUG-2020, entry version 38.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 2361
    end_line: 2366
    text: |
      - entry_version: 48
        url: https://rest.uniprot.org/unisave/F7J0M4?format=txt&versions=48
        entry_date: 27-NOV-2024, entry version 48.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
- path: genes/ORYSJ/RGA4/RGA4-bioinformatics/reference-counterparts/comparison.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/ORYSJ/RGA4/RGA4-bioinformatics/reference-counterparts/comparison.yaml
  sha256: 4d0c0223cbcbc12c85c82491ebb2bbef6af3b82537dc2369131da6cc8d492d26
  excerpts:
  - start_line: 25
    end_line: 29
    text: |2
        - -v
        - '1'
        target_sequence_count: 48896
        query_sha256: f438f46d720abbe6f1b5b803e2ec2d4020199c216894a25ffffdaa192a22566a
        targets_sha256: b38f535a59131e6ea44278e4d553bf418972dbcbda74cb374e7445844dc51963
  - start_line: 44
    end_line: 48
    text: |2
          sha256: b38f535a59131e6ea44278e4d553bf418972dbcbda74cb374e7445844dc51963
        detailed_alignment_limit: 10
      candidate_count: 358
      candidates:
      - accession: F7J0M6
  - start_line: 52
    end_line: 64
    text: |2
        bit_score: 1879.0
        global_score: 4845.0
        query_length: 996
        target_length: 1014
        alignment_columns: 1017
        identities: 951
        mismatches: 42
        gap_columns: 24
        identity_percent: 93.5103
        query_coverage_percent: 99.6988
        target_coverage_percent: 97.929
        substitutions:
        - query_position: 22
comparison:
  provenance:
    query_accession: F7J0M4
    run_at: '2026-10-18T23:33:39.433600+00:00'
    biopython_version: '1.85'
    mmseqs_version: 18-8cc5c
    command:
    - mmseqs
    - easy-search
    - genes/ORYSJ/RGA4/RGA4-bioinformatics/reference-counterparts/query.fasta
    - .cache/orphan-curated/UP000059680.fasta
    - genes/ORYSJ/RGA4/RGA4-bioinformatics/reference-counterparts/search.tsv
    - genes/ORYSJ/RGA4/RGA4-bioinformatics/reference-counterparts/tmp
    - --threads
    - '4'
    - -s
    - '7.5'
    - -e
    - 1e-5
    - --max-seqs
    - '1000'
    - --format-output
    - query,target,pident,alnlen,qstart,qend,qlen,tstart,tend,tlen,evalue,bits
    - --remove-tmp-files
    - '1'
    - -v
    - '1'
    target_sequence_count: 48896
    query_sha256: f438f46d720abbe6f1b5b803e2ec2d4020199c216894a25ffffdaa192a22566a
    targets_sha256: b38f535a59131e6ea44278e4d553bf418972dbcbda74cb374e7445844dc51963
    global_alignment:
      mode: global
      matrix: BLOSUM62
      open_gap: -10
      extend_gap: -0.5
      terminal_gaps_penalized: true
    identity_denominator: All global alignment columns, including gaps
    coverage_denominator: Full query/target length; numerator is paired nongap residues
    limitation: MMseqs2 heuristic search; no guarantee of exhaustive retrieval or locus equivalence
    target_source:
      url: https://rest.uniprot.org/uniprotkb/stream?query=proteome%3AUP000059680&format=fasta
      retrieved_at: '2026-10-18T23:32:29.836656+00:00'
      uniprot_release: '2026_03'
      sequence_count: 48896
      sha256: b38f535a59131e6ea44278e4d553bf418972dbcbda74cb374e7445844dc51963
    detailed_alignment_limit: 10
  candidate_count: 358
  retained_alignment_count: 10
  candidates:
  - accession: F7J0M6
    description: sp|F7J0M6|RGA4S_ORYSJ Disease resistance protein RGA4 OS=Oryza sativa subsp. japonica
      OX=39947 GN=RGA4 PE=2 SV=1
    evalue: 0.0
    bit_score: 1879.0
    global_score: 4845.0
    query_length: 996
    target_length: 1014
    alignment_columns: 1017
    identities: 951
    mismatches: 42
    gap_columns: 24
    identity_percent: 93.5103
    query_coverage_percent: 99.6988
    target_coverage_percent: 97.929
  - accession: A0A0P0Y1V1
    description: tr|A0A0P0Y1V1|A0A0P0Y1V1_ORYSJ Os11g0462500 protein OS=Oryza sativa subsp. japonica OX=39947
      GN=Os11g0462500 PE=3 SV=1
    evalue: 9.586e-219
    bit_score: 704.0
    global_score: 1851.5
    query_length: 996
    target_length: 989
    alignment_columns: 1030
    identities: 434
    mismatches: 521
    gap_columns: 75
    identity_percent: 42.1359
    query_coverage_percent: 95.8835
    target_coverage_percent: 96.5622
