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/P06107.json
  retrieved_at: '2026-10-18T23:39:03.268506+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/proteomes/UP000306300.json
  retrieved_at: '2026-10-18T23:39:03.417780+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/P06107?format=txt&versions=36
  retrieved_at: '2026-10-18T23:39:05.417073+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/P06107?format=txt&versions=43
  retrieved_at: '2026-10-18T23:39:07.512210+00:00'
  uniprot_release: '2026_03'
- url: https://rest.uniprot.org/unisave/P06107?format=txt&versions=50
  retrieved_at: '2026-10-18T23:39:08.222263+00:00'
  uniprot_release: '2026_03'
observations:
  primary_accession: P06107
  alternative_accession: null
  sequence_identical: null
  primary_sequence_length: 161
  alternative_sequence_length: null
  shared_uniparc_id: null
  same_taxon: null
  reference_proteome: UP000306300
  proteome_is_reference: true
  proteome_taxon_matches: true
  primary_in_reference_proteome: false
  alternative_in_reference_proteome: null
  searched_reference_proteomes:
  - UP000306300
  primary_in_any_reference_proteome: false
  sampled_history_versions:
  - 36
  - 43
  - 50
  sampled_versions_with_proteome_links: []
current_records:
- primaryAccession: P06107
  entryType: UniProtKB reviewed (Swiss-Prot)
  entryAudit:
    firstPublicDate: '1988-01-01'
    lastAnnotationUpdateDate: '2026-09-02'
    lastSequenceUpdateDate: '1988-01-01'
    entryVersion: 53
    sequenceVersion: 1
  genes:
  - geneName:
      value: linA
  organism:
    scientificName: Staphylococcus haemolyticus
    taxonId: 1283
  sequence:
    length: 161
    sha256: c3c6e52721b064ea8e67ddd74428733f2a167c4aa7d1295d5297f31ad0ee427e
  uniProtKBCrossReferences: []
reference_proteomes:
- id: UP000306300
  proteomeType: Reference proteome
  taxonomy:
    scientificName: Staphylococcus haemolyticus
    taxonId: 1283
    mnemonic: STAHA
unisave_records:
- entry_version: 36
  url: https://rest.uniprot.org/unisave/P06107?format=txt&versions=36
  entry_date: 11-NOV-2015, entry version 36.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 43
  url: https://rest.uniprot.org/unisave/P06107?format=txt&versions=43
  entry_date: 02-DEC-2020, entry version 43.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
- entry_version: 50
  url: https://rest.uniprot.org/unisave/P06107?format=txt&versions=50
  entry_date: 24-JUL-2024, entry version 50.
  proteomes: []
  reference_proteome_keyword: false
  record_text: ''
archived_sources:
- path: genes/STAHA/lnuA/lnuA-record-evidence.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/STAHA/lnuA/lnuA-record-evidence.yaml
  sha256: baddff52167b3940112a6f8e00ff2c0d5f9e01363b4500f3e29a2f48e38c2623
  excerpts:
  - start_line: 31
    end_line: 35
    text: |2
        searched_reference_proteomes:
        - UP000306300
        primary_in_any_reference_proteome: false
        sampled_history_versions:
        - 36
  - start_line: 605
    end_line: 610
    text: |
      - entry_version: 36
        url: https://rest.uniprot.org/unisave/P06107?format=txt&versions=36
        entry_date: 11-NOV-2015, entry version 36.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 671
    end_line: 676
    text: |
      - entry_version: 43
        url: https://rest.uniprot.org/unisave/P06107?format=txt&versions=43
        entry_date: 02-DEC-2020, entry version 43.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
  - start_line: 761
    end_line: 766
    text: |
      - entry_version: 50
        url: https://rest.uniprot.org/unisave/P06107?format=txt&versions=50
        entry_date: 24-JUL-2024, entry version 50.
        proteomes: []
        reference_proteome_keyword: false
        record_text: |
- path: genes/STAHA/lnuA/lnuA-bioinformatics/reference-counterparts/comparison.yaml
  url: https://github.com/ai4curation/uniprot-orphan-analysis/blob/f6a331cb47f61256ad070bbaa75567094ef64e8a/genes/STAHA/lnuA/lnuA-bioinformatics/reference-counterparts/comparison.yaml
  sha256: 0adf8171820565eb08f9325cfbce15d58f3005a0cc003f49dac36c1e2bae877b
  excerpts:
  - start_line: 25
    end_line: 29
    text: |2
        - -v
        - '1'
        target_sequence_count: 2337
        query_sha256: c527a81825b7f188d79b53d6ad333539192faef4c64a3240eb49ce54c3e66bbe
        targets_sha256: 115325720169baa3cd21debe7a76736d2319825a782b0cf5fa0857e9b433c002
  - start_line: 44
    end_line: 47
    text: |2
          sha256: 115325720169baa3cd21debe7a76736d2319825a782b0cf5fa0857e9b433c002
        detailed_alignment_limit: 10
      candidate_count: 0
      candidates: []
comparison:
  provenance:
    query_accession: P06107
    run_at: '2026-10-18T23:34:24.791633+00:00'
    biopython_version: '1.85'
    mmseqs_version: 18-8cc5c
    command:
    - mmseqs
    - easy-search
    - genes/STAHA/lnuA/lnuA-bioinformatics/reference-counterparts/query.fasta
    - .cache/orphan-curated/UP000306300.fasta
    - genes/STAHA/lnuA/lnuA-bioinformatics/reference-counterparts/search.tsv
    - genes/STAHA/lnuA/lnuA-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: 2337
    query_sha256: c527a81825b7f188d79b53d6ad333539192faef4c64a3240eb49ce54c3e66bbe
    targets_sha256: 115325720169baa3cd21debe7a76736d2319825a782b0cf5fa0857e9b433c002
    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%3AUP000306300&format=fasta
      retrieved_at: '2026-10-18T23:32:31.523406+00:00'
      uniprot_release: '2026_03'
      sequence_count: 2337
      sha256: 115325720169baa3cd21debe7a76736d2319825a782b0cf5fa0857e9b433c002
    detailed_alignment_limit: 10
  candidate_count: 0
  retained_alignment_count: 0
  candidates: []