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/A6Q0K5.json
  retrieved_at: '2026-10-18T23:38:45.566064+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/uniprotkb/A0A2K3DI03.json
  retrieved_at: '2026-10-18T23:38:46.129295+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/proteomes/UP000006906.json
  retrieved_at: '2026-10-18T23:38:47.116798+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/A6Q0K5?format=txt&versions=31
  retrieved_at: '2026-10-18T23:38:49.928166+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/A6Q0K5?format=txt&versions=49
  retrieved_at: '2026-10-18T23:38:53.634750+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/A6Q0K5?format=txt&versions=65
  retrieved_at: '2026-10-18T23:38:55.437361+00:00'
  uniprot_release: '2026_03'
observations:
  primary_accession: A6Q0K5
  alternative_accession: A0A2K3DI03
  sequence_identical: false
  primary_sequence_length: 107
  alternative_sequence_length: 131
  shared_uniparc_id: null
  same_taxon: true
  reference_proteome: UP000006906
  proteome_is_reference: true
  proteome_taxon_matches: true
  primary_in_reference_proteome: false
  alternative_in_reference_proteome: true
  searched_reference_proteomes:
  - UP000006906
  primary_in_any_reference_proteome: false
  sampled_history_versions:
  - 31
  - 49
  - 65
  sampled_versions_with_proteome_links:
  - 31
current_records:
- primaryAccession: A6Q0K5
  entryType: UniProtKB reviewed (Swiss-Prot)
  entryAudit:
    firstPublicDate: '2007-09-11'
    lastAnnotationUpdateDate: '2026-09-02'
    lastSequenceUpdateDate: '2012-05-16'
    entryVersion: 69
    sequenceVersion: 2
  genes:
  - geneName:
      value: CP12
    orfNames:
    - value: CHLREDRAFT_148487
  organism:
    scientificName: Chlamydomonas reinhardtii
    taxonId: 3055
  sequence:
    length: 107
    sha256: 6d043a11e13d2e22450648dda7badb64c8347b1bbf2a3407915ee60163579a99
  uniProtKBCrossReferences: []
- primaryAccession: A0A2K3DI03
  entryType: UniProtKB unreviewed (TrEMBL)
  entryAudit:
    firstPublicDate: '2018-03-28'
    lastAnnotationUpdateDate: '2026-09-02'
    lastSequenceUpdateDate: '2018-03-28'
    entryVersion: 25
    sequenceVersion: 1
  genes:
  - orfNames:
    - evidences:
      - evidenceCode: ECO:0000313
        source: EMBL
        id: PNW80155.1
      value: CHLRE_08g380250v5
  organism:
    scientificName: Chlamydomonas reinhardtii
    taxonId: 3055
  sequence:
    length: 131
    sha256: 7d102cff0160d01a07ca0815660989d3487e55474ae75dd0e9e8713e0c499821
  uniProtKBCrossReferences:
  - database: Gramene
    id: PNW80155
    properties:
    - key: ProteinId
      value: PNW80155
    - key: GeneId
      value: CHLRE_08g380250v5
  - database: Proteomes
    id: UP000006906
    properties:
    - key: Component
      value: Chromosome 8
reference_proteomes:
- id: UP000006906
  proteomeType: Reference proteome
  taxonomy:
    scientificName: Chlamydomonas reinhardtii
    synonyms:
    - Chlamydomonas smithii
    taxonId: 3055
    mnemonic: CHLRE
unisave_records:
- entry_version: 31
  url: https://rest.uniprot.org/unisave/A6Q0K5?format=txt&versions=31
  entry_date: 11-NOV-2015, entry version 31.
  proteomes:
  - UP000006906
  reference_proteome_keyword: true
  record_text: ''
- entry_version: 49
  url: https://rest.uniprot.org/unisave/A6Q0K5?format=txt&versions=49
  entry_date: 07-OCT-2020, entry version 49.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 65
  url: https://rest.uniprot.org/unisave/A6Q0K5?format=txt&versions=65
  entry_date: 27-NOV-2024, entry version 65.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
archived_sources:
- path: genes/CHLRE/CP12/CP12-record-evidence.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/CHLRE/CP12/CP12-record-evidence.yaml
  sha256: d8687e2f37920acfe93dd684cf23dbf58b936196f8a1eb1c56a5ea75ca4f6098
  excerpts:
  - start_line: 26
    end_line: 38
    text: |2
        alternative_sequence_length: 131
        shared_uniparc_id: null
        same_taxon: true
        reference_proteome: UP000006906
        proteome_is_reference: true
        proteome_taxon_matches: true
        primary_in_reference_proteome: false
        alternative_in_reference_proteome: true
        searched_reference_proteomes:
        - UP000006906
        primary_in_any_reference_proteome: false
        sampled_history_versions:
        - 31
  - start_line: 497
    end_line: 501
    text: |2
            value: Genomic_DNA
        - database: RefSeq
          id: XP_001694345.2
          properties:
          - key: NucleotideSequenceId
  - start_line: 947
    end_line: 951
    text: |2
            value: Genomic_DNA
        - database: RefSeq
          id: XP_001694345.2
          properties:
          - key: NucleotideSequenceId
  - start_line: 1524
    end_line: 1530
    text: |
      - entry_version: 31
        url: https://rest.uniprot.org/unisave/A6Q0K5?format=txt&versions=31
        entry_date: 11-NOV-2015, entry version 31.
