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/B5UBC1.json
  retrieved_at: '2026-10-18T23:38:49.610001+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/uniprotkb/Q2QZF2.json
  retrieved_at: '2026-10-18T23:38:49.781867+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/proteomes/UP000059680.json
  retrieved_at: '2026-10-18T23:38:50.020661+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/B5UBC1?format=txt&versions=28
  retrieved_at: '2026-10-18T23:38:52.123577+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/B5UBC1?format=txt&versions=50
  retrieved_at: '2026-10-18T23:38:55.658824+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/B5UBC1?format=txt&versions=64
  retrieved_at: '2026-10-18T23:38:57.549715+00:00'
  uniprot_release: '2026_03'
observations:
  primary_accession: B5UBC1
  alternative_accession: Q2QZF2
  sequence_identical: false
  primary_sequence_length: 1143
  alternative_sequence_length: 1125
  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:
  - 28
  - 50
  - 64
  sampled_versions_with_proteome_links: []
current_records:
- primaryAccession: B5UBC1
  entryType: UniProtKB reviewed (Swiss-Prot)
  entryAudit:
    firstPublicDate: '2018-07-18'
    lastAnnotationUpdateDate: '2026-09-02'
    lastSequenceUpdateDate: '2008-11-25'
    entryVersion: 69
    sequenceVersion: 1
  genes:
  - geneName:
      evidences:
      - evidenceCode: ECO:0000312
        source: EMBL
        id: BAG71909.1
      value: PIKM1-TS
    synonyms:
    - evidences:
      - evidenceCode: ECO:0000312
        source: EMBL
        id: ADE80944.1
      - evidenceCode: ECO:0000312
        source: EMBL
        id: ADE80945.1
      - evidenceCode: ECO:0000312
        source: EMBL
        id: ADE80946.1
      - evidenceCode: ECO:0000312
        source: EMBL
        id: ADE80948.1
      - evidenceCode: ECO:0000312
        source: EMBL
        id: ADE80951.1
      value: PI-KM1
  organism:
    scientificName: Oryza sativa subsp. japonica
    taxonId: 39947
  sequence:
    length: 1143
    sha256: c0eb25a3645feba54d2016ad41125fc57a3938807e46be2d5ef1e80f279bbf61
  uniProtKBCrossReferences: []
- primaryAccession: Q2QZF2
  entryType: UniProtKB reviewed (Swiss-Prot)
  entryAudit:
    firstPublicDate: '2018-07-18'
    lastAnnotationUpdateDate: '2026-09-02'
    lastSequenceUpdateDate: '2006-01-24'
    entryVersion: 111
    sequenceVersion: 1
  genes:
  - geneName:
      evidences:
      - evidenceCode: ECO:0000303
        source: PubMed
        id: '18940787'
      value: PIK5-NP
    synonyms:
    - evidences:
      - evidenceCode: ECO:0000312
        source: EMBL
        id: BAH79844.1
      - evidenceCode: ECO:0000312
        source: EMBL
        id: BAH79845.1
      - evidenceCode: ECO:0000312
        source: EMBL
        id: BAH79846.1
      value: PIKM1
    orderedLocusNames:
    - evidences:
      - evidenceCode: ECO:0000312
        source: EMBL
        id: BAT15296.1
      value: Os11g0688832
    - evidences:
      - evidenceCode: ECO:0000312
        source: EMBL
        id: ABA95385.1
      value: LOC_Os11g46200
  organism:
    scientificName: Oryza sativa subsp. japonica
    taxonId: 39947
  sequence:
    length: 1125
    sha256: 4196f33690ee5dc4519cac7eae97db175c8f5037cc90c3eeb3846c248a7b4fdf
  uniProtKBCrossReferences:
  - database: Gramene
    id: Os11t0688832-01
    properties:
    - key: ProteinId
      value: Os11t0688832-01
    - key: GeneId
      value: Os11g0688832
  - 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: 28
  url: https://rest.uniprot.org/unisave/B5UBC1?format=txt&versions=28
  entry_date: 09-DEC-2015, entry version 28.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 50
  url: https://rest.uniprot.org/unisave/B5UBC1?format=txt&versions=50
  entry_date: 11-DEC-2019, entry version 50.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 64
  url: https://rest.uniprot.org/unisave/B5UBC1?format=txt&versions=64
  entry_date: 27-NOV-2024, entry version 64.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
archived_sources:
- path: genes/ORYSJ/PIKM1-TS/PIKM1-TS-record-evidence.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/ORYSJ/PIKM1-TS/PIKM1-TS-record-evidence.yaml
  sha256: 126b62e29461d440ff18a5c7dfcfba65694fe6f7492640783b06dffdd2f3e5fa
  excerpts:
  - start_line: 26
    end_line: 38
    text: |2
        alternative_sequence_length: 1125
        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:
        - 28
  - start_line: 88
    end_line: 92
    text: |2
              source: EMBL
              id: BAG71909.1
            value: PIKM1-TS
          synonyms:
          - evidences:
  - start_line: 1048
    end_line: 1052
    text: |2
              source: PubMed
              id: '18940787'
            value: PIK5-NP
          synonyms:
          - evidences:
  - start_line: 1060
    end_line: 1064
    text: |2
              source: EMBL
              id: BAH79846.1
            value: PIKM1
          orderedLocusNames:
          - evidences:
  - start_line: 1084
    end_line: 1088
    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 cultivar Kusabue, the cultivar Nipponbare doesn't recognize the effector avirulence protein AVR-Pik from
              M.oryzae
          commentType: FUNCTION
  - start_line: 2151
    end_line: 2156
    text: |
      - entry_version: 28
        url: https://rest.uniprot.org/unisave/B5UBC1?format=txt&versions=28
        entry_date: 09-DEC-2015, entry version 28.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 2236
    end_line: 2241
    text: |
      - entry_version: 50
        url: https://rest.uniprot.org/unisave/B5UBC1?format=txt&versions=50
        entry_date: 11-DEC-2019, entry version 50.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 2433
    end_line: 2438
    text: |
      - entry_version: 64
        url: https://rest.uniprot.org/unisave/B5UBC1?format=txt&versions=64
        entry_date: 27-NOV-2024, entry version 64.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
- path: genes/ORYSJ/PIKM1-TS/PIKM1-TS-bioinformatics/reference-counterparts/comparison.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/ORYSJ/PIKM1-TS/PIKM1-TS-bioinformatics/reference-counterparts/comparison.yaml
  sha256: 63b9256c1da3fd748576b2518590e3e80251db1192923e9ea825e7085eb699ad
  excerpts:
  - start_line: 25
    end_line: 29
    text: |2
        - -v
        - '1'
        target_sequence_count: 48896
        query_sha256: d05dfd512d15f04651d7eaaf65aec5447ab5255009594536ad746729ad3684e9
        targets_sha256: b38f535a59131e6ea44278e4d553bf418972dbcbda74cb374e7445844dc51963
  - start_line: 44
    end_line: 48
    text: |2
          sha256: b38f535a59131e6ea44278e4d553bf418972dbcbda74cb374e7445844dc51963
        detailed_alignment_limit: 10
      candidate_count: 384
      candidates:
      - accession: Q2QZF2
  - start_line: 52
    end_line: 64
    text: |2
        bit_score: 1188.0
        global_score: 3081.0
        query_length: 1143
        target_length: 1125
        alignment_columns: 1193
        identities: 697
        mismatches: 378
        gap_columns: 118
        identity_percent: 58.4241
        query_coverage_percent: 94.0507
        target_coverage_percent: 95.5556
        substitutions:
        - query_position: 6
comparison:
  provenance:
    query_accession: B5UBC1
    run_at: '2026-10-18T23:33:12.553250+00:00'
    biopython_version: '1.85'
    mmseqs_version: 18-8cc5c
    command:
    - mmseqs
    - easy-search
    - genes/ORYSJ/PIKM1-TS/PIKM1-TS-bioinformatics/reference-counterparts/query.fasta
    - .cache/orphan-curated/UP000059680.fasta
    - genes/ORYSJ/PIKM1-TS/PIKM1-TS-bioinformatics/reference-counterparts/search.tsv
    - genes/ORYSJ/PIKM1-TS/PIKM1-TS-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: d05dfd512d15f04651d7eaaf65aec5447ab5255009594536ad746729ad3684e9
    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: 384
  retained_alignment_count: 10
  candidates:
  - accession: Q2QZF2
    description: sp|Q2QZF2|PIK5_ORYSJ Disease resistance protein PIK5-NP OS=Oryza sativa subsp. japonica
      OX=39947 GN=PIK5-NP PE=2 SV=1
    evalue: 0.0
    bit_score: 1188.0
    global_score: 3081.0
    query_length: 1143
    target_length: 1125
    alignment_columns: 1193
    identities: 697
    mismatches: 378
    gap_columns: 118
    identity_percent: 58.4241
    query_coverage_percent: 94.0507
    target_coverage_percent: 95.5556
  - accession: Q6Z011
    description: tr|Q6Z011|Q6Z011_ORYSJ Os08g0388300 protein OS=Oryza sativa subsp. japonica OX=39947
      GN=Os08g0388300 PE=1 SV=1
    evalue: 1.252e-63
    bit_score: 241.0
    global_score: 748.0
    query_length: 1143
    target_length: 974
    alignment_columns: 1230
    identities: 318
    mismatches: 569
    gap_columns: 343
    identity_percent: 25.8537
    query_coverage_percent: 77.6028
    target_coverage_percent: 91.0678