        proteomes:
        - UP000006906
        reference_proteome_keyword: true
        record_text: |
  - start_line: 1673
    end_line: 1678
    text: |
      - entry_version: 49
        url: https://rest.uniprot.org/unisave/A6Q0K5?format=txt&versions=49
        entry_date: 07-OCT-2020, entry version 49.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 1830
    end_line: 1835
    text: |
      - entry_version: 65
        url: https://rest.uniprot.org/unisave/A6Q0K5?format=txt&versions=65
        entry_date: 27-NOV-2024, entry version 65.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
- path: genes/CHLRE/CP12/CP12-bioinformatics/reference-counterparts/comparison.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/CHLRE/CP12/CP12-bioinformatics/reference-counterparts/comparison.yaml
  sha256: bc41730afd427f061b06d5cfcf131cc1b75e76679f4785c32902c0c8666364ca
  excerpts:
  - start_line: 25
    end_line: 29
    text: |2
        - -v
        - '1'
        target_sequence_count: 18840
        query_sha256: 264a89142e640e0fb64713881fa60cc0089dbeb943b56aaf5428671f96ef96c8
        targets_sha256: 3f9cb5324b0a7201c253b79f9e4e63a593691319ade81d6158597cd3efe93552
  - start_line: 44
    end_line: 48
    text: |2
          sha256: 3f9cb5324b0a7201c253b79f9e4e63a593691319ade81d6158597cd3efe93552
        detailed_alignment_limit: 10
      candidate_count: 1
      candidates:
      - accession: A0A2K3DI03
  - start_line: 52
    end_line: 63
    text: |2
        bit_score: 207.0
        global_score: 519.5
        query_length: 107
        target_length: 131
        alignment_columns: 131
        identities: 107
        mismatches: 0
        gap_columns: 24
        identity_percent: 81.6794
        query_coverage_percent: 100.0
        target_coverage_percent: 81.6794
        substitutions: []
comparison:
  provenance:
    query_accession: A6Q0K5
    run_at: '2026-10-18T23:33:03.057131+00:00'
    biopython_version: '1.85'
    mmseqs_version: 18-8cc5c
    command:
    - mmseqs
    - easy-search
    - genes/CHLRE/CP12/CP12-bioinformatics/reference-counterparts/query.fasta
    - .cache/orphan-curated/UP000006906.fasta
    - genes/CHLRE/CP12/CP12-bioinformatics/reference-counterparts/search.tsv
    - genes/CHLRE/CP12/CP12-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: 18840
    query_sha256: 264a89142e640e0fb64713881fa60cc0089dbeb943b56aaf5428671f96ef96c8
    targets_sha256: 3f9cb5324b0a7201c253b79f9e4e63a593691319ade81d6158597cd3efe93552
    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%3AUP000006906&format=fasta
      retrieved_at: '2026-10-18T23:32:17.496537+00:00'
      uniprot_release: '2026_03'
      sequence_count: 18840
      sha256: 3f9cb5324b0a7201c253b79f9e4e63a593691319ade81d6158597cd3efe93552
    detailed_alignment_limit: 10
  candidate_count: 1
  retained_alignment_count: 1
  candidates:
  - accession: A0A2K3DI03
    description: tr|A0A2K3DI03|A0A2K3DI03_CHLRE CP12 domain-containing protein OS=Chlamydomonas reinhardtii
      OX=3055 GN=CHLRE_08g380250v5 PE=4 SV=1
    evalue: 1.667e-62
    bit_score: 207.0
    global_score: 519.5
    query_length: 107
    target_length: 131
    alignment_columns: 131
    identities: 107
    mismatches: 0
    gap_columns: 24
    identity_percent: 81.6794
    query_coverage_percent: 100.0
    target_coverage_percent: 81.6794
